Aerosol generating system and computer-implemented method

Abstract

The aerosol generating system includes an aerosol generating device configured to accept each of a plurality of aerosol-generating substrates and generate a respective aerosol for inhalation by a user, a feedback interface for receiving user response data of the user in response to inhaling the generated aerosol, and a preference identification system configured to obtain the user response data from the feedback interface for each of the plurality of aerosol-generating substrates and identify a recommended aerosol for the user based on the user response data.

Description

[Technical field]

[0001] The present disclosure relates to an aerosol generating device in which an aerosol-generating substrate is aerosolized for inhalation by a user of the device. The present disclosure also relates to a method of controlling aerosol generation by an aerosol generating device. [Background technology]

[0002] The popularity and use of risk reduction or risk modification devices (also known as vaporizers) has grown rapidly in recent years as an aid to assist habitual smokers wishing to quit smoking traditional tobacco products such as cigarettes, cigars, cigarillos, and rolling tobacco. A variety of devices and systems are available that heat or warm an aerosolizable substance, as opposed to burning tobacco in traditional tobacco products.

[0003] Different users of such devices have different preferences for the composition of the aerosol they inhale. For example, different users may desire different nicotine strengths or different flavors. It is known to provide a range of aerosol-generating substrates for use as options in an aerosol-generating device. In this way, a range of aerosol compositions can be presented for a single aerosol-generating device.

[0004] However, known systems require the user to identify the recommended composition of the aerosol to be inhaled. It would be desirable to provide an aerosol generating system that can assist the user in identifying those recommended aerosol compositions. Summary of the Invention [Means for solving the problem]

[0005] According to a first aspect, there is provided an aerosol generation system comprising: an aerosol generating device configured to receive each of a plurality of aerosol-generating substrates and generate a respective aerosol for inhalation by a user; a feedback interface for receiving user response data of a user in response to inhaling the generated aerosol; An aerosol generating system is provided, comprising: a preference identification system configured to obtain user response data from a feedback interface for each of a plurality of aerosol-generating substrates, and to identify a recommended aerosol for the user based on the user response data.

[0006] The user response data may be involuntary response data and / or voluntary response data. More specifically, an "involuntary response" is a user response that is not consciously selected and that may be measured without the user's conscious involvement. In contrast, a "voluntary response" is deliberate user feedback, for example by pressing a button or entering a rating in a graphical user interface.

[0007] Optionally, the preference identification system is configured to obtain initial user response data from the feedback interface for each of a plurality of aerosol-generating substrate samples, the plurality of aerosol-generating substrate samples being provided in a pack, and to identify an initial recommended aerosol for the user based on the initial user response data. In this manner, the user is guided through trying out an initial set of aerosol-generating substrates to select a recommended aerosol and to identify a corresponding aerosol-generating substrate that the user may advantageously use in the future.

[0008] Furthermore, each aerosol generated from a plurality of aerosol-generating substrate samples is optionally distributed across a sensory range of different compositions. For example, the sensory range may include a range of intensities of each of one or more aerosol components. By providing a sampling pack that includes a range of aerosol-generating substrates, the user has an improved chance of successfully identifying the most recommended aerosol within the available range.

[0009] Optionally, the preference identification system is further configured to obtain subsequent user response data from the feedback interface for one or more subsequent aerosol-generating substrates, and identify an updated recommended aerosol for the user based on the subsequent user response data and the initial recommended aerosol. In this manner, the aerosol generation system may iteratively improve the identification of the recommended aerosol for the user.

[0010] Optionally, the preference identification system is configured to identify a plurality of candidate recommended aerosols for the user based on the user response data, and present the plurality of candidate recommended aerosols in the user interface. By presenting the set of candidate recommended aerosols to the user, the system further improves the chances that the user will successfully and simply identify the most recommended aerosol.

[0011] Additionally, the preference identification system is optionally configured to receive a user selection of a recommended aerosol from among the candidate recommended aerosols. By allowing the user to select from among the candidate options, a simple interface is provided to the user for selecting an aerosol while increasing the chances that an aerosol that is particularly preferred by the user is included in the available options (candidate aerosols).

[0012] Optionally, the aerosol generating device is configured to simultaneously accept at least two of the plurality of aerosol-generating substrates and control which of the accepted aerosol-generating substrates is used to generate the aerosol. In this manner, the aerosol generating device can automatically switch between producing at least two different aerosols, improving user convenience in testing a range of aerosols.

[0013] Further, the aerosol generating device is optionally configured to receive an indication of a recommended aerosol and to control which of the accepted aerosol-generating substrates is used to generate the aerosol based on the recommended aerosol. In this manner, the aerosol generating system may automatically switch between generating the identified recommended aerosol.

