Information processing device, information processing method, program

Abstract

The objective is to provide technology that enables the evaluation of behavioral change content. [Solution] The information processing device of the present invention controls each of a plurality of first agents having different behavioral characteristics. As a result of applying the same behavioral change content to the multiple first agents, A first agent processing unit that acquires multiple reactions obtained from each, and a unit having predetermined attributes The second agent receives a plurality of reactions obtained from each of the plurality of first agents. Based on the above, a second agent processing unit is used to evaluate the behavior change content, and the behavior It includes an output unit that outputs the evaluation results of the transformed content.

Description

Technical Field

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

Background Art

[0002] In recent years, approaches based on theories of behavioral science that scientifically study human behavior have been spreading in various fields such as public policy, medicine, retail, and education for service development. In addition, systems for technically realizing support for behavior modification and habituation of subjects in such various fields have also been studied (for example, Patent Document 1).

[0003] In the system described in Patent Document 1, various data including behavioral data measured for a plurality of subjects is analyzed, and based on the results of the analysis of the behavioral data, a stage index that is an index as a criterion for a plurality of stages that gradually lead to the target behavior of habituation, and each of the plurality of stages according to the stage index are defined, and for each pair of adjacent stages, the gap between the two stages constituting the pair is specified, and for each stage pair, at least one of the reason for the existence of the specified gap and the measure for causing a behavior change for the subject belonging to the lower stage to transition to the higher stage is specified from the 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.

[0004]

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

[0005] However, the system described in Patent Document 1 is a measure to bring about behavioral change. This does not evaluate the effectiveness of behavioral change content. Furthermore, even if behavioral change content Even when evaluating the effectiveness, it is necessary to actually apply behavioral change content to multiple subjects. It is necessary to analyze behavioral data that measures actions at a given time and to actually apply it to the target group. Previously, evaluating behavioral change content was difficult.

[0006] Therefore, the present invention provides a technology that enables the evaluation of behavioral change content. This is the purpose. [Means for solving the problem]

[0007] An information processing device according to one aspect of the present invention comprises a plurality of first agents having different behavioral characteristics. As a result of applying the same behavioral change content to each of the first A A first agent processing unit that acquires multiple reactions obtained from each of the gents, and a predetermined A second agent having the attribute obtained from each of the plurality of first agents A second agent processing unit evaluates the behavioral change content based on multiple responses. The system includes an output unit that outputs the evaluation results of the behavioral change content.

[0008] An information processing method according to one aspect of the present invention involves a plurality of first agents having different behavioral characteristics. As a result of applying the same behavioral change content to each of the first agents, An acquisition step to obtain multiple reactions obtained from each of the ions, and having predetermined attributes The second agent is based on multiple reactions obtained from each of the multiple first agents. This involves an evaluation step where participants evaluate the behavioral change content, and the evaluation results of the behavioral change content. It has an output step that outputs the following.

[0009] A program according to one aspect of the present invention comprises a plurality of first agents having different behavioral characteristics. As a result of applying the same behavioral change content to each of them, multiple first agents An acquisition step to obtain multiple reactions obtained from each of the to, and a to having predetermined attributes The second agent is based on multiple reactions obtained from each of the multiple first agents. The evaluation step involves having participants evaluate the behavioral change content, and the evaluation results of the behavioral change content are then recorded. The computer executes the output steps to be output.

[0010] According to these embodiments, for example, for multiple agents having different behavioral characteristics By having another agent evaluate the results of applying behavioral change content, It is possible to evaluate behavioral change content without using real-world human groups.

[0011] In the above embodiment, each of the plurality of first agents is a predetermined agent relating to a behavioral change method. An agent that reflects multiple independent concepts included in the classification method without overlapping with each other. It may be considered a to.

[0012] According to this configuration, the behavioral characteristics of each agent group are efficiently and without overlap in the real world. Because it can reflect the behavioral characteristics of human groups, it can be performed with fewer agents. It becomes possible to evaluate the behavior-variable content.

[0013] In the above aspect, each of the plurality of first agents is an agent that comprehensively reflects a plurality of independent concepts included in a predetermined classification method related to the behavior variation method. This may be the case.

[0014] According to this aspect, since it is possible to comprehensively reflect the behavior characteristics of each group of people in the real world as a whole group of agents, it becomes possible to evaluate the behavior-variable content more widely and objectively. It becomes possible to evaluate the behavior-variable content.

[0015] In the above aspect, it may further have a reception unit that receives a predetermined specified content from the user, and the second agent is an agent that reflects the predetermined specified content received from the user. This may be the case.

[0016] According to this aspect, by giving the second agent a role according to the specified content from the user and evaluating it, it becomes possible to enhance the acceptance of the evaluation result.

Effect of the Invention

[0017] According to the present invention, it is possible to provide a technology capable of evaluating behavior-variable content. This is achievable.

