Personal Care Devices

Abstract

The personal healthcare device monitors one or more parameters that allow the current use angle to be obtained. For example, there may be motion sensors to monitor acceleration and angular velocity. The current use angle is compared to the ideal use angle. A light output ring around the handle of the device is used to provide feedback to the user of the device. Rotating lighting effects indicate the direction of rotation of the device needed to approach the ideal use angle.

Description

[Technical Field]

[0001] The present invention relates to personal care devices, and in particular to handheld devices that assist users in achieving optimal operation of the device, for example, toothbrushes that assist users in achieving good brushing technique. [Background technology]

[0002] In order for a person to brush their teeth properly and prevent future oral health problems, their brushing technique must ensure that all teeth and gums are properly cleaned.

[0003] The American Dental Association, for example, recommends brushing for two minutes twice a day with fluoride toothpaste. This guideline does not go into much detail about the various aspects that make or break a good brushing session. One should, of course, apply enough pressure, but not too much. All the different surfaces of the teeth should be brushed without skipping any tooth segments. These aspects are part of brushing technique and, combined with brushing habits (i.e., how often and for how long), are essential for maintaining good oral hygiene.

[0004] They are known to provide feedback to users and help them achieve good brushing habits. Most simple electric toothbrushes have a counter that guides users to brush for at least two minutes.

[0005] In more advanced toothbrushes, the toothbrush measures whether the appropriate amount of force is being applied and provides a warning when too much force is being applied. Additionally, known power toothbrushes can measure whether a user is scrubbing too hard. Ideally, a user of a power toothbrush should scrub less than a user of a manual toothbrush.

[0006] The latest generation Philips Sonicare Prestige 9900 toothbrush has coverage guidance that provides feedback on whether all tooth segments have been brushed for a sufficient amount of time, ensuring, for example, that users have brushed the insides of their front teeth for a sufficient amount of time, as these are areas that are typically forgotten. Summary of the Invention [Problem to be solved by the invention]

[0007] One aspect not addressed by currently available toothbrushes is ensuring that users brush their teeth at the correct brushing angle. Using the correct brushing angle (45 degrees), also known as the bath angle technique, can result in better removal of plaque near the gum line.

[0008] US8393037 discloses a toothbrush that determines which tooth segments are to be brushed, the force to be applied, and the brushing angle. For example, a notification alert in the form of an audible beep is used to provide guidance to the user to tilt the toothbrush to an optimal brushing angle (e.g., 35 to 55 degrees). Audio, light, or vibration outputs can also be used. However, these do not provide an output signal that is intuitive to the user.

[0009] Instead, once the brushing angle is measured, deviations from the ideal brushing angle need to be translated into an easily interpretable feedback signal to guide the user to rotate the toothbrush clockwise or counterclockwise towards the ideal angle.

[0010] US20196 / 082819 discloses a toothbrush with an illumination ring around the top of the handle (between the handle and the head). The toothbrush has an acceleration sensor for detecting the angle of the toothbrush. The illumination ring is used to indicate whether the toothbrush is on or off and different toothbrush angles. The illumination ring can be controlled to different intensities and different flashing frequencies.

[0011] US2013 / 074616 discloses a toothbrush equipped with a sensor that detects brushing patterns and also discloses an illuminated ring around the toothbrush body. The illuminated ring is used to indicate when the detected brushing pattern matches a standard, allowing the user to proceed to the next brushing area. [Means for solving the problem]

[0012] The invention is defined by the claims.

[0013] According to an example in accordance with an aspect of the present invention, there is provided a personal care device comprising:

[0014] an instrument head and an instrument handle;

[0015] a sensor that provides a sensor output that is dependent on the movement or orientation of the device;

[0016] a light output ring that creates a rotating lighting effect around the device handle;

[0017] and a controller for processing the sensor output, the processor comprising:

[0018] Obtain the current angle of use from the sensor output,

[0019] Determine the ideal angle of use

[0020] Compare the current angle of use with the ideal angle of use, and

[0021] The light output ring is configured to control and provide feedback to a user of the device, with the rotation of the rotating lighting effect indicating the direction of rotation of the device required to approach the ideal angle of use.

[0022] The present invention provides a device that provides user feedback, including real-time feedback on the device to obtain a use angle and rotate the device toward a better use angle. The controller can also provide offline feedback on how the use angle was applied in previous personal healthcare sessions.

