Food information provision system, food information provision method, food information provision device, food information provision program product, and recording medium on which program product is recorded

By combining biological information, hobbies and environmental information, using emotion models and coordinate recognition technology, accurately identifying and providing recommended dishes that match users' emotions, the problem of existing systems failing to accurately consider emotions and improving the satisfaction of dietary behaviors .

CN118974721APending Publication Date: 2024-11-15KIKKOMAN CORP +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202280094395.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2022-03-29
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing system fails to accurately consider the user's emotions when recommending dishes, making it difficult to accurately master dishes with high likelihood of achieving satisfaction through dietary behavior.

Method used

A cooking information provision system was designed, through the user information identification department, the current emotion identification department and the recommended cooking identification department, the predictive model combines biological information, hobbies and environmental information, and combines the emotional model and coordinate recognition to accurately identify and provide users with Recommended dishes for emotional matching.

Benefits of technology

It realizes providing users with appropriate recommended cooking information based on accurate consideration of emotions, and improves the probability of users gaining satisfaction through dietary behavior.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118974721A_ABST
    Figure CN118974721A_ABST
Patent Text Reader

Abstract

A system S is provided with: a user information recognition unit (10) that recognizes user information; a current emotion recognition unit (12) that recognizes the current emotion of a user; and a recommended food recognition unit (13) that recognizes a recommended food using a prediction model that inputs the user information and the current emotion and outputs the recommended food. And a cuisine information provision unit (15) that acquires cuisine information relating to the recommended cuisine and provides the cuisine information to the user. A current emotion recognition unit (12) estimates the coordinates selected by the user as the current emotion in an emotion model in which the coordinates are defined on the basis of a plurality of basic emotions.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a cooking information providing system, a cooking information providing method, a cooking information providing device, a cooking information providing program product, and a recording medium recording the program product, which provide information related to cooking recommended for dietary actions to a user. Background Art

[0002] In the past, there existed a system which suggested a dish for a user to take dietary action. Here, "dietary action" refers to various actions related to food intake, including not only the action of eating a dish itself, but also the action of cooking and preparing the dish and making a reservation at a store providing the dish.

[0003] However, the recommended dishes differ not only according to the user's own conditions such as the user's preferences for dishes, but also according to environmental conditions (e.g., the time when eating can be performed, the available ingredients, etc.). Therefore, as such a system, there is a known system that presents recommended dishes based on environmental conditions in addition to the user's preferences for dishes (e.g., see Patent Document 1).

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: International Publication No. 2020 / 241693 Summary of the invention

[0007] Problems to be solved by the invention

[0008] The system described in Patent Document 1 refers only to parameters that are fixed to a certain extent, such as preferences and conditions, when identifying recommended dishes, but does not refer to parameters that are easily variable, such as the user's mood (ie, emotions).

[0009] However, it is known that there is a certain correlation between emotions and eating behaviors (for example, see Imada Jun'o (2009). Emotions and eating behaviors, Emotional Psychology Research 17, 120-128). Therefore, if emotions are not accurately considered, it is difficult to accurately grasp the dishes that are likely to satisfy the eating behavior.

[0010] On the other hand, it is generally difficult for users to accurately express their emotions (and then input these emotions into the system). In addition, the research for accurately expressing their emotions will make users feel complicated, and as a result, they may cause further emotional changes.

[0011] The present invention has been completed in view of the above-mentioned problems, and its purpose is to provide a cooking information providing system, a cooking information providing method, a cooking information providing device, a cooking information providing program product and a recording medium recording the program product, which can accurately take emotions into consideration and provide users with information related to dishes with a high possibility of achieving satisfaction through eating behavior.

[0012] Means for solving problems

[0013] The cooking information providing system of the present invention is used to provide cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat.

[0014] The cooking information providing system is characterized by comprising:

[0015] A user information recognition unit that recognizes user information, the user information being information including at least one of biological information of the user, hobbies, and environment of the eating behavior;

[0016] a current emotion recognition unit for recognizing a current emotion, the current emotion being the emotion at the time when the user wishes to obtain the cooking information;

[0017] a recommended dish recognition unit that recognizes the recommended dish using a prediction model, the prediction model being a model that inputs the user information and the current emotion and outputs the recommended dish; and

[0018] a cooking information providing unit that acquires the cooking information from a cooking information identifying unit and provides the cooking information to the user, wherein the cooking information identifying unit identifies a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking,

[0019] The current emotion recognition unit comprises an emotion model prompting unit and a coordinate recognition unit, wherein the emotion model prompting unit prompts the user with an emotion model in the form of selecting any coordinate in the emotion model, wherein the emotion model is a plane model or a three-dimensional model with coordinates specified based on a plurality of basic emotions; and the coordinate recognition unit recognizes the selected coordinates as the current emotion, wherein the selected coordinates are the coordinates in the emotion model selected by the user.

[0020] The recommended dish recognition unit uses the following prediction model as the prediction model: each candidate dish among the plurality of candidate dishes, the selection coordinates, and the user information are used as learning data, so that the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the plurality of candidate dishes and outputs it.

[0021] Here, "user" refers to the user of the cooking information providing system of the present invention. Therefore, the person set as a user includes not only the person who performs the eating behavior, but also the person who lets others perform the eating behavior and the person who is performed by others. For example, it includes parents who use the system for their children and children whose parents manage their eating behavior.

[0022] Here, the “recipe information” includes information related to the dish itself, such as the name of the dish, ingredients, and recipe, as well as information related to the store that provides the dish and information related to means for obtaining the dish, such as the name of a service that can deliver the dish.

[0023] In addition, here, "learning data" refers to data used to train a machine learning algorithm, such as feature quantities, correct answer data, or a combination thereof used for the training. More specifically, the so-called "learning data" refers to data used to determine parameters of a machine learning algorithm, such as feature quantities, correct answer data, or a combination thereof used to determine the parameters.

[0024] Thus, in the cooking information providing system of the present invention, a plane model or a three-dimensional model, i.e., an emotion model, in which coordinates are defined based on a plurality of basic emotions is used as an interface for inputting the user's emotions, and the coordinates selected in the emotion model are recognized as the user's emotions. Thus, the user can easily and accurately express his or her emotions as values ​​such as coordinates without converting the emotions into language expressions.

[0025] Furthermore, in this system, the coordinates are used as input data. That is, in this system, the coordinates, which are clear parameters, are used instead of the vague parameters of emotions. Thus, in this system, the ambiguity in the input data is eliminated, and accurate recommended dishes can be obtained as output data.

[0026] Therefore, according to the system of the present invention, it is possible to provide the user with cooking information related to appropriate recommended cooking while accurately considering emotions. Furthermore, by eating the recommended cooking, the user can obtain a sense of satisfaction with a high probability.

[0027] Furthermore, in the cooking information providing system of the present invention, it is preferable that:

[0028] The emotion model is a model including a first coordinate axis representing one or more basic emotions and a second coordinate axis representing the strength of the basic emotions.