[0014] Additionally, the aerosol-generating device optionally includes an aerosol-generating chamber and a substrate mixing element configured to mix multiple aerosol-generating substrates received simultaneously and to supply the mixed aerosol-generating substrate to the heating chamber. In this manner, the aerosol-generating device creates new aerosol-generating substrates and the user may identify a recommended aerosol to greater accuracy without being limited to a predefined set of possible aerosol-generating substrates.

[0015] Optionally, the preference identification system is configured to identify the recommended aerosol based on the user response data and a predefined model relating the user response data to aerosol preferences. By using the predefined model, the user's recommended aerosol may be more accurately identified using less data from a particular user.

[0016] Optionally, the preference identification system is configured to obtain user response data for each of a plurality of training users and train a model to predict a recommended aerosol based on the user response data for the plurality of training users. The trained model can then be used to identify a user's recommended aerosol using less data from the particular user.

[0017] Optionally, the feedback interface includes a sensor for measuring an involuntary response of the user, and the user response data includes an indication of the involuntary response. Using the involuntary response improves the accuracy and convenience of the system, since the user feedback is collected automatically with the involuntary response and the system does not have to rely on the user to accurately indicate or quantify aerosol preference.

[0018] Optionally, the sensor is configured to measure heart rate, blood pressure, skin temperature, or galvanic skin response, any of which are responses over which the user has no direct control and which may be used to infer levels of relaxation or stress, or to infer the quality of the user experience.

[0019] Optionally, the sensor is positioned on an outer surface of the housing of the aerosol generating device, in which case the sensor may be close to or in direct contact with the user when the user is holding the aerosol generating device, and the involuntary response may be measured without requiring any additional action by the user other than using the aerosol generating device.

[0020] Optionally, the feedback interface includes a voluntary response interface for receiving a voluntary response from the user in response to inhaling the generated aerosol, and the user response data includes an indication of the voluntary response. By obtaining the voluntary response, the system may improve the accuracy of identifying the recommended aerosol by calibrating the interpretation of the involuntary response. Alternatively, if a voluntary response is received, the system can be simplified by not measuring the involuntary response.

[0021] Optionally, the feedback interface includes an airflow sensor arranged to measure aerosol inhalation in the aerosol generating device when the user inhales the generated aerosol, and the user response data includes an indication of the aerosol inhalation. By measuring the aerosol inhalation, the preference identification system can additionally identify the recommended aerosol based on the duration of inhalation or the number of times the aerosol is inhaled as a criterion of the user's perception of the aerosol, thereby more accurately identifying the recommended aerosol.

[0022] Optionally, the aerosol-generating device includes substrate identification means for identifying the accepted aerosol-generating substrate, and the user response data includes an indication of the accepted aerosol-generating substrate. By providing a substrate identification means, accuracy and user convenience are improved without the user having to manually communicate to the preference identification system which aerosol-generating substrate they have used.

[0023] Optionally, the preference identification system is further configured to determine a health characteristic of the user based on the involuntary response data, and identifying the recommended aerosol comprises allowing or blocking the aerosol-generating substrate based on the health characteristic. By controlling the available aerosols based on the determined health characteristic, an aerosol that is more likely to be suitable for the user may be selected.

[0024] According to a second aspect, the present disclosure provides a pack comprising a plurality of aerosol-generating substrate samples each for generating a different respective aerosol in an aerosol generating system, the different respective aerosols being distributed across a sensory range of different compositions such that a recommended aerosol may be identified based on user response data obtained in response to inhaling each of the aerosols.

[0025] According to a third aspect, the present disclosure provides a kit comprising a pack according to the second aspect and an aerosol generating device configured to receive each of a plurality of aerosol-generating substrates and generate a respective aerosol for inhalation by a user, the kit being for use in an aerosol generating system according to the first aspect.

[0026] According to a fourth aspect, the present disclosure provides a method and a computer program for operating the aerosol generating system according to the first aspect. The computer program may be stored as instructions in a memory storage medium or a data signal, or may be hard-coded into a circuit. In particular, the preference identification system may be implemented as software running on a computing system located in or in communication with the aerosol generating device and the feedback interface. More specifically, the present disclosure provides a method for controlling an aerosol generating system, the aerosol generating system comprising an aerosol generating device configured to receive an aerosol-generating substrate and generate a respective aerosol for a user to inhale, and a feedback interface for receiving user response data of the user in response to inhaling the generated aerosol, the method comprising: for each of a plurality of aerosol-generating substrates, generating a respective aerosol using the aerosol generating device, and obtaining user response data from the feedback interface, and identifying a recommended aerosol for the user based on the user response data. [Brief description of the drawings]

