Information processing method, information processing program, information processing system, and learning system

Abstract

Provided is an information processing method performed by a computer, said method comprising: a step (S203) for acquiring desired emotion information related to an emotion desired by a user with regard to a meal; a step (S204) for generating, on the basis of the desired emotion information, recommended meal information related to meal content to be recommended to the user in order to realize the emotion desired by the user with regard to the meal; and a step (S205) for outputting the generated recommended meal information.

Description

Information processing method, information processing program, information processing system, and learning system

[0001] The present disclosure relates to an information processing method, an information processing program, an information processing system, and a learning system.

[0002] Patent Literature 1 discloses a recipe suggestion system that predicts a user's future emotions based on the user's schedule information and suggests recipes for dishes that are optimal for the predicted emotions.

[0003] Japanese Patent Application Laid-Open No. 2022-150207

[0004] “About the Dietary Balance Guide,” [online], Ministry of Agriculture, Forestry and Fisheries, [searched October 27, 2023], Internet <URL: https: / / www.maff.go.jp / j / balance_guide / >

[0005] However, with the above-described conventional technology, it is difficult to predict the user's future emotions based on the user's schedule information, and it is difficult to provide recommended meal information that will enable the user to achieve the emotions they desire.

[0006] Therefore, the present disclosure provides an information processing method and the like that can provide recommended meal information for realizing a user's desired emotion.

[0007] An information processing method according to one aspect of the present disclosure is an information processing method performed by a computer, and includes the steps of acquiring desired emotion information regarding an emotion a user desires to feel through a meal, generating recommended meal information regarding meal contents recommended to the user to achieve the user's desired emotion through a meal based on the desired emotion information, and outputting the generated recommended meal information.

[0008] This comprehensive or specific aspect may be realized by an apparatus, a system, an integrated circuit, a computer program, or a computer-readable recording medium, or by any combination of an apparatus, a system, a method, an integrated circuit, a computer program, and a recording medium. The computer-readable recording medium includes, for example, a non-volatile recording medium such as a CD-ROM (Compact Disc-Read Only Memory).

[0009] According to the present disclosure, it is possible to provide recommended meal information for realizing a user's desired emotion.

[0010] FIG. 1 is a block diagram showing the configurations of a learning system and an information processing system according to Embodiment 1. FIG. 2 is a sequence diagram of a learning phase according to Embodiment 1. FIG. 3 is a diagram showing an example of first emotion information according to Embodiment 1. FIG. 4 is a diagram showing an example of first biological information according to Embodiment 1. FIG. 5 is a diagram showing an example of dietary information according to Embodiment 1. FIG. 6 is a diagram showing an example of second emotion information according to Embodiment 1. FIG. 7 is a sequence diagram of a prediction phase according to Embodiment 1. FIG. 8 is a diagram showing an example of an input screen for desired emotion information according to Embodiment 1. FIG. 9 is a diagram showing an example of recommended dietary information according to Embodiment 1. FIG. 10 is a diagram showing an example of a display screen for recommended dietary information according to Embodiment 1. FIG. 11 is a block diagram showing the configurations of an information processing system and a learning system according to Embodiment 2. FIG. 12 is a sequence diagram of a learning phase according to Embodiment 2. FIG. 13 is a diagram showing an example of second biological information according to Embodiment 2. FIG. 14 is a sequence diagram of a prediction phase according to Embodiment 2. FIG. 15 is a diagram showing an example of a training dataset according to a modification.

[0011] (Outline of the Present Disclosure) Before describing the embodiments, an outline of the present disclosure will be described.

[0012] An information processing method according to a first aspect of the present disclosure is an information processing method performed by a computer, and includes the steps of acquiring desired emotion information regarding an emotion a user desires to feel through a meal, generating recommended meal information regarding meal contents recommended to the user to achieve the user's desired emotion through a meal based on the desired emotion information, and outputting the generated recommended meal information.

[0013] According to this method, recommended meal information for realizing the user's desired emotion is generated based on desired emotion information related to the emotion the user desires through a meal. Therefore, more suitable recommended meal information can be provided for realizing the user's desired emotion. For example, when meal information is provided based on the user's future emotion predicted from schedule information, as in Patent Document 1, meal information may be provided based on an emotion different from the user's desired emotion. Therefore, the method described in Patent Document 1 may provide meal information that is not suitable for realizing the user's desired emotion. On the other hand, according to the information processing method of the first aspect of the present disclosure, recommended meal information is generated based on desired emotion information, so more suitable recommended meal information can be provided for realizing the user's desired emotion. Furthermore, for users who receive the recommended meal information, the user can realize the emotion they desire through a meal, thereby enhancing the customer experience value.

[0014] An information processing method according to a second aspect of the present disclosure is the information processing method according to the first aspect, wherein in the step of generating the recommended meal information, the recommended meal information is generated by inputting the desired emotion information into a trained model, and the trained model has been machine-trained using a set of meal information on the contents of the meal eaten by the user and second emotion information on the emotion of the user after the meal as a training dataset.

[0015] According to this, recommended meal information is generated by inputting desired emotional information into a trained model that has been machine-learned using the user's information set as a training data set, so that recommended meal information that is more suitable for the user can be provided.

