EP4635339A1

EP4635339A1 - Information processing device, information processing method, and program

Info

Publication number: EP4635339A1
Application number: EP22968414.7A
Authority: EP
Inventors: Ikuo Fujinaga
Original assignee: Japan Tobacco Inc
Current assignee: Japan Tobacco Inc
Priority date: 2022-12-13
Filing date: 2022-12-13
Publication date: 2025-10-22
Also published as: KR20250108684A; WO2024127502A1; JPWO2024127502A1

Abstract

[Problem] To provide a mechanism capable of further improving the quality of user experience. [Solution] An information processing device comprising a control unit (116) that generates control information used by an inhalation device (100) that heats an aerosol source to generate aerosol based on control information specifying parameters related to the temperature for heating the aerosol source, wherein the control unit collects multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generates the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.

Description

TECHNICAL FIELD

The present disclosure relates to an information processing device, an information processing method, and a program.

BACKGROUND ART

Inhalation devices that generate substances to be inhaled by a user, such as electronic cigarettes and nebulizers, are in widespread use. For example, an inhalation device uses a substrate that includes an aerosol source for generating aerosol and a flavor source for imparting flavor components to the generated aerosol, thereby generating an aerosol with flavor components. The user can enjoy the flavor by inhaling the aerosol to which the flavor component has been imparted, generated by the inhalation device. The action by which the user inhales the aerosol is also referred to below as puffing or a puff action.
Preferences for the flavor experienced during a puff vary from user to user. Therefore, it is preferable that the temperature at which the aerosol source, which directly affects the flavor, is heated can be customized by the user. Patent Document 1 below discloses a technology that allows users to customize the temperature at which the aerosol source is heated.

CITATION LIST

PATENT LITERATURE

PTL 1 WO 2019/104227 A1

SUMMARY OF INVENTION

TECHNICAL PROBLEM

However, the technology disclosed in PTL 1 is still relatively new and has room for improvement from various standpoints.
The present disclosure was devised in view of these problems and has as an object to provide a mechanism capable of further improving the quality of user experience.

SOLUTION TO PROBLEM

To solve the above problem, one aspect of the present invention provides an information processing device comprising a control unit that generates control information used by an inhalation device that heats an aerosol source to generate aerosol based on control information specifying parameters related to the temperature for heating the aerosol source, wherein the control unit collects multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generates the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.
The control unit may generate the modified control information used by the inhalation device of the first user by inputting the unmodified control information used by the inhalation device of the first user and the evaluation set for the unmodified control information by the first user into the generation model.
The training data may include the first control information used by the inhalation device of the first user, the evaluation set for the first control information by the first user, and the second control information set by the first user with a better evaluation than the first control information.
The control unit may collect the training data in the process of repeating a customization process that includes generating the modified control information used by the inhalation device of the first user based on the unmodified control information used by the inhalation device of the first user and the evaluation set for the unmodified control information by the first user.
The training data may include the unmodified control information in the first customization process as the first control information and the modified control information in the second customization process as the second control information, where the second customization process is the same as the first customization process or is repeated after the first customization process.
The control unit may replace the second control information included in the collected training data with the modified control information set having a better evaluation than the second control information in the process of repeating the customization process.
The training data may include the first control information used by the inhalation device of a second user other than the first user, the evaluation set for the first control information by the second user, and the second control information set by the second user having a better evaluation than the first control information.
The training data may further include the evaluation set for the second control information.
The training data may further include information indicating the attributes of the user of the inhalation device that used the first control information, and the control unit may generate the control information used by the inhalation device of the first user based on the training data that includes information indicating the same attributes as the attributes of the first user.
The training data may further include information indicating the type of aerosol source heated based on the first control information, and the control unit may generate the control information used by the inhalation device of the first user based on the training data that includes information indicating the same type of aerosol source as that heated by the inhalation device of the first user.
The training data may further include information indicating the type of inhalation device that used the first control information, and the control unit may generate the control information used by the inhalation device of the first user based on the training data that includes information indicating the same type of inhalation device as that of the first user.
Furthermore, to solve the above problem, another aspect of the present invention provides an information processing method executed by a computer, wherein the information processing method includes generating control information used by an inhalation device that heats an aerosol source to generate aerosol based on the control information specifying parameters related to the temperature for heating the aerosol source, and generating the control information includes collecting multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generating the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.
Furthermore, to solve the above problem, another aspect of the present invention provides a program that causes a computer to function as a control unit that generates the control information used by an inhalation device that heats an aerosol source to generate aerosol based on control information specifying parameters related to the temperature for heating the aerosol source, wherein the control unit collects multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generates the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.

ADVANTAGEOUS EFFECTS OF THE INVENTION

As described above, according to the present disclosure, it is possible to further improve the quality of user experience.

BRIEF DESCRIPTION OF DRAWINGS

Figure 1 is a diagram showing a configuration example of a system according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram schematically showing a configuration example of an inhalation device according to the same embodiment.
Figure 3 is a block diagram showing a configuration example of a terminal device according to the same embodiment.
Figure 4 is a block diagram showing a configuration example of a server according to the same embodiment.
Figure 5 is a graph schematically showing an example of a heating profile.
Figure 6 is a diagram for explaining a generation model according to the same embodiment.
Figure 7 is a sequence diagram showing an example of the flow of a customization process executed by the system according to the same embodiment.
Figure 8 is a flowchart showing an example of the flow of a training data collection process executed by the server according to the same embodiment.

DESCRIPTION OF EMBODIMENTS

Preferred embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that in the specification and the drawings, duplicate descriptions are omitted by using the same reference signs to denote constituent elements having substantially the same functional configuration.
In the present specification and drawings, elements having substantially the same functional configuration may be distinguished by attaching different letters after the same reference numeral. For example, multiple elements having substantially the same functional configuration may be distinguished as necessary, such as inhalation device 100A and inhalation device 100B. However, if there is no need to specifically distinguish between each of the plurality of elements having a substantially identical functional configuration, only the same reference numeral is assigned. For example, if there is no need to particularly distinguish between inhalation device 100A and inhalation device 100B, they are simply referred to as inhalation device 100.

<1. Configuration Example>

Figure 1 is a diagram showing a configuration example of a system 1 according to the present embodiment. As shown in Figure 1, the system 1 includes multiple inhalation devices 100 (100A and 100B), multiple terminal devices 200 (200A and 200B), and a server 300.
The inhalation device 100 is a device that generates substances to be inhaled by the user. Hereinafter, the substance generated by the inhalation device 100 is described as aerosol. The inhalation device 100 is an example of an aerosol generating device. Additionally, the substance generated by the inhalation device may be a gas. The inhalation device 100 can accommodate a stick-type substrate 150. The inhalation device 100 generates aerosol using the accommodated stick-type substrate 150. The stick-type substrate 150 is an example of a substrate that contributes to the generation of aerosol. The stick-type substrate 150 contains an aerosol source. The inhalation device 100 generates aerosol by heating the accommodated stick-type substrate 150.
The terminal device 200 is a device used by the user of the inhalation device 100. The terminal device 200 is associated with the inhalation device 100. The inhalation device 100 and the terminal device 200 may be pre-paired for wireless communication, or it may be pre-registered in the server 300 that the user of the inhalation device 100 and the terminal device 200 are the same. The terminal device 200 may be any device such as a smartphone, tablet, wearable device, or PC (Personal Computer). Alternatively, the terminal device 200 may be a charger for charging the inhalation device 100.
The server 300 is a control device that manages information of each device included in the system 1. The server 300 communicates with the terminal device 200 via the network 900. In particular, the server 300 indirectly communicates with the inhalation device 100 via the terminal device 200. The server 300 may perform various processes based on information collected from the inhalation device 100 via the terminal device 200. Alternatively, the server 300 may perform various processes based on user operations performed on the terminal device 200.
The system 1 includes multiple inhalation devices 100 and multiple terminal devices 200 used by multiple users. For example, the user using inhalation device 100A and terminal device 200A is also referred to as user A. Similarly, the user using inhalation device 100B and terminal device 200B is also referred to as user B.