[0027] [Figure 1] FIG. 1 is a block diagram illustrating a schematic of an aerosol generating device and pack according to the present invention. [Diagram 2] FIG. 1 is a block diagram that illustrates a schematic of an aerosol generation system, according to an embodiment. [Diagram 3] 1 is a flow chart that generally illustrates a computer-implemented method for controlling an aerosol generation system. [Figure 4] 1 is a flow chart that generally illustrates optional features of a method for controlling an aerosol generation system. [Figure 5A] 11 is a flow chart that generally illustrates further optional features of a method for controlling an aerosol generation system. [Figure 5B] 1 is a graphical depiction of a trained model for identifying recommended aerosols. [Figure 5C] 1 is a flow chart that illustrates a schematic of a method for training a model. [Figure 6] FIG. 2 is a block diagram that illustrates a schematic representation of an alternative aerosol generating device according to the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] FIG. 1A shows a schematic representation of an aerosol generating device for use in an aerosol generating system according to the present invention.

[0029] The aerosol generating device 1 includes an aerosol generating chamber 12 and a control circuit 13 .

[0030] The aerosol-generating chamber 12 is configured to receive the aerosol-generating substrate 11. The aerosol-generating chamber 12 may, for example, take the form of a pot having an opening at one end that allows the aerosol-generating substrate 11 to be inserted and removed.

[0031] The aerosol-generating substrate 11 may, for example, take the form of a solid package that can be easily inserted into and removed from an aerosol-generating device. Alternatively, the aerosol-generating substrate may be a loose material or a liquid. By way of example, the substrate may comprise tobacco. The tobacco may, for example, comprise randomly oriented tobacco strands including tobacco powder and an aerosol-forming agent.

[0032] The aerosol-generating device 1 is configured to generate an aerosol from an aerosol-generating substrate 11, whereby the aerosol may be inhaled by a user. In the embodiment of Figure 1, the aerosol is generated by heating the aerosol-generating substrate 11 using a heater 121. The heater may be located on at least one side of the aerosol-generating chamber 12, for example in the form of a thin film heater or a ceramic heater, or may be located within the aerosol-generating chamber 12, for example in the form of a blade heater. The aerosol may alternatively be generated by other means, such as an atomizer or nebulizer.

[0033] The aerosol-generating device 1 may further include a mouthpiece through which a user obtains the aerosol generated in the aerosol-generating chamber 12. Alternatively, as shown in Figure 1, the aerosol-generating substrate 11 may be provided as part of a package that includes a disposable mouthpiece. More specifically, in the example of Figure 1, the aerosol-generating substrate 11 is provided in a cigarette-style package, with a wrapper 111 enclosing the substrate 11 and a filter 112.

[0034] The control circuit 13 is configured to control the heating element 121 and thereby the generation of the aerosol. The control circuit 13 is configured to draw power from a power source to control and drive the generation of the aerosol. The power source is preferably included in the aerosol generating device, for example in the form of a battery 14. Alternatively, the control circuit 13 may be provided with an external power source.

[0035] 1B, the aerosol-forming substrate 11 may be provided as part of a pack 2 which includes a plurality of aerosol-forming substrate samples 11B-11E. Each of the plurality of aerosol-forming substrate samples 11B-11E may be a different aerosol-forming substrate which generates a different aerosol.

[0036] Each aerosol generated from a plurality of aerosol-generating substrate samples may be distributed across a sensory range of different compositions. Users respond differently to each aerosol, and thus the range of aerosol-generating substrates will produce a range of different user response data, which may be used to identify a recommended aerosol.

[0037] More specifically, the aerosol-generating substrate may have a range of strengths of one or more respective aerosol components, for example, different substrates may have different strengths of nicotine, or different strengths of flavors such as mint.

[0038] The pack 2 shown in Figure 1B may be provided together with the aerosol generating device 1 shown in Figure 1A as a kit for use in an aerosol generating system.

[0039] Referring again to FIG. 1A, in this embodiment, the aerosol generating device 1 also includes a sensor 15 configured to measure the user's involuntary reaction as user reaction data in response to inhaling the generated aerosol. The involuntary reaction may indicate, for example, arousal or positive / negative emotion. Involuntary reactions that may be measured by the sensor 15 include heart rate, blood pressure, or galvanic skin response (galvanic skin response correlates with sweating) as indicators of arousal, or skin temperature as indicators of emotion. The involuntary reaction may, for example, be sampled at a sampling rate and averaged or normalized to reduce noise and baseline effects.

[0040] Sensor 15 may be located, for example, on the outer surface of the housing of the aerosol generating device. In this location, sensor 16 can contact the user's hand when the user is holding the aerosol generating device and measure a response through the fingertip. For example, a sensor located on the housing may be particularly suitable for measuring galvanic skin response and skin temperature.

