Information management system, information management method, program

Abstract

When updating a content generation model that generates behavior-variable content, consider the necessity of obtaining additional information used for the update. 【Solution means】An information processing system includes a contribution evaluation unit that evaluates the contribution degree of update information for updating a content generation model that generates behavior-variable content for causing a user to execute a predetermined target behavior, based on a contribution evaluation rule for evaluating the contribution degree to the update of the content generation model; an acquisition necessity determination unit that determines the necessity of obtaining the update information based on the contribution degree; an update information acquisition unit that acquires the update information based on the result of the determination of the necessity; and a model update unit that updates the content generation model using the acquired update information.

Description

Technical Field

[0001] The present invention relates to an information management system, an information management method, and a program.

Background Art

[0002] In recent years, efforts to utilize an approach based on theories of behavioral science, which scientifically studies human behavior, in service development have spread in various fields such as public policy, medicine, retail, and education. Also, systems for technically realizing the support for behavioral transformation and habituation of target persons in such various fields have been studied (for example, Patent Document 1).

[0003] In the system described in Patent Document 1, behavioral data including various data measured for the behaviors of a plurality of target persons is analyzed, and based on the results of the analysis of the behavioral data, a stage index that is an index serving as a standard for a plurality of stages gradually leading to a behavior as a goal of habituation, and each of the plurality of stages according to the stage index are defined, for each pair of adjacent stages, the gap between the two stages constituting the pair is specified, for each stage pair, at least one of the reason for the existence of the specified gap and the measure for causing a behavioral transformation for a target person belonging to the lower stage to transition to the higher stage is specified from relationship information in which the relationship between the gap and the reason / measure is defined, and it is described that processing regarding the reason / measure specified for each stage pair is executed.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] By the way, the content generation model that generates behavior modification content for promoting behavior modification can be updated in a timely manner for the purpose of generating more effective behavior modification content. For the purpose of updating the content generation model to be able to generate higher-quality behavior modification content, there may be a case where update information used for updating the content generation model is easily obtained. The easy acquisition of update information may lack the protection of user privacy, and may also cause a great deal of cost in the acquisition and management of update information.

[0006] Therefore, an object of the present invention is to consider the necessity of obtaining update information used for updating when updating a content generation model that generates behavior modification content.

Means for Solving the Problems

[0007] An information management system according to an aspect of the present invention includes a contribution evaluation unit that evaluates the contribution degree of update information for updating a content generation model to the update of the content generation model based on a contribution evaluation rule for evaluating the contribution degree of the update information used for updating to the update of the content generation model for generating behavior modification content for causing a user to execute a predetermined target behavior, an acquisition necessity determination unit that determines the necessity of acquiring the update information based on the contribution degree, an update information acquisition unit that acquires the update information based on the result of the determination of the necessity, and a model update unit that updates the content generation model using the acquired update information.

Effects of the Invention

[0008] According to the present invention, when updating a content generation model that generates behavior modification content, it is possible to consider the necessity of acquiring update information used for the update.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

[0010] Preferred embodiments of the present invention will be described with reference to the accompanying drawings. FIG. 1 is a diagram showing an overview of the processing in an information processing system 100 according to an embodiment of the present invention.

[0011] As a first example, the information processing system 100 determines whether it is necessary to acquire first user information based on the contribution degree according to a contribution degree evaluation rule for evaluating the contribution degree of the first user information to the generation of behavior-variable content.

[0012] In this case, first, the information processing system 100 receives an application for providing behavior-variable content and receives the provision of first user information from the information processing device 200 (S111). The information processing system 100 inputs the first user information into the content generation model to generate behavior-variable content (S112). The information processing system 100 evaluates the contribution degree of the first user information to the generation of behavior-variable content based on the contribution degree evaluation rule (S113). The information processing system 100 determines whether it is necessary to acquire the first user information based on the contribution degree (S114).

[0013] Then, based on the result of the necessity determination, the information processing system 100 acquires, from the information processing apparatus 200, the first user information determined to be necessary for acquisition when providing the behavior modification content when providing the behavior modification content (S115). The information processing system 100 inputs the first user information into the content generation model to generate behavior modification content, and provides it to the information processing apparatus 200 (S116).

[0014] In this way, the information processing system 100 can reduce the user information acquired from the user and avoid the easy acquisition of user information. The easy acquisition of user information includes, for example, acquiring user information that has little effect on generating high-quality behavior modification content. As a result of avoiding the easy acquisition of user information, the privacy of the user can be protected, and the entity that has acquired the user information (for example, the administrator of the information processing system 100) can reduce the cost of collecting user information and the cost of appropriately managing user information.

[0015] Also, as a second embodiment, the information processing system 100 determines the necessity of acquiring update information for updating the content generation model based on the contribution degree according to the contribution degree evaluation rule that evaluates the contribution degree of the update information for updating the content generation model to the update of the content generation model, and updates the content generation model based on the acquired update information.

[0016] In this case, first, the information processing system 100 receives the provision of update information from the information processing apparatus 200 (S121). The information processing system 100 evaluates the contribution degree of the update information to the update of the content generation model based on the contribution degree evaluation rule (S122). The information processing system 100 determines the necessity of acquiring the update information based on the contribution degree (S123).

[0017] Then, when updating the content generation model, the information processing system 100 acquires the update information from the information processing apparatus 200 (S124). The information processing system 100 updates the content generation model based on the update information (S125).

[0018] In this way, the information processing system 100 can reduce the update information to be obtained when updating the content generation model, and can avoid the easy acquisition of the update information. As a result of avoiding the easy acquisition of the update information, the privacy of the user corresponding to the update information can be protected, and the entity that has obtained the update information (for example, the administrator of the information processing system 100) can reduce the cost for collecting the update information and the cost for appropriately managing the update information.

[0019] Note that the two information processing apparatuses 200 shown in FIG. 1 may be different information processing apparatuses from each other, or may be the same information processing apparatus.