[0016] An information processing method according to a third aspect of the present disclosure is the information processing method according to the first aspect, further comprising the step of acquiring at least one of first emotion information related to the emotion of the user before the meal and first biological information of the user before the meal, and in the step of generating the recommended meal information, the recommended meal information is generated based on the desired emotion information as well as at least one of the first emotion information and the first biological information.

[0017] This allows the generation of recommended meal information based on the user's pre-meal emotions and / or biometric information in addition to the emotions desired by the user after eating, making it possible to provide more suitable recommended meal information for realizing the user's desired emotions. In particular, it is possible to provide more suitable recommended meal information for changing the user's state from before eating to after eating, which will realize the user's desired emotions.

[0018] An information processing method according to a fourth aspect of the present disclosure is the information processing method according to the third aspect, wherein in the step of generating the recommended meal information, the recommended meal information is generated by inputting the desired emotion information and at least one of the first emotion information and the first biometric information into a trained model, and the trained model has been machine-trained using a set of meal information related to the contents of the meal eaten by the user, second emotion information related to the emotion of the user after the meal, and at least one of first emotion information related to the emotion of the user before the meal and the first biometric information of the user before the meal as training datasets.

[0019] According to this, recommended meal information is generated by inputting desired emotional information into a trained model that has been machine-learned using the user's information set as a training data set, so that recommended meal information that is more suitable for the user can be provided.

[0020] An information processing method according to a fifth aspect of the present disclosure is the information processing method according to the first aspect, wherein the step of generating the recommended meal information includes a step of generating desired biometric information corresponding to the emotion desired by the user through a meal based on the desired emotion information, and a step of generating the recommended meal information based on the desired biometric information.

[0021] According to this, desired biological information is generated based on desired emotion information, and recommended meal information is generated based on the desired biological information. By generating recommended meal information from desired emotion information via desired biological information in this way, it becomes possible to reflect emotions that the user consciously desires as well as emotions that the user potentially desires in the recommended meal information, and it is possible to provide recommended meal information that is more suited to the emotions that the user desires.

[0022] An information processing method according to a sixth aspect of the present disclosure is the information processing method according to the fifth aspect, wherein in the step of acquiring the desired biometric information, the desired biometric information is generated by inputting the desired emotion information into a first trained model, and the first trained model is machine-trained using a set of emotion information related to the user's emotion and the user's biometric information corresponding to the emotion information as a training dataset.

[0023] According to this, desired biometric information is generated by inputting desired emotion information into a first trained model that has been machine-learned using the user's information set as a training data set, so that biometric information of the user corresponding to the emotion desired by the user can be generated.

[0024] An information processing method according to a seventh aspect of the present disclosure is the information processing method according to the fifth or sixth aspect, wherein in the step of acquiring the recommended meal information, the recommended meal information is generated by inputting the desired biometric information into a second trained model, and the second trained model is machine-trained using a set of meal information regarding the contents of the meal eaten by the user and the second biometric information of the user after the meal as a training dataset.

[0025] According to this, recommended meal information is generated by inputting desired biometric information into a second trained model that has been machine-learned using the user's information set as a training dataset, so that recommended meal information that is more suitable for the user can be provided.

[0026] An information processing method according to an eighth aspect of the present disclosure is the information processing method according to the fifth or sixth aspect, further comprising the step of acquiring at least one of first emotion information relating to the emotion of the user before the meal and first biological information of the user before the meal, and in the step of generating the recommended meal information, the recommended meal information is generated based on at least one of the first emotion information and the first biological information in addition to the desired biological information.

[0027] This allows the generation of recommended meal information based on the user's pre-meal emotions and / or biometric information in addition to the emotions desired by the user after eating, making it possible to provide more suitable recommended meal information for realizing the user's desired emotions. In particular, it is possible to provide more suitable recommended meal information for changing the user's state from before eating to after eating, which will realize the user's desired emotions.

[0028] An information processing method according to a ninth aspect of the present disclosure is the information processing method according to the eighth aspect, wherein in the step of generating the recommended meal information, the recommended meal information is generated by inputting the desired biometric information and at least one of the first emotional information and the first biometric information into a second trained model, and the second trained model has been machine-trained using a set of dietary information related to the contents of the meal eaten by the user, the second biometric information of the user after the meal, and at least one of first emotional information related to the emotion of the user before the meal and the first biometric information of the user before the meal as a training dataset.

[0029] According to this, recommended meal information is generated by inputting desired biometric information into a second trained model that has been machine-learned using the user's information set as a training dataset, so that recommended meal information that is more suitable for the user can be provided.

[0030] An information processing method according to a tenth aspect of the present disclosure is an information processing method according to any one of the first to ninth aspects, wherein in the step of outputting the recommended meal information, the recommended amount of each of a plurality of dish categories that make up the meal is displayed on a display as the recommended meal information.

[0031] This allows the recommended amount for each food category to be presented on the display, effectively supporting the user in preparing meals.

[0032] An information processing method according to an eleventh aspect of the present disclosure is the information processing method according to the tenth aspect, wherein the step of outputting the recommended meal information further includes displaying one or more candidate dish menus belonging to the plurality of cuisine categories, and the information processing method further includes receiving from the user a selection of the one or more candidate dish menus displayed and an input of the quantity of each of the one or more selected cuisine menus.

[0033] This allows the user to select from the displayed candidates a dish menu that satisfies the recommended amount for each dish category indicated by the recommended meal information, thereby more effectively supporting the user in preparing meals.