[0041] Additionally, in the embodiment shown in FIG. 1, the aerosol generating device 1 includes an airflow sensor 16 positioned to measure aerosol inhalation in the aerosol generating device 1 when the user inhales the generated aerosol. This measured inhalation can be used as part of the user response data. The airflow sensor 16 may be located in or beside the mouthpiece, or may be located elsewhere in the aerosol generating chamber 12. The airflow sensor 16 is configured to measure aerosol inhalation by the user. This measured aerosol inhalation can include the length or amount of consecutive inhalations, the frequency or occurrence of inhalations, and / or the intensity or pressure drop of inhalation. The measured aerosol inhalation can be used in identifying a recommended aerosol. For example, a large number or percentage of puffs can indicate an aerosol that is enjoyable or pleasant, while a small number or percentage of puffs can suggest an aerosol that causes a longer-lasting response.

[0042] More generally, the aerosol generating system of the present invention (including the aerosol generating device 1) includes a feedback interface for receiving user response data of a user in response to inhaling the generated aerosol. The feedback interface may include sensor 15 and / or airflow sensor 16, and / or one or more further sensors that collect involuntary response data of the user in response to inhaling the generated aerosol.

[0043] The feedback interface may be separate from the aerosol generation device or may include multiple interfaces, each of which is part of the aerosol generation device or is separate from the aerosol generation device.

[0044] FIG. 2 is a block diagram that illustrates a schematic of an aerosol generation system, according to an embodiment.

[0045] 2, the feedback interface may include sensors in a wearable device 3, such as a smartwatch. Wearable sensors may be particularly suited to measuring involuntary responses such as heart rate or blood pressure through the skin, which cannot easily be measured through the fingertip.

[0046] As additionally shown in Figure 2, the feedback interface may include a sensor in a smart device having a display, such as a smartphone 4. Either the wearable device 3 or the smartphone 4 may communicate with the aerosol generating device 1 via a wireless communication module 17 (also shown in Figure 1), and optionally also via a network 5, such as a wireless local area network (WLAN).

[0047] In addition to the sensors configured to acquire involuntary response data, the feedback interface may receive user response data in the form of voluntary response data. For example, the smartphone 4 may display a prompt for the user to give feedback. The user feedback may take the form of an affective preference score, such as a rating of the aerosol on a scale of 1 to 5 stars, or any other rating. The user feedback may also take the form of a comparison of the current aerosol to a previously used aerosol.

[0048] As will be discussed further below, the aerosol generating system further includes a preference identification system. The preference identification may be implemented in the control circuit 13, but more preferably is at least partially implemented in the remote processing unit 6. The remote processing unit 6 may be, for example, a physical server or a cloud server. The remote processing unit 6 may also be, for example, a system including more than one physical server or cloud server.

[0049] A method of operating the control circuitry 13 is illustrated generally in Fig. 3 by means of a flow chart. The method may be stored as computer program instructions in memory within the control circuitry 13 and / or the smartphone 4 and / or the remote processing unit 6. The instructions defining the method may be installed or updated by means of a communication signal, such as over a network connection, or by means of a computer-readable storage medium. Alternatively, the control circuitry 13, the smartphone 4, and / or the remote processing unit 6 may include an application specific integrated chip (ASIC) or other custom hardware configured to perform the method.

[0050] Referring to FIG. 3, in step S1, control circuitry 13 controls aerosol-generating chamber 12 to generate aerosols according to each of a plurality of different aerosol-generating substrates.

[0051] Each different aerosol generation may include generating the aerosol from a different aerosol-generating substrate and / or generating the aerosol with a different intensity of aerosol generation by the heating element 121.

[0052] For example, step S1 may include a user replacing each of the substrates 11B-11E of the pack 2 (FIG. 1B) into the aerosol generating device 1, and the aerosol generating device 1 generating a respective aerosol from each substrate.

[0053] The different aerosols preferably include a range of pre-determined aerosols known to be preferred by individual users. Alternatively, the aerosol preferences may be constrained to a large but finite number of possible aerosol preferences.

[0054] In step S2, the preference identification system obtains user response data for users of the aerosol generating device. Step S2 is performed for each of the different aerosols of step S1, and therefore step S2 is performed in parallel with step S1.

[0055] Once steps S1 and S2 have been performed to generate a number of different aerosols and obtain user response data for each setting, in step S3 the control circuit 13 identifies a recommended aerosol for the user based on the user response data.

[0056] For example, in step S3, control circuitry 13 may identify the aerosol associated with the involuntary response indicative of the greatest relaxation of the user. In a more specific example, if sensor 15 measures heart rate, the aerosol that prompted the involuntary response including the lowest heart rate may be identified as the recommended aerosol. Control circuitry 13 may then store the identified aerosol in memory as the default aerosol.