[0023] For example, the ideal angle of use will depend on the location of the device.

[0024] The sensor may be for measuring movement or orientation. For example, it may comprise an inertial monitoring unit, such as an accelerometer and a gyroscope, to measure movement as acceleration and angular velocity of the device. Another example is a force sensor to measure (reaction) force on the device head (as a vector with magnitude and direction). This can be used to obtain the angle between the device head and the surface to which the force is applied. Thus, various sensors can be used to determine the current angle of use.

[0025] The controller is preferably configured to generate a light animation having a clockwise or counterclockwise lighting pattern around the light ring. User feedback is thus provided using the light ring to generate a visible clockwise or counterclockwise pattern. The light output ring, for example, comprises a ring of LEDs defining a set of angle segments.

[0026] The light output ring may be around the base of the device handle opposite the device head. Alternatively or additionally, the light output ring may be around the top of the device handle adjacent the device head.

[0027] The controller may include an AI model for determining the angle of use, which provides an accurate method for obtaining the current angle of use. The AI ​​model may, for example, have a long-short-term memory (LSTM) model.

[0028] In one set of examples, the personal healthcare device includes an electric toothbrush with a toothbrush head and a toothbrush handle, the angle of use is a brushing angle, and the processor: determining a current tooth segment on which the toothbrush head is located; The ideal brushing angle is configured to be determined by determining the ideal brushing angle based on the current brushing segment.

[0029] Therefore, the ideal brushing angle may depend on the particular brushing segment in which the toothbrush head is located.

[0030] Brushing at the correct angle, also known as the bass angle technique, results in greater plaque removal at the gum line, thus the device provides assistance to the user in achieving optimal brushing technique.

[0031] The controller can be configured to compare the current use angle with the ideal use angle using both the sine and cosine values, allowing the direction in which rotation is required (and the amount of rotation required) to be determined.

[0032] The controller a first neural network for determining a brushing angle; a second neural network for determining brushing segments; and a comparator that compares the ideal brushing angle with the current brushing angle.

[0033] The first neural network, for example, has an LSTM layer and an output layer that predicts the angle (e.g., a convolutional layer with a two-channel output that provides the sine and cosine components of the brushing angle). The second neural network determines the position of the toothbrush head so that the brushing segment can be identified.

[0034] A lookup table can be used that stores ideal brushing angle values ​​for each segment. Thus, the ideal brushing angle can be obtained using the output of the second neural network. Furthermore, a time threshold can be introduced that displays the light animation only when brushing at an incorrect brushing angle for more than a predetermined time (e.g., 4-10 seconds).

[0035] The present invention also provides a method of providing angle of use guidance for a personal healthcare device having a device head and a device handle, the method comprising: receiving a sensor output that is dependent on the motion or orientation of the device; processing the sensor output to obtain a current angle of use; determining an ideal angle of use; comparing the current use angle with the ideal use angle; and providing feedback to a user of the device by controlling a light output ring around the device handle to generate a rotating lighting effect around the device handle, the rotation of the rotating lighting effect indicating the direction of rotation of the device required to approach the ideal angle of use.

[0036] The rotation speed and light intensity of the rotating light effect may depend on the brushing angle error (ie, the difference between the ideal angle and the measured angle).

[0037] Controlling the light output ring preferably comprises generating a light animation having a clockwise or counterclockwise lighting pattern around the light ring.

[0038] The method may include using an AI model to determine the angle of use.

[0039] When the method is implemented with an electric toothbrush, the angle of use comprises a brushing angle, and the method further comprises: determining the current tooth segment on which the toothbrush head is located from the sensor output; and determining an ideal brushing angle based on the current brushing segment.

[0040] The present invention also provides a computer program comprising computer program code means adapted to implement the method defined above when the computer program is executed on a computer.

[0041] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter. [Brief explanation of the drawings]

[0042] [Figure 1] FIG. 1 shows a personal care device in the form of a toothbrush. [Figure 2] FIG. 10 is a diagram showing angle symbols for explaining brushing angles. [Figure 3] FIG. 1 illustrates an AI model for angle prediction. [Figure 4] FIG. 10 shows an example of predicted brushing angles as a function of time. [Figure 5] FIG. 10 shows an example of predicted brushing angles as a function of time. [Figure 6] FIG. 1 illustrates an AI model for brushing segment prediction. [Figure 7] This diagram shows two AI models merged into one. [Figure 8] 10A-10C illustrate a method for providing angle of use guidance. DETAILED DESCRIPTION OF THE INVENTION

[0043] For a better understanding of the present invention, and in order to show more clearly how it may be carried into effect, reference will now be made to the accompanying drawings, which are given by way of example only, in which:

[0044] The present invention will now be described with reference to the figures.

