Support method and information processing device

Abstract

To provide a support method and an information processing device which support discovery of an aerosol source suitable for a user.SOLUTION: A support method supports discovery of an aerosol source matching preference of a user by making the user smoke at least one kind of aerosol source as a trial from among multiple kinds of aerosol sources. A server 30 executes: an acquisition step which acquires predetermined input data which are inputted through a terminal device 20 from the user, and includes information about the user's preference with respect to the aerosol source smoked by the user as the trial; and an identifying step which identifies at least one aerosol source matching the preference of the user, on the basis of the input data. The input data includes a first evaluation value related to a plurality of feature amounts including the taste of smoking of the aerosol source smoked as the trial. The first evaluation value indicates a difference of the user's preference with respect to a reference value of each of the plurality of feature amounts.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a method and an information processing device for assisting a user in finding an aerosol source that matches their preferences. [Background technology]

[0002] Conventionally, aerosol generating devices that enable the inhalation of aerosols with a flavor and aroma have been known. There are a wide variety of flavors and aromas of aerosols that can be inhaled using aerosol generating devices. Here, the term "flavor and aroma" is a concept that includes either or both of the flavor and aroma. The flavor is a general term for the stimulation of the throat and lungs, the taste, and the smell that are perceived by inhaling components that are produced when tobacco leaves are heated. The flavor is a general term for the taste and smell that are perceived by inhaling components of additives added to tobacco leaves.

[0003] Users of aerosol generating devices select an aerosol source based on their personal preference for flavor and taste before using the aerosol generating device. Regarding taste preference, Patent Document 1 discloses a method for determining taste preference for food in consideration of salt concentration, although it is not related to aerosols. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-060990 Summary of the Invention [Problem to be solved by the invention]

[0005] Users tend to become accustomed to using a particular aerosol source and continue to select that particular aerosol source, so that among the wide variety of aerosol sources, a truly suitable aerosol source for the user may not be selected.

[0006] The present disclosure provides a support method and information processing device that support a user in finding a suitable aerosol source. [Means for solving the problem]

[0007] A first aspect of the present disclosure is A method for assisting a user in finding an aerosol source that matches a user's preferences by having the user try at least one aerosol source from among a plurality of aerosol sources, the method comprising: an acquiring step of acquiring predetermined input data inputted from the user via a terminal device, the input data including information regarding the user's preferences for the aerosol source sampled by the user; and identifying at least one aerosol source that matches the user's preferences based on the input data; the input data includes a first evaluation value that is an evaluation by the user regarding a plurality of feature amounts including a taste of the aerosol source that has been sampled; The first evaluation value indicates a deviation of the user's preference from a reference value for each of the plurality of feature amounts of the sampled aerosol source.

[0008] A second aspect of the present disclosure is An information processing device that supports a user in finding an aerosol source that matches the user's preferences by having the user try at least one aerosol source from among a plurality of aerosol sources, acquiring predetermined input data inputted from the user via a terminal device and including information regarding the user's preferences for the aerosol source sampled by the user; Identifying at least one aerosol source that meets the user's preferences based on the input data; the input data includes a first evaluation value that is an evaluation by the user regarding a plurality of feature amounts including a taste of the aerosol source that has been sampled; The first evaluation value indicates a deviation of the user's preference from a reference value for each of the plurality of feature amounts of the sampled aerosol source. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to assist a user in finding a suitable aerosol source from among a plurality of types of aerosol sources, based on data input by the user regarding the aerosol sources that have been tried. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a schematic diagram showing a general configuration of a support system 1 capable of executing a support method according to the present disclosure. [Figure 2] 2 is a diagram showing the exchange of information between a terminal device 20 and a server 30. FIG. [Figure 3] This is a screen displayed on the terminal device 20 for inputting impressions about the sample brands. [Figure 4] 10 is a screen showing the results displayed on the display device of the terminal device 20. [Figure 5] 10 shows an example of a control flow of a support method executed by the server 30. [Figure 6] 10 shows an example of a control flow of a calculation process based on inputs for a plurality of feature amounts. [Figure 7] 10 shows an example of a control flow of a calculation process based on correlation data. [Figure 8] 10 shows an example of correlation data. [Figure 9] 10 shows an example of a control flow of a process for calculating a match degree score of a stock. [Figure 10] FIG. 1 is a schematic diagram showing a first configuration example of a suction device (suction device 100A). [Figure 11] FIG. 10 is a schematic diagram showing a second configuration example of the suction device (suction device 100B). DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, a support method and an information processing device according to an embodiment of the present disclosure will be described with reference to the drawings. Note that, in the following, identical or similar elements will be denoted by identical or similar reference numerals, and their description may be omitted or simplified as appropriate.

[0012] [1. Overview of the support system] 1 is a schematic diagram showing the general configuration of an assistance system 1 capable of executing the assistance method of the present disclosure. The assistance system 1 is a system that enables a user of an aerosol source to be suggested an aerosol source suitable for the user's preferences, taking into account taste tendencies that the user may not be aware of.

[0013] The support system 1 includes a terminal device 20 used by a user of the aerosol source, and a server 30 capable of communicating with the terminal device 20. The terminal device 20 and the server 30 communicate with each other via a network NW realized by, for example, the Internet or a cellular line.

[0014] The terminal device 20 includes a mobile terminal (smartphone, tablet terminal, wearable terminal, etc.) or a PC (Personal Computer) used by a user. A predetermined application program (hereinafter also simply referred to as an "app") provided by the operator of the server 30, for example, is installed in the terminal device 20.

[0015] The terminal device 20 includes a control unit 21, a storage unit 22, a communication unit 23, and a UI (User Interface) unit 24.