Brief Description of the Drawings

[0018] [Figure 1] FIG. 1 is a diagram showing an example of the system configuration of the information processing system in the present embodiment. [Figure 2] FIG. 2 is a diagram showing an example of the hardware configuration of the information processing apparatus and the information processing terminal in the present embodiment. [Figure 3] FIG. 3 is a diagram showing an example of the functional block configuration of the information processing apparatus in the present embodiment. [Figure 4] Figure 4 shows an example of the hardware configuration of an information processing terminal according to this embodiment. [Figure 5] Figure 5 is an explanatory diagram illustrating the evaluation process for behavioral change content according to this embodiment. [Figure 6] Figure 6 shows an example of a nudge message according to this embodiment. [Figure 7] Figure 7 shows an example of behavioral characteristics data 40 according to this embodiment. [Figure 8] Figure 8 shows an example of attribute data according to this embodiment. [Figure 9] Figure 9 is a flowchart showing an example of processing in the information processing device according to this embodiment. [Figure 10] Figure 10 shows an example of BCT classification. [Modes for carrying out the invention]

[0019] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The same symbol is used for each item, and redundant explanations are omitted.

[0020] In this embodiment, the agent is a system for autonomously performing a specific task. It is a computer or software program. The agent is, for example, a large-scale language model (L). Examples include LM (Large Language Model) and LAM (Large Action Model). It may be an agent that utilizes generative AI (hereinafter referred to as "AI agent"). The AI ​​agent interacts with the environment and, based on the collected data, determines the next action to take. They can make decisions and act autonomously.

[0021] Furthermore, each agent can be given specific behavioral characteristics. For example, AI agents If you set the agent's behavioral characteristics to be proactive and curious, the AI ​​agent Based on their defined behavioral characteristics, Gents take proactive action and embrace new challenges. They tend to behave in a way that involves moving within a range. <System Overview> Figure 1 shows an example of the system configuration of the information processing system in this embodiment. In the example shown in Figure 1, the information processing system 1 consists of an information processing device 10 and an information processing terminal 20 It is configured to include a network N.

[0022] The information processing device 10 and the information processing terminal 20 can communicate with each other via the network N. Figure 1 illustrates one information processing device 10 and two information processing terminals 20. However, the number of information processing devices 10 and information processing terminals 20 included in the information processing system 1 is This is not limited to this; each can include any number of devices.

[0023] The information processing device 10 is, for example, a server device, a cloud computing device, ASP (Application Service Provider), client It consists of, but is not limited to, server models. Information processing terminals 20 is an information processing terminal device used by a user, for example, a mobile phone terminal (smartphone This includes, but is not limited to, smartphones, tablets, or personal computers. No.

[0024] Network N is a communication network for communication between the information processing device 10 and the information processing terminal 20. It is a network. For example, network N can be the internet, an intranet, L AN, mobile communication networks, dedicated lines, packet communication networks, telephone lines, corporate networks, and others It may be a communication line, or a combination thereof. Also, network N is It doesn't matter whether it's wired or wireless.

[0025] <Hardware Configuration> Figure 2 shows the hardware configuration of the information processing device 10 and the information processing terminal 20 in this embodiment. This figure shows an example of the configuration. The information processing device 10 includes a CPU (Central Processing Unit), Processor such as GPU (Graphical Processing Unit), memory, HDD (Hard Disk) A storage device 12 such as a Drive and an SSD (Solid State Drive), which communicates via wired or wireless communication. Communication interface 13, input device 14 for accepting input operations, and information output It has an output device 15 that performs the following. The input device 14 is, for example, a keyboard, a touch panel. Examples include a screen, mouse, and microphone. Output device 15 is, for example, a display, touch These include panels and speakers. The information processing terminal 20 has a similar hardware configuration.

[0026] <Functional Block Configuration> (Information processing device 10) Figure 3 is a diagram showing an example of the functional block configuration of the information processing device 10 in this embodiment. The information processing device 10 includes a storage unit 100 and a control unit 110. The storage unit 100 is an information processing device. This can be achieved using the storage device 12 provided in the information processing device 10.

[0027] Furthermore, the control unit 110 controls the information processing device 10's processor 11, which stores information in the storage device 12. This can be achieved by executing the program. Furthermore, the program is It can be stored on a storage medium. The storage medium on which the program is stored is a computer. A non-transitory computer-readable medium. This is also acceptable. The non-temporary storage medium is not particularly limited, but examples include a USB memory stick or a CD. - A storage medium such as ROM may also be used.

[0028] The information processing device 10 performs various communications with the information processing terminal 20 using the communication IF 13. It has the function of providing a communication interface compliant with various communication standards. The system is equipped to send and receive various types of information with external devices, including each information processing terminal 20. Device 10 receives data transmitted from information processing terminal 20 via network N. .

[0029] The storage unit 100 stores the data necessary for the information processing device 10 to perform the determination process. The data includes behavioral characteristic data 40 related to human behavioral characteristics, and agent attributes. This includes attribute data 41 and behavioral change content 52 to encourage behavioral change in the target individuals. It can be done.