[0057] Steps S1-S3 may be performed iteratively to identify the user's recommended aerosol with improved accuracy. For example, an initial iteration of step S1 may include generating an aerosol from each of a plurality of aerosol-generating substrates 11 in pack 2. The initial iteration may identify which of the pure aerosol-generating substrates provides the user with the most preferred aerosol as the initial recommended aerosol. Subsequent iterations of steps S1-S3 may then obtain subsequent user response data from the feedback interface for one or more subsequent aerosol-generating substrates and identify an updated recommended aerosol based on the subsequent user response data and the initial recommended aerosol.

[0058] The preference identification system may be software implemented directly by the control circuitry 13 in the aerosol generating device 1. Alternatively, the functionality of the preference identification system may be at least partially performed in a remote processing unit 5. For example, the preference identification system may perform at least part of step S3 by analyzing raw data obtained by the control circuitry 13 to identify a recommended aerosol. The preference identification system may perform complex learning analysis, such as by following a design of experiments (DoE) approach, and may generate a multidimensional map of involuntary responses to the aerosol. Such a map may be based on Tucker-1 Principal Component Analysis (PCA).

[0059] Figure 4 is a schematic flow chart illustrating optional features of the method shown in Figure 3. Steps S1 and S2 are identical to the above-described method of Figure 3 and will not be described again.

[0060] Referring to FIG. 4, the user is presented with a selection of aerosols based on previously collected user response data.

[0061] In step S31, the control circuitry 13 or remote processing unit 5 identifies at least one, and preferably multiple, candidate recommended aerosols. In this manner, multiple aerosols may be identified as candidates, rather than requiring automatic selection of a single recommended aerosol.

[0062] In step S32, the candidate recommended aerosols are presented on a user interface. For example, the candidates may be presented on a user interface of the aerosol generating device 1 or the smart device 3.

[0063] For example, the candidate recommended aerosols may be presented as a sensory map, and the user may select a recommended aerosol from the sensory map.

[0064] In step S33, the user interface receives a user selection of a recommended aerosol to be used. The selected aerosol is then communicated directly or indirectly to the control circuit 13 of the aerosol generating device 1.

[0065] In step S4, control circuitry 13 controls aerosol generation chamber 12 to generate the recommended aerosol identified in step S3 (steps S31-S33). Step S4 may be repeated with the recommended aerosol as often as the user desires.

[0066] The modifications to step S3 and the addition of step S4 are unique possible modifications of the method of Fig. 3. In other words, any method in which a recommended aerosol is identified may be followed by step S4. Similarly, steps S31-S33 may be performed without subsequently performing step S34. In some cases, steps S33 and S34 may be omitted, and the user may manually control the aerosol generating device 1 based on the candidate recommended aerosols presented in step S32.

[0067] Figure 5A is a schematic flow chart illustrating a further optional feature of the method shown in Figure 3, which may be combined with the first modification shown in Figure 4. Steps S1 and S2 are identical to the above-described method of Figure 3 and will not be described again.

[0068] In the modified method of Figure 5A, step S3 of Figure 3 is replaced with an alternative step S34, in which the preference identification system identifies a recommended aerosol for the user based on the user response data obtained in step S2 and based on a predetermined model relating user response data to aerosol preferences.

[0069] The model may also be expanded to predict more than a recommended aerosol. For example, the model may be trained to determine a user's health profile based on the user response data, and in identifying a possible next aerosol, allow or prevent the use of an aerosol-generating substrate depending on the user response data. In one example, if the response to a previous aerosol had a high concentration of active ingredient, an aerosol-generating setting may be identified that limits the amount of active ingredient below a threshold.

[0070] FIG. 5B shows an example representation of a predetermined model that may be used in step S34. More specifically, FIG. 5B shows a 2D heat map and a 3D graph of voluntary response data, i.e., "preference," for a scaled "fruity" flavor characteristic and effect characteristic (such as nicotine strength). The 2D heat map and the 3D graph may only represent a part of the model, which also describes the relationship between involuntary and voluntary response data, such as heart rate and galvanic skin response. For example, the trained model may include a series of graphs, one or more tables, or more preferably, parameter definitions of the model. By fitting the model to the user response data obtained in step S2 for individual users, the preference identification system may identify the predicted "preference" peak for the individual user and identify the aerosol ng associated with the peak as the recommended aerosol.

[0071] 5C is a schematic flow chart showing a method for training a model to predict a recommended aerosol for a user. The method may be performed by a preference identification system that communicates with a plurality of aerosol generating devices using a test sample of initial training users of the device. Alternatively, the method of FIG. 5C may be performed continuously to improve the model based on user responses from all or a subset of device users as the device is widely deployed.

[0072] 5C, in step S5, the preference identification system collects response data from one or more aerosol generating devices for each of a plurality of training users involved in training the model. Steps S51 and S52 may be similar to steps S1 and S2 of FIG.