[0029] When a model using such a coordinate axis is adopted as an emotion model, it is easy for the user to intuitively understand what emotions the coordinates in the emotion model refer to. Furthermore, it is easy for the user to accurately express his or her emotions as coordinates, further eliminating the ambiguity of input data. As a result, it is possible to provide the user with more appropriate recipe information related to recommended dishes based on accurate consideration of emotions.

[0030] It should be noted that, as an emotion model using such a coordinate axis, for example, EmojiGrid, Plutchik's emotion ring, and models generated based on them (for example, a circular model using the color configuration of Plutchik's emotion ring, etc.) can be used. In addition, as the basic emotion, for example, joy, trust, fear, panic, sadness, disgust, anger, and expectation used in Plutchik's emotion ring, and joy, fear, panic, sadness, disgust, and anger in Ekman's theory can be used.

[0031] Furthermore, in the cooking information providing system of the present invention, it is preferable that

[0032] The recommended dish recognition unit recognizes a plurality of the recommended dishes,

[0033] The recipe information providing unit provides the user with the recipe information corresponding to each of the plurality of recommended recipes.

[0034] In this way, when the cooking information related to a plurality of recommended dishes is provided, the user is made to make the final choice of which recommended dish to perform the dietary action on. Thus, when the user actually performs the dietary action on the selected recommended dish, the user will have a sense of identity that the dish that became the subject of the dietary action is based on his / her own choice, and thus it is easy for the user to obtain a sense of satisfaction from the result of the dietary action.

[0035] Furthermore, when the recipe information providing system of the present invention is configured to provide a plurality of recipe information, it is preferable that:

[0036] The recipe information providing system includes a selection status recognition unit for recognizing a selection status for each of the plurality of recommended recipes, the selection status being a state at a time point when the recommended recipe is selected by the user from among the plurality of recommended recipes, i.e., a recipe is selected.

[0037] The recommended dish recognition unit uses the following prediction model as the prediction model: using each candidate dish among the plurality of candidate dishes, the selection coordinates, the user information and the selection status as learning data, the machine learns the correlation between the candidate dishes, the selection coordinates, the user information and the selection status, and outputs the recommended dish selected from the plurality of candidate dishes.

[0038] In this way, the prediction model using the selection status as learning data matches the actual state of the user, where the selection status is the state until the time point when the last selected dish becomes the selected dish. As a result, when the user eats the recommended dish output by the prediction model, the user can obtain satisfaction with a higher probability.

[0039] Here, the "selection status" as the system side status refers to, in addition to the number of selections and display positions described below, the recommended dishes that became the selected dishes before the selected dish was selected, the types of recommended dishes that were prompted at the time when the selected dish was selected, etc. In addition, the "selection status" as the user side status may include the time when the selected dish was selected (and then confirm whether it was breakfast or dinner, etc.), the user's actions before and after the time when the selected dish was selected (for example, the content of the operation on the portable terminal), etc.

[0040] In addition, in the cooking information providing system of the present invention, when a prediction model that uses the condition at the time point when a dish becomes a selected dish, i.e., the selection condition, as learning data is used, it is preferred that the selection condition identification unit identifies at least the number of selections of each of a plurality of the recommended dishes as the selection condition, wherein the number of selections is the number of times the dish becomes the selected dish.

[0041] The fact that a dish is selected can be considered to be a dish that the user directly likes. Therefore, when the number of selections is used as the selection condition, the recommended dish output is likely to be a dish that meets the user's preferences. Furthermore, it is possible to provide the user with dish information related to appropriate recommended dishes.

[0042] Furthermore, in the cooking information providing system of the present invention, in the case of using a configuration of a prediction model using a selection status as learning data, the recommended cooking recognition unit uses the following prediction model as the prediction model: using each candidate cooking dish among the plurality of candidate cooking dishes, the selection coordinates, the user information, and the selection status as learning data, the machine learns a correlation between the candidate cooking dish and the selection coordinates, the user information, and the selection status, and a recommendation degree as the strength of the correlation, and outputs the recommended cooking dish selected from the plurality of candidate cooking dishes and the recommendation degree of the recommended cooking dish,

[0043] The recipe information providing unit provides the recipe information corresponding to each of the plurality of recommended recipes to the user together with a recommendation degree, or provides the recipe information corresponding to a recommended recipe with a higher recommendation degree to the user with priority.

[0044] In this way, if the cooking information corresponding to each of a plurality of recommended dishes is provided to the user together with the recommendation degree, or in a form in which the higher the recommendation degree, the higher the recommendation priority, the user can naturally and easily select the cooking information related to the recommended dish with a high recommendation degree and a high possibility of being satisfied by the user.

[0045] In addition, the cooking information providing system of the present invention is used to provide cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat.

[0046] The cooking information providing system is characterized by comprising:

[0047] A user information recognition unit that recognizes user information, the user information being information including at least one of biological information of the user, hobbies, and environment of the eating behavior;

[0048] a current emotion recognition unit for recognizing a current emotion, the current emotion being the emotion at the time when the user wishes to obtain the cooking information;

[0049] a recommended dish identifying unit that identifies the recommended dish based on correlation data, wherein the correlation data indicates a correlation between the user information and the current emotion and each of a plurality of candidate dishes that may become the recommended dish; and

[0050] a cooking information providing unit that obtains the cooking information from a cooking information identifying unit that identifies a plurality of pieces of information related to the candidate cooking and provides the cooking information to the user,

[0051] The current emotion recognition unit includes an emotion model prompting unit and a coordinate recognition unit, wherein the emotion model prompting unit prompts the emotion model to the user in the form of selecting any coordinate in the emotion model, and the emotion model is a plane model or a three-dimensional model with coordinates specified based on multiple basic emotions; the coordinate recognition unit recognizes the selected coordinates as the current emotion, and the selected coordinates are the coordinates in the emotion model selected by the user.

[0052] Thus, in the cooking information providing system of the present invention, as an interface for inputting the user's emotions, a plane model or a three-dimensional model, i.e., an emotion model, in which coordinates are defined based on a plurality of basic emotions, is used, and the coordinates selected in the emotion model are recognized as the user's emotions. Thus, the user can easily and accurately express his or her emotions as values ​​such as coordinates without converting the emotions into language expressions.

[0053] Furthermore, in this system, the coordinates are used as the current emotion. That is, in this system, the coordinates, which are clear parameters, are used instead of the vague parameters of emotions. Thus, in this system, the ambiguity of the current emotion corresponding to one side of the correlation data is eliminated, so that the recommended dishes corresponding to the other side of the correlation data can be accurately obtained.

[0054] Therefore, according to the system of the present invention, it is possible to provide the user with cooking information related to appropriate recommended dishes in consideration of emotions, and the user can obtain a sense of satisfaction with a high probability by eating the recommended dishes.

[0055] In addition, the cooking information providing method of the present invention is used to provide cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat.