[0030] The control unit 110 provides various functions necessary for executing the determination process. 0 is the agent generation unit 111, the first agent processing unit 112, and the second agent It includes an agent processing unit 113, a reception unit 114, and an output unit 115.

[0031] Furthermore, the agent generation unit 111, the first agent processing unit 112 and the second agent The data processing unit 113 may be built on the information processing device 10, or it may be provided by an external system. As a generative AI system (not shown) that can communicate via network N, it operates on this system. It may be constructed.

[0032] For example, on a generation AI service such as ChatGPT (registered trademark), the agent generation unit 111, the ring in which the first agent processing unit 112 and the second agent processing unit 113 operate The boundary is constructed, and the agent generation unit 111, the first agent processing unit 112 and the second agent The processing in the input processing unit 113 may be executed.

[0033] The agent generation unit 111 generates agents with different behavioral characteristics based on the behavioral characteristics data 40. It has the function of generating multiple first agents 51. The first agents 51 interact with each other. They are independent of each other. The agent generation unit 111 is a specially designed academic classification method for behavioral change techniques. Based on the concept of fixed behavior, the behavioral characteristics of each first agent 51 can be set. The agent generation unit 111 generates multiple first agents 51, each of which is an academically-based behavioral change method. A group of agents may be assembled that completely and without overlapping the concepts of the classification method. The first agent 51, as a whole, completely omits the concept of the academic classification method for behavioral change methods, that is, By forming a comprehensive group of agents, the entire group of agents can create a network. In other words, it can reflect the behavioral characteristics of entire groups of people in the real world. This will enable a broader and more objective evaluation of behavioral change content. Each of the 51 agents uniquely mimics a concept from an academic classification system of behavioral change methods. By forming a group of agents, each agent can efficiently interact with real-world people without overlap. This allows for the reflection of the behavioral characteristics of the group in between. This reduces the number of agents required. This makes it possible to evaluate behavioral change content. Furthermore, multiple first A generated The Gent 51 is also called the crowd AI 50.

[0034] Various behavioral characteristics can be applied, but in this embodiment, each agent It is preferable to define the behavioral characteristics of the subject based on academic classification methods for behavioral change techniques. Examples of academic classification methods for dynamic transformation techniques include the following: • Integrated Behavioral Model (IBM) • Health Belief Model (HBM) • Big Five personality traits

[0035] For example, when defining behavioral characteristic data 40 based on the Big Five behavioral characteristics, The trait data 40 includes each factor of the Big Five behavioral traits (extraversion, agreeableness, conscientiousness, The strength of tendencies related to neuroticism (openness to experience) is quantified. A higher number indicates a greater tendency. This can be interpreted as indicating a strong tendency toward the relevant factor.

[0036] Furthermore, the agent generation unit 111 generates an agent with predetermined attributes based on the attribute data 41. It has the function of generating one or more second agents 61. Attributes include, for example, gender. Includes age, educational and professional history, annual income, lifestyle, family structure, hobbies and preferences, values, etc. The attribute generation unit 111 generates data for politicians and men in their 30s living in urban areas by setting predetermined attributes. This generates a second agent that mimics a specific person. This refers to a group of multiple second agents 61, also known as AI60.

[0037] The first agent processing unit 112 performs behavioral changes on each of the multiple first agents 51. After applying Content 52, the multiple reactions obtained from each of them are To acquire. The first agent processing unit 112, for example, simulates human society. A crowd AI is constructed on the AI ​​generation system and generated by the agent generation unit 111. The same behavioral change content 52 is applied to each of the 50. Behavioral change content 5 An example of 2 is a nudge message. Each first agent 51 makes up the crowd AI 50. Based on the behavioral characteristics set for each individual, they will take action in response to a nudge message. The system generates responses such as determining whether to cause or not cause an incident using an AI system.

[0038] The first agent processing unit 112 processes the responses of the crowd AI 50 and each of the first agents. You may also measure the time it takes to react, the amount of information consumed, etc.

[0039] The second agent processing unit 113 receives reaction information 53 from the first agent processing unit 112. The second agent processing unit 113 responds to one or more second agents 61. By having the user evaluate information 53, the behavioral change content 52 is evaluated.

[0040] In this embodiment, the behavior change content 52 refers to a predetermined target behavior directed at the user. This is content intended to encourage action. In other words, behavior change content 52 is an example. For example, it is content that has the effect of changing user behavior.

[0041] One example of behavioral change content is nudge messages. A change is when economic incentives are drastically altered, or when actions are enforced through penalties and rules. Without doing so, we influence people's decision-making through small triggers based on behavioral science. It is one or more messages that encourage change. Note that the behavior change content 52 is a string of characters. This is not limited to text format containing symbols, but also includes specified information such as audio, video, or images. That's good too.

[0042] The second agent 61, for example, the percentage of the first agent who performed the target action, The system outputs an evaluation showing the reasons why the agent did not perform the target action and the percentage of such cases.