[0020] In the present embodiment, the behavior modification content is content that causes a user to execute a predetermined target behavior (also referred to as behavior modification). That is, the behavior modification content is, for example, content that has an effect of modifying the behavior of the user. In the present embodiment, the case where the behavior modification content is one piece of behavior modification content will be described as an example, but when the behavior modification content is a series of behavior modification contents, the behavior modification content can be read as a series of behavior modification contents as appropriate.

[0021] Behavior change content is content generated based on, for example, behavior change techniques (BCTs). For example, according to BCTTv1 (Michie S, Richardson M, Johnston M, et al.: The behavior change technique taxonomy (v1) of 93 hierarchically clustered techniques: building an international consensus for the reporting of behavior change interventions. Ann Behav Med 2013; 46: 81~95.), 93 BCTs in 16 groups are defined. Note that the definition of BCTs is not limited to BCTTv1 and may be defined in any way as long as it comprehensively covers behavior change techniques.

[0022] BCTTv1 defines 16 BCT groups, namely, "1. Goals and planning", "2. Feedback and monitoring", "3. Social support", "4. Shaping knowledge", "5. Natural consequences", "6. Comparison of behaviour", "7. Associations", "8. Repetition and substitution", "9. Comparison of outcomes", "10. Reward and threat", "11. Regulation", "12. Antecedents", "13. Identity", "14. Scheduled consequences", "15. Self-belief", and "16. Covert learning".

[0023] In BCTTv1, each of the 16 BCT groups shown in FIG. 2 belongs to one or more BCTs. For example, BCTs such as "5.5.Anticipated regret" belong to the BCT group "5.Natural consequences". Also, BCTs such as "10.11.Future punishment" belong to the BCT group "10.Reward and threat". Although not shown, one or more BCTs also belong to other groups.

[0024] In addition, each BCT has components, and the degree of each BCT included in a certain content may be shown as a component value. Also, the sum of the component values of each BCT belonging to the same BCT group may be shown as the component value of the BCT group.

[0025] The behavior change promoted by the behavior change content is assumed to be, for example, language learning, dieting, purchase of financial products provided by financial institutions, regular medical examinations, use of public services, etc., but is not limited thereto. Also, the behavior change content is not limited to being provided to the user using electromagnetic methods such as applications installed on the terminal, web pages, e-mails, short messages, etc., and may be provided to the user using other methods (for example, customer service, mail, etc.). Also, the behavior change content is, for example, text information related to a specific service (for example, chat logs, etc.), moving images, still images, voice of conversation, data related to applications, etc., but is not limited thereto, and may be any information related to the content of the behavior change.

[0026] When generating and evaluating the behavior change content, a coordinate system with a plurality of behavior change factors as axes is generated, and a target coordinate or a target area (hereinafter, these are collectively referred to as the target area) is set in this coordinate system. Then, whether or not the user has caused a behavior change is evaluated in the coordinate system by whether or not the user's coordinates have approached the target area. Hereinafter, the distance calculated in this coordinate system is referred to as "Behavioral Scientific Distance (BSD)".

[0027] In such a coordinate system, for each user, by setting the current coordinates and the target area that the intervention should aim at, the behavioral science distance from the current coordinates to the target area can be expressed as a multi-dimensional vector, and it becomes possible to objectively and clearly visualize the BCT to be adopted to fill this distance. That is, higher-quality behavior modification content is, for example, behavior modification content that reduces the behavioral science distance from the current coordinates to the target area.

[0028] Behavior modification factors are, for example, factors for causing a user to perform a target behavior. Based on surveys such as academic surveys or awareness surveys, theories related to behavioral science, user persona settings, or behavioral process maps, etc., a plurality of behavior modification factors in the target field can be identified. Examples of behavior modification factors include "Capacity", "Opportunity", and "Motivation" in the COM-B model commonly used in behavioral science. Alternatively, as another example of behavior modification factors, factors defined by the Integrated Behavioral Model (IBM) (also called "IBM factors") such as experiential attitude, instrumental attitude, injunctive norm, descriptive norm, perceived control, self-efficacy, knowledge, skills, salience of the behavior, environmental constraints, and habituation are also known. In the present embodiment, behavior modification factors including at least two of these may be identified.

[0029] Note that each of the above-mentioned IBM factors is merely an example, and higher-level factors including the above IBM factors may be specified as behavior modification factors. For example, the above empirical attitude and instrumental attitude are included in "Attitude", the above injunctive norm and descriptive norm are included in "Perceived norm", the above sense of behavioral control and self-efficacy are included in "Personal Agency", the above knowledge and technology are included in "Knowledge", the importance of behavior is included in "Importance", and environmental constraints may be included in "Friction". Alternatively, lower-level factors obtained by dividing the above IBM factors may be specified as behavior modification factors. In the present embodiment, any factors related to human behavior will, such as factors defined by the COM-B model or behavior models other than IBM, may be adopted as behavior modification factors.

[0030] The ease of response to behavior modification factors may vary from user to user. That is, in some users, behavior modification is likely to occur due to behavior modification content that strongly acts on the first behavior modification factor, while in other users, behavior modification may be likely to occur due to behavior modification content that strongly acts on the second behavior modification factor. Also, even for the same user, the ease of response to behavior modification factors may vary depending on the passage of time, the situation such as the time when the behavior modification content is given and the environment at that time, and the target behavior and the content of the behavior modification. The ease of response to behavior modification factors may be expressed as behavior characteristics in a user. Thus, the behavioral science distance at which behavior modification content can act may vary depending on the behavior characteristics of the user.

[0031] FIG. 3 is a diagram showing the configuration of an information processing system 100 according to an embodiment of the present invention. The information processing system 100 is communicably connected via a network such as the Internet to an information processing device 200. Details of the information processing system 100 will be described later.