[0056] The method for providing cooking information is characterized by comprising the following steps:

[0057] A step of a user information recognition unit recognizing user information including at least one of biological information of the user, hobbies, and environment of the eating behavior;

[0058] A step of a current emotion recognition unit recognizing a current emotion, the current emotion being the emotion at a time point when the user wishes to obtain the cooking information;

[0059] a step of a recommended dish recognition unit recognizing the recommended dish using a prediction model, the prediction model being a model that receives the user information and the current emotion as input and outputs the recommended dish;

[0060] a step of acquiring the cooking information from a cooking information identification unit and providing the cooking information to the user, the cooking information identification unit identifying a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking,

[0061] In the step of identifying the current emotion, the emotion model prompting unit of the current emotion recognition unit prompts the emotion model to the user in the form of selecting any coordinate in the emotion model, and the coordinate recognition unit of the current emotion recognition unit recognizes the selected coordinate as the current emotion, wherein the emotion model is a plane model or a three-dimensional model with coordinates specified based on multiple basic emotions; the selected coordinates are coordinates in the emotion model selected by the user,

[0062] In the step of identifying the recommended dish, the recommended dish identification unit uses the following prediction model as the prediction model: each candidate dish among the multiple candidate dishes, the selection coordinates and the user information are used as learning data, and the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the multiple candidate dishes and outputs it.

[0063] In addition, the cooking information providing device of the present invention is used to provide cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat.

[0064] The cooking information providing device is characterized by comprising:

[0065] A user information recognition unit that recognizes user information, the user information being information including at least one of biological information of the user, hobbies, and environment of the eating behavior;

[0066] a current emotion recognition unit for recognizing a current emotion, the current emotion being the emotion at the time when the user wishes to obtain the cooking information;

[0067] a recommended dish recognition unit that recognizes the recommended dish using a prediction model, the prediction model being a model that inputs the user information and the current emotion and outputs the recommended dish; and

[0068] a cooking information providing unit that acquires the cooking information from a cooking information identifying unit and provides the cooking information to the user, wherein the cooking information identifying unit identifies a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking,

[0069] The current emotion recognition unit comprises an emotion model prompting unit and a coordinate recognition unit, wherein the emotion model prompting unit prompts the user with an emotion model in the form of selecting any coordinate in the emotion model, wherein the emotion model is a plane model or a three-dimensional model with coordinates specified based on a plurality of basic emotions; and the coordinate recognition unit recognizes the selected coordinates as the current emotion, wherein the selected coordinates are the coordinates in the emotion model selected by the user.

[0070] The recommended dish recognition unit uses the following prediction model as the prediction model: each candidate dish among the plurality of candidate dishes, the selection coordinates, and the user information are used as learning data, so that the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the plurality of candidate dishes and outputs it.

[0071] In addition, the cooking information providing program product of the present invention is used to cause a computer to execute a cooking information providing method, wherein the cooking information providing method is used to provide cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to perform dietary behavior.

[0072] The cooking information providing program product is characterized in that it causes a computer to execute the cooking information providing method having the following steps:

[0073] A step of a user information recognition unit recognizing user information, the user information including at least one of biological information of the user, hobbies, and environment of the eating behavior;

[0074] A step of a current emotion recognition unit recognizing a current emotion, the current emotion being the emotion at a time point when the user wishes to obtain the cooking information;

[0075] a step of a recommended dish recognition unit recognizing the recommended dish using a prediction model, the prediction model being a model that receives the user information and the current emotion as input and outputs the recommended dish;

[0076] a step of acquiring the cooking information from a cooking information identification unit and providing the cooking information to the user, the cooking information identification unit identifying a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking,

[0077] In the step of identifying the current emotion, the emotion model prompting unit of the current emotion recognition unit prompts the emotion model to the user in the form of selecting any coordinate in the emotion model, and the coordinate recognition unit of the current emotion recognition unit recognizes the selected coordinate as the current emotion, wherein the emotion model is a plane model or a three-dimensional model with coordinates specified based on multiple basic emotions; the selected coordinates are coordinates in the emotion model selected by the user,

[0078] In the step of identifying the recommended dish, the recommended dish identification unit uses the following prediction model as the prediction model: each candidate dish among the multiple candidate dishes, the selection coordinates and the user information are used as learning data, and the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the multiple candidate dishes and outputs it.

[0079] Furthermore, the recording medium of the present invention is characterized in that the cooking information providing program product is recorded thereon, and the cooking information providing program product can be read by the computer.

[0080] Brief description of the attached figure

[0081] Figure 1 It is an explanatory diagram showing a schematic configuration of a providing system according to an embodiment.

[0082] Figure 2 Yes means Figure 1 A block diagram of the structure of the processing unit of the providing system.

[0083] Figure 3A It means in Figure 1 A schematic diagram of an example of an emotion model used in a providing system to obtain current emotions.

[0084] Figure 3B This is a schematic diagram showing an example of an emotion model used to acquire current emotions in the providing system according to the first modification.

[0085] Figure 3C This is a schematic diagram showing an example of an emotion model used to acquire current emotions in the providing system according to the second variation.

[0086] Figure 4A Yes means Figure 1 A flowchart of a process performed by the providing system before providing cooking information.

[0087] Figure 4B Yes means Figure 1 Flowchart of the processing performed by the providing system when cooking information is selected.

[0088] Figure 5 Yes means Figure 1 A schematic diagram of an example of an image displayed on a user terminal when the providing system recognizes user information.

[0089] Figure 6 Yes means Figure 1 A schematic diagram of an example of an image displayed on a user terminal when the providing system recognizes the current emotion.

[0090] Figure 7 Yes means Figure 1 A schematic diagram of an example of an image displayed on a user terminal when the providing system provides cooking information.

[0091] Figure 8 Yes means Figure 1 This is a schematic diagram of an example of an image displayed on a user terminal when any of the cooking information is selected by the providing system. DETAILED DESCRIPTION

[0092] Hereinafter, a cooking information providing system (hereinafter referred to as “providing system S”) according to an embodiment and a cooking information providing method implemented using the providing system will be described with reference to the drawings.

[0093] The providing system S in this embodiment is used for a service of extracting a recommended dish from a plurality of candidate dishes as a dish to be recommended to the user U for dietary action in response to a request from the user U, and providing the user U with dish information related to the recommended dish.

[0094] It should be noted that in the following description, "user" refers to the user who provides the system S. Therefore, the person assumed to be the user U includes not only the person who performs the eating behavior, but also the person who lets others perform the eating behavior and the person who is performed by others. For example, it includes parents who use the system for their children and children whose parents manage their eating behavior.

[0095] Here, the “recipe information” includes information related to the recipe itself, such as the recipe name, ingredients, and recipe, as well as information related to the store that provides the recipe and information related to means for obtaining the recipe, such as the name of a service that can deliver the recipe.

[0096] [System overview]

[0097] Below, refer to Figure 1 and Figure 2 The general structure of the providing system S is described.

[0098] like Figure 1 As shown, the providing system S is a computer system for providing cooking information to the user U, and is composed of a server 1 owned by a provider who provides services using the providing system S.

