Hair drying and / or styling apparatus and methods

Abstract

In some examples, it is described apparatus for drying or styling hair, the apparatus comprising: a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface; and a controller configured to control the apparatus to determine whether a hair tress size is greater than a threshold value and, if it is, to cause the apparatus to: output a feedback message indicating that too much hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the hair styling device accordingly, and / or control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.

Description

[0001]HAIR DRYING AND / OR STYLING APPARATUS AND METHODSField of the InventionThe present invention relates to hair drying and / or styling apparatus and methods and to parts used therein. Suchstyling and / or drying of the hair may be performed by a user in respect of their own hair, for example, or by a hair stylist. The invention has particular, but not exclusive, relevance to a styling and / or drying device comprising one or more low thermal mass heaters. Background to the Invention Heated hair styling tools use heat to increase the temperature of hair to a desired styling temperature. For example, ahair straightener having a heated plate applies heat directly via conduction to heat the hair, which may be either wetor dry, to achieve the desired temperature for styling. The hair may be heated to a temperature that is particularlysuitable for styling hair (for example, to or beyond a hair glass transition phase temperature). At lower temperatures,the user may have to make many passes with the hair straightener over the hair to achieve a desired styling effect,whereas at higher temperatures, there is a risk of causing permanent damage to the hair.Similarly, a heated brush or hair dryer can also be used to style hair by heating air which in turn heats the hair to atemperature suitable for styling. The hair is typically styled from wet, for example after the user has washed their hair,although the hair could also be styled from dry. Existing hair styling appliances typically use heaters that provide a certain amount of thermal mass to the hair styling appliance.The amount of thermal energy provided to the hair styling appliance corresponds to one mode of operation that isparticularly suitable for a desired amount of hair and / or such that the hair of most users of the hair styling appliancemay be heated to a temperature that is particularly suitable for styling hair. However, there is a need for improvements to such existing hair styling appliances. There is a particular need for improvement of useability by the user, of such existing hair styling appliances. For example, users generally do not know the amount of hair they should be loading into the hair styling appliance. If the user loads too much hair, the hair will not be heated adequately, resulting in a frustrating styling experience.However, if the user does not load enough hair into the styler, they will have their hair damaged when styling. Thisissue might be exacerbated depending on the type of hair.For example, users with hair types which do not correspond to that of most users feel a more frustrating experienceand / or have their hair damaged when styling.The present invention aims to address or at least partially ameliorate one or more of the above problems.Summary of the Invention Aspects and embodiments of the invention are set out in the appended claims. These and other aspects of the invention, and aspects and embodiments which are useful in understanding the invention set out in the appended claims, are also described in the disclosure herein. Any feature in one aspect of the disclosure may be applied to other aspects of the disclosure, in any appropriate combination. In particular, method aspects may be applied to device and computer program aspects, and vice versa. Furthermore, features implemented in hardware may generally be implemented in software, and vice versa. Any reference to software and hardware features herein should be construed accordingly. Tress size calculator In one aspect, the invention provides apparatus for drying or styling hair, the apparatus comprising: a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface; and a controller configured to control the apparatus to: determine, based on a drop of a temperature of one or more heating zones of the plurality of independently controllable heating zones or based on an increase in a power output needed to maintain the one or more heating zones at a target temperature, whether hair is engaged with the one or more heating zones and, if it is, to determine an amount of hair which is engaged with the one or more heating zones; determine, based on the determined amount of hair engaged with the one or more heating zones across all of the one or more heating zones, a hair tress size which has been loaded by the user into the apparatus; determine whether the determined hair tress size is greater than a thresholdvalue and, if it is, to cause the apparatus to: output a feedback message indicating that too much hair has been loadedinto the apparatus, so as to prompt the user to modify the amount of hair loaded into the hair styling device accordingly, and / or control the temperature or the power output of the one or more heating zones of the plurality of controllableheating zones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.The threshold value may be a first threshold value. The controller may further be configured to determine whether the determined hair tress size is smaller than a second threshold value, smaller than the first threshold value and, if it is, to cause the apparatus to: output a feedback message indicating that too little hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the apparatus accordingly, and / or control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones whichare engaged with the hair, to avoid the hair loaded into the apparatus being burnt.The apparatus may comprise: a user interface for outputting a feedback message to the user. The controller may be configured to cause the user interface to output the feedback message indicating whether too much hair has been loaded into the apparatus. The user interface may comprise at least one of a sound generator, lighting means and / or a haptic feedback generator. The lighting means may comprise one or more lamps arranged along a length the apparatus, sideways of the heater, the controller being configured to control the apparatus to light up one or more lights of the lighting means on a length corresponding to the extent of the one or more heating zones which are engaged with the hair, in a length of the heater. The controller may be configured to control the apparatus to cause the lighting means to produce a first colour, such as green, when it is determined that the hair tress size corresponds to a desiredamount of hair, and at least one second colour different from the first colour, otherwise, thus prompting the user tomodify the amount of hair loaded in the apparatus. The controller may be configured to control the apparatus to causethe lighting means to produce a second colour, such as blue, to prompt the user to increase the amount of hair loadedin the apparatus, and a third colour, such as red, to prompt the user to decrease the amount of hair loaded in theapparatus. The controller may be configured to control the apparatus to: cause the sound generator to produce a first sound, whenit is determined that the hair tress size corresponds to a desired amount of hair, and to produce at least one secondsound different from the first sound, otherwise, thus prompting the user to increase or decrease the amount of hair loaded in the apparatus, and / or cause the haptic feedback generator to produce a first haptic feedback, when it isdetermined that the hair tress size corresponds to a desired amount of hair, and to produce at least one second hapticfeedback different from the first haptic feedback, otherwise, thus prompting the user to increase or decrease the amountof hair loaded in the apparatus. For example, the controller may be configured to control the apparatus to: cause thesound generator to produce a second sound and / or the haptic feedback generator to produce a second hapticfeedback, to prompt the user to increase the amount of hair loaded in the apparatus, and / or cause the sound generatorto produce a third sound and / or the haptic feedback generator to produce a third haptic feedback, to prompt the userto decrease the amount of hair loaded in the apparatus. The apparatus may further comprise communication circuitry such that the apparatus is configured to output the feedback message to an external processing device and wherein the output feedback message is output on a user interface associated with the user. The external processing device may be part of a mobile phone or smart watch or tablet or other such device and may be configured to run an application, remote from the apparatus. If it is determined that the determined hair tress size is greater than the threshold value and thus is bigger than a desired amount of hair, the controller may be configured to cap the increase in the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, so as to enable a better drying or styling of the hair which is loaded in the apparatus while avoiding burning of the hair. If it is determined that the determined hair tress size is smaller than the second threshold value and thus is smallerthan a desired amount of hair, the controller may be configured to turn off the heater or to reduce the temperature orthe power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to prevent the hair being burnt. The one or more heating zones may be adjacent to each other along a length and / or across a width of the heater. The one or more heating zones may be substantially thermally isolated from each other. The controller may be configured to control the apparatus to: determine the resistance of a heater electrode of the one or more heating zones based on a voltage supplied to the heater electrode and the current passing through the heater electrode; and determine the temperature of the one or more heating zones based on the determined resistance. The controller may be configured to control the apparatus to supply power to a heater electrode of the heater to determine the resistance of the heater electrode even in a case where it is determined that the corresponding heating zone is not engaged with hair. The apparatus may further comprise a pair of opposing heating zones, heat being allowed to flow between the opposing heating zones when the apparatus is in use. The controller may be configured to control the apparatus to: determine whether hair is engaged with at least one of the pair of opposing heating zones based on a sum or average of a powerneeded to maintain each of the pair of opposing heating zones at a target temperature.The controller may be configured to control power supplied to a heater electrode of the one or more heating zones to control the temperature of the one or more heating zones towards a first target temperature in a case where it is determined that the hair is engaged with the one or more heating zones, and to control the temperature of the one or more heating zones towards a second target temperature, lower than the first target temperature, in a case where it is determined that the hair is not engaged with the one or more heating zones; and intermittently supply power to theheater electrode to determine the resistance of the heater electrode even in the case where it is determined that theone or more heating zones is not engaged with the hair, and determine the temperature of the one or more heating zones based on the resistance. The apparatus may further comprise a pressure sensor configured to sense and output data indicative of a pressure between a first movable arm and a second movable arm of the apparatus, to enable the controller to verify the determination of the hair tress size, as larger hair tresses require more pressure to stay in place in the apparatus. The controller may be configured to receive data indicative of the hair type of the user, to enable the controller to refine the determination of the hair tress size, as thick curly hair has larger hair tress sizes than fine straight hair.The apparatus may be a hair straightener, a hair dryer, a hot paddle brush, a hot round brush, a heated roller, or a haircurler. In another aspect, the invention provides a method performed by apparatus for drying or styling hair, the apparatus comprising a heater having a hair contacting surface for heating hair that contacts the hair contacting surface by conduction, and the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface, wherein the method comprises: decreasing a temperature or increasing a power output of one or more heating zones of the plurality of independently controllable heating zones; determining, based on the drop of a temperature of one or more heating zones of the plurality of independently controllable heating zones or based on the increase in a power output needed to maintain the one or more heating zones at a target temperature, whether hair is engaged with the one or more heating zones and, if it is, to determine an amount of hair which is engaged with the one or more heating zones; determining whether the determined hair tress size is greater than a threshold value and, if it is, the method further comprising: outputting a feedback message indicating that too much hair has been loaded into the apparatus, so as to prompt the user to modifythe amount of hair loaded into the hair styling device accordingly, and / or controlling the temperature or the poweroutput of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair,to avoid the hair loaded into the apparatus being burnt.The threshold value may be a first threshold value. The method may further comprise determining whether the determined hair tress size is smaller than a second threshold value, smaller than the first threshold value and, if it is, the method may further comprise: outputting a feedback message indicating that too little hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the apparatus accordingly, and / or controlling the temperature or the power output of the one or more heating zones of the plurality of controllable heatingzones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.The apparatus may comprise a user interface for outputting a feedback message to the user, the user interface comprising at least one of a sound generator, lighting means and / or a haptic feedback generator. The method may further comprise: producing a first feedback, when it is determined that the hair tress size corresponds to a desiredamount of hair, and producing at least one second feedback, different from the first feedback, otherwise, thus promptingthe user to modify the amount of hair loaded in the apparatus. For example, the user interface may be configured tooutput a second feedback, to prompt the user to increase the amount of hair loaded in the apparatus, and / or to outputa third feedback, to prompt the user to decrease the amount of hair loaded in the apparatus.If it is determined that the determined hair tress size is greater than the threshold value and thus is bigger than a desired amount of hair, the method may further comprise: capping the increase in the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, so as to enable a better drying or styling of the hair which is loaded in the apparatus while avoiding burning of the hair. If it is determined that the determined hair tress size is smaller than the second threshold value and thus is smallerthan a desired amount of hair, the method may further comprise: turning off the heater or reducing the temperature orthe power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to prevent the hair being burnt. Hair type predictor In one aspect the invention provides apparatus for drying or styling hair, the apparatus comprising: a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface; a memory that stores a trained classifier configured to classify the hair of the user of the apparatus into a class among a plurality of reference hair classes; and a controller coupled to the memory and configured to control the apparatus to: determine a power demand of the apparatus, based on a temperature of the plurality of independently controllable heating zones or based on the power output needed to maintain each heating zone of the plurality of heating zones at a target temperature; determine a hair tress size whichhas been loaded by the user into the apparatus, by determining, based on a drop of the temperature of one or moreheating zones of the plurality of independently controllable heating zones or based on an increase in the power output needed to maintain the one or more heating zones at the target temperature, whether hair is engaged with the one or more heating zones, and, if it is, by determining an amount of hair which is engaged with the one or more heating zones, the hair tress size being determined based on the amount of hair engaged with the one or more heating zonesacross all of the one or more heating zones; use the stored trained classifier to determine the type of hair of the userby classifying the hair into a reference hair class, based on the determined power demand and the determined hair tress size; and cause the apparatus to control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined hair type. The apparatus may further comprise communication circuitry such that the apparatus is configured to receive user input information from an external processing device. The user input information may be input on a user interface associated with the user and configured to enable the user to input the input information. The external processingdevice may be part of a mobile phone or a smart watch or tablet or other such device and may be configured to run anapplication, remote from the apparatus. The controller may be further configured to control the apparatus to use the stored trained classifier such that the plurality of reference hair classes into which the hair of the user is to be classified is narrowed down to a subset of the plurality of reference hair classes, based on the received user input information. The user input information may comprise at least one of: an indication by the user of the hair type they believe they have; a result from the useranswering a questionnaire about their hair and / or the environment. In some examples, the memory may be configuredto store the user input information, so that the user does not have to input the information every time they use thestyler. In some examples, the stored input information may be updated if, e.g., the user has a haircut, or gets their hairdyed. The controller may be configured to: determine a grip pressure based on data associated with a pressure sensor configured to measure a pressure between movable arms of the apparatus; and cause the apparatus to use the stored trained classifier to determine the type of hair of the user, further based on the grip pressure. The controller may be configured to: determine a motion of the apparatus when the user is styling or drying their hair, based on data associated with one or more motion sensors of the apparatus; and cause the apparatus to use the stored trained classifier to determine the type of hair of the user, further based on the motion of the apparatus. The one or more motion sensors of the apparatus may comprise any one or more of an accelerometer, a gyrometer, amagnetometer, an inclination sensor. The motion of the hair styling or drying appliance may comprises: a rotation ofthe apparatus when styling or drying the hair; and / or a speed of movement of the apparatus when styling or drying the hair. The controller may be configured to: process further sensor data to determine diagnostic information about the hair being styled or dried; and cause the apparatus to use the stored trained classifier to determine the type of hair of theuser, further based on the determined diagnostic information. The diagnostic information may comprise at least oneof: a level of moisture in the hair, a humidity ambient to the hair being styled or dried, a temperature ambient to the hairbeing styled or dried, a geographic location of the hair being styled or dried.The controller may be configured to control the temperature or the power output of the one or more heating zones by capping the increase in the temperature or the power output of the one or more heating zones of the plurality ofcontrollable heating zones based on the determined type of hair, to avoid the hair being burnt.The plurality of reference hair classes may comprise nine reference classes, referred to as (1a, 1b, 1c, 2a, 2b, 2c, 3a, 3b, 3c), the class 1a corresponding to fine, straight blonde hair and the class 3c corresponding to thick, curly dark hair. The controller may be configured to set the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined type of hair with reference to the nine reference classes. The controller may be configured set the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones so as to enable a better drying or styling of the hair which is loaded in the apparatus. The trained classifier may comprise a machine learning algorithm comprising a convolutional neural network.The apparatus may be a hair straightener, a hair dryer, a hot paddle brush, a hot round brush, a heated roller, or a haircurler. In another aspect the invention provides a method for generating a classifier configured to classify hair of a user of apparatus for drying or styling hair, into a class among a plurality of reference hair classes, the method comprising: obtaining a plurality of annotated training streams of data; and training the classifier by applying a machine learning algorithm to the obtained training streams of data. The annotation indicates the class of hair associated with each training stream of data, and the plurality of annotated training streams of data comprises, for each class of hair among the plurality of reference hair classes: a training stream of data corresponding to a power demand of the apparatus when styling or drying hair belonging to the class of hair; and a training stream of data corresponding to a hair tress size which is typically loaded in the apparatus when styling or drying hair belonging to the class of hair. The classifier may be trained to minimize a classification loss between the annotated class of hair associated with each training stream of data and a classification of the hair determined by the classifier. The classification loss may comprise a similarity metric of Lp-norm, p being an integer greater or equal to 1, such as an average absolute deviation or a least mean square distance. The plurality of training streams of data may comprise, for each class of hair among the plurality of reference hair classes: a training stream of data corresponding to sensor data indicative of a grip pressure between movable arms of the apparatus when styling or drying hair belonging to the class of hair; and / or one or more training streams of data corresponding to sensor data indicative of a motion of the apparatus when the user is styling or drying hair belonging to the class of hair. The motion of the hair styling or drying appliance may comprise: a rotation of the apparatus whenstyling or drying the hair; and / or a speed of movement of the apparatus when styling or drying the hair; and / or a trainingstream of data corresponding to sensor data indicative of diagnostic information about the hair being styled or dried. The classifier may be trained to classify the hair of the user into a subset of the plurality of reference hair classes, based on user input information. The user input information may comprise at least one of: an indication of a suspected use’s hair type; a result from a questionnaire about their hair and / or the environment. The machine learning algorithm may comprise a convolutional neural network. In another aspect the invention provides a method of producing apparatus for drying or styling hair, wherein the apparatus comprises a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface, a memory and acontroller coupled to the memory, the method comprising: obtaining a classifier; and storing the obtained classifier inthe memory of the appliance. The controller is configured to control the apparatus to: use the stored trained classifier to determine the type of hair of the user by classifying the hair into a reference hair class; and cause the apparatus to control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined hair type.The storing may comprise transmitting the generated classifier to the apparatus via a network, the apparatus receivingand storing the classifier. The classifier may be generated, stored and / or transmitted in the form of one or more of: a data representation of the classifier; executable code for applying the classifier. In another aspect, the invention provides a corresponding computer program product comprising computer implementable instructions. Brief Description of the Drawings Embodiments of the invention will now be described, by way of example only, and with reference to the drawings in which:Figure 1a shows an overview of an exemplary hair styling device;Figure 1b shows a hair styling device in use;Figure 2 is a block diagram illustrating the main electronic components of the hair styling device shown in Figure 1; Figure 3a is an exploded view of a heater forming part of the hair styling device shown in Figure 1; Figure 3b is an assembled partially transparent view of the heater shown in Figure 3a;Figure 4a schematically illustrates the heating zones on the heating surface of the heater shown in Figure 3;Figure 4b schematically illustrates an alternative arrangement of heating zones; Figure 5 schematically illustrates a further alternative arrangement of heating zones that are of different sizes and shapes; Figure 6a illustrates the way in which the heating zones may be formed on a tubular substrate for use in a curling tong or the like; Figure 6b illustrates the way in which the heating zones may be arranged on a curved substrate which may be used on a heated brush; Figure 7 illustrates a tress of hair that partly overlaps with zones Z2 and Z4 of a heater; Figure 8 shows a flow chart illustrating an example method for operating an appliance according to the disclosure;Figures 9A and 9B show an interface of the appliance comprising lighting means, the lighting means comprising oneor more lamps arranged along a length the appliance, sideways of a heater;Figure 10 shows a flow chart illustrating an example method for operating an appliance according to the disclosure;Figure 11 is another block diagram illustrating the main electronic components of the hair styling device shown in Figure 1; Figure 12 shows a flow chart illustrating an example method for generating a classifier according to the disclosure; Figure 13 shows an example architecture of a classifier according to the disclosure; Figure 14 shows another example architecture of a classifier according to the disclosure; Figure 15 shows a flow chart illustrating an example method for producing a hair styling appliance according to the disclosure; and Figure 16 shows a flow chart illustrating an example method for operating a hair styling appliance according to the disclosure; Figure 17 shows a flow chart illustrating an example method for operating an appliance according to the disclosure, for treating hair according to a desired treatment; Figure 18 shows a flow chart illustrating an example method for operating an appliance according to the disclosure, for generating a reference treatment; Figure 19 shows a flow chart illustrating an example method for performing some steps of the method of Figure 18; Figures 20a, 20b, 20c, 20d and 20e show examples of one or more sequences obtained after a processing of raw data from an appliance according to the disclosure; Figure 21 shows an overview of an exemplary hair styling device; Figure 22 is a block diagram illustrating the main electronic components of the hair styling device shown in Figure 21; Figure 23a is an exploded view of a thermal somatosensory feedback generator forming part of the hair styling device shown in Figure 21; Figure 23b is an assembled partially transparent view of the thermal somatosensory feedback generator shown in Figure 23a; Figure 24 schematically illustrates a first example of heating zones on the handle of a styler; Figure 25 schematically illustrates a second example of heating zones on the handle of a styler; and Figure 26 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure; Figure 27 is another block diagram illustrating the main electronic components of the hair styling device shown in Figure 1; Figure 28 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure; Figure 29 shows a flow chart illustrating an example method of generating a trained machine learning algorithm, according to the disclosure; Figure 30 shows an example architecture of a frustration calculator according to the disclosure; and Figure 31 shows a flow chart illustrating an example method for producing a hair styling appliance according to the disclosure; Figure 32 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure; and Figure 33 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure; Figure 34 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure; Figure 35 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure; Figure 36a shows an example of a reading, by the microcontroller, of the translation acceleration along one spatialdimension (such as the x-, y- or z-axis), as a function of time;Figure 36b shows an example of a transformation performed by the microcontroller using a Fourier Transform; Figure 37a shows an example of a reading, by the microcontroller, of the translation acceleration along three spatialdimensions (such as the x-, y- and z-axes), as a function of time;Figure 37b shows an example of a transformation performed by the microcontroller using a variance; Figure 38 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure. Figure 39 shows an overview of an exemplary hair styling device; Figure 40 is a block diagram illustrating the main electronic components of the hair styling device shown in Figure 39; Figure 41 shows a flow chart illustrating an example method of operation of the apparatus, according to the disclosure; and Figure 42 is another block diagram illustrating the main electronic components of the hair styling device shown in Figure 1a; Figure 43 illustrates a cross-sectional view of a further example of a low thermal mass heater that has curved edges and a supporting substrate onto which the heater is attached with an adhesive or via a diffusion bonding process (e.g. by melting them together); Figure 44 is a partially exploded cross-sectional and perspective view of the different layers that form the heater shown in Figure 43; Figure 45 is a plan view illustrating the form of a heat spreading layer forming part of the heater illustrated in Figure 43; Figure 46 illustrates a main heating element layer forming part of the heater shown in Figure 43; and Figure 47 is a simplified block diagram illustrating the way in which the heater electrodes of the heater shown in Figure 43 are used to heat the heater and to sense the temperature of the heating zones;Figure 48 shows another overview of an exemplary hair styling device;Figure 49 is a block diagram illustrating the main electronic components of the hair styling device shown in Figure 48;Figure 50 illustrates a control sequence for the hair styling device; andFigure 51 is a graph illustrating a control sequence based on the method of Figure 50.Overview of Hair Styling DeviceFigure 1a illustrates a hand-held (portable) hair styler 1 (or hair styling appliance or apparatus in the present disclosure).The hair styler 1 includes a handle 10 that the user holds during use. The hair styler 1 includes a first movable arm 4a and a second movable arm 4b, which are coupled at proximal ends thereof to a shoulder 2. In Figure 1a, the first arm 4a bears a first heater 6a at its distal end, and the second arm 4b bears a second heater 6b at its distal end. The first and second heaters 6a, 6b oppose one another and are brought together as the first and second arms 4a, 4b are moved from an open configuration to a closed configuration. As shown in Figure 1b, during use, a tress of hair 40 issandwiched between the two arms 4 so that the user’s hair is in contact with, and therefore heated by, outer heatingsurfaces of the heaters 6a, 6b. Therefore, as the user pulls the hair styler 1 along the tress of hair 40, the tress of hair40 is heated by conductive heating to a suitable temperature to facilitate styling.A user interface 11 is provided to allow the user to input information about them to the device and / or for the device tooutput information to the user. The user interface 11 may have a dial, button or touch display for allowing the user to input information to the device 1.The user interface 11 may have an indicator light, and / or a display, and / or a sound generator comprising a loudspeaker,and / or haptic feedback generator for outputting information to the user. The sound generator may be configured for providing a polyphonic sound. The sound generator may provide a particular sound brand or jingle when switching onand / or off. The sound generator may provide a sound to indicate particular events, such as reaching a desired operatingtemperature and / or sleep mode. The indicator light may provide a pleasing aesthetic appearance as well as indicate temperature or other events. The indicator light may comprise an electroluminescent backlight as it enables wide angle, wide area viewing. Alternatively or additionally, the indicator light may comprise an LED lighting with a suitable light- pipe and / or optical diffuser. In this embodiment, the user interface 11 also comprises a control button or switch 14 to enable the user to turn the device 1 on or off; and an indicator light 15 to show whether the power is on. A printed circuit board assembly (not shown) may be provided at any suitable location within the housing of the device 1 and carries the control circuitry for controlling the operation of the device 1 and for controlling the interaction with the user via the user interface 11. In this example, electrical power is provided to the device 1 by means of a power supply located at an end of the device, via a power supply cord 3. The power supply may be an AC mains power supply. However, in an alternative embodiment the power supply may comprise one or more DC batteries or cells (which maybe rechargeable, e.g., from the mains or a DC supply via a charging lead), thereby enabling the device 1 to be acordless product. In use, the device 1 is turned on, energising the heaters 6 to cause them to heat up. The user then opens the first and second arms 4a, 4b and, normally starting from the roots of the hair (i.e. near the scalp), a length or tress of hair 40 (which may be clumped) is introduced between the arms 4a, 4b, transversely across the heaters 6a, 6b. The user then closes the arms 4a, 4b so that the length of hair 40 is held between the first and second arms 4a, 4b and then the user pulls the hair through the closed arms (as illustrated in Figure 1b). The outer (hair contacting) surface of the heaters 6 is flat in this embodiment and so the hair styler 1 can be used to straighten the user’s hair. The hair styling device 1shown in Figure 1 can also be used to curl the hair by turning the device 1 through approximately 180 degrees or moreafter clamping the hair between the arms 4a, 4b and before moving the device 1 along the tress of hair 40. Hair has a relatively high thermal mass and when in contact with the heating surface of the heater 6 the hair absorbs a significant amount of the heat energy. The heaters 6 must quickly supply the lost heat energy back to the heating surface otherwise the temperature of the heating surface will drop and potentially impact on the quality of the thermal styling.If the temperature of the heaters 6 falls below that required to raise the hair temperature above the glass transitiontemperature of the hair, the hair will not retain the styled shape. However, if the hair is heated to a temperature that is too high, the hair can undergo significant damage.Furthermore, different hair types require different amounts of heat energy for hair styling (because of differentthickness, quality, condition, thermal mass of hair). Typically, fine straight hair requires less heat than thick curly hairfor styling. Depending on the type of hair, the glass transition temperature of the hair when dry may be a temperaturein the range of approximately 40°C-200°C. When the hair is moist or damp, the glass transition temperature may bein the range of 0°C to 150°C. As such, the device 1 must be able to control the temperature so that the heating surface of the heaters 6 remains within a particular temperature range. Furthermore, it must maintain the temperature range both when hair is frequently and quickly loaded and unloaded onto the heating surface, and when hair is held on the heating surface for a prolonged period of time. Control CircuitryFigure 2 is a simplified block diagram of control circuitry 15 that controls the operation of the hair styler device 1 shownin Figure 1. As shown, the control circuitry 15 comprises a power supply 21 that, in this embodiment, derives power from a battery power source. A mains power supply input may be provided to charge the battery via an AC to DC converter (not shown), which may be external or internal to the device 1. Alternatively, the power supply 21 may derivepower from an AC mains supply input.In this example, power is provided to the heaters 6 for heating the user’s hair. The power supplied to the heaters 6 iscontrolled by a controller 28 having a microprocessor 29. The power supplied to the heaters 6 is controlled by drivecircuitry 23 (which may include one or more power semiconductor switching devices (triacs)) which controls theapplication of an AC mains voltage, or a DC voltage derived from the AC mains or from a battery, to the heaters 6 inaccordance with instructions from the microprocessor 29.The microprocessor 29 is coupled to a memory 30 (which is typically a non-volatile memory) that stores processorcontrol code for implementing one or more control methods that control the heating of the heaters 6 in accordance with a desired operating temperature of the heaters 6 and sensed temperatures of the heaters obtained from temperature measurement circuitry 25. The microprocessor 29 allows for complex control of the heaters 6. For example, the controller 28 may be configured to adjust the power delivered to heaters by using an on / off triac based upon the output of the temperature measurement circuitry 25.The memory 30 may store a number of transfer functions such as:simple on-off control means or bang-bang control means; proportional-integral-derivative (PID) control means; a set of deterministic rules; data for an artificial intelligence algorithm; fuzzy logic; feed back control means; feed forward control means.The controller 28 comprises means to measure the input voltage or alternatively to detect the speed at which theheaters 6 heat up, so as to detect the type of input voltage. A high input voltage would lead to a faster heat up of theheaters 6 and hence a control loop can react appropriately. The input voltage and / or speed of heat up can also beused to detect a failure. The controller 28 may comprise means to detect the use of the hair styling appliance and control the power supply to the heaters accordingly. This feature helps to reduce power consumption and improve safety. For example, the controller 28 may comprise means to reduce the temperature of the heaters when they are not active and then rapidly heat them up when they are about to be used. The controller 28 may allow a heater to power down to a standby temperature if a user momentarily places the hair styling appliance on a table. The controller 28 may then power up the heater to an operating temperature when the hair styling appliance is picked up to be used. If the controller 28 detects that the hair styling appliance has not been used for a longer period of time, then the control means may shut down the hair styling appliance. This enables the hair styling appliance to meet the mandatory requirement of the safety standard that the appliance must turn off after 30 minutes whether it is being used or not. Detection of use may be achieved by detecting the opening and closing of the first movable arm and a second movablearm of the hair styling appliance, or through the use of one or more motion detection devices to detect the motion ofthe hair styling appliance or the use of a capacitive touch system. The one or more motion detection devices are shown in Figure 2 and referred to with numerical reference 31. The one or more motion detection devices 31 may comprise any one of an accelerometer, a gyrometer, a magnetometer, an inclination sensor. The controller is configured to determine amplitudes of movements of the apparatus, includingangles, inclinations and rotations, based on sensor data from the motion detection devices 31. In an example, the oneor more motion sensors 31 comprise an accelerometer and a gyrometer. In such an example, the controller 28 is configured to process the data from the accelerometer and the gyrometer to determine absolute movements of the styler in space, by taking into account the orientation of the styler. In such an example, if the styler is upside down, the controller 28 is configured to interpret a left swipe of the styler as a movement to the left instead of a right movement as shown by the