[0043] The reception unit 114 receives instructions and input from the user. For example, the reception unit 114 receives user From the agent, the behavioral characteristics and attributes of the agent to be generated, as well as the behavioral change content It can accept instructions and input regarding T52.

[0044] The output unit 115 outputs the evaluation result 70 of the behavior change content 52. For example, the evaluation results 70 of the behavioral change content 52 are transmitted to the information processing terminal 20. It is possible.

[0045] (Information processing terminal 20) Figure 4 shows an example of the functional block configuration of the information processing terminal 20 according to this embodiment. The information processing terminal 20 includes a storage unit 200, a communication unit 201, and a UI (User Interface) unit 2 It includes 02 and the control unit 203. The storage unit 200 stores the storage device provided by the information processing terminal 20. This can be achieved using the following: Furthermore, the communication unit 201, the UI unit 202, and the control unit 203 This means that the processor of the information processing terminal 20 executes a program stored in the memory device. This can be achieved by [method]. Furthermore, the program can be stored on a storage medium. The storage medium containing the program is a computer-readable, non-temporary storage medium. It may also be a medium. Non-temporary storage mediums are not particularly limited, but for example, USB memory Alternatively, a storage medium such as a CD-ROM may be used.

[0046] The storage unit 200 stores various programs necessary for the control unit 203 to perform this information processing. Store data.

[0047] The communication unit 201 has functions to perform various communications with the information processing device 10 using a communication interface. It possesses. The communication unit 201 is equipped with communication interfaces compliant with various communication standards, and each information Various types of information are sent and received between the device and external devices, including the processing unit 10.

[0048] <Agent Processing> Figure 5 illustrates the sequence of steps for evaluating the behavioral change content 52 in this embodiment. This is an explanatory diagram for doing so. In this embodiment, the same behavioral change content 52 is used for each of the first A By collecting the results of the reaction to Gent 51 and having each of the second agents 61 evaluate them, Evaluate the 52 behavioral change content pieces.

[0049] First, the agent generation unit 111 generates the first agent 51 and the second agent 6 1 is formed. The agent generation unit 111 generates different based on the behavioral characteristics data 40. Multiple first agents 51 with behavioral characteristics are generated. Behavioral characteristic data 40 is a human This data pertains to behavioral characteristics, and for example, to specific concepts in academic classification methods of behavioral change techniques. This is the data. Each first agent 51 has different behavioral characteristic data 40. Different behavioral characteristics are set for each. In addition, the agent generation unit 111 has attributes Based on data 41, a second agent 61 having predetermined attributes is generated.

[0050] Then, the first agent processing unit 112 processes each of the multiple first agents 51. The same behavioral change content 52 is applied. The first agent processing unit 112 is applied. As a result, the reaction information is obtained as multiple reactions from each of the first agents 51. Obtain report 53.

[0051] Next, the second agent processing unit 113 sends reaction information 5 to the second agent 61. Based on 3, the behavior change content 52 is evaluated. The output unit 115 evaluates the behavior change content. Output the evaluation result 70 for T52.

[0052] Thus, obtained from each of the multiple first agents 51 having different behavioral characteristics Based on the results of multiple responses to the behavioral change content 52, the second agent 6 1 evaluates behavior change content 52. This uses a group of people in the real world. This allows for efficient evaluation of the 52 behavioral change content items.

[0053] <Examples> Next, we will describe more specific examples. The following describes the integrated behavioral model. An example of defining behavioral characteristics based on factors (hereinafter referred to as "IBM factors") is provided below.

[0054] Figure 6 shows an example of a nudge message according to this embodiment. As shown in Figure 6, A nudge message is associated with each of the multiple IBM factors. IBM factors include, for example, experiential attitude and instrumental attitude. tal attitude), injunctive norm, descriptive norm, Perceived control, self-efficacy, knowledge Ledger, skills, importance of the behavior, environmental constraints This may include at least two of the following: environmental constraints and habituation.

[0055] Note that the IBM factors shown in Figure 6 are merely examples and are not limited to those illustrated. At least two of the IBM factors shown are encompassed and defined as higher-level IBM factors. It is also acceptable. For example, the above-mentioned empirical attitude and instrumental attitude are included in "attitude". Alternatively, one IBM factor as shown in Figure 6 may be divided into multiple lower-level factors. IBM factors may be defined. Nudge messages should be associated with any level of IBM factors. I don't mind being kicked.

[0056] As shown in Figure 6, each of the multiple IBM factors has an IBM factor identifier (hereinafter referred to as " An IBM ID (or similar) and a nudge message may be associated with it. For example, the target group is "residents of XX city," and the behavioral change is "specific health checkup (hereinafter referred to as 'specific health checkup')." A nudge message is displayed that is intended to encourage people to undergo regular health checkups. The corresponding nudge messages encourage behavioral change in the target audience, taking into account each IBM factor. It is generated in this way. Note that in Figure 6, one nudge message is associated with each IBM factor. However, multiple nudge messages may be associated with each IBM factor. The IBM ID used to identify the M factor is not limited to those shown in the diagram. The message may be stored in the memory unit 100.