[0099] The server 1 is configured to communicate information with a user terminal 2 such as a smartphone or tablet computer owned by a user U via the Internet, a public line, or the like.

[0100] It should be noted that the recipe information providing system of the present invention is not limited to being composed of one server, and any processing unit described below may be included in any terminal constituting the recipe information providing system.

[0101] Therefore, for example, the entire cooking information providing system may be composed of a plurality of servers. In addition, at least one processing unit or at least a part of the functions of the processing unit may be installed in the user terminal, and the user terminal and the server may cooperate, or the system may be composed of only the user terminal. Furthermore, in the present embodiment, the functions equivalent to the input unit 20 and the output unit 21 provided on the user terminal 2 may be provided on the terminal having the processing unit, thereby forming an independent cooking information providing device.

[0102] In addition, if Figure 2 As shown, the user terminal 2 capable of communicating with the server 1 as the providing system S includes an input unit 20 and an output unit 21 as functions (processing units) realized by at least one of an installed hardware configuration and a program.

[0103] In this embodiment, a touch panel is used as the input unit 20 and the output unit 21 of the user terminal 2. However, the user terminal is not limited to this structure, as long as it can accept information input from the user and can output information to the user. Therefore, in addition to the touch panel, the user terminal can also be configured to use a keyboard, a microphone, a camera, a speaker, etc. for input and output.

[0104] [Structure of each processing unit]

[0105] like Figure 2 As shown, the server 1 includes a user information recognition unit 10, a user information storage unit 11, a current emotion recognition unit 12, a recommended dish recognition unit 13, a dish information storage unit 14 (dish information recognition unit), a dish information providing unit 15 and a selection status recognition unit 16 as functions (processing units) implemented by at least one of the installed hardware configuration and programs.

[0106] The user information recognition section 10 recognizes information including at least one of biological information, preferences, and environment of eating behavior of the user U as user information.

[0107] The "biological information" here refers to information related to the user's body that may affect eating behavior. Examples of physical information include the user's gender, age, height, and weight. In addition, the "hobbies" here include not only user hobbies related to cooking or ingredients themselves, but also user hobbies that may affect eating behavior. For example, it also includes whether or not you like summer (and therefore the state of appetite caused by the temperature).

[0108] In addition, the "eating environment" here includes, for example, the number of users performing eating behaviors, the relationship between the users and the people performing eating behaviors together, the scheduled time of eating behaviors, the place where eating behaviors are performed, the type of eating behaviors (eating by oneself or letting others eat, cooking by oneself or dining out, etc.), etc.

[0109] In the providing system S, the user information identification unit 10 first presents a predetermined questionnaire (see Figure 5 ). Then, the user information identification unit 10 refers to the user's answer to the questionnaire and the information stored in the user information storage unit 11 to identify the user information related to the user U who receives the service of the provision system S this time.

[0110] Furthermore, when the recognized user information is different from the user information stored in the user information storage unit 11 , the user information recognition unit 10 stores the new user information in the user information storage unit 11 .

[0111] The user information storage unit 11 stores user information corresponding to each user U. The user information storage unit 11 first stores the user information acquired during the registration procedure for the user U to receive the service provided by the provision system S as initial information. Thereafter, when the user information recognition unit 10 recognizes new user information, information obtained by adding or changing the initial information based on the new user information is stored.

[0112] It should be noted that, in a case where a registration procedure for receiving a service has not been performed, when the user information recognition unit 10 recognizes the user information for the first time, the user information may be stored as initial information.

[0113] Furthermore, when the selection status recognition unit 16 recognizes a selection status described later, the user information storage unit 11 stores the selection status of each user U or the selection status of each group having the same or corresponding user information as the user U. The corresponding user information refers to user information having a part of the same or similar user information.

[0114] The current emotion recognition unit 12 recognizes the current emotion of the user U when he / she wants to receive the service provided by the provision system S (ie, when he / she wants to obtain cooking information). The current emotion recognition unit 12 includes an emotion model presenting unit 12a and a coordinate recognition unit 12b.

[0115] The emotion model presenting unit 12 a presents the emotion model to the user U via the user terminal 2 by allowing the user U to select an emotion model that is a plane model whose coordinates are defined based on a plurality of basic emotions in a manner that allows the user U to select one of the coordinates of the emotion model.

[0116] Here, as "basic emotions", for example, joy / trust / fear / horror / sadness / disgust / anger / expectation adopted in Plutchik's emotion cycle, joy / fear / horror / sadness / disgust / anger in Ekman's theory, etc. can be adopted.

[0117] In the providing system S, a model including a first coordinate axis representing a plurality of basic emotions and a second coordinate axis representing the strength of the basic emotions is used as the emotion model. Figure 3A EmojiGrid shown (refer to Figure 6 ) as an emotion model.

[0118] In the EmojiGrid, images of faces expressing certain emotions are arranged at predetermined intervals in the peripheral part to define a first coordinate axis representing basic emotions. In addition, in the EmojiGrid, an image of a face expressing a state without a specific emotion is arranged at the center position constituting an origin, and the distance from the origin to each image expressing a certain emotion arranged in the peripheral part is defined as a second coordinate axis representing the strength of the emotion corresponding to each image.

[0119] It should be noted that the emotion model in the present invention is not limited to such an EmojiGrid, and any model may be a plane model or a three-dimensional model whose coordinates are specified based on a plurality of basic emotions.

[0120] So, for example, Figure 3B As in the first variant shown in FIG. 1 , the Platschek emotion ring may be used as the emotion model. Furthermore, a model using the color arrangement of the Platschek emotion ring, that is, a model without text, may be used. Conversely, a model using the text arrangement of the Platschek emotion ring, that is, a model without color, may be used.

[0121] In addition, for example, Figure 3C As shown in the second variant, facial expression quantity can also be used as an emotion model. Figure 3CIn the example shown, an example is shown in which only one type of facial expression amount is used to construct the emotion model, but an example in which a plurality of types of facial expression amounts are arranged to construct the emotion model is also possible.

[0122] In the present embodiment, the first modification, and the second modification, a case where a planar model is used as the emotion model is described. However, the emotion model of the present invention is not limited to such a configuration, and a three-dimensional model may be used.

[0123] The coordinate recognition unit 12b recognizes the coordinates in the emotion model selected by the user U via the input unit 20 of the user terminal 2, i.e., the selected coordinates. In the providing system S, the coordinate recognition unit 12b recognizes the coordinates specified by the user U touching in the emotion model displayed on the touch panel of the input unit 20 and the output unit 21 of the user terminal 2 as the selected coordinates.

[0124] It should be noted that in Figure 3C When the facial expression amount is used as in the second modified example shown, it is also possible to set only the image (button icon) of the face constituting the facial expression amount to be selectable, and the coordinates of the selected facial expression amount are recognized as the selected coordinates. In addition, it is also possible to set any coordinates within the range of the facial expression amount to be selectable.

[0125] Then, the coordinate recognition unit 12b recognizes the recognized selection coordinates themselves as the current emotion. Therefore, the coordinate recognition unit 12b does not particularly determine what emotion the emotion based on the coordinates is.