[0016] The control unit 21 functions as a processing unit and a control device, and in accordance with various programs controls the overall operation of the terminal device 20. The control unit 21 is realized by an electronic circuit such as a CPU or a microprocessor, for example.

[0017] The storage unit 22 stores various types of information for the operation of the terminal device 20. The storage unit 22 is configured by a non-volatile storage medium such as a flash memory.

[0018] The communication unit 23 is a communication interface that can communicate under the control of the control unit 21, and communicates with the server 30.

[0019] The UI unit 24 includes an input device that accepts information input (operation input) from the user, and an output device that outputs various information to the user. The input device of the terminal device 20 may be configured, for example, with a touch panel, a keyboard, a microphone, or a mouse. The output device of the terminal device 20 includes, for example, a display device that displays images. As the display device, a liquid crystal display, an organic EL display, or the like may be adopted. The output device of the terminal device 20 may also include a sound output device such as a speaker that outputs sound, a light-emitting device such as an LED that emits light, a vibration device such as a vibrator that vibrates, or the like.

[0020] The terminal device 20 is configured to be able to communicate with the inhalation device 100. The inhalation device 100 is an aerosol generating device that generates an aerosol from an aerosol source to be inhaled by a user, and in this case, the user of the aerosol source can also be said to be the user of the inhalation device 100. The terminal device 20 and the inhalation device 100 communicate with each other via wired communication using, for example, USB (Universal Serial Bus (registered trademark)) or wireless communication such as Wi-Fi (registered trademark) or Bluetooth (registered trademark). The specific configuration of the inhalation device 100 will be described later.

[0021] The server 30 is, for example, a computer managed by the manufacturer of the suction device 100, and communicates with the terminal device 20 used by the user. The server 30 may be a virtual server (cloud server) realized in a cloud computing service, or may be a physical server realized as a single device.

[0022] The server 30 includes a memory unit 31 that saves and stores data and programs, and a calculation unit 32 that can access the memory unit 31 and has a processor that performs calculations such as arithmetic operations and logical operations. A support program that supports the user in finding a suitable aerosol source is stored in the memory unit 31. The calculation unit 32 executes this support program, thereby performing a process of supporting the user in finding a suitable aerosol source.

[0023] 2. Methods for supporting aerosol source detection Next, a method for assisting a user in finding an aerosol source that matches the user's preferences from among multiple aerosol sources (hereinafter also referred to as an assistance method) will be described. The multiple aerosol sources are, for example, aerosol sources used in the inhalation device 100, but are not limited thereto and may also be aerosol sources that are not used in the inhalation device 100.

[0024] In the assistance method of the present disclosure, the assistance system 1 assists the user in finding an aerosol source that matches the user's preferences by having the user sample at least one type of aerosol source from among multiple types of aerosol sources. In the following, multiple types (e.g., 26 types) of aerosol sources are described as "brands A to Z," and an example will be described in which the assistance system 1 assists the user in finding a brand that matches the user's preferences from among the 26 types of brands A to Z by having the user sample three types of brands (specifically, brands A to C).

[0025] FIG. 2 is a diagram showing the exchange of information between a terminal device 20 used by a user and a server 30. The user samples brands A to C and inputs their impressions of each brand A to C as input data via the terminal device 20 (app). Here, brands A to C are also referred to as sample brands A to C. The input data for the sample brands A to C is transmitted from the terminal device 20 to the server 30 ((1) in FIG. 2) and stored in the memory unit 31. The memory unit 31 stores data (preliminary data) obtained by a preliminary survey on brands A to Z, including the sample brands A to C. The calculation unit 32 identifies brands recommended for the user based on the input data and the preliminary data and suggests them on the app of the terminal device 20 ((2) in FIG. 2). Details of each data in FIG. 2 will be described later.

[0026] 3 is a screen displayed on the terminal device 20 for inputting impressions about sampled brands A to C. The user inputs impressions about each of the sampled brands A to C. The input data includes a first evaluation value 41, which is the user's evaluation of multiple feature quantities including the smoking sensation of the sampled brand, and a second evaluation value 42, which is the user's evaluation of the user's overall preference for the sampled brand.

[0027] The first evaluation value 41 is a relative evaluation, for example, on an 11-point scale, of the multiple feature values of the sample brand, indicating whether the user prefers a stronger or weaker flavor. In FIG. 3, six feature values are shown as examples: "drawability," "volume," "savory," "menthol flavor," "fruity," and "bitterness." However, the present invention is not limited to these, and other feature values may be added, or some feature values may be deleted from the six feature values. These feature values have a high contribution rate to identifying a brand that matches the user's preferences. Therefore, based on the user's evaluation of these feature values, an aerosol source that matches the user's preferences can be accurately identified.

[0028] The first evaluation value 41 is input, for example, by the user operating a slide bar, and the further to the right of the slide bar the higher the degree of "preferring stronger" compared to the sample brand, and the further to the left of the slide bar the higher the degree of "preferring weaker" compared to the sample brand.

[0029] The second evaluation value 42 is an evaluation of the like / dislike of the sample brand, for example, on an 11-point scale. The second evaluation value 42 is input, for example, by the user operating a slide bar, with the degree of "like" increasing as the user moves to the right of the slide bar and the degree of "dislike" increasing as the user moves to the left of the slide bar. As will be described in more detail later, the second evaluation value 42 takes a value between -1 and 1.

[0030] When the user inputs the first evaluation value 41 and the second evaluation value 42 for each of the sample brands A to C, the server 30 executes a predetermined calculation process to identify at least one brand that matches the user's preferences from among multiple brands, including not only the sample brand but also other brands. The server 30 then transmits the result information to the terminal device 20, and the terminal device 20 outputs the result information to an output device.