[0032] The information processing apparatus 200 outputs at least one of user information regarding a user and update information for updating a content generation model to the information processing system 100. The information processing apparatus 200 may be, for example, a computer, a smartphone, a tablet terminal, a personal computer, or the like.

[0033] The information processing apparatus 200 may be a user device used by the user. Also, in this case, the information processing apparatus 200 may output user information to the information processing system 100 and may not output update information.

[0034] Also, the information processing apparatus 200 may be an information management apparatus that manages information. In this case, the information processing apparatus 200 may output update information to the information processing system 100 and may not output user information.

[0035] Note that in FIG. 3, one information processing apparatus 200 is shown, but the information processing apparatus 200 may be a plurality of information processing apparatuses 200 (for example, a user device and an information management apparatus).

[0036] Subsequently, details of the information processing system 100 will be described. The information processing system 100 includes a storage unit 110, an acquisition processing unit 120, an update information acquisition unit 130, a behavior characteristic acquisition unit 140, a content generation unit 150, a content evaluation unit 160, a contribution degree evaluation unit 170, an acquisition necessity determination unit 180, a content output unit 190, and a model update unit 195. Each unit shown in FIG. 3 can be realized, for example, by using a storage area or by the processor executing a program stored in the storage area.

[0037] The storage unit 110 stores information processed in the information processing system 100. The storage unit 110 can store, for example, user information, update information, behavior characteristic information, behavior-varied content, effect evaluation result information, contribution degree evaluation result information, and determination result information, which will be described later.

[0038] The acquisition processing unit 120 acquires user information and stores the acquired user information in the storage unit 110. The acquisition processing unit 120 acquires, for example, from the information processing apparatus 200.

[0039] Before the acquisition necessity determination processing by the acquisition necessity determination unit 180 described later, the acquisition processing unit 120 can acquire user information (for example, first user information) that is the target of the acquisition necessity determination processing.

[0040] Based on the result of the necessity determination by the acquisition necessity determination unit 180, the acquisition processing unit 120 can perform acquisition processing for acquiring user information (for example, first user information). Further, based on the result of the necessity determination by the acquisition necessity determination unit 180, the acquisition processing unit 120 can perform acquisition processing for not acquiring user information (for example, first user information).

[0041] The user information includes, but is not limited to, biological information regarding the user's living body, position information of the user or a device (information processing apparatus 200) owned by the user, or device information regarding the device, and information regarding the content of the answer results to the questionnaire. The biological information includes, for example, but is not limited to, information regarding the content of the results of the user's health check, and vital information such as the user's heartbeat.

[0042] Before the acquisition necessity determination processing, the user information acquired as the target of the acquisition necessity determination processing may be user information having a larger amount of information (at least one of the content and items) than the user information acquired based on the result of the necessity determination. That is, the information processing system 100 can, so to speak, first widely acquire acquirable user information and then further acquire only the user information determined to be necessary for acquisition, and generate action-variable content to be provided to the user.

[0043] The update information acquisition unit 130 acquires update information and stores the acquired update information in the storage unit 110.

[0044] Before the acquisition necessity determination process by the acquisition necessity determination unit 180 described later, the update information acquisition unit 130 can acquire update information that is the target of the acquisition necessity determination process.

[0045] Based on the result of the necessity determination by the acquisition necessity determination unit 180, the update information acquisition unit 130 can perform an acquisition process of acquiring update information. Further, based on the result of the necessity determination by the acquisition necessity determination unit 180, the update information acquisition unit 130 can perform an acquisition process of not acquiring the update information.

[0046] The update information may be any information that can update the content generation model. The update information may include user information and may also include the behavior characteristic information described later.

[0047] Before the acquisition necessity determination process, the update information acquired as the target of the acquisition necessity determination process may be update information with a larger amount of information (at least one of content, type, and items) than the update information acquired based on the result of the necessity determination. That is, the information processing system 100 can, so to speak, first widely acquire the acquirable update information and then further acquire only the update information determined to be necessary for acquisition to update the content generation model.

[0048] The behavior characteristic acquisition unit 140 acquires behavior characteristic information regarding the user's behavior characteristics and stores the acquired behavior characteristic information in the storage unit 110. Here, the behavior characteristic is, for example, the ease of reaction of each behavior change factor in the user.

[0049] The behavior characteristic information of the same user may be different each time the behavior characteristic acquisition unit 140 acquires it. That is, the behavior characteristic information may be different for the same user according to the passage of time, the situation such as the time when the behavior characteristic acquisition unit 140 acquires it and the environment at that time, the target behavior, and the content of the behavior change.

[0050] The content generation unit 150 generates behavior-transformed content that causes a user to perform a predetermined target behavior, stores the generated behavior-transformed content in the storage unit 110 based on a content generation model for generating the behavior-transformed content.

[0051] The content generation model may be, for example, a model that generates behavior-transformed content in response to the input of user information. That is, in this case, the content generation unit 150 can input first user information into the content generation model to generate behavior-transformed content (post-input behavior-transformed content). The content generation unit 150 may generate behavior-transformed content (pre-input behavior-transformed content) without inputting the first user information into the content generation model. Note that in the present embodiment, generating behavior-transformed content (pre-input behavior-transformed content) without inputting the first user information means inputting user information that does not include the first user information, that is, user information different from the first user information, into the content generation model to generate behavior-transformed content (pre-input behavior-transformed content).

[0052] Also, the content generation model may be a model that generates behavior-transformed content based on a user's behavior characteristics in response to the input of user information and behavior characteristic information. That is, in this case, the content generation unit 150 can input user information and behavior characteristic information into the content generation model to generate behavior-transformed content based on the user's behavior characteristics.

[0053] Also, the content generation model may be a model that generates a series of behavior-transformed content corresponding to each of a plurality of behaviors to be performed until a predetermined target behavior. That is, in this case, the content generation unit 150 can generate a series of behavior-transformed content based on the content generation model.

