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 comprises: a first agent processing unit that acquires a plurality of responses obtained from each of a plurality of first agents having different behavioral characteristics as a result of applying the same behavioral modification content to each of the plurality of first agents; a second agent processing unit that causes a second agent having predetermined attributes to evaluate the behavioral modification content based on the plurality of responses obtained from each of the plurality of first agents; and an output unit that outputs the evaluation result of the behavioral modification content.

Description

Technical Field

[0005] ,

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

Background Art

[0002] In recent years, efforts to utilize an approach based on the theory of behavioral science that scientifically studies human behavior in service development have been spreading in various fields such as public policy, medicine, retail, and education. Also, systems for technically realizing the support of behavior modification 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 as a criterion for a plurality of stages that gradually lead to a behavior as a habituation goal, and each of the plurality of stages according to the stage index are defined, for each pair of adjacent stages, identifying the gap between the two stages constituting the pair, for each stage pair, at least one of the reason why the identified gap exists and the measure for causing a behavior change for a target person belonging to the lower stage to transition to the higher stage from the relationship information in which the relationship between the gap and the reason / measure is defined, and executing processing related to the reason / measure identified for each stage pair is described.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the system described in Patent Document 1 does not evaluate the effectiveness of behavioral change content, which is a measure to bring about behavioral change. Furthermore, even if the effectiveness of behavioral change content were to be evaluated, it would be necessary to analyze behavioral data measuring the behavior of multiple subjects when the behavioral change content was actually applied, making it difficult to evaluate the behavioral change content before actually applying it to subjects.

[0006] Therefore, the present invention aims to provide a technology that enables the evaluation of behavioral change content. [Means for solving the problem]

[0007] An information processing device according to one aspect of the present invention includes: a first agent processing unit that acquires a plurality of responses obtained from each of a plurality of first agents having different behavioral characteristics as a result of applying the same behavioral modification content to each of the plurality of first agents; a second agent processing unit that causes a second agent having predetermined attributes to evaluate the behavioral modification content based on the plurality of responses obtained from each of the plurality of first agents; and an output unit that outputs the evaluation result of the behavioral modification content.

[0008] An information processing method according to one aspect of the present invention includes an acquisition step of acquiring a plurality of responses obtained from each of a plurality of first agents having different behavioral characteristics as a result of applying the same behavioral modification content to each of a plurality of first agents; an evaluation step of having a second agent having predetermined attributes evaluate the behavioral modification content based on the plurality of responses obtained from each of the plurality of first agents; and an output step of outputting the evaluation result of the behavioral modification content.

[0009] A program according to one aspect of the present invention causes a computer to perform the following steps: an acquisition step of acquiring multiple responses obtained from each of a plurality of first agents having different behavioral characteristics as a result of applying the same behavioral modification content to each of the plurality of first agents; an evaluation step of causing a second agent having predetermined attributes to evaluate the behavioral modification content based on the multiple responses obtained from each of the plurality of first agents; and an output step of outputting the evaluation result of the behavioral modification content.

[0010] According to these embodiments, for example, by having another agent evaluate the results of applying behavioral change content to multiple agents with different behavioral characteristics, it becomes possible to evaluate behavioral change content without using a real-world human population.

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

[0012] According to this configuration, the behavioral characteristics of each agent group can efficiently reflect the behavioral characteristics of real-world human groups without overlap, making it possible to evaluate behavioral change content with a smaller number of agents.

[0013] In the above embodiment, each of the multiple first agents may be an agent that comprehensively reflects multiple independent concepts included in a predetermined classification method relating to behavioral change methods.

[0014] According to this configuration, the entire group of agents can comprehensively reflect the behavioral characteristics of each individual in a real-world human group, making it possible to evaluate behavioral change content more broadly and objectively.

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

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

Effects of the Invention

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

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] FIG. 4 is a diagram showing an example of the hardware configuration of the information processing terminal according to the present embodiment. [Figure 5] FIG. 5 is an explanatory diagram for explaining the evaluation flow of the behavior-variable content according to the present embodiment. [Figure 6] FIG. 6 is a diagram showing an example of the nudge message according to the present embodiment. [Figure 7] FIG. 7 is a diagram showing an example of the behavior characteristic data 40 according to the present embodiment. [Figure 8] FIG. 8 is a diagram showing an example of the attribute data according to the present embodiment. [Figure 9] FIG. 9 is a flowchart showing an example of the processing in the information processing apparatus according to the present embodiment. [Figure 10] FIG. 10 is a diagram showing an example of the classification of BCT.

Embodiment for Carrying Out the Invention

[0019] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The same elements are denoted by the same reference numerals, and redundant descriptions will be omitted.

[0020] In this embodiment, an agent is a system or software program for autonomously performing a specific task. The agent may be, for example, an agent that utilizes generative AI such as a large language model (LLM) or a large action model (LAM) (hereinafter referred to as an "AI agent"). The AI agent can interact with the environment, determine the next action to be executed based on the collected data, etc., and act autonomously.

