Prediction apparatus and prediction method

The prediction device uses AI to analyze user attributes and desires to accurately predict health consciousness and behavior, improving personalized health suggestions and product recommendations.

JP2024169317APending Publication Date: 2024-12-05DENTSU INC +1
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024067242
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-24
Filing Date
2024-04-18
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Existing technologies fail to accurately predict a user's health consciousness and behavior based on their attributes, personal desires, and social desires.

Method used

A prediction device and method using trained artificial intelligence to analyze user attribute information, personal desires, interpersonal desires, and social desires, utilizing a questionnaire-based approach to determine health consciousness and behavior.

Benefits of technology

Enhances the accuracy of predicting user health consciousness and behavior, enabling personalized health suggestions and product recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024169317000001_ABST
    Figure 2024169317000001_ABST
Patent Text Reader

Abstract

To make a proposal more appropriate for a user.SOLUTION: A prediction apparatus includes prediction means which predicts the amount that a user accepts to use for their health, health consciousness of the user, and health action of the user, using a trained artificial intelligence, on the basis of attribute information of the user and information on personality / concept of values of the user. The attribute information of the user includes at least sexuality, age and income. The information on personality / concept of values of the user includes at least whether the user has a desire for goods of special value and whether the user desires to collect goods.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a prediction device and a prediction method. [Background technology]

[0002] Patent Document 1 discloses a technology for generating a meal menu to be suggested to a user based on at least one of the user's attributes, symptoms the user has, and the user's physical goals, as well as a meal record and an exercise record. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2022-71655 [Non-Patent Document 2] https: / / www.dentsu.co.jp / news / release / pdf-cms / 2009053-0901.pdf Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present invention is to predict a user's health consciousness. [Means for solving the problem]

[0005] According to one aspect of the present invention, [1] A prediction device is provided that includes a prediction means for predicting at least one of a user's health consciousness and health behavior (behavioral preferences) using trained artificial intelligence based on a user's attribute information, first information related to the user's personal needs, second information related to the user's interpersonal needs, and third information related to the user's social needs.

[0006] [2] In the prediction device according to [1], The first information, the second information and the third information may be based on answers to questions posed to the user.

[0007] [3] [2] The prediction device according to the present invention, each of the first information, the second information, and the third information includes a plurality of evaluation axes; The question may be linked to any one of the plurality of evaluation axes.

[0008] [4] [1] to [3], wherein the prediction device comprises: At least one of the user's health consciousness and health behavior may include health behavior related to diet.

[0009] According to another aspect of the present invention, [5] A prediction method is provided, which includes a step of predicting at least one of a user's health consciousness and health behavior using trained artificial intelligence based on a user's attribute information, first information regarding the user's personal needs, second information regarding the user's interpersonal needs, and third information regarding the user's social needs.

[0010] [6] [5] The prediction method according to the present invention, The method may include a step of grasping the first information, the second information, and the third information by asking the user a question.

[0011] [7] A prediction means for predicting an amount of money that the user is willing to spend on health, the health consciousness of the user, and the health behavior of the user, based on attribute information of the user and information about the user's personality and values, using a trained artificial intelligence; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want something with special value or not, and whether or not the person wants to collect things.

[0012] [8] A prediction means for predicting an amount of money that the user is willing to spend on health, the health consciousness of the user, and the health behavior of the user, based on attribute information of the user and information about the user's personality and values, using a trained artificial intelligence; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want to be healed or not, Whether you want to relieve stress or not, Whether you want to build good relationships or not, Whether you want to share your feelings or not Whether you want to learn or not, Whether you want to explore or not, Whether you want to experience something brand new or not, Whether you want to give love or not, Whether you want to look after them or not, Whether or not you want to protect society and the community, and whether or not you want to do the right thing.

[0013] [9] The information about the user's personality and values ​​is further Whether you want something with special value or not, and whether or not the user wants to collect the item.

[0014]

[10] The user attribute information further includes Place of residence, Single or married? Whether or not you have children Occupation and A prediction device described in any one of [7] to [9], including family members living together.

[0015]

[11] A prediction device described in any of [7] to [9], wherein the amount that the user is willing to spend on health includes an amount that the user is willing to spend on health products and an amount that the user is willing to spend on health services.