[0034] An information processing program according to a twelfth aspect of the present disclosure causes a computer to execute the information processing method according to any one of the first to eleventh aspects.

[0035] This makes it possible to achieve the same effect as the above-described information processing method with the information processing program.

[0036] An information processing system according to a thirteenth aspect of the present disclosure includes an acquisition unit that acquires desired emotion information related to an emotion desired by a user through a meal, a generation unit that generates recommended meal information related to meal contents recommended to the user for realizing the desired emotion of the user through a meal based on the desired emotion information, and an output unit that outputs the generated recommended meal information.

[0037] This makes it possible to realize the same effect as the above-described information processing method in an information processing system.

[0038] A learning system according to a fourteenth aspect of the present disclosure includes a meal information acquisition unit that acquires meal information related to the contents of a meal eaten by a user; a biometric information acquisition unit that acquires biometric information of the user after the meal; an emotional information acquisition unit that acquires emotional information related to the user's emotions after the meal; a first model construction unit that performs machine learning using a set of the emotional information and the biometric information as a training dataset to construct a first trained model that outputs desired biometric information corresponding to desired emotional information based on input of desired emotional information related to an emotion desired by the user through a meal; and a second model construction unit that performs machine learning using the set of the biometric information and the meal information as a training dataset to construct a second trained model that outputs recommended meal information to the user based on the input desired biometric information so that the user can achieve the desired biometric information through a meal.

[0039] According to this, a first trained model is constructed in which desired biometric information is generated by inputting desired emotion information, and a second trained model is constructed in which recommended diet information is generated by inputting desired biometric information. The desired biometric information is generated from the desired emotion information using this first trained model, and the recommended diet information is generated from the desired biometric information using the second trained model. By generating recommended diet information from the desired emotion information via the desired biometric information in this way, it is possible to reflect the user's potentially desired emotion in the desired biometric information, and it is possible to provide recommended diet information that is more suited to the user's desired emotion.

[0040] Hereinafter, the embodiments will be specifically described with reference to the drawings.

[0041] Note that the embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection configurations, steps, and step sequences shown in the following embodiments are merely examples and are not intended to limit the technology of the present disclosure. Furthermore, each figure is a schematic diagram and is not necessarily an exact illustration. Therefore, for example, the scales and the like do not necessarily match in each figure. Furthermore, in each figure, substantially identical configurations are assigned the same reference numerals, and duplicated descriptions may be omitted or simplified.

[0042] In the following, all or part of a circuit, unit, or device, or all or part of a functional block in a block diagram, may be implemented by a software program. In this case, the software program is recorded on one or more non-transitory storage media such as a ROM, optical disk, hard disk drive, etc., and when the software program is executed by a processor, the functions specified in the software program are performed by the processor and peripheral devices. A system or device may include one or more non-transitory storage media in which the software program is stored, a processor, and necessary hardware devices (e.g., memory, interface, etc.).

[0043] Furthermore, all or part of a circuit, unit (part), or device, or all or part of a functional block in a block diagram, may be implemented by one or more electronic circuits, including, for example, a semiconductor device, a semiconductor integrated circuit (IC), or an LSI (Large Scale Integration). The LSI or IC may be integrated on a single chip or may be configured by combining multiple chips. For example, functional blocks other than memory elements may be integrated on a single chip. While the terms LSI or IC are used here, the term may be changed depending on the degree of integration, and may be called a system LSI, a VLSI (Very Large Scale Integration), or an ULSI (Ultra Large Scale Integration). Field programmable gate arrays (FPGAs), which are programmed after the LSI is manufactured, or reconfigurable logic devices (RLDs), which can reconfigure the connections within the LSI or set up circuit partitions within the LSI, can also be used for the same purpose.

[0044] (Embodiment 1) A learning system 100 and an information processing system 200 according to embodiment 1 will be described below with reference to Fig. 1. Fig. 1 is a block diagram showing the configurations of learning system 100 and information processing system 200 according to this embodiment.

[0045] [1.1 Configuration of the Learning System 100] The learning system 100 is realized using one or more computers (for example, an application server and a database server). The one or more computers may be provided by cloud computing.

[0046] As shown in FIG. 1 , learning system 100 comprises first emotion information acquisition section 111, first biological information acquisition section 112, dietary information acquisition section 113, second emotion information acquisition section 114, model construction section 120, and trained model 130.

[0047] The first emotion information acquisition unit 111 can acquire first emotion information related to the user's emotion before a meal from the user terminal 300. The first emotion information indicates the user's mental attribute before a meal. For example, the first emotion information indicates a mental attribute selected by the user from a plurality of predetermined mental attributes. Examples of the plurality of predetermined mental attributes include excitement, energy, happiness, joy, fun, satisfaction, relief, relaxation, fatigue, boredom, depression, sadness, discomfort, worry, fear, and vigilance. The first emotion information may be expressed as coordinate values ​​on a two-dimensional plane composed of two axes, one indicating pleasant / unpleasant and the other indicating alertness / sleepiness. The first emotion information may be a mental attribute based on the results of an emotion diagnosis received by the user, or may be a mental attribute detected and recognized using emotion detection and recognition technology. The first emotion information acquisition unit 111 is optional and need not be included in the learning system 100.