[0045] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the devices, systems, and methods, are for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the devices, systems, and methods of the present invention will be better understood from the following description, appended claims, and accompanying drawings. It should be understood that the figures are schematic only and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the figures to indicate the same or similar parts.

[0046] The present invention provides a personal healthcare device that monitors one or more parameters that allow the current use angle to be obtained. For example, there may be motion sensors to monitor acceleration and angular velocity. The current use angle is compared to an ideal use angle. A light output ring around the handle of the device is used to provide feedback to the device user. Rotating lighting effects indicate the direction of device rotation required to approach the ideal use angle.

[0047] FIG. 1 shows a personal care device in the form of a toothbrush that can be designed and controlled in accordance with the present invention.

[0048] The toothbrush 100 has a head 102 and a handle 104. The handle 104, in this example, has an inertial monitoring unit 106 for monitoring the movement of the device, preferably housing sensors including an accelerometer and a gyroscope, which measures the acceleration and angular velocity of the device, preferably three-axis acceleration and three-axis angular velocity. Any suitable known motion tracking sensor can be used.

[0049] Other parameters can additionally or alternatively be sensed, allowing the angle of the head to be obtained, for example using a force sensor to monitor the force the head exerts on the teeth.

[0050] A controller 108 processes the outputs provided by the sensors. In this example, the measured movement is processed to obtain, for example, acceleration and angular velocity. The controller controls the light output rings to provide feedback to the user. The feedback is a rotating lighting effect around the device handle. In the example shown, there is a first light output ring 110 around the base of the device handle opposite the device head and a second light output ring 112 around the top of the device handle adjacent the device head.

[0051] There may be only one light output ring, two, or more than two.

[0052] In its simplest implementation, the light output ring (or each light output ring) has multiple LEDs in a circular arrangement. The LEDs can shine directly onto the outside of the toothbrush, or a plastic light guide can be used to direct light from a printed circuit board (PCB) where the LEDs are located on the outside of the toothbrush. For example, a convincing rotational animation can be achieved using only eight LEDs. As a result, there are preferably between eight and thirty segments around the circumference of the ring. The ring extends around the longitudinal axis of the handle.

[0053] The controller obtains the current use angle from the sensor output, which in this example is the measured acceleration and angular velocity. In the case of a toothbrush, the use angle is the brushing angle. The controller also determines an ideal use angle and compares the current use angle to the ideal use angle. The ideal use angle depends on the position of the device, e.g., in the case of a toothbrush, the tooth segment on which the device is used. The light output ring(s) are controlled so that a rotation of the lighting effect indicates the direction of device rotation of the toothbrush required to approach the ideal use angle.

[0054] It is noted that existing toothbrushes already include light rings on the top or bottom of the toothbrush handle that allow user feedback while brushing. These light rings are driven, for example, by red / green / blue (RGB) LEDs, and different colors can represent different feedback messages.

[0055] The light ring used in the device of the present invention is divided so that an animation can be generated that provides a rotational effect around the toothbrush handle, which then guides the user to provide the appropriate device rotation (in the same direction as the rotational direction of the rotating lighting effect) to readjust the device to the most appropriate use (i.e., brushing) angle.

[0056] Preferably, an AI model is used to determine the current use angle. To illustrate this implementation, a detailed example of toothbrush application is presented. In this application, tooth segment determination is also required because the brushing angle depends on the tooth segment. Therefore, a brushing segment prediction model is also used.

[0057] To predict brushing angle using an AI model, the model needs to be trained, which requires input data (IMU signals) and ground truth data that provides the ideal output.

[0058] When building a brushing segment prediction model, we can rely on manual annotators who watch videos of users brushing their teeth and label tooth segments x when they brush their teeth at time step t. For the 16-segment model, x is an integer between 1 and 16, indicating the 16 segments corresponding to the combinations of left / front / right, upper / lower, and inner / biting / outer tooth segments.

[0059] When building a brushing angle prediction model, annotators cannot easily determine the brushing angle between the toothbrush and the teeth / gums from videos. Therefore, a motion tracking system is used to generate ground truth data. To generate ground truth data, users are asked to wear a headband, use a toothbrush, and brush using special motion tracking markers in front of the motion tracking system.