[0054] In addition, the content generation unit 150 can generate action-varied content (updated action-varied content) based on the pre-update content generation model before being updated by the model update unit 195 described later, and the post-update content generation model updated by the model update unit 195.

[0055] The content generation model is, for example, a model that generates action-varied content and has an effect of reducing the behavioral scientific distance from the current coordinates to the target area.

[0056] The content generation model may generate content using, for example, artificial intelligence (AI) technology, particularly generative AI. Specifically, when the content generation model receives an input of user information, it generates generation request information incorporating the user information into pre-set generation request information (so-called prompt), obtains action-varied content generated by the generative AI using the generated generation request information, and outputs the action-varied content. Here, the generation request information may include, for example, information regarding the target action, the content of action variation, or information regarding the type of action-varied content to be generated. Also, the generation request information may be generation request information for causing the generative AI to generate action-varied content with the highest effect of reducing the behavioral scientific distance from the current coordinates to the target area.

[0057] In addition, the content generation model may be a model that generates action-varied content by selecting at least one action-varied content from a plurality of pre-set action-varied contents based on user information. At this time, the content generation model may select the action-varied content with the highest effect of reducing the behavioral scientific distance from the current coordinates to the target area among the plurality of action-varied contents.

[0058] Alternatively, the content generation model may generate one action-variant content by combining action-variant content or elements of action-variant content selected from, for example, a plurality of pre-set action-variant contents or elements of action-variant content.

[0059] Alternatively, the content generation model may generate a series of action-variant content composed of a plurality of action-variant contents.

[0060] The content evaluation unit 160 evaluates the effect of the action-variant content based on a content evaluation rule for evaluating the effect of the action-variant content on causing a user to perform a predetermined target action, and stores effect evaluation result information regarding the evaluated effect in the storage unit 110.

[0061] The content evaluation rule may be, for example, correspondence relationship information showing a correspondence relationship between a plurality of elements for evaluating the content, which are pre-set, and weights for each of the elements. Alternatively, the content evaluation rule may be, for example, an evaluation model that inputs the content and outputs a score indicating the evaluation result of the content.

[0062] Alternatively, the content evaluation rule may be a rule for evaluating the magnitude of the behavioral science distance on which the action-variant content acts. That is, in this case, the content evaluation rule may be a rule that evaluates more highly the action-variant content that reduces the behavioral science distance to the target action in the user. The content evaluation rule may be a rule in which the behavioral science distance on which the action-variant content acts is associated with the evaluation result.

[0063] In addition, for example, when the content (e.g., text) is general content, the content evaluation rule may evaluate that the quality of the content is low, and when the content (e.g., text) is characteristic content, the content evaluation rule may evaluate that the quality of the content is high. Here, whether the content of the content is characteristic content may be evaluated, for example, based on the ratio of proper nouns included in the content. That is, the higher the ratio of proper nouns included in the content, the more characteristic the content may be evaluated to be.

[0064] In addition, for example, for content composed of a plurality of sentences, when the similarity of the meaning of each sentence is low and the information density is high, when the usage ratio of Chinese characters and hiragana is appropriate and the readability is high, when the content is appropriate for the context even if translated into another language, or when the content includes a font, size, figure, or color considering universal design, the content evaluation rule may evaluate that the quality of the content is high.

[0065] Based on the content evaluation rule, the content evaluation unit 160 can output, as an evaluation result, for example, a quantitative score (e.g., a score according to the behavioral science distance) or a qualitative score (e.g., "very good", "good", etc.) indicated by using a numerical value.

[0066] Based on the content evaluation rule, the content evaluation unit 160 can evaluate the effect of the post-input behavior-variable content. In addition, based on the content evaluation rule, the content evaluation unit 160 can evaluate the effect of the pre-input behavior-variable content. In addition, the content evaluation unit 160 can evaluate the effect of a series of post-input behavior-variable content generated by inputting the first user information into the content generation model.

[0067] The content evaluation unit 160 can evaluate the effects of the post-update behavior-varied content based on the content evaluation rules. Also, the content evaluation unit 160 can evaluate the effects of the behavior-varied content (pre-update behavior-varied content) generated based on the pre-update content generation model based on the content evaluation rules. Further, the content evaluation unit 160 can evaluate the effects of a series of post-update behavior-varied content.

[0068] In this way, the content evaluation unit 160 can evaluate the degree of importance of the generated behavior-varied content for achieving the target behavior.

[0069] The contribution evaluation unit 170 evaluates the contribution degree of the first user information to the generation of the behavior-varied content based on the first contribution evaluation rule for evaluating the contribution degree of the first user information to the generation of the behavior-varied content, and stores the contribution evaluation result information regarding the evaluated contribution degree in the storage unit 110.

[0070] The contribution evaluation unit 170 can evaluate the contribution degree of the first user information to the effects evaluated by the content evaluation unit 160.

[0071] Here, the content evaluation unit 160 may evaluate the magnitude of the behavioral science distance on which the behavior-varied content acts as the effect of the behavior-varied content.

[0072] The contribution evaluation unit 170 can evaluate the contribution degree of the first user information based on the effects of the pre-input behavior-varied content and the post-input behavior-varied content evaluated by the content evaluation unit 160. That is, in this case, the first contribution evaluation rule may be, for example, a rule for evaluating the contribution degree of the first user information based on the effects of the pre-input behavior-varied content and the post-input behavior-varied content.