[0073] In step S6, the user response data is then collected to train a model. Specifically, the model is trained to predict a recommended aerosol for a user based on the user response data, and the training is based on the user response data for a plurality of training users. The trained model can then be used in step S34 of FIG. 5A to identify a recommended aerosol for a particular aerosol generating device 1 based on the user response data.

[0074] For example, the trained model may be provided as a pre-defined model stored in the control circuitry 13 or remote processing unit 5 to perform a mapping between user response data and recommended aerosols. Thus, the method of Figure 5C may be performed entirely separately from the method of Figure 5A.

[0075] Step S6 may be performed using any machine learning technique, for example training may be based on principal component analysis (PCA), generalized linear regression model (GLM), or partial least squares (PLS) analysis.

[0076] Such machine learning may also be used to predict properties other than recommended aerosols: for example, machine learning may be used to consolidate raw user response data into more general response characteristics, such as arousal and valence.

[0077] FIG. 6 illustrates diagrammatically an alternative aerosol generating device for use in an aerosol generating system according to the present invention.

[0078] In this embodiment, the aerosol-generating substrate is a liquid aerosol substrate, such as a white spirit, and may include tobacco or a tobacco extract, such as nicotine.

[0079] The aerosol-generating device 1 includes a number of substrate storage chambers 11, an aerosol-generation chamber 12, and a control circuit 13. The substrate storage chambers 11 are each configured to store an aerosol-generating substrate, and the aerosol-generation chamber 12 is configured to generate an aerosol component from each of the aerosol-generating substrates and mix the aerosol components to form an aerosol. The control circuit 13 is configured to control the aerosol-generation chambers 12 and to control the supply of aerosol-generating substrates from the substrate storage chambers 11 to the aerosol-generation chambers 12.

[0080] The aerosol-generating substrate stored in each chamber 11 may be a different substrate that produces a different aerosol component. For example, each aerosol-generating substrate may have a different flavor. Alternatively, two or more substrate storage chambers 11 may contain the same aerosol-generating substrate.

[0081] Optionally, the substrate storage chambers 11 may be provided together in a removable cartridge 111 that may be used to replace the substrate storage chambers 11 after the stored aerosol-generating substrate has been used. The removable cartridge 111 may be compared to pack 2 in Figure 1B. Alternatively, each of the substrate storage chambers 11 may be individually replaceable.

[0082] Although three substrate storage chambers 11 are shown in FIG. 6, any number of one, two or more substrate storage chambers 11 may be used.

[0083] Each aerosol-generating substrate is transported from its substrate storage chamber 11 to the aerosol-generating chamber 12 via tube 18. Tube 18 may be a capillary tube such that the liquid aerosol-generating substrate flows along tube 18 without the need for a driving pressure. Alternatively, tube 18 may include one or more pumps for driving each aerosol-generating substrate along tube 18.

[0084] Pipe 18 includes valves 181 for controlling the flow of aerosol-generating substrate from substrate storage chamber 11 to aerosol-generation chamber 12. Each valve 181 can be controlled to be anywhere between fully closed and fully open according to the required amount of each aerosol-generating substrate for generating the corresponding aerosol component.

[0085] Pipe 18 functions as a substrate mixing element configured to mix the aerosol-generating substrates and supply the mixed aerosol-generating substrates to aerosol-generation chamber 12. More specifically, separate branches of pipe 18 connect to each substrate storage chamber 11 and merge after valve 181 such that the aerosol-generating substrates are mixed before reaching aerosol-generation chamber 12.

[0086] The aerosol-generating chamber includes a heating element 121 configured to generate each aerosol component by heating each of the aerosol-generating substrates. In this embodiment, the heating element is a resistive coil wrapped around the tube 18. Alternatively, the heating element may be, for example, a planar film heater.

[0087] Due to the branching of the tube 18, the aerosol-generating substrate is already mixed before it reaches the heating element 121, so that the aerosol components are generated and mixed simultaneously.

[0088] Once the aerosol components have been mixed to create the aerosol, a user of the aerosol generating device can inhale the aerosol from the device by inhaling to draw air into the aerosol generating chamber 12 through the inlet 122 and out of the aerosol generating chamber 12 through the mouthpiece 123.

[0089] The aerosol generating device of Figure 6 produces an aerosol that may include a mixture of components. Control circuitry 13 is configured to regulate the ratio of these aerosol components generated by aerosol generation chamber 12. More specifically, control circuitry 13 is configured to control heating element 121, and to control valve 181 to set the ratio of aerosol-generating substrates in the mixed liquid that reaches heating element 121, thereby setting the ratio of the aerosol components created by heating the combined liquid.