[0016]

[12] The prediction means includes a step of predicting, based on the attribute information of the user and information related to the personality and values ​​of the user, an amount that the user is willing to spend on health, the health consciousness of the user, and the health behavior of the user, using a trained artificial intelligence; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want something with special value or not, and whether or not a person wants to collect things.

[0017]

[13] The prediction means includes a step of predicting, based on the attribute information of the user and information related to the personality and values ​​of the user, an amount that the user is willing to spend on health, the health consciousness of the user, and the health behavior of the user, using a trained artificial intelligence; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want to be healed or not, Whether you want to relieve stress or not, Whether you want to build good relationships or not, Whether you want to share your feelings or not Whether you want to learn or not, Whether you want to explore or not, Whether you want to experience something brand new or not, Whether you want to give love or not, Whether you want to look after them or not, Whether or not you want to protect society and the community, A method of prediction, including whether or not you want to do the right thing. Effect of the Invention

[0018] It is possible to predict the user's health awareness with greater accuracy. [Brief description of the drawings]

[0019] [Figure 1] FIG. 1 is a block diagram showing a schematic configuration of a prediction device according to a first embodiment. [Figure 2A] FIG. 13 is a diagram illustrating information regarding personal needs. [Figure 2B] A diagram illustrating information regarding interpersonal needs. [Figure 2C] FIG. 13 is a diagram illustrating information regarding social desires. [Diagram 3] FIG. 11 is a diagram illustrating examples of questions to a user. [Figure 4] FIG. 11 is a block diagram showing a schematic configuration of a prediction device according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Hereinafter, an embodiment of the present invention will be specifically described with reference to the drawings.

[0021] Fig. 1 is a block diagram showing a schematic configuration of a prediction device according to a first embodiment. The prediction device includes a prediction means 1. The prediction means 1 receives as input attribute information of a user, information on the user's personal needs, information on the user's interpersonal needs, and information on the user's social needs. The prediction means 1 then predicts at least one of the user's health consciousness and health behavior (behavioral preference) based on the above information using trained artificial intelligence.

[0022] The prediction means 1 can also be considered an artificial intelligence that uses attribute information, information on personal needs, information on interpersonal needs, and information on social needs as explanatory variables (causative items) and health awareness and / or health behavior as objective variables (items to be predicted).

[0023] Examples of attribute information that serves as explanatory variables include, but are not limited to, age, sex, residential area, marital status, occupation, and income.

[0024] Each of the information on the user's personal needs, interpersonal needs, and social needs may include one or more evaluation axes. Each evaluation axis may include one or more items. Then, whether or not each evaluation axis or item applies (or to what extent it applies) may be input to the prediction means 1.

[0025] Figure 2A is a diagram illustrating information about personal desires. An example of an evaluation axis included in information about personal desires is "possessions," and examples of items included in this are "want something with special value" and "want to collect things." Another example of an evaluation axis is "intellectual curiosity," and examples of items included in this are "want to explore," "want to learn," and "want to experience unknown and brand new things." Other possible evaluation axes include "individuality and freedom," "intake and consumption," "activity and exercise," "future prospects," and "order."

[0026] Figure 2B is a diagram illustrating information related to interpersonal needs. An example of an evaluation axis included in information related to interpersonal needs is "peace of mind," and examples of items included in this are "want to be comforted" and "want to relieve stress." Another example of an evaluation axis is "love," and examples of items included in this are "want to show affection," "want to look after," and "want to look after." Other possible evaluation axes include "sex / love," "repulsion," and "improvement / achievement."

[0027] Figure 2C is a diagram illustrating information about social needs. An example of an evaluation axis included in information about social needs is "Connection," and examples of items included in this are "Want to build good relationships" and "Want to share feelings." Another example of an evaluation axis is "Social belonging," and examples of items included in this are "Want to protect society and the community" and "Want to do the right thing."

[0028] It is conceivable that the prediction means 1 presents the user with evaluation axes (or items) for personal needs, interpersonal needs, and social needs, and allows the user to select the one that applies.

[0029] The health consciousness and / or health behavior as the objective variable may include, for example, health behavior regarding food. Specific examples of the health consciousness and / or health behavior include whether the user cooks at home for health reasons, whether the user considers nutritional balance when eating, whether the user values ​​efficiency when doing something for health, etc.