[0073] Specifically, first, the content evaluation unit 160 evaluates the effect of the pre-input behavior-modified content and outputs pre-input effect evaluation result information as the evaluation result. Subsequently, the content evaluation unit 160 evaluates the effect of the post-input behavior-modified content and outputs post-input effect evaluation result information as the evaluation result. Then, the contribution evaluation unit 170 compares the pre-input effect evaluation result information and the post-input effect evaluation result information to evaluate the contribution degree of the first user information. At this time, the contribution evaluation unit 170 may evaluate, for example, the difference or discrepancy between the effect (e.g., score) indicated by the pre-input effect evaluation result information and the effect (e.g., score) indicated by the post-input effect evaluation result information as the contribution degree of the first user information. Thereby, the contribution evaluation unit 170 can evaluate the contribution degree of the resource of the first user information to the return of the evaluation result, so to speak, from the perspective of ROI (Return On Investment). In other words, the contribution evaluation unit 170 can evaluate the contribution degree according to the degree to which it is expected that more effective behavior-modified content can be generated when the first user information is acquired. In this case, the contribution evaluation unit 170 can evaluate the contribution degree from the perspective of how much the first user information contributes to the determination of the behavior-modified content that is highly likely to enable the user to achieve the target behavior.

[0074] At this time, the difference between the effect (e.g., score) indicated by the pre-input effect evaluation result information and the effect (e.g., score) indicated by the post-input effect evaluation result information may be the difference in behavioral science distance. Taking the case where the target behavior is the commuting behavior and the first user information is that the user is at home as an example. In this case, for example, the post-input behavior modification content may be, for example, a message such as "Don't you want to leave home?" Since the location of the user is unknown for the pre-input behavior modification content, it may not be a message such as "Don't you want to leave home?" but a message such as "Don't you want to go to the company?" In this case, the behavioral science distance at which the message "Don't you want to leave home?" acts may be greater than the behavioral science distance at which the message "Don't you want to go to the company?" acts. This is because, for example, the word "company" may be a barrier to the user's behavior modification. In such a case, the contribution evaluation unit 170 can evaluate, for example, the difference in behavioral science distance as the contribution of the first user information that the user is at home. In this way, when generating effective behavior modification content from a plurality of assumed behavior modification contents, the contribution evaluation unit 170 can evaluate the degree to which the first user information contributes.

[0075] In addition, the contribution evaluation unit 170 can further evaluate the contribution of the first user information based on external environment information regarding the external environment related to the execution of a predetermined target behavior. That is, in this case, the first contribution evaluation rule may be, for example, a rule for evaluating the contribution of the first user information based on the external environment information.

[0076] In this case, the contribution evaluation unit 170 can evaluate, so to speak, the degree to which the first user information contributes to the response to changes in the environment surrounding the target behavior. Consider as an example the case where the target behavior is the behavior of going to work, the first user information is the route used by the user for commuting, and the external environment information is the operation status of the train used for commuting. In this case, when the train used for commuting is operating normally, although the influence of the first user information on the generation of behavior modification content and the achievement of the target behavior is small, when the train used for commuting is not operating normally, the influence of the first user information on the generation of behavior modification content and the achievement of the target behavior may become large. This is because, for example, when the train used for commuting is not operating normally, the user may dislike going to work. When the train used for commuting is not operating normally, instead of or in addition to the message "Shall we leave home?", behavior modification content that presents the time until the train schedule used by the user for commuting normalizes or a detour route different from the route used by the user for commuting may be effective. That is, it is conceivable that the first user information, which has a small contribution during normal schedule times, becomes the first user information with a high contribution during abnormal schedule times. Thus, the contribution evaluation unit 170 can evaluate the contribution by further considering the external environment information.

[0077] The external environment information may be, for example, information regarding changes in the environment surrounding the target behavior, such as the fact that a scandal at the user's workplace has been reported in the news, but is not limited to these.

[0078] The contribution evaluation unit 170 evaluates the contribution of the update information to the content generation model based on a second contribution evaluation rule for evaluating the contribution of the update information to the update of the content generation model, and stores contribution evaluation result information regarding the evaluated contribution in the storage unit 110.

[0079] The contribution degree evaluation unit 170 can evaluate the contribution degree of the update information to the content generation model based on the effects of the pre-update behavior-variable content and the post-update behavior-variable content. That is, in this case, the second contribution degree evaluation rule may be a rule for evaluating the contribution degree based on the effects of the pre-update behavior-variable content and the post-update behavior-variable content. Here, in the pre-update behavior-variable content and the post-update behavior-variable content, the information input to the content generation model may be the same. That is, the difference between the pre-update behavior-variable content and the post-update behavior-variable content may be the difference in the content generation model, in other words, the difference between the pre-update content generation model and the post-update content generation model.

[0080] Specifically, first, the content evaluation unit 160 evaluates the effect of the pre-update behavior-variable content and outputs pre-update effect evaluation result information as the evaluation result. Subsequently, the content evaluation unit 160 evaluates the effect of the post-update behavior-variable content and outputs post-update effect evaluation result information as the evaluation result. Then, the contribution evaluation unit 170 compares the pre-update effect evaluation result information and the post-update effect evaluation result information, and evaluates the contribution degree of the update information for the content generation model. At this time, the contribution evaluation unit 170 may evaluate, for example, the difference or discrepancy between the effect (e.g., score) indicated by the pre-update effect evaluation result information and the effect (e.g., score) indicated by the post-update effect evaluation result information as the contribution degree of the update information for the content generation model. Thereby, the contribution evaluation unit 170 can evaluate the contribution degree of the update (so to speak, improvement) of the content generation model to the return of further investing the resource of the update information from the perspective of ROI (Return On Investment). In other words, the contribution evaluation unit 170 can evaluate the contribution degree according to the degree to which it is expected that the pre-update content generation model can be updated to a post-update content generation model capable of generating more effective behavior-variable content when the update information is obtained. In this case, the contribution evaluation unit 170 can evaluate the contribution degree from the perspective of how much the update information contributes to the update of the content generation model that generates behavior-variable content with a high possibility of enabling the user to achieve the target behavior.