[0057] <Agent Composition> In this embodiment, the agent generation unit 111 generates behavioral characteristics based on IBM factors. Defines a -40 and generates multiple first agents 51. Agent generation unit 11 1 may assign a first agent ID to each first agent 51 that has been generated.

[0058] Furthermore, the agent generation unit 111 assigns different roles based on predetermined attribute data 41. This generates at least one second agent 61 having the following characteristics.

[0059] Figure 7 shows an example of behavioral characteristic data 40 according to this embodiment. For example, in Figure 7 For each first agent 51, the first agent ID and the parameters of each IBM factor are recorded. An example of behavioral characteristic data 40, to which the following are associated, is given. Parameters assigned to each IBM factor The parameter is set within the range of 1 to 10, and the higher the parameter value, the greater the behavioral change. The contribution rate of IBM factors increased, and IBM factors were reflected in the response results to nudge messages. This indicates that it will become easier. Note that the behavioral characteristics data 40 are not limited to those shown in Figure 7.

[0060] Figure 8 shows an example of attribute data 41 according to this embodiment. For example, in Figure 8, For each second agent 61, the second agent ID and the typical evaluator profile, Pel An example of attribute data 41 is shown, which associates Sona with the parameters of each IBM factor. Oh, attribute data 41 is not limited to what is shown in Figure 8. For example, the second agent 61 Information regarding the attributes of the second agent 61, such as age and gender, may be added.

[0061] <Crowd AI> The first agent processing unit 112 acquires each response of the crowd AI 50 as response information 53. Here, the response information 53 is, for example, from the crowd AI 50 to which a nudge message has been attached. This information shows the response, including the response to the nudge message and the situation regarding behavioral change. Responses (for example, the status of appointments for specific health checkups), responses regarding the results of behavioral changes (for example, specific health checkups) (Results of medical examination, etc.) may be helpful.

[0062] The first agent processing unit 112 determines that a response from a certain first agent 51 has finished. When making a determination, the total time from when the first agent 51 starts responding until it finishes, and The total number of questions consumed and the total amount of information obtained may be included in the response information 53.

[0063] Furthermore, the completion of the response of Agent 51 is indicated, for example, by the behavioral change content 5 The final question is prepared in section 2, and the first agent processing unit 112 is a first agent The session may be terminated if it is determined that To51 has responded to the final question. Furthermore, the first agent processing unit 112, for example, will input "final quality" to the behavior change content 52. The string "Question" may be included, and the end of the process may be determined based on that string.

[0064] <Summary AI> The agent generation unit 111 generates the AI ​​system using the second agent processing unit 113. Generate the second agent 61 to be used. The number of agents in the second agent 61 is left to the user. It is the intention.

[0065] The second agent processing unit 113, based on the reaction information 53, sends a message to the second agent 61. For example, the behavioral change content 52 applied to the crowd AI 50 was evaluated according to the following evaluation criteria. To value. • Number of first agents out of 50 AI crowds that successfully completed the target action • Total amount of time spent by crowd AI50 • The amount of time or information consumed by the slowest of the crowd AIs, Agent 51. • Of the crowd AI 50, the fastest first agent 51 and the slowest first agent 51 required Difference in time or amount of information consumed

[0066] Furthermore, if there are multiple second agents 61, the second agent processing unit 113 will process each agent 61. The two agents 61 may each perform evaluations according to different evaluation criteria. For example, Agent 61A of Agent 2 61 was able to complete the target action. The number of toes may be evaluated. Also, different second agents 61B This includes the amount of time required by the fastest and slowest first agent 51 among the first agent 51 group. Alternatively, the difference in the amount of information consumed may be evaluated. The two agents, Agent 61C, comprehensively evaluate their respective advantages and disadvantages according to the evaluation criteria. I'm willing to let them evaluate it.

[0067] Furthermore, the second agent processing unit 113, for example, responds to nudge messages. By analyzing responses and comparing texts with high and low response rates, nudge messages can be developed. The appropriateness of the wording used in the page may be evaluated. <Processing flow> Next, refer to the flowchart shown in Figure 9 for an example of a process performed by the information processing device 10. I will explain while shining a light on it.

[0068] In step S101, the agent generation unit 111 generates agents with different behavioral characteristics. The first agent 51, i.e., the crowd AI 50, is generated.

[0069] In step S102, the first agent processing unit 112 configures the crowd AI 50. The same behavioral change content 52 is applied to each of the first agents 51, and As a result, reaction information 53 obtained from each is acquired.

[0070] In step S103, the agent generation unit 111 generates a second agent having predetermined attributes. Generate Agent 61, which is the summary AI60.

[0071] In step S104, the second agent processing unit 113 sends the group AI60 to the group Based on the response information 53 obtained from the AI ​​50, the behavioral change content 52 is evaluated. .

[0072] In step S105, the output unit 115 outputs the evaluation result 70 of the behavior change content 52. Outputs.