[0030] A questionnaire survey may be utilized for learning the artificial intelligence for such prediction means 1. According to the applicant's investigation, it has been confirmed that a model for predicting health awareness and / or health behavior with high accuracy can be created by obtaining predetermined attribute information, information on personal needs, information on interpersonal needs, information on social needs, and health awareness and / or health behavior from a user through a questionnaire and using this as training data for learning.

[0031] As described above, the prediction device of the present embodiment predicts the health consciousness and / or health behavior of a user based on the user's attribute information, information on personal needs, information on interpersonal needs, and information on social needs. This improves prediction accuracy and enables more suitable (personalized) suggestions for the user.

[0032] For example, a provider of a health app service can use this prediction device to recommend supermarkets that sell suitable ingredients to users who cook at home, while also recommending restaurants that offer healthy meals to users who do not cook at home.As another example, an operator of an e-commerce site can use this prediction device to recommend products with more immediate effects to users who value efficiency.

[0033] The information on the personal needs, interpersonal needs, and social needs may be obtained by asking the user questions (survey) and figuring out the answers. There is no limit to the method of obtaining the information, and the information may be obtained by hardware or manually.

[0034] 3 is a diagram illustrating examples of questions to a user. Each question may be associated with one or more of information on personal needs, information on interpersonal needs, and information on social needs. Also, each question may be associated with one or more evaluation axes, or one or more items.

[0035] For example, if a user answers "Yes" to question 1 "Are you ____?", then that user falls into the category of "I want something with special value." If the user answers "No" to the same question, then that user does not fall into the category of "I want something with special value." The same applies to other questions. Each piece of information obtained in this way is input to the prediction means 1, and the user's health consciousness and / or health behavior is predicted.

[0036] In this way, according to this embodiment, the health consciousness and / or health behavior of a user can be predicted from the results of a questionnaire given to the user.

[0037] 4 is a block diagram showing a schematic configuration of a prediction device according to the second embodiment. A user's attribute information and information related to the user's personality and / or values ​​are input to a prediction means 1 of this prediction device. Then, the prediction means 1 uses trained artificial intelligence to predict one or more of the amount the user is willing to spend on health, the user's health consciousness, and the user's health behavior based on the input information.

[0038] The attribute information includes, but is not limited to, one or more of the user's gender, age, income, place of residence, whether single or married, whether or not they have children, occupation, and whether or not they have family members living together. The attribute information preferably includes gender, age, and income, and more preferably includes place of residence, whether single or married, whether or not they have children, occupation, and whether or not they have family members living together.

[0039] Examples of information regarding a user's personality and values ​​include the following: (1) Do you want something that has special value? (2) Do you want to collect things? (3) Do you want to be healed? (4) Do you want to relieve stress? (5) Do you want to build good relationships? (6) Do you want to share your feelings? (7) Do you want to learn? (8) Do you want to explore? (9) Do you want to experience something brand new? (10) Do you want to show affection? (11) Do you want to look after or take care of someone? (12) Do you want to protect society and the community? (13) Do you want to do the right thing?

[0040] The prediction means 1 may include one or more of (1) to (13) above, for example, it may include (1) and (2) above, or it may include (3) to (13) above, or it may include (1) to (13) above.

[0041] The output amount that the user is willing to spend on health may be divided into an amount that the user is willing to spend on health products and an amount that the user is willing to spend on health services.

[0042] A questionnaire survey may be utilized for learning the artificial intelligence for such prediction means 1. According to the applicant's investigation, it has been confirmed that a model can be created that predicts with high accuracy the amount of money that a user is willing to spend on health, health consciousness, and health behavior by obtaining predetermined attribute information, information on personality and values, amount of money that the user is willing to spend on health, health consciousness, and health behavior through a questionnaire survey and using this information as training data for learning.

[0043] As an example, a prediction model was created by acquiring attributes such as gender, age, and income from a large number of subjects, as well as the above information (1) to (13).The amount of money that users would be willing to spend on their health (three-value classification: 0 yen, 1 to less than 1000 yen, and 1000 yen or more) output from prediction means 1 to which this model was applied matched with a high degree of accuracy with the amount of money that users would be willing to spend on their health (three-value classification: 0 yen, 1 to less than 1000 yen, and 1000 yen or more) that they answered in a questionnaire.