[0090] The control circuitry 13 may control the ratio of aerosol-generating substrates based on a recommended aerosol identified using one of the methods described above. In such an embodiment, the recommended aerosol may be numerically represented using the relative amounts of a set of known possible aerosol components included in the recommended aerosol.

[0091] Additionally, control circuitry 13 may generate aerosols for each random subset of possible aerosols by controlling the ratios of the mixed aerosol-generating substrates. By introducing randomness into the aerosol generation, a more complete exploration of possible aerosols may be achieved.

[0092] Although the example of FIG. 6 is described with a liquid substrate stored in chamber 11, the concept of mixing components can be applied to solid substrates, for example by mixing powdered substrate components.

[0093] In any of the embodiments shown in Fig. 1 and Fig. 6, the aerosol generating device may further include a substrate identification means 19 to identify the substrate 11 used in the aerosol generating device. For example, the aerosol generating device of Fig. 1 may be configured to read a barcode on the packaging material 111. Similarly, the aerosol generating device of Fig. 6 may be configured to read an identifier chip from the removable cartridge 111. The identified substrate may then be provided to a feedback interface or a preference identification system for use in identifying the recommended aerosol. By automatically identifying the substrate, the preference identification system may associate user response data with a particular aerosol-generating substrate without the need to manually indicate the aerosol-generating substrate being used, thereby improving the accuracy and convenience of the aerosol generating system.

[0094] Usage example We now provide specific examples of how the aerosol generating systems described above can be used.

[0095] First, after initial start-up, the aerosol generating system performs an initial learning phase.

[0096] The initial learning phase includes providing 15 different aerosol generation sessions, each generating a different aerosol. During each session, the aerosol generation device monitors involuntary response data including heart rate, blood pressure, skin temperature, and galvanic skin response, and also monitors aerosol inhalation. After each session, the user provides voluntary response data by rating the aerosol in an application on the smartphone 4. The aerosol generation device communicates user response data including involuntary response data, inhalation data, and voluntary response data to a remote processing unit 6, which functions as a preference identification system.

[0097] A remote processing unit receives and analyzes the data to determine preference patterns.

[0098] The remote processing unit 6 transmits the preference pattern to an application on the smartphone 4, which Contour plots showing preferences on sensory maps for different aerosol-generating substrates; A bar graph showing how well or badly the user responded to each different aerosol-generating substrate or each other factor controlling the generated aerosol; · An automatically generated text summary of your preferences; and Feedback on how the session affected the user's relaxation or alertness The method provides feedback to the user in the form of

[0099] Once the initial learning phase is complete, the remote processing unit 5 may provide suggestions for new aerosols that the user is likely to enjoy. The suggestions may be provided in an application on the smartphone 3. For example, the suggestions may be displayed on a further sensory map.

[0100] The suggestions may be generated based on the machine learning models described above. Additionally, the response data may be analyzed to identify one or more user parameters for suggesting aerosols. For example, a Kano model may be used to identify "must-haves," "performance drivers," or "attractives" to classify potential aerosols and generate suggested aerosols that are likely to be appealing to a particular user.

[0101] When the user wishes to select a proposed aerosol, he indicates this to the aerosol generating device 1. In a preferred example, an application on the smartphone 3 is configured to receive the selection (e.g., as a selection on a sensory map) and communicate the selection to the aerosol generating device 1. Alternatively, the user may indicate the selection by controlling the aerosol in an interface of the aerosol generating device 1 or by manually inserting the recommended aerosol-generating substrate into the aerosol generating device 1.

[0102] Once an aerosol is selected, the aerosol generating device provides an aerosol generating session in which the selected aerosol is generated, and further user responses are measured based on the selected aerosol to provide further feedback and suggestions.

[0103] In the above-mentioned method, the recommended aerosol is identified based on the user response data, including voluntary response data, inhalation data, and involuntary response data. Other data may also be used to assess user preferences. For example, environmental parameters such as date, time, day of the week, and location may be used to identify patterns of user preferences and habits.

[0104] In both the embodiments of Figures 1 and 6, each different aerosol may involve generating the aerosol from a different aerosol-generating substrate and / or generating the aerosol with a different intensity of aerosol generation by heating element 121.

[0105] The different aerosols preferably include a range of pre-determined aerosols known to be preferred by individual users. Alternatively, the aerosol preferences may be constrained to a large but finite number of possible aerosol preferences.

[0106] For example, if six aerosol-generating base materials (five flavors and one nicotine component) are mixed, each base material being included in one of three levels (high, medium, low), and the intensity of aerosol generation by the heating element 121 is also high, medium, or low, there are 3^7=2187 possible aerosols.