[0073] Based on the above, in this embodiment, from a plurality of first agents 51 having different behavioral characteristics The second agent 61 evaluates the response information 53 obtained, thereby creating behavioral change content. It is possible to perform 52 evaluations. This allows for the use of real-world human groups without the need for such evaluations. This can reduce certain costs such as time and effort.

[0074] For example, on information processing system 1, behavioral change content 52 is used for vaccination. A questionnaire regarding aversion to the subject was used, and the behavioral change content was assessed by the crowd AI50. The T52 is activated. Then, the summary AI60 evaluates the time budget and the mental load budget. This can be used to improve the architecture of the behavioral change content 52.

[0075] Furthermore, on information processing system 1, a simulation space modeled after human society is generated, A crowd AI 50 is deployed, and based on the reflected behavioral changes, behavioral change content 52 is generated. Then, by having the AI60 evaluate the reaction information 53 obtained, it becomes more efficient. This allows for the evaluation of behavioral change content 52.

[0076] Furthermore, each of the multiple first agents 51 belonging to the crowd AI 50 is a behavioral change agent. It reflects multiple independent concepts included in a prescribed classification system of law without overlapping with each other. It may be an agent that has been partially implemented, or it may be an agent that comprehensively reflects the data.

[0077] Based on the above, each of the multiple first agents 51 comprehensively, without overlap, It is possible to generate crowd AI50 that mimics specific concepts of academic classification methods for behavioral change techniques. As a result, by having the crowd AI 50 respond with behavioral change content 52, each first A From GENT 51, reaction information 53 can be obtained comprehensively without duplication. Furthermore, Summary AI60 can perform evaluations that take into account even a small number of responses.

[0078] The information processing device 10 includes a receiving unit 114 that receives predetermined specifications from the user. The second agent 61 receives the specified content from the user via the reception unit 114 and then... It would also be acceptable to have an agent project the image.

[0079] The reception unit 114 can, for example, receive requests from users for more detailed information regarding the evaluation results 70 of the summary AI 60. Upon receiving a request for detailed analysis results, the second agent processing unit 113 takes the request into consideration. If successful, the summary AI60 may re-evaluate according to the user's instructions. The evaluation methods and output methods for the 60 evaluation methods may be changed according to user instructions. For example, The user calculates the total amount of time spent by a specific first agent 51 in the summary AI 60. By issuing an instruction to output, the second agent processing unit 113 calculates its contents. That's good too.

[0080] Furthermore, the reception unit 114 receives instructions from the user regarding the attributes of the second agent 61. In accordance with the instructions, the agent generation unit 111 generates the second agent from the received attributes. This may also be reflected in the input 61. The instructions received by the reception unit 114 may, for example, be... This may also be done by inputting configuration instructions as a romptu.

[0081] Based on the above, this configuration accepts instructions from the user, and the crowd AI 50 and summary A By reflecting the instructions in I60, we can implement what the user wants and gain their satisfaction. It becomes possible to improve it.

[0082] This embodiment is provided to facilitate understanding of the present invention and does not limit the present invention. This invention is not intended to be interpreted. This invention may be modified or improved without departing from its spirit. In addition to obtaining it, the present invention also includes its equivalent.

[0083] Furthermore, in this invention, "part" does not simply mean a physical means, but rather its " This also includes cases where the functions of a "part" are implemented by software. Even if the functions of the device are realized by two or more physical means, devices, or software, The functions of two or more "parts" or devices are controlled by one physical means, device, or software. It may be implemented.

[0084] <Variation> The above embodiments or examples are provided to facilitate understanding of the present invention, and the present invention is intended to facilitate understanding of the present invention. This invention is not intended to be limited in its interpretation. This invention may be modified or improved without departing from its spirit. In addition to obtaining, the present invention also includes equivalents thereof. Furthermore, the present invention is based on the above embodiments or each Various disclosures can be formed by appropriate combinations of the multiple components disclosed in the examples. For example, some components may be removed from all the components shown in the embodiment. Furthermore, the components may be appropriately combined in different embodiments. For example, in this embodiment, The AI ​​system generates agents, but the method for generating agents is... This is not limited to generation AI systems. It applies to any AI capable of generating text, etc., based on predetermined information. Various proposals have been made regarding this, and in this embodiment, the agent generation unit 111 is text This is not limited to publicly known AI capable of generating stories.

[0085] Furthermore, the AI ​​can be either machine learning-based or non-machine learning-based (rule-based). The AI ​​that generates the agent may be provided by the information processing device 10, as in this embodiment. Alternatively, you may use a generation AI system provided by an external system. Examples of AI systems that generate data include ChatGPT and Google Bard (registration required). Generative AI systems such as (trademark), Claude (registered trademark), etc. may be used.

[0086] <Behavioral Characteristics Data and Other Examples> In the modified form, the health belief model is used as a specific concept in the academic classification of behavior change methods. Let's explain using (HBM) as an example. The Health Belief Model is one of the theories of health behavior, and it is used to explain how people The main factors that increase the likelihood of engaging in health-benefiting behaviors are the recognition of threats and the understanding of benefits and drawbacks. It's about balance.