[0048] The first biological information acquisition unit 112 can acquire the first biological information of the user before a meal from the user terminal 300. The first biological information acquisition unit 112 may acquire the first biological information from a biological sensor worn by the user. The first biological information is physiological information emitted by the user before a meal. Examples of the first biological information that can be used include, but are not limited to, heart rate, body temperature, blood pressure, blood sugar, or any combination of these. The first biological information acquisition unit 112 is optional and does not need to be included in the learning system 100.

[0049] The meal information acquisition unit 113 can acquire meal information related to the contents of a meal eaten by the user from the user terminal 300. The meal information indicates the amount of each of a plurality of dish categories that make up the meal. The plurality of dish categories may be, for example, but are not limited to, the categories described in Non-Patent Document 1 (staple food, side dish, main dish, dairy product, and fruit). Note that food components (e.g., carbohydrates, protein, calcium, vitamins, etc.) may be used instead of or in addition to the dish categories.

[0050] Second emotion information acquisition section 114 is able to acquire second emotion information about the user's emotion after a meal from user terminal 300. The second emotion information indicates the user's mental attribute after a meal. The second emotion information is similar to first emotion information, except that it indicates the user's mental attribute after a meal.

[0051] The model construction unit 120 can construct the trained model 130 by performing machine learning (supervised learning) using a set of first emotional information, first biological information, dietary information, and second emotional information as a training dataset. The model construction unit 120 can improve the prediction accuracy of the trained model 130 by repeatedly updating model parameters and evaluating a model having the updated parameters using multiple training datasets. Note that the first emotional information and / or the first biological information are optional and do not need to be used in constructing the trained model 130. Furthermore, there are no particular limitations on the algorithm used in constructing the trained model 130.

[0052] The trained model 130 is machine-learned using a set of meal information related to the contents of the meal eaten by the user, second emotion information related to the user's emotion after the meal, first emotion information related to the user's emotion before the meal, and first biometric information of the user before the meal as a training dataset. As a result, in response to input of desired emotion information related to the emotion the user desires to feel after eating, the user's first emotion information before the meal (optional), and the user's first biometric information before the meal (optional), the trained model 130 can output recommended meal information related to the meal contents recommended to the user to achieve the user's desired emotion through eating. In other words, in the trained model 130, the desired emotion information, the first emotion information (optional), and the first biometric information (optional) are explanatory variables, and the recommended meal information is a target variable.

[0053] [1.2 Configuration of Information Processing System 200] The information processing system 200 is realized using one or more computers (e.g., an application server and a database server). Part or all of the information processing system 200 may be configured on the same computer as the learning system 100.

[0054] As shown in FIG. 1, information processing system 200 comprises first emotion information acquisition section 211 , first biological information acquisition section 212 , desired emotion information acquisition section 213 , generation section 220 , and output section 230 .

[0055] Like first emotion information acquisition section 111, first emotion information acquisition section 211 is able to acquire first emotion information from user terminal 300. Note that first emotion information acquisition section 211 is optional, and does not have to be included in information processing system 200.

[0056] Like the first biometric information acquisition unit 112, the first biometric information acquisition unit 212 can acquire the first biometric information from the user terminal 300. Note that the first biometric information acquisition unit 212 is optional and does not need to be included in the information processing system 200.

[0057] The desired emotion information acquisition unit 213 can acquire desired emotion information related to the emotion the user desires to feel as a result of eating from the user terminal 300 before eating. The desired emotion information indicates the user's psychological attributes that the user desires to feel as a result of eating. For example, the desired emotion information may be interpreted as information related to the emotion the user desires to feel after eating.

[0058] The generator 220 can generate recommended meal information based on the first emotion information, first biometric information, and desired emotion information. Specifically, the generator 220 can generate recommended meal information by inputting the first emotion information, first biometric information, and desired emotion information into the trained model 130. Note that the generator 220 does not have to generate the recommended meal information based on the first emotion information and first biometric information. In other words, the generator 220 may generate recommended meal information based on the desired emotion information, but not on the first emotion information or the first biometric information.

[0059] The output unit 230 can output the recommended meal information to the user terminal 300 .

[0060] [1.3 Configuration of the User Terminal 300] The user terminal 300 is realized using a portable device (e.g., a tablet computer or a smartphone) that can be connected to the learning system 100 and the information processing system 200 via a communication network (e.g., the Internet). The user terminal 300 may also be realized using a wearable device (e.g., a smartwatch or smart glasses).

[0061] The user terminal 300 can receive first emotional information, first biometric information, and desired emotional information from the user before a meal, and can receive meal information from the user before, during, or after a meal. Furthermore, the user terminal 300 can receive second emotional information from the user after a meal. The user terminal 300 can transmit the first emotional information, first biometric information, meal information, and second emotional information to the learning system 100, and can transmit the first emotional information, first biometric information, and desired emotional information to the information processing system 200. The user terminal 300 can also receive recommended meal information from the information processing system 200 before a meal and display it on the display.

[0062] The user terminal 300 does not need to receive various pieces of information from the user. For example, the user terminal 300 may acquire an image of a dish taken with a camera and perform object recognition or the like on the image to acquire meal information. Also, for example, the user terminal 300 may acquire first biometric information from a biometric sensor.