(1) Configuration Example of Inhalation Device

Figure 2 is a schematic diagram schematically showing a configuration example of the inhalation device 100. As shown in Figure 2, the inhalation device 100 according to this configuration example includes a power supply unit 111, a sensor unit 112, a notification unit 113, a memory unit 114, a communication unit 115, a control unit 116, a heating unit 121, an accommodating portion 140, and a heat insulation unit 144.
The power source unit 111 stores electrical power. The power supply unit 111 then supplies the electric power to each component of the inhalation device 100 in accordance with control performed by the control unit 116. The power supply unit 111 may be configured, for example, by a rechargeable battery such as a lithium ion secondary battery.
The sensor unit 112 acquires various types of information relating to the inhalation device 100. As an example, the sensor unit 112 is configured by a pressure sensor such as a condenser microphone, a flow rate sensor or a temperature sensor, etc., and acquires values associated with inhalation by a user. As another example, the sensor unit 112 is configured by an input device, such as a button or switch, for accepting input of information from the user.
The notification unit 113 notifies the user of the information. The notification unit 113 is configured by a light emitting device that emits light, a display device that displays images, a sound output device that outputs sound, or a vibrating device that vibrates, for example.
The memory unit 114 stores various types of information for the operation of the inhalation device 100. The memory unit 114 is configured by a non-volatile storage medium such as a flash memory, for example.
The communication unit 115 is a communication interface capable of performing communication conforming to any wired or wireless communication standard. Examples of communication standards that may be used include standards that employ Wi-Fi (registered trademark), Bluetooth (registered trademark), Bluetooth Low Energy (BLE) (registered trademark), Near-Field Communication (NFC), or Low Power Wide Area (LPWA), for example.
The control unit 116 functions as an arithmetic processing device and a control device, and controls overall operation within the inhalation device 100 in accordance with various programs. The control unit 116 is realized by a Central Processing Unit (CPU) or an electronic circuit such as a microprocessor, for example.
The accommodating portion 140 has an internal space 141, and holds a stick-shaped substrate 150 while accommodating a portion of the stick-shaped substrate 150 in the internal space 141. The accommodating portion 140 has an opening 142 allowing the internal space 141 to communicate with the outside, and accommodates the stick-type substrate 150 that has been inserted into the internal space 141 from the opening 142. For example, the accommodating portion 140 is a cylindrical body comprising the opening 142 and a bottom portion 143 serving as a bottom surface, and defines a columnar internal space 141. An air flow path for supplying air to the internal space 141 is connected to the accommodating portion 140. An air inflow hole, which is an inlet for air into the air flow path, is disposed in a side surface of the inhalation device 100, for example. An air outflow hole serving as an outlet for air from the air flow path to the internal space 141 is disposed in the bottom portion 143, for example.
The stick-type substrate 150 comprises a substrate portion 151 and a mouthpiece portion 152. The substrate portion 151 contains an aerosol source. The aerosol source includes a tobacco-derived or non-tobacco-derived flavor component. If the inhalation device 100 is a medical inhaler such as a nebulizer, the aerosol source may include a drug. The aerosol source may, for example, be a liquid such as water or a polyhydric alcohol, for example glycerol or propylene glycol, containing the tobacco-derived or non-tobacco-derived flavor component, or may be a solid including the tobacco-derived or non-tobacco-derived flavor component. In a state in which the stick-type substrate 150 is being held in the accommodating portion 140, at least a portion of the substrate portion 151 is accommodated in the internal space 141, and at least a portion of the mouthpiece portion 152 protrudes from the opening 142. Then, when the user holds the mouthpiece portion 152 protruding from the opening 142 in his or her mouth and inhales, air flows into the internal space 141 via the air flow path, which is not illustrated in the drawings, and reaches the inside of the user's mouth together with the aerosol generated from the substrate portion 151.
The heating unit 121 heats the aerosol source to atomize the aerosol source, thereby generating the aerosol. In the example illustrated in Figure 2, the heating unit 121 is configured in a film shape and is disposed so as to cover the outer periphery of the accommodating portion 140. Then, when the heating unit 121 generates heat, the substrate portion 151 of the stick-type substrate 150 is heated from the outer periphery, generating the aerosol. The heating unit 121 generates heat when supplied with electricity from the power supply unit 111. By way of example, electricity may be supplied when the sensor unit 112 detects that the user has started inhaling and/or that predetermined information has been input. The supply of electricity may then be stopped when the sensor unit 112 detects that the user has finished inhaling and/or that predetermined information has been input.
The heat insulating portion 144 prevents heat transfer from the heating unit 121 to other components. For example, the heat insulating portion 144 is configured from a vacuum heat insulating material or an aerogel heat insulating material, or the like.
A configuration example of the inhalation device 100 has been described above. The inhalation device 100 is, of course, not limited to the configuration described above, and may adopt various configurations, such as those illustrated below by way of example.
As one example, the heating unit 121 may have a blade-like form and may be arranged so as to protrude into the internal space 141 from the bottom portion 143 of the accommodating portion 140. In that case, the blade-like heating unit 121 is inserted into the substrate portion 151 of the stick-type substrate 150 and heats the substrate portion 151 of the stick-type substrate 150 from the inside. As another example, the heating unit 121 may be arranged so as to cover the bottom portion 143 of the accommodating portion 140. Furthermore, the heating unit 121 may be configured by a combination of two or more from among a first heating unit covering the outer circumference of the accommodating portion 140, a blade-like second heating unit, and a third heating unit covering the bottom portion 143 of the accommodating portion 140.
As another example, the accommodating portion 140 may comprise an opening/closing mechanism such as a hinge for opening/closing part of a casing that forms the internal space 141. By opening/closing the casing, the accommodating portion 140 may then receive and hold the stick-type substrate 150 which has been inserted into the internal space 141. In that case, the heating unit 121 may be provided on the part of the accommodating portion 140 holding the stick-type substrate 150, and may heat the stick-type substrate 150 while pressing same.
Furthermore, the means for atomizing the aerosol source is not limited to heating provided by the heating unit 121. For example, the means for atomizing the aerosol source may be induction heating. In that case, the inhalation device 100 comprises at least an electromagnetic induction source such as a coil for generating a magnetic field, instead of the heating unit 121B. A susceptor which generates heat by means of induction heating may be provided in the inhalation device 100, or may be contained in the stick-type substrate 150.
Note that the inhalation device 100, in cooperation with the stick-type substrate 150, generates aerosol to be inhaled by the user. Therefore, the combination of the inhalation device 100 and the stick-type substrate 150 may be regarded as an aerosol generation system.