[0081] At this time, the difference between the effect (e.g., score) indicated by the pre-update effect evaluation result information and the effect (e.g., score) indicated by the post-update effect evaluation result information may be the difference in the behavioral science distance. In this way, the contribution evaluation unit 170 can evaluate how much the update information contributes when updating the pre-update content generation model to a post-update content generation model capable of generating more effective behavior-variable content. For example, when the target action is the commuting-to-work action, it is conceivable to register the user's workplace (e.g., the user's affiliated company) as update information. By registering the user's affiliated company, specific station names related to the workplace (e.g., the nearest station to the workplace) can be included in the behavior modification content. When the station name is not included in the behavior modification content before the update and is included in the behavior modification content after the update, it may be possible to switch whether to obtain the workplace information from the user as update information based on whether the evaluation result after the update is a certain level or higher than the evaluation result before the update.

[0082] Further, the contribution evaluation unit 170 can evaluate the contribution degree of the update information to the content generation model based on the external environment information. That is, in this case, the second contribution evaluation rule may be, for example, a rule for evaluating the contribution degree of the update information to the content generation model based on the external environment information. For example, assume that when the target action is the commuting-to-work action, the user has registered the information of their affiliated company. In this case, due to factors such as the transfer of the office, the location where the user commutes to work may change. By obtaining information related to the transfer of the user's affiliated company as external environment information, it may be necessary to change the station names included in the behavior modification content sent to the user.

[0083] The acquisition necessity determination unit 180 determines the necessity of acquiring the first user information based on the contribution degree evaluated according to the first contribution evaluation rule, and stores the determination result information related to the determination result in the storage unit 110.

[0084] Further, the acquisition necessity determination unit 180 determines the necessity of acquiring the update information based on the contribution degree evaluated according to the second contribution evaluation rule, and stores the determination result information related to the determination result in the storage unit 110.

[0085] The determination result information may be information, for example, in which "required" indicating that acquisition is necessary or "not required" indicating that acquisition is not necessary is associated for each of the first user information and the update information.

[0086] The acquisition necessity determination unit 180 may determine that acquisition is necessary, for example, when the contribution degree exceeds a predetermined threshold value.

[0087] In this way, the acquisition necessity determination unit 180 can determine that acquisition is necessary, for example, for the first user information for which it is expected that more effective action-variable content can be generated. Also, the acquisition necessity determination unit 180 can determine that acquisition is necessary, for example, for the update information for which it is expected that the content generation model can be updated more effectively.

[0088] The content output unit 190 outputs the action-variable content obtained by inputting the first user information acquired based on the necessity of acquisition determined by the acquisition necessity determination unit 180 into the content generation model. Thereby, the information processing system 100 can output the action-variable content generated based on the first user information for which it is expected that more effective action-variable content can be generated.

[0089] The content output unit 190 may output the action-variable content to, for example, the information processing device 200. Also, the content output unit 190 may output the action-variable content to the information processing device used by the person who provides the action-variable content to the user.

[0090] The model update unit 195 updates the content generation model using the update information. The model update unit 195 can update the pre-update content generation model before being updated by the update information using the update information to generate the post-update content generation model.

[0091] The model update unit 195 can update the content generation model using the update information acquired based on the necessity of acquisition determined by the acquisition necessity determination unit 180.

[0092] In addition, the model update unit 195 can update the content generation model based on the contribution degree evaluated by the contribution degree evaluation unit 170 according to the second contribution degree evaluation rule. In this case, the model update unit 195 may update the content generation model using update information having a contribution degree exceeding a predetermined threshold value. Thereby, the information processing system 100 can update the content generation model without further acquiring the update information, and can simplify the information processing. Further, in this case, at the time of the next update of the content generation model, the update information acquisition unit 130 may acquire only the update information determined to be necessary, and the processing of the second embodiment in the information processing system 100 may be performed. Thereby, the acquired update information can be sequentially selected.

[0093] Also, the model update unit 195 can update the content generation model using the behavior characteristic information.

[0094] The first user information may be a plurality of pieces of first user information. In this case, the contribution degree evaluation unit 170 can evaluate the contribution degree of each of the plurality of pieces of first user information based on the first contribution degree evaluation rule. Further, the acquisition necessity determination unit 180 determines the necessity of acquisition of each of the plurality of pieces of first user information based on the contribution degree of each of the plurality of pieces of first user information, and the acquisition processing unit 120 can acquire the first user information determined to be necessary among the plurality of pieces of first user information.

[0095] The update information may be a plurality of pieces of update information. In this case, the contribution degree evaluation unit 170 can evaluate the contribution degree of each of the plurality of pieces of update information. Further, the acquisition necessity determination unit 180 determines the necessity of acquisition of each of the plurality of pieces of update information, and the update information acquisition unit 130 can acquire the update information determined to be necessary among the plurality of pieces of update information.

[0096] Subsequently, a specific example in the information processing system 100 will be described.

[0097] FIG. 4 is a flowchart showing an example of the processing of the information processing system 100 in the first embodiment.

[0098] First, the acquisition processing unit 120 acquires a plurality of user information (S401). Here, the plurality of user information may be, for example, user information of the same type common to a plurality of users (for example, a plurality of users belonging to a predetermined group). Subsequently, the content generation unit 150 generates behavior-variable content based on the plurality of user information, and the content evaluation unit 160 evaluates the generated behavior-variable content (S402). At this time, the content generation unit 150 may generate behavior-variable content obtained by inputting all of the plurality of user information into the content generation model, and behavior-variable content obtained by inputting a part of the plurality of user information (for example, excluding each of the user information included in the plurality of user information) into the content generation model. Further, the content generation unit 150 may further input the behavior characteristic information acquired by the behavior characteristic acquisition unit 140 into the content generation model to generate behavior-variable content. The contribution degree evaluation unit 170 evaluates the contribution degree of each of the plurality of user information based on the first contribution degree evaluation rule (S403). At this time, the contribution degree evaluation unit 170 may evaluate the contribution degree of each of the plurality of user information based on, for example, the effect of the behavior-variable content after input and the evaluation of the behavior-variable content before input for each of the plurality of user information. The acquisition necessity determination unit 180 determines the necessity of acquisition of each of the plurality of user information (S404).