[0044] In this way, according to this embodiment, based on the user's attribute information and information related to their personality and values, it is possible to use trained artificial intelligence to predict the amount of money that a user is willing to spend on health, their health awareness, and their health behavior.

[0045] Any part or all of the functional units described in this specification may be realized by a program. The program mentioned in this specification may be distributed in a non-temporary manner recorded on a computer-readable recording medium, or may be distributed via a communication line (including wireless communication) such as the Internet, or may be distributed in a state in which it is installed on any terminal.

[0046] Based on the above description, a person skilled in the art may be able to conceive additional effects and various modifications of the present invention, but the aspects of the present invention are not limited to the individual embodiments described above. Various additions, modifications, and partial deletions are possible within the scope of the conceptual idea and intent of the present invention derived from the contents defined in the claims and their equivalents.

[0047] For example, what is described in this specification as one device (or component, the same applies below) (including what is depicted in the drawings as one device) may be realized by multiple devices. Conversely, what is described in this specification as multiple devices (including what is depicted in the drawings as multiple devices) may be realized by one device. Alternatively, some or all of the means or functions included in a certain device (e.g., a server) may be included in another device (e.g., a user terminal). Furthermore, a "system" may be composed of one device, or may be composed of two or more devices (e.g., a server and a user terminal, or multiple user terminals).

[0048] Furthermore, not all of the features described in this specification are essential requirements, and in particular, any feature described in this specification but not included in the claims may be considered as optional additional features.

[0049] It should be noted that the applicant is merely aware of the inventions disclosed in the documents in the "Prior Art Documents" column of this specification, and the present invention does not necessarily aim to solve the problems of the inventions disclosed in the documents. The problems that the present invention aims to solve should be identified by taking into consideration the entire specification. For example, if the specification states that a specific effect is achieved by a specific configuration, it can also be said that the problem that is the reverse of the specific effect is solved. However, it is not necessarily intended that such a specific configuration is an essential requirement. [Explanation of symbols]

[0050] 1. Prediction methods

Claims

1. A prediction means for predicting an amount of money that the user is willing to spend on health, the health consciousness of the user, and the health behavior of the user, based on attribute information of the user and information related to the user's personality and values, using a trained artificial intelligence; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want something with special value or not, and whether or not the person wants to collect things.

2. A prediction means for predicting an amount of money that the user is willing to spend on health, the health consciousness of the user, and the health behavior of the user, based on attribute information of the user and information related to the user's personality and values, using a trained artificial intelligence; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want to be healed or not, Whether you want to relieve stress or not, Whether you want to build good relationships or not, Whether you want to share your feelings or not Whether you want to learn or not, Whether you want to explore or not, Whether you want to experience something brand new or not, Whether you want to give love or not, Whether you want to look after them or not, Whether or not you want to protect society and the community, and whether or not you want to do the right thing.

3. The information regarding the user's personality and values ​​is further Whether you want something with special value or not, The prediction device of claim 2 , further comprising: whether the user wants to collect the object.

4. The user attribute information further includes Place of residence, Single or married? Whether or not you have children Occupation and The prediction device according to claim 1 , further comprising: a family member living in the same household.

5. The prediction device according to claim 1 , wherein the amount that the user is willing to spend on health includes an amount that the user is willing to spend on health products and an amount that the user is willing to spend on health services.

6. The prediction means includes a step of predicting an amount that the user is willing to spend on health, the user's health consciousness, and the user's health behavior using trained artificial intelligence based on the user's attribute information and information related to the user's personality and values; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want something with special value or not, and whether or not a person wants to collect things.

7. The prediction means includes a step of predicting an amount that the user is willing to spend on health, the user's health consciousness, and the user's health behavior using trained artificial intelligence based on the user's attribute information and information related to the user's personality and values; The user attribute information includes at least Gender and Age and Including income, The information on the user's personality and values ​​includes at least Whether you want to be healed or not, Whether you want to relieve stress or not, Whether you want to build good relationships or not, Whether you want to share your feelings or not Whether you want to learn or not, Whether you want to explore or not, Whether you want to experience something brand new or not, Whether you want to give love or not, Whether you want to look after them or not, Whether or not you want to protect society and the community, A method of prediction, including whether or not you want to do the right thing.

Citation Information

Patent Citations

  • Program and information processor

    JP2022071655A