[0087] Recognizing a threat means feeling a sense of crisis that things are "not good" if they continue as they are. To sense the situation, one must recognize both the "possibility" and the "seriousness" of the situation. Recognition means feeling that, if things continue as they are, you are highly likely to develop an illness or complications. Recognizing the seriousness of a situation means understanding the consequences if you were to develop an illness or complications, both in terms of your health and your finances. This is something that I feel is important from a social perspective, etc. What is the balance between the advantages and disadvantages? When considering the benefits and drawbacks of engaging in healthy behaviors, It's about feeling that the benefits outweigh the drawbacks.

[0088] The memory unit 100 contains different factors defined by the Health Belief Model (HBM). Each agent has 40 behavioral characteristic data points stored, which are digitized according to their specific behavioral characteristics and reflected in their respective systems. It's fine if it is done.

[0089] For example, a nudge message might target "residents of XX city" and target behavior change by "specifically" This message is intended to encourage people to undergo health checkups (hereinafter referred to as "specific health checkups"). The nudge messages that correspond to the factors defined in the Rusbelief Model (HBM) are: Encouraging behavioral change in participants by considering the factors defined in each Health Belief Model (HBM). It is generated in this manner. The memory unit 100 stores the previously generated nudge messages. That's fine.

[0090] For example, the target group could be "residents of XX city," and the behavioral change could be "specific health checkups (e.g., screenings)." While the initial intention was to include "medical consultations," it is not limited to this. The target group is not limited to users of administrative services. They may also be users of various services such as English conversation classes and qualification exams. Furthermore, behavioral change is a matter for the government. This is not limited to using the service; it may also include continuing to learn, using various other services, etc. <Behavioral Characteristics Data BCTTv1>

[0091] Behavioral change content 52, behavioral characteristics data 40 and / or attribute data 41 are, for example, It may be generated based on behavior change techniques (BCT). For example, BCTTv1 (Michie S, Richardson M, Johnston M, et al.: The behavior c hange technique taxonomy (v1) of 93 hierarchically clustered techniques: buildin an international consensus for the reporting of behavior change interventions. According to Ann Behav Med 2013; 46: 81~95.), 93 BCTs are defined in 16 groups. Furthermore, the BCT regulations are not limited to BCTTv1, but comprehensively cover methods of behavioral change. As long as it is done, it may be stipulated in any way.

[0092] BCTTv1 includes "1. Goals and planning" and "2. Feedback and monitoring". , "3.Social support", "4.Shaping knowledge", "5.Natural consequences" ”, “6.Comparison of behavior”, “7.Association”, “8.Repetition and substitution”, “9.Comparison of outcomes”, “10.Reward and threat”, “ 11.Regulation”, “12.Antecedents”, “13.Identity”, “14.Scheduled The 16 items are "consequences", "15. Self-belief", and "16. Covert learning". The BCT group is defined.

[0093] Figure 10 shows an example of BCT classification. In BCTTv1, as shown in Figure 10... Each of the 16 BCT groups contains one or more BCTs. For example, BCT group The section "5. Natural consequences" includes, for example, "5.5. Anticipated regret." BCT belongs to this group. Also, the BCT group "10. Reward and threat" includes, for example, This includes BCTs such as "10.11. Future punishment". Although not shown in the diagram, other groups include Each of these includes one or more BCTs.

[0094] Furthermore, each BCT has components, and the degree of each BCT contained in a given content is the component value. It may also be shown as follows. Furthermore, the sum of the component values ​​of each BCT belonging to the same BCT group is BCT It may also be shown as a group component value.

[0095] Behavioral change promoted by behavioral change content 52, behavioral characteristics data 40 and / or attribute data 41 Examples include language learning, dieting, purchasing financial products offered by financial institutions, regular medical checkups, and This includes, but is not limited to, the use of public services. It also includes behavioral change content. 52 refers to applications, web pages, emails, and other items installed on the device. This is not limited to information provided to the user by electronic means such as text messages, but also by other means ( For example, it may be provided to users through customer service, mail, etc. Also, behavioral change content. 52, for example, text information related to a specific service (e.g., chat logs), This includes moving images, still images, audio of conversations, and data related to applications, etc. This information is not limited to any specific type of information regarding the content of the behavioral change in question.

[0096] Generation and evaluation of behavioral change content 52, behavioral characteristics data 40, and / or attribute data 41. In evaluating the results, a coordinate system is generated with multiple behavioral change factors as axes, and the target is set within this coordinate system. Coordinates or a target area (hereinafter collectively referred to as the target area) are set. Then, Whether or not the user has undergone a behavioral change is determined by the coordinate system, where the user's coordinates approach the target area. It may be evaluated based on whether or not it occurred. Hereafter, the distance calculated in this coordinate system will be referred to as "behavioral distance." This is referred to as "Behavioral Scientific Distance (BSD)."