[0021] Also, each agent can be given specific behavioral characteristics. For example, if the AI agent is set with behavioral characteristics such as being proactive and highly curious, the AI agent will tend to act actively and challenge new things based on the set behavioral characteristics. <System Overview> FIG. 1 is a diagram showing an example of the system configuration of the information processing system in this embodiment. In the example shown in FIG. 1, the information processing system 1 includes an information processing device 10, an information processing terminal 20, and a network N.

[0022] The information processing device 10 and the information processing terminal 20 can communicate with each other via the network N. In FIG. 1, one information processing device 10 and two information processing terminals 20 are illustrated, but the number of information processing devices 10 and information processing terminals 20 included in the information processing system 1 is not limited to this, and any number of devices can be included respectively.

[0023] The information processing device 10 is composed of, for example, a server device, a cloud computing system, an ASP (Application Service Provider), or a client-server model, but is not limited to these. The information processing terminal 20 is an information processing terminal device used by the user, and is, for example, a mobile phone (including a smartphone), a tablet, or a personal computer, but is not limited to these.

[0024] Network N is a communication network for communication between the information processing device 10 and the information processing terminal 20. For example, Network N may be the Internet, an intranet, a LAN, a mobile communication network, a dedicated line, a packet communication network, a telephone line, an internal corporate network, other communication lines, or a combination thereof. Furthermore, Network N may be wired or wireless.

[0025] <Hardware Configuration> Figure 2 shows an example of the hardware configuration of the information processing device 10 and the information processing terminal 20 in this embodiment. The information processing device 10 has a processor 11 such as a CPU (Central Processing Unit) and a GPU (Graphical Processing Unit), a storage device 12 such as memory, an HDD (Hard Disk Drive) and an SSD (Solid State Drive), a communication interface 13 for wired or wireless communication, an input device 14 for receiving input operations, and an output device 15 for outputting information. The input device 14 is, for example, a keyboard, a touch panel, a mouse and a microphone. The output device 15 is, for example, a display, a touch panel and a speaker. The information processing terminal 20 has a similar hardware configuration.

[0026] <Functional Block Configuration> (Information processing device 10) Figure 3 shows 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 can be realized using a storage device 12 provided by the information processing device 10.

[0027] Furthermore, the control unit 110 can be realized by the processor 11 of the information processing device 10 executing a program stored in the storage device 12. This program can be stored in a storage medium. The storage medium containing the program may be a non-transitory computer-readable medium. The non-transitory storage medium is not particularly limited, but may be, for example, a USB memory stick or a CD-ROM.

[0028] The information processing device 10 has the function of performing various communications with the information processing terminal 20 using the communication IF 13. The information processing device 10 is equipped with communication interfaces compliant with various communication standards and performs various information transmission and reception with external devices, including each information processing terminal 20. The information processing device 10 receives data transmitted from the information processing terminal 20 via the network N.

[0029] The memory unit 100 stores data necessary for the information processing device 10 to perform the determination process. The data includes behavioral characteristic data 40 related to the behavioral characteristics of people, attribute data 41 representing the attributes of agents, and behavioral change content 52 to encourage behavioral change in the target person.

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

[0031] The agent generation unit 111, the first agent processing unit 112, and the second agent processing unit 113 may be built on the information processing device 10, or they may be built to operate on an external system, such as a generation AI system (not shown) that can communicate via a network N.

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

[0033] The agent generation unit 111 has the function of generating multiple first agents 51, each possessing different behavioral characteristics, based on behavioral characteristic data 40. Each first agent 51 is independent of the others. The agent generation unit 111 can set the behavioral characteristics of each first agent 51 based on a specific concept of an academic classification method for behavioral change methods. The agent generation unit 111 may organize a group of agents in which each of the multiple first agents 51 completely and without overlapping concepts of an academic classification method for behavioral change methods. By organizing a group of agents in which the multiple first agents 51 as a whole completely, i.e., comprehensively, mimic the concepts of an academic classification method for behavioral change methods, the entire group of agents can comprehensively reflect the behavioral characteristics of an entire human population in the real world. This makes it possible to evaluate behavioral change content more broadly and objectively. Furthermore, by organizing a group of agents in which each of the multiple first agents 51 completely and without overlapping concepts of an academic classification method for behavioral change methods, each agent can efficiently and without overlapping reflect the behavioral characteristics of a human population in the real world. This makes it possible to evaluate behavioral change content with fewer agents. The multiple generated first agents 51 are also referred to as crowd AI 50.

[0034] While various behavioral characteristics can be applied, in this embodiment, it is preferable to set the behavioral characteristics of each agent based on an academic classification method for behavioral modification techniques. Examples of academic classification methods for behavioral modification techniques include the following: • Integrated Behavioral Model (IBM) • Health Belief Model (HBM) • Big Five personality traits

[0035] For example, when defining behavioral trait data 40 based on the Big Five behavioral traits, the behavioral trait data 40 quantifies the strength of the tendency for each factor of the Big Five behavioral traits (extraversion, agreeableness, conscientiousness, neuroticism, and openness to experience). A higher numerical value indicates a stronger tendency for that factor.