[0126] The recommended dish identification unit 13 identifies a plurality of recommended dishes and the recommendation degrees of the recommended dishes using a predetermined prediction model.

[0127] The prediction model used by the recommended dish recognition unit 13 uses each of the plurality of candidate dishes, the selection coordinates recognized by the current emotion recognition unit 12, the user information recognized by the user information recognition unit 10, and the selection status described later as learning data to machine-learn the correlation between the candidate dishes and their selection coordinates and the user information, and the recommendation degree as the strength of the correlation. When the user information recognized by the user information recognition unit 10 and the current emotion recognized by the current emotion recognition unit 12 are input to the prediction model, the recommended dish and the recommendation degree of the recommended dish are output.

[0128] Here, the “candidate dish” refers to a dish used in the prediction model, and is a dish that may become a recommended dish.

[0129] In addition, here, "learning data" refers to data used to train a machine learning algorithm, such as feature quantities, correct answer data, or a combination thereof used for the training. More specifically, the so-called "learning data" refers to data used to determine parameters of a machine learning algorithm, such as feature quantities, correct answer data, or a combination thereof used to determine the parameters.

[0130] Furthermore, after the selection condition recognition unit 16 recognizes the selection condition described later, each time the selection condition is recognized or when the selection condition is recognized a prescribed number of times, the prediction model uses the past selection conditions as learning data to machine learn the correlation between the candidate dish, its selection coordinates and the user information, and the degree of recommendation as the strength of the correlation, in addition to each candidate dish among the plurality of candidate dishes, its selection coordinates and the user information.

[0131] It should be noted that as the past selection status, it is not necessary to use all the selection statuses so far, and the selection status at a predetermined timing (for example, the most recent predetermined number of times, within a predetermined period, etc.) may be used.

[0132] The cooking information storage unit 14 stores a plurality of information related to candidate cooking. The types of information correspond to the aforementioned cooking information. Specifically, the stored information includes information related to the cooking itself, such as the name of the cooking, ingredients, and recipes, as well as information related to the store that provides the cooking and the name of the service that can deliver the cooking, which is related to the means for obtaining the cooking.

[0133] It should be noted that, in the providing system S, the recipe information storage unit 14 as a recipe information recognition unit constitutes a part of the providing system S. However, the recipe information recognition unit according to the present invention is not limited to this configuration, and may recognize a variety of information related to the candidate recipes.

[0134] Therefore, for example, the recipe information recognition unit may be a recognition unit provided in another independent system different from the recipe information providing system. Also, as the recipe information recognition unit, a processing unit that searches for information on the Internet and collects and recognizes a plurality of recipe information may be used instead of a database storing the recipe information.

[0135] The recipe information providing unit 15 acquires information about each of the plurality of recommended recipes identified by the recommended recipe identifying unit 13 from the recipe information storage unit 14 as recipe information to be presented to the user U. Then, the recipe information providing unit 15 provides the user U with the recipe information corresponding to each of the plurality of recommended recipes acquired via the output unit 21 of the user terminal 2 in a selectable form.

[0136] At this time, the recipe information providing unit 15 identifies the recommendation degree identified by the recommended recipe identifying unit 13 for each of the plurality of recommended recipes, and provides recipe information based on the recommendation degree. Specifically, in the providing system S, recipe information of a recommended recipe with a higher recommendation degree is displayed on the screen with higher priority (e.g., at the top) (see Figure 7 ).

[0137] In addition, the cooking information providing unit 15 can change the way of providing cooking information according to the current user information of the user U identified by the user information identifying unit 10. For example, when the user information includes information about self-cooking, the cooking information providing unit 15 provides the recipe of the cooking as the cooking information. On the other hand, when the user information includes information about dining out, the cooking information providing unit 15 does not provide the recipe of the cooking but provides the restaurant of the cooking as the cooking information.

[0138] When the user U selects a certain dish among the plurality of dish information provided by the dish information providing unit 15 via the input unit 20 of the user terminal 2, the selection status recognition unit 16 first recognizes the recommended dish corresponding to the dish information as the selected dish. In addition, the selection status recognition unit 16 recognizes the time point at which the selected dish is recognized (i.e., the time point at which a certain recommended dish becomes the selected dish) as the selection status.

[0139] Here, the "selection status" as a system status includes, in addition to the number of selections and display positions of the number of times a dish is selected, recommended dishes that become selected dishes before the selected dish is selected, and the types of recommended dishes that are displayed at the time when the selected dish is selected.

[0140] In addition, as the "selection status" of the user side, the time of selecting the selected dish (and then confirming whether it is breakfast or dinner, etc.), the user's actions before and after the time of selecting the selected dish (for example, the content of the operation on the portable terminal), etc. In addition, the content of the operation on the portable terminal includes not only the operation performed by the user consciously on the terminal (for example, the operation on the touch panel, etc.), but also the operation performed by the user unconsciously (for example, the reading time of the dish information, etc.).

[0141] Furthermore, the selection status recognition unit 16 stores, for each user U or for each group having the same or corresponding user information as the user U, the recognized selection status of each of the plurality of recommended dishes in the user information storage unit 11 .

[0142] [Processing performed by each processing unit]

[0143] Next, refer to Figure 2 and Figures 5 to 8 , a method for providing cooking information, which is a process performed by the providing system S, will be described.

[0144] In this process, first, the user information identification unit 10 presents a questionnaire ( ) for confirming the current user information to the user U in an answerable form via the user terminal 2. Figure 4A / Step (STEP)01).

[0145] Specifically, when the service is used for the first time by the provision system S, a questionnaire asking for information for identifying the user U (for example, a separately registered account name) is first presented in an answerable form.

[0146] If the user answers the questionnaire or uses it for the second time or later, Figure 5 As shown, a questionnaire asking the user U's age (biological information), number of cohabitants, whether he cooks at home or eats out (eating environment), and favorite ingredients (preferences) is presented in an answerable form.

[0147] Next, when answering the questionnaire, the user information identification unit 10 identifies the user information of the current user U based on the answer to the questionnaire and the known user information ( Figure 4A / Step (STEP) 02).

[0148] Next, the user information identification unit 10 determines whether the current user information is different from the known user information ( Figure 4A / Step (STEP) 03).

[0149] When the current user information is different from the known user information (if YES in step 03), the user information recognition unit 10 updates the user information by storing the current user information in the user information storage unit 11. Figure 4A / Step (STEP) 04).

[0150] Specifically, at the time of first use, the user information recognition unit 10 recognizes the current user information of the user U based on the information separately obtained during account registration and the answers to the current questionnaire. At this time, the user information has not yet been saved, and the current user information is of course different from the known user information, so the user information recognition unit 10 directly saves the current user information as the user information of the user U in the user information storage unit 11.