(2) Configuration Example of Terminal Device

Figure 3 is a block diagram showing a configuration example of the terminal device 200 according to the present embodiment. As shown in Figure 3, the terminal device 200 includes an input unit 210, an output unit 220, a detection unit 230, a communication unit 240, a memory unit 250, and a control unit 260.
The input unit 210 has a function for accepting the input of various types of information. The input unit 210 may include an input device for accepting input of information from the user. Examples of input devices include buttons, keyboards, touch panels, and microphones. Additionally, the input unit 210 may include various sensors such as an image sensor.
The output unit 220 has a function for outputting information. The output unit 220 may include an output device for outputting information to the user. Examples of output devices include a display device for displaying information, a light-emitting device for emitting light, a vibrating device for vibrating, and a sound output device for outputting a sound. An example of a display device is a display. An example of a light-emitting device is an LED (Light Emitting Diode). An example of a vibrating device is an eccentric motor. An example of a sound output device is a speaker. The output unit 220 outputs information input from the control unit 260 to notify the user of the information.
The detection unit 230 has a function for detecting information related to the terminal device 200. The detection unit 230 may detect the position information of the terminal device 200. For example, the detection unit 230 receives GNSS (Global Navigation Satellite System) signals from GNSS satellites (e.g., GPS (Global Positioning System) signals from GPS satellites) to detect position information consisting of latitude and longitude of the device. The detection unit 230 may detect the movement of the terminal device 200. For example, the detection unit 230 includes a gyro sensor and an acceleration sensor to detect angular velocity and acceleration.
The communication unit 240 is a communication interface for transmitting and receiving information between the terminal device 200 and other devices. The communication unit 240 performs communication conforming to any wired or wireless communication standard. Such communication standards may include, for example, USB (Universal Serial Bus), Wi-Fi (registered trademark), Bluetooth (registered trademark), NFC (Near Field Communication), or LPWA (Low Power Wide Area).
The memory unit 250 stores various types of information. The memory unit 250 is configured by a non-volatile storage medium such as a flash memory, for example.
The control unit 260 functions as an arithmetic processing device or a control device and controls overall operation within the terminal device 200 in accordance with various programs. The control unit 260 is realized by a Central Processing Unit (CPU) or an electronic circuit such as a microprocessor, for example. Additionally, the control unit 260 may include a ROM (Read Only Memory) for storing programs and arithmetic parameters used, and a RAM (Random Access Memory) for temporarily storing parameters that change as needed. The terminal device 200 executes various processes based on control by the control unit 260. Processing of information input by the input unit 210, output of information by the output unit 220, detection of information by the detection unit 230, transmission and reception of information by the communication unit 240, and storage and reading of information by the memory unit 250 are examples of processes controlled by the control unit 260. Other processes executed by the terminal device 200, such as input of information to each component and processing based on information output from each component, are also controlled by the control unit 260.
The functions of the control unit 260 may be realized using an application. The application may be pre-installed or downloaded. Additionally, the functions of the control unit 260 may be realized by PWA (Progressive Web Apps).

(3) Configuration Example of Server

Figure 4 is a block diagram showing a configuration example of the server 300 according to the present embodiment. As shown in Figure 4, the server 300 includes a communication unit 310, a memory unit 320, and a control unit 330.
The communication unit 310 is a communication interface for transmitting and receiving information between the server 300 and other devices. The communication unit 310 performs communication conforming to any wired or wireless communication standard.
The memory unit 320 stores various types of information for the operation of the server 300. The memory unit 320 is configured by non-volatile storage media such as an HDD (Hard Disc Drive) and an SSD (Solid State Drive), for example.
The control unit 330 functions as an arithmetic processing device and a control device, and controls overall operation within the server 300 in accordance with various programs. The control unit 330 is realized by a CPU (Central Processing Unit) and an electronic circuit such as a microprocessor, for example. Additionally, the control unit 330 may include a ROM (Read Only Memory) for storing programs and arithmetic parameters used, and a RAM (Random Access Memory) for temporarily storing parameters that change as needed. The server 300 executes various processes based on control by the control unit 330. Transmission and reception of information by the communication unit 310 and storage and reading of information by the memory unit 320 are examples of processes controlled by the control unit 330. Other processes executed by the server 300, such as input of information to each component and processing based on information output from each component, are also controlled by the control unit 330.

<2. Technical Features>

(1) Heating Profile

The control unit 116 controls the operation of the heating unit 121 based on the heating profile. The control of the operation of the heating unit 121 is realized by controlling the power supply from the power supply unit 111 to the heating unit 121. The heating unit 121 uses the power supplied from the power supply unit 111 to heat the stick-type substrate 150.
The heating profile comprises control information for controlling the temperature at which the aerosol source is heated. The heating profile specifies parameters related to the temperature for heating the aerosol source. An example of the temperature for heating the aerosol source is the temperature of the heating unit 121. An example of a parameter related to the temperature for heating the aerosol source is the target value of the temperature of the heating unit 121 (hereinafter also referred to as the target temperature). The temperature of the heating unit 121 may be controlled to change according to the elapsed time from the start of heating. In that case, the heating profile includes information specifying the time-series transition of the target temperature. As another example, the heating profile may include parameters (hereinafter also referred to as power supply parameters) specifying the power supply method to the heating unit 121. The power supply parameters may include, for example, the voltage applied to the heating unit 121, the ON/OFF of power supply to the heating unit 121, or the method of feedback control to be adopted. The ON/OFF of power supply to the heating unit 121 may be regarded as the ON/OFF of the heating unit 121.
The control unit 116 controls the operation of the heating unit 121 so that the temperature of the heating unit 121 (hereinafter also referred to as the actual temperature) transitions similarly to the target temperature specified in the heating profile. The heating profile is typically designed so that the flavor experienced by the user when inhaling the aerosol generated from the stick-type substrate 150 is optimized. Therefore, by controlling the operation of the heating unit 121 based on the heating profile, the flavor experienced by the user can be optimized.
The temperature control of the heating unit 121 can be realized by known feedback control, for example. The feedback control may be, for example, PID control (Proportional-Integral-Differential Controller). The control unit 116 may supply power from the power supply unit 111 to the heating unit 121 in the form of pulses by pulse width modulation (PWM) or pulse frequency modulation (PFM). In that case, the control unit 116 can control the temperature of the heating unit 121 by adjusting the duty ratio or frequency of the power pulses in the feedback control. Alternatively, the control unit 116 may perform simple on/off control in the feedback control. For example, the control unit 116 may execute heating by the heating unit 121 until the actual temperature reaches the target temperature, interrupt heating by the heating unit 121 when the actual temperature reaches the target temperature, and resume heating by the heating unit 121 when the actual temperature becomes lower than the target temperature.
The temperature of the heating unit 121 can be quantified by measuring or estimating the electrical resistance value of the heating unit 121 (more precisely, the heating resistor constituting the heating unit 121), for example. This is because the electrical resistance value of the heating resistor changes according to the temperature. The electrical resistance value of the heating resistor can be estimated by measuring the voltage drop across the heating resistor, for example. The voltage drop across the heating resistor can be measured by a voltage sensor that measures the potential difference applied to the heating resistor. In another example, the temperature of the heating unit 121 can be measured by a temperature sensor such as a thermistor installed near the heating unit 121.
The period from the start to the end of the process of generating aerosol using the stick-type substrate 150 is hereinafter also referred to as a heating session. In other words, a heating session is a period during which power supply to the heating unit 121 is controlled based on the heating profile. The start of the heating session is the timing at which heating based on the heating profile is started. The end of the heating session is the timing at which a sufficient amount of aerosol is no longer generated. The heating session includes an initial preheating period and a subsequent puffable period. The puffable period is the time during which a sufficient amount of aerosol is expected to be generated. The preheating period is the time from the start of heating until the puffable period begins. Heating conducted during the preheating period is also referred to as preheating.
The notification unit 113 may notify the user of information indicating the timing when preheating ends. For example, the notification unit 113 may report information predicting the end of preheating before the preheating period ends or report information indicating that preheating has ended at the time preheating ends. Notification to the user may be performed by lighting an LED or vibrating, for example. The user can refer to such notifications to start puffing immediately after preheating ends.
Similarly, the notification unit 113 may notify the user of information indicating the timing when the puffable period ends. For example, the notification unit 113 notifies the user of information announcing the end of the puffable period before the puffable period ends, or notifies the user of information indicating that the puffable period has ended at the timing at which the puffable period has ended. Notification to the user may be performed by lighting an LED or vibrating, for example. The user can refer to such notifications to continue puffing until the puffable period ends.
An example of a heating profile will be described with reference to Figure 5. Figure 5 is a graph schematically showing an example of a heating profile. The horizontal axis of graph 20 represents time. The vertical axis of graph 20 represents temperature. Line 21 shows the time-series transition of the target temperature. As shown in Figure 5, the heating session may include an initial temperature rise period, an intermediate temperature drop period, and a re-temperature rise period in sequence. The initial temperature rise period is the time after the start of heating when the temperature of the heating unit 121 rapidly rises and is maintained at a high temperature. The intermediate temperature drop period is the time after the initial temperature rise period when the temperature of the heating unit 121 decreases. The re-temperature rise period is the time after the intermediate temperature drop period when the temperature of the heating unit 121 rises again. In the example shown in Figure 5, the target temperature rapidly rises to around 300°C during the initial temperature rise period, then decreases to about 230°C during the intermediate temperature drop period, and subsequently rises gradually to around 260°C during the re-temperature rise period. During the intermediate temperature drop period, the power supply to the heating unit 121 may be interrupted, and heating may be turned off. In the example shown in Figure 5, the period from the start of heating to the middle of the initial temperature rise period is the preheating period, and the period from the middle of the initial temperature rise period to the end of the re-temperature rise period is the puffable period.