[0031] Furthermore, when identifying a plurality of brands that match the user's preferences from among a plurality of types of brands, the server 30 may rank them. Then, the server 30 may transmit result information to the terminal device 20, and the terminal device 20 may output the result information to an output device in a manner that allows the user to understand the ranking results.

[0032] FIG. 4 is a screen showing the results displayed on the display device (an example of an output device) of the terminal device 20. The screen displays a plurality of (here, five) recommended brands identified by calculation processing by the server 30. The plurality of recommended brands are ranked in descending order of recommendation degree, and the screen of the terminal device 20 displays the ranking results in a manner that allows the user to grasp them. Specifically, the screen displays a plurality of concentric circles with different radii, with brands with higher recommendation degrees being displayed closer to the center of the circles. In this way, by displaying brands that match the user's preferences on the screen, the user can find recommended brands in a visually easy-to-understand manner.

[0033] Furthermore, the result information transmitted from the server 30 may include the reason for proposing the recommended brand identified by the server 30 to the user. For example, as shown in Fig. 4, the reason for proposing the recommended brand (here, "Brand V") to the user may be displayed at the bottom of the screen displaying the result information. The reason for the suggestion is displayed based on, for example, the user's input regarding the aforementioned feature (here, "bitterness").

[0034] [3. Specific calculation process of the support method] Next, a specific calculation process of the support method for supporting the discovery of an aerosol source (brand) that matches the user's preferences will be described.

[0035] 5 shows an example of the control flow of the support method executed by the server 30. First, the calculation unit 32 of the server 30 acquires user input data for the sample brand (step S10). The input data includes the first evaluation value 41 and the second evaluation value 42 for the sample brand.

[0036] Then, the calculation unit 32 of the server 30 executes calculation processing based on the input for the plurality of feature amounts (i.e., the first evaluation value 41) (step S20). Fig. 6 shows an example of a control flow of the calculation processing based on the input for the plurality of feature amounts.

[0037] First, the calculation unit 32 of the server 30 obtains the average value of each characteristic amount of the sampled brand (step S21). The average values of each characteristic amount of multiple types of brands A to Z are data 51A to 51Z obtained by a preliminary survey and stored in advance in the storage unit 31. The calculation unit 32 of the server 30 obtains the average value of each characteristic amount of the sampled brand from the average values of each characteristic amount of multiple types of brands A to Z stored in the storage unit 31.

[0038] The average values of each feature of multiple brands A to Z are expressed as a vector, with vector components equal to the number of feature values (six in this embodiment). For example, a vector base_vecA representing the average values of each feature value of brand A has six vector components. The six vector components correspond to quantitative evaluation values of brand A's "drawability," "vapor volume," "savory," "menthol feel," "fruity," and "bitterness," respectively, and the vector base_vecA is expressed as, for example, [2.3, 4.5, 4.2, 3.2, 1.3, 5.3]. In this example, the average value (=5.3) of the feature value "bitterness" is higher than the other feature values, indicating that brand A is characterized by a high "bitterness." Such a vector of average values represents the smoking taste characteristics of each brand.

[0039] The average values of each feature for multiple types of brands A to Z are obtained through a preliminary survey. Each vector component of the average values is the average of the evaluation values of multiple people who have previously tried brands A to Z. To explain the average value for brand A in more detail, multiple people who have previously tried brand A evaluated each feature value, and the average of these evaluations becomes the vector base_vecA.

[0040] Next, the calculation unit 32 of the server 30 weights the user's input data for each characteristic of the sample brand (step S22). The input data here is a first evaluation value 41, which is an evaluation value for each characteristic of the sample brand. For example, the first evaluation value 41 for brand A is represented by the vector feedback_vecA, which has six vector components. The six vector components correspond to the quantitative evaluations of "drawability," "amount of vapor," "savory," "menthol feel," "fruity," and "bitterness" input by the user for sample brand A, and are represented, for example, as feedback_vecA=[2.0, 1.2, 1.0, -1.0, 1.2, -1.5].

[0041] Each vector component has a larger value when the user selects "prefers stronger" in Figure 3, and a smaller value when the user selects "prefers weaker" in Figure 3. In other words, the first evaluation value 41 indicates the deviation of the user's preference from the reference values (average values mentioned above) of each of the multiple feature quantities of the sampled brand.

[0042] The calculation unit 32 multiplies the vector feedback_vecA (first evaluation value 41 input by the user) by a predetermined weighting coefficient β to determine the weight of the user's input relative to the vector base_vecA (average value of each feature amount). The weighting coefficient β is an arbitrary real number, for example, 1.

[0043] Next, the calculation unit 32 of the server 30 calculates the user's preference vector for the sample brand (step S23). Specifically, for sample brand A, as shown in the following equation (1), the preference vector vecA for brand A is calculated by adding the vector base_vecA and the vector feedback_vecA multiplied by a weighting coefficient β.

[0044] vecA=base_vecA+β×feedback_vecA (1)

[0045] The preference vector is a feedback of the deviation of the user's preference (first evaluation value 41) from the average value of each feature of the sampled brand, and indicates the direction of the user's preference for the sampled brand. For example, for the aforementioned brand A, although the average value (5.3) of each feature for "bitterness" is high, the user's first evaluation value (-1.5) for the "bitterness" of brand A is small, meaning that "I prefer weaker flavors," and so it can be seen that the user prefers brands that are less "bitter" than brand A.

[0046] Returning to Fig. 5, the calculation unit 32 of the server 30 executes calculation processing based on the correlation data (step S30). Fig. 7 shows an example of a control flow of the calculation processing based on the correlation data.

[0047] The calculation unit 32 of the server 30 acquires correlation data 52 indicating the correlation between the sampled brand and other brands (step S31). The correlation is, for example, a correlation coefficient indicating the strength of the relationship between the sampled brand and other brands. The correlation data 52 between brands is data obtained through a preliminary survey and is stored in advance in the storage unit 31. The calculation unit 32 of the server 30 acquires, as a vector, a portion indicating the correlation coefficient between the sampled brand and other brands from the correlation data 52 between brands stored in the storage unit 31.