[0063] 2 to 6, the machine learning method performed by the learning system 100 will be described. Fig. 2 is a sequence diagram of the learning phase according to this embodiment. In the learning phase, machine learning is performed by the learning system 100.

[0064] <Step S101> First, first emotion information acquisition section 111 acquires first emotion information relating to the user's emotion before a meal from user terminal 300. Figure 3 shows an example of first emotion information according to the present embodiment. In Figure 3, the first emotion information includes items for time and emotion. For example, the first emotion information indicates that the user's emotion at 6:00 "before breakfast" is "sleepy." Note that step S101 is optional and may be skipped.

[0065] <Step S102> Next, the first biological information acquisition unit 112 acquires the user's first biological information before a meal from the user terminal 300. FIG. 4 shows an example of the first biological information according to this embodiment. In FIG. 4, the first biological information includes items such as time, heart rate, body temperature, diastolic blood pressure, systolic blood pressure, and blood glucose. For example, the first biological information indicates that at a time of "6:00" "before breakfast," the heart rate is "68 bpm," the body temperature is "36.4°C," the diastolic blood pressure is "111 mmHg," the systolic blood pressure is "72 mmHg," and the blood glucose level is "84 mg / dL." Note that step S102 is optional and may be skipped.

[0066] <Step S103> Next, the meal information acquisition unit 113 acquires meal information related to the contents of the meal eaten by the user from the user terminal 300. Fig. 5 shows an example of meal information according to this embodiment. In Fig. 5, the meal information includes items such as time, contents, staple food, side dish, main dish, dairy product, fruit, and caffeine. For example, the meal information indicates that the contents of breakfast eaten at time "7:00" were "sandwich," "salad," "yogurt," and "coffee," and that the amounts of staple food, side dish, main dish, dairy product, fruit, and caffeine were "2 mg," "1 mg," "0.5 mg," "1 mg," "1 mg," and "112 mg," respectively.

[0067] <Step S104> Next, second emotion information acquisition section 114 acquires second emotion information relating to the user's emotion after eating from user terminal 300. Fig. 6 shows an example of second emotion information according to the present embodiment. In Fig. 6, the second emotion information includes items for time and emotion. For example, the second emotion information indicates that the user's emotion at the time "7:30" "after breakfast" is "relieved."

[0068] <Step S105> Finally, the model construction unit 120 performs machine learning using the set of first emotion information, first biometric information, diet information, and second emotion information acquired in steps S101 to S104 as a training dataset, to construct a trained model 130 that outputs recommended diet information based on the input first emotion information, first biometric information, and desired emotion information.

[0069] 7 to 10, an information processing method performed by the information processing system 200 will be described. Fig. 7 is a sequence diagram of the prediction phase according to this embodiment. In the prediction phase, the information processing system 200 generates (predicts) recommended meal information using the trained model 130.

[0070] <Step S201> First, first emotion information acquisition section 211 acquires first emotion information about the user's emotion before eating from user terminal 300. The first emotion information acquired here is similar to the first emotion information acquired in step S101 in Figure 2, and so description thereof will be omitted. Note that step S201 is optional and may be skipped.

[0071] <Step S202> Next, the first biological information acquisition unit 212 acquires the first biological information of the user before eating from the user terminal 300. The first biological information acquired here is the same as the first biological information acquired in step S102 in Fig. 2, and therefore a description thereof will be omitted. Note that step S202 is optional and may be skipped.

[0072] <Step S203> Next, the desired emotion information acquisition unit 213 acquires desired emotion information regarding the emotion the user desires to experience through eating. FIG. 8 shows an example of a desired emotion information input screen according to this embodiment. In FIG. 8 , a plurality of predetermined psychological attributes (excitement, energy, happiness, joy, fun, satisfaction, relief, relaxation, fatigue, boredom, depression, sadness, discomfort, worry, fear, and alertness) are displayed on a two-dimensional plane on the display of the user terminal 300, with a horizontal axis indicating pleasantness / unpleasantness and a vertical axis indicating wakefulness / drowsiness. The user can input the desired emotion information by touching the psychological attribute desired through eating from among the plurality of psychological attributes displayed on the display. Note that the means for inputting the desired emotion information is not limited to the GUI (Graphical User Interface) shown in FIG. 8 . For example, the means for inputting the desired emotion information may be a VUI (Voice User Interface).

[0073] <Step S204> Next, the generation unit 220 generates recommended meal information based on the first emotion information, first biometric information, and desired emotion information. Specifically, the generation unit 220 generates the recommended meal information by inputting the first emotion information, first biometric information, and desired emotion information into the trained model 130. In other words, the generation unit 220 provides the first emotion information, first biometric information, and desired emotion information to the trained model 130, and obtains the recommended meal information from the trained model 130.

[0074] <Step S205> Finally, the output unit 230 outputs the recommended meal information to the user terminal 300. Fig. 9 shows an example of the recommended meal information according to this embodiment. In Fig. 9, the recommended meal information includes the items of desired emotion, staple food, side dish, main dish, dairy product, fruit, and caffeine. For example, the recommended meal information indicates that the recommended meal content for achieving the desired emotion of "relaxation" is "1.8 mg," "1.7 mg," "0.8 mg," "0.9 mg," "0.5 mg," and "18 mg" for the multiple dish categories that make up the meal (staple food, side dish, main dish, dairy product, fruit, and caffeine), respectively.