(2) Customization Process

The system 1 repeatedly executes the customization process. The customization process is a process of customizing (i.e., changing) the heating profile. In the customization process, the system 1 changes the heating profile to improve the user's evaluation. Therefore, by repeating the customization process, the system 1 can gradually generate a heating profile that provides an optimal user experience. The customization process is executed or controlled by each of the inhalation device 100, the terminal device 200, and the server 300.
The customization process includes at least generating aerosol using the heating profile by the inhalation device 100, setting an evaluation period, accepting the setting of the user's evaluation, changing the heating profile based on the set evaluation, and setting the modified heating profile in the inhalation device 100. The customization process may be repeatedly executed until a heating profile that matches the user's intention is generated. A heating profile that matches the user's intention is one in which a good evaluation is set for the entire heating session (i.e., for all puffs). The following describes each process included in the customization process in detail.

Generating Aerosol Based on the Heating Profile

The inhalation device 100 generates aerosol by heating the stick-type substrate 150 based on the heating profile (hereinafter also referred to as the unmodified heating profile). The user inhales the aerosol generated by the inhalation device 100 to check the inhalation feel. The user may perform multiple puffs during the heating session.
The timing for performing puffs (hereinafter referred to as puff timing) may be set in advance. In that case, the user performs puffs at the pre-set puff timing. For example, the terminal device 200 obtains information indicating the progress of heating from the inhalation device 100 and prompts the user to perform puffs at predetermined timings during the heating session. The information indicating the progress of heating may include the elapsed time from the start of heating or the temperature of the heating unit 121, etc. The terminal device 200 may obtain from the inhalation device 100 identification information of the heating profile used by the inhalation device 100 along with or prior to the information indicating the progress of heating. This allows the appropriate determination of the arrival of puff timing even if the puff timing differs for each heating profile. Of course, the puff timing may also not be set in advance. In that case, the user performs puffs at any timing. The inhalation device 100 may transmit information for specifying the actual puff timing to the terminal device 200. The information for specifying the puff timing may indicate how many puffs have been performed during the heating session or may specify the puff timing based on the elapsed time from the start of heating. The information for specifying the puff timing may be included in the information indicating the progress of heating.

Setting the Evaluation Period

The terminal device 200 divides the heating session and sets multiple evaluation periods. The evaluation period is the period subject to evaluation by the user. For example, the terminal device 200 sets the evaluation period based on the identification information of the heating profile used by the inhalation device 100 and the information indicating the progress of heating.
The evaluation period may include multiple puff timings. That is, the user may set evaluations for multiple puffs collectively. The puff timing here may be the pre-set puff timing or the actual puff timing. With this configuration, it is possible to roughly customize the heating profile. As a result, it is possible to reduce the user's burden compared to setting evaluations for each puff.
Of course, the evaluation period may include a single puff timing. That is, the user may set evaluations for each puff. With this configuration, it is possible to finely customize the heating profile.
The terminal device 200 may set the evaluation period based on the elapsed time from the start of heating. For example, the terminal device 200 may divide the puffable period into 30-second intervals and set multiple 30-second evaluation periods.
The terminal device 200 may set the evaluation period based on the number of puff timings. For example, the terminal device 200 may divide the puffable period for each puff timing and set an evaluation period for each puff timing. With this configuration, it is possible to appropriately set the evaluation period even if the user's puff intervals are uneven.