[0048] As shown in Figure 8, the correlation data is data represented in a matrix, with the correlation coefficients between one brand shown in a column and multiple other brands shown in a row. For example, the correlation coefficient between sample brand A and brands A to Z is shown in the area surrounded by a bold frame and expressed as a vector corr_A, such as corr_A = [1, 0.2, 0.56, , 0.88, 0.3]. Each vector component indicates the correlation coefficient between sample brand A and the other brands, and takes a value between 0 and 1. For convenience, the correlation coefficient between brand A and brand A (= 1) is also included. In this example, the correlation coefficient between brand A and brand Y is high at 0.88, indicating a high degree of similarity.

[0049] Next, the calculation unit 32 of the server 30 acquires the evaluation value (i.e., first evaluation value 41) regarding the "overall preference" of the sample brand input by the user (step S32). If the first evaluation value 41 regarding the user's overall preference for the sample brand A is represented as like_value_A, like_value_A takes a real number between -1 and 1, as described above.

[0050] Next, the calculation unit 32 of the server 30 calculates a correlation score for the sampled brand (step S33). The correlation score is the product of the correlation coefficient obtained in step S31 and the second evaluation value 42 for "overall preference" obtained in step S32, and is expressed as a vector having as many components as there are types of brands. The correlation score is a numerical value that evaluates the brand that matches the user's preferences based on the correlation between brands. For sampled brand A, the correlation score score_A for sampled brand A is calculated using the following formula (2):

[0051] score_A=like_value_A×corr_A (2)

[0052] To explain the correlation score score_A for the sample brand A in more detail, if the second evaluation value 42 for the "overall preference" of the sample brand A is high and like_value_A is close to 1, the value of the component of the correlation score score_A corresponding to the brand with a high correlation coefficient with the sample brand A will be large. In such a case, it can be inferred that a brand with a high correlation coefficient with the sample brand A is highly likely to match the user's preferences. On the other hand, if the evaluation value for the "overall preference" of the sample brand A is low and like_value_A is close to -1, the value of the component of the correlation score score_A corresponding to the brand with a high correlation coefficient with the sample brand A will be small. In such a case, it can be inferred that a brand with a high correlation coefficient with the sample brand A is highly likely to not match the user's preferences.

[0053] The calculation unit 32 of the server 30 repeatedly executes the above-described steps S10, S20, and S30 until the user inputs input data for a plurality of sample brands (three brands A to C in this embodiment).

[0054] Once the input data for the multiple sample brands has been entered, the calculation unit 32 of the server 30 executes a match score calculation process to calculate a match score for each brand (step S40). The match score numerically indicates the degree to which multiple brands A to Z match the user's preferences. Figure 9 shows an example of the control flow for the match score calculation process for each brand.

[0055] The calculation unit 32 of the server 30 calculates the final user preference vector by taking into account all sampled brands (step S41). The final user preference vector is calculated based on the first evaluation value 41 input by the user, and indicates the user's preference characteristics for each feature. Specifically, the final user preference vector is calculated by adding up all the preference vectors for each sampled brand and dividing the result by the number of sampled brands. For example, if the user samples three brands A to C, the final user preference vector vec is calculated using the following formula (3):

[0056] vec=(vecA+vecB+vecC) / 3 (3)

[0057] Here, vecB and vecC are preference vectors for brands B and C, and are calculated by the calculation process shown in FIG. 6, similar to vecA.

[0058] Next, the calculation unit 32 of the server 30 calculates the distance between the user's preference vector vec and a vector representing the average value of each feature amount of each of the brands A to Z as a first score (step S42). The first score is a numerical representation of the similarity between the user's preference characteristics and the smoking taste characteristics of each of the brands A to Z. Specifically, the distance calculated as the first score is the sum of the squares of the differences of each component between the final user's preference vector (i.e., the user's preference characteristics) and the vector representing the average value of each of the brands A to Z (i.e., the smoking taste characteristics of each of the brands A to Z). Taking brand A as an example, the distance dist_A between the user's preference vector vec and a vector base_vecA representing the average value of each feature amount of brand A is calculated using the following formula (4):

[0059] dist_A=Σ_{j}(vec(j)-base_vecA(j)) 2 (4)

[0060] In equation (4), vec(j) and base_vecA(j) represent the jth component (j is an integer between 1 and 6) of each vector. The calculation unit 32 of the server 30 performs the distance calculation for all brands A to Z, and calculates a distance vector dists having components equal to the number of brands as the first score. That is, the distance vector dists is expressed by the following equation (5).

[0061] dists=[dist_A, dist_B, ···, dist_Z] (5)

[0062] It is estimated that a component of the distance vector dists with a small value, that is, a small distance, is a brand that is highly similar to the user's preference characteristics.

[0063] Next, the calculation unit 32 of the server 30 calculates a correlation score that takes into account all the brands sampled as the second score (step S43). Specifically, the correlation scores calculated for each sampled brand are all added together and multiplied by a predetermined weighting coefficient α to obtain the second score. For example, if the user samples three brands A to C, the second score scores is calculated using the following formula (3):

[0064] scores=(score_A+score_B+score_C)×α (6)

[0065] In equation (6), score_B and score_C are correlation scores for sample brands B and C, respectively, and are calculated in the same way as equation (2) above, which calculated score_A. The weighting coefficient α is an arbitrarily determined real number.