accelerometer data in isolation.The hair styler 1 includes a pressure or grip sensor 32 to measure a pressure between the first movable arm 4a andthe second movable arm 4b, e.g., when styling the hair. The pressure sensor 32 may be configured to sense andoutput sensor data indicative of whether moveable arms 4a and 4b of the appliance are: in a closed position, in which the arms are adjacent each other, or in an open position, in which the arms are spaced apart. In an example, the pressure or grip sensor 32 comprises a magnetometer coupled to a magnet, such as a part of a loudspeaker of the sound generator already described. In such an example, the controller 28 is configured to process the grip sensor data to detect a peak in a magnetic field amplitude when the movable arms 4a and 4b are moved from the open configuration to the closed configuration. The temperature measurement circuitry 25 may be temperature sensors such as thermistors or they may use circuitry that senses the resistance of heater electrodes that are used to heat the heaters 6, which resistance depends on the temperature of the heater electrode.Figure 2 also shows that the user interface 11 is coupled to the microprocessor 29, for example to provide one or moreuser controls, input and / or output indications such as a visual indication or an audible alert.Finally, the control circuitry includes communications circuitry 27 to allow the device to communicate with a remotesensor, a remote server, or a remote application (e.g., on a mobile telephone or a smart watch or tablet or other suchdevice). The communications circuitry 27 may use, for example, Bluetooth, Wi-Fi and / or 3GPP communicationprotocols to communicate with the remote device.As already stated, the user interface 11 comprises feedback means for providing feedback to the user of the styler.The operation of the feedback means will be described in greater detail below. HeatersThe heaters 6a, 6b are low thermal mass heaters and can therefore heat up and cool down quickly. Figures 3a and 3bshow an exemplary embodiment of such heaters 6a, 6b, which comprise a stack of thin layers. Referring in particular to Figure 3a, the heaters 6a, 6b include an upper dielectric (electrically insulating) layer 62, an electrode layer 63 that has a plurality of separate heater electrodes 64, and a lower dielectric layer 66 which electrically insulates the heater electrodes 64 from other components mounted behind the heater 6a, 6b. The three layers 62, 63 and 66 are bonded together either through an adhesive layer (pressure set or thermoset) or through diffusion bonding of the contacting materials (e.g. melting them together) and define a heater 6 that is very thin (the three layers have an overall thicknessof between 30µm to 1000µm in the case of Safe Extra Low Voltage (SELV) operation (less than 42.4 Volts) and 0.8mmto 2.0mm in the case of AC operation) and with very low thermal mass. The upper surface of the layer 62 provides thehair contacting surface of the heater 6, although a non-stick coating may be applied to the upper surface of the layer62 to facilitate the passage of the user’s hair over the heating surface. The bonded layers 62, 63 and 66 define aflexible heater 6 and rigidity of the heater is provided in the illustrated embodiment by mounting the heater layers 62, 63 and 66 into a rigid support 68 which forms a base. These layers may be mounted onto the rigid support after thelayers themselves have been bonded together or they may be bonded one at a time (or multiple at a time) onto therigid support 68. If a flexible heater is desired, then there is no need for the rigid support 68 or if a support is used, thismay be a non-rigid support. Thus, in this embodiment, there is no heater plate or tube that is heated by the heaters 6, and instead, the heaters 6 directly heat the user’s hair. This provides a hair styler 1 having a very low thermal mass which can therefore heat up and cool down much more quickly than prior art stylers. In the illustrated embodiment, there are ten heater electrodes 64 that each snake across and back across the width of the heater 6, folding twice such that they each cross the width three times. The ends of each of the heater electrodes64 are electrically connected through the lower dielectric layer 66 to electrical connections within the rigid support 68,which connect to an electrical connector 70. Drive circuitry 23 that is mounted within one of the arms 4 connects to theheater electrodes 64 via the electrical connector 70 and applies electrical power to the individual heater electrodes 64to control the heat generated by each heater electrode 64. The electrical connector 70 extends from a surface of therigid support 68 facing away from the surface layer 62 (shown in Figures 3a and 3b as extending directly away fromthe upper layer 62, but it could also be provided as extending in a perpendicular direction).Each of the heater electrodes 64 thus creates an individual heating zone 642 on the hair contacting surface of theheater 6, which spans the width (which we shall refer to as the x-direction) of the heater 6 and the heater electrodes 64 are arranged sequentially one after the other along the length (the y-direction) of the heater 6.Figures 4a and 4b show schematic views of different arrangements of such heating zones 642. Figure 4a shows anarrangement corresponding to that of Figures 3a and 3b, in which the heating zones 642-1 to 642-10 are arrangedalong the y-direction only. Figure 4b shows an alternative arrangement, in which heating zones 642-1 to 642-16 arearranged in both the x- and y-directions. Such an arrangement of heating zones 642 can be provided by arranging twosets of heater electrodes 64 like those shown in Figure 3a side by side in the width, x-direction. The heaters 6 may beseparated in this way into any number of heating zones 642 and may comprise any number of heating zones alongthe x- and y-directions. In particular, whilst Figure 4b shows two zones along the x-direction, a greater number of zonesin the x-direction could also be provided. The heating zones 642 of the heaters 6a, 6b can be operated (heated) independently, which can help to reduce hot / cold spots when using very low thermal mass heaters 6 such as those shown in Figure 3. The heating zones illustrated in Figure 4 are all the same size. Of course, different sized heating zones 642 may beprovided, as illustrated in Figure 5, which shows a heater 6 having seven different sized heating zones (labelled Z1 toZ7). The way in which the heater electrodes 64 would be arranged to define these different sized zones would be understood by the skilled reader and will not be described in detail here.The heating zones 642 described above form part of a heater having a flat hair contacting surface. The heater is notlimited to flat hair contacting surfaces and can be configured for use a tubular form (as illustrated in Figure 6a) for example for use in a hair curler device or in a curved form (as illustrated in Figure 6b) for example for use in a heated hair brush. The heater surface may have a corrugated or ribbed shape to provide a hair crimping device.The temperature of each heating zone 642 is independently controllable. Each heating zone 642 can be set to a targettemperature. The target temperature of each heating zone 642 may be different. A separate temperature sensor may be provided for sensing the temperature of each heating zone 642 which is fed back to the microprocessor 29 to allow the microprocessor 29 to control the delivery of power to the heater electrode64 of the corresponding heating zone 642.Alternatively, if the heater electrodes 64 are formed of a material having a Positive Temperature Coefficient (PTC) or a Negative Temperature Coefficient (NTC) (such that its resistance varies with its temperature), then the temperatureof each heating zone 642 can be determined by determining the resistance of the corresponding heater electrode 64.Tress Size CalculatorWhen hair is present on the hair contacting surface, the temperature of the hair contacting surface drops more rapidlythan when hair is not present. Therefore, when the hair styling appliance is unpowered, presence of hair can bedetected by measuring a rate of change of temperature gradient of the hair contacting surface. Alternatively oradditionally, and as discussed in more detail below, hair presence can be detected by zonal power loading. The microprocessor 28 controls the heating in order to reduce the difference between the actual temperature of theheating zone 642 and the target temperature for that heating zone 642.The controller may be configured to determine the resistance of a heater electrode of the one or more heating zones based on a voltage supplied to the heater electrode and the current passing through the heater electrode; and determine the temperature of the one or more heating zones based on the determined resistance. The controller may be configured to control the supply of power to a heater electrode of the heater to determine the resistance of the heater electrode even in a case where it is determined that the corresponding heating zone is not engaged with hair. When there is a pair of opposing heating zones, heat can flow between the opposing heating zones when the apparatus is in use, and the controller may be configured to determine whether hair is engaged with at least one of the pair ofopposing heating zones based on a sum or average of a power needed to maintain each of the pair of opposing heatingzones at a target temperature. In some examples, the controller may be configured to control power supplied to a heater electrode of the one or more heating zones to control the temperature of the one or more heating zones towards a first target temperature in a case where it is determined that the hair is engaged with the one or more heating zones, and to control the temperature of the one or more heating zones towards a second target temperature, lower than the first target temperature, in a case where it is determined that the hair is not engaged with the one or more heating zones; and intermittently supply power to the heater electrode to determine the resistance of the heater electrode even in the case where it is determined that the one or more heating zones is not engaged with the hair, and determine the temperature of the one or more heating zones based on the resistance. Heating Zone Sizing When the user loads a tress of hair 40 onto the heaters 6, some parts of the heater will be loaded with hair whilst other parts will not be loaded with hair.Upon loading with hair, and using the already described temperature measurement circuitry 25, more power is suppliedto the heater 6 to ensure that all regions on the hair contacting surface can be retained within and / or recovered backto the desired operating temperature limits. Figure 7 shows a tress of hair 40 overlying heating zones Z2, Z3 and Z4, with heating zone Z3 being fully loaded with hair whilst heating zones Z2 and Z4 being only partially loaded with hair.Tress Size Calculator - Operation based on different input streams of dataTress Load The microprocessor 28 can detect when the heaters have detected the presence of hair, by using a measure of a rate of change of temperature gradient of the hair contacting surface and / or a measure of the zonal power loading. In other words, based on the temperature loss of the heaters and on how many heating zones are activated for heating, the microprocessor 28 can calculate how much hair was loaded into it. The Figure 7 extent of the heating zones gives the microcontroller 28 an indication of the size of the tress of hair 40 introduced between the arms of the styling appliance. In the present disclosure, the size of the tress of hair can refer to a volume of hair, a number of hair fibres, a surface area of hair, or any combinations of the previous, such as a hair density. The size of the tress of hair 40 gives an indication of the amount of hair introduced between the arms of the styling appliance.Additionally or alternatively, the styler may comprise sensing means to determine the amount of hair introduced in thestyling apparatus. The sensing means may include capacitive sensing means to detect the amount of hair between the heaters. Figure 8 shows a flow chart illustrating an example method 100 for operating an appliance according to the disclosure. In the method 100 of Figure 8, the microcontroller 28 determines, at S1, based on a drop of a temperature of one or more heating zones of the plurality of independently controllable heating zones or based on an increase in a poweroutput needed to maintain the one or more heating zones at a target temperature, whether hair is engaged with theone or more heating zones. If it is determined that hair is present, the method 100 moves to S2 where themicrocontroller 28 determines an amount of hair which is engaged with the one or more heating zones. The determinedamount of hair in contact with each heating zone is based on the amplitude of the drop of temperature or the amplitudeof the increase in power output. The method 100 moves to S3, where the microcontroller 28 determines, based on the determined amount of hair engaged with the one or more heating zones across all of the one or more heating zones, a hair tress size which has been loaded by the user into the apparatus. The method 100 moves to S4, where the microcontroller 28 determineswhether the determined hair tress size is greater than a threshold value. If it is determined that the determined hairtress size is greater than a threshold value, this means that too much hair has been loaded in the styler, and the methodmoves to S5. In S5, the microcontroller 28 causes the appliance to output a feedback message indicating that toomuch hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into thehair styling device accordingly. Alternatively or additionally, in S5, the microcontroller 28 causes the styler to control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair,to avoid the hair loaded into the apparatus being burnt. Therefore, in an example, when it is determined that thedetermined hair tress size is greater than the threshold value and thus is bigger than a desired amount of hair, the microcontroller 28 causes the appliance to cap the increase in the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, so as to enable a better drying or styling of the hair which is loaded in the apparatus while avoiding burning of the hair. Alternatively or additionally, as shown in Figure 9A, the interface of the appliance comprises lighting means and the lighting means comprise one or more lamps 111 arranged along a length the apparatus, sideways of the heater 6a. In the example of Figure 9A, when it is determined that the determined hair tress size is greater than the threshold value and thus is bigger than a desired amount of hair, the controller controls the appliance to light up one or more lights 111 of the lighting means on a length corresponding to the extent of the one or more heating zones which are engaged with the hair, in a length of the heater, thus prompting the user to modify the amount of hair loaded in the styler. As shown in Figure 9A, the lighting means are configured to produce, in such a case, a first colour, such as red, to prompt the user to modify the amount of hair loaded in the appliance. Alternatively or additionally, as shown in Figure 9B, when it is determined that the hair tress size corresponds to a desired amount of hair, the lighting means are configured to produce, a second colour, different from the first colour, such as green, reassuring the user that the amount of hair corresponds to the desired amount of hair. Other examples of feedback messages are envisaged. When the interface comprises a sound generator, the controller is configured to control the apparatus to cause the sound generator to produce a first sound, when it is determined that the hair tress size corresponds to a desired amount of hair, and to produce a second sound different from the first sound, otherwise, thus prompting the user to decrease the amount of hair loaded in the apparatus. Alternatively or additionally, when the interface comprises a haptic feedback generator, the controller is configured to control the apparatus to cause the haptic feedback generator to produce a first haptic feedback, when it is determined that the hair tress size corresponds to a desired amount of hair, and to produce a second haptic feedback different from the first haptic feedback, otherwise thus prompting the user to decrease the amount of hair loaded in the apparatus. Alternatively or additionally, when the user is connected to an application running on e.g., their mobile phone, the communication circuitry of the appliance may output the feedback message to the user interface associated with theuser on the mobile phone. In some examples the haptic feedback may be produced by a smart watch or tablet or othersuch device without needing to install a haptic feedback generator on the styler.In an optional step, in S4 the microcontroller 28 may set the threshold value discussed above to a first threshold value, and determine whether the determined hair tress size is smaller than a second threshold value, smaller than the first threshold value. If it is determined in S4 that the determined hair tress size is smaller than the second threshold value, the controller is configured to cause the apparatus to, in S5: output a feedback message indicating that too little hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the apparatus accordingly, and / or control the temperature or the power output of the one or more heating zones of the plurality of controllableheating zones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.Similarly to what has been already described, in such a case the feedback message is different from the feedback produced when it is determined that the hair tress size corresponds to a desired amount of hair. Additionally, in such a case the feedback message may be different or similar to the feedback produced when it is determined that too muchhair has been loaded in the appliance, thus prompting the user to modify, here increase, the amount of hair loaded inthe appliance. In some examples, controlling at S5 the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, comprises turning off the heater or reducing the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to prevent the hair being burnt. Grip Pressure The hair styler 1 includes a pressure sensor 32 to enable the microcontroller 28 to measure a pressure between the first movable arm 4a and the second movable arm 4b, e.g., when styling the hair. The determination of the hair tress size can be further verified by the controller 28, using the grip pressure sensor data, as larger hair tresses require more pressure to stay in place. Hair Type Knowledge of the hair style of the user may be used to determine the size of the hair tress more accurately, as thick curly hair has larger hair tress sizes than fine straight hair. The data indicative of hair type of the user may be provided directly by the user, possibly by utilising responses to ahair quiz on their mobile phone, or may be provided as the result of a determination by the appliance (e.g., using a setof deterministic rules or an artificial intelligence algorithm). In some examples, the data indicative of the hair type of theuser may be stored in the memory 30, so that the user does not have to input the data every time they use the styler.Using the determined hair tress size, the settings applied to the appliance correspond to the determined hair tress size,such that the settings are tailored to the amount of hair of the user loaded in the appliance. The user has thus a betterstyling experience, a better styling result and the hair is less likely to get damaged when styling. Figure 10 shows an example method 200 of operating the appliance. At step S0 the appliance is turned on. At S01, it is determined whether the appliance is linked to a remote application running e.g., on a mobile telephone, via the communications circuitry 27 (for example, Bluetooth, Wi-Fi and / or 3GPP communication protocols to communicatewith the mobile telephone). If the appliance is linked to the application, then at S02, the settings from the applicationare applied to the appliance (this may include the indication of the hair type of the user). If the appliance is not linked to an application or in any case after S02, the method 200 moves to the method 100 described above. The method 100 is run until it is determined at S10 that the appliance should be turned off, and in that case the appliance is turned off and the method 200 stops. Hair type predictor Figure 11 is a simplified block diagram of another control circuitry 15 that controls the operation of the hair styler device 1 shown in Figure 1. It comprises the same elements as those described with reference to Figure 2, but, in Figure 11, the hair styler 1 includes a hair diagnostic sensor 33 configured to output data indicative of diagnostic information aboutthe hair being styled or dried. The diagnostic information comprises at least one of: a level of moisture in the hair, ahumidity ambient to the hair being styled or dried, a temperature ambient to the hair being styled or dried, a geographic location of the hair being styled or dried.Hair type predictor - Input streams of dataTress Load As already stated, the Figure 7 extent of the heating zones gives the microcontroller 28 an indication of the size of the tress of hair 40 introduced between the arms of the styling appliance. The microcontroller 28 is configured to determine a hair tress size which has been loaded by the user into the apparatus. In order to determine the hair tress size, the microcontroller 28 determines, based on a drop of the temperature of one or more heating zones of the plurality of independently controllable heating zones or based on an increase in the power output needed to maintain the one or more heating zones at the target temperature, whether hair is engaged with the one or more heating zones. If it is determined that hair is engaged with the one or more heating zones, the microcontroller 28 determines an amount of hair which is engaged with the one or more heating zones. Themicrocontroller 28 then determines the hair tress size based on the amount of hair engaged with the one or moreheating zones across all of the one or more heating zones. The size of the tress of hair 40 in turn gives an indication of the amount of hair introduced between the arms of the styling appliance. Additionally or alternatively, the styler may comprise sensing means to determine the amount of hair introduced in the styling apparatus. The sensing means may include capacitive sensing means to detect the amount of hair between the heaters. Motion: Rotation and Speed As already stated, the one or more motion detection devices 31, comprising any one of an accelerometer, a gyrometer, a magnetometer, an inclination sensor, are configured to enable the microprocessor 29 to determine motion of the styling appliance. The motion may comprise the rotation and / or the speed of the styling appliance. Grip Pressure The hair styler 1 includes a pressure sensor 32 to enable the microcontroller 28 to measure a pressure between the first movable arm 4a and the second movable arm 4b, e.g., when styling the hair. Power Demand As already stated, the controller 28 comprises means to measure the power demand.In a preferred example, the microcontroller 28 determines a power demand of the apparatus, based on a temperatureof the plurality of independently controllable heating zones or based on the power output needed to maintain each heating zone of the plurality of heating zones at a target temperature. Determination of class of hair based on the streams of data Hair types have already been broadly categorised into nine reference classes (1a, 1b, 1c, 2a, 2b, 2c, 3a, 3b, 3c). The class 1a corresponds to fine, straight blonde hair and the class 3c corresponds to thick, curly dark hair. As explained in greater detail below, the memory 30 comprises a trained classifier, comprising a trained machine learning algorithm, which determines the class of hair of the user, based on their use of the hair styling appliance. As explained in greater detail below, the microcontroller 28 is configured to use the stored trained classifier to determine the type of hair of the user by classifying the hair into a reference hair class, based on the determined power demand and the determined hair tress size and control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined hair type. The microcontroller 28 is configured to control the temperature or the power output of the one or more heating zones by capping the increase in the temperature or the power output of the one or more heating zones of the plurality ofcontrollable heating zones based on the determined type of hair, to avoid the hair being burnt. Therefore even userswith hair types which do not correspond to that of most users do not get their hair damaged when styling or drying their hair. As explained in greater detail below, the controller 28 is configured set the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined type of hair with reference to the nine reference classes. The controller 28 is configured set the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones, based on the determined type of hair with reference to the nine reference classes, such that even users with hair types whichdo not correspond to that of most users have a better styling or drying experience.Generating the classifierFigure 12 shows a flow chart illustrating an example method 100-1 according to the disclosure. The method 100-1 isfor generating a classifier configured to determine the type of hair of the user of the hair styling appliance. In Figure12, the method 100-1 comprises:obtaining, at S1-1, a plurality of annotated training streams of data; and training, at S2-1, the classifier by applying a machine learning algorithm to the obtained training streams of data. The learning process is typically computationally intensive and may involve large volumes of training data.As explained in more detail below, the machine learning step S2-1 involves inferring the type of hair, such as the classof hair among the nine reference classes mentioned above, based on the training data, and encoding the determined class in the form of the classifier. The training data are annotated. In other words, during the training and in the streams of data, the class of hair isknown. As such, in the method 100-1 of Figure 12, the annotation indicates the class of hair associated with eachtraining stream of data. A domain specialist may manually annotate the streams data with ground truth annotation corresponding to the class of hair during the training.In the method 100-1 of Figure 12, the plurality of annotated training streams of data comprises, for each class of hairamong the plurality of reference hair classes: a training stream of data corresponding to a power demand of the apparatus when styling or drying hair belonging to the class of hair; and a training stream of data corresponding to a hair tress size which is typically loaded in the apparatus when styling or drying hair belonging to the class of hair. For example, for a 1a class of hair, a training stream of data corresponding to the power demand of the appliance shows less power demand than that for a 3c class of hair, as the 1a class of hair requires less heat than the 3c class of hair; and for a 1a class of hair, a training stream of data corresponding to the tress load in the appliance shows tressload greater than that for a 3c class of hair, as the 1a class of hair is thinner and straighter than the 3c class of hair.Training at S2-1 the classifier comprises training the machine learning algorithm to minimise a classification loss, forthe classification of the hair in a class of the plurality of classes of hair, such as a similarity metric of Lp-norm, p being an integer greater or equal to 1, such as an average absolute deviation or a least mean square distance from the class of hair as determined by the classifier during the training to the known class of hair. Other ways of calculating theclassification loss are envisaged.Referring back to Figure 12, the classifier is built by applying the machine learning algorithm to the training data. Any suitable machine learning algorithm may be used for building the classifier. For example, approaches based on a convolutional neural network may be used. As explained above, the classifier is primarily trained to determine the type of hair of the user based on the power demand and the hair tress size. However, additional, optional training streams of data may be fed to the classifier during training, such as one or more training streams of data corresponding to sensor data indicative of a motion of the apparatus when the user is styling or drying hair belonging to the class of hair. The motion of the hair styling or drying appliance comprises a rotation of the apparatus when styling or drying the hair and / or a speed of movement of the apparatus when styling or drying the hair. Additionally, the classifier may be trained using a training stream of data corresponding to sensor data indicative of diagnostic information about the hair being styled or dried. The diagnostic information may comprise at least one of: a level of moisture in the hair, a humidity ambient to the hair being styled or dried, a temperature ambient to the hair being styled or dried, a geographic location of the hair being styled or dried.Figure 13 shows a non-limiting example architecture of a classifier according to the disclosure. The classifier of Figure13 is generated based on the training data obtained at S1-1. In Figure 13, the training streams of data comprise: a training stream of data corresponding to a power demand of the apparatus when styling or drying hair belonging to the class of hair; and a training stream of data corresponding to a hair tress size which is typically loaded in the apparatus when styling or drying hair belonging to the class of hair. a training stream of data corresponding to sensor data indicative of a grip pressure between movable arms of the apparatus when styling or drying hair belonging to the class of hair; a stream of data corresponding to the rotation of the hair styling appliance which is typical for the given class of hair; and a stream of data corresponding to the speed of motion of the hair styling appliance when in use which is typical for the given class of hair. For example, for a 1a class of hair, a training stream of data corresponding to the grip pressure of the appliance shows less grip pressure than that for a 3c class of hair, as the 1a class of hair requires less grip pressure for styling than the 3c class of hair; for a 1a class of hair, a training stream of data corresponding to the rotation of the hair styling appliance shows less rotation of the hair styling appliance than that for a 3c class of hair, as the 1a class of hair is usually easier to curl than the 3c class of hair; and for a 1a class of hair, a training stream of data corresponding to the speed of motion of the hair styling appliance shows more speed of motion of the hair styling appliance than that for a 3c class of hair, as the 1a class of hair is usually quicker to style than the 3c class of hair. In the non-limiting example of Figure 13, in, the example classifier comprises one or more layers: an appliance input layer 101, such that the input layer 101 ∈ ℝ^, each dimension of the appliance input layer101 corresponding to a training stream of data; ahidden layer 102, such that the hidden layer 102 ∈ ℝ^; andan output layer 103 such that the output layer 104 ∈ ℝ^, each dimension of the output layer 103corresponding to a class of hair. Other configurations with other layers may also be envisaged, and other architectures are also envisaged for the classifier. For example, deeper architectures may be envisaged and / or an architecture of the same shape as the architecture described above that would generate an output layer 103 with sizes different from those already discussed may be envisaged. For example, an architecture using user input is shown in Figure 14. As shown in Figure 14, the classifier comprises one or more layers: an appliance input layer 101, such that the input layer 101 ∈ ℝ^, each dimension of the input layer 101corresponding to a stream of training data; a user input 104; ahidden layer 102, such that the hidden layer 102 ∈ ℝ^; andan output layer 103 such that the output layer 104 ∈ ℝ^, the total dimension of the output layer 103corresponding to a narrowed down subset of the classes of hair. The user input 104 enables the classifier to narrow down the possible hair classes of the user (for example here from nine reference classes to only three possible classes) and to deliver a more confident prediction of the hair class. The input in the user input 104 may result from the user simply indicating to the classifier the class of hair they believe they have. A confidence interval may be taken around the class of hair indicated by the user. For example, if the user indicates that they have a 2c class of hair, the classifier can narrow down the possible class of hair of the user to a narrowed down subset of the nine reference classes of hair which comprises e.g., one class around the input class, such as either class 2b, 2c and 3a. It should be understood that other dimensions of the subset of the classes of hair (e.g., two classes around the input class) are also envisaged. Alternatively or additionally, the input in the user input 104 may result from the user answering a questionnaire, asking questions to the user about their hair (e.g., general questions or more specific questions such as “has the hair beenmoisturised?” or “has the hair been bleached?”…), in order to determine a narrowed down subset of the classes ofhair. The questionnaire may ask more advanced questions, e.g., asking questions about the environment (such as room temperature or humidity as non-limiting examples) to account for the influence of the environment on differenthair classes. As already stated, in some examples, the user input may be stored in the memory 30, so that the userdoes not have to input the data every time they use the styler. In some examples, the styler 1 is configured to output aprompt to check with the user every so often if there is any change in the hair of the user, e.g., in case they bleachtheir hair. In some examples, the styler 1 is configured to determine that hair has changed based on deviation fromprevious performance and / or styling time.The input in the user input 104 may be performed on the user interface 11 and / or a remote application (e.g., on a mobile telephone) connected to the communications circuitry 27. After it has been trained, the classifier is used for determining the class of hair of the user of the hair styling appliance, with a confidence in the determined classification (in % of confidence in the classification). Based on the confidence of the classification, a matrix can be built to apply different settings (including e.g., a target temperature of the heaters) to the hair styling appliance (see Table 1 reproduced below). Confidence In In In In In In In In In in class class class class class class class class class classificatio 1a 1b 1c 2a 2b 2c 3a 3b 3c n Greater Setting Setting Settin Setting Setting Setting Setting Setting Setting than 85% 1a 1b g 1c 2a 2b 2c 3a 3b 3c Setting Group Between SettingSetting Group 6 Setting Group 8 Setting Group 10Setting 4 55% and Group Group Setting 85% 4 Setting Group 5 Setting Group 7 Setting Group 911 Group 11 Between 15% andSetting Group 1 Setting Group 2 Setting Group 354% Smaller Default setting for all classes of hair than 15% Table 1 When the confidence in the classification by the classifier is greater than a great degree of confidence, e.g., greater than 85% in Table 1, each class of hair has its own setting, for example a target temperature of 160°C for class 1a and a target temperature of 200°C for class 3c. When the confidence in the classification is great, e.g., a degree of confidence between 55% and 85% in Table 1, small overlapping groups of classes of hair have their own setting, for example a target temperature of 170°C if the determined class of hair is between class 1a and class 1b (Setting Group 4) and a target temperature of e.g., 190°C if the determined class of hair is between class 3b and class 3c (SettingGroup 11). When the confidence in the classification is not great, e.g., a degree of confidence between 15% and 84%in Table 1, three main groups of classes of hair have their own setting, for example a target temperature of e.g., 175°C if the determined class of hair is between classes 1a and 1c (Setting Group 1), a target temperature of e.g., 180°C if the determined class of hair is between classes 2a and 2c (Setting Group 2), and a target temperature of e.g., 185°C if the determined class of hair is between classes 3a and class 3c (Setting Group 3) for class 3c. If there is no confidence in the classification, the target temperature is set to the default temperature for all of the classes of hair. Other temperatures and groupings than those mentioned above are envisaged. Computer system and hair styling appliance A computer system (not shown in the Figures) may execute the deep learning algorithm to generate the classifier to be stored on the memory 30 of the hair styling appliance. The computer system may communicate and interact with multiple such hair styling appliances. The computer system may conventionally comprise a memory, a processor and a communications interface. The computer system may be configured to communicate with one or more hair styling appliances, via the communications interface and a link (e.g. Wi-Fi connectivity, but other types of connectivity may be envisaged). The memory of the computer system is configured to store data, for example for use by the processor. In some examples the data stored on the memory may comprise the training data and / or the deep learning algorithm. In some examples, the training data may correspond to actual observed data streams on the hair styling appliance, or the training data may be generated, for example in a laboratory. The training may be performed at the computer system separate, optionally remote, from hair styling appliance. However, if sufficient processing power is available locally then the classifier learning could be performed (at least partly) by the microprocessor 29 of the hair styling appliance. The classifier is arranged to produce the determination of the class of hair more easily, after it is stored in the memory30 of the hair styling appliance, even though the process 100-1 for generating the classifier from the training data maybe computationally intensive. After it is configured, the hair styling appliance may provide determination of a class of hair of the user of the hair styling appliance, by applying the learned classifier during use of the hair styling appliance, using the same input data streams as during the training. Hair styling appliance manufactureAs illustrated in Figure 15, the method 200-1 of producing the hair styling appliance configured to determine the classof hair of the user using the hair styling appliance comprises: obtaining, at S31, a classifier generated by the method 100-1 according to any aspects of the disclosure; andstoring, at S32, the obtained classifier in the memory 30 of the hair styling appliance. The classifier may be generated and stored using any suitable representation, for example as a data description comprising data elements specifying classification conditions and their classification outputs. Such a data description could be encoded e.g. using XML or using a bespoke binary representation. The data description is then interpreted by the microprocessor 29 running on the appliance when applying the classifier. Alternatively, the deep learning algorithm may generate the classifier directly as executable code (e.g. machine code, virtual machine byte code or interpretable script). This may be in the form of a code routine that the appliance can invoke to apply the classifier. The appliance may be connected temporarily to the computer system to transfer the generated classifier (e.g. as a data file or executable code) or transfer may occur using a storage medium (e.g. memory card). In a preferred approach, the classifier is transferred to the appliance from the computer system over the communications link (this could include transmission over the Internet from a central location of the computer system to a local network where the appliance is located using the communications circuitry 27, e.g., via a mobile phone connected to the appliance via the Bluetooth, Wi-Fi and / or 3GPP communication protocols). Thanks to the communications circuitry 27, the classifier could be installed as part of a firmware update of device software, or independently. Installation of the classifier may be performed once (e.g. at time of manufacture orinstallation) or repeatedly (e.g. as a regular update). The latter approach can allow the classification performance ofthe classifier to be improved over time, as new training data become available. The latter approach can allow updating the setting for different hair types. Applying the classifier to perform classificationFigure 16 shows a flow chart illustrating an example method 300 for operating the hair styling appliance, using theclassification of the hair of the user of the hair styling appliance. The method 300 is performed by the hair styling appliance. The method 300 comprises: obtaining, at S41, streams of data during use of the hair styling appliance; classifying, at S42, the hair of the user, by applying the learned algorithm to the obtained streams of