Accepting the Setting of Evaluations

The terminal device 200 accepts user operations for setting evaluations of the unmodified heating profile. Specifically, the terminal device 200 accepts the setting of evaluations for the aerosol inhaled by the user in each of the multiple evaluation periods. Hereinafter, it is assumed that the terminal device 200 accepts the setting of evaluations for each puff performed multiple times during the heating session. For example, the terminal device 200 displays a screen for accepting the setting of evaluations for each puff and accepts tap operations on the screen. The evaluations set by the user are used for modifying the heating profile. That is, accepting the setting of evaluations may be regarded as accepting the setting of a modify instruction (modification values described later) for the heating profile.
The terminal device 200 may accept the setting of evaluations in real-time according to the progress of heating. When accepting the setting of evaluations in real-time, the terminal device 200 obtains information indicating the progress of heating from the inhalation device 100 and may prompt the user to set evaluations immediately after a puff is performed. With this configuration, the user can set evaluations for each puff in real-time while performing puffs. Of course, the terminal device 200 may accept user operations to collectively set evaluations for each puff after the heating session ends.
The terminal device 200 may accept the setting of evaluations for multiple evaluation items. With this configuration, it is possible to improve evaluations from various standpoints. Examples of evaluation items include smoking flavor, smoke volume, tobacco feel, kick feel, odor, and draw resistance. Smoking flavor refers to the overall taste of the aerosol. The stronger the taste, the higher the smoking flavor is evaluated, and the weaker the taste, the lower the smoking flavor is evaluated. Smoke volume refers to the perceived amount of aerosol. The more aerosol that reaches the user's mouth per puff, the higher the smoke volume is evaluated, and the less aerosol that reaches the user's mouth per puff, the lower the smoke volume is evaluated. Tobacco feel refers to the perceived closeness to the taste of a traditional cigarette. The closer the taste or intensity of the aerosol is to the taste of a traditional cigarette, the stronger the tobacco feel is evaluated. Conversely, the more refreshing the taste becomes due to factors like strong fruit or mint flavors, the weaker the tobacco feel is evaluated. Kick feel refers to the sensation of throat irritation. Typically, the higher the nicotine content in the aerosol, the stronger the kick feel is evaluated. Odor refers to the perceived similarity to the smell of a traditional cigarette. The closer the aerosol's smell is to that of a traditional cigarette, the stronger the odor is evaluated. Conversely, the more refreshing the smell becomes due to factors like strong fruit or mint aromas, the weaker the odor is evaluated. Draw resistance refers to the sensation of stimulation to the entire oral cavity. For these evaluation items, a good evaluation such as "just right" or a bad evaluation such as "too weak/strong" or "too little/much" can be set.
Additionally, the terminal device 200 may accept the setting of an evaluation for the entire heating session (i.e., the entirety of multiple puffs performed during the heating session). For example, after the heating session ends, the terminal device 200 may present questions such as "Were you satisfied with this heating profile?" In that case, a good evaluation such as "satisfied" or a bad evaluation such as "not satisfied" can be set.

Changing the Heating Profile

The server 300 (e.g., control unit 330) is an example of an information processing device that generates heating profiles. The server 300 generates a new heating profile (hereinafter also referred to as the modified heating profile) by changing the unmodified heating profile based on the evaluation set by the user. For example, the server 300 increases the target temperature at puff timings evaluated as having low smoking flavor and decreases the target temperature at puff timings evaluated as having high smoking flavor. With this configuration, it becomes possible to generate a modified heating profile that may improve the evaluation compared to the unmodified heating profile.
When evaluations for multiple evaluation items are set, the server 300 generates the modified heating profile based on the evaluations for the multiple evaluation items. For example, the server 300 integrates multiple change values of target temperatures based on the evaluations for the multiple evaluation items, such as by averaging them, and applies them to the unmodified heating profile to generate the modified heating profile. For example, if the change value based on the evaluation of smoking flavor is +30°C and the change value based on the evaluation of smoke volume is +10°C, the average of +20°C may be adopted as the integrated change value. Then, by increasing the target temperature of the unmodified heating profile by 20°C, the modified heating profile may be generated. With this configuration, it is possible to improve evaluations from various standpoints.
The server 300 may generate the modified heating profile based on a learned generation model for generating heating profiles. The generation model will be explained with reference to Figure 6.
Figure 6 is a diagram for explaining the generation model according to the present embodiment. As shown in Figure 6, when the generation model M receives the unmodified heating profile and the evaluation set for the unmodified heating profile, it outputs the modified heating profile. The generation model M for heating profiles may be a model learned using known machine learning techniques such as SVM (Support Vector Machine) or neural networks. With this configuration, it becomes possible to automatically and accurately generate heating profiles that improve user evaluations. The accuracy of generating heating profiles refers to the degree to which the generated heating profile matches the user's intention. The higher the accuracy of generating heating profiles, the higher the user evaluation set for the generated heating profile. The ability to easily generate and provide heating profiles that match the user's intention greatly enhances the quality of the user experience.

Setting the Modified Heating Profile

The inhalation device 100 sets the modified heating profile. For example, the inhalation device 100 receives and stores the modified heating profile generated by the server 300 via the terminal device 200. This is expected to improve the user's evaluation in the next customization process.

Repeating the Customization Process

The above has described each process included in the customization process in detail. The system 1 repeatedly executes the above-described customization process until a heating profile that matches the user's intention is generated. The repetition of the customization process will be explained with reference to Table 1 below.

[Table 1]

Table 1. Example of inputs and outputs of generated model in repeated customization process
Customization process repetition count	Input	Output
1	P1, E1	P2
2	P2, E2	P3
3	P3, E3	P4
...
99	P99, E99	P100
100	P100, E100	P100

In Table 1, P indicates the heating profile, E indicates the evaluation, and the numbers following P and E indicate the index corresponding to the repetition count of the customization process. According to Table 1, in the first customization process, the heating profile P1 and the evaluation E1 set for the heating profile P1 are input into the generation model, and the heating profile P2 is output. The heating profile P2 is a heating profile in which changes have been made to improve the bad evaluations included in evaluation E1 compared to heating profile P1. Such a customization process is repeated, with the heating profile generated in the previous customization process being used as input to the generation model in the next customization process. In the 100th customization process, if the evaluation E100 set for the heating profile P100 is a good evaluation for all puffs, as shown in Table 1, the input heating profile P100 is output as is from the generation model. Then, the repetition of the customization process stops. In this way, a heating profile P100 that matches the user's intention is generated.

(3) Learning the Generation Model

The server 300 collects multiple training data sets and learns a generation model for generating heating profiles based on the collected multiple training data sets. Then, the server 300 generates heating profiles based on the learned generation model. The training data includes a combination of a first heating profile, an evaluation set for the first heating profile, and a second heating profile to be generated based on the first heating profile and the evaluation set for the first heating profile. In other words, the training data is a desirable combination of the unmodified heating profile and the evaluation set for the unmodified heating profile as input to the generation model, and the modified heating profile as output from the generation model. By collecting such training data, it becomes possible to learn a highly accurate generation model. The accuracy of the generation model corresponds to the accuracy of the heating profiles generated using the generation model.
Hereinafter, it is assumed that the server 300 generates a heating profile for user A (an example of the first user). The heating profile for user A is the heating profile used by the inhalation device 100A used by user A.
In this case, the server 300 inputs the unmodified heating profile used by the inhalation device 100A and the evaluation set for the unmodified heating profile by user A into the generation model. This allows the server 300 to generate the modified heating profile used by the inhalation device 100A. With this configuration, the server 300 can automatically and accurately execute the generation of heating profiles for user A in the customization process using the generation model. As a result, a heating profile that matches the user's intention is generated earlier, and the number of repetitions of the customization process can be reduced.
The training data used for learning the generation model for generating a heating profile for user A may be training data involving user A. Specifically, the training data may include the first heating profile used by the inhalation device 100A, the evaluation set for the first heating profile by user A, and the second heating profile set by user A with a better evaluation than the first heating profile. By generating a heating profile for user A using a generation model learned based on training data involving user A, it becomes possible to more efficiently improve user A's evaluation.
The server 300 may collect training data involving user A in the process of repeating the customization process for generating a heating profile for user A. The customization process for generating a heating profile for user A includes generating the modified heating profile used by the inhalation device 100A based on the unmodified heating profile used by the inhalation device 100A and the evaluation set for the unmodified heating profile by user A. With this configuration, it is possible to utilize the relationship between the change values of the target temperature and the changes in evaluation obtained in the trial-and-error process of reaching a heating profile that matches the user's intention as training data. This improves the learning efficiency of the generation model.
The training data may include the unmodified heating profile in the first customization process as the first heating profile and the modified heating profile in the second customization process as the second heating profile. Here, the second customization process is the same as or repeated after the first customization process. In the example shown in Table 1, as an example, the server 300 may collect training data including the heating profile P1 as the first heating profile, evaluation E1, and the heating profile P2 as the second heating profile if evaluation E2 is improved compared to evaluation E1. As another example, the server 300 may collect training data including the heating profile P1 as the first heating profile, evaluation E1, and the heating profile P100 as the second heating profile. With this configuration, it becomes possible to efficiently collect training data while repeating the customization process.
The server 300 may replace the second heating profile included in the collected training data with the modified heating profile set with a better evaluation than the second heating profile in the process of repeating the customization process. As an example, let us assume that the server 300 has collected training data including the heating profile P1 as the first heating profile, evaluation E1, and the heating profile P2 as the second heating profile. Subsequently, if evaluation E3 is improved compared to evaluation E2, the server 300 may replace the heating profile P2 as the second heating profile in the collected training data with the heating profile P3. In other words, the server 300 may update the training data including the heating profile P1, evaluation E1, and the heating profile P2 to training data including the heating profile P1, evaluation E1, and the heating profile P3. If the training data is updated in the process of repeating the customization process, the server 300 will eventually collect training data including the heating profile P100 as the second heating profile. For example, the server 300 may collect training data including the heating profile P1, evaluation E1, and the heating profile P100. With this configuration, it becomes possible to update the collected training data to more suitable training data for learning. For example, a generation model learned based on the updated training data will output the heating profile P100 that matches the user's intention when the heating profile P1 and evaluation E1 are input. In this way, it becomes possible to improve the accuracy of the generation model.
Additionally, training data including a heating profile in the middle of the customization process as the first heating profile may be collected. For example, the server 300 may collect training data including the heating profile P2, evaluation E2, and heating profile P100.