[0066] Next, the calculation unit 32 of the server 30 calculates a match degree score for each of the brands A to Z based on the first score and the second score calculated by the above formula (5) and formula (6) (step S44). Specifically, the calculation unit 32 of the server 30 calculates the match degree score final_scores for each of the brands A to Z by subtracting the first score from the second score, as shown in the following formula (7). The match degree score final_scores is expressed as a vector having components equal to the number of types of brands.

[0067] final_scores=scores-dists (7)

[0068] The higher the value of the second score, scores, the more likely it is to be recommended to the user, and the lower the value of the first score, dists, the more likely it is to be recommended to the user.Therefore, the higher the value of the final score, the match score final_scores, the more likely it is to be recommended.

[0069] 5, the calculation unit 32 of the server 30 identifies brands that match the user's preferences based on the match score final_scores (step S50). Specifically, the calculation unit 32 of the server 30 expresses each component of the match score final_scores in a probability format so that the sum of each component is 1, and identifies brands recommended to the user in descending order of the component. The match score final_scores expresses each component in a probability format as shown in the following equation (8).

[0070] prob=exp(final_scores) / Σ_{i}(exp(final_scores(i)) (8)

[0071] The probability prоb is a vector with components equal to the number of stock types, and exp(final_scores(i)) represents the i-th component (i is an integer between 1 and 26 (corresponding to stocks A to Z, respectively)). For example, the user's recommended stocks are quantitatively identified by score, such as prоb=[0.03, 0.15, 0.02, , 0.2], and the stock with the highest score is identified as the recommended stock for the user.

[0072] Then, the calculation unit 32 of the server 30 transmits result information regarding the identified recommended brand to the terminal device 20, and causes an output device (e.g., a display) of the terminal device 20 to output the result information (step S60). Specifically, the calculation unit 32 of the server 30 causes the terminal device 20 to display a plurality of brands recommended to the user in descending order of the probability prоb score, as shown in Fig. 4 .

[0073] As described above, the server 30 identifies a brand that matches the user's preferences based on input data entered by the user via the terminal device 20. This allows the user to sample a specific brand and discover a brand that matches the user's preferences from among multiple brands, including brands that the user has not sampled. As a result, the user can enjoy a brand that they have not previously been aware of, and user satisfaction increases.

[0074] Furthermore, when identifying brands that suit the user's preferences, the server 30 identifies brands that suit the user's preferences based on correlation data that indicates correlations between the sample brand and other types of brands in addition to the input data from the user. This allows the server 30 to identify brands that suit the user's preferences with greater accuracy than when based solely on the input data.

[0075] [4. Schematic configuration of the suction device] Next, specific configurations of the above-mentioned suction device 100 will be described, including a suction device 100A of a first configuration example and a suction device 100B of a second configuration example.

[0076] (First configuration example) 10 is a schematic diagram illustrating an inhalation device 100A according to a first exemplary configuration. The inhalation device 100A according to this exemplary configuration includes a power supply unit 110, a cartridge 120, and a flavor-imparting cartridge 130. The power supply unit 110 includes a power supply section 111A, a sensor section 112A, a notification section 113A, a memory section 114A, a communication section 115A, and a control section 116A. The cartridge 120 includes a heating section 121A, a liquid guide section 122, and a liquid storage section 123. The flavor-imparting cartridge 130 includes a flavor source 131 and a mouthpiece 124. An air flow path 180 is formed in the cartridge 120 and the flavor-imparting cartridge 130.

[0077] Power supply unit 111A stores electric power. Power supply unit 111A supplies electric power to each component of suction device 100A under the control of control unit 116A. Power supply unit 111A may be configured with, for example, a rechargeable battery such as a lithium ion secondary battery.

[0078] Sensor unit 112A acquires various types of information related to suction device 100A. As one example, sensor unit 112A is configured with a pressure sensor such as a condenser microphone, a flow rate sensor, or a temperature sensor, and acquires values associated with suction by the user. As another example, sensor unit 112A is configured with an input device such as a button or a switch that accepts information input from the user.

[0079] Notification unit 113A notifies the user of information. The information notified to the user by notification unit 113A includes, for example, various information such as SOC (State Of Charge) indicating the charging state of power supply unit 111A, preheating time for suction, and suction possible period. Notification unit 113A is configured by, for example, a light emitting device that emits light, a display device that displays images, a sound output device that outputs sound, or a vibration device that vibrates.

[0080] Storage unit 114A stores various types of information for the operation of suction device 100 A. Storage unit 114A is configured by, for example, a nonvolatile storage medium such as a flash memory.

[0081] The communication unit 115A is a communication interface capable of performing communication in accordance with any wired or wireless communication standard, such as Wi-Fi (registered trademark), Bluetooth (registered trademark), BLE (Bluetooth Low Energy (registered trademark), NFC (Near Field Communication), or LPWA (Low Power Wide Area) standards.

[0082] The control unit 116A functions as an arithmetic processing unit and a control unit, and controls the overall operation within the suction device 100A in accordance with various programs. The control unit 116A is realized by an electronic circuit such as a CPU (Central Processing Unit) or a microprocessor, for example.

[0083] The liquid reservoir 123 stores an aerosol source. The aerosol source is atomized to generate an aerosol. The aerosol source is a liquid, such as a polyhydric alcohol, such as glycerin or propylene glycol, or water. The aerosol source may contain a tobacco-derived or non-tobacco-derived flavor component. When the inhalation device 100A is a medical inhaler, such as a nebulizer, the aerosol source may contain a drug.

[0084] The liquid guide portion 122 guides and holds the aerosol source, which is a liquid stored in the liquid storage portion 123, from the liquid storage portion 123. The liquid guide portion 122 is, for example, a wick formed by twisting a fiber material such as glass fiber or a porous material such as porous ceramic. In this case, the aerosol source stored in the liquid storage portion 123 is guided by the capillary effect of the wick.