data; and applying, at S43, settings to the hair styling appliance, based on the classifying. The obtained streams of data correspond to the observed streams of data during use of the hair styling appliance and which are similar to the training streams of data. As already stated, the streams of data primarily comprise a power demand and a hair tress size which has been loaded by the user, and the trained classifier is configured to determine the type of hair of the user by classifying the hair into a reference hair class, based on the determined power demand and the determined hair tress size, so that the appliance can control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined hair type. However, additional, optional streams of data may be fed to the classifier during use to have a better classification. Optional additional streams of data may include: one or more training streams of data corresponding to sensor data indicative of a motion of the apparatus when the user is styling or drying hair belonging to the class of hair. The motion of the hair styling or drying appliancecomprises a rotation of the apparatus when styling or drying the hair and / or a speed of movement of the apparatuswhen styling or drying the hair, as explained above. a stream of data corresponding to the grip pressure that the user applies to the hair styling appliance when styling or drying. The communication circuitry may receive the user input information from an external processing device of a mobile phone of the user, and the stored trained classifier can narrow down the plurality of reference hair classes into which the hair of the user is to be classified, based on the received user input information. The input may comprise at least one of: an indication by the user of the hair type they believe they have and / or a result from the user answering a questionnaire about their hair and / or the environment, as explained above. The controller 28 may configured to process further sensor data to determine diagnostic information about the hair being styled or dried, and the diagnostic information comprises at least one of: a level of moisture in the hair, a humidity ambient to the hair being styled or dried, a temperature ambient to the hair being styled or dried, a geographic location of the hair being styled or dried. After the class of hair has been determined by the appliance with a percentage of confidence, the settings corresponding to Table 1 already discussed may be applied to the appliance. The microcontroller controls the temperature or the power output of the one or more heating zones by capping the increase in the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones based on the determinedtype of hair, to avoid the hair being burnt.The applied settings correspond to the determined class of hair, such that the settings are tailored to the type of hair of the user. The user has thus a better styling experience, a better styling result and the hair is less likely to get damaged when styling. STYLE RECIPES When a user wants to replicate a hair treatment (for example a hair style generated by a stylist, a friend or an influencer), the user has, at best, a video recording of the motions they need to do to achieve the treatment, or, at worst, the user has to work out the hair treatment from memory. Therefore, the users generally do not know the full instructions they should be following in order to achieve a desired treatment. The lack of full knowledge of the instructions often results in the hair of the user being treated according to a treatment which is different from the desired treatment, in turn resulting in a frustrating styling experience. Sometimes the user will have their hair damaged when styling.Style recipes - Operation of the apparatusAchievement of a desired hair treatmentFigure 17 shows a flow chart illustrating an example method 100-2 for operating an appliance for treating hair,according to the disclosure.In the method 100-2 of Figure 17, at S1-2, a user specifies a desired treatment to be performed on hair and that theuser wishes to copy. In the method 100-2, the user’s desired treatment comprises one or more desired sequences and is associated with pre-stored data, the pre-stored data being for example stored in a remote server (not shown in the Figures). The pre- stored data includes information on how the appliance should be moved by the user during each of the one or more desired sequences to achieve the desired treatment. In the method 100-2, the user uses the user interface 11 (for example a touch display) to specify the desired treatment(such as “beach-curl” or “curtain bangs”, as non-limiting examples), for example among a library of available referencetreatments. The specification could conventionally involve a search engine to search the library of pre-stored reference treatments. The communication circuitry 27 may be configured to access the pre-stored data associated with the user’s desired treatment via the external processing device already described. For example, the pre-stored data is downloaded from the remote server via a phone application or accessed remotely using a web browser. The user interface 11 is configured to output to the user, at S2-2, the one or more sequences of the desired treatment to the user, such as on the display of the user interface associated with the user on the external device. For example, the user interface 11 may be configured to output to the user a name to the treatment (such as “curtain bangs”), and / ora name of each of the one or more sequences (such as “straighten” and / or “curl front sections”), and / or output writteninstructions, pictures and / or video instructions associated with the desired treatment or the one or more sequence (such as “Split your hair into multiple sections over your whole head. Make sure there are two sections at the front, on the left and right sides”), to help explain the treatment and / or the one or more sequences. As already stated, the motion sensors 31 are configured to sense and output, at S3-2, sensor data indicative of operational parameters of the appliance during the treatment, including motion data that indicates how the appliance is being moved by the user. In the method 100-2, for each of the one or more desired sequences of the user’s desired treatment, the microcontroller 28 determines, at S4-2, whether a deviation of the user’s manipulation of the appliance from how the appliance should be moved by the user to complete the desired sequence is greater than a threshold value. The threshold value corresponds to a tolerance in the movements of the appliance. The tolerance allows for the user not to match the movements of the sequence perfectly, movement by movement. Each sequence has a certain tolerance to failure. Forexample, a regular sequence corresponding to "straighten hair" has a relatively high tolerance in movement, as thedesired style is not greatly dependant on user error. However, a sequence for “curl hair in beach-curl” has a relativelylow tolerance on the direction of rotation of the appliance. In other words, each of the desired sequence has its own threshold value.If it is determined at S4-2 that the deviation of the user’s manipulation of the appliance is greater than the thresholdvalue, the method 100-2 moves to S5-2 where the microcontroller 28 outputs one or more feedback messages for theuser to modify the way the appliance is manipulated, to help the user to complete the desired sequence.The user interface 11 is configured to output the one or more feedback messages to the user on the appliance. In suchexamples, the user interface 11 comprises at least one of a sound generator, lighting means, a thermal somatosensory feedback generator, and / or a haptic feedback generator already described. In such examples, it is determined at S4-2 that the deviation of the user’s manipulation of the appliance is greater than the threshold value, the controller isconfigured to control the apparatus to cause the sound generator, the lighting means, the thermal somatosensory feedback generator, and / or the haptic feedback generator to produce a feedback message, such as a sound of a given type (such as a buzz), a light of a given colour (such as red), heat up the somatosensory feedback generator and / or a given haptic feedback. The feedback prompts the user to modify the way the appliance is manipulated, to help the user to complete the desired sequence.Alternatively or additionally, the user interface 11 is configured to output the one or more feedback messages to theuser on the external processing device. In such examples, when the user is connected to an application running on their mobile phone or their smartwatch, the communication circuitry of the appliance may output the feedback message (such as a visual indication or an audible alert) to the user interface associated with the user on the mobile phone orsmartwatch or tablet or other such device. In such examples, haptic feedback may be produced e.g., via the smartwatchor the mobile phone, without needing to install a haptic feedback generator in the appliance. Other examples offeedback messages are envisaged.Alternatively or additionally, if it is determined at S4-2 that the deviation of the user’s manipulation of the appliance isgreater than the threshold value, at S5-2 the microcontroller 28 controls the temperature or the power output of theone or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to avoid the hair loaded into the apparatus to be treated according to an undesired sequence. In such an example, controlling atS5-2 the temperature or the power output of the one or more heating zones of the plurality of controllable heating zoneswhich are engaged with the hair, comprises turning off the heater or individually modifying and / or individually reducing and / or individually capping the temperature or the power output of the one or more heating zones of the plurality of individually controllable heating zones which are engaged with the hair. The controlling also prevents the hair being burnt.Some treatments do not have any ordered sequences or any particular orientation with respect to the head of the user,such as the treatment “straighten hair”. However, some treatments comprise one or more desired sequences which are ordered and / or are associated with a side the user’s head, to achieve the user’s desired treatment. For example, in order to achieve the style “curtain bangs”, the sequences “straighten hair” and “curl front sections” are ordered such that the sequence “straighten hair” has to be performed and completed before the sequence “curl front sections” can be performed and completed. In some cases, the one or more desired sequences are ordered in groups of equal priority in the order, such that any sequences in a group can be performed and completed before or after another sequence in the group. In such examples, the user interface 11 is further configured to allow the user to specify when a desired sequence has been completed.It is determined at S6-2 whether the treatment has been completed. If it is determined at S6-2 that the treatment hasbeen completed, the method 100-2 ends or moves to optional step S7-2. In S7-2, the user interface is configured tooutput one or more user messages for the user, to allow the user to upload a picture of the completed treatment and / or rate the desired treatment. Higher rated treatments may have a higher priority in the searchable library of available treatments and / or may help enhance the quality of new treatments. After the optional step S7-2, the method 100-2ends. If it is determined at S6-2 that the treatment has not been completed, the method 100-2 moves to S3-2 foranother sequence of the desired treatment. If it is determined at S4-2 that the deviation of the user’s manipulation ofthe appliance is smaller than the threshold value, the method 100-2 moves to S6-2 described above.Generation of a reference hair treatmentFigure 18 shows a flow chart illustrating an example method 200-2 allowing a stylist (such as a professional stylist, afriend of the user or an influencer whom the user follows as non-limiting examples) to generate a reference hair treatment on an appliance according to the disclosure. In the method 200-2, the appliance is manipulable by the stylist to perform on hair the reference treatment and that isdestined to be copied by a user (using the method 100-2 already described with reference to Figure 17 describedabove). It should be understood that, in the context of the disclosure, the user may be a trainee stylist. In other words,e.g., a stylist could perform a reference treatment on a client’s hair, and the reference treatment could be saved toallow a trainee stylist to learn how to replicate the style - either on another client’s hair, or on a head block (dummywith hair for training / practise). In some examples, the appliance is manipulable by the stylist to perform the referencetreatment on their hair. As already stated, the motion sensors 31 of the appliance are configured to sense and output, at S10-2, sensor data indicative of operational parameters of the appliance during the reference treatment, the sensor data including motion data that indicates how the appliance is being moved by the stylist. At S20-2, the raw data including the motion data corresponding to the sensor data representative of the stylist’s manipulation of the appliance is processed by the microcontroller 28, to be recorded. At S30-2, the microcontroller 28 processes the recorded data to determine which movements of the appliance effectively contribute to achievement of the reference treatment. At S40-2, the microcontroller 28 processes the recorded data corresponding to the determined effective movements of the appliance to generate pre-stored data which includes one or more reference sequences to achieve the stylist’s reference treatment, each reference sequence including information on how the appliance should be moved by the user during the reference sequence. For example, in order to achieve the reference style “curtain bangs”, the sequences include the sequence “straighten hair” and the sequence “curl front sections”.In some examples, at S40-2 the user interface 11 is configured to allow the stylist toassign a name to the treatment (such as “curtain bangs”), and / or assign a name to the one or more reference sequences (such as “straighten hair” for a sequence and “curl front sections” for another sequence), and / or upload written instructions, pictures and / or video instructions associated with the reference treatment and / or the one or more sequences (such as “Split your hair into multiple sections over your whole head. Make sure there are two sections at the front, on the left and right sides”), to help explain the treatment and / or the one or more sequences. In the method 200-2, the generated pre-stored data is then stored at S50-2, in a remote server (not shown in the Figures), for example among a library of reference treatments, conventionally searchable using a search engine. As already stated, the library of reference treatments may be accessed by a user via an external processing device. For example, the pre-stored data is downloaded from the remote server via a phone application or accessed remotely using a web browser.Some aspects of the processing performed in the method 200-2 are disclosed below.In Figure 18, at S10-2, the sensor data representative of the operational parameters of the appliance during thereference treatment further include sensor data output by the pressure sensor 32, the further data being indicative ofwhether the moveable arms of the appliance are: in a closed position, in which the arms are adjacent each other, or in an open position, in which the arms are spaced apart. At S20-2, the microcontroller 28 processes the data to record the further data being indicative of whether the moveable arms of the appliance are in the closed position or in the open position, together with the motion data that indicates how the appliance is being moved by the user. At S30-2, the microcontroller 28 works on an assumption that movements which are performed when the arms of theappliance are in the closed position are intentional movements and are, in other words, movements which contributeto the achievement of the reference treatment. It may be also considered at S30-2 that movements which are performedwhen the arms of the appliance are in the open position do not contribute to the achievement of the reference treatment. Therefore, at S30-2, the microcontroller 28 processes the recorded data to determine that movements of the appliance performed when the moveable arms of the appliance are in the closed position effectively contribute to the achievement of the reference treatment. Alternatively or additionally, at S30-2, the microcontroller 28 processes the recorded data to determine that movements of the appliance performed when the moveable arms of the appliance are in the open position do not contribute to the achievement of the reference treatment.Figure 19 shows a flow chart illustrating some further steps of the step S40-2 of the method 200-2 of Figure 18. In thestep S40-2 shown at Figure 19, at S41-2 the microcontroller 28 processes the recorded data including the further dataas described above with reference to S30. At S42-2, the microcontroller 28 determines whether one or more movements of the appliance which effectively contribute to the achievement of the reference treatment are repeated at a frequency which is lower than a threshold. Movements of the appliance which are repeated at lower frequencies (such as one repetition every second or every other second, as non-limiting examples) are indicative of an intentional movement on different parts of the hair being styled. Higher frequencies of repetitions of movements are indicative of the stylist going over a same tress of hair, multiple times.If it is determined at S42-2 that one or more movements of the appliance which effectively contribute to the achievementof the reference treatment are repeated at a frequency which is lower than the threshold, then the microcontroller 28groups at S43-2 the determined repeated effective movements together into a sequence, and the method moves toS44-2. At S44-2, the microcontroller 28 compares the one or more grouped sequences and determines whether thereis a deviation between at least two sequences of the one or more sequences.If it is determined at S44-2 that there is a deviation between at least two sequences of the one or more sequences, themicrocontroller 28 determines at S45-2 whether the deviation between the at least two sequences is greater than athreshold value. The threshold value corresponds to a significantly different action on the hair. If it is determined atS45-2 that the deviation between the at least two sequences is greater than a threshold value, then the microcontroller28 determines at S46-2 that the at least two sequences are reference sequences to achieve the stylist’s referencetreatment.However, if it is determined at S44-2 that there is no deviation between the at least two sequences of the one or moresequences, or if it is determined at S45-2 that there is a deviation which is smaller than the threshold value, the methodmoves to S47-2 where the microcontroller 28 determines that the at least two sequences correspond to a singlereference sequence to achieve the stylist’s reference treatment. After S46-2 and S47-2, the method moves to S48-2,where the microcontroller 28 determines whether there is a pattern of one or more sequences.If it is determined at S48-2 that there is a pattern of one or more sequences, then the microcontroller 28 assigns atS49-2 an order and / or a side of the stylist’s head to the one or more reference sequences according to the determined pattern. In some examples, the one or more desired sequences are ordered in groups of equal priority in the order. If it is determined at S48-2 that there is no pattern of one or more sequences, then the microcontroller 28 does not assign any order to the one or more reference sequences, and the method moves to S50-2 already described. Afterstep S48-2 and S49-2 the method of Figure 19 moves to S50-2 already described with reference to Figure 18.If it is determined at S42-2 that one or more movements of the appliance which effectively contribute to the achievementof the reference treatment are repeated at a frequency which is higher than the threshold, then the microcontroller 28 determines at S420 that the movements are indicative of the stylist going over a same tress of hair, multiple times, and the corresponding movements are not grouped into a sequence, but the microcontroller 28 determines that the movements correspond to a single movement for the achievement of the treatment. The method then moves back toS42-2 already described.In an example, the microcontroller 28 is configured to process the sensor data to discard data which is representative of the stylist’s manipulation of the appliance above a movement amplitude or movement speed safety line (for example shown in Figure 20a, discussed in greater detail below). In other words, any movement that is determined as too rapid (i.e., above the safety line shown in Figure 20a) is filtered out. In this example it is considered that when the styler is moved too rapidly, heat from the heater is not sufficiently applied to the hair, which in turn creates the need for repeat passes on the hair which ultimately ends up damaging the hair. The control of the heating of the heater is based on the remaining sensor data based on the data. The control of the heating of the heater is thus based on the safe movements for the hair. The microcontroller may process the data based on a set of deterministic rules and / or data for an artificial intelligence algorithm, stored in the memory 30 already described. Figures 20a, 20b, 20c, 20d and 20e show an example result obtained after a processing of raw data from an appliance according to the disclosure. Figure 20a shows the recorded raw data about the movement of the appliance, obtained at the step S30 described above, as a function of time. In Figure 20a, a first part of the curve (solid line in Figure 20a) shows the movements of the appliance performed with the arms of the appliance in the open position (and which will be filtered out), and a second part of the curve (dotted line in Figure 20a) shows the movements of the appliance performed with the arms of the appliance in the closed position (i.e. the effective movements for the achievement of the treatment). The mixed dotted line shows the safety line, above which the movements are not taken into account (the movements above the safety line are filtered out in the example of Figure 20a), for safety reasons, as explained above. Figures 20b, 20c, 20d and 20e respectively represent one or more sequences identified after the processing of the rawdata according to the step S40-2 described above, as shown in Figure 20a.In a first example, the microprocessor 28 has determined that the treatment corresponding to the raw data of Figure 20a has two sequences. The first sequence comprises the effective movements of Figure 20b and the effective movements of Figure 20e, with the movements of Figure 20b being performed on the right of the head of the user and the movements of Figure 20e being performed on the left of the head of the user. The second sequence comprises the effective movements of Figure 20c and the effective movements of Figure 20d, with the movements of Figure 20c being performed on the right of the head of the user and the movements of Figure 20d being performed on the left of the head of the user. In the first example, the microprocessor 28 has also determined that the first sequence and the second sequence belong to the same priority, such that the order in which the sequences are performed with respect to each other has no impact on the achievement of the treatment. In a second example, the microprocessor 28 has determined that the treatment corresponding to the raw data of Figure 20a, has four ordered sequences. The first sequence comprises the effective movements of Figure 20b, with the movements of Figure 20b being performed on the right of the head of the user. In the second example, the first sequence must be performed and completed before the second sequence. The second sequence comprises the effective movements of Figure 20e, the movements of Figure 20e being performed on the left of the head of the user. In the second example, the second sequence must be performed and completed before the third sequence. The third sequence comprises the effective movements of Figure 20c, the movements of Figure 20c being performed on the right of the head of the user, and the fourth sequence comprises the effective movements of Figure 20d, the movements of Figure 20d being performed on the left of the head of the user. In the second example, it might be determined that the third sequence can be performed and completed before or after the fourth sequence. THERMAL SOMATOSENSORY FEEDBACK Users often do not realise how hot the heaters are, which can provoke damage to the hair.Thermal somatosensory feedback - OverviewFigure 21 illustrates a hand-held (portable) hair styler 1 (or hair styling appliance or apparatus in the present disclosure), similar to the hair styler 1 of Figure 1a and the elements in common will not be described in detail, for the sake of conciseness. In Figure 21, the hair styler 1 includes a handle 10 that the user holds during use. In Figure 21 the handle 10 comprises a first movable arm 4a and a second movable arm 4b, which are coupled at proximal ends thereof to a shoulder 2. The hair styler 1 includes at least one heater for heating hair during drying and / or styling. In Figure 1a, the first arm 4a bears a first heater 6a at its distal end, and the second arm 4b bears a second heater 6b at its distal end. The first and second heaters 6a, 6b oppose one another and are brought together as the first and second arms 4a, 4b are moved from an open configuration to a closed configuration. In Figure 21, the hair styler 1 includes a thermal somatosensory feedback generator 12. As described in more detail below, the thermal somatosensory feedback generator 12 comprises at least one heater electrode 13 for heating at least one portion of the handle 10. The at least one heater electrode 13 for heating the handle is different from heater electrodes which will be described in more detail below and which are used for heating the heaters 6a and 6b that heat the hair. The at least one heater electrode 13 for heating the handle is mounted within the handle 10. In use, when the device 1 is turned on, energising the heaters 6 to cause them to heat up, the thermal somatosensory feedback generator 12 may also be energised and the at least one heater electrode 13 heated up, as described in more detail below.Thermal somatosensory feedback - Control circuitryFigure 22 is a simplified block diagram of control circuitry 15 that controls the operation of the hair styler device 1 shownin Figure 21. The control circuitry 15 of Figure 22 is similar to that of Figure 2 and the elements in common will not bedescribed in detail, for the sake of conciseness. In the example of Figure 22, power may also be provided to the at least one heater electrode 13 of the thermal somatosensory feedback generator 12 for heating at least one portion of the handle. The power supplied to the at least one heater electrode 13 is controlled by the controller 28 and the microprocessor 29. The power supplied to the at least one heater electrode 13 is controlled by drive circuitry 33-1 (which may include one or more power semiconductor switching devices (triacs)) which controls the application of an AC mains voltage, or a DC voltage derived from the ACmains or from a battery, to the at least one heater electrode 13 in accordance with instructions from the microprocessor29. The microprocessor 29 is coupled to a memory 30 (which is typically a non-volatile memory) that stores processor control code for implementing one or more control methods that control the heating of the heaters 6 and / or of the atleast one heater electrode 13 in accordance with a desired operating temperature and sensed temperatures of theheaters 6 and / or of the at least one heater electrode 13, for example obtained from temperature measurement circuitry 25. The microprocessor 29 allows for complex control of the heaters 6 and / or of the at least one heater electrode 13. For example, the controller 28 may be configured to adjust the power delivered to heaters by using an on / off triac based upon the output of the temperature measurement circuitry 25. The controller 28 comprises means to measure the input voltage or alternatively to detect the speed at which the heaters 6 and / or the at least one heater electrode 13 heat up, so as to detect the type of input voltage. A high input voltage would lead to a faster heat up of the heaters 6 and / or of the at least one heater electrode 13, and hence a control loop can react appropriately. The input voltage and / or speed of heat up can also be used to detect a failure. A rated power output for the heater for heating hair is greater than a rated power output for the at least one heater for heating the handle. In Figure 22, the hair styler 1 includes a hand placement sensor 34 configured to measure the placement of the hand of the user during the treatment. The hand placement sensor 34 comprises at least one of resistive and / or capacitive means to measure the placement of the hand of the user on an outside casework (of the moveable arms 4a and 4b) of the styler 1. The temperature measurement circuitry 25 may be temperature sensors such as thermistors or they may use circuitry that senses the resistance of heater electrodes that are used to heat the heaters 6 and / or the at least one heater electrode 13, which resistance depends on the temperature of the heater electrode. Thermal somatosensory feedback generator In the example of Figures 23a and 23b, the thermal somatosensory feedback generator 12 comprises at least one low thermal mass heater and can therefore heat up and cool down quickly. Figures 23a and 23b show an exemplary embodiment of such at least one heater. Similarly to the heaters 6a, 6b described above, the at least one heater of the thermal somatosensory feedback generator 12 comprises a stack of thin layers. Referring in particular to Figure 23a, the thermal somatosensory feedback generator 12 includes an upper, electrically insulating layer 122, an electrode layer 123 that has a plurality of separate heater electrodes 13, and a lower dielectric layer 126 which electrically insulates the heater electrodes 13 from other components mounted behind the thermal somatosensory feedback generator 12. The three layers 122, 123 and 126 are bonded together either through an adhesive layer (pressure set or thermoset) or through diffusion bonding of the contacting materials (e.g. melting them together) and define a thermal somatosensory feedback generator 12 that is very thin (the three layers have an overall thickness of between 30µm to 1000µm in the case of Safe Extra Low Voltage (SELV) operation (less than 42.4 Volts) and 0.8mm to 2.0mm in the case of AC operation) and with very low thermal mass. The upper surface of the layer 122 provides the hand contacting surface of the handle 10. The bonded layers 122, 123 and 126 define a thermal somatosensory feedback generator 12 and rigidity of the thermal somatosensory feedback generator 12 is provided in the illustrated embodiment by mounting the layers 122, 123 and 126 into a rigid support 128 which forms a base. These layers may be mounted onto the rigid support after the layers themselves have been bonded together or they may be bonded one at a time (or multiple at a time) onto the rigid support 128. If a flexible thermal somatosensory feedback generator 12 is desired, then there is no need for the rigidsupport 128 or if a support is used, this may be a non-rigid support.In the illustrated embodiment, the thermal somatosensory feedback generator 12 comprises ten heater electrodes 13 that each snake across and back across the width of the thermal somatosensory feedback generator 12, folding twice such that they each cross the width three times. The ends of each of the heater electrodes 13 are electrically connected through the lower dielectric layer 126 to electrical connections within the rigid support 128, which connect to an electrical connector 130. Drive circuitry 33 that is mounted within one of the arms 4, at the level of the handle 10, connects to the heater electrodes 13 via the electrical connector 130 and applies electrical power to the individual heater electrodes 13 to control the heat generated by each heater electrode 13. The electrical connector 130 extends from a surface of the rigid support 128 facing away from the surface layer 122 (shown in Figures 23a and 23b as extending directly away from the upper layer 122, but it could also be provided as extending in a perpendicular direction). As illustrated in Figures 24 and 25, each of the heater electrodes 13 thus creates an individual heating zone 131 on the handle 10, which spans the width (which we shall refer to as the z-direction) of the handle 10 and the heater electrodes 13 are arranged sequentially one after the other along the length (the y-direction) of the handle 10. Figures 24 and 25 show a schematic view of a possible arrangement of such heating zones 131. Figures 24 and 25 show an arrangement corresponding to that of Figures 23a and 23b, in which the heating zones 131 are arranged along the y-direction only.Alternative arrangements are also envisaged, in which heating zones are arranged in both the z- and y-directions.Such an arrangement of heating zones can be provided by arranging two sets of heater electrodes 13 like those shown in Figure 23a side by side in the width, z-direction. The heaters 13 may be separated in this way into any number ofheating zones 131 and may comprise any number of heating zones along the z- and y-directions.The heating zones 131 of the thermal somatosensory feedback generator 12 can be operated (heated) independently. The heating zones 131 illustrated in Figures 24 and 25 are all the same size. Of course, different sized heating zones 131 may be provided. The way in which the heater electrodes 13 would be arranged to define these different sized zones would be understood by the skilled reader and will not be described in detail here. The heating zones 131 described above are not limited to flat hand contacting surfaces and can be configured for use a tubular form or in a curved form, depending on the desired handle shape. The temperature of each heating zone 131 is independently controllable. Each heating zone 131 can be set to a target temperature. The target temperature of each heating zone 131 may be different. The controller is configured to control a temperature or a power output of the at least one heater electrode 13 for heating the handle to avoid the hand of the user being burnt. In a preferred embodiment, the temperature or the poweroutput of the at least one heater electrode 13 is capped to a target temperature comprised between 35°C and 40°C,to avoid the hand of the user being burnt. A separate temperature sensor may be provided for sensing the temperature of each heating zone 131 which is fed back to the microprocessor 29 to allow the microprocessor 29 to control the delivery of power to the heater electrode 13 of the corresponding heating zone 131. Alternatively, if the heater electrodes 13 are formed of a material having a Positive Temperature Coefficient (PTC) or a Negative Temperature Coefficient (NTC) (such that its resistance varies with its temperature), then the temperature of each heating zone 131 can be determined by determining the resistance of the corresponding heater electrode 13. The microcontroller 28 controls the heating in order to reduce the difference between the actual temperature of the heating zone 131 and the target temperature for that heating zone 131.Thermal somatosensory feedback - OperationFigure 26 shows a flow chart illustrating an example method 100-3 of operation of the apparatus, according to the disclosure. In the method 100-3, the apparatus is manipulable by a user to perform a desired treatment on the hair of the user. In the method 100-3 of Figure 26, at S1-3, one or more sensors already described in the present disclosure sense and output sensor data indicative of one or more operating parameters of the apparatus during use.At S2-3, the microcontroller 28 processes the sensor data. At S3-3, the microcontroller 28 controls the thermalsomatosensory feedback generator to provide thermal feedback to the user by varying the heating of the at least one portion of the handle during use of the apparatus to dry and / or style hair.In a first example of the method 100-3 of Figure 26, at S1-3, the one or more sensors (such as components in themicrocontroller 28) sense whether the apparatus has been switched on. In the first example of the method 100-3 ofFigure 26, the controller 28, at S3-3, provides thermal feedback indicative that the apparatus has been switched on. The heaters 6a and 6b have a low thermal mass with very rapid heating capabilities. The handle 10 of the styler might feel cold to the touch to some users. The users may thus not realise that the apparatus is switched on. The users might therefore get burnt or might burn their hair. By giving thermal feedback by heating at least one portion of the handle 10, the thermal feedback in the handle being indicative that the apparatus has been switched on, the apparatus prevents the users from being burnt or from burning their hair. The users are also reassured that they are not putting a cold styler on their hair.In a second example of the method 100-3 of Figure 26, at S1-3, the one or more sensors (such as the temperaturemeasurement circuitry 25) sense a temperature of the heaters 6a and 6b. In the second example of the method 100-3 of Figure 26, the controller 28, at S3-3, provides thermal feedback indicative of the temperature of the heaters 6a and6b. As already stated, the heaters 6a and 6b have a low thermal mass with very rapid heating capabilities. The usersmay thus not realise that the heaters 6a and 6b have reached a given temperature and / or the users may not perceive the heaters 6a and 6b as being hot enough. The users might thus get burnt or might burn their hair, or perceive the styler 1 as being deficient. By giving thermal feedback by varying the heating of at least one portion of the handle, the apparatus prevents the users from being burnt or from burning their hair or from perceiving the styler 1 as being deficient or low quality. Theusers are also reassured that they are not putting a too cold or a too hot styler on their hair. In a first variant, in S3-3the temperature of the thermal feedback may be proportional to the temperature of the heaters 6a and 6b, a lower temperature of the thermal feedback corresponding to a lower temperature of the heaters 6a and 6b, and a greater temperature of the thermal feedback corresponding to a greater temperature of the heaters 6a and 6b.In a second variant, in S3-3 the controller provides thermal feedback indicative that the temperature of the heater hasreached a target temperature. For example, the thermal feedback may be given by heating at least one portion of the handle after the temperature of the heaters 6a and 6b have reached 160°C.In a third example of the method 100-3 of Figure 26, at S1-3, the one or more sensors (such as the temperaturemeasurement circuitry 25 or such as components in the microcontroller 28) sense a temperature of the heaters 6aand / or 6b or a power output of the heaters 6a and / or 6b. In the third example of the method 100-3 of Figure 26, thecontroller 28, at S2-3, processes the sensor data to determine a temperature of the hair engaged with the apparatus during drying and / or styling. The determination of the temperature of the hair is based on a drop of the temperature of heaters 6a and / or 6b or based on an increase in the power output needed to maintain the heaters 6a and / or 6b at atarget temperature. In the third example of the method 100-3 of Figure 26, the controller 28, at S3-3, provides thermalfeedback indicative of the determined temperature of the hair. As the heaters 6a and 6b have a low thermal mass with very rapid heating capabilities, heat is rapidly injected into the hair either by clamping or wrapping the hair around the arms 4a and 4b. The users may not realise that the heaters 6a and 6b have heated the hair to a desired temperature. The users might burn their hair. By giving thermal feedback by heating at least one portion of the handle to indicate that the hair has reached a desired temperature, for example to indicate to the user that their hair has heated to the correct temperature when curling, the apparatus prevents the users from burning their hair. When the hair gets to the desired temperature, the thermal somatosensory feedback generator heats up, thus giving thermal feedback informing the user that their hair can be released from the arms 4a and 4b. In the example illustrated in Figure 25, the hand placement sensor 34 comprises a plurality of independent resistive and / or capacitive means which define a plurality of independently measurable zones 341 of the handle 10. In the example of Figure 25, each resistive and / or capacitive means is configured to sense and output data indicative of a hand placement on a respective independently measurable zone 341.In a fourth example of the method 100-3 of Figure 26, in S1 the hand placement sensor 34 senses and outputs dataindicative of a hand placement on the respective independently measurable zones 341. In the fourth example of themethod 100-3 of Figure 26, in S2-3 the controller 28 processes the