[0151] In addition, at the second and subsequent times of use, the user information recognition unit 10 first compares the current user information of the recognized user U with the previous user information of the user U obtained from the user information storage unit 11. Furthermore, when there are differences between these user information, the user information recognition unit 10 creates new user information using the current user information for the different parts, and stores the new user information as the user information of the user U in the user information storage unit 11.

[0152] When the current user information is the same as the known user information (in the case of No (N0) in step 03) or when the user information is newly stored in the user information storage unit 11 (in the case of executing step 04), the current emotion recognition unit 12 prompts the user U via the user terminal 2 with the coordinates of the emotion model being selectable ( Figure 4A / Step (STEP) 05).

[0153] Specifically, if Figure 6 As shown, the current emotion recognition unit 12 displays an emotion model (EmojiGrid) on the touch panel of the user terminal 2. Then, when the user touches any point of the emotion model, the current emotion recognition unit 12 determines that the coordinates of the point are selected.

[0154] Next, the current emotion recognition unit 12 determines whether a certain coordinate in the emotion model is selected ( Figure 4A / Step (STEP) 06).

[0155] When any coordinate is not selected (in the case of No (N0) in step 06), the current emotion recognition unit 12 repeats the determination in step 06 at a predetermined control cycle.

[0156] On the other hand, when any coordinate is selected (in the case of YES in step 06), the current emotion recognition unit 12 recognizes the coordinate as the selected coordinate, and recognizes the selected coordinate as the current emotion ( Figure 4A / Step (STEP) 07).

[0157] Next, the recommended dish recognition unit 13 inputs the current user information and current emotions into the prediction model, and outputs a plurality of recommended dishes for the user U and the recommendation degree of each of the plurality of recommended dishes ( Figure 4A / Step (STEP) 08).

[0158] Next, the recipe information providing unit 15 obtains recipe information ( Figure 4A / Step (STEP) 09).

[0159] Next, the recipe information providing unit 15 provides the user U with a recipe name ( ) as one of the acquired recipe information in a selectable form in the order of recommendation degree of the recommended recipe corresponding to the recipe information via the user terminal 2. Figure 4A / Step (STEP) 10).

[0160] Specifically, if Figure 7 As shown, the recipe information providing unit 15 provides recipe information by displaying recipe names in a vertical arrangement on the touch panel of the user terminal 2. At this time, the higher the recommendation degree of the corresponding recommended recipe, the higher the recipe names are ranked in the ranking of these recipe names. Then, when the user touches any of these recipe names, the recipe information providing unit 15 determines that the recommended recipe corresponding to the recipe name is selected.

[0161] Next, the cooking information providing unit 15 determines whether any cooking name ( Figure 4B / Step (STEP) 11).

[0162] When any dish name is not selected (in the case of No (N0) in step 11), the dish information providing unit 15 repeats the determination in step 11 at a predetermined control cycle.

[0163] On the other hand, when any dish name is selected (if the answer is YES in step 11), the dish information providing unit 15 provides the user U with details of the dish information of the recommended dish corresponding to the selected dish name via the user terminal 2 ( Figure 4B / Step (STEP) 12).

[0164] Specifically, if Figure 8 As shown, for example, when the user information includes information related to eating behavior and self-cooking, the cooking information providing unit 15 displays a recipe of a recommended cooking corresponding to the selected cooking name on the touch panel of the user terminal 2. In addition, when the user information includes information related to dining out, the cooking information providing unit 15 displays a store or service that provides the recommended cooking corresponding to the selected cooking name on the touch panel.

[0165] Next, the selection status recognition unit 16 determines whether the selected recipe information is adopted (that is, whether it has become a selected recipe) ( Figure 4B / Step (STEP) 13).

[0166] Specifically, when the recipe information providing unit 15 displays a recipe of a dish on the touch panel of the user terminal 2, the selection status recognition unit 16 displays an adoption button together with the recipe. When the adoption button is selected, it is determined that the recommended dish corresponding to the recipe (i.e., the recipe information) is adopted together with the adoption button and becomes the selected dish.

[0167] When the selected recipe information is not adopted (in the case of No (N0) in step 13), the process returns to step 11, and the providing system S executes the processes of steps 11 to 13 again.

[0168] On the other hand, when the selected recipe information is adopted (if YES in step 13), the selection status recognition unit 16 recognizes the selection status ( Figure 4B / Step (STEP) 14).

[0169] Specifically, the selection status recognition unit 16 extracts and recognizes the selection status based on information input or output to the user terminal 2, information about the current user U in the user information stored in the user information storage unit 11, and time acquired from a clock of the providing system S.

[0170] As selection conditions, for example, the number of times a dish has been selected, i.e., the number of selections, the display position, the recommended dishes that were selected before the current dish selected by user U, the types of recommended dishes that are prompted when the current dish is selected, the time of selection (and then confirming whether it is breakfast or dinner, etc.), etc.

[0171] Next, the selection status recognition unit 16 stores the selection status of the selected dish in the user information storage unit 11 for each user U or for each group having the same or corresponding user information as the user U ( Figure 4B / Step (STEP) 15).

[0172] Next, the recommended dish recognition unit 13 adds the currently recognized selection status to the prediction model, and uses the past selection status as learning data in addition to the selected dish (i.e., the corresponding candidate dish), the selection coordinates, and the user information, and performs machine learning on the correlation between the candidate dish, the selection coordinates, the user information, and the selection status, and the recommendation degree as the degree of the correlation ( Figure 4B / Step (STEP) 16), end this processing.

[0173] It should be noted that the recommended dish recognition unit 13 may not execute machine learning with the selection status added every time a selection status is recognized, but may execute machine learning after a certain number of selection statuses have been collected.

[0174] As described above, in the cooking information providing method executed by using the providing system S, a plane model that defines coordinates based on a plurality of basic emotions, i.e., an emotion model, is used as an interface for inputting the emotions of the user S, and the coordinates selected in the emotion model are recognized as the emotions of the user U. Thus, the user U can easily and accurately express his or her emotions as values ​​such as coordinates without converting them into expressions in words.

[0175] Then, in the providing system S, the coordinates are used as input data. That is, in the system, the coordinates, which are clear parameters, are used instead of the vague parameters, which are emotions. Thus, in the system, the ambiguity is eliminated from the input data, and thus accurate recommended dishes can be obtained as output data.

[0176] Therefore, according to the providing system S, it is possible to provide the user U with cooking information related to appropriate recommended cooking while accurately considering emotions. Furthermore, the user U can obtain a sense of satisfaction with a high probability by eating the recommended cooking.

[0177] [Variation of the provision system]

[0178] In addition, in this embodiment, a model including a first coordinate axis representing one or more basic emotions and a second coordinate axis representing the strength of the basic emotions is used as the emotion model.

[0179] When a model using such a coordinate axis is adopted as an emotion model, it is easy for the user U to intuitively understand what emotions the coordinates in the emotion model refer to. Furthermore, it is easy for the user U to accurately express his or her emotions using the coordinates, and it is possible to further eliminate ambiguity in the input data. As a result, it is possible to provide the user U with more appropriate recipe information related to recommended dishes based on accurate consideration of emotions.