[0085] The heating unit 121A generates aerosol by heating the aerosol source and atomizing the aerosol source. In the example shown in FIG. 10, the heating unit 121A is configured as a coil and is wound around the liquid guide unit 122. When the heating unit 121A generates heat, the aerosol source held in the liquid guide unit 122 is heated and atomized, generating aerosol. The heating unit 121A generates heat when power is supplied from the power supply unit 111A. For example, power may be supplied to the heating unit 121A when the sensor unit 112A detects that the user has started inhaling and / or that predetermined information has been input. Then, power supply to the heating unit 121A may be stopped when the sensor unit 112A detects that the user has stopped inhaling and / or that predetermined information has been input. Note that the user's inhalation operation on the inhalation device 100A can be detected, for example, based on the pressure (internal pressure) within the inhalation device 100A detected by a puff sensor exceeding a predetermined threshold.

[0086] Flavor source 131 is a component for imparting flavor components to the aerosol. Flavor source 131 may include tobacco-derived or non-tobacco-derived flavor components.

[0087] The air flow path 180 is a path for air inhaled by the user. The air flow path 180 has a tubular structure with an air inlet 181, which is an entrance for air into the air flow path 180, and an air outlet 182, which is an exit for air from the air flow path 180, at both ends. In the middle of the air flow path 180, a liquid guide section 122 is disposed on the upstream side (the side closer to the air inlet 181) and a flavor source 131 is disposed on the downstream side (the side closer to the air outlet 182). Air flowing in from the air inlet 181 as the user inhales is mixed with the aerosol generated by the heating section 121A and, as shown by arrow 190, passes through the flavor source 131 and is transported to the air outlet 182. When the mixed fluid of the aerosol and air passes through the flavor source 131, flavor components contained in the flavor source 131 are imparted to the aerosol.

[0088] Mouthpiece 124 is a member that is held in the mouth by the user when inhaling. Air outlet holes 182 are arranged in mouthpiece 124. By holding mouthpiece 124 in the mouth and inhaling, the user can take in the mixed fluid of the aerosol and air into the oral cavity.

[0089] The above describes an example of the configuration of the suction device 100A. Of course, the configuration of the suction device 100A is not limited to the above, and various configurations such as those exemplified below may be used.

[0090] As an example, the inhalation device 100A may not include the flavoring cartridge 130. In that case, the cartridge 120 is provided with the mouthpiece 124.

[0091] As another example, the inhalation device 100A may include multiple aerosol sources. Multiple types of aerosols generated from the multiple aerosol sources may be mixed in the air flow path 180 and undergo a chemical reaction to generate additional types of aerosols.

[0092] Furthermore, the means for atomizing the aerosol source is not limited to heating by the heating unit 121 A. For example, the means for atomizing the aerosol source may be vibration atomization or induction heating.

[0093] (1-2) Second configuration example 11 is a schematic diagram showing a suction apparatus 100B of a second configuration example. The suction apparatus 100B includes a power supply unit 111B, a sensor unit 112B, a notification unit 113B, a memory unit 114B, a communication unit 115B, a control unit 116B, a heating unit 121B, a housing unit 140, and a heat insulating unit 144. In the suction apparatus 100A of the first configuration example, the power supply unit 110 housing the power supply unit 111A and the heating unit 121A are separate entities, but in the suction apparatus 100B of the second configuration example, the power supply unit 111B and the heating unit 121B are integrated. In other words, the suction apparatus 100B of the second configuration example can also be said to be a power supply unit with a built-in heating unit.

[0094] Each of the power supply unit 111B, sensor unit 112B, notification unit 113B, memory unit 114B, communication unit 115B, and control unit 116B is substantially identical to the corresponding component included in the suction device 100A according to the first configuration example.

[0095] The storage unit 140 has an internal space 141 and holds the stick-shaped substrate 150 while accommodating a portion of the stick-shaped substrate 150 in the internal space 141. The storage unit 140 has an opening 142 that connects the internal space 141 to the outside, and accommodates the stick-shaped substrate 150 inserted into the internal space 141 through the opening 142. For example, the storage unit 140 is a cylindrical body with the opening 142 and a bottom 143 as its bottom surface, and defines a columnar internal space 141. An air flow path that supplies air to the internal space 141 is connected to the storage unit 140. An air inlet, which is an air inlet to the air flow path, is arranged, for example, on a side surface of the suction device 100. An air outlet, which is an air outlet from the air flow path to the internal space 141, is arranged, for example, on the bottom 143.

[0096] The stick-shaped substrate 150 includes a substrate portion 151 and a mouthpiece portion 152. The substrate portion 151 includes an aerosol source. The aerosol source includes a tobacco-derived or non-tobacco-derived flavor component. When the inhalation device 100B is a medical inhaler such as a nebulizer, the aerosol source may include a drug. The aerosol source may be a liquid, such as a polyhydric alcohol (e.g., glycerin or propylene glycol) containing a tobacco-derived or non-tobacco-derived flavor component, or water, or a solid containing a tobacco-derived or non-tobacco-derived flavor component. When the stick-shaped substrate 150 is held in the storage portion 140, at least a portion of the substrate portion 151 is housed in the internal space 141, and at least a portion of the mouthpiece portion 152 protrudes from the opening 142. When a user holds the mouthpiece portion 152 protruding from the opening 142 in their mouth and inhales, air flows into the internal space 141 via an air flow path (not shown) and reaches the user's mouth along with the aerosol generated from the substrate portion 151.

[0097] 11, the heating part 121B is configured in a film shape and is arranged so as to cover the outer periphery of the storage part 140. When the heating part 121B generates heat, the substrate part 151 of the stick-shaped substrate 150 is heated from the outer periphery, and an aerosol is generated.