hand placement sensor data to determine whetherthe user has placed a part of their hand on the independently measurable zones 341. In the fourth example of themethod 100-3 of Figure 26, in S3-3 the controller 28 controls the thermal somatosensory feedback generator to providethermal feedback to the user by varying the heating of the plurality of independently controllable heating zones, basedon the processed hand placement sensor data. In the example of Figure 25, the zone 131-1 is heated up first, indicating to the user where to place their thumb. In the example of Figure 25, after it is determined, using the hand placement sensor 34 data, that the user has placed their thumb on the zone 131-1, the zones 131-2 are heated up to show to the user where to place the rest of their hand.In the fourth example of the method 100-3 of Figure 26, the thermal feedback is for the user to place at least one partof their hand on the handle in a desired way and / or to modify the way the at least one part of their hand is placed on the handle. The thermal feedback may be to help the user to complete a desired hair treatment. LED lighting of the indicator light and / or audio feedback from the sound generator, both described above, may be usedin accompaniment to the thermal feedback to indicate whether the user is gripping the styler correctly. For example,the indicator light may comprise one or more lamps arranged along a length of the handle of the styler, sideways of the handle. The controller may be configured to light up one or more lights of the lighting means on a lengthcorresponding to the extent of the one or more the zones on which the user has to place at least part of their hand (i.e.,the independently measurable zones 341 and / or the heating zones 131), in a length of the handle. Alternatively or additionally, the lights may produce a first colour, such as green, when it is determined that hand placement corresponds to a desired hand placement, and a second colour different from the first colour, such as red, otherwise, thus prompting the user to modify their hand placement. The thermal feedback may be indicative of one or more desired ordered hand placement sequences, to achieve a user’s desired treatment.In the example illustrated in Figure 25 and described above, the styler 1 comprises a hand placement sensor 34.However, alternatively or additionally, in a variant, the styler 1 is configured to use each of the individual heating zones 131 on the handle 10 to sense and output, and in a corresponding variant of the method 100-3, at S1-3, data indicative of a hand placement on a respective individual heating zones 131. The controller 28 is configured to determine at S2- 3, based on a drop of the temperature of a heating zone 131 or based on an increase in the power output needed to maintain the heating zone 131 at a target temperature, whether a part of a hand of a user is in contact with the heating zone 131.In the variant of the fourth example of the method 100-3 of Figure 26, in S3-3 the controller 28 controls the thermalsomatosensory feedback generator to provide thermal feedback to the user by varying the heating of the plurality of independently controllable heating zones, based on the processed hand placement data, as described above in connection with Figure 25. As already stated, in all the examples described above, the temperature or the power output of the at least one heater electrode 13 is capped to a target temperature comprised between 35°C and 40°C, to avoid the hand of the user being burnt. STYLING PERFORMANCE AND FRUSTRATION PREDICTOR Users often have an expected result for the styling of their hair. When the styling result does not correspond to the expected result, the discrepancy generates user’s frustration. The user’s frustration leads to user’s behaviours, such as a tighter grip on the hair, which in turn provoke damage to the hair.Styling Performance and Frustration Predictor - CircuitryFigure 27 is a simplified block diagram of control circuitry 15 that controls the operation of the hair styler device 1 shown in Figure 1a. The control circuitry 15 of Figure 27 is similar to that of Figure 2 and the elements in common will not be described in detail, for the sake of conciseness. In the example of Figure 27, the hair styler 1 includes a hand sensor 34 configured to measure the placement of the hand of the user during the treatment. The hand sensor 34 comprises at least one of resistive and / or capacitive means to measure the placement of the hand of the user on an outside casework (of the moveable arms 4a and 4b) of the apparatus. In the example of Figure 27, the hair styler 1 includes a timer 35 configured to measure time elapsed while attempting to achieve the desired treatment. In Figure 27, the hair styler 1 includes an optional hair diagnostic sensor 33 configured to output data indicative of diagnostic information about the hair being styled or dried. The diagnostic information comprises at least one of: a levelof moisture in the hair, a humidity ambient to the hair being styled or dried, a temperature ambient to the hair beingstyled or dried, a geographic location of the hair being styled or dried.Styling Performance and Frustration Predictor - Operation based on different input streams of dataFigure 28 shows a flow chart illustrating an example method 100-4 of operation of the apparatus, according to the disclosure. In the method 100-4, the apparatus is manipulable by a user to perform a desired treatment on the hair ofthe user. In the method 100-4 of Figure 28, at S1-4, sensors already described in the present disclosure sense andoutput sensor data indicative of operational parameters on how the apparatus is operated by the user during the treatment. At S2-4, the microcontroller 28 processes the sensor data to predict the desired treatment which the user is trying to achieve and / or processes the sensor data to calculate a frustration score, the frustration score being indicative of a level of frustration of the user while attempting to achieve the desired treatment. At S3-4, the microcontroller 28 individually controls the temperature or the power output of the one or more heating zones of the plurality of individually controllable heating zones, based on the predicted desired treatment and / or on the calculated frustration score, to help the user to achieve the desired treatment and to avoid the hair being burnt.In the present disclosure, the desired “treatment” or “style” refers to a general, high-level type of hair styling, such asat least one of: curling, straightening, crimping or brushing. In a first example of the method 100-4 of Figure 28, at S1-4, the one or more motion sensors 31 sense and output sensor data and the grip sensor 32 senses and outputs sensor data. When the appliance is used for styling, the user performs specific movements and / or the user holds the appliance at certain angles, with the appliance having its moveable arms 4a and 4b in a closed position, depending on the style they are trying to achieve. Different styles require different movements, movement speeds, and angles, with the appliance having its moveable arms 4a and 4b in a closed position. In the first example, the microcontroller 28 uses the sensor data from the motion sensors 31 and the grip sensor 32 to predict the attempted style (i.e., is the user trying to curl, straighten, crimp, etc.). At S2-4, the controller 28 processes the sensor data from the sensors 31 and the sensor 32 to predict the desired treatment which the user is trying to achieve. Additionally, optionally, in some further examples of the method 100-4 of Figure 28, at S1-4, the hand sensor 34 also senses and outputs sensor data. When the appliance is used for styling, the user places their hand at specific points depending on the style they are trying to achieve. Different styles require different hand placement. The controller, at S2-4, further processes the sensor data from the hand sensor 34 to predict the desired treatment which the user is trying to achieve, giving a better indication of the style being attempted. Additionally, optionally, in some further examples of the method 100-4 of Figure 28, at S2-4, the controller is further configured to predict the desired treatment which the user is trying to achieve based on time data, such as time of day (e.g., the user curls their hair in the morning and straightens their hair in the evening), day of the week (e.g., the usercurls their hair on Saturdays), historical data from previous styling sessions. Additionally, optionally, in some furtherexamples of the method 100-4 of Figure 28, at S2-4, the controller is further configured to predict the desired treatmentwhich the user is trying to achieve based on hair type data (this can be input by the user on the user interface 11).In some examples, as already stated, the user interface 11 allows the user to specify the desired treatment to be performed on their hair. In such examples, at S2-4, the controller 28 is further configured to predict the desiredtreatment which the user is trying to achieve based on the desired treatment specified by the user. Additionally oralternatively, as already stated, the styler may be configured to receive user input information, such as information about the desired treatment, from the external processing device, and the controller may further be configured to predict the desired treatment which the user is trying to achieve based on such received user input information about the desired treatment.In all of the cases disclosed above, after the style is predicted at S2-4, the controller 28 controls at S3-4 the heater(e.g., a heater plate, as explained in greater detail below, or the individually controllable heating zones already described) to help the user to promote their hair health (such as by avoiding the hair being burnt) and / or to help the user to more accurately achieve the desired style. In some examples, the controller is configured to control a temperature or a power output of the one or more heating zones by capping an increase in the temperature or the power output of the one or more heating zones of the pluralityof controllable heating zones, based on the predicted desired treatment score, to avoid the hair being burnt. Additionallyor alternatively, the controller is configured to control a temperature or a power output of the one or more heating zones by setting a target temperature or power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the predicted desired treatment, to help the user to achieve the desired treatment. The controller is for instance configured to control the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones so as to enable a better drying or styling of the hair which is loaded in the apparatus.For example, the controller 28 may determine at S2-4 that the styler moves slower and then may determine that thedesired treatment is “curling”. At S3-4, the controller 23 may lower the amount of heat injected into the hair, while curling, to help preserve hair health and / or achieve a shinier, longer lasting styler.Additionally or alternatively to the first example described above, in a second example of the method 100-4 of Figure28, at S1-4, the timer 35 measures and outputs data about the time elapsed while the user is attempting to achieve the desired treatment, such as the curling, straightening, crimping or brushing of the hair. At S2-4, the controller 28 processes the sensor data from the timer 35 to calculate the frustration score from the measured time elapsed while attempting to achieve the desired treatment, as the time spent by the user while trying to style their hair is indicative of how frustrated the user may be. For example, the longer the time, the more frustrated the user. As a non-limiting example, the frustration score may be a real number, e.g., between 0 and 1, wherein a score of 0 is indicative of theuser being “very happy” and a score of 1 is indicative of the user being “very frustrated” (or vice versa).Additionally, optionally, in some further examples of the method 100-4 of Figure 28, at S1-4, the grip sensor 32 sensesand outputs data indicative of the measured pressure between movable arms of the apparatus. At S2-4, the controller is further configured to process the data from the grip sensor 32 and to calculate the frustration score based on the processed data from the grip sensor. The pressure applied to the moveable arms 4a and 4b may be indicative of the frustration of the user while trying to style their hair. For example, the tighter the grip on the hair, the more frustrated the user. As explained below, other behaviours may be indicative of frustration.Additionally, optionally, in some further examples of the method 100-4 of Figure 28, at S1-4, the motion sensors 31sense and output data indicative of speed of the determined movements of the apparatus. At S2-4, the controller 28 is further configured to process the data from the motion sensors 31 and to calculate the frustration score based on the processed data from the motion sensors 31. For example, rapid movements on the hair are indicative of frustration. Behaviours showing frustration and associated with the speed may include rapid rotations, rapid passes on one tressof hair, rapid shaking of the styler, the styler is still and / or stationary during a prolonged duration (i.e., total absence ofspeed in that latter case).Additionally, optionally, in some further examples of the method 100-4 of Figure 28, at S2-4, the controller is furtherconfigured to calculate the frustration score based on data about power output of the apparatus. For example, the greater the power output, the greater the frustration. As already stated, the controller 28 comprises means to measure the power demand. In a preferred example, the microcontroller 28 determines a power demand of the apparatus, based on a temperature of the plurality of independently controllable heating zones or based on the power output needed to maintain each heating zone of the plurality of heating zones at a target temperature.Other optional inputs can include data about the desired treatment, as the greater the divergence from the expectedstyle, the greater the frustration. In all of the cases disclosed above, after the frustration score is calculated at S2-4, the controller 28 controls at S3-4 the heater (e.g., a heater plate, as explained in greater detail below, or the individually controllable heating zones already described) to help the user to promote their hair health (such as by avoiding the hair being burnt) and / or to help the user to more accurately achieve the desired style. In some examples, the controller is configured to control a temperature or a power output of the one or more heating zones by capping an increase in the temperature or the power output of the one or more heating zones of the pluralityof controllable heating zones, based on the calculated frustration score, to avoid the hair being burnt, as a frustrateduser is more likely to burn their hair. Additionally or alternatively, the controller is configured to control a temperature or a power output of the one or more heating zones by setting a target temperature or power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the calculated frustration score, to help the user to achieve the desired treatment, as a frustrated user is less likely to perform a desired styling. The controller is for instance configured to control the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones so as to enable a better drying or styling of the hair which is loaded in the apparatus.The step S2-4 of method 100-4 may further comprise a step where the controller 28 determines whether the calculatedfrustration score is greater than a threshold value. The threshold value may correspond to a critical frustration, for example 0.5 if the score is between 0 and 1.If it is determined at S2-4 that the calculated frustration score is greater than a threshold value, then the controller isconfigured to control the apparatus so that in S3-4, the apparatus: outputs one or more feedback messages for the user to lower the user’s frustration, and / or inhibits the output of feedback messages which are likely to increase the user’s frustration. The feedback messages are output on the user interface 11 already described. The feedback messages may comprise visual messages and / or audible messages. The one or more feedback messages to lower the user’s frustration may comprise instructions to help the user toachieve the desired treatment (such as “slow down” or “rotate styler” as non-limiting examples) and / or written messageof encouragement and / or a calming music, as non-limiting examples). Inhibiting the output of feedback messages which are likely to increase the user’s frustration may comprise inhibiting the output of messages irrelevant to and / or out-of-synchrony with the treatment (such as “are you happy with yourtreatment?” when the frustration score is greater than the threshold value, for instant), as non-limiting examples.Alternatively or additionally, if it is determined at S2-4 that the calculated frustration score is greater than a thresholdvalue, then the controller may be configured to control a target temperature or power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to help the user to achieve the desired treatment and / or to avoid the hair being burnt, as already described. In another example embodiment, the sensors of the apparatus are for sensing and outputting sensor data indicative of operational parameters on how the apparatus is operated by the user during the treatment. In this embodiment, the sensor data includes data indicative of a time elapsed while attempting to achieve the desired treatment and / or data indicative of a pressure between movable arms of the apparatus. In this embodiment, the controller is configured to process the sensor data to calculate a frustration score based on the time elapsed while attempting to achieve the desired treatment and / or the pressure between movable arms of the apparatus. In this embodiment, the controller is configured to individually control the temperature or the power output of the one or more heating zones of the plurality of individually controllable heating zones, based on the calculated frustration score, to help the user to achieve the desired treatment and to avoid the hair being burnt. Alternatively or additionally, in this embodiment, the controller is configured to output one or more feedback messages for the user to lower the user’s frustration, and / or inhibit the output of feedback messages which are likely to increase the user’s frustration, based on the calculated frustration score, as already described. In the examples described above, the controller is configured to predict the desired treatment and / or to calculate the frustration score based on a set of deterministic rules. As described above, for the prediction of the desired treatment, the set of deterministic rules may be mainly based on data from the one or more motion sensors 31 and the grip sensor 32, optionally based on data from the hand sensor, time data and / or hair type data. As described above, for the calculation of the frustration score, the set of deterministic rules may be mainly based on data from the timer 35 and / or the grip sensor 32, as a longer time spent styling is likely to frustrate the user and / or a tighter grip on the hair is indicative of frustration. A combination of the data may be beneficial in the calculation, as a slow increase of the grip is not necessarily indicative of frustration, whereas a rapid increase in the grip is more likely an indication of the frustration of the user. Optionally the set of deterministic rules, as already explained, may be based on data from the motion sensors 31, about power output or the desired style. Alternatively or additionally, the controller is configured to predict the desired treatment and / or to calculate the frustration score based data for a trained artificial intelligence algorithm stored in a memory of the apparatus. As described in more detail below, the artificial intelligence algorithm may comprise a trained convolutional neural network and / or modular neural network and / or random forest and / or K-Nearest Neighbours. Generating the trained machine learning algorithmFigure 29 shows a flow chart illustrating an example method 200-4 according to the disclosure.The method 200-4 is for generating a trained machine learning algorithm.In one example, the trained algorithm is a trained frustration calculator configured to calculate a frustration score, the frustration score being indicative of a level of frustration of a user while attempting to achieve a desired treatment. In another example, the trained algorithm is a trained desired treatment predictor configured to predict a desired treatment which a user is trying to achieve.In Figure 29, the method 200-4 comprises:obtaining, at S21-4, a plurality of annotated training streams of data; and training, at S22-4, the algorithm by applying the algorithm to the obtained training streams of data. The learning process is typically computationally intensive and may involve large volumes of training data.As explained in more detail below, the machine learning step S22-4 involves inferring the frustration score or thedesired treatment, based on the training data, and encoding the determined frustration score or the desired treatment in the form of the trained algorithm. The training data are annotated. In other words, during the training and in the streams of data, the state of frustration of the user or the desired treatment are known.As such, in the method 200-4 of Figure 29, in the one example, the annotation indicates a level of frustration of theuser, associated with each training stream of data. In the other example, the annotation indicates a desired treatment which a user is trying to achieve, associated with each training stream of data. A domain specialist may manually annotate the streams of data with ground truth annotation corresponding to the level of frustration or the desired treatment, during the training.In the method 200-4 of Figure 29, in the one example, for a plurality of different levels of frustration, the plurality ofannotated training streams of data comprise: a training stream of data corresponding to a time elapsed while attempting to achieve the desired treatment and / or a training stream of data corresponding to a pressure between movable arms of the apparatus. For example, the machine learning algorithm may learn that a longer time spent styling frustrates the user and / or a tighter grip on the hair is indicative of frustration. A combination of the data may be beneficial in the calculation, as the machine learning can learn that a slow increase of the grip is not necessarily indicative of frustration, whereas a rapidincrease in the grip is more likely an indication of the frustration of the user.In the method 200-4 of Figure 29, in the other example, for a plurality of desired treatments (such as such as at leastone of curling, straightening, crimping or brushing), the plurality of annotated training streams of data comprise: a training stream of data corresponding to motion sensors indicative of amplitudes of movements of the apparatus, and a training stream of data corresponding to a grip sensor indicative of an open or closed position between movable arms of the apparatus. For example, the machine learning algorithm may learn that, for each treatment, the user performs specific movements and / or the user holds the appliance at certain angles, with the appliance having its moveable arms 4a and 4b in a closed position, depending on the style they are trying to achieve.Training at S22-4 the machine learning algorithm comprises training the machine learning algorithm to minimise a lossbetween the annotation associated with each training stream of data and a prediction (of a level of frustration of the user or a desired treatment) by the machine learning algorithm. The loss may be a similarity metric of Lp-norm, p being an integer greater or equal to 1, such as an average absolute deviation or a least mean square distance from the prediction (of the level of frustration of the user or the desired treatment) as determined by the machine learning algorithm during the training to the known annotation (the known level of frustration or the known desired treatment). Other ways of calculating the loss are envisaged. Referring back to Figure 29, the trained algorithm is built by its application to the training data. Any suitable machine learning algorithm may be used. For example, approaches based on a convolutional neural network and / or modular neural network and / or random forest and / or K-Nearest Neighbours may be used. As explained above, the trained frustration calculator is primarily trained to calculate the frustration score based on data corresponding to the time elapsed while attempting to achieve the desired treatment and / or data corresponding to the pressure between the movable arms of the apparatus. However, additional, optional training streams of data may be fed to the frustration calculator during training, such as: a training stream of data indicative of speed of the determined movements of the apparatus; and / or a stream of data indicative of the desired treatment. Figure 30 shows a non-limiting example architecture of a frustration calculator according to the disclosure. The frustration calculator of Figure 30 is generated based on the training data obtained at S21-4. In Figure 30, the training streams of data comprise: a training stream of data corresponding to a time elapsed while attempting to achieve the desired treatment (stream “Time Styling”), a training stream of data corresponding to a pressure between movable arms of the apparatus (stream “Grip Pressure”), a training stream of data indicative of speed of the determined movements of the apparatus (stream “User Speed”), a stream of data indicative of the desired treatment (stream “Predicted Style”). The stream “Predicted Style” may correspond to an actual prediction by the treatment predictor already described and / or correspond to an input by the user on the user interface, as the machine learning algorithm learns that when the styling result does not correspond to the expected result, the discrepancy generates user’s frustration. In the non-limiting example of Figure 30, the example frustration calculator comprises one or more layers: an appliance input layer 101, such that the input layer 101 ∈ ℝ^, each dimension of the appliance input layer101 corresponding to a training stream of data; ahidden layer 102, such that the hidden layer 102 ∈ ℝ^; andan output layer 103 such that the output layer 104 ∈ ℝ^, the dimension of the output layer 103 correspondingto the calculated frustration score. Other configurations with other layers may also be envisaged, and other architectures are also envisaged for the machine learning algorithm. For example, deeper architectures may be envisaged and / or an architecture of the same shape as the architecture described above that would generate an output layer 103 with sizes different from those already discussed may be envisaged. For example, as explained above, the trained desired treatment predictor is primarily trained to predict the treatment based on data corresponding to amplitudes of movements of the apparatus and data corresponding to an open or closed position between movable arms of the apparatus. However, additional, optional training streams of data may be fed to the desired treatment predictor during training, such as: a training streams of data from the hand sensor, time data and / or hair type data.It should be understood that an appliance may have both a trained frustration calculator and a trained treatmentpredictor. Computer system and hair styling appliance A computer system (not shown in the Figures) may execute the deep learning algorithm to generate the trained algorithm to be stored on the memory 30 of the hair styling appliance. The computer system may communicate and interact with multiple such hair styling appliances. The computer system may conventionally comprise a memory, a processor and a communications interface. The computer system may be configured to communicate with one or more hair styling appliances, via the communications interface and a link (e.g. Wi-Fi connectivity, but other types of connectivity may be envisaged). The memory of the computer system is configured to store data, for example for use by the processor. In some examples the data stored on the memory may comprise the training data and / or the deep learning algorithm. In some examples, the training data may correspond to actual observed data streams on the hair styling appliance, or the training data may be generated, for example in a laboratory. The training may be performed at the computer system separate, optionally remote, from the hair styling appliance. However, if sufficient processing power is available locally then the deep learning could be performed (at least partly) by the microprocessor 29 of the hair styling appliance. The trained algorithm is arranged to produce the calculation of the frustration score and / or the prediction of the treatment more easily, after it is stored in the memory 30 of the hair styling appliance, even though the process 200-4 for generating the trained algorithm from the training data may be computationally intensive. After it is configured, the hair styling appliance may provide calculation of a frustration score and / or prediction of a desired treatment, by applying the learned algorithm during use of the hair styling appliance, using the same input data streams as during the training. Hair styling appliance manufactureAs illustrated in Figure 31, a method 300-4 of producing a hair styling appliance configured to calculate a frustrationscore and / or predict a desired treatment comprises: obtaining, at S31-4, a trained algorithm generated by the method 200-4 according to any aspects of thedisclosure; and storing, at S32-4, the obtained classifier in the memory 30 of the hair styling appliance. The trained algorithm may be generated and stored using any suitable representation, for example as a data description comprising data elements specifying calculation and / or prediction conditions and their outputs. Such a data description could be encoded e.g. using XML or using a bespoke binary representation. The data description is then interpreted by the microprocessor 29 running on the appliance when applying the trained algorithm. Alternatively, the deep learning algorithm may generate the calculator and / or the predictor directly as executable code (e.g. machine code, virtual machine byte code or interpretable script). This may be in the form of a code routine that the appliance can invoke to apply the calculator and / or the predictor. The appliance may be connected temporarily to the computer system to transfer the generated calculator and / or predictor (e.g. as a data file or executable code) or transfer may occur using a storage medium (e.g. memory card). In a preferred approach, the calculator and / or the predictor is transferred to the appliance from the computer system over the communications link (this could include transmission over the Internet from a central location of the computer system to a local network where the appliance is located using the communications circuitry 27, e.g., via a mobile phone connected to the appliance via the Bluetooth, Wi-Fi and / or 3GPP communication protocols). Thanks to the communications circuitry 27, the calculator and / or the predictor could be installed as part of a firmware update of device software, or independently. Installation of the calculator and / or the predictor may be performed once (e.g. at time of manufacture or installation) or repeatedly (e.g. as a regular update). The latter approach can allow the calculator and / or the predictor performance of the calculator and / or the predictor to be improved over time, as new training data become available. REMOTE CONTROL STYLER Users sometimes need to move from a seated position while styling, e.g., to switch on / off an external device and / or to command the external device, which can provoke damage to the hair.Remote control styler - OverviewIn this example, hair styler 1 may be as illustrated in Figure 1a, in Figure 21 or in Figure 27 already described (as non- limiting examples), with corresponding circuitry as represented in Figure 2 or Figure 22 already described. The elements in common are not described in detail, for the sake of conciseness. In an example where the hair styler 1 is as illustrated in Figure 1a already described, the circuitry also comprises a hand placement sensor (not shown in Figure 2) configured to measure the placement of the hand of the user during the treatment. As already described in the context of the disclosure, the hand placement sensor comprises at least one of resistive and / or capacitive means to measure the placement of the hand of the user on an outside casework (of the moveable arms 4a and 4b) of the styler 1. As already stated, the control circuitry includes communications circuitry 27 to allow the device to communicate with an external processing device, remote from the styler. As already stated, in some examples, the external processing device comprises a smartphone or a smartwatch. Alternatively or additionally, the external processing device comprises at least part of a domotic system. The domotic system may comprise at least one of: home lights, home heating, home entertainment, such as a television and / or a sound system, and / or a home appliance, such as a coffee machine and / or a refrigerator. Alternatively or additionally, the external processing device comprises a server remote from the apparatus. The communications circuitry 27 may use, for example, Bluetooth, Wi-Fi and / or 3GPP communication protocols to communicate with the external processing device. A user interface may be provided on the external processing device, such that the user may input user input information.Remote control styler - CommandFigure 32 shows a flow chart illustrating an example method 100-5 of operation of the apparatus, according to thedisclosure. In the method 100-5, the apparatus is manipulable by a user to perform a desired treatment on the hair ofthe user, such as drying and / or styling of the hair of the user. In the method 100-5 of Figure 32, at S1-5, one or moresensors already described in the present disclosure sense and output sensor data indicative of one or more operatingparameters of the styler during use. At S1-5 the sensor data includes data indicative of how the apparatus is movedduring use and / or data indicative of an open or closed configuration of movable arms of the apparatus.At S2-5, the microcontroller 28 processes the sensor data. At S2-5 the sensor data is processed to determine whetherthe way the styler is operated during use corresponds to an on / off command for the external processing device and / ora control command for controlling editing and / or playout of media on the external device. If it is determined at S2-5 thatthe way the styler is operated during use corresponds to an on / off command and / or a control command, the method100-5 moves to S3-5. At S3-5, the microcontroller 28 controls the communication circuitry 27 to provide to the externalprocessing device the on / off command and / or the control command. In the method 100-5, if at S2-5 it is determinedthat the way the styler is operated during use does not correspond to an on / off command and / or a control command,the method 100-5 moves back to S1-5.In the present disclosure, the on / off command for the external processing device may be configured to cause the external processing device to switch on or to switch off. In the present disclosure, when an application is running on the external processing device, the control command may cause the application to perform an action other than providing a feedback message about the drying and / or styling of the hair of the user. In some examples, the communication circuitry 27 is configured to communicate with an external processing device comprising a video and / or audio application running on the external processing device, as explained in greater detail below.In a first example of the method 100-5 of Figure 32, the video and / or audio application running on the externalprocessing device may be a video content creation application. In such an example, the control command for the video content creation application causes the application to perform a video editing action. The first example of the method100-5 of Figure 32 enables the user to easily edit media on the external device, such as recording certain clips for thevideo content creation application, without moving from a seated position while styling, without letting go of the styler, and without needing to access the remote external processing device. This reduces the risk of the hair being damaged during styling. In such a first example, the controller 28 is configured to, at S2-5, determine whether the moveable arms of the apparatus are in the closed position for a time period which is greater than a threshold value, such as three seconds (other durations are envisaged).If it is determined at S2-5 that the moveable arms of the apparatus are in the closed position for a time period which isgreater than the threshold value, then at S3-5 the controller 28 is configured to provide the control command to theexternal processing device to cause the application to record as a clip the whole video captured when the movable arms are in the closed position, such that all the movements helping for the drying and / or styling hair are recorded as clips by the video content creation application.Alternatively or additionally, in such a first example, the controller 28 is configured to, at S2-5, determine whether themoveable arms of the apparatus are closed, by the user, at least twice at a frequency which is greater than a threshold value, such as twice in a second (other frequencies are envisaged).If it is determined at S2-5 that the moveable arms of the apparatus are closed, by the user, at least twice at a frequencywhich is greater than the threshold value, then at S3-5 the controller 28 is configured to provide the control commandto the external processing device to cause the application to record as a clip the video captured from the moment the movable arms are in the closed position for the second time until the moment it is determined again that the moveable arms of the apparatus are closed, by the user, at least twice at a frequency which is greater than the threshold value.In the first example of the method 100-5 of Figure 32, the user interface associated with the user on the externalprocessing device, which was already described above, may be configured to enable the user to at least one of: add a musical background, speed up or slow down clips, over dub clips, remove clips, add filters to clips, render clips, and upload clips to desired social medias. The clips represent one or more desired sequences to achieve a desired hair treatment.In a second example of the method 100-5 of Figure 32, the video and / or audio application running on the externalprocessing device is a video and / or audio playing application. The second example of the method 100-5 of Figure 32enables the user to easily playout media on the external device, without moving from a seated position while styling, without letting go of the styler, and without needing to access the remote external processing device. This reduces the risk of the hair being damaged during styling. In such a second example, the control command for the video and / or audio playing application causes the application to perform a remote-control action comprising at least one of: video and / or audio track selection and / or skipping; video and / or audio track fast forwarding or fast rewinding; video and / or audio track modifying the volume up or down.In the second example of the method 100-5 of Figure 32, at S2-5, the controller 28 determines whether the moveablearms of the styler are in the open configuration and swiped in a given direction, such as towards the right, the left, upwards or downwards, by the user, at a speed which is greater than a threshold value.If it is determined at S2-5 that the moveable arms of the styler are in the open configuration and swiped in the givendirection at a speed which is greater than the threshold value, then at S3-5 the controller is configured to provide thecontrol command to the external processing device to cause the application to perform a remote-control action. In the second example, e.g.,: a rapid swipe towards the right corresponds to a forward track skipping remote-control action, a rapid swipe towards the left corresponds to a backward track skipping remote-control action; a rapid swipe upwards corresponds to modifying the volume up remote-control action; a rapid swipe downwards corresponds to modifying the volume down remote-control action.In a third example of the method 100-5 of Figure 32, the video and / or audio application running on the externalprocessing device is a drying and / or styling training tutorial and / or a video game. The third example of the method 100-5 of Figure 32 enables the user to easily playout media, such as a position of a virtual styler in a training tutorial and / ora position of a virtual character of a video game, on the external device. This can be used to teach users how to hold and move the styler to achieve looks and improve dexterity with the styler, therefore minimising the risk of damage tothe hair during a treatment. In such a third example of the method 100-5 of Figure 32, at S2-5 the controller isconfigured to determine whether the moveable arms of the apparatus are swiped in a given