(4) Process Flow

Customization Process

Figure 7 is a sequence diagram showing an example of the flow of the customization process executed by the system 1. This sequence involves the inhalation device 100, the terminal device 200, and the server 300.
As shown in Figure 7, first, the inhalation device 100 heats the stick-type substrate 150 based on the heating profile (Step S102).
Next, the inhalation device 100 transmits the identification information of the heating profile used for heating to the terminal device 200 (Step S104).
Then, the terminal device 200 accepts the setting of evaluations (Step S106). Specifically, during the heating session, the inhalation device 100 transmits information indicating the progress of heating to the terminal device 200. The terminal device 200 prompts the user to perform puffs at predetermined timings according to the progress of heating and encourages the user to set evaluations immediately after puffs are performed, accepting the setting of evaluations for each puff from the user.
Next, the terminal device 200 transmits the identification information of the heating profile used by the inhalation device 100 and the information indicating the evaluations set by the user to the server 300 (Step S108). The information indicating the evaluations set by the user includes information for specifying multiple puff timings and evaluations for each evaluation item at each puff timing.
Then, the server 300 changes the heating profile using the learned generation model (Step S110). Specifically, the server 300 inputs the heating profile received from the terminal device 200 and the evaluations set for the heating profile into the learned generation model to generate the modified heating profile.
Next, the server 300 transmits the modified heating profile to the terminal device 200 (Step S112). When the terminal device 200 receives the modified heating profile from the server 300, it forwards the received modified heating profile to the inhalation device 100 (Step S114).
Then, when the inhalation device 100 receives the modified heating profile, it stores the received modified heating profile (Step S116). As a result, in the next customization process, the stick-type substrate 150 will be heated based on the modified heating profile.

Training Data Collection Process

Figure 8 is a flowchart showing an example of the flow of the training data collection process executed by the server 300.
As shown in Figure 8, first, the server 300 acquires the unmodified heating profile, the evaluation of the unmodified heating profile, the modified heating profile, and the evaluation of the modified heating profile in the process of repeating the customization process (Step S202). For example, the server 300 receives the heating profile P1, evaluation E1, heating profile P2, and evaluation E2 from the terminal device 200.
Next, the server 300 determines whether the evaluation has improved before and after the change in the heating profile (Step S204). For example, the server 300 determines that the evaluation has improved if the number of puffs with better evaluations set in evaluation E2 than in evaluation E1 has increased, and determines that it has not improved otherwise. If it is determined that the evaluation has not improved before and after the change in the heating profile (Step S204: NO), the process proceeds to Step S210.
If it is determined that the evaluation has improved before and after the change in the heating profile (Step S204: YES), the server 300 generates training data (Step S206). For example, the server 300 generates training data including the heating profile P1 as the first heating profile, evaluation E1, and the heating profile P2 as the second heating profile. If, in the process of repeating the customization process, a heating profile P100 with a better evaluation than the heating profile P2 is obtained, the server 300 may replace the second heating profile in the training data with the heating profile P100. In other words, the server 300 may generate training data including the heating profile P1 as the first heating profile, evaluation E1, and the heating profile P100 as the second heating profile.
Next, the server 300 learns the generation model (Step S208). For example, the server 300 learns the generation model based on the newly generated training data in Step S206 in addition to the existing training data.
Then, the server 300 determines whether the repetition of the customization process has ended (Step S210). An example of a condition for determining that the repetition of the customization process has ended is that good evaluations have been set for all puffs, good evaluations have been set for the entire heating session, and the user has instructed to terminate.
If it is determined that the repetition of the customization process has not ended (Step S210: NO), the process returns to Step S202. On the other hand, if it is determined that the repetition of the customization process has ended (Step S210: YES), the process ends.