[0098] The heat insulating section 144 prevents heat transfer from the heating section 121B to other components. For example, the heat insulating section 144 is made of a vacuum heat insulating material, an aerogel heat insulating material, or the like.

[0099] The above describes an example of the configuration of the suction device 100B. Of course, the configuration of the suction device 100B is not limited to the above, and various configurations such as those exemplified below may be used.

[0100] As one example, the heating unit 121B may be configured in a blade shape and disposed so as to protrude from the bottom 143 of the storage unit 140 into the internal space 141. In this case, the blade-shaped heating unit 121B is inserted into the substrate 151 of the stick-shaped substrate 150 and heats the substrate 151 of the stick-shaped substrate 150 from the inside. As another example, the heating unit 121B may be disposed so as to cover the bottom 143 of the storage unit 140. Furthermore, the heating unit 121B may be configured as a combination of two or more of a first heating unit covering the outer periphery of the storage unit 140, a blade-shaped second heating unit, and a third heating unit covering the bottom 143 of the storage unit 140.

[0101] As another example, the storage unit 140 may include an opening / closing mechanism such as a hinge that opens and closes a portion of the outer shell that forms the internal space 141. The storage unit 140 may then open and close the outer shell to hold and store the stick-shaped substrate 150 inserted into the internal space 141. In this case, the heating unit 121B may be provided at the holding location in the storage unit 140, and may heat the stick-shaped substrate 150 while pressing it.

[0102] Furthermore, the means for atomizing the aerosol source is not limited to heating by the heating unit 121B. For example, the means for atomizing the aerosol source may be induction heating. In that case, the suction device 100B has at least an electromagnetic induction source such as a coil that generates a magnetic field, instead of the heating unit 121B. A susceptor that generates heat by induction heating may be provided in the suction device 100B, or may be included in the stick-shaped substrate 150.

[0103] Furthermore, the suction device 100B may further include the heating unit 121A, the liquid guide unit 122, the liquid storage unit 123, and the air flow path 180 according to the first configuration example, and the air flow path 180 may supply air to the internal space 141. In this case, the mixed fluid of the aerosol and air generated by the heating unit 121A flows into the internal space 141 and is further mixed with the aerosol generated by the heating unit 121B, and reaches the oral cavity of the user.

[0104] Although one embodiment of the present invention has been described above with reference to the accompanying drawings, it goes without saying that the present invention is not limited to such an embodiment. It is clear that a person skilled in the art can conceive of various modifications or alterations within the scope of the claims, and it is understood that these also naturally fall within the technical scope of the present invention. Furthermore, the components of the above embodiment may be combined in any manner without departing from the spirit of the invention.

[0105] In the support method of the above-described embodiment, the user samples multiple brands (aerosol sources) and identifies at least one aerosol source that matches the user's preferences based on the input data for each brand, but this is not limited to this. For example, the support method may be configured such that the user samples one brand and identifies at least one aerosol source that matches the user's preferences based on the input data for that one brand.

[0106] This specification describes at least the following items. Note that the components in parentheses correspond to those in the above-described embodiment, but are not limited to these.

[0107] (1) A method for assisting a user in finding an aerosol source that matches a user's preferences by having the user try at least one aerosol source from among a plurality of aerosol sources, the method comprising: An acquisition step (step S10) of acquiring predetermined input data input from the user via a terminal device (terminal device 20) and including information about the user's preferences for the aerosol source sampled by the user; The computer (server 30) executes an identification step (steps S20 to S50) of identifying at least one aerosol source that matches the user's preferences based on the input data; The input data includes a first evaluation value (first evaluation value 41) that is the user's evaluation of a plurality of feature amounts including the taste of the aerosol source that was sampled, the first evaluation value indicates a deviation of the user's preference from a reference value of each of the plurality of feature amounts of the sampled aerosol source. How to help.

[0108] According to (1), it is possible to assist a user in finding a suitable aerosol source from among multiple types of aerosol sources, including aerosol sources that have not been tried, based on the user's input data for the aerosol sources that have been tried. In addition, by using the deviation of the user's preference from the reference value of each of multiple feature quantities as input data, it is possible to appropriately grasp the user's preference characteristics for each feature quantity.

[0109] (2) The support method according to (1), The reference value is an average of evaluation values by a plurality of people who have previously tried the aerosol source. How to help.

[0110] According to (2), the reference values for the plurality of feature quantities can be appropriately determined.

[0111] (3) The support method according to (1) or (2), each of the plurality of types of aerosol sources has a smoking taste characteristic including the reference value for each of the plurality of feature quantities; In the specifying step, the computer Calculating the user's preference characteristics based on the first evaluation value (step S41); A first score is calculated by quantifying the similarity between the user's preference characteristics and the smoking taste characteristics of the plurality of types of aerosol sources (step S42); Identifying the aerosol source that matches the user's preferences based on the first score (step S50); How to help.

[0112] According to (3), an aerosol source that appropriately matches the user's preferences can be identified based on the first score, which quantitatively evaluates the similarity between the user's preference characteristics and the smoking taste characteristics of the aerosol source.

[0113] (4) The support method according to any one of (1) to (3), the plurality of feature quantities include at least two of a draw, an amount of vapor, and a flavor component when the aerosol source is sampled; How to help.

[0114] According to (4), the features include at least two of the draw feel, vapor volume, and flavor elements, which have a high contribution rate to identifying an aerosol source that matches the user's preferences, so that the aerosol source that matches the user's preferences can be accurately identified.

[0115] (5) The support method according to (4), The flavor elements include at least one of an aroma intensity, a menthol flavor intensity, a fruit flavor intensity, and a bitterness intensity. How to help.

[0116] According to (5), the flavor elements of the characteristic quantities include at least one of the fragrance intensity, menthol flavor intensity, fruit flavor intensity, and bitterness intensity, which have a high contribution to identifying an aerosol source that matches the user's preferences, so that an aerosol source that matches the user's preferences can be accurately identified.