direction, such as towards the right or the left or upwards or downwards, by the user.If it is determined at S2-5 that the controller is configured to determine whether the moveable arms of the apparatusare swiped in a given direction, then at S3-5 the controller is configured to provide the control command to the externalprocessing device to cause the application to perform a remote-control action. In the third example, the remote-control action comprises moving, on a display of the external device, a virtual character and / or virtual styler in a direction corresponding to the determined direction of the swipe.In an example of the method 100-5 of Figure 32, the external processing device comprises at least part of a domoticsystem as already described. In such an example, the method 100-5 of Figure 32 enables the user to command theexternal device which is part of a domotic system, without moving from a seated position while styling, without lettinggo of the styler, and without needing to access the remote external processing device. This reduces the risk of the hairbeing damaged during styling. In such an example, at S2-5 the controller 28 is configured to process the sensor datato determine whether the way the apparatus is operated during use corresponds to an on / off command for the external processing device.If it is determined at S2-5 that the way the apparatus is operated during use corresponds to an on / off command, thenat S3-5 the controller 28 is configured to send the on / off command to switch on or off the domotic system.Alternatively or additionally, at S2-5 the controller 28 is configured to process the sensor data to determine whetherthe way the apparatus is operated during use corresponds to a control command for the external processing device.If it is determined at S2-5 that the way the apparatus is operated during use corresponds to a control command, thenat S3-5 the controller 28 is configured to send the control command to control operation of the domotic system, basedon the way the apparatus is moved during use and / or on whether the movable arms of the apparatus are in the open or closed configuration. In this example, e.g.,: a rapid swipe towards the right corresponds to brightening up the lighting of the domotic system, and / or a rapid swipe towards the left corresponds to dimming down the lighting of the domotic system; and / or a rapid swipe upwards corresponds to modifying the volume up of the television; and / or a rapid swipe downwards corresponds to modifying the volume down of the television; and / or a push on a button on the interface 11 corresponding a start of the coffee machine, etc. Alternatively or additionally to the four examples described above, in cases where the user interface 11 is configured to allow the user to specify the on / off command for the external processing device and / or the control command for the application running on the external processing device, the controller may be configured to further determine, at S2-5, the on / off command and / or the control command to be sent to the external processing device based on the input specified by the user.Figure 33 shows a flow chart illustrating an example method 200-5 of operation of the apparatus, according to thedisclosure. The method 200-5 is performed by the styler for drying or styling hair, the styler comprising the user interfacefor allowing the user to specify an on / off command for the external processing device and / or a control command for controlling editing and / or playout of media on the external device, as described above. At S10-5, the controller 28determines whether a command is specified on the user interface, and, if it is, at S20-5 the controller 28 controls thecommunication circuitry already described to provide to the external processing device the on / off command and / or the control command. IDLE MODE Using straighteners or drying tools consumes a significant amount of electrical energy which is costly both for the environment and for the consumer. However, during around 50% of the on-time, the appliance is actually laid down or otherwise not in use.Idle mode - OperationFigure 34 shows a flow chart illustrating an example method 100-6 of operation of the styler, according to the disclosure. In the method 100-6, an appliance that is manipulable by a user comprises a heater for heating hair during drying and / or styling. In the method 100-6, the styler comprises sensors for sensing and outputting sensor data indicative of operational parameters of the appliance during drying and / or styling of the hair. The sensor data includes motion data indicative of how the appliance is being moved by translation along three spatial dimensions and / or by rotation around the three spatial dimensions, the motion data being thus indicative of six motion parameters. In the method 100-6 of Figure 34, at S0-6, the heater is on and is heating to a styling and / or drying operating target temperature, and the method 100-6 moves to S1-6. At S1-6, one or more sensors, already described in the present disclosure, sense and output motion data indicative of how the appliance is being moved by translation along three spatial dimensions (such as mutually orthogonal x, y and z directions) and / or by rotation around the three spatialdimensions during use. At S2-6, the microcontroller 28 processes the motion data to determine whether the motiondata are indicative, for at least five motion parameters of the six motion parameters, of a status of the appliance comprising at least one of: the appliance being stationary, the appliance having had one or more sensor read-out noise peaks, the appliance being manipulated by the user, and / or the appliance being transported.If it is determined at S2-6 that the motion data are indicative of a status other than the appliance being manipulated bythe user (such as the appliance being stationary, the appliance having had one or more sensor read-out noise peaks,or such as the appliance is being transported), the method 100-6 moves to S3-6.At S3-6, the microcontroller 28 controls the heater to place the heater in an idle status. In the idle status the heater is still on, but the heating of the heater is reduced to a lower, standby temperature (still above the ambient temperature). For example, at S3-6, the controller controls the heater by lowering a power usage of the heater in order to save energy and / or sets a target temperature of the heater to a standby temperature which corresponds to a temperature which islower than the styling and / or drying operating target temperature, the standby temperature still being above an ambienttemperature.In the method 100-6, if at S2-6 it is determined that the user is manipulating the appliance, the method 100-6 movesback to S0-6. Optionally, at S2-6 it is determined whether the motion data are indicative, for the at least five motionparameters of the six motion parameters, of the status of the appliance if the motion data is indicative of such a statusduring at least a predetermined period of time. In some examples the predetermined period of time is factory-defined.In a non-limiting example, the predetermined period of time may be equal to a duration such as 3 seconds. Thepredetermined period of time corresponds to an additional precaution to prevent placing the appliance in the idle statustoo often.After S3-6, the method 100-6 moves to S4-6, where the controller determines whether the heater is in the idle statusfor a duration longer than a predetermined duration threshold. In some examples, the predetermined duration threshold may be factory-defined. In some examples, the predetermined duration threshold may be equal to a duration such as 5 minutes, but other durations are envisaged.If it is determined at S4-6 that the heater is in the idle status for a duration longer than the predetermined durationthreshold, then the method moves to S5-6. At S5-6, the controller switches off the heater. Alternatively or additionally,at S5-6 the controller indicates to the user, e.g., on the interface of the external processing device, a current switchedoff status of the heater.Alternatively or additionally, at S3-6 the controller indicates to the user, e.g., on the interface of the external processingdevice, a current idle status of the heater, or a countdown to placing the heater to such an idle status and / or a switch off status.If it is determined at S4-6 that the heater is in the idle status for a duration shorter than the predetermined durationthreshold, then the method moves back to S1-6.After S5-6, the method 100-6 moves to S6-6, where the controller determines whether:for at least five motion parameters of the six motion parameters, the motion data are indicative that the appliance is manipulated by the user, or the user specifies a command which activates the heater, for example manually or using a voice commandor any other method.If at S6-6 it is determined that the motion data are indicative that the appliance is manipulated by the user, or that theuser specifies a command which activates the heater, the method 100-6 moves back to S0-6 where the heater is in astyling and / or drying operating target temperature.If at S6-6 it is determined that the motion data are not indicative that the appliance is manipulated by the user, or thatthe user does not specify a command which activates the heater, the method 100-6 moves to S7-6 where the heaterstays off and is not heating. In the method 100-6, the controller may process the motion data based on a probabilistic model and / or a machine learning algorithm. For example, the probabilistic model may be based on statistical tests, such as conditionalprobabilities, such as ^(^^|^) = probability of hypothesis n being true (such as a given status of the appliance) giventhe motion data d.Alternatively or additionally, the machine learning algorithm may be based on at least one of a random forest algorithm,a Bayesian classification, a support vector machine, a K-nearest neighbour algorithm. Other algorithms are envisaged.Figure 35 shows a flow chart illustrating an example method 200-6 of operation of the apparatus, according to thedisclosure, e.g. to process the motion data. In the method 200-6, at S10-6 the processor 28 reads the motion dataindicative of a translation acceleration of the appliance along the three spatial dimensions and / or the sensor data indicative of the rotation around the three spatial dimensions. An example of a reading, by the microcontroller, of thetranslation acceleration along one spatial dimension (such as the x-, y- or z-axis), as a function of time, is schematicallyillustrated in Figure 36a. It should be understood that, although Figure 36a illustrates the acceleration along one dimension only for clarity, the microcontroller reads the acceleration along the three dimensions and the rotation around the three dimensions. An example of a reading, by the microcontroller, of the translation acceleration along the threespatial dimensions (such as the x-, y- and z-axes), as a function of time, is schematically illustrated in Figure 37a.At S20-6, the microprocessor 28 performs a transformation on the read motion data, for each one of the six motion parameters. In some examples, the performed transformation includes at least one of a Fourier Transform or a Lomb-Scargle Transform. An example of a result of a transformation of the translation acceleration illustrated in Figure 36a asperformed by the microcontroller using a Fourier Transform is schematically illustrated in Figure 36b.In some examples, the performed transformation includes a determination of a variance of the read motion data. An example of results of a transformation of the translation accelerations illustrated in Figure 37a as performed by the microcontroller by calculating the variance of the accelerations as a function of time is schematically illustrated in Figure 37b.After S10-6 and S20-6, each of the motion parameter is associated with one or more of:at least one maximum frequency; and / or at least one parameter indicative of a frequency power distribution, such as a mean frequency power distribution, a median frequency power distribution or a standard frequency power distribution; and / or at least one maximum acceleration and / or at least one maximum rotation amplitude; and / or at least one minimum acceleration and / or at least one minimum rotation amplitude; and / or at least one signal entropy; and / or at least one zero-crossing rate; and / or at least one autocorrelation.After S20-6, the method 200-6 moves to S30-6, where the controller determines the status of the appliance, based onthe motion data and / or the transformation. In a first example of the method 200-6, the controller determines the status of the appliance, based on the acceleration as illustrated in Figure 36a and / or based on the frequency and / or frequency distribution as illustrated in Figure 36b.In the first example of the method 200-6, at S30-6 the controller determines that the motion data are indicative that themovements of the appliance are caused by the manipulation by the user, when, for at least five motion parameters of the six motion parameters: the frequency distribution is above a first predetermined threshold; and / or the acceleration amplitude is below a second predetermined threshold.Alternatively or additionally, in the first example of the method 200-6, at S30-6 the controller determines that the motiondata are indicative that the appliance is in the stationary status, when, for at least five motion parameters of the six motion parameters, a frequency of the appliance having had one or more sensor read-out noise is below a third predetermined threshold.Alternatively or additionally, in the first example of the method 200-6, at S30-6 the controller determines that the motiondata are indicative that the appliance is being transported, when, for at least five motion parameters of the six motion parameters, the frequency power distribution comprises a peak greater than a fourth predetermined threshold.Alternatively or additionally, in the first example of the method 200-6, at S30-6 the controller determines that the motiondata are indicative that the appliance is being transported, when, for at least five motion parameters of the six motion parameters, the signal entropy is greater than a fifth predetermined threshold. Initially, the first, second, third, fourth and fifth predetermined thresholds are factory-defined. However, in an example, the fourth predetermined threshold and / or the fifth predetermined threshold are raised, if it is determined that the motion data are indicative that the appliance is being transported. Alternatively or additionally, in a second example of the method 200-6, the controller determines the status of the appliance, based on the acceleration as illustrated in Figure 37a and / or based on the variance as illustrated in Figure 37b.In the second example of the method 200-6, at S30-6 the controller determines that the motion data are indicative thatthe movements of the appliance are caused by the manipulation by the user, when, for at least five motion parameters of the six motion parameters the determined variance is above a sixth predetermined threshold T. Figure 37b only illustrates three variances for clarity, but six variances are considered. It should be understood that,according to an example of the disclosure, if it is determined that five of the six considered parameters are below thethreshold T, the styler is considered idle. The sixth predetermined threshold is initially factory-defined and / or updated as explained below. Alternatively or additionally, in a third example of the method 200-6, the controller determines the status of the appliance, based on probabilities.In the third example of the method 200-6, at S20-6 the microcontroller 28 determines:(i) a first probability ^(^^|^) that the motion data d are indicative of the appliance being manipulatedby the user, (ii) a second probability ^(^^|^) that the motion data d are indicative of the appliance beingtransported, (iii) a third probability ^(^^|^) that the motion data d are indicative of the appliance is stationary, theappliance having had one or more sensor read-out noise peaks. In the third example of the method 200-6, the sum of the first probability, the second probability and the third probability is equal to 1.In the third example of the method 200-6, at S20-6 the microcontroller 28 also determines a maximum between thefirst probability ^^, the second probability ^^and the third probability ^^.In the third example, if it is determined at S20-6 that the maximum is the first probability (i.e. it is more probable thatthe appliance is being manipulated by the user), in S30-6 the controller establishes that the appliance is manipulatedby the user.Alternatively or additionally, if it is determined at S20-6 that the maximum is the first probability, the sixth threshold Tis set at S30-6 to a predetermined value, such as 0.25 (other values are envisaged).In the third example, if it is determined at S20-6 that the maximum is the second probability (i.e. it is more probablethat the appliance is not used by the user but is being transported), in S30-6 the controller establishes that the applianceis being transported.Alternatively or additionally, if it is determined at S20-6 that the maximum is the second probability, the sixth thresholdT is set at S30-6 to a running variance of the motion data.In the third example, if it is determined at S20-6 that the maximum is the third probability (i.e. it is more probable thatthe appliance is stationary, the appliance having had one or more sensor read-out noise peaks), in S30-6 the controllerestablishes that the appliance is stationary. and / orAlternatively or additionally, if it is determined at S20-6 that the maximum is the third probability, the sixth threshold Tis set at S30-6 to a most recent value of the sixth threshold.Alternatively or additionally, in the third example of the method 200-6, if the maximum is undetermined at S20-6, atS30-6 the sixth threshold T is set to a predetermined value, such as 0.25 (other values are envisaged).Figure 37a also illustrates at 111-6 the at least predetermined period of time (such as 3 seconds), which translates astime 112 in Figure 37b. Alternatively or additionally the processor uses a trained machine learning algorithm. In one example, the trained algorithm is a trained status classifier configured to determine whether the motion data are indicative, for at least five motion parameters of the six motion parameters, of a status of the appliance comprising at least one of: the appliance being stationary, the appliance having had one or more sensor read-out noise peaks, the appliance being manipulated by the user, and / or the appliance being transported. During training, a plurality of annotated training streams of data is obtained, and the algorithm is trained by applying the algorithm to the obtained training streams of data. The learning process is typically computationally intensive and may involve large volumes of training data. As explained in more detail below, the machine learning involves inferring the status of the appliance, based on the training data, and encoding the determined status in the form of the trained algorithm. The training data are annotated. In other words, during the training and in the streams of data, the status of the appliance is known. As such, during the training, in the one example, the annotation indicates a status of the appliance, associated with each training stream of data. A domain specialist may manually annotate the streams of data with ground truth annotation corresponding to the status of the appliance, during the training. For example, the machine learning algorithm may learn that a certain type of motion data is indicative of: the appliance being stationary, the appliance having had one or more sensor read-out noise peaks, the appliance being manipulated by the user, and / or the appliance being transported. During the training, the plurality of annotated training streams of data comprises a plurality of training streams of data corresponding to motion sensors indicative of how the appliance is being moved by translation along three spatial dimensions and / or by rotation around the three spatial dimensions, the motion data being indicative of six motion parameters. Training the machine learning algorithm comprises training the machine learning algorithm to minimise a loss between the annotation associated with each training stream of data and a prediction (of a status of the appliance) by the machine learning algorithm. The loss may be a similarity metric of Lp-norm, p being an integer greater or equal to 1, such as an average absolute deviation or a least mean square distance from the prediction as determined by the machine learning algorithm during the training to the known annotation (the known status of the appliance). Other ways of calculating the loss are envisaged. The trained algorithm is built by its application to the training data. Any suitable machine learning algorithm may be used. For example, approaches based on a convolutional neural network and / or modular neural network and / or randomforest and / or K-Nearest Neighbours, a Bayesian classification, a support vector machine may be used.After it has been trained, the trained algorithm is arranged to produce the determination of the status of the appliance, after it is stored in a memory of the apparatus, even though the process for generating the trained algorithm from the training data may be computationally intensive. After it is configured, the processor may provide the status of the appliance based on the motion data, by applying the learned algorithm during use of the hair styling appliance, using the same input data streams as during the training. The idle mode may be implemented on any device, either on a buttonless styler (i.e. not comprising any button or any user interface) or in a styler which comprises a user interface to allow the user to input information about them to the device and / or for the device to output information to the user. As already described, the user interface of the apparatus may have a dial, button, slider or touch display for allowing the user to input information to the device. The user interface may be configured for allowing the user to specify e.g., a desired treatment to be performed on their hair. The user interface may have an indicator light, display, sound generator or haptic feedback generator for outputting information to the user. In this embodiment, the user interface also comprises a control button, slider or switch to enable the user to turn the device on or off; and an indicator light to show whether the power is on. The user interface of the apparatus may be configured to indicate to the user a current idle status and / or a switch off status of the heater, or a countdown to such a status. FIND MY STYLE Users sometimes perform the same styling on their hair, over and over again, which can provoke boredom in the user and / or lack of attention of the user, while styling, which in turn can provoke damage to the hair. Users often get their hair type from an in-depth, time-consuming quiz, for which, they often decide the wrong hair type due to misinterpretation of the questions and inconsistent answering. This provokes results which are disappointing if the style is not as expected, and frustration can in turn provoke damage to the hair.Find my style - OverviewIn this example, hair styler 1 may be as illustrated in Figure 1a, in Figure 21 or in Figure 27 already described (as non- limiting examples), with corresponding circuitry as represented in Figure 2 or Figure 22 already described. The elements in common are not described in detail, for the sake of conciseness. In an example where the hair styler 1 is as illustrated in Figure 1a already described, the circuitry also comprises a hand placement sensor (not shown in Figure 2) configured to measure the placement of the hand of the user during the treatment. As already described in the context of the disclosure, the hand placement sensor comprises at least one of resistive and / or capacitive means to measure the placement of the hand of the user on an outside casework (of the moveable arms 4a and 4b) of the styler 1. The control circuitry includes communications circuitry 27 to allow the device to communicate with an external processing device, remote from the styler. The external processing device may comprise a camera, configured to capture one or more images of the user’s hair and / or one or more images of the clothes and / or accessories of the user. A user interface may be provided on the external processing device, such that the user may input user input information. The user interface of the processing device may be configured to input information about the hair of the user and / or information about the clothes and / or accessories of the user an / or about a desired treatment.Find my style - CommandFigure 38 shows a flow chart illustrating an example method 100-7 of operation of the apparatus, according to the disclosure. In the method 100-7, the apparatus is manipulable by a user to perform a treatment on the hair of the user, such as drying and / or styling of the hair of the user. In the method 100-7 of Figure 38, at S1-7, one or more images of the user’s hair are captured by the camera of theexternal processing device and / or information about the hair of the user is input on the user interface of the externalprocessing device. The information about the hair of the user may be input using a questionnaire to be filled in by theuser and / or a stylist. In some examples, the memory of the apparatus may be configured to store the user inputinformation, so that the user does not have to input the information every time they use the styler. In some examples,the stored input information may be updated if, e.g., the user has a haircut, or gets their hair dyed.At S2-7, the communication circuitry 27 obtains the data associated with the information about the hair of the userwhich is input on the user interface and / or data associated with one or more images of a user’s hair. At S3-7, the microcontroller 28 processes the obtained data. At S3-7 the obtained data is processed to determine a hair type of the user (such as thin or thick, and / or straight or curly, as non-limiting examples) and a current hair styleof the user. In some examples, the determined hair style comprises information about at least one of: hair colour and / orhair length. At S4-7, the microcontroller 28 outputs one or more feedback messages for the user about one or more suggested treatments, based on the determined hair type and the current hair style of the user. The one or more suggested treatments are different from the determined current hair style. Alternatively or additionally, at S4-7 the microcontroller 28 outputs one or more suggestions on how to operate the appliance to obtain the one or more suggested treatments, based on the determined hair type and the current hair style of the user. In some examples, the one or more feedback messages for the user about the one or more suggested treatments and / or the one or more suggestions on how to operate the appliance are output on the user interface of the external processing device. In some examples, the one or more suggested treatments may be very different from the determined current hair style of the user, but still possible to achieve given the determined hair type. In some other examples, the one or more suggested treatments may be variations from the determined current hair style of the user, e.g., based on generally accepted and / or usual variations from a given hair style, but still possible to achieve given the determined hair type. In the disclosure, the one or more suggested treatments engage the attention and / or interest of the user, such that the user pays more attention during the styling of their hair, and hair damage is avoided. In some examples, the one or more suggestions on how to operate the appliance may comprise instructions such as recommended set temperatures for the heater, and / or recommended sequences for movements of the appliance during styling, to improve styling and / or avoid hair damage, based on the determined hair type and the current hair style of the user. Alternatively or additionally, at S4-7 the microcontroller 28 controls the heater to treat the hair of the user according to the one or more suggested treatments and / or the one or more suggestions of operation, to improve styling and / or avoid hair damage. In an optional step S5-7, the microprocessor may use means for outputting one or more generated images of the hair of the user after the one or more suggested treatments, based on the captured one or more images of the hair of the user. The generated images may be output on the user interface of the external processing device. For example the generated images may be displayed next to the captured images of the current hair style, for comparison. The outputting of the generated images allows the user to see the result of the suggested treatment, so that they can make an informed decision on the treatment that they would like to achieve. In some examples, the outputting to the one or more generated images may be performed in real-time, for example as the one or more suggested treatments are achieved and / or while the one or more suggestions on how to operate the appliance are implemented by the user and / or while the heater is controlled to treat the hair of the user according to the one or more suggested treatments and / or the one or more suggestions of operation. In some examples, the means for outputting the generated image may comprise a generative artificial intelligence configured to generate the images based on the one or more suggested treatments and / or the one or more suggestions on how to operate the appliance, which may be stored on a memory of the apparatus, such as the memory 30. In some examples, the data obtained at S2-7 by the communication circuitry may further comprise additional data associated with one or more captured images of the clothes and / or accessories of the user and / or with information about the clothes and / or accessories of the user. As non-limiting examples, the clothes and / or accessories comprise at least one of: earrings, necklace, glasses, neckline, clothes type, clothes colour, make-up choice, tattoos. In that embodiment, at S3-7 the microprocessor 28 processes the additional data. In that embodiment at S4-7 the microprocessor 28 outputs the one or more feedback messages for the user about the one or more suggested treatments and / or the one or more suggestions on how to operate the appliance, based on the additional data associated with the one or more images of and / or the information about the clothes and / or accessories. The one or more suggested treatments and / or the one or more suggestions may be based on generally accepted and / or usual associations of hair styles with the clothes and / or accessories of the user, but still possible to achieve given the determined hair type. Once again, the method of the disclosure enables to engage the attention and / or interest of the user, such that the user pays more attention during the styling of their hair, and hair damage is avoided. In some examples, the additional data is associated with the one or more images captured by the camera of theexternal processing device, and / or the additional data is associated with information input on the user interface of theexternal processing device. Additionally or alternatively, the user interface is configured to enable input, at S1-7, of information about a desired hair treatment by the user. In that embodiment, at S2-7 the information may be processed by the microcontroller 28 and at S3-7 the controller outputs the one or more feedback messages for the user about the one or more suggested treatments and / or the one or more suggestions on how to operate the appliance, also taking into account the input desired hair treatment. The one or more suggested treatments may be very different from the desired treatment, but still possible to achieve given the determined hair type. In some other examples, the one or more suggested treatments may be variations from the desired treatment, e.g., based on generally accepted and / or usual variations from the desired treatment, but still possible to achieve given the determined hair type. Alternatively or additionally, the controller processes information input on the user interface of the styler (such as information about the hair of the user, and / or information about the clothes and / or accessories of the user, and / or information about a desired hair treatment by the user) and the controller outputs the one or more feedback messages for the user about the one or more suggested treatments and / or the one or more suggestions on how to operate the appliance, based on the input on the appliance user interface. In some examples, the appliance user interface is configured to output the one or more feedback messages for the user about the one or more suggested treatments and / or the one or more suggestions on how to operate the appliance. TACTI-MOTION SENSE STYLER Buttons and other interactive components on styling devices are expensive. Buttons also take up space in the device. However, simply controlling the heating of the styling device remotely can be a fire hazard and therefore dangerous.Tacti-motion sense styler - Overview of Hair Styling DeviceFigure 39 illustrates a hand-held (portable) hair styler 1 (or hair styling appliance or apparatus in the present disclosure). The elements in common and which have already been described are not described again in detail, for the sake of conciseness. As can be appreciated from Figure 39, the hair styler 1 is buttonless. In the context of the disclosure, “buttonlessappliance” (e.g., the styler 1, including e.g., the outside casework of the moveable arms 4a and 4b) means that anoutside casework of the appliance does not have: any physical buttons (such as any control button or switch, e.g., to enable the user to turn the appliance on or off, slider etc.), and / or does not have any other interactive components (such as any indicator light, e.g., to show whether the power is on, etc.), and / or does not have any user interface, such as any dial, button or touch display, e.g., to allow the user to input information about them directly on the appliance, or for the appliance to output information to the user, or for the user to specify anycommand directly on the appliance (such as an on / off command).The hair styler is cheaper to design and manufacture. Figure 40 schematically illustrates that the hair styler comprises communication circuitry 27 configured to communicate with an external processing device (not shown) remote from the hair styler. As described in more detail in the below disclosure, the external processing device comprises a user interface for allowing the user to specify an on / off command for the buttonless hair styler. In Figure 40, the hair styler 1 includes a fingerprint sensor 35 configured to sense and output data about the fingerprint of the user which manipulates the styler 1.Tacti-motion sense styler - OperationFigure 41 shows a flow chart illustrating an example method 100-8 of operation of the styler, according to the disclosure. In the method 100-8, a buttonless appliance that is manipulable by a user comprises a heater for heating hair during drying and / or styling. The styler comprises communication circuitry configured to communicate with an external processing device remote from the apparatus, the external processing device comprising a user interface for allowing the user to specify an on / off command for the buttonless appliance. In the method 100-8 of Figure 41, at S1-8, one or more sensors already described in the present disclosure sense and output sensor data indicative of one or more operating parameters of the styler during use, and the communication circuitry 27 output data. At S2-8, the microcontroller 28 processes data from the communication circuitry 27 to determine whether the user has specified an on command, such as a command to heat the heater. If it is determined at S2-8 that that the user has specified an “on” command, the method 100-8 moves to S3-8. At S3-8, the microcontroller 28 processes the sensor data. At S3-8 the sensor data is processed to determine whether the buttonless appliance is manipulated by the user. Manipulation by the user may be based on at least one: detection of a change of an open or closed configuration between arms of the appliance, as measured by the grip sensor, and / or detection of a change in a pressure between the arms of the appliance and / or a pressure in a handle and / or a head of the appliance, as measured by the grip sensor; and / or detection of a manipulation movement of the appliance as detected by the motion sensors; and / or detection of skin contact with an outside casework of the appliance, as detected by the at least one of resistive and / or capacitive means. If it is determined at S3-8 that the buttonless appliance is not manipulated by the user, the method moves to S4-8. Optionally, at S3-8, the controller further processes data from the fingerprint sensor to determine whether the user is a user who is authorised to manipulate the appliance, and controls the heater of the buttonless appliance to prevent the heater from heating if it is determined that the user is not authorised to manipulate the appliance (such as a child),even if the appliance is manipulated by the user. Optionally, a child may need an authorisation by an adult before thechild may use the styler. In S4-8, the microcontroller 28 controls the heater of the buttonless appliance to prevent the heater from heating. The buttonless styler requires a remote connection and will only heat up when being manipulated by the user.In the method 100-8, if at S2-8 it is determined that the user has not specified an “on” command, the method 100-8moves back to S1-8.In the method 100-8, if at S3-8 it is determined that the user is manipulating the appliance, the method 100-8 movesback to S1-8. At S4-8, controlling the heater comprises at least one of: switching off the heater; and / or placing the heater in an idle status. In the idle status the heater is still on, but the heating of the heater is reduced to a lower, standby temperature(still above the ambient temperature). For example, at S4-8, the controller controls the heater by lowering a powerusage of the heater in order to save energy and / or sets a target temperature of the heater to a standby temperature which corresponds to a temperature which is lower than the styling and / or drying operating target temperature, thestandby temperature still being above an ambient temperature. Alternatively or additionally, at S4-8 the controllerindicates to the user, e.g., on the interface of the external processing device, a current switched off status of the heater.Alternatively or additionally, at S4-8 the controller indicates to the user, e.g., on the interface of the external processingdevice, a current idle status of the heater, or a countdown to placing the heater to such an idle status and / or a switch off status.Alternatively or additionally, at S4-8, the method 100-8 comprises the controller:determining whether the heater is in the idle status, and switching off the heater if it is determined that the heater is in the idle status for a duration longer than a predetermined duration threshold. In some examples, the predetermined duration threshold may be factory-defined. For example, the predetermined duration threshold may be equal to a duration such as 5 minutes. HAIR STYLER CONTROL ARRANGEMENT It is desirable for further improvements to hair styling appliances to be made. Aspects of the invention provide a hair drying and / or styling appliance comprising any or all of the following features:a first arm; a second arm; the first and second arms being mutually opposed and adapted for movement between anopen configuration in which a tress of hair can be positioned between the first and second arms and a closed configuration in which the tress of hair is sandwiched between the first arm and the second arm; a sensor configured to sense relative movement of the first arm and the second arm between said open configuration and said closed configuration; and a controller configured to: determine whether the appliance is in the open configuration or the closed configuration based on the sensed relative movement; determine a pull duration that the appliance is pulled along the tress of hair based on a duration that the appliance is determined to be in the closed configuration, and perform a control action based on the determined pull duration. One or both arms may include a heater for heating the hair when sandwiched between the first and second arms. In this case the information based on whether the appliance is in an open configuration or a closed configuration can beused to influence how the heaters are controlled. Calculating the pull duration and using it to perform a control actionof the appliance provides additional data on which a control algorithm can operate, for example by classifying the current operating mode. In particular, this allows the appliance to be controlled in a targeted manner with respect tothe hair that is being styled (for example, the length of the hair) and the behaviour of the user (for example, the speedat which a user pulls a tress of hair through the appliance). The control action may comprise displaying information to the user. The control action may comprise storing information in a memory of the appliance. This provides options for the appliance to learn behaviour about how the styler is used and to learn the characteristics of