[0075] The recommended meal information output from the information processing system 200 to the user terminal 300 is displayed on the display of the user terminal 300. FIG. 10 shows an example of a display screen for recommended meal information according to this embodiment. In FIG. 10, the display of the user terminal 300 displays the recommended portion size (SV) for each of the multiple dish categories that make up the meal as the meal content recommended for achieving the desired feeling of "relaxation." The display of the user terminal 300 also displays one or more dish menu candidates belonging to the multiple dish categories in a drop-down list. In FIG. 10, for example, "rice" is selected from the multiple dish menu candidates belonging to the staple food category, and "1.0" is selected as the portion size. In this way, the dish menu and its portion size are set for each of the multiple dish categories and transmitted to the learning system 100.

[0076] [1.6 Summary] As described above, according to the information processing method and information processing system 200 of this embodiment, recommended meal information for realizing a user's desired emotion is generated based on desired emotion information related to the emotion the user desires to feel through a meal. Therefore, it is possible to provide recommended meal information that is more suitable for realizing the user's desired emotion. For example, when meal information is provided based on the user's future emotion predicted from schedule information, as in Patent Document 1, meal information may be provided based on an emotion different from the user's desired emotion. Therefore, the method described in Patent Document 1 may provide meal information that is not suitable for realizing the user's desired emotion. On the other hand, according to the information processing method and information processing system 200 of this embodiment, recommended meal information is generated based on desired emotion information, so it is possible to provide recommended meal information that is more suitable for realizing the user's desired emotion.

[0077] (Embodiment 2) Next, embodiment 2 will be described. In this embodiment, the main difference from embodiment 1 is that recommended diet information is not generated directly from desired emotion information, but desired biological information is generated from desired emotion information, and recommended diet information is then generated from the generated desired biological information. Below, embodiment 2 will be specifically described with reference to the drawings, focusing on the differences from embodiment 1.

[0078] FIG. 11 is a block diagram showing the configuration of a learning system 100A and an information processing system 200A according to this embodiment.

[0079] 2.1 Configuration of learning system 100A Learning system 100A comprises first emotion information acquisition unit 111, first biological information acquisition unit 112, diet information acquisition unit 113, second emotion information acquisition unit 114, second biological information acquisition unit 115, first model construction unit 121, second model construction unit 122, first trained model 131, and second trained model 132.

[0080] The second biological information acquisition unit 115 can acquire second biological information of the user after a meal from the user terminal 300. The second biological information acquisition unit 115 may acquire the second biological information from a biological sensor worn by the user. The second biological information is physiological information emitted by the user after a meal. As with the first biological information, the second biological information may be, but is not limited to, for example, heart rate, body temperature, blood pressure, blood sugar, or any combination thereof.

[0081] The first model construction unit 121 can construct the first trained model 131 by performing machine learning (supervised learning) using a set of second emotion information and second biometric information as a training dataset. The first model construction unit 121 can improve the prediction accuracy of the first trained model 131 by repeatedly updating model parameters and evaluating a model having the updated parameters using multiple training datasets. Note that the algorithm used to construct the first trained model 131 is not particularly limited.

[0082] The second model construction unit 122 can construct the second trained model 132 by performing machine learning (supervised learning) using a set of first emotional information, first biological information, dietary information, and second biological information as a training dataset. The second model construction unit 122 can improve the prediction accuracy of the second trained model 132 by repeatedly updating model parameters and evaluating a model having the updated parameters using multiple training datasets. Note that the first emotional information and / or the first biological information are optional and may not be used to construct the second trained model 132. Furthermore, there are no particular limitations on the algorithm used to construct the second trained model 132.

[0083] The first trained model 131 is machine-learned using a set of second emotion information and second biometric information as a training dataset. As a result, the first trained model 131 can output desired biometric information corresponding to the emotion the user desires to feel as a result of eating in response to input of desired emotion information related to the emotion the user desires to feel as a result of eating. In other words, in the first trained model 131, the desired emotion information is an explanatory variable, and the desired biometric information is a target variable.

[0084] The second trained model 132 has been machine-trained using a set of first emotional information, first biological information, dietary information, and second biological information as a training dataset. As a result, the second trained model 132 can output recommended dietary information in response to input of first emotional information, first biological information, and desired biological information. That is, in the second trained model 132, the desired biological information, first emotional information (optional), and first biological information (optional) are explanatory variables, and the recommended dietary information is a target variable.

[0085] 2.2 Configuration of Information Processing System 200A Information processing system 200A comprises first emotion information acquirer 211, first biological information acquirer 212, desired emotion information acquirer 213, generator 220A, and output section 230.

[0086] The generation unit 220A is capable of generating recommended meal information based on the first emotion information, the first biological information, and the desired emotion information. Specifically, the generation unit 220A includes a biological information generation unit 221 and a meal information generation unit 222.

[0087] The biometric information generation unit 221 can generate desired biometric information corresponding to the emotion the user desires to have after eating, based on the desired emotion information. Specifically, the biometric information generation unit 221 can generate the desired biometric information by inputting the desired emotion information into the first trained model 131.