[0060] Based on the output of the motion tracking system, the position and orientation of the toothbrush can be determined relative to the teeth because the upper teeth are firmly connected to the head with a headband equipped with motion tracking markers.

[0061] Figure 2 shows the brushing angle, with the upper side of the image representing the upper teeth and the lower side representing the lower teeth. P indicates the point where the hair touches the tooth, TIFF2025537111000002.tif77 shows the vector from P along the bristles toward the brush.

[0062] In P, a coordinate system consisting of three orthogonal vectors t is defined, TIFF2025537111000003.tif77: From left to right, tangent to the parabolic tooth curve (in the plane of the jaw), TIFF2025537111000004.tif67: Outer normal to tooth curve (in the plane of the jaw), TIFF2025537111000005.tif79: "Up" normal to the jaw plane.

[0063] If P is on the upper teeth, the brushing angle β is It is specified as TIFF2025537111000006.tif1287.

[0064] If P is on the lower teeth, the brushing angle β is It is specified as TIFF2025537111000007.tif1083.

[0065] The vector operation is an inner product (or dot product) and therefore provides a scalar number, which is applied to the arctan2 function to obtain the brushing angle.

[0066] The arctan2 function has two arguments: it accepts the cosine and sine components (or x and y components) and can calculate the appropriate quadrant into which the resulting angle lies.

[0067] These values ​​can be converted to degrees by multiplying by 180 / π.

[0068] These transformations are vectors TIFF2025537111000008.tif86 and TIFF2025537111000009.tif88 encodes the geometric function that projects the hair onto the plane spanned by TIFF2025537111000010.tif87 (upper jaw) or TIFF2025537111000011.tif65 is the angle between the lower jaw and the projected hair.

[0069] Therefore, the brushing angle is (i) (ii) the tooth plane determined by TIFF2025537111000012.tif711 The angle between two planes, the plane of the toothbrush, determined by TIFF2025537111000013.tif811.

[0070] Based on the definition and interpretation of angles, three categories of user movements when brushing specific teeth can be defined.

[0071] (i) Toothbrushes are TIFF2025537111000014.tif79 Rotation around the axis (gum line). Angle detection and coaching focuses on coaching such movement to optimally stay at a 45 degree bass angle.

[0072] (ii) The toothbrush moves in the plane of the teeth. This type of movement can generally be achieved by holding the brush vertically rather than horizontally. To maximize contact with the jawline, users should be encouraged to hold the brush horizontally.

[0073] (iii) The toothbrush moves in the toothbrush plane. This type of movement does not seem natural because it moves the toothbrush away from the tooth surface. However, it can occur when the toothbrush moves from one tooth to another.

[0074] In particular, actions under (i) and (ii) will be monitored and guided.

[0075] The algorithm calculates the brushing angle β for each time step of the brushing session (typically 1 / 30th of a second) and stores it in combination with the IMU sensor data.

[0076] During the training procedure, IMU data is used as input, and the ideal brushing angle serves as the ground truth that the feedback strives to achieve. During the training procedure, sensor data is used as input, and the ideal brushing angle serves as the ground truth that the AI ​​model's output is compared to. During the training procedure, the AI ​​model's parameters are updated so that the angle prediction is as close as possible to the ground truth angle (by minimizing the difference).

[0077] Therefore, when the AI ​​model predicts brushing angles, it minimizes the difference from the ideal brushing angle. This difference (loss function) should converge. When naively using the simple mean absolute difference in angles, there is a potential problem arising from the circular definition of these angles: here, an angle of -179 degrees is only 2 degrees away from an angle of +179 degrees.

[0078] To address this issue, the cosine and sine components of the brushing angle are predicted (effectively a vector of length = 1), and the ground truth is also transformed into the cosine and sine of the ground truth angle. Then, the loss function (i.e., the loss to be minimized during training) can be expressed as 1 minus cosine similarity, The result is TIFF2025537111000015.tif1662.

[0079] The loss function is the dot product between 1 minus 2 vectors.

[0080] Instead of this loss formulation, cosine similarity can be used to determine the angle error (difference) and calculate the mean square (or mean absolute) error of this error angle.

[0081] In either case, the current use angle is compared to the ideal use angle using a metric based on sine and cosine values.