the hair being styled. The appliance may be configured to determine a velocity of the appliance as it is moved along the tress of hair. The appliance may be configured to determine a tress length based on the determined velocity and the determined pull duration. The control action may be based on the determined tress length. This advantageously combines information gathered from the appliance to calculate additional behaviours of how the appliance is used and the characteristics of the hair being styled. The controller may be configured to determine whether the determined pull duration is within a predefined range before performing the control action. This allows the appliance to ensure that the pull duration is neither too long nor too short before using this information to influence the behaviour of the styler or infer characteristics of the hair being styled. The control action may comprise controlling the power supplied to the heaters. This has the advantage of controlling the temperature of the heaters dynamically based on the pull duration, which may be determined by the length of a tress and how quickly a user moves the appliance along the tress. Controlling the power may include initially increasing the temperature of the heaters from a standby temperature to a start temperature, being higher than the standby temperature, when the controller determines that the appliance is in the closed configuration. Controlling the power may include maintaining the temperature of the heaters at the start temperature for a predetermined time. This advantageously delays heating up the roots of the hair (i.e. the hair near the scalp) further while the styler is presumed to be momentarily stationary on the root at the moment the appliance is closed. Controlling the power may further include increasing the temperature of the heaters during the pull from the start temperature to an end temperature, being higher than the start temperature. This provides a higher temperaturetowards the tip where the hair may be older and more heat resistant.Controlling the power may comprise increasing the power supplied to the heaters to gradually increase the temperature of the heaters during the pull at a rate based on the determined pull duration. The rate may be proportional to the determined pull duration. The rate may be linearly proportional to the determined pull duration. This can provide an advantageous mode of operation in which lower temperatures are applied toward the root and the heaters gradually heat up toward the tip of a tress. The controller may be further configured to determine an open duration during which the appliance has remained in the open configuration and is configured to reduce the temperature of the heaters to a standby temperature if the open duration is greater than a first threshold. This provides leniency in controlling the appliance such that, for example, if the user were to mistakenly open the appliance during a tress pull, it would not reduce the temperature of the heaters straight away. The controller may be further configured to switch off the heaters if the open duration is greater than a second threshold, being greater than the first threshold. This has the advantage of allowing the controller to infer that the appliance is no longer in use and switching off the heaters accordingly. The sensor may comprise at least one sensor selected from the group consisting of: a microswitch; a magnetic field sensor; an optical sensor; a capacitive sensor; and a strain gauge transducer. Overview of Hair Styling Device and Control Circuitry Figure 42 is a simplified block diagram of another control circuitry 15 that controls the operation of the hair styler device 1 shown in Figure 1a. With reference to Figure 1a, the hair styler 1 includes a first movable arm 4a and a second movable arm 4b, which are coupled at proximal ends thereof to a shoulder 2. The first arm 4a bears a first heater 6a at its distal end, and the second arm 4b bears a second heater 6b at its distal end. A user interface 11 is provided to allow the user to set user defined parameters and for the device to output information to the user. In this embodiment, the user interface 11 also comprises a control button or switch 14 to enable the user to turn the device 1 on or off; and an indicator light 15 to show whether the power is on. In this example, electrical power is provided to the device 1 by means of a power supply located at an end of the device, via a power supply cord 3. As shown in Figure 42, the control circuitry 15 comprises a power supply 21. In this example, power is provided to the heaters 6 for heating the users hair. The power supplied to the heaters 6 is controlled by a controller 28 having a microprocessor 29. The power supplied to the heaters 6 is controlled by drive circuitry 23 to the heaters 6 in accordance with instructions from the microprocessor 29. The microprocessor 29 is coupled to a memory 30 (which is typically a non-volatile memory) that stores processor control code for implementing one or more control methods that control theheating of the heaters 6 in accordance with a desired operating temperature of the heaters 6 and sensed temperaturesof the heaters obtained from temperature measurement circuitry 25. The temperature measurement circuitry 25 may be temperature sensors such as thermistors or they may use circuitry that senses the resistance of heater electrodes that are used to heat the heaters 6, which resistance depends on the temperature of the heater electrode. Figure 42 also shows that the user interface 11 is coupled to the microprocessor 29, for example to provide one or more user controls and / or output indications such as a visual indication or an audible alert. The output(s) may be used to indicate to the user, for example, if they have inserted too much hair between the heaters 6 or if they are moving the device 1 too quickly along the hair tress 40. Finally, the control circuitry includes communications circuitry 27 to allow the device to communicate with a remote sensor, a remote server, or a remote application (e.g. on a mobile telephone). The communications circuitry 27 may use, for example, Bluetooth, Wi-Fi and / or 3GPP communication protocols to communicate with the remote device.The elements of Figure 42 that have already been described in the present disclosure are not described again in detail,for the sake of conciseness. HeatersIn an example, the heaters 6a and 6b of Figure 42 may be as already described with reference to Figures 3a, 3b, 4, 5and 6a and 6b, and the elements that have already been described in the present disclosure with reference to Figures3a, 3b, 4, 5 and 6a and 6b are not described again in detail, for the sake of conciseness.Heating Zone Sizing One issue with low thermal mass heaters 6 is the regulation of hair contacting surface temperature in the locally hair loaded regions of the heater within desired temperature limits, without causing overheating of the unloaded regions at the same time. Specifically, when the user loads a tress of hair 40 onto the heaters 6, some parts of the heater will be loaded with hair whilst other parts will not be loaded with hair. Upon loading with hair, more power is supplied to the heater 6 to ensure that all regions on the hair contacting surface can be retained within and / or recovered back to the desired operating temperature limits. The low thermal mass heaters 6 described above are relatively thin and the dielectric layers are formed of materials with relatively low thermal diffusivities. If there was just a single heating zone, and hence a single continuous heater electrode 64 running across the whole length and whole width of the heater 6, then when more power is supplied to the heater 6 to recover the temperature drop in the locally hair loaded regions, the unloaded regions would undergo overheating, which could cause the heater materials to exceed their maximum operating temperatures, or cause the overheated regions to burn relatively small bundles / strands of hair that come into contact with them. This overheating can be prevented by using materials with higher thermal diffusivities in the layers that constitute the heater, and / or by increasing the thicknesses of the layers that constitute the heater and / or by dividingthe heater 6 into multiple separately powered and controlled heating zones 642 across its length or its length and width.Increasing the thickness of the layers increases the thermal mass of the heater 6 which is undesired and there arelimited materials that have the required dielectric strength and high thermal diffusivity (and which are available for usein mass produced consumer products). Therefore, the inventors have divided the heaters 6 up into plural heating zones. These heating zones can be equally and / or unequally sized and can be arranged regularly and / or irregularly across the width and / or length of the heater. However, overheating can still occur within a single heating zone. For example, if half of the heating zone is loadedwith hair (which is assumed to be the realistic worst case scenario during operation) and the other half is not loadedwith hair, then the half that is loaded with hair will cause the temperature of that part of the heating zone to drop whichwill cause more power to be applied to that heating zone in its entirety. That applied power will bring the averagetemperature of the heating zone back up to the desired operating temperature, but the unloaded part of the heating zone will be above the average temperature of the heating zone. This temperature increase may be sufficient to causethe unloaded part to overheat. At the same time the loaded part of the heating zone will be below the averagetemperature causing a reduction in heat transfer and reduced styling performance. This situation is illustrated in Figure 7, which shows a tress of hair 40 overlying heating zones Z2, Z3 and Z4, with heating zone Z3 being fully loaded withhair and heating zones Z2 and Z4 being only partially loaded with hair. This problem can be reduced by making theheating zones very small – but that is costly due to all the connections needed to connect each heater electrode 64 foreach heating zone back to the drive circuitry 23 as well as the number of control switches in the drive circuitry 23needed to control the powering of each heater electrode 64. The inventors have found that for a given permitted maximum temperature within the heater, a maximum size of the heating zones can be defined which depends on themaximum power density to hair that can be extracted from the heating zone and the material characteristics of thelayers forming the heating zone. Specifically, if it is assumed that only one half of a heating zone 642 is loaded with hair, upon loading with hair, themaximum temperature that occurs in the unloaded half of a heating zone 642 can be defined with the equation below: where, ^^^^= maximum temperature (°C) on the surface of the heater which would occur in the unloaded half (worst case)of an individual heating zone;^^^^ = target operational temperature or average temperature (°C) of individual heating zones;^̇ = power density (Wm-2) required to heat hair passing over the surface to the desired temperature for styling;W = width of a heating zone measured perpendicular to the motion of hair over the surface;^ = total thickness of the layers that constitute the heating zone; and^^ = the thickness averaged thermal conductivity of the thin layers that constitute the heating zone.If it is assumed that the thickness averaged thermal conductivity of the constituent layers of a heating zone 642 areknown and fixed (for any given device), then the above equation can be used to determine the required zone width (W)and hence a number of divisions along the length of the heater that will prevent overheating of the unloaded halves,when their other halves are loaded with hair, and more power is supplied to maintain and / or recover the hair contactingsurface temperatures back to the desired operating limits. Consequently, for a given surface area that must be covered with the considered heater technology, the equation above can be used to determine the number of heating zones thatshould be positioned along the length of the given surface area, so that each heating zone 642 can be operated withoutexceeding the maximum operating temperature of the heater materials and without causing the temperature of theunloaded part of a heating zone 642 to exceed the maximum temperature (Δ^^^^) that could cause burning of relativelysmall bundles / strands of hair that come in contact with such overheated regions of the heating zone.Specifically, the required divisions along the length can be determined from: Where,^ = length of the heater plate (perpendicular to the direction that hair typically travels across the surface);^^= number of zonal divisions along the length of the heater plate; ^^^^= maximum permitted temperature (°C) on the surface of the heater (which would occur in the unloaded half(worst case) of an individual heating zone) needed to avoid damage to hair or the heater;^^^^= target operational temperature or average temperature (°C) of individual heating zones;^^ = the thickness averaged thermal conductivity (Wm-1°C-1) of the layers that constitute the heating zone;^ = total thickness of the layers that constitute the heating zone; and^̇ = maximum power density (Wm-2) required to heat hair passing over the surface to the desired temperature forstyling. For a hair styling device, the inventors have found the following suitable ranges for these parameters: -Peak power density required for styling dry hair (^̇) is typically greater than 4 W / cm2 and less than 50 W / cm2and preferably greater than 8 W / cm2 and less than 25 W / cm2- The average thermal conductivity of the layers forming the heating zone (^^) (averaged through the depth ofthe various layers) is between 15 and 300 W / m.K and preferably between 80 and 200 W / m.K.- The maximum permitted temperature of a heating zone to manage (ideally avoid) hair damage is less than250°C, more preferably less than 220°C and most preferably less than 200°C.- The total thickness of the layers (^) which make up the heater is less than 300µm but no less than 75µm dueto manufacturing limitations. -The target operational temperature of the heater (^^^^) is between 150°C and 230°C.Operating within these ranges, the inventors have found that the required number of heating zones per unit length (cm)along the length of the heater is between 0.6 and 2.5 per cm which is equivalent to a zone width (in the lengthwisedirection of the heater) of between 0.4 cm and 1.7 cm.Of course, this is for the case of there not being multiple zones in the width direction of the heater as well (e.g. this isfor the single row case shown in Figure 4a). If multiple rows of heating zones 642 are provided along the length of theheater (such as is shown in Figure 4b), then each row of heating zones 642 should meet the limits defined above if theabove described overheating problem is to be avoided. Alternative Heater Arrangements An alternative flexible heater 6’ is illustrated in Figure 43, which shows on the left hand side an exploded cross-sectional view of the heater 6’ and substrate 68’ and on the right hand side a perspective view of the heater 6’ and substrate 68’. As shown in Figure 43, the heater 6’ has curved edges 72-1 and 72-2 that are shaped to match the shape of an upper surface 74 of the rigid support substrate 68’ so that the flexible heater 6’ can be bonded securely using an adhesive ordiffusion bonding (thermoforming) of the underlying materials to the upper surface of the rigid substrate 68’ or by over-moulding in which the carrier is injection moulded over the back of the flexible heater within the mould. The curvededges of the heater 6’ can be formed, for example, using a heat forming process. Figure 43 also illustrates that one ormore surface mounted electronic components 76 may be attached to an underside of the heater 6’. These componentsmay be, for example thermistors for sensing the temperature of the heating zones 642 of the heater 6’ or fuses thatcan cut power to the heater electrode of each zone or all zones in the case of a zone overheating. Figure 43 alsoshows a control printed circuit board (PCB) 78 that carries the drive and control electronics 15 illustrated in Figure 2 that controls the heating of the different heating zones 642 of the heater 6’. As before, the heater 6’ is formed from a number of discrete layers that are mechanically or chemically bonded together. Each layer has a thickness between about 1 µm and 150 µm and preferably between 1 µm and 100 µm, more preferably between 10 µm and 70 µm or between 2 µm and 10 µm. The different layers forming part of the heater 6’ are shown in exploded cross-sectional and perspective views in Figure 44. A description of each layer is given below. Low Friction Coating 81 (Optional) This is an optional layer and can be added to create a smooth, low friction surface to enhance the user experience bymaking the heater 6’ feel less grippy against the hair. This layer would be as thin as possible (for example, between10 and 50 µm and preferably between 1 and 3 µm) to reduce the thermal resistance from the heater 6’ to the hair,whilst still being sufficiently durable and scratch resistant. This layer would typically be applied last, possibly as a spray coating (e.g. Cerasol), after the rest of the heater 6’ hasbeen produced and assembled around the rigidifying substrate 68’. This may be needed with Cerasol because thiscoating is prone to cracking when flexed, and once applied the coating will reduce the natural flexibility of the heater, and so it should be applied once the heater 6’ has been formed into its final shape.Alternatively, this coating may comprise multiple layers including, for example, a primer layer (of about 6 µm), a basecoat layer (of about 25 µm) and a top coat layer (of about 10 µm). This layer could also have combined functionalities with other proposed layers (e.g. more than just offering low friction) such as dielectric strength / electrical separation provided the material is sufficiently electrically insulative. Heat Spreading Layer 82 (optional) This is also an optional layer and, when provided, helps to spread the heat within each heating zone 642 to ensure that the temperature of individual heating zones 642 is able to maintain an acceptable degree of homogeneity duringtypical use. As discussed above, if a heating zone 642 was to be partially loaded with hair and was sufficiently large,the unloaded portion of the heating zone 642 could develop an unacceptably high temperature, whereas the loadedregion would be too cold, as heat could not adequately flow from the hot region to the cold region. This problem isexacerbated by the anisotropic thermal characteristics of the serpentine like heater electrodes 64, and by the fact the control electronics 15 would typically work to maintain an “average” temperature within the heating zone 64 based onthe overall resistance of the heater electrode that forms the heating zone 642 - from the perspective of the controlelectronics 15, the heating zone 642 would be at the “correct” temperature despite having hot and cold regions.Each heating zone 642 would have its own heat spreader, which is thermally separated (there is a high thermal impedance / low thermal conductivity) from the heat spreaders for adjacent zones. This is desirable to prevent heatingzones 642 from heating neighbouring heating zones 642 which might otherwise increase power consumption, reducewarm up time and complicate algorithms based on zonal power consumption by adding crosstalk. Figure 45 illustratesan example form of the heat spreader layer 82. As shown, in this example there are 20 heat spreaders 91-1 to 91-20, each formed of a relatively high thermal conductivity material (such as copper). Each heat spreader 91 is separated from its neighbouring heat spreaders 91 and in effect forms an island of thermally conductive material over the corresponding heating zone. The heat spreaders 91 may be separated from each other by a solid material having a thermal conductivity lower than 35 W / mK or they may be separated by air. The heat spreaders 91 may be formed, for example, by taking a planar layer of metal (such as a layer of copper) that is bonded onto the layer below and then etching this layer of copper to physically separate the individual heat spreaders 91 (so that they do not touch each other). Provided there is a break between neighbouring heat spreaders 91, it is difficult for heat from one heating zone 642 to pass into neighbouring heating zones 642. The solid material (dielectric and / or scratch resistant low frictionmaterial(s)) that is provided in the gap between adjacent heat spreaders 91 may be provided by a PVD (PhysicalVapour Deposition) DLC (Dimond Like Carbon), bond film, coating or a wash that is applied to the heat spreading layer82 after the etching process has formed the gaps between adjacent heat spreaders 91 and may be the coating layer 81 described above. Alternatively other suitable methods may be used to provide solid material in the gap between adjacent heat spreaders, such as masking and vapour deposition etc.This heat spreader layer 82 can provide mechanical integrity to the overall heater 6’, providing some protection fromdamage to the hair contacting surface that might otherwise expose the underlying heater electrodes 64, which in turn could lead to short circuits or loss of functionality. Polyimide Separator layer 83The polyimide separator layer 83 provides electrical insulation between the hair contacting surface of the heater 6’(which may be the upper surface of this layer 83 if the optional layers 81 and 82 are not provided) and the main heaterelectrode layer. This layer 83 would have as low thermal impedance as possible whilst still achieving the dielectricrequirements of the layer. As the name suggests, this layer is formed of polyimide, although other dielectric materialscould be used. Because this layer is relatively thin, it does not significantly impede heat transfer between the in heaterelectrodes and the hair contacting surface, despite its low thermal conductivity (less than 0.2 W / mK). However, in-plane, it is able to prevent heat spreading from one heating zone 642 to an adjacent heating zone 642.Main Heater Electrode & Sensing Layer 84 This layer 84 is where heat is created by dissipating electric power from the power source (e.g. a power supply unit (PSU) or one or more batteries). This layer 84 comprises a number of independently controllable heater electrodes 64 each defining a corresponding heating zone 642. Independently controllable means that each heating zone can be heated to any desired target temperature (or switched on / off) independently of the other heating zones. So, the set point temperature of a heatingzone may, if desired, be different from the set point temperature of other heating zones. Figure 46 illustrates in moredetail the form that this layer 84 takes in this example heater 6’. As shown, in this example, there are twenty independently controllable heater electrodes 64-1 to 64-20 that each defines a corresponding heating zone 642. Each heater electrode 64 is formed of a track of resistive material, whose geometry (track width, thickness, length) andmaterial are specified in order to achieve the desired resistance and peak power density (W / cm2) requirements basedon the voltage output of the relevant power source.Each heater electrode 64 is formed into a serpentine pattern using, for example, chemical etching as a manufacturingprocess. In more detail, a solid layer of electrically conductive material is provided and then etched to form the differentheater electrodes 64. The straight lines shown in Figure 46 are the etched parts of the layer 84 and the white parts ofthe figure show the serpentine conductor paths that form the heater electrodes 64. Other processes such as printing, thick film printing, physical vapour deposition and the like could be used to form the heater electrodes 64. In this illustrated example, adjacent heater electrodes 64 share a common positive terminal (although in other embodiments they may share a common ground terminal) to reduce the number of electrical connections needed to be made betweenthe drive and control board 78 and the heater 6’. This common positive terminal is connected to the different heaterelectrodes at suitable vias 65-1 to 65-5, which connect through to connection circuitry below (not shown) that connectsto the drive and control board 78. The other end of each heater electrode connects through a respective switch (not shown) to the drive and control board 78 to allow independent control of current flow through each heater electrode 64. As those skilled in the art will appreciate, it is not essential to have such a common positive (or ground) terminal, each heater electrode 64 may be physically separate from all other heater electrodes 64 in which case, each end of each heater electrode 64 would be connected separately back to the drive and control board 78. As schematically illustrated in Figure 46, the end of each heater electrode 64 that is connected to the switch is providedat the edge of the heater and the direction of the serpentine tracks changes in this edge portion (which corresponds tothe portion of the heater which is curved over the upper surface 74 of the rigid support substrate 68’). The inventors have found that this arrangement helps heat generated in the heater electrodes 64 in these edge portions to pass up to the top surface of the heater which is more likely to come into contact with the user’s hair. However, if the device istwisted in use such that the user’s hair comes into contact with this curved edge portion, then the hair will still be heatedas this curved edge portion is heated. The conductive material used in the layer 84 is preferably a PTC or an NTC material (such as stainless steel or copper)so that the resistance of the heater electrode 64 depends upon its temperature – and so the temperature of the heatingzone 642 can be determined by measuring a parameter that varies with the resistance of the corresponding heater electrode 64. This removes the need for separate temperature sensors for each heating zone as a single sensor canbe used to measure the temperature of each heating zone (as discussed below with reference to Figure 47).Figure 47 is a schematic view of the way in which the heater electrodes 64 may be connected together and to the drivecircuitry 23 and the power supply 21. As shown in Figure 47, each heater electrode 64 is connected at one end to the power supply 21 and at the other end to a respective switch (in this case a MOSFET switch) 95-1 to 95-20. The switches 95 are controlled by the microprocessor 29. When a heater electrode 64 is to provide heat, the corresponding switch 95 is closed thereby connecting the heater electrode 64 to ground through the resistor R. As a result, current flows from the power supply 21 to ground causing the heater electrode 64 to heat up. The microprocessor 29 can control the position of each switch 95 independently thereby allowing each heater electrode 64 to be powered independently. When the temperature of a selected heating zone 642 is to be determined, the switch 95 of the corresponding heater electrode 64 is closed and all other switches 95 are opened. In this way, the selected heater electrode 64 is provided in series with the resistor R. Since the heater electrodes 64 are formed of a PTC or an NTC material whose resistance changes with the temperature of the heater electrode 64, by measuring the voltage dropped across the resistor R (using the operational amplifier 97), the microprocessor 29 can determine the resistance of the selected heater electrode 64 and hence can determine the temperature of the corresponding heating zone 642. If the determined temperature is above the desired temperature for that heating zone 642, then the microprocessor 29 can reduce the power applied to that heater electrode 64; or if the heating zone 642 is at a lower temperature than that desired, then the microprocessor 29 can increase the power applied to the corresponding heater electrode 64. Any suitable ON / OFF control or PWM (pulse width modulation) control can be used to vary the power applied to the different heater electrodes 64. The microprocessor 29 can select each heater electrode 64 in turn in order to determine the temperature of each heater electrode 64 / heating zone 642. Polyimide Separator (Optional) 85 When an auxiliary heater electrode layer is provided, this layer is required to provide the required electrical separation(insulation) between that auxiliary heater electrode layer and the main heater electrode layer 84 described above. Thispolyimide layer 85 would have a low thermal resistance in the thickness direction whilst still achieving the dielectric requirements. Due to this layer being relatively thin, it will have a low thermal conductivity in the plane perpendicular to its thickness of less than about 35 W / mK. Other dielectric materials could be used instead of polyimide. Auxiliary Heater Electrode Layer (Optional) 86 Some embodiments of the heater 6’ may benefit from the presence of an additional heating element layer 86. This additional layer 86 could be used to dissipate power (create heat) from a secondary power source that operates at a different voltage to the main power source 21, for example the main power source could be a power supply and thepower source for the auxiliary heater electrode layer 86 could be one or more batteries or supercapacitors. In otherembodiments the primary source could be one or more batteries and the auxiliary one or more supercapacitors. Alternatively still, the conductors on this auxiliary layer 86 could become the primary heaters, and those on the mainheater electrode layer 984 would just be used for temperature sensing or vice versa. The heater electrodes on the auxiliary layer 86 will typically have the same form as the heater electrodes 64 used inthe main heater electrode layer 84 – so that they will define the same heating zones 642 as the heating zones 642defined by the heater electrodes 64 on the main heater electrode layer 84. The path taken by the heater electrodes onthe auxiliary layer 86 does not need to follow the same path as the corresponding heater electrodes 64 formed on themain heater electrode layer 84. For example, whilst the main part of each heater electrode 64 on the main heater electrode layer 84 (ignoring the edge part of each heater electrode 64) serpentines in the longitudinal direction of the heater 6’ in Figure 46, the corresponding heater electrodes of the auxiliary heater electrode layer 86 could be arranged to serpentine in the width direction of the heater 6’. Such an arrangement would reduce the anisotropic thermal conductivity caused by tracks mostly facing one direction, and may help to spread the heat flow within the heating zone 642 particularly if the heating zone 642 is only partially loaded with hair. Polyimide backing 87 This layer encapsulates and electrically insulates the bottom heating layer (either the main or the auxiliary heating layer) so as not to allow it’s accidental exposure and to prevent moisture ingress. This backing layer 87 electricallyseparates the bottom heating layer from any surface mounted components that are present on the surface mountinglayer 88 (discussed below) on the bottom of the heater 6’. If desired, this dielectric layer 87 can be made thicker thanthe upper dielectric layers to provide enhanced structural integrity of the flexible part of the multilayer heater. As withthe other dielectric layers, this backing layer 87 does not need to be a polyimide layer and other dielectric materials could be used. Rear Side Surface Mount Components (Optional) 88 This layer is used to mount components on to the rear of the flexible heater 6. These components may be temperature sensors (e.g. thermistors) or other components involved in providing fusing functionality for the heater (e.g. solder links).This layer may be produced using standard chemical etching methods from the PCB manufacturing process. Additionalsurface mount components would be added later. This layer may be treated during manufacturing to provide a rough copper surface (e.g. “Brown Oxide” or “BlackOxide”). This enables better bonding of the flexible heater 6’ to the underlying support structure 68’ when using anadhesive film 89.High Temperature Adhesive / Bonding Layer 89 (Optional)The function of this layer is to enable bonding of the flexible heater 6’ to the rigid substrate 68 (shown in Figure 43)that forms the final shape of the overall heater. Various types of adhesive could be used such as a pressure activatedadhesive (PAA), heat activated adhesive (HAA) or thermosetting epoxy films (prepregs and B-stage films). It couldalso be a thermoplastic bonding film which sets after heat and pressure have been applied in a forming tool.Detecting pull duration Disclosed herein is a hair styling appliance, such as a set of hair straighteners, having a pair of opposing jaws or arms, connected by a hinge, and a heating surface on each jaw. The heating surfaces face each other so that, when the jaws are closed, hair can be sandwiched between the heating surfaces for straightening or otherwise styling the hair. Hair can be styled by systematically running tresses of hair between the heating surfaces. A single tress pull can be done by pulling the hair styling appliance along the tress of hair from the root of the tress (i.e., near the scalp) to the tip of the tress (i.e., at the free end of the tress). The heaters may be low thermal mass heaters such as those described above that can heat up and cool down quickly. When using such a hair drying and / or styling appliance, it is advantageous for the heaters to switch off or to reduce their temperature between successive tress pulls. In some modes of styling, it may also be considered advantageous for the heaters to have a relatively lower temperature at the start of the tress pull, i.e. near the roots where the hair is younger (and more susceptible to heat damage), and to increase the temperature of the heaters at a later stage in the tress pull, i.e. towards the tip of the tress where the hair is older and less sensitive to heat. The hair styling appliance disclosed herein senses whether the jaws are open or closed using a hinge switch. Based on whether the jaws are open or closed, a controller of the appliance can perform a control action to control the heaters according to the advantageous behaviours mentioned above. For example, the controller can switch off or reduce the temperature of the heaters when the jaws are opened. Also, the controller can time the duration of a tress pull, forexample by determining the time between the jaws closing and subsequently opening. This information can be usedto perform an action, such as displaying information on a display or storing information in a memory or controlling the temperature of the heaters by altering the power supplied to the heaters. The controller can also infer the position of the appliance along a tress of hair based on how long the jaws have been closed as a fraction of the determined duration of a tress pull. In this way, the controller can control the temperature of the heaters based on the position of the appliance along the tress, so as to increase the temperature of the heaters for example at a rate appropriate to the length of the hair and the speed of the tress pull.Referring now to the figures, Figure 48 illustrates a handheld (portable) hair styler 1-1. The hair styler 1-1 includes afirst arm 1-4a and a second arm 1-4b, which are coupled at proximal ends thereof by a hinge, such as a shoulder 1-2. The first arm 1-4a bears a first heater 1-6a at its distal end, and the second arm 1-4b bears a second heater 1-6b at its distal end. The first and second heaters 1-6a, 1-6b oppose one another and are brought together as the first and second arms 1-4a, 1-4b are moved from an open configuration to a closed configuration. During use, a tress of hair issandwiched between the two arms 1-4 so that the user’s hair is in contact with, and therefore heated by, outer heatingsurfaces of the heaters 1-6a, 1-6b. Therefore, as the user pulls the hair styler 1-1 along the tress of hair, the tress ofhair is heated by conductive heating to a suitable temperature to facilitate styling. A user interface 1-11 is provided to allow the user to set user defined parameters for the device and to output information to the user. For example, a desired operating temperature may be set via the user interface 1-11. The userinterface 1-11 may have a dial, button or touch display for allowing the user to input information to the device 1-1 andthe user interface 1-11 may have an indicator light, display, sound generator or haptic feedback generator for outputting information to the user. In this embodiment, the user interface 1-11 also comprises a control button or switch 1-14 toenable the user to turn the device 1-1 on or off; and an indicator light 1-15 to show whether the power is on.A printed circuit board assembly (not shown) may be provided at any suitable location within the housing of the device1-1 and carries the control circuitry for controlling the operation of the device 1-1 and for controlling the interaction withthe user via the user interface 1-11. In this example, electrical power is provided to the device 1-1 by means of a powersupply located at an end of the device, via a power supply cord 1-3. The power supply may be an AC mains power supply. However, in an alternative embodiment the power supply may comprise one or more DC batteries or cells (which may be rechargeable, e.g. from the mains or a DC supply via a charging lead), thereby enabling the device 1-1 to be a cordless product.In use, the device 1-1 is turned on, energising the heaters 1-6 to cause them to heat up. The user then opens the firstand second arms 1-4a, 1-4b and, normally starting from the roots of the hair (i.e. near the scalp), a length or tress of hair (which may be clumped) is introduced between the arms 1-4a, 1-4b, transversely across the heaters 1-6a, 1-6b. The user then closes the arms 1-4a, 1-4b so that the length of hair is held between the first and second arms 1-4a, 1-4b and then the user pulls the hair through the closed arms. The outer (hair contacting) surface of the heaters 1-6 isflat in this embodiment and so the hair styler 1-1 can be used to straighten the user’s hair. The hair styling device 1-1shown in Figure 48 can also be used to curl the hair by turning the device 1-1 through approximately 180 degrees ormore after clamping the hair between the arms 1-4a, 1-4b and before moving the device 1-1 along the tress of hair.The device 1-1 also comprises a sensor (not shown). The sensor may be comprised in sensor circuitry 2-50 (see Figure49). The sensor is configured to detect relative movement between the first arm 1-4a and the second arm 1-4b. The sensor may therefore be considered a hinge switch or hinge sensor. The sensor may comprise a switch configured to be actuated upon opening and / or closing of the device 1-1. In one example, the sensor may comprise an electromechanical contact, such as a microswitch, which may be open when the appliance is in the open configuration and closed when the appliance is in the closed configuration, or vice versa. The sensor may comprise a first sensing component and a second sensing component, which can interact with one another to detect relative movement therebetween. For example, the first sensing component may be provided on the first arm 1-4a and the second sensingcomponent may be provided on the second arm 1-4b. The sensor may be connected to the controller 2-28 (see Figure49) in order to output a detection signal to the controller 2-28. In one such arrangement, the sensor comprises a magnetic switch arrangement. The magnetic switch arrangement may comprise a magnet and a magnetic field sensor. As such, the magnet may be the first sensing component and the magnetic field sensor may be the second sensing component. The magnet may be provided on the first arm 1-4a and the magnetic field sensor may be provided on the second arm 1-4b. The magnetic field sensor may comprise a semiconductor hall effect sensor. The sensor may be configured to output a signal based on the strength of the magnetic field detected by the magnetic field sensor. The magnetic field sensor may also be a reed switch. In such an arrangement, the sensor may be configured to output a signal based on whether the reed switch is closed by virtue of its interaction with the magnet. In another arrangement, the sensor comprises an optical sensor arrangement. The optical sensor arrangement may comprise a retro-reflective sensor comprising an emitter / receiver and a retroreflector. In this arrangement, the emitter / receiver may be the first sensing component and the retroreflector may be the second sensing component. In another example, the optical sensor comprises an interruptive sensor comprising an emitter and a receiver. In this arrangement, the emitter may be the first sensing component and the receiver may be the second sensing component. The sensor may be configured to output a signal based on the intensity of the light received by the receiver, or based on whether or not the optical sensor is interrupted. In some arrangements, the sensor comprises a capacitive sensor arrangement. The capacitive sensor arrangement may comprise a capacitive sensor and a conductive object. In this arrangement, the capacitive sensor may be the first sensing component and the conductive object may be the second sensing component. The sensor may be configured to output a signal based on the strength of the electric field detected by the capacitive sensor. In a different example, the sensor comprises a strain gauge