[0088] The diet information generation unit 222 can generate recommended diet information based on the first emotion information, the first biological information, and the desired biological information. Specifically, the diet information generation unit 222 can generate recommended diet information by inputting the first emotion information, the first biological information, and the desired biological information into the second trained model 132. Note that the generation of recommended diet information by the diet information generation unit 222 does not have to be based on the first emotion information and the first biological information. In other words, the diet information generation unit 222 may generate recommended diet information based on the desired biological information, but not based on the first emotion information or the first biological information.

[0089] 2.3 Machine Learning Method Next, the machine learning method performed by the learning system 100A will be described with reference to Fig. 12 and Fig. 13. Fig. 12 is a sequence diagram of the learning phase according to this embodiment. In the learning phase, machine learning is performed by the learning system 100A.

[0090] <Steps S101 to S104> First, as in the first embodiment, first emotion information, first biometric information, dietary information and second emotion information are acquired from user terminal 300 by first emotion information acquisition section 111, first biometric information acquisition section 112, dietary information acquisition section 113 and second emotion information acquisition section 114, respectively.

[0091] <Step S111> Next, the second biological information acquisition unit 115 acquires the user's second biological information after a meal from the user terminal 300. Fig. 13 shows an example of the second biological information according to this embodiment. In Fig. 13, the second biological information includes items of time, heart rate, body temperature, diastolic blood pressure, systolic blood pressure, and blood glucose. For example, the second biological information indicates that at a time of "7:30" "after breakfast," the heart rate is "83 bpm," the body temperature is "36.8°C," the diastolic blood pressure is "123 mmHg," the systolic blood pressure is "80 mmHg," and the blood glucose is "139 mg / dL."

[0092] <Step S112> Next, the first model construction unit 121 performs machine learning using the set of second emotion information and second biometric information acquired in steps S104 and S111 as a training dataset, to construct a first trained model 131 that outputs desired biometric information based on input of desired emotion information.

[0093] <Step S113> Finally, the second model construction unit 122 performs machine learning using the set of first emotional information, first biological information, dietary information, and second biological information acquired in steps S101 to S103 and S111 as a training dataset, to construct a second trained model 132 that outputs recommended dietary information based on the input of the first emotional information, first biological information, and desired biological information.

[0094] [2.4 Information Processing Method] Next, the information processing method performed by the information processing system 200A will be described with reference to Fig. 14. Fig. 14 is a sequence diagram of the prediction phase according to this embodiment. In the prediction phase, the information processing system 200A generates (predicts) recommended meal information using the first trained model 131 and the second trained model 132.

[0095] <Steps S201 to S203> First, as in Embodiment 1, first emotion information, first biometric information and desired emotion information are acquired from user terminal 300 by first emotion information acquisition section 211, first biometric information acquisition section 212 and desired emotion information acquisition section 213, respectively.

[0096] <Step S211> Next, the biometric information generation unit 221 generates desired biometric information based on the desired emotion information. Specifically, the biometric information generation unit 221 generates the desired biometric information by inputting the desired emotion information to the first trained model 131. In other words, the biometric information generation unit 221 provides the desired emotion information to the first trained model 131 and obtains the desired biometric information from the first trained model 131.

[0097] <Step S212> Next, the diet information generation unit 222 generates recommended diet information based on the first emotion information, the first biological information, and the desired biological information. Specifically, the diet information generation unit 222 generates the recommended diet information by inputting the first emotion information, the first biological information, and the desired biological information into the second trained model 132. In other words, the diet information generation unit 222 provides the first emotion information, the first biological information, and the desired biological information to the second trained model 132, and obtains the recommended diet information from the second trained model 132.

[0098] <Step S205> Finally, similar to the first embodiment, the recommended meal information is output to the user terminal 300 by the output unit 230.

[0099] [2.5 Summary] As described above, according to the information processing method and information processing system 200A of this embodiment, desired biometric information is generated based on desired emotion information, and recommended diet information is generated based on that desired biometric information. By generating recommended diet information from desired emotion information via the desired biometric information in this way, it becomes possible to reflect in the recommended diet information not only emotions that the user consciously desires but also emotions that the user potentially desires, and it is possible to provide recommended diet information that is more suited to the emotions that the user desires.

[0100] (Other Embodiments and Modifications) The information processing system, information processing method, learning system, and learning method have been described above based on the embodiments, but the information processing system, information processing method, learning system, and learning method according to the present disclosure are not limited to the above embodiments. This disclosure also includes other embodiments realized by combining any of the components in the above embodiments, and modifications obtained by applying various modifications to the above embodiments that would occur to those skilled in the art without departing from the spirit of the present disclosure.

[0101] For example, the training dataset used for machine learning is not limited to the dataset described in the above embodiment. For example, the training dataset may include a sensory evaluation value of the meal, and emotional information and / or biometric information during the meal. A modified example of such a training dataset will be described in detail with reference to FIG. 15 . FIG. 15 shows an example of a training dataset according to the modified example. In FIG. 15 , the training dataset includes a set of meal information, first emotional information, first biometric information, second emotional information, and second biometric information. In addition to the items in FIG. 5 , the meal information includes items for sweetness, saltiness, sourness, bitterness, umami, and preference. Sensory evaluation values ​​are input for each of the items for sweetness, saltiness, sourness, bitterness, umami, and preference. Furthermore, although emotional information and biometric information during the meal are displayed as "***" in FIG. 15 , values ​​may be input instead.