Claims

1. 1. An aerosol generation system comprising: an aerosol generating device configured to receive each of a plurality of aerosol-generating substrates and generate a respective aerosol to be inhaled by a user; a feedback interface for receiving user response data of the user in response to inhaling the generated aerosol; A preference identification system, comprising: obtaining user response data from the feedback interface for each of the plurality of aerosol-generating substrates; Identifying a recommended aerosol for the user based on the user response data. A preference identification system configured to: An aerosol generating system comprising:

2. The preference identification system comprises: obtaining initial user response data from the feedback interface for each of a plurality of aerosol-generating substrate samples, the plurality of aerosol-generating substrate samples being provided in a pack; Identifying an initial recommended aerosol for the user based on the initial user response data The aerosol generating system of claim 1 , configured as follows:

3. 3. The aerosol generating system of claim 2, wherein each of the aerosols generated from the plurality of aerosol-generating substrate samples is distributed across a sensory range of different compositions.

4. The aerosol generating system of claim 3 , wherein the sensory range comprises an intensity range for each of one or more aerosol components.

5. The preference identification system further comprises: obtaining subsequent user response data from the feedback interface for one or more subsequent aerosol-generating substrates; Identifying an updated recommended aerosol for the user based on the subsequent user response data and the initial recommended aerosol. The aerosol generating system according to any one of claims 2 to 4, configured as follows:

6. The preference identification system comprises: identifying a plurality of candidate recommended aerosols for the user based on the user response data; Presenting the plurality of candidate recommended aerosols in a user interface. The aerosol generating system according to any one of claims 1 to 4, configured as follows:

7. The aerosol-generating device simultaneously receives at least two of the plurality of aerosol-generating substrates and controls which of the received aerosol-generating substrates are used to generate an aerosol. The aerosol generating system according to any one of claims 1 to 4, configured as follows:

8. 8. The aerosol generating system of claim 7, wherein the aerosol generating device is configured to receive an indication of the recommended aerosol and control which of the accepted aerosol-generating substrates is used to generate the aerosol based on the recommended aerosol.

9. 8. The aerosol generating system of claim 7, wherein the aerosol generating device comprises an aerosol generating chamber and a substrate mixing element configured to mix the simultaneously received multiple aerosol-generating substrates and supply the mixed aerosol-generating substrates to the heating chamber.

10. An aerosol generating system as described in any one of claims 1 to 4, wherein the preference identification system is configured to identify the recommended aerosol based on the user response data and based on a predetermined model relating user response data to aerosol preferences.

11. The preference identification system comprises: obtaining user response data for each of a plurality of training users; training the model to predict recommended aerosols based on user response data for the plurality of training users; The aerosol generating system of claim 10 configured as follows:

12. An aerosol generating system as described in any one of claims 1 to 4, wherein the feedback interface includes a sensor for measuring an involuntary response of the user, and the user response data includes an indication of the involuntary response.

13. The aerosol generating system of claim 12 , wherein the sensor is configured to measure heart rate, blood pressure, skin temperature, or galvanic skin response.

14. The aerosol generating system of claim 12 , wherein the sensor is disposed on an outer surface of a housing of the aerosol generating device.

15. The aerosol generating system of any one of claims 1 to 4, wherein the feedback interface includes a voluntary response interface for receiving a voluntary response from the user in response to inhaling the generated aerosol, and the user response data includes an indication of the voluntary response.

16. An aerosol generation system as described in any one of claims 1 to 4, wherein the feedback interface includes an airflow sensor positioned to measure aerosol inhalation in the aerosol generation device when the user inhales the generated aerosol, and the user response data includes an indication of the aerosol inhalation.

17. 5. The aerosol generating system of claim 1, wherein the aerosol generating device includes a substrate identification means for identifying a received aerosol-generating substrate, and the user response data includes an identification of the received aerosol-generating substrate.

18. A pack comprising a plurality of aerosol-generating substrate samples each for generating a different respective aerosol in an aerosol generating system, the different respective aerosols being distributed across a sensory range of different compositions such that a recommended aerosol can be identified based on user response data obtained in response to inhaling each of the aerosols.

19. 20. A kit comprising the pack of claim 18 and an aerosol generating device configured to receive each of the plurality of aerosol-generating substrates and generate a respective aerosol to be inhaled by a user, the kit being for use in an aerosol generating system according to any one of claims 1 to 4.

20. 1. A method of controlling an aerosol generating system, the aerosol generating system comprising: an aerosol generating device configured to receive an aerosol-generating substrate and generate a respective aerosol to be inhaled by a user; a feedback interface for receiving user response data of the user in response to inhaling the generated aerosol; The method comprises: generating a respective aerosol for each of a plurality of aerosol-generating substrates using the aerosol-generating device; obtaining user reaction data from the feedback interface; identifying a recommended aerosol for the user based on the user response data; A method comprising:

Images