arrangement. The sensor can comprise a flexible member with a strain gauge transducer configured to measure the strain of the flexible member. The flexible member may be positioned in the appliance so as to measure a strain proportional to the separation between the arms 1-4a, 1-4b. In this respect, the flexible member may be provided between the first arm 1-4a and the second arm 1-4b and may be incorporated into the shoulder 1-2. The sensor may be configured to output a signal based on the strain detected by the strain gauge transducer.In view of the foregoing, the sensor can be configured to output a signal to the sensor circuitry 2-50 representative ofthe separation between the arms 1-4a, 1-4b, in order to detect whether the appliance is in the open configuration orthe closed configuration. In some examples, the sensor can be configured to measure a degree of opening of the arms 1-4a, 1-4b, such as an angle between the arms 1-4a, 1-4b, and to output a signal based on the degree of opening.Figure 49 is a simplified block diagram of control circuitry 2-16 that controls the operation of the hair styler device 1-1shown in Figure 48. Labels in the figures that indicate similar features to other figures have been allocated the samereference numerals prefixed with the figure number. The control circuitry 2-16 comprises a power supply 2-21 that, inthis embodiment, derives power from a battery power source. A mains power supply input may be provided to charge the battery via an AC to DC converter (not shown), which may be external or internal to the device 1-1. Alternatively,the power supply 2-21 may derive power from an AC mains supply input.In this example, power is provided to the heaters 2-6 for heating the user’s hair. The power supplied to the heaters 2-6 is controlled by a controller 2-28 having a microprocessor 2-29. The power supplied to the heaters 2-6 is controlledby drive circuitry 2-23 (which may include one or more power semiconductor switching devices (triacs)) which controlsthe application of an AC mains voltage, or a DC voltage derived from the AC mains or from a battery, to the heaters 2-6 in accordance with instructions from the microprocessor 2-29. The microprocessor 2-29 is coupled to a memory 2-30 (which is typically a non-volatile memory) that stores processor control code for implementing one or more controlmethods that control the heating of the heaters 2-6 in accordance with a desired operating temperature of the heaters2-6 and sensed temperatures of the heaters obtained from temperature measurement circuitry 2-25. The temperaturemeasurement circuitry 2-25 may be temperature sensors such as thermistors or they may use circuitry that senses theresistance of heater electrodes that are used to heat the heaters 2-6, which resistance depends on the temperature of the heater electrode.Figure 49 also shows that the user interface 2-11 is coupled to the microprocessor 2-29, for example to provide one ormore user controls and / or output indications such as a visual indication or an audible alert. The output(s) may be usedto indicate to the user, for example, if they have inserted too much hair between the heaters 2-6 or if they are movingthe device 1-1 too quickly along the hair tress.The control circuitry 2-16 includes communications circuitry 2-27 to allow the device to communicate with a remotesensor, a remote server, or a remote application (e.g. on a mobile telephone). The communications circuitry 2-27 mayuse, for example, Bluetooth, Wi-Fi and / or 3GPP communication protocols to communicate with the remote device.The control circuitry 2-16 further comprises hinge sensor circuitry 2-50. The hinge sensor circuitry 2-50 is configuredto transmit signals from the sensor to microprocessor 2-29 in the controller 2-28. The controller 2-28 is configured tointerpret the signals to determine whether the appliance is in the open configuration or the closed configuration. Forexample, in the case of a microswitch, the controller 2-28 may determine based on the microswitch being closed thatthe appliance is in the closed configuration, and may determine that the appliance is in the open configuration basedon the absence of a signal if the microswitch is open. In the case of a magnetic switch arrangement, the controller 2-28 may determine that the appliance is in the closed configuration when the magnetic field sensor detects a magneticfield above a threshold strength, and may determine that the appliance is in the open configuration when the magnetic field sensor detects a magnetic field below a threshold strength. In the case of an optical sensor arrangement, thecontroller 2-28 may determine that the appliance is in the closed configuration based on an intensity of light receivedby the receiver being above a threshold, and vice versa for the open configuration. In the case of a capacitive sensorarrangement, the controller 2-28 may determine that the appliance is in the closed configuration based on the detectedstrength of the electric field being above a threshold, and vice versa for the open configuration. In the case of a straingauge arrangement, the controller 2-28 may determine that the appliance is in the closed configuration based on thedetected strain being below a threshold, and vice versa for the open configuration.The control circuitry 2-16 may further comprises accelerometer circuitry 2-51. The accelerometer circuitry 2-51 isconfigured to detect an acceleration of the appliance and to transmit acceleration information to the microprocessor 2-29 in the controller 2-28.Figure 50 illustrates a control sequence 3-S that the controller 2-28 can be configured to perform. The controller 2-28is configured to detect 3-S1 a first closure based on determining that the appliance is in the closed configuration. The appliance is configured to detect 3-S2 a first opening based on subsequently determining that the appliance is in theopen configuration. The controller 2-28 is configured to measure 3-S3 a pull duration between determining that theappliance is in the closed configuration and determining that the appliance is in the open configuration. In other words,once it is detected via the hinge sensor circuitry 2-50 that the appliance is in the closed configuration, the controller 2-28 is configured to measure the time taken until the appliance is detected to be in the open configuration again. Thedetermined pull duration represents how long it takes a user to perform one tress pull, i.e. pulling the appliance fromthe root of the hair tress to the tip of the hair tress. The appliance is configured to perform 3-S4 a control action basedon the determined pull duration. The control action can comprise displaying information to the user via the user interface 1-11 and / or storing information in the memory 2-30. For example, the controller can be configured to store the tress pull duration in the memory for association with a user profile, in order to build data on the styling behaviour of a particular user. The controller can also be configured to determine a velocity of the appliance at a given time. In one example, thevelocity can be determined based on the acceleration detected by the accelerometer 2-51 and on determining that theappliance is in the closed configuration. In particular, it may be inferred that, at the moment when the closed configuration is detected, the appliance is stationary with respect to the user’s hair. Therefore, the controller can combine the acceleration from the accelerometer with the time elapsed since the appliance was closed in order to calculate the velocity of the appliance with respect to the user’s hair at a given time. The variation of the determined velocity over the course of a tress pull (i.e. between the appliance closing and theappliance opening) can be used by the controller 2-28 to calculate the tress length, for example by integrating thevelocity with respect to time. In this way, the controller can be configured to determine a tress length based on the determined velocity and the determined pull duration. The determined velocity and / or tress length can be used in addition to the pull duration to perform the control action. For example, the control action can comprise storing or displaying such information as described above, or controlling the power supplied to the heaters based on this information.Figure 51 is a graph of temperature against time according to an example of how the controller 2-28 can control thetemperature of the heaters based on the pull duration. Once the appliance is powered on, the controller 2-28 may beconfigured to supply power to the heaters to achieve a standby temperature, Tstby, which may be above ambient andwhich may be 100°C for example. Initially, when the first closure is detected at time 4-t1, the controller 2-28 isconfigured to increase the temperature of the heaters from Tstbyto Tstart. Tstartmay be a temperature suitable for heating hair at the roots of a tress, in that the temperature is high enough to achieve efficient styling (i.e., in a minimal number of passes) but sufficiently cool to prevent damage to the relatively young hair at the root.At this stage, the controller 2-28 may be configured to maintain the heaters at Tstart until the first opening is detected attime 4-t2. In other examples, the controller 2-28 may be configured to increase the temperature at a predefined rate toa predefined maximum temperature. Once the first opening is detected, the controller 2-28 is configured to reduce thetemperature of the heaters to Tstby. In some examples, the reduction to Tstby may be immediate upon detecting that theappliance is open. In other examples, the controller 2-28 is configured to determine an open duration during which theappliance has remained in the open configuration, and reduce the temperature of the heaters, for example to thestandby temperature, if the open duration is greater than a first threshold.Following the first closure and the first opening, the controller 2-28 is configured to measure the pull duration. This canbe calculated using the time elapsed between the appliance closing and the appliance subsequently opening, i.e. the difference between time 4-t2 and time 4-t1 in Figure 51.In the example shown, at time 4-t3, a closure is detected such that, as before, the controller 2-28 is configured toincrease the temperature of the heaters from Tstby to Tstart. Then, the controller 2-28 is configured to increase thetemperature of the heaters from Tstart to Tend, which represents a temperature higher than Tstart for efficient styling of the hair that is further down the tress and hence older and less prone to heat damage. If the power supplied to the heaters is such that the temperature of the heaters increases too slowly, then the tress pull will be finished before Tend is reached and the styling may be inefficient, for example requiring many passes. Conversely, if the power supplied to the heaters is such that the temperature is increased too quickly, then hair closer to the root may be more liable to heatdamage. Using the pull duration, the controller 2-28 can be configured to calculate the position of the appliance alongthe tress at a given point in time during a tress pull. For example, assuming each tress of hair has about the same length and assuming an approximately constant velocity of the appliance once a tress pull begins, the proportional position of the appliance along the tress at a given time can be approximated by dividing the elapsed time since the appliance was closed by the pull duration of the first pull.In some modes, the controller 2-28 can be configured to increase the temperature of the heaters linearly, from Tstart toTend, in proportion to the proportional position of the appliance along the tress. For example, when the controller 2-28 infers, based on the elapsed time into a tress pull and the pull duration, that the appliance is 50% along the length ofthe tress, then the controller 2-28 may set the temperature of the heaters to be halfway between Tstart and Tend. It willbe appreciated that other heating modes, which may be non-linear, may be employed, for example to increase the temperature slowly for the majority of the length of the tress and then increase the temperature more quickly towards the end of the tress, or vice versa.In the illustrated example, when the controller 2-28 determines that the appliance is in the open configuration at time4-t4, the controller 2-28 reduces the temperature of the heaters from Tend to Tstby. This temperature pattern can berepeated for subsequent tress pulls, as indicated by the dashed lines.The controller 2-28 can be configured to measure how long the appliance remains in the open configuration and, if thisduration is determined to be greater than a second threshold, then the controller 2-28 is configured to switch off theheaters. The second threshold is greater than the first threshold. In this way, upon detecting that the appliance is openand remains in the open configuration, the controller 2-28 is configured to wait for a first time period before reducingthe temperature to Tstby, and to wait for a second time period before switching off the heaters. In the arrangement shown, the duration of time between time 4-t6 and time 4-t5 is greater than the second threshold such that the heaters are switched off.In some arrangements, after determining that the appliance is in the closed configuration, the controller 2-28 may beconfigured to set the temperature to Tstartand maintain it for a predetermined delay, before increasing the temperatureto Tend. In other words, the controller 2-28 is configured to account for the appliance being momentarily stationary whenit is first closed, and to wait until the appliance is inferred to be moving along the tress before increasing the temperature of the heaters. While the control sequence has been described as using the first tress pull to control the temperature of the heatersfor subsequent tress pulls, the controller 2-28 may be configured to measure the pull duration of multiple tress pullsand control the power based on the determined pull duration of multiple preceding tress pulls, for example by calculating an average pull duration.The controller 2-28 may also be configured to determine whether the determined pull duration is within a predefinedrange and to control the power supplied to the heaters based on the determined pull duration and also based on whether the determined pull duration falls within the predefined range. In other words, before using the determined pullduration to determine how the heaters are controlled, the controller 2-28 can check whether the determined pullduration is too long or too short. Modifications and alternatives Detailed embodiments and some possible alternatives have been described above. As those skilled in the art will appreciate, a number of modifications and further alternatives can be made to the above embodiments whilst stillbenefiting from the inventions embodied therein. It will therefore be understood that the invention is not limited to thedescribed embodiments and encompasses modifications apparent to those skilled in the art lying within the scope ofthe claims appended hereto. It will be understood that any element and / or step described in relation with an embodiment and / or arrangement and / or method may be associated with any other embodiment and / or arrangement and / or method. It will be understood that any feature described in relation with an aspect of the disclosure may be associated with any other aspect. The invention has been described above in a styler comprising a heater having a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface. Details of further multi-zone heaters that can be used are described in the Applicant’s earlier patent application PCT / GB2024 / 052563, the contents of which are incorporated herein by reference. However, the heater may not comprise a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface, but the heater may have a single heating zone or one or more heating zones which are not independently controllable. The invention also applies to any styler comprising a heater for heating hair during drying and / or styling, for example a heater comprising only one heater electrode for heating the hair, the controller being configured to control a temperature or a power output of the at least one heater electrode of the heater. The invention applies to any type of heater configured to heat the hair. The invention has been described above by way of implementation in a hair styling device for straightening hair (‘hair straighteners’) which employ flat hair styling heaters 6. However, it could alternatively be implemented in any form of hair styling device, such as (but not limited to) crimpers, curlers or heated brushes. The heaters 6 may define a heating surface that is flat, curved, ridged or in the shape of a barrel. The hair styling device may have two arms, for example like the device illustrated in Figure 1, or it may be a single armed device. For example, the device may be a device with a first arm and a second moveable arm arranged to be moveable relative to the first arm between an open configuration and a closed configuration. Such a device may comprise first and second heaters opposing one another at the distal ends of the two arms, as previously described, that are brought together as the second moveable arm is moved towards the first arm from an open configuration to a closed configuration. During use, a tress of hair is sandwiched between the two arms so that the user’s hair is in contact with, and therefore heated by, outer heating surfaces of the heaters. In some arrangements, pressure sensors in a handle and / or a head of the device may be used to sense how the user is gripping the handle and / or how the user is wrapping the hair around the head. For example, another embodiment would be to place a pressure sensor in the handle of a single armed device, such as a curling wand, to determine how the user grips the device. Another example is to place a pressure sensor in the head of a single armed device, such as a curling wand, to determine how the user wraps their hair around the head of the device. Pressure between the two arms may be indicative of the user’s frustration as described above. In some arrangements, pressure sensors in a handle and / or a head of the device may be used to determine a frustration score, for example by sensing how tightly the user is gripping the handle and / or how tightly the user is wrapping the hair around the head. For example, another embodiment would be to place a pressure sensor in the handle of a single armed device, such as a curling wand; the user will grip the device harder as they become more frustrated. Another example is to place a pressure sensor in the head of a single armed device, such as a curling wand; the user wraps their hair around the head of the device and pulls it taut. The tighter the wrap, the more frustration the user is feeling. The heaters described above may also be used in hair dryers or in combination devices that use conductive heating and air to dry and style the user’s hair (such as those described in the applicant’s earlier PCT application WO 2021 / 019239, which is hereby incorporated by reference in its entirety). In embodiments where air is used, the heaters 6 may be perforated so that air passes through the heater and is warmed by the heater as the air passes through. In this respect, some embodiments may be incorporated into a wet-to-style product, which may incorporate heaters (such as heaters 6a, 6b) for straightening hair, as well as means to dry hair, for example by delivering heated airflow to the hair. Such means may comprise a fan assembly to generate airflow, which may be driven by a motor, and an air heater (which may be separate to the heaters 6a, 6b) to heat the airflow. The inventors have recognised that high thrust airflow can be important in enhancing heat transfer efficiency through the entirety of the hair section, which helps to minimise the size, power consumption and performance requirements of a hair styling and drying product. However, while high thrust airflow enhances drying efficiency, it can cause hair to fly around when the tress is inserted into such a product, leading to poor hair alignment, shine and smoothness due to the creation of flyaway hairs and frizz. Therefore, it may be advantageous to control the fan speed, in particular by reducing the fan speed while loading a tress of hair into the product (to reduce the thrust force acting on the hair, thereby reducing or preventing the creation of flyaway hairs and frizz) and to increase the fan speed once a tress of hair has been loaded (to benefit from maximum heat transfer efficiency). In addition or instead of controlling the temperature of the heaters, any of the sensing methods discussed above may be used to control the fan speed. For example, in the case of the sensor configured to sense relative movement of the first arm and the second arm between the open and closed configurations, the controller maybe configured to control the fan speed based on an output of the sensor. In other words, by determining whether theappliance is in the open configuration or the closed configuration based on the sensed relative movement, the controller can control the fan speed accordingly. The controller can therefore be configured to reduce the fan speed (e.g., to a first predefined speed) when the appliance is determined to be in the open configuration and to increase the fan speed (e.g., to a second predefined speed, being higher than the first predefined speed) when the appliance is determined tobe in the closed configuration. The reduction of the fan speed upon opening the appliance may be selected to generatea 20-50% air flow rate reduction with respect to the intended flow rate for drying. Since the output air temperature is a function of the flow rate and the air heater input power, it may be advantageous to control the air heater power to prevent or reduce spikes in air temperature at the outlet. Therefore, the controllermay be configured to control the air heater power based on an output of the sensor. In other words, by determiningwhether the appliance is in the open configuration or the closed configuration based on the sensed relative movement, the controller can control the air heater power accordingly. The controller can therefore be configured to reduce the air heater power (e.g., to a first predefined power) when the appliance is determined to be in the open configuration and to increase the air heater power (e.g., to a second predefined power, being higher than the first predefined power) when the appliance is determined to be in the closed configuration. In some examples, after determining that the appliance is in the open configuration, the controller is configured to reduce the air heater power before reducing the fan speed. Similarly, after determining that the appliance is in the closed configuration, the controller may be configured to increase the fan speed before increasing the air heater power. The above examples may be performed by implementing a delay between controlling the fan speed and the air heater power.Users sometimes need to move their hand position during the styling and / or drying process to be able to change modeson the apparatus, which can provoke damage to the hair. The apparatus may thus comprise a functionality where theuser is able to switch between styling and / or drying modes by clapping the arms of the apparatus. In operation, inembodiments where air is used as a non-limiting example, the user runs the apparatus through their hair on a firstmode (e.g., the fast mode to begin with to dry their hair faster), then claps the arms of the apparatus a predeterminednumber of times, such as twice (but other number of times may be envisaged), and runs the apparatus through theirhair in a second mode, different from the first mode, e.g., for a final pass (such as a slower airflow mode for the finalpass in order to give a better styling result). Instead of using a switch on the apparatus to change airflow modes on theproduct, the user can thus clap (i.e. open and close) the arms to switch between the airflow modes. Therefore, the userdoes not have to move their hand position during the styling and / or drying process to be able to change modes. Thisis a more dynamic and engaging way to switch between styling and / or drying modes (such as airflow modes as non-limiting examples) on the apparatus. In embodiments, the user will be able to tell which mode they are on by listeningto the sound level of the apparatus. The sensor configured to sense relative movement of the first arm and the secondarm between the open and closed configurations may be based on detection of a hall effect or may comprise a switchsensor to detect the hinge activations, but other methods of detection are also envisaged, as it is apparent from thepresent disclosure, such as detection of vibrations and / or of sounds made by the clapping of the arms.The invention also applies to any styler com prising a heater for heating hair during drying and / or styling, regardless ofthe type of thermal somatosensory feedback generator, for example a heater comprising only one heater electrode forheating the hair, the controller being configured to control a temperature or a power output of the at least one heaterelectrode of the heater. Similarly, it has been described above a styler comprising a thermal somatosensory feedback generator comprising a plurality of independently controllable heater electrodes which are configured to heat a plurality of portions of the handle which define a plurality of independently controllable heating zones of the handle. However, the invention also applies to any styler comprising a thermal somatosensory feedback generator comprising at least one heater electrode for heating at least one portion of the handle, regardless of the type of heater for heating hair during drying and / or styling, for instance a thermal somatosensory feedback generator comprising a single heater electrode for heating the handle. The invention applies to any type of heater configured to heat at least one portion of the handle.The child safety lock functionality of the fingerprint sensor has been described in combination with a buttonlessapparatus, but an apparatus with one or more buttons or any other user interfaces may also comprise a userauthorisation feature using a fingerprint sensor.In the above embodiments, Metal Oxide Semiconductor Field Effect Transistor (MOSFET) switches were used tocontrol powering and sensing of the heater electrodes. As those skilled in the art will appreciate, other switches couldbe used instead. For example, Field Effect Transistors (FETs) could be used, such as Gallium Nitride FETs or bipolarjunction transistors (BJTs). In the above embodiments, a DC power source was used to provide electrical power for heating the heater electrodes 64. This DC power source will typically be one or more batteries, although DC supplies that derive their power from amains power AC signal may be used. Thicker or more dielectric layers are typically used between the heater electrodes64 and the hair contacting surface of the hair styler when AC power is used to heat the heaters.In the above-described examples the hair styling device 10 may comprise a single heater 6, or may alternativelycomprise two or more heaters 6.Throughout the description and claims of this specification, the words “comprise” and “contain” and variations of thewords, for example “comprising” and “containing”, means “including but not limited to”, and is not intended to (and doesnot) exclude other components, integers or steps. The expressions “to dry hair”, “drying hair” or “decrease a moisture level of hair” and the like, as used in the present disclosure, can refer both to the removal of “unbound” water that exists on the outside of hair when wet, or the removal of “bound” water, which exists inside individual hairs, and which can be interacted with when heat styling hair. The “bound” water need not necessarily be removed when drying hair, although removal of some bound water may occur during a drying or styling process. Various other modifications will be apparent to those skilled in the art and will not be described in further detail here. The disclosure also comprises numbered clauses. Style recipes When a user wants to replicate a hair treatment (for example a hair style generated by a stylist, a friend or an influencer), the user has, at best, a video recording of the motions they need to do to achieve the treatment, or, at worst, the user has to work out the hair treatment from memory. Therefore, the users generally do not know the full instructions they should be following in order to achieve a desired treatment. The lack of full knowledge of the instructions often results in the hair of the user being treated according to a treatment which is different from the desired treatment, in turn resulting in a frustrating styling experience. Sometimes the user will have their hair damaged when styling.The following numbered clauses 1-29 aim to address or at least partially ameliorate one or more of the above problems.Style recipes - Clauses 1-291. Apparatus for drying or styling hair, the apparatus comprising: a user interface for allowing a user to specify a desired treatment to be performed on hair and that the user wishes to copy, wherein the user’s desired treatment comprises one or more desired sequences and is associated with pre-stored data, and wherein the pre-stored data includes information on how the appliance should be moved by the user during each of the one or more desired sequences to achieve the desired treatment; an appliance that is manipulable by the user to perform the desired treatment on the hair of the user; sensors for sensing and outputting sensor data indicative of operational parameters of the appliance during the treatment, wherein the sensor data includes motion data that indicates how the appliance is being moved by the user; a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface; and a controller configured to control the apparatus to, for each of the one or more desired sequences of the user’s desired treatment: process the sensor data to determine whether a deviation of the user’s manipulation of the appliance from how the appliance should be moved by the user to complete the desired sequence is greater than a threshold value, and, if it is, to output one or more feedback messages for the user to modify the way the appliance is manipulated, to help the user to complete the desired sequence, and / or control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to avoid the hair loaded into the apparatus to be treated according to an undesired sequence.2. The apparatus of clause 1, wherein the user interface is further configured to output the one or more feedbackmessages to the user, optionally wherein the user interface comprises at least one of a sound generator, lighting means, a thermal somatosensory feedback generator, and / or a haptic feedback generator.3. The apparatus of clause 1 or clause 2, wherein the controller is configured to control the apparatus such thatcontrolling the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, comprises: turning off the heater, or individually reducing and / or capping and / or modifying the temperature or the power output of the one or more heating zones of the plurality of individually controllable heating zones which are engaged with the hair.4. The apparatus according to any of the preceding clauses, further comprising communication circuitry suchthat the apparatus is configured to communicate with an external processing device, the external processing device comprising a user interface associated with the user.5. The apparatus according to clause 4, wherein the communication circuitry is such that the apparatus isconfigured to output the feedback message to the external processing device and wherein the output feedback message is output on the user interface associated with the user.6. The apparatus according to clause 4 or 5, wherein the external processing device is part ofa server remote from the apparatus, and / or a mobile phone or a smartwatch, the external processing device being configured to run an application, remote from the apparatus.7. The apparatus according to any of the preceding clauses, wherein the one or more desired sequences areordered and / or are associated with a side of the user’s head, to achieve the user’s desired treatment, optionally wherein the one or more desired sequences are ordered in groups of equal priority in the order.8. The apparatus according to any of the preceding clauses, wherein the user interface is configured tooutput the one or more desired sequences to the user, and / or output a name of the treatment, and / or a name of each of the one or more sequences, and / or written instructions, pictures and / or video instructions associated with the treatment and / or the one or more sequences, to help explain the treatment and / or the one or more sequences, and / or allow the user to specify when a desired sequence has been completed. 9. The apparatus according to any of the preceding clauses, wherein the user interface is configured to, after the desired treatment has been completed, output one or more user messages for the user, to allow the user to upload a picture of the completed treatment and / or rate the desired treatment, and / or wherein the apparatus is a hair straightener, a hair dryer, a hot paddle brush, a hot round brush, a heated roller, or a hair curler.10. The apparatus according to any of clauses 4 to 9, wherein the communication circuitry is configured to accessthe pre-stored data associated with the user’s desired treatment via the external processing device.11. The apparatus according to any of the preceding clauses, wherein the controller is further configured toprocess the sensor data to filter out data corresponding to movements which are performed when one or more armsof the appliance are in an open position, in which the arms are spaced apart, optionally the controller being configured to keep as data indicative of the user’s manipulation of the appliance datacorresponding to movements which are performed when the one or more arms are in a closed position, in which thearms are adjacent each other.12. The apparatus according to any of the preceding clauses, wherein the controller is further configured toprocess the sensor data to filter out data corresponding to movements which are greater than an amplitude threshold and / or a speed threshold, optionally the controller being configured to keep as data indicative of the user’s manipulation of the appliance data corresponding to movements which are smaller than the amplitude threshold and / or the speed threshold. 13. Apparatus for drying or styling hair, the apparatus comprising: an appliance that is manipulable by a stylist to perform a reference treatment to be performed on hair and that is destined to be copied by a user; a heater for heating hair during drying and / or styling; sensors for sensing and outputting sensor data indicative of operational parameters of the appliance during the reference treatment, wherein the sensors comprise motion sensors and the sensor data includes motion data that indicates how the appliance is being moved by the stylist; and a controller configured to control the apparatus to: process the sensor data to record data representative of the stylist’s manipulation of the appliance, process the recorded data to determine which movements of the appliance effectively contribute to achievement of the reference treatment, and process the recorded data corresponding to the determined effective movements of the appliance to generate pre-stored data which includes one or more reference sequences to achieve the stylist’s reference treatment, each reference sequence including information on how the appliance should be moved by the user during the reference sequence.14. The apparatus according to the preceding clause, wherein the reference treatment is performed on the hairof the stylist; and / orwherein the sensors further comprise sensors configured to sense and output sensor data indicative of whether arms of the appliance are: in a closed position, in which the arms are adjacent each other, or in an open position, in which the arms are spaced apart, and wherein the controller is configured to control the apparatus to process the recorded data to determine that movements of the appliance performed when the arms of the appliance are in the closed position effectively contribute to the achievement of the reference treatment, and / or determine that movements of the appliance performed when the arms of the appliance are in the open position do not contribute to the achievement of the reference treatment.15. The apparatus according to any of the two preceding clauses, wherein the controller is configured to controlthe apparatus to process the recorded data to determine whether one or more movements of the appliance which effectively contribute to the achievement of the reference treatment are repeated at a frequency which is lower than a threshold, and if they are, group the determined repeated effective movements together into a sequence. 16. The apparatus according to the preceding clause, wherein the controller is configured to control the apparatus to process the recorded data to compare the one or more grouped sequences and determine whether there is a deviation between at least two sequences of the one or more sequences, and if, there is, to determine whether the deviation between the at least two sequences is greater than a threshold value and if it is, to determine that the at least two sequences are reference sequences to achieve the stylist’s reference treatment. 17. The apparatus according to the preceding clause, wherein the controller is configured to control the apparatus to process the recorded data to determine, if there is no deviation between the at least two sequences of the one or more sequences and / or if there is a deviation which is smaller than threshold value, that the at least two sequences correspond to a single reference sequence to achieve the stylist’s reference treatment. 18. The apparatus according to any of clauses 13 to 17, wherein the controller is configured to control the apparatus to process the recorded data to process the recorded data corresponding to the one or more reference sequences to determine whether there is a pattern of one or more sequences, and if there is, to assign an order and / or a side of the stylist’s head to the one or more reference sequences according to the determined pattern, optionally wherein the one or more desired sequences are ordered in groups of equal priority in the order. 19. The apparatus according to any of clauses 13 to 18, wherein the controller is configured to control the apparatus to: process the sensor data to discard data which is representative of the stylist’s manipulation of the appliance above a movement safety line.20. The apparatus of any of clauses 13 to 19, wherein the controller is configured to process the data based ona set of deterministic rules and / or data for an artificial intelligence algorithm.21. The apparatus of any of clauses 13 to 20, further comprising communication circuitry such that the apparatusis configured to communicate with an external processing device, the external processing device comprising a user interface associated with the stylist.22. The apparatus according to the preceding clause, wherein the external processing device is part ofa server remote from the apparatus, and / or a mobile phone or a smartwatch, the external processing device being configured to run an application, remote from the apparatus. 23. The apparatus according to any of clauses 13 to 22, further comprising a user interface for allowing the stylist to assign a name to the treatment, and / or assign a name to the one or more reference sequences, and / or upload written instructions, pictures and / or video instructions associated with the reference treatment and / or the one or more sequences, to help explain the treatment and / or the one or more sequences. 24. The apparatus of any of clauses 13 to 23, configured as the apparatus of any of clauses 1 to 12, and / or wherein the apparatus is a hair straightener, a hair dryer, a hot paddle brush, a hot round brush, a heated roller, or a hair curler, and / or wherein the heater comprises a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface. 25. A hair treatment method comprising: inputting a desired treatment to be performed on hair and that a user wishes to copy, wherein the user’s desired treatment comprises one or more desired sequences and is associated with pre-stored data, and wherein the pre-stored data includes information on how the appliance should be moved by the user during each of the one or more desired sequences to achieve the desired treatment; providing an appliance that is manipulable by the user to perform the desired treatment on the hair of the user, the appliance comprising a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface; outputting sensor data indicative of operational parameters of the appliance during the treatment, wherein the sensor data includes motion data that indicates how the appliance is being moved by the user; controlling the apparatus to, for each of the one or more desired sequences of the user’s desired treatment: process the sensor data to determine whether a deviation of the user’s manipulation of the appliance from how the appliance should be moved by the user to complete the desired sequence is greater than a threshold value, and, if it is, to output one or more feedback messages for the user to modify the way is manipulated, to help the user to complete the desired sequence, and / or control the temperatu...