<3. Supplement>

Although preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, the present disclosure is not limited to such examples. It is obvious that a person having an ordinary level of knowledge in the technical field to which the present disclosure belongs could conceive of various modified examples or variations within the scope of the technical concepts set forth in the claims, and these modified examples and variations will naturally be understood to fall within the technical scope of the present disclosure.
In the above embodiment, an example was described in which the training data used for learning the generation model for generating a heating profile for user A is training data involving user A, but the present disclosure is not limited to such an example. The training data used for learning the generation model for generating a heating profile for user A may include training data involving other users (e.g., user B) besides user A. The training data involving user B includes the first heating profile used by the inhalation device 100B used by user B, the evaluation set for the first heating profile by user B, and the second heating profile set by user B with a better evaluation than the first heating profile. Other users are not limited to one person, and training data involving multiple other users may be used for learning the generation model for generating a heating profile for user A. By learning the generation model based on training data involving user A and/or training data involving user B, it becomes possible to further improve the accuracy of the generation model. This is because it is possible to increase the number of training data.
In the above, an example was described in which one user (user A or user B) is involved in one training datum, but the present disclosure is not limited to such an example. Multiple users may be involved in one training datum. For example, the user involved in the first heating profile and the user involved in the second heating profile may be different. As an example, the training data may include the top-ranked heating profiles on a web page where heating profiles are made available for download as the second heating profile. As another example, the training data may include heating profiles that are used by many users or evaluated as satisfactory by many users as the second heating profile. With this configuration, it becomes possible to further improve the accuracy of the generation model.
In the above embodiment, an example was described in which the training data includes the first heating profile, the evaluation set for the first heating profile, and the second heating profile, but the present disclosure is not limited to such an example. Below, an example of other information that may be included in the training data will be described.
The training data may further include the evaluation set for the second heating profile. For example, the training data may include the heating profile P1, evaluation E1, heating profile P2, and evaluation E2. With this configuration, it becomes possible to associate the difference between the first heating profile and the second heating profile with the difference in the evaluations set for these heating profiles. As a result, the server 300 can more accurately grasp the causal relationship between the changes in the heating profile and the changes in evaluation and utilize this for generating heating profiles. As an example, let us assume that the difference between the heating profile P1 and the heating profile P2 is an increase of 10°C in the target temperature at the third puff timing. Also, let us further assume that the difference between evaluation E1 and evaluation E2 is an improvement from weak to just right in the evaluation of smoking flavor for the third puff. In that case, the server 300 can grasp the detailed causal relationship that increasing the target temperature by 10°C at the third puff timing improved the evaluation of smoking flavor for the third puff from weak to just right. By clarifying such causal relationships, it becomes possible to generate more accurate heating profiles. The generation model may be learned by using the first heating profile, the evaluation set for the first heating profile, and the evaluation set for the second heating profile as inputs and the second heating profile as output. When the learned generation model is input with the unmodified heating profile, the evaluation set for the unmodified heating profile, and the desired evaluation (e.g., good evaluation for all puffs), a modified heating profile with the desired evaluation can be generated.
The training data may further include information indicating the attributes of the user of the inhalation device 100 that used the first heating profile. Then, the server 300 may generate a heating profile for user A based on the training data that includes information indicating the same attributes as those of user A. In other words, the server 300 may learn the generation model based on the training data that includes information indicating the same attributes as those of user A and generate a heating profile for user A using the learned generation model. Examples of user attributes include gender, age, and residence. Additionally, user attributes may include browsing information on a web page where heating profiles are made available for download. An example of browsing information is an HTTP cookie. The inhalation device 100 may download and use heating profiles from the web page via the terminal device 200. With this configuration, it becomes possible to further improve the accuracy of the generation model according to the user's attributes.
The training data may further include information indicating the type of aerosol source heated based on the first heating profile, i.e., the type of stick-type substrate 150. Then, the server 300 may generate a heating profile for user A based on the training data that includes information indicating the same type as the stick-type substrate 150 heated by the inhalation device 100A. As an example, assume that the inhalation device 100A heats a stick-type substrate 150 containing menthol. In that case, the server 300 learns the generation model based on the training data collected when using the stick-type substrate 150 containing menthol. Then, the server 300 generates a heating profile for user A and for the stick-type substrate 150 containing menthol using the learned generation model. With this configuration, it becomes possible to further improve the accuracy of the generation model according to the type of stick-type substrate 150 used by the inhalation device 100A.
The training data may further include information indicating the type of inhalation device 100 that used the first heating profile. Then, the server 300 may generate a heating profile for user A based on the training data that includes information indicating the same type as the inhalation device 100A. For example, if the inhalation device 100A is a high-heating type, the server 300 learns the generation model based on training data collected when a high-heating type inhalation device 100 was used. Then, the server 300 generates a heating profile for user A and for the high-heating type inhalation device 100A using the learned generation model. Note that the type of inhalation device 100 may refer to the type of software (e.g., software version) and not just the type of hardware. With this configuration, it becomes possible to further improve the accuracy of the generation model according to the type of inhalation device 100A.
The above describes an example of other information that may be included in the training data.
In the above embodiment, an example was described in which training data for the entire heating profile is collected, but the present disclosure is not limited to such an example. Training data for part of the heating profile may be collected. As an example, consider a case where 15 puffs are performed during the heating session, and the evaluation for 10 of the 15 puffs is improved through the customization process. In that case, training data including the part corresponding to the improved 10 puffs of the unmodified heating profile, the evaluation of the improved 10 puffs of the unmodified heating profile, and the part corresponding to the improved 10 puffs of the modified heating profile may be collected. With this configuration, it becomes possible to collect training data even if the repetition of the customization process is interrupted midway.
The processes executed by the terminal device 200 or the server 300 described in the above embodiment may be executed by any device. As an example, the learning of the generation model or the modification of the heating profile may be executed by the terminal device 200.
In the above embodiment, an example was described in which evaluations are set for each puff for multiple evaluation items, i.e., an example in which a common evaluation period is set for multiple evaluation items, but the present disclosure is not limited to such an example. The terminal device 200 may set multiple evaluation periods for each of the multiple evaluation items. For example, the terminal device 200 may set evaluation periods every 30 seconds for smoking flavor and set evaluation periods for each puff for smoke volume. With this configuration, it becomes possible to flexibly set evaluation periods for each evaluation item, thereby improving the ease of customization.
In the above embodiment, changing the target temperature was mentioned as an example of modifying the heating profile, but the present disclosure is not limited to such an example. The server 300 may change the time-related parameters of the heating profile. Examples of time-related parameters of the heating profile include the duration of the heating session, the duration of the initial temperature rise period, the intermediate temperature drop period, and the re-temperature rise period. Additionally, puff timing is another example of a time-related parameter of the heating profile.
In the above embodiment, an example was described in which the parameter related to the temperature for heating the aerosol source specified in the heating profile is the target value of the temperature of the heating unit 121, but the present disclosure is not limited to such an example. An example of a parameter related to the temperature for heating the aerosol source is the target value of the electrical resistance of the heating unit 121. Additionally, if the means for heating the aerosol source is induction heating, examples of parameters related to the temperature for heating the aerosol source specified in the heating profile include the temperature of the susceptor or the target value of the electrical resistance of the electromagnetic induction source.
In the above embodiment, an example was described in which the inhalation device 100 generates aerosol by heating the stick-type substrate 150, but the present disclosure is not limited to such an example. The inhalation device 100 may be configured as a so-called liquid atomization type aerosol generating device that generates aerosol by heating and atomizing a liquid aerosol source. The technology according to the present disclosure can also be applied to liquid atomization type aerosol generating devices.
As described in the above embodiment, the setting of evaluations is accepted by the terminal device 200. Here, the acceptance of evaluation settings by the terminal device 200 may refer to accepting evaluation settings via a native application installed on the terminal device 200. Additionally, the acceptance of evaluation settings by the terminal device 200 may refer to accepting evaluation settings via a PWA (Progressive Web App) provided for the terminal device 200. As an example, the server 300 may accept evaluation settings via a PWA provided for the terminal device 200.
At least part of the functional configuration of the inhalation device 100 described in the above embodiment may be included in other devices. An example of such other devices is a charging device for charging the inhalation device 100. The charging device has a mechanism for detachable connection with the inhalation device 100 and may charge the inhalation device 100 or transmit and receive information with the inhalation device 100 while connected thereto. As an example, the charging device may have a wireless communication function and may relay information transmission and reception between the inhalation device 100 and a device such as a smartphone. As another example, the charging device may have a storage function and may store information received from or to be transmitted to the inhalation device 100. The combination of the inhalation device 100 and the charging device may be regarded as an aerosol generation system. Additionally, at least part of the functional configuration of the terminal device 200 described in the above embodiment may be included in other devices such as a charging device for charging the inhalation device 100.
Note that the series of processes by each device described in this specification may be realized using software, hardware, or a combination of software and hardware. Programs constituting the software are stored in advance on a recording medium (more specifically, a non-transitory computer-readable storage medium) provided internally or externally to each device, for example. Then, when the programs are executed, for example, by a computer for controlling each device described in the present description, the programs are read into a RAM and executed by means of a processing circuit such as a CPU. The recording medium is, for example, a magnetic disk, an optical disk, a magneto-optical disk, or a flash memory, etc. Furthermore, the computer programs may be distributed via a network, for example, without the use of a recording medium. The computer may be a specific-purpose integrated circuit such as an ASIC, a general-purpose processor that executes functions by loading a software program, or a computer on a server used for cloud computing. Furthermore, the series of processes performed by each device described in the present description may be processed in a distributed manner by multiple computers.
Furthermore, the processing described using flowcharts or sequence diagrams in the present description need not necessarily be implemented in the order depicted. Some processing steps may be executed in parallel. Furthermore, additional processing steps may be employed and some processing steps may be omitted.
The following configurations also fall within the technical scope of the present disclosure.