[0117] (6) A support method according to any one of (1) to (5), In the specifying step, the computer Identifying at least one aerosol source that matches the user's preferences based on the input data and correlation data that indicates correlations between the aerosol source and other types of aerosol sources sampled by the user; How to help.

[0118] According to (6), it is possible to accurately identify an aerosol source that matches the user's preferences based on the input data and the correlation data.

[0119] (7) The support method according to (6), The input data includes a second rating value (second rating value 42) that is the user's rating regarding the user's overall preference for the sampled aerosol source. How to help.

[0120] According to (7), by combining the evaluation value regarding the user's overall preference for the aerosol source sampled with the correlation data, it is possible to identify an aerosol source from among multiple types of aerosol sources that is closest to the user's overall preference for the aerosol source sampled.

[0121] (8) The support method according to any one of (1) to (7), The computer further executes a result output step (step S60) of outputting result information including information on the aerosol source identified in the identification step to the terminal device of the user; the result information includes a reason for suggesting to the user the aerosol source identified in the identifying step. How to help.

[0122] According to (8), it is possible to increase the user's satisfaction with the recommended aerosol source.

[0123] (9) The support method according to any one of (1) to (8), The computer In the identifying step, ranking and identifying a plurality of aerosol sources that match the user's preferences; a result output step (step S60) of outputting the plurality of aerosol sources identified in the identification step to the terminal device in a manner that allows the user to understand the ranking results; How to help.

[0124] According to (9), users can find an aerosol source that suits their preferences by considering the recommendation order from among multiple recommended aerosol sources.

[0125] (10) An information processing device (server 30) that supports a user in finding an aerosol source that matches the user's preferences by having the user try at least one aerosol source from among a plurality of aerosol sources, Acquire predetermined input data input from the user via a terminal device (terminal device 20) and including information regarding the user's preferences for the aerosol source sampled by the user; Identifying at least one aerosol source that meets the user's preferences based on the input data; The input data includes a first evaluation value (first evaluation value 41) that is the user's evaluation of a plurality of feature amounts including the taste of the aerosol source that was sampled, the first evaluation value indicates a deviation of the user's preference from a reference value of each of the plurality of feature amounts of the sampled aerosol source. Information processing device.

[0126] According to (10), based on the user's input data for the aerosol sources that have been tried, it is possible to assist the user in finding an aerosol source that is suitable for the user from among multiple types of aerosol sources, including aerosol sources that have not been tried. [Explanation of symbols]

[0127] 20 Terminal equipment 30 Servers (computers, information processing devices) 100, 100A, 100B Suction device (aerosol generating device)

Claims

1. A method for assisting a user in finding an aerosol source that matches a user's preferences by having the user try at least one aerosol source from among a plurality of aerosol sources, the method comprising: an acquiring step of acquiring predetermined input data inputted from the user via a terminal device, the input data including information regarding the user's preferences for the aerosol source sampled by the user; and identifying at least one aerosol source that matches the user's preferences based on the input data; the input data includes a first evaluation value that is an evaluation by the user regarding a plurality of feature amounts including a taste of the aerosol source that has been sampled; the first evaluation value indicates a deviation of the user's preference from a reference value of each of the plurality of feature amounts of the sampled aerosol source. How to help.

2. The support method according to claim 1, The reference value is an average of evaluation values by a plurality of people who have previously tried the aerosol source. How to help.

3. The support method according to claim 1, each of the plurality of types of aerosol sources has a smoking taste characteristic including the reference value for each of the plurality of feature quantities; In the specifying step, the computer calculating a preference characteristic of the user based on the first evaluation value; calculating a first score that quantifies the similarity between the user's preference characteristics and the smoking taste characteristics of the plurality of types of aerosol sources; identifying the aerosol source that matches the user's preferences based on the first score; How to help.

4. The support method according to claim 1, the plurality of feature quantities include at least two of a draw, an amount of vapor, and a flavor component when the aerosol source is sampled; How to help.

5. The support method according to claim 4, The flavor elements include at least one of an aroma intensity, a menthol flavor intensity, a fruit flavor intensity, and a bitterness intensity. How to help.

6. The support method according to any one of claims 1 to 5, In the specifying step, the computer Identifying at least one aerosol source that matches the user's preferences based on the input data and correlation data that indicates correlations between the aerosol source and other types of aerosol sources sampled by the user. How to help.

7. The support method according to claim 6, The input data includes a second rating value, which is the user's rating regarding the user's overall preference for the sampled aerosol source. How to help.

8. The support method according to any one of claims 1 to 5, The computer further executes a result output step of outputting result information including information on the aerosol source identified in the identification step to the terminal device of the user; the result information includes a reason for suggesting to the user the aerosol source identified in the identifying step. How to help.

9. The support method according to any one of claims 1 to 5, The computer In the identifying step, ranking and identifying a plurality of aerosol sources that match the user's preferences; a result output step of outputting the plurality of aerosol sources identified in the identification step to the terminal device in a manner that allows the user to understand the ranking results; How to help.

10. An information processing device that supports a user in finding an aerosol source that matches the user's preferences by having the user try at least one aerosol source from among a plurality of aerosol sources, acquiring predetermined input data inputted from the user via a terminal device and including information regarding the user's preferences for the aerosol source sampled by the user; Identifying at least one aerosol source that meets the user's preferences based on the input data; the input data includes a first evaluation value that is an evaluation by the user regarding a plurality of feature amounts including a taste of the aerosol source that has been sampled; the first evaluation value indicates a deviation of the user's preference from a reference value of each of the plurality of feature amounts of the sampled aerosol source. Information processing device.

Images