[0099] Then, the acquisition processing unit 120 performs an acquisition process of acquiring user information (for example, the first user information) among the plurality of user information based on the result of the necessity determination, and performs an acquisition process of not acquiring user information (for example, the second user information) among the plurality of user information (S405). At this time, the types of user information to be acquired and the user information not to be acquired may differ for each user. The content generation unit 150 generates behavior-modified content based on the user information (for example, the first user information) acquired based on the acquisition necessity, and the content output unit 190 outputs the behavior-modified content (S406).

[0100] In this way, the information processing system 100 first acquires a plurality of pieces of user information, determines the necessity of acquisition of each of the plurality of pieces of user information based on the contribution degree of each of the plurality of pieces of user information, and acquires the user information (for example, the first user information) determined to be necessary for acquisition. That is, for example, when providing behavior-modified content based on user information, the information processing system 100 acquires a plurality of pieces of user information before providing the behavior-modified content, identifies the user information necessary for acquisition in providing effective behavior-modified content, and acquires the user information (for example, the first user information) determined to be necessary for acquisition when generating and providing the behavior-modified content. Thereby, the amount of user information acquired from the user can be reduced. As a result of reducing the amount of user information acquired from the user, the privacy of the user can be protected, and the entity that has acquired the user information (for example, the administrator of the information processing system 100) can reduce the cost for collecting the user information and the cost for appropriately managing the user information. Further, the information processing system 100 may discard including the information acquired in the past regarding the user information determined to be unnecessary for acquisition. Thereby, the information processing system 100 can avoid the need to manage unnecessary information, reduce the cost of information management, and reduce the risk of information leakage.

[0101] FIG. 5 is a flowchart showing an example of the processing of the information processing system 100 in the second embodiment.

[0102] First, the update information acquisition unit 130 acquires a plurality of pieces of update information (S501). The contribution degree evaluation unit 170 evaluates the contribution degree of each of the plurality of pieces of update information for updating the content generation model based on the second contribution degree evaluation rule (S502). The acquisition necessity determination unit 180 determines the necessity of acquisition of each of the plurality of pieces of update information (S503).

[0103] Then, based on the result of the acquisition necessity determination, the update information acquisition unit 130 acquires the update information determined to be necessary for acquisition among the plurality of pieces of update information (S504). The model update unit 195 updates the content generation model using the update information determined to be necessary for acquisition and acquired (S505). At this time, the information processing system 100 may discard including the information acquired in the past regarding the update information determined to be unnecessary for acquisition.

[0104] Next, with reference to FIG. 6, an example of the hardware configuration when the information processing system 100 is realized by a computer 600 will be described. FIG. 6 is a diagram showing an example of the hardware configuration of the computer 600.

[0105] As shown in FIG. 6, the computer 600 includes, for example, a processor 601, a memory 602, a storage device 603, an input I / F unit 604, a data I / F unit 605, a communication I / F unit 606, and a display device 607.

[0106] The computer 600 may be, for example, a server computer, a personal computer (e.g., desktop, laptop, tablet, etc.), a media computer platform (e.g., cable, satellite set-top box, digital video recorder, etc.), a handheld computer device (e.g., PDA, email client, etc.), or another type of computer or communication platform.

[0107] The processor 601 is a control unit that controls various processes in the computer 600 by executing a program stored in the memory 602.

[0108] The memory 602 is a storage medium such as a RAM (Random Access Memory). The memory 602 temporarily stores the program code of the program executed by the processor 601 and the data required during the execution of the program.

[0109] The storage device 603 is a non-volatile storage medium such as a hard disk drive (HDD) or a flash memory. The storage device 603 stores the operating system and various programs for realizing the above-described components.

[0110] The input I / F unit 604 is a device for receiving an input from a user. The input I / F unit 604 is, for example, a keyboard, a mouse, a touch panel, various sensors, a wearable device, or the like. The input I / F unit 604 may be connected to the computer 600 via an interface such as a USB (Universal Serial Bus).

[0111] The data I / F unit 605 is a device for inputting data from the outside of the computer 600. The data I / F unit 605 is, for example, a drive device for reading data stored in various storage media. The data I / F unit 605 may be provided outside the computer 600. When the data I / F unit 605 is provided outside the computer 600, the data I / F unit 605 is connected to the computer 600 via an interface such as a USB.

[0112] The communication I / F unit 606 is a device for performing data communication via a network such as the Internet, either wired or wirelessly, with a device external to the computer 600. The communication I / F unit 606 may be provided outside the computer 600. When the communication I / F unit 606 is provided outside the computer 600, the communication I / F unit 606 is connected to the computer 600 via an interface such as USB, for example.

[0113] The display device 607 is a device for displaying various types of information. The display device 607 is, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, a display of a wearable device, or the like. The display device 607 may be provided outside the computer 600. When the display device 607 is provided outside the computer 600, the display device 607 is connected to the computer 600 via a display cable or the like, for example. Also, when a touch panel is adopted as the input I / F unit 604, the display device 607 may be configured integrally with the input I / F unit 604.

[0114] As described above, one embodiment of the present invention has been explained. The information processing system 100 evaluates the contribution degree of the update information for the content generation model based on the second contribution degree evaluation rule, determines the necessity of acquiring the update information based on the contribution degree, acquires the update information based on the result of the necessity determination, and can update the content generation model using the acquired update information. Thereby, when updating the content generation model that generates behavior-variable content, the information processing system 100 can consider the necessity of acquiring the update information used for the update.

[0115] Also, the information processing system 100 can acquire behavior characteristic information and update the content generation model using the behavior characteristic information. Thereby, the information processing system 100 can update the content generation model in consideration of the behavior characteristics of the user.

[0116] In addition, the information processing system 100 can evaluate the effect of the updated action-variable content obtained from the updated content generation model updated using the update information based on the content evaluation rules, and evaluate the contribution degree of the update information to the update of the content generation model with respect to the evaluated effect. Thereby, the information processing system 100 can consider the necessity of acquiring the update information based on the effect of the updated action-variable content.