[0180] However, the emotion model of the present invention is not limited to such a configuration, and any plane model or three-dimensional model in which coordinates are specified based on a plurality of basic emotions may be used. Therefore, for example, an emotion model that does not include a coordinate axis may also be used. Specifically, a model in which a plurality of colors are simply arranged at specified positions may also be used as an emotion model.

[0181] In the present embodiment, the recommended recipe recognition unit 13 recognizes a plurality of recipe information, and the recipe information providing unit 15 provides the user U with recipe information corresponding to each of the plurality of recommended recipes.

[0182] In this way, when dish information related to a plurality of recommended dishes is provided, the final choice of which recommended dish to perform dietary action depends on the user U. Therefore, when actually performing dietary action on the selected recommended dish, the user U is given a sense of identity that the dish that is the subject of the dietary action is a dish based on his / her own choice, and thus is likely to obtain a sense of satisfaction with the result of the dietary action.

[0183] However, the recipe information providing system of the present invention is not limited to this configuration, and the recommended recipe identification unit may be configured to identify only one recommended recipe, and the recipe information providing unit may be configured to provide recipe information of only one recommended recipe among a plurality of recommended recipes.

[0184] In the present embodiment, when recipe information is selected, the selection situation recognition unit 16 recognizes the selection situation, and the recommended recipe recognition unit 13 performs machine learning of the prediction model using the selection situation.

[0185] In this way, regarding the selected dish obtained last time, the state at the time of selecting the dish, that is, the selection status, adopts the prediction model as learning data to match the actual state of the user U. As a result, when the user U eats the recommended dish output from the prediction model, he or she can obtain satisfaction with a higher probability.

[0186] However, the prediction model of the present invention is not limited to such a structure, and the prediction model only needs to have the following structure: taking each candidate dish, selection coordinates and user information of a plurality of candidate dishes as learning data, performing machine learning on the correlation between the candidate dish, the selection coordinates and the user information, inputting user information and current emotions, selecting a recommended dish from the plurality of the aforementioned candidate dishes and outputting it.

[0187] Therefore, for example, instead of performing machine learning to identify the selection status and use the prediction model of the selection status, the prediction model introduced when the system is built may be configured to be used directly without performing machine learning thereafter.

[0188] In addition, in the present embodiment, the number of selections is used as the selection condition. This is because the fact that a dish is selected can be considered to directly indicate to the user U that the dish is likely to be liked. Therefore, if the number of selections is used as the selection condition, the recommended dish output is likely to be a recommended dish that meets the taste of the user U. Furthermore, it is possible to provide the user with dish information related to appropriate recommended dishes.

[0189] However, the selection status of the present invention is not limited to this configuration, and the selection status may be any status as long as the user selects a recommended dish for which dish information is provided and the dish is selected. Therefore, for example, the selection status may not include the number of selections.

[0190] In the present embodiment, the prediction model of the recommended recipe recognition unit 13 outputs a plurality of recommended recipes and the recommendation degree of each of the plurality of recommended recipes, and the recipe information provision unit 15 changes the recipe information provision method based on the recommendation degree.

[0191] In this way, if the cooking information corresponding to multiple recommended dishes is presented to user U together with the recommendation degree, or is presented to user U in a form in which the recommended dishes with higher recommendation degrees are presented with higher priority, user U can naturally and easily select the cooking information related to the recommended dishes with high recommendation degrees and high possibility of being satisfied by him / her.

[0192] However, the cooking information providing unit of the present invention is not limited to such a configuration, and the cooking information providing unit can be used as long as it can provide cooking information to the user. Therefore, for example, the display order of cooking information can be changed using criteria other than the recommendation degree (for example, the order of the 50-sounding alphabets, the order of the total price of ingredients, etc.). In addition, the display size on the display screen can be larger as the priority increases. In addition, the value of the recommendation degree itself can also be displayed together with the cooking information.

[0193] [Other embodiments]

[0194] As mentioned above, although the embodiment shown in figure was demonstrated, this invention is not limited to this form.

[0195] For example, in the above-mentioned embodiment, the recommended dish identification unit 13 uses a predetermined prediction model to identify the recommended dish. However, the recommended dish identification unit of the present invention is not limited to this configuration. Therefore, the prediction model may be replaced by a method of identifying the recommended dish based on correlation data indicating the correlation between the user information and the current mood and each of the plurality of candidate dishes that can become the recommended dish.

[0196] In addition, in the above embodiment, the case where the providing system S is a computer system is described. However, the present invention also includes a cooking information providing program product for causing any one or more computers to execute the above cooking information providing method, and a computer-readable recording medium that records the program product and allows users to use the program product.

[0197] Explanation of symbols

[0198] 1…server, 2…user terminal, 10…user information identification unit, 11…user information storage unit, 12…current emotion identification unit, 12a…emotion model prompting unit, 12b…coordinate identification unit, 13…recommended food identification unit, 14…food information storage unit (food information identification unit), 15…food information providing unit, 16…selection status identification unit, 20…input unit, 21..·output unit, S…providing system (food information providing system), U..·user.

Claims

1. A cooking information providing system for providing cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat. The cooking information providing system is characterized by comprising: A user information recognition unit that recognizes user information, the user information being information including at least one of biological information of the user, hobbies, and environment of the eating behavior; a current emotion recognition unit for recognizing a current emotion, the current emotion being the emotion at the time when the user wishes to obtain the cooking information; a recommended dish recognition unit that recognizes the recommended dish using a prediction model, the prediction model being a model that inputs the user information and the current emotion and outputs the recommended dish; and a cooking information providing unit that acquires the cooking information from a cooking information identifying unit and provides the cooking information to the user, wherein the cooking information identifying unit identifies a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking, The current emotion recognition unit comprises an emotion model prompting unit and a coordinate recognition unit, wherein: The emotion model prompting unit prompts the emotion model to the user in a form in which any coordinate in the emotion model can be selected, wherein the emotion model is a plane model or a three-dimensional model whose coordinates are specified based on a plurality of basic emotions; the coordinate recognition unit recognizes the selected coordinates as the current emotion, wherein the selected coordinates are the coordinates in the emotion model selected by the user, The recommended dish recognition unit uses the following prediction model as the prediction model: each candidate dish among the plurality of candidate dishes, the selection coordinates, and the user information are used as learning data, so that the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the plurality of candidate dishes and outputs it.

2. The cooking information providing system according to claim 1, characterized in that: The emotion model is a model including a first coordinate axis representing one or more basic emotions and a second coordinate axis representing the strength of the basic emotions.

3. The cooking information providing system according to claim 1 or 2, characterized in that: The recommended dish recognition unit recognizes a plurality of the recommended dishes, The recipe information providing unit provides the user with the recipe information corresponding to each of the plurality of recommended recipes.