[0102] The phrase "at least one of a first element and a second element" may be interpreted as "the first element, the second element, or a combination of the first element and the second element."

[0103] The present disclosure is applicable to an information processing system that outputs recommended meal information regarding meal contents that are recommended to a user in order to achieve a desired feeling of the user through a meal.

[0104] REFERENCE SIGNS LIST 100, 100A Learning system 111, 211 First emotion information acquisition unit 112, 212 First biometric information acquisition unit 113 Diet information acquisition unit 114 Second emotion information acquisition unit 115 Second biometric information acquisition unit 120 Model construction unit 121 First model construction unit 122 Second model construction unit 130 Trained model 131 First trained model 132 Second trained model 200, 200A Information processing system 213 Desired emotion information acquisition unit 220, 220A Generation unit 221 Biometric information generation unit 222 Diet information generation unit 230 Output unit 300 User terminal

Claims

1. An information processing method carried out by a computer, comprising the steps of: acquiring desired emotion information relating to an emotion desired by a user through a meal; generating recommended meal information relating to meal contents recommended to the user for achieving the emotion desired by the user through a meal based on the desired emotion information; and outputting the generated recommended meal information.

2. The information processing method of claim 1, wherein in the step of generating the recommended meal information, the recommended meal information is generated by inputting the desired emotion information into a trained model, and the trained model is machine-trained using a set of meal information on the contents of the meal eaten by the user and second emotion information on the emotion of the user after the meal as a training dataset.

3. The information processing method according to claim 1, further comprising the step of acquiring at least one of first emotion information relating to the emotion of the user before the meal and first biometric information of the user before the meal, and in the step of generating recommended meal information, the recommended meal information is generated based on at least one of the first emotion information and the first biometric information in addition to the desired emotion information.

4. The information processing method of claim 3, wherein in the step of generating the recommended meal information, the recommended meal information is generated by inputting the desired emotion information and at least one of the first emotion information and the first biometric information into a trained model, and the trained model is machine-learned using as a training dataset a set of meal information related to the contents of the meal eaten by the user, second emotion information related to the emotion of the user after the meal, first emotion information related to the emotion of the user before the meal, and at least one of the first biometric information of the user before the meal.

5. An information processing method as described in claim 1, wherein the step of generating recommended meal information includes the steps of: generating desired biometric information corresponding to the emotion desired by the user through a meal based on the desired emotion information; and generating the recommended meal information based on the desired biometric information.

6. The information processing method of claim 5, wherein in the step of acquiring the desired biometric information, the desired biometric information is generated by inputting the desired emotion information into a first trained model, and the first trained model is machine-trained using a set of emotion information regarding the user's emotion and the user's biometric information corresponding to the emotion information as a training dataset.

7. The information processing method of claim 5 or 6, wherein in the step of acquiring the recommended dietary information, the recommended dietary information is generated by inputting the desired biometric information into a second trained model, and the second trained model is machine-trained using a set of dietary information regarding the contents of the meal eaten by the user and the second biometric information of the user after the meal as a training dataset.

8. The information processing method according to claim 5 or 6, further comprising a step of acquiring at least one of first emotion information relating to the emotion of the user before the meal and first biometric information of the user before the meal, and in the step of generating recommended meal information, the recommended meal information is generated based on at least one of the first emotion information and the first biometric information in addition to the desired biometric information.

9. The information processing method of claim 8, wherein in the step of generating the recommended meal information, the recommended meal information is generated by inputting the desired biometric information and at least one of the first emotion information and the first biometric information into a second trained model, and the second trained model is machine-trained using a set of meal information related to the contents of the meal eaten by the user, the second biometric information of the user after the meal, and at least one of first emotion information related to the emotion of the user before the meal and the first biometric information of the user before the meal as a training dataset.

10. An information processing method according to any one of claims 1 to 6, wherein in the step of outputting the recommended meal information, the recommended portions of each of a plurality of dish categories constituting the meal are displayed on a display as the recommended meal information.

11. The information processing method of claim 10, wherein the step of outputting the recommended meal information further includes displaying one or more candidate dish menus belonging to the plurality of food categories, and the information processing method further includes a step of receiving from the user a selection of the one or more candidate dish menus displayed and an input of the quantity of each of the one or more selected dish menus.

12. An information processing program for causing a computer to execute the information processing method according to any one of claims 1 to 6.

13. An information processing system comprising: an acquisition unit that acquires desired emotion information related to an emotion desired by a user through a meal; a generation unit that generates recommended meal information related to meal contents recommended to the user for achieving the user's desired emotion through a meal based on the desired emotion information; and an output unit that outputs the generated recommended meal information.

14. A learning system comprising: a meal information acquisition unit that acquires meal information related to the contents of a meal eaten by a user; a biometric information acquisition unit that acquires biometric information of the user after the meal; an emotion information acquisition unit that acquires emotion information related to the emotion of the user after the meal; a first model construction unit that constructs a first trained model that outputs desired biometric information corresponding to desired emotion information based on input of desired emotion information related to an emotion desired by the user through a meal, by performing machine learning using a set of the emotion information and the biometric information as a training dataset; and a second model construction unit that constructs a second trained model that outputs recommended meal information to the user so that the user can realize the desired biometric information through a meal, based on the input of the desired biometric information, by performing machine learning using the set of the biometric information and the meal information as a training dataset.

Images