[0117] In addition, the information processing system 100 can further evaluate the effect of the pre-updated action-variable content based on the content evaluation rules, and evaluate the contribution degree of the update information to the update of the content generation model based on the effect of the pre-updated action-variable content and the effect of the updated action-variable content. Thereby, the information processing system 100 can consider the necessity of acquiring user information, for example, based on the difference or disparity in the effects of the updated action-variable content and the pre-updated action-variable content, from the perspective of ROI so to speak.

[0118] In addition, the information processing system 100 can evaluate the contribution degree of the update information to the update of the content generation model based on the external environment information. Thereby, the information processing system 100 can consider the necessity of acquiring the update information based on the external environment information.

[0119] In addition, the information processing system 100 can generate a series of action-variable content and evaluate the effect of the series of updated action-variable content. Thereby, the information processing system 100 can consider the necessity of acquiring the update information when generating the series of action-variable content.

[0120] In addition, the information processing system 100 can evaluate the contribution degree of each of a plurality of pieces of update information, and determine the necessity of acquiring each of the plurality of pieces of update information based on the contribution degree of each of the plurality of pieces of update information. Thereby, the information processing system 100 can select only the update information that can be updated to a content generation model capable of generating, for example, more effective behavior-variable content.

[0121] Note that this embodiment is for facilitating the understanding of the present invention and is not for limiting the interpretation of the present invention. The present invention can be changed / improved without departing from its gist, and equivalents thereof are also included in the present invention.

[0122] In the present invention, the "section" does not merely mean a physical means, and also includes a case where the function of the "section" is realized by software. Also, even if the function of one "section" or device is realized by two or more physical means, devices, or software, or the functions of two or more "sections" or devices are realized by one physical means, device, or software, it is also acceptable.

Description of Reference Numerals

[0123] 100 Information processing system, 110 Storage unit, 120 Acquisition processing unit, 130 Update information acquisition unit, 140 Behavior characteristic acquisition unit, 150 Content generation unit, 160 Content evaluation unit, 170 Contribution degree evaluation unit, 180 Acquisition necessity determination unit, 190 Content output unit, 195 Model update unit, 200 Information processing apparatus

Claims

1. A contribution evaluation unit that evaluates the contribution degree of update information for updating a content generation model for generating behavior modification content for causing a user to execute a predetermined target behavior, based on a contribution evaluation rule for evaluating the contribution degree of the update information to the update of the content generation model; A content evaluation unit that evaluates the effect of the updated behavior modification content obtained from the updated content generation model updated using the update information, based on a content evaluation rule for evaluating the effect of the behavior modification content on causing the user to execute a predetermined target behavior; An acquisition necessity determination unit that determines whether it is necessary to acquire the update information based on the contribution degree; An update information acquisition unit that acquires the update information based on the result of the determination of necessity; A model update unit that updates the content generation model using the acquired update information; Comprising; The contribution evaluation unit evaluates the contribution degree with respect to the evaluated effect; An information processing system.

2. Further comprising a behavior characteristic acquisition unit that acquires behavior characteristic information regarding the behavior characteristics of the user, included in the update information; The model update unit updates the content generation model using the behavior characteristic information; The information processing system according to claim 1.

3. The content evaluation unit further evaluates the effect of the pre-update behavior modification content obtained from the pre-update content generation model that is to be updated using the update information, based on the content evaluation rule; The contribution evaluation unit evaluates the contribution degree based on the effect of the pre-update behavior modification content and the effect of the post-update behavior modification content; The information processing system according to claim 1.

4. The contribution evaluation unit according to claim 1, further evaluating the contribution degree based on external environment information regarding an external environment related to the execution of the predetermined target behavior.

5. The behavior modification content includes a series of behavior modification contents including behavior modification contents corresponding to each of a plurality of behaviors to be executed until the predetermined target behavior; The content evaluation unit evaluates the effect of the series of post-update behavior modification contents obtained from the post-update content generation model; The information processing system according to claim 1.

6. The update information includes a plurality of pieces of update information. The contribution degree evaluation unit evaluates the contribution degree of each of the plurality of pieces of update information to the content generation model when each of the plurality of pieces of update information is used for updating. The acquisition necessity determination unit determines the necessity of acquisition of each of the plurality of pieces of update information. The update information acquisition unit acquires the update information determined to be necessary for acquisition among the plurality of pieces of update information. The information processing system according to claim 1 or 2.

7. A computer evaluates the contribution degree of the update information to the update of the content generation model based on a contribution degree evaluation rule for evaluating the contribution degree of the update information for updating a content generation model for generating behavior-transforming content for causing a user to execute a predetermined target behavior to the content generation model, evaluates the effect of the updated behavior-transforming content obtained from the updated content generation model updated using the update information based on a content evaluation rule for evaluating the effect of the behavior-transforming content on causing the user to execute a predetermined target behavior, determines the necessity of acquisition of the update information based on the contribution degree, acquires the update information based on the result of the determination of the necessity, updates the content generation model using the acquired update information, wherein the evaluation of the contribution degree is an evaluation of the contribution degree to the evaluated effect, An information processing method.

8. In a computer evaluate the contribution degree of the update information for updating a content generation model for generating behavior-transforming content for causing a user to execute a predetermined target behavior to the update of the content generation model based on a contribution degree evaluation rule for evaluating the contribution degree of the update information to the update of the content generation model; evaluate the effect of the updated behavior-transforming content obtained from the updated content generation model updated using the update information based on a content evaluation rule for evaluating the effect of the behavior-transforming content on causing the user to execute a predetermined target behavior; determine the necessity of acquisition of the update information based on the contribution degree; acquire the update information based on the result of the determination of the necessity; update the content generation model using the acquired update information; and cause the above to be executed. The evaluation of the contribution degree is an evaluation of the contribution degree to the evaluated effect. Program.

Images