[0097] In this coordinate system, each user has their current coordinates and a target area that the intervention should aim for. By setting this, the behavioral scientific distance from the current coordinates to the target area is converted into a multidimensional vector. It allows for better expression. Furthermore, it allows for objectively selecting the BCT (Body Control Theory) that should be adopted to bridge this gap. This makes it possible to visualize the changes more clearly. In other words, it allows for higher quality behavioral change content. For example, behavioral change content that reduces the behavioral scientific distance from the current coordinate to the target area. It is Tsu52.

[0098] Furthermore, behavioral change factors may include, for example, factors that cause users to take a target action. Good. This includes academic research or opinion surveys, theories related to behavioral science, and user persona development. Based on the definition or behavioral process map, identify multiple behavioral change factors in the target field. It can be determined. As an example of a factor in behavioral change, COM- is commonly used in behavioral science. In the B model, "Capacity," "Opportunity," and "Motivation" are key factors. One example is "engineered."

[0099] The IBM factors mentioned above are merely examples, and there are higher-level factors that encompass these IBM factors. Factors may be identified as factors for behavioral change. For example, the above-mentioned empirical attitudes and instrumental attitudes are It may be included in "Attitude". The above-mentioned referential and descriptive norms are "norms (Pe The above sense of behavioral control and self-efficacy may be included in the "established norm". The above knowledge and skills may be included in "Personal Agency". The importance of an action is included in "importance" and the environment. The above constraints may be included in "Friction." Alternatively, the above IBM factors can be separated. The lower-level factors mentioned above may be identified as factors that influence behavioral change. In this embodiment, Factors that influence behavioral change include those defined by the COM-B model and behavioral models other than IBM's. Any factors relating to human behavioral will may be used.

[0100] The ease with which a user responds to behavioral change factors can vary from person to person. In the case of the first behavioral change factor, behavioral change content 52 strongly influences it. Behavioral change is likely to occur, and in other users, it strongly influences a second behavioral change factor. Behavioral change may be more likely to occur due to the behavioral change content 52. Also, the same user Even in the case of the behavioral change, the ease of responding to behavioral change factors changes over time, and the behavioral change content The timing of administering the 52 dose, the surrounding environment, and the content of the target behavior and behavioral change will vary. It is possible. The ease with which a user responds to behavioral change factors is expressed as a behavioral characteristic. There are cases where this is the behavioral science distance at which behavioral change content 52 can be effective. This can vary depending on the behavioral characteristics of the creature. [Explanation of Symbols]

[0101] 1... Information processing system, 10... Information processing device, 11... Processor, 12... Memory device, 13 ...Communication interface, 14...Input device, 15...Output device, 20...Information processing terminal, 40...Line Dynamic characteristics data, 41... Attribute data, 50... Crowd AI, 51... First agent, 52... Row Dynamic change content, 53…Reaction information, 60…Summary AI, 61…Second agent, 70 ...Evaluation results, 100...Storage unit, 110...Control unit, 111...Agent generation unit, 112... First agent processing unit, 113... Second agent processing unit, 114... Reception unit, 115... Output unit, 200...Storage unit, 201...Communication unit, 202...UI unit, 203...Control unit

Claims

1. The same behavioral change content is applied to each of the multiple first agents, each possessing different behavioral characteristics. As a result of applying the solution, a plurality of first agents obtained from each of the plurality of first agents A first agent processing unit that acquires the reaction, A second agent having predetermined attributes receives from each of the plurality of first agents. A second agent evaluates the behavioral change content based on the multiple responses obtained. Processing unit and An output unit that outputs the evaluation results of the behavioral change content, An information processing device equipped with the following features.

2. Each of the aforementioned plurality of first agents is included in a predetermined classification method relating to behavioral change methods. It is an agent that reflects multiple independent concepts without overlapping with each other. The information processing apparatus according to claim 1.

3. Each of the aforementioned plurality of first agents is included in a predetermined classification method relating to behavioral change methods. It is an agent that comprehensively reflects multiple independent concepts. The information processing apparatus according to claim 1.

4. It further includes a reception unit that receives specified information from the user, The second agent reflects the predetermined specified content received from the user. The agent The information processing apparatus according to claim 1.

5. The same behavioral change code is applied to each of the multiple first agents, each possessing different behavioral characteristics. As a result of applying the contents, obtained from each of the plurality of first agents Acquisition step to obtain multiple reactions, A second agent having predetermined attributes receives from each of the plurality of first agents. An evaluation step in which the behavioral change content is evaluated based on the multiple responses obtained, The output step includes outputting the evaluation results of the behavioral change content, An information processing method performed by an information processing device.

6. The same behavioral change code is applied to each of the multiple first agents, each possessing different behavioral characteristics. As a result of applying the contents, obtained from each of the plurality of first agents Acquisition step to obtain multiple reactions, A second agent having predetermined attributes receives from each of the plurality of first agents. An evaluation step in which the behavioral change content is evaluated based on the multiple responses obtained, An output step that outputs the evaluation results of the behavioral change content, A program that causes a computer to execute something.

Images