Claims

CLAIMS 1. Apparatus for drying or styling hair, the apparatus comprising: a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface; and a controller configured to control the apparatus to: determine, based on a drop of a temperature of one or more heating zones of the plurality of independently controllable heating zones or based on an increase in a power output needed to maintain the one or more heating zones at a target temperature, whether hair is engaged with the one or more heating zones and, if it is, to determine an amount of hair which is engaged with the one or more heating zones; determine, based on the determined amount of hair engaged with the one or more heating zones across all of the one or more heating zones, a hair tress size which has been loaded by the user into the apparatus; determine whether the determined hair tress size is greater than a threshold value and, if it is, to cause the apparatus to: output a feedback message indicating that too much hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the hair styling device accordingly, and / or control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.

2. The apparatus of claim 1, wherein the threshold value is a first threshold value, and wherein the controller isfurther configured to determine whether the determined hair tress size is smaller than a second threshold value, smaller than the first threshold value and, if it is, to cause the apparatus to: output a feedback message indicating that too little hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the apparatus accordingly, and / or control the temperature or the power output of the one or more heating zones of the plurality of controllableheating zones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.

3. The apparatus of claim 1 or 2, comprising:a user interface for outputting a feedback message to the user; the controller being configured to cause the user interface to output the feedback message indicating whether too much hair has been loaded into the apparatus.

4. The apparatus of claim 3, wherein the user interface comprises at least one of a sound generator, lightingmeans and / or a haptic feedback generator.

5. The apparatus of claim 4, wherein the lighting means comprise one or more lamps arranged along a lengththe apparatus, sideways of the heater, the controller being configured to control the apparatus to light up one or more lights of the lighting means on a length corresponding to the extent of the one or more heating zones which are engaged with the hair, in a length of the heater.

6. The apparatus of claim 5, wherein the controller is configured to control the apparatus to cause the lightingmeans to produce a first colour, such as green, when it is determined that the hair tress size corresponds to a desiredamount of hair, and at least one second colour different from the first colour, otherwise, thus prompting the user tomodify the amount of hair loaded in the apparatus, optionally wherein the controller is configured to control the apparatus to cause the lighting means to producea second colour, such as blue, to prompt the user to increase the amount of hair loaded in the apparatus, and a thirdcolour, such as red, to prompt the user to decrease the amount of hair loaded in the apparatus.

7. The apparatus of any of claims 4 to 6, wherein the controller is configured to control the apparatus to:cause the sound generator to produce a first sound, when it is determined that the hair tress size corresponds to a desired amount of hair, and to produce at least one second sound different from the first sound, otherwise, thus prompting the userto increase or decrease the amount of hair loaded in the apparatus, and / or cause the haptic feedback generator to produce a first haptic feedback, when it is determined that the hair tress size corresponds to a desired amount of hair, and to produce at least one second haptic feedback different from the first haptic feedback, otherwise, thusprompting the user to increase or decrease the amount of hair loaded in the apparatus, optionally wherein the controller is configured to control the apparatus to: cause the sound generatorto produce a second sound and / or the haptic feedback generator to produce a second haptic feedback, toprompt the user to increase the amount of hair loaded in the apparatus, and / or cause the sound generator toproduce a third sound and / or the haptic feedback generator to produce a third haptic feedback, to prompt theuser to decrease the amount of hair loaded in the apparatus.

8. The apparatus according to any of claims 1 to 7, further comprising communication circuitry such that theapparatus is configured to output the feedback message to an external processing device and wherein the output feedback message is output on a user interface associated with the user.

9. The apparatus according to claim 8, wherein the external processing device is part of a mobile phone and / ora smart watch and / or tablet and / or other such device and is configured to run an application, remote from the apparatus.

10. The apparatus according to any of claims 1 to 9, wherein, if it is determined that the determined hair tresssize is greater than the threshold value and thus is bigger than a desired amount of hair, the controller is configured to cap the increase in the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, so as to enable a better drying or styling of the hair which is loaded in the apparatus while avoiding burning of the hair.

11. The apparatus according to any of claims 2 to 10, wherein, if it is determined that the determined hair tresssize is smaller than the second threshold value and thus is smaller than a desired amount of hair, the controller isconfigured to turn off the heater or to reduce the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to prevent the hair being burnt.

12. The apparatus according to any preceding claim, wherein the one or more heating zones are adjacent to eachother along a length and / or across a width of the heater, and / or wherein the one or more heating zones are substantially thermally isolated from each other.

13. The apparatus according to any preceding claim, wherein the controller is configured to control the apparatusto:determine the resistance of a heater electrode of the one or more heating zones based on a voltage supplied to the heater electrode and the current passing through the heater electrode; and determine the temperature of the one or more heating zones based on the determined resistance, and / or wherein the controller is configured to control the apparatus to supply power to a heater electrode of the heater to determine the resistance of the heater electrode even in a case where it is determined that the corresponding heating zone is not engaged with hair.

14. The apparatus according to any preceding claim, wherein the apparatus further comprises a pair of opposingheating zones, wherein heat can flow between the opposing heating zones when the apparatus is in use, and whereinthe controller is configured to control the apparatus to:determine whether hair is engaged with at least one of the pair of opposing heating zones based on a sum or average of a power needed to maintain each of the pair of opposing heating zones at a target temperature.

15. The apparatus according to any preceding claim, wherein the controller is configured tocontrol power supplied to a heater electrode of the one or more heating zones to control the temperature of the one or more heating zones towards a first target temperature in a case where it is determined that the hair is engaged with the one or more heating zones, and to control the temperature of the one or more heating zones towards a second target temperature, lower than the first target temperature, in a case where it is determined that the hair is not engaged with the one or more heating zones; and intermittently supply power to the heater electrode to determine the resistance of the heater electrode even in the case where it is determined that the one or more heating zones is not engaged with the hair, and determine the temperature of the one or more heating zones based on the resistance.

16. The apparatus according to any preceding claim, further comprising a pressure sensor configured to senseand output data indicative of a pressure between a first movable arm and a second movable arm of the apparatus, to enable the controller to verify the determination of the hair tress size, as larger hair tresses require more pressure to stay in place in the apparatus.

17. The apparatus according to any preceding claim, wherein the controller is configured to receive data indicativeof the hair type of the user, to enable the controller to refine the determination of the hair tress size, as thick curly hair has larger hair tress sizes than fine straight hair.

18. The apparatus according to any preceding claim, wherein the apparatus is a hair straightener, a hair dryer, ahot paddle brush, a hot round brush, a heated roller, or a hair curler.

19. A method performed by apparatus for drying or styling hair, the apparatus comprising a heater having a haircontacting surface for heating hair that contacts the hair contacting surface by conduction, and the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface, wherein the method comprises: decreasing a temperature or increasing a power output of one or more heating zones of the plurality of independently controllable heating zones; determining, based on the drop of a temperature of one or more heating zones of the plurality of independently controllable heating zones or based on the increase in a power output needed to maintain the one or more heating zones at a target temperature, whether hair is engaged with the one or more heating zones and, if it is, to determine an amount of hair which is engaged with the one or more heating zones; determining whether the determined hair tress size is greater than a threshold value and, if it is, the method further comprising:outputting a feedback message indicating that too much hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the hair styling device accordingly, and / or controlling the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.

20. The method according to claim 19, wherein the threshold value is a first threshold value, and wherein themethod further comprises determining whether the determined hair tress size is smaller than a second threshold value, smaller than the first threshold value and, if it is, the method further comprising: outputting a feedback message indicating that too little hair has been loaded into the apparatus, so as to prompt the user to modify the amount of hair loaded into the apparatus accordingly, and / or controlling the temperature or the power output of the one or more heating zones of the plurality of controllableheating zones which are engaged with the hair, to avoid the hair loaded into the apparatus being burnt.

21. The method according to claim 19 or 20, wherein the apparatus comprises a user interface for outputting afeedback message to the user, the user interface comprising at least one of a sound generator, lighting means and / or a haptic feedback generator, the method further comprising: producing a first feedback, when it is determined that the hair tress size corresponds to a desired amount of hair, and producing at least one second feedback different from the first feedback, otherwise, thus prompting the userto modify the amount of hair loaded in the apparatus, optionally wherein the user interface is configured to output a second feedback, to prompt the user to increasethe amount of hair loaded in the apparatus, and / or to output a third feedback, to prompt the user to decrease theamount of hair loaded in the apparatus.

22. The method according to any of claims 19 to 21, wherein, if it is determined that the determined hair tresssize is greater than the threshold value and thus is bigger than a desired amount of hair, the method further comprising: capping the increase in the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, so as to enable a better drying or styling of the hair which is loaded in the apparatus while avoiding burning of the hair.

23. The method according to any of claims 20 to 22, wherein, if it is determined that the determined hair tresssize is smaller than the second threshold value and thus is smaller than a desired amount of hair, the method furthercomprising: turning off the heater or reducing the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, to prevent the hair being burnt.

24. A computer program product comprising computer implementable instructions for causing a programmabledevice to carry out the method of any of claims 19 to 23.

25. Apparatus for drying or styling hair, the apparatus comprising: a heater comprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independently controllable heating zones of the hair contacting surface; a memory that stores a trained classifier configured to classify the hair of the user of the apparatus into a class among a plurality of reference hair classes; and a controller coupled to the memory and configured to control the apparatus to:determine a power demand of the apparatus, based on a temperature of the plurality of independently controllable heating zones or based on the power output needed to maintain each heating zone of the plurality of heating zones at a target temperature; determine a hair tress size which has been loaded by the user into the apparatus, by determining, based on a drop of the temperature of one or more heating zones of the plurality of independently controllable heating zones or based on an increase in the power output needed to maintain the one or more heating zones at the target temperature, whether hair is engaged with the one or more heating zones, and, if it is, by determining an amount of hair which is engaged with the one or more heating zones, the hair tress size being determined based on the amount of hair engaged with the one or more heating zones across all of the one or more heating zones; use the stored trained classifier to determine the type of hair of the user by classifying the hair into a reference hair class, based on the determined power demand and the determined hair tress size; cause the apparatus to control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined hair type.

26. The apparatus of claim 25, further comprising:communication circuitry such that the apparatus is configured to receive user input information from an external processing device, and wherein the user input information is input on a user interface associated with the user and configured to enable the user to input the input information.

27. The apparatus according to claim 26, wherein the external processing device is part of a mobile phone and / ora smart watch and / or tablet and / or other such device and is configured to run an application, remote from the apparatus.

28. The apparatus according to claim 26 or 27, wherein the controller is further configured to control the apparatusto use the stored trained classifier such that the plurality of reference hair classes into which the hair of the user is to be classified is narrowed down to a subset of the plurality of reference hair classes, based on the received user input information.

29. The apparatus according to claim 28, wherein the user input information comprises at least one of:an indication by the user of the hair type they believe they have; a result from the user answering a questionnaire about their hair and / or the environment, optionally wherein the memory is configured to store the user input information, optionally wherein the stored input information isconfigured to be updated.

30. The apparatus according to any of claims 25 to 29, wherein the controller is configured to: determine a grip pressure based on data associated with a pressure sensor configured to measure a pressure between movable arms of the apparatus; and cause the apparatus to use the stored trained classifier to determine the type of hair of the user, further based on the grip pressure.

31. The apparatus according to any of claims 25 to 30, wherein the controller is configured to: determine a motion of the apparatus when the user is styling or drying their hair, based on data associated with one or more motion sensors of the apparatus; andcause the apparatus to use the stored trained classifier to determine the type of hair of the user, further based on the motion of the apparatus.

32. The apparatus according to claim 31, wherein the one or more motion sensors of the apparatus comprise anyone or more of an accelerometer, a gyrometer, a magnetometer, an inclination sensor, and wherein the motion of the hair styling or drying appliance comprises: a rotation of the apparatus when styling or drying the hair; and / or a speed of movement of the apparatus when styling or drying the hair.

33. The apparatus according to any of claims 25 to 32, wherein the controller is configured to: process further sensor data to determine diagnostic information about the hair being styled or dried; and cause the apparatus to use the stored trained classifier to determine the type of hair of the user, further based on the determined diagnostic information.

34. The apparatus of claim 33, wherein the diagnostic information comprises at least one of: a level of moisturein the hair, a humidity ambient to the hair being styled or dried, a temperature ambient to the hair being styled or dried, a geographic location of the hair being styled or dried.

35. The apparatus according to any of claims 25 to 34, wherein the controller is configured to control the temperature or the power output of the one or more heating zones by capping the increase in the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones based on the determined type of hair, toavoid the hair being burnt.

36. The apparatus according to any of claims 25 to 35, wherein the plurality of reference hair classes comprises nine reference classes, referred to as (1a, 1b, 1c, 2a, 2b, 2c, 3a, 3b, 3c), the class 1a corresponding to fine, straight blonde hair and the class 3c corresponding to thick, curly dark hair, and wherein the controller is configured to set the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined type of hair with reference to the nine reference classes.

37. The apparatus according to claim 36, wherein the controller is configured to set the target temperature or the power output of the one or more heating zones of the plurality of controllable heating zones so as to enable a better drying or styling of the hair which is loaded in the apparatus.

38. The apparatus of any of claims 25 to 37, wherein the trained classifier comprises a machine learning algorithmcomprising a convolutional neural network.

39. The apparatus according to any of claims 25 to 38, wherein the apparatus is a hair straightener, a hair dryer,a hot paddle brush, a hot round brush, a heated roller, or a hair curler.

40. A method for generating a classifier configured to classify hair of a user of apparatus for drying or styling hair,into a class among a plurality of reference hair classes, the method comprising: obtaining a plurality of annotated training streams of data; and training the classifier by applying a machine learning algorithm to the obtained training streams of data, wherein the annotation indicates the class of hair associated with each training stream of data, and wherein the plurality of annotated training streams of data comprises, for each class of hair among the plurality of reference hair classes:a training stream of data corresponding to a power demand of the apparatus when styling or drying hair belonging to the class of hair; and a training stream of data corresponding to a hair tress size which is typically loaded in the apparatus when styling or drying hair belonging to the class of hair.

41. The method according to claim 40, wherein the classifier is trained to minimize a classification loss betweenthe annotated class of hair associated with each training stream of data and a classification of the hair determined by the classifier.

42. The method of claim 41, wherein the classification loss comprises a similarity metric of Lp-norm, p being aninteger greater or equal to 1, such as an average absolute deviation or a least mean square distance.

43. The method of any of claims 40 to 42, wherein the plurality of training streams of data comprises, for eachclass of hair among the plurality of reference hair classes: a training stream of data corresponding to sensor data indicative of a grip pressure between movable arms of the apparatus when styling or drying hair belonging to the class of hair; and / or one or more training streams of data corresponding to sensor data indicative of a motion of the apparatus when the user is styling or drying hair belonging to the class of hair, optionally wherein the motion of the hair styling or drying appliance comprises: a rotation of the apparatus when styling or drying the hair; and / or a speed of movement of the apparatus when styling or drying the hair; and / or a training stream of data corresponding to sensor data indicative of diagnostic information about the hair being styled or dried.

44. The method according to any of claims 40 to 43, wherein the classifier is trained to classify the hair of the userinto a subset of the plurality of reference hair classes, based on user input information.

45. The method according to claim 44, wherein the user input information comprises at least one of:an indication of a suspected use’s hair type; a result from a questionnaire about their hair and / or the environment.

46. The method of any of claims 40 to 45, wherein the machine learning algorithm comprises a convolutional neural network.

47. A method of producing apparatus for drying or styling hair, wherein the apparatus comprises a heatercomprising a hair contacting surface for heating hair of a user that contacts the hair contacting surface by conduction, the heater comprising a plurality of independently controllable heater electrodes that define a plurality of independentlycontrollable heating zones of the hair contacting surface, a memory and a controller coupled to the memory, the methodcomprising: obtaining a classifier generated by the method according to any one of claims 40 to 46; and storing the obtained classifier in the memory of the appliance, the controller being configured to control the apparatus to: use the stored trained classifier to determine the type of hair of the user by classifying the hair into a reference hair class; cause the apparatus to control the temperature or the power output of the one or more heating zones of the plurality of controllable heating zones which are engaged with the hair, based on the determined hair type.

48. The method of claim 47, wherein the storing comprises transmitting the generated classifier to the apparatus via a network, the apparatus receiving and storing the classifier, optionally wherein the classifier is generated, stored and / ortransmitted in the form of one or more of: a data representation of the classifier; executable code for applying theclassifier.

49. A computer program or a computer program product comprising instructions which, when executed by aprocessor, enable the processor to perform the method according to any one of claims 40 to 48.

Images