4. The cooking information providing system according to claim 3, characterized in that: The recipe information providing system includes a selection status recognition unit configured to recognize a selection status for each of the plurality of recommended recipes, the selection status being a status at a time point when the recommended recipe is selected by the user from among the plurality of recommended recipes, The recommended dish recognition unit uses the following prediction model as the prediction model: using each candidate dish among the plurality of candidate dishes, the selection coordinates, the user information and the selection status as learning data, the machine learns the correlation between the candidate dishes, the selection coordinates, the user information and the selection status, and outputs the recommended dish selected from the plurality of candidate dishes.

5. The cooking information providing system according to claim 4, characterized in that: The selection status recognition unit recognizes at least a selection count of each of the plurality of recommended dishes as the selection status, wherein the selection count is a number of times the dish is selected.

6. The cooking information providing system according to claim 4 or 5, characterized in that: The recommended dish recognition unit uses the following prediction model as the prediction model: using each candidate dish among the plurality of candidate dishes, the selection coordinates, the user information, and the selection status as learning data, the machine learns the correlation between the candidate dish and the selection coordinates, the user information, and the selection status, and the recommendation degree as the strength of the correlation, and outputs the recommended dish selected from the plurality of candidate dishes and the recommendation degree of the recommended dish, The recipe information providing unit provides the recipe information corresponding to each of the plurality of recommended recipes to the user together with the recommendation degree, or provides the recipe information corresponding to the recommended recipe with a higher recommendation degree to the user with higher priority.

7. A cooking information providing system for providing cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat. The cooking information providing system is characterized by comprising: A user information recognition unit that recognizes user information, the user information being information including at least one of biological information of the user, hobbies, and environment of the eating behavior; a current emotion recognition unit for recognizing a current emotion, the current emotion being the emotion at the time when the user wishes to obtain the cooking information; a recommended dish identifying unit that identifies the recommended dish based on correlation data, wherein the correlation data indicates a correlation between the user information and the current emotion and each of a plurality of candidate dishes that can become the recommended dish; and a cooking information providing unit that obtains the cooking information from a cooking information identifying unit that identifies a plurality of pieces of information related to the candidate cooking and provides the cooking information to the user, The current emotion recognition unit includes an emotion model prompting unit and a coordinate recognition unit, wherein the emotion model prompting unit prompts the emotion model to the user in the form of selecting any coordinate in the emotion model, and the emotion model is a plane model or a three-dimensional model with coordinates specified based on multiple basic emotions; the coordinate recognition unit recognizes the selected coordinates as the current emotion, and the selected coordinates are the coordinates in the emotion model selected by the user.

8. A method for providing cooking information, for providing cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat. The method for providing cooking information is characterized by comprising the following steps: A step of a user information recognition unit recognizing user information including at least one of biological information of the user, hobbies, and environment of the eating behavior; A step of a current emotion recognition unit recognizing a current emotion, the current emotion being the emotion at a time point when the user wishes to obtain the cooking information; a step of a recommended dish recognition unit recognizing the recommended dish using a prediction model, the prediction model being a model that receives the user information and the current emotion as input and outputs the recommended dish; a step of acquiring the cooking information from a cooking information identification unit and providing the cooking information to the user, the cooking information identification unit identifying a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking, In the step of identifying the current emotion, the emotion model prompting unit of the current emotion recognition unit prompts the user with an emotion model in the form of selecting any coordinate in the emotion model, and the coordinate recognition unit of the current emotion recognition unit recognizes the selected coordinate as the current emotion, wherein: The emotion model is a plane model or a three-dimensional model that specifies coordinates based on a plurality of basic emotions; the selected coordinates are coordinates in the emotion model selected by the user, In the step of identifying the recommended dish, the recommended dish identification unit uses the following prediction model as the prediction model: each candidate dish among the multiple candidate dishes, the selection coordinates and the user information are used as learning data, and the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the multiple candidate dishes and outputs it.

9. A cooking information providing device, for providing cooking information to a user, wherein the cooking information is information related to recommended cooking, and the recommended cooking is cooking recommended for the user to eat. The cooking information providing device is characterized by comprising: A user information recognition unit that recognizes user information, the user information being information including at least one of biological information of the user, hobbies, and environment of the eating behavior; a current emotion recognition unit for recognizing a current emotion, the current emotion being the emotion at the time when the user wishes to obtain the cooking information; a recommended dish recognition unit that recognizes the recommended dish using a prediction model, the prediction model being a model that inputs the user information and the current emotion and outputs the recommended dish; and a cooking information providing unit that acquires the cooking information from a cooking information identifying unit and provides the cooking information to the user, wherein the cooking information identifying unit identifies a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking, The current emotion recognition unit comprises an emotion model prompting unit and a coordinate recognition unit, wherein: The emotion model prompting unit prompts the emotion model to the user in a form in which any coordinate in the emotion model can be selected, wherein the emotion model is a plane model or a three-dimensional model whose coordinates are specified based on a plurality of basic emotions; the coordinate recognition unit recognizes the selected coordinates as the current emotion, wherein the selected coordinates are the coordinates in the emotion model selected by the user, The recommended dish recognition unit uses the following prediction model as the prediction model: each candidate dish among the plurality of candidate dishes, the selection coordinates, and the user information are used as learning data, so that the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the plurality of candidate dishes and outputs it.

10. A cooking information providing program product, configured to cause a computer to execute a cooking information providing method, the cooking information providing method being configured to provide cooking information to a user, the cooking information being information related to a recommended cooking, the recommended cooking being a cooking recommended for the user to perform an eating behavior, The cooking information providing program product is characterized in that it causes a computer to execute the cooking information providing method having the following steps: A step of a user information recognition unit recognizing user information including at least one of biological information of the user, hobbies, and environment of the eating behavior; A step of a current emotion recognition unit recognizing a current emotion, the current emotion being the emotion at a time point when the user wishes to obtain the cooking information; a step of a recommended dish recognition unit recognizing the recommended dish using a prediction model, the prediction model being a model that receives the user information and the current emotion as input and outputs the recommended dish; a step of acquiring the cooking information from a cooking information identification unit and providing the cooking information to the user, the cooking information identification unit identifying a plurality of information related to a candidate cooking, the candidate cooking being a cooking used in the prediction model and being a cooking that can become the recommended cooking, In the step of identifying the current emotion, the emotion model prompting unit of the current emotion recognition unit prompts the user with an emotion model in the form of selecting any coordinate in the emotion model, and the coordinate recognition unit of the current emotion recognition unit recognizes the selected coordinate as the current emotion, wherein: The emotion model is a plane model or a three-dimensional model that specifies coordinates based on a plurality of basic emotions; the selected coordinates are coordinates in the emotion model selected by the user, In the step of identifying the recommended dish, the recommended dish identification unit uses the following prediction model as the prediction model: each candidate dish among the multiple candidate dishes, the selection coordinates and the user information are used as learning data, and the prediction model performs machine learning on the correlation between the candidate dish and the selection coordinates and the user information, and selects the recommended dish from the multiple candidate dishes and outputs it.

11. A recording medium, characterized in that: The cooking information providing program product according to claim 10 is recorded, and the computer is capable of reading the cooking information providing program product.