(1) An information processing device comprising a control unit that generates control information used by an inhalation device that heats an aerosol source to generate aerosol based on control information specifying parameters related to the temperature for heating the aerosol source, wherein the control unit collects multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generates the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.
(2) The information processing device according to (1), wherein the control unit generates the modified control information used by the inhalation device of the first user by inputting the unmodified control information used by the inhalation device of the first user and the evaluation set for the unmodified control information by the first user into the generation model.
(3) The information processing device according to (1) or (2), wherein the training data includes the first control information used by the inhalation device of the first user, the evaluation set for the first control information by the first user, and the second control information set by the first user with a better evaluation than the first control information.
(4) The information processing device according to (3), wherein the control unit collects the training data in the process of repeating a customization process that includes generating the modified control information used by the inhalation device of the first user based on the unmodified control information used by the inhalation device of the first user and the evaluation set for the unmodified control information by the first user.
(5) The information processing device according to (4), wherein the training data includes the unmodified control information in the first customization process as the first control information and the modified control information in the second customization process as the second control information, where the second customization process is the same as the first customization process or is repeated after the first customization process.
(6) The information processing device according to (5), wherein the control unit replaces the second control information included in the collected training data with the modified control information set having a better evaluation than the second control information in the process of repeating the customization process.
(7) The information processing device according to any one of (1) to (6), wherein the training data includes the first control information used by the inhalation device of a second user other than the first user, the evaluation set for the first control information by the second user, and the second control information set by the second user having a better evaluation than the first control information.
(8) The information processing device according to any one of (1) to (7), wherein the training data further includes the evaluation set for the second control information.
(9) The information processing device according to any one of (1) to (8), wherein the training data further includes information indicating the attributes of the user of the inhalation device that used the first control information, and the control unit generates the control information used by the inhalation device of the first user based on the training data that includes information indicating the same attributes as the attributes of the first user.
(10) The information processing device according to any one of (1) to (9), wherein the training data further includes information indicating the type of aerosol source heated based on the first control information, and the control unit generates the control information used by the inhalation device of the first user based on the training data that includes information indicating the same type of aerosol source as that heated by the inhalation device of the first user.
(11) The information processing device according to any one of (1) to (10), wherein the training data further includes information indicating the type of inhalation device that used the first control information, and the control unit generates the control information used by the inhalation device of the first user based on the training data that includes information indicating the same type of inhalation device as that of the first user.
(12) An information processing method executed by a computer, wherein the information processing method includes generating control information used by an inhalation device that heats an aerosol source to generate aerosol based on the control information specifying parameters related to the temperature for heating the aerosol source, and generating the control information includes collecting multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generating the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.
(13) A program that causes a computer to function as a control unit that generates the control information used by an inhalation device that heats an aerosol source to generate aerosol based on control information specifying parameters related to the temperature for heating the aerosol source, wherein the control unit collects multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generates the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.

REFERENCE SIGNS LIST

1 System
100 Inhalation device
111 Power supply unit
112 Sensor unit
113 Notification unit
114 Memory unit
115 Communication unit
116 Control unit
121 Heating unit
140 Accommodating portion
141 Internal space
142 Opening
143 Bottom portion
144 Heat insulating unit
150 Stick-type substrate
151 Substrate portion
152 Mouthpiece portion
200 Terminal device
210 Input unit
220 Output unit
230 Detection unit
240 Communication unit
250 Memory unit
260 Control unit
300 Server
310 Communication unit
320 Memory unit
330 Control unit
900 Network

Claims

An information processing device comprising a control unit that generates control information used by an inhalation device that heats an aerosol source to generate aerosol based on control information specifying parameters related to the temperature for heating the aerosol source, wherein the control unit collects multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generates the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.
The information processing device as claimed in claim 1, wherein the control unit generates the modified control information used by the inhalation device of the first user by inputting the unmodified control information used by the inhalation device of the first user and the evaluation set for the unmodified control information by the first user into the generation model.
The information processing device as claimed in claim 1 or 2, wherein the training data includes the first control information used by the inhalation device of the first user, the evaluation set for the first control information by the first user, and the second control information set by the first user with a better evaluation than the first control information.
The information processing device as claimed in claim 3, wherein the control unit collects the training data in the process of repeating a customization process that includes generating the modified control information used by the inhalation device of the first user based on the unmodified control information used by the inhalation device of the first user and the evaluation set for the unmodified control information by the first user.
The information processing device as claimed in claim 4, wherein the training data includes the unmodified control information in the first customization process as the first control information and the modified control information in the second customization process as the second control information, where the second customization process is the same as the first customization process or is repeated after the first customization process.
The information processing device as claimed in claim 5, wherein the control unit replaces the second control information included in the collected training data with the modified control information set having a better evaluation than the second control information in the process of repeating the customization process.
The information processing device as claimed in any one of claims 1 to 6, wherein the training data includes the first control information used by the inhalation device of a second user other than the first user, the evaluation set for the first control information by the second user, and the second control information set by the second user having a better evaluation than the first control information.
The information processing device as claimed in any one of claims 1 to 7, wherein the training data further includes the evaluation set for the second control information.
The information processing device as claimed in any one of claims 1 to 8, wherein the training data further includes information indicating the attributes of the user of the inhalation device that used the first control information, and the control unit generates the control information used by the inhalation device of the first user based on the training data that includes information indicating the same attributes as the attributes of the first user.
The information processing device as claimed in any one of claims 1 to 9, wherein the training data further includes information indicating the type of aerosol source heated based on the first control information, and the control unit generates the control information used by the inhalation device of the first user based on the training data that includes information indicating the same type of aerosol source as that heated by the inhalation device of the first user.
The information processing device as claimed in any one of claims 1 to 10, wherein the training data further includes information indicating the type of inhalation device that used the first control information, and the control unit generates the control information used by the inhalation device of the first user based on the training data that includes information indicating the same type of inhalation device as that of the first user.
An information processing method executed by a computer, wherein the information processing method includes generating control information used by an inhalation device that heats an aerosol source to generate aerosol based on the control information specifying parameters related to the temperature for heating the aerosol source, and generating the control information includes collecting multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generating the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.
A program that causes a computer to function as a control unit that generates the control information used by an inhalation device that heats an aerosol source to generate aerosol based on control information specifying parameters related to the temperature for heating the aerosol source, wherein the control unit collects multiple training data sets, each including a combination of first control information, an evaluation set for the first control information, and second control information to be generated based on the first control information and the evaluation set for the first control information, and generates the control information used by the inhalation device of a first user based on a generation model of the control information learned from the collected multiple training data sets.