[0082] 3, the AI ​​model for angle prediction consists of an encoder 200, an LSTM layer 202, and a decoder 204. The brushing angle prediction is provided as output 205.

[0083] In the encoder 200, the input IMU sensor signal is filtered (linearly) in a convolutional layer 200a and scaled in a batch normalization layer 200b. This filtered signal enters an LSTM layer 202, which updates its internal state (also called the hidden state).

[0084] The hidden state of the LSTM is then used as input to the decoder 204, which maps the hidden state to two channels (using a convolutional layer 204a with two output channels and a kernel size of 1).

[0085] As a final step, these two channels are normalized in step 204b to represent a vector of length one.

[0086] 4 and 5 show examples of predicted brushing angles as a function of time.

[0087] In each case, one plot is the predicted brushing angle versus time, and the other plot is the ground truth brushing angle versus time. The two plots are for two different brushing sessions. Figures 4 and 5 show the brushing angle prediction accuracy.

[0088] The AI ​​model can determine the orientation of the toothbrush relative to the teeth, but not relative to the real world (i.e., the gravity vector). To this end, the AI ​​model takes into account head tilt, which cannot be achieved using a simple accelerometer system such as that disclosed in US8393037, nor using the simple mathematical formulas disclosed. In particular, the AI ​​can learn from large amounts of data to improve its predictions.

[0089] Figure 6 shows the real-time model of brushing segment prediction. The angle prediction model has a very similar architecture to the real-time model of brushing segment prediction.

[0090] The same encoder 200 and LSTM layer 202 are used. Only the decoder is different, which consists of a classifier 300 with multiple convolutional batch network corrected linear unit layers 300a, 300b, 300c, or "conv-bn-relu" layers. For classification and segmentation problems, the decoder typically ends with a softmax layer 300d, representing probabilities that sum to 1. Brushing segment predictions are provided as output 301.

[0091] The similarity of the architecture allows the encoder / LSTM weights in the brushing segment prediction model to be reused for the angle prediction model. This can result in better angle prediction because the brushing segment model is trained on a larger dataset with segment labels. The decoder can, for example, be trained on a dataset where brushing angles are available, or the encoder / LSTM layers can be fine-tuned after certain training epochs (transfer learning).

[0092] By having two different output heads but only one encoder and LSTM, the two AI models can be unified into one model that predicts brushing segments and brushing angles simultaneously.

[0093] This is shown in Figure 7, where one head predicts the brushing segments and another predicts the brushing angle. This model is much smaller than having two separate models (only slightly larger than the original brushing segment model, since the decoder in the angle prediction model is very small).

[0094] The controller has a comparator whose output is used to control a light ring, which determines the brushing angle for the current brushing segment. Each brushing segment has a target brushing angle βtarget. If the user brushes a segment for more than τ seconds while being more than Δ degrees away from the target brushing angle, the light ring displays an animation to the user, indicating that they should rotate the toothbrush clockwise or counterclockwise (towards the target brushing angle).

[0095] Both the target brushing angle βtarget and the range Δ are segment dependent. The delay time τ before the indication is provided ranges, for example, from 4 to 10 seconds.

[0096] To achieve a smooth coaching experience, the target coaching angle can start at a typical angle related to the user's personal situation (e.g., the average angle from the last 10 sessions, or a typical angle for a population). Over time, the target angle can be moved closer to the ideal bass angle (45 degrees). A typical / personal value is used to avoid providing excessive angle feedback directly.

[0097] The above examples utilize a light output ring formed as a line of individual LEDs. The light output ring may alternatively be based on a scroll display, which allows a light movement pattern to be displayed not only along the longitudinal axis of the toothbrush, but also around the toothbrush (radially). A small (bright) display (e.g., flat) can be used in combination with a light guide to direct the light output to different segments that form the light ring around the handle.

[0098] The angle prediction model can also be run offline for post-brushing analysis to provide brushing insights in a brushing report. For example, a report can be provided on how much of the brushing time was at the correct angle (using bus angle technology) for each segment. Additionally, more detailed brushing angle and time-related information can be provided for the last brushing session. Examples of suitable statistics are the mean or median brushing angle (per tooth segment), standard deviation, amount of jawline covered (percentage), and amount of teeth covered (percentage).

[0099] The real-time angle coaching feedback is not limited to being realized only in the light ring of the electric toothbrush: additional feedback can be realized in another device connected to the toothbrush, such as a charging station, a smartphone, or other smart gadget.

[0100] Next generation toothbrushes will have integrated directional force sensors. Such force sensors can be used to measure the direction of the force the brush head exerts on the teeth / gums. This provides an additional way to measure (or verify) the angle of brushing.

[0101] FIG. 8 illustrates a method for providing angle of use guidance to a personal healthcare device having a device head and a device handle.

[0102] In step 400, the measured acceleration and angular velocity of the device are received. In step 402, they are processed to obtain a current use angle. In step 404, an ideal use angle is determined, and in step 406, the current use angle and the ideal use angle are compared.

[0103] The light output ring around the device handle is controlled in step 408 to provide feedback to the device user, as described above.

[0104] The above example is based on a toothbrush, which monitors the angle of brushing, however, the correct operation of other personal care products, such as shavers and intense pulsed light (IPL) photo-hair removal devices, depends on the correct angle of use.

[0105] Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the figures, the disclosure and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0106] The functions performed by a processor may be performed by a single processor or by multiple individual processing units which together may constitute a “processor.” Such processing units may, in some cases, be remote from each other and in wired or wireless communication with each other.

[0107] The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0108] The computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless communication systems.

[0109] It should be noted that when the term "adapted to" is used in the claims or the specification, it is intended to be equivalent to the term "configured to." It should be noted that when the term "arrangement" is used in the claims or the specification, it is intended to be equivalent to the term "system," and vice versa.

[0110] Any reference signs in the claims should not be construed as limiting the scope of the invention.

Claims

1. 1. A personal healthcare device, comprising: an instrument head and an instrument handle; a sensor providing a sensor output dependent on a movement or orientation of the device; a light output ring that creates a rotating lighting effect around the device handle; a controller for processing the sensor output, the controller comprising: Obtaining the current angle of use from the sensor output; Determine the ideal angle of use Comparing the current use angle with the ideal use angle; and 1. A personal healthcare device configured to control the light output ring to provide feedback to a user of the device, wherein rotation of the rotating lighting effect indicates the direction of device rotation required to approach the ideal angle of use.

2. 10. The apparatus of claim 1, wherein the light output ring comprises a ring of LEDs defining a set of angular segments.

3. 3. The device of claim 1 or 2, wherein the controller generates a light animation comprising a clockwise or counterclockwise lighting pattern around the light ring.

4. 4. The device of claim 1, wherein the light output ring is around the base of the device handle, opposite the device head.

5. 5. The device of claim 1, wherein the light output ring is located around the top of the device handle, adjacent the device head.

6. 6. The device of claim 1, wherein the controller comprises an AI model for determining the angle of use.

7. The apparatus of claim 6 , wherein the AI ​​model comprises an LSTM model.

8. 8. The apparatus of claim 1, wherein the controller compares the current use angle to the ideal use angle by comparing a metric based on sine and cosine values.

9. an electric toothbrush having a toothbrush head and a toothbrush handle, the angle of use being a brushing angle, and the controller determining a current tooth segment on which the toothbrush head is located; 9. A personal care device according to any preceding claim, wherein the ideal brushing angle is determined by determining the ideal brushing angle based on a current brushing segment.

10. The controller: a first neural network for determining the brushing angle; a second neural network for determining the brushing segments; 10. The device of claim 9, further comprising a comparator for comparing the ideal brushing angle with the current brushing angle.

11. 1. A method of providing angle of use guidance for a personal healthcare device having a device head and a device handle, comprising: receiving a sensor output dependent on the movement or orientation of the device; processing the sensor output to obtain a current use angle; determining an ideal angle of use; comparing the current use angle with the ideal use angle; and controlling a light output ring around the device handle to provide feedback to a user of the device by generating a rotating lighting effect around the device handle, the rotation of the rotating lighting effect indicating the direction of device rotation required to approach the ideal angle of use.

12. The method of claim 11 , wherein controlling the light output ring comprises generating a light animation having a clockwise or counterclockwise lighting pattern around the light ring.

13. 13. The method of claim 11 or 12, comprising using an AI model to determine the use angle.

14. 14. The method of any one of claims 11 to 13 implemented with an electric toothbrush, wherein the angle of use comprises a brushing angle, the method further comprising: determining the current tooth segment on which the toothbrush head is located from the sensor output; and determining an ideal brushing angle based on the current brushing segment.

15. A computer program comprising computer program code means adapted to implement the method of any one of claims 11 to 14 when the computer program is run on a computer.

Images