[0036] Furthermore, the agent generation unit 111 has the function of generating one or more second agents 61 having predetermined attributes based on attribute data 41. Attributes include, for example, gender, age, educational and professional history, annual income, lifestyle, family structure, hobbies and preferences, values, etc. By setting predetermined attributes, the agent generation unit 111 generates second agents that mimic specific individuals, such as politicians or men in their 30s living in urban areas. Note that one or more second agents 61 having predetermined attributes are collectively referred to as AI 60.

[0037] The first agent processing unit 112 applies behavioral change content 52 to each of the multiple first agents 51 and obtains multiple responses from each as a result of the application. For example, the first agent processing unit 112 constructs a simulation space that mimics human society on the generation AI system and applies the same behavioral change content 52 to each of the crowd AIs 50 generated by the agent generation unit 111. An example of behavioral change content 52 is a nudge message. Each first agent 51 constituting the crowd AI 50 responds to the nudge message by making a judgment such as taking action or not taking action, based on the behavioral characteristics set for each agent, and responds to the generation AI system.

[0038] The first agent processing unit 112 may measure the time taken to react, the amount of information consumed, and other factors for each reaction of the crowd AI 50 and each first agent.

[0039] The second agent processing unit 113 obtains response information 53 from the first agent processing unit 112. The second agent processing unit 113 evaluates the behavioral change content 52 by having one or more second agents 61 evaluate the response information 53.

[0040] In this embodiment, the behavioral change content 52 is content intended to cause the user to perform a predetermined target behavior. That is, the behavioral change content 52 is, for example, content that has the effect of changing the user's behavior.

[0041] An example of behavioral change content 52 is a nudge message. A nudge message is a single or multiple message that influences people's decision-making and encourages behavioral change through small triggers based on behavioral science, without significantly altering economic incentives or forcing behavior through penalties or rules. Note that behavioral change content 52 is not limited to text format including strings of characters and symbols, but may also include specified information such as audio, video, or images.

[0042] The second agent 61 outputs evaluations such as the percentage of first agents who performed the target behavior, and the reasons why first agents did not perform the target behavior and the percentage of those reasons.

[0043] The reception unit 114 receives instructions and input from the user. For example, the reception unit 114 can receive instructions and input from the user regarding the behavioral characteristics and attributes of the agent to be generated, as well as the behavioral change content 52.

[0044] The output unit 115 outputs the evaluation result 70 of the behavioral change content 52. The output unit 115 can, for example, transmit the evaluation result 70 of the behavioral change content 52 to the information processing terminal 20.

[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, a UI (User Interface) unit 202, and a control unit 203. The storage unit 200 can be implemented using a storage device provided by the information processing terminal 20. The communication unit 201, the UI unit 202, and the control unit 203 can be implemented by the processor of the information processing terminal 20 executing a program stored in the storage device. The program can be stored in a storage medium. The storage medium on which the program is stored may be a computer-readable non-temporary storage medium. The non-temporary storage medium is not particularly limited, but may be, for example, a USB memory or a CD-ROM.

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

[0047] The communication unit 201 has the function of performing various types of communication with the information processing device 10 using a communication interface. The communication unit 201 is equipped with communication interfaces compliant with various communication standards and performs various types of information transmission and reception with external devices, including each information processing device 10.

[0048] <Agent Processing> Figure 5 is an explanatory diagram illustrating the series of steps for evaluating the behavioral change content 52 in this embodiment. In this embodiment, the behavioral change content 52 is evaluated by collecting the results of each first agent 51 reacting to the same behavioral change content 52 and having each second agent 61 evaluate them.

[0049] First, the agent generation unit 111 organizes a first agent 51 and a second agent 61. Based on behavioral characteristic data 40, the agent generation unit 111 generates multiple first agents 51, each possessing different behavioral characteristics. The behavioral characteristic data 40 is data relating to human behavioral characteristics, such as data relating to a specific concept in an academic classification method of behavioral change techniques. Each first agent 51 is assigned different behavioral characteristics based on different behavioral characteristic data 40. The agent generation unit 111 also generates a second agent 61 having predetermined attributes based on attribute data 41.

[0050] The first agent processing unit 112 then applies the same behavioral modification content 52 to each of the multiple first agents 51. As a result of applying the content, the first agent processing unit 112 obtains response information 53 as multiple responses obtained from each of the first agents 51.

[0051] Next, the second agent processing unit 113 instructs the second agent 61 to evaluate the behavioral change content 52 based on the response information 53. The output unit 115 outputs the evaluation result 70 of the behavioral change content 52.

[0052] In this way, the second agent 61 evaluates the behavioral change content 52 based on the results of multiple responses to the behavioral change content 52 obtained from each of the multiple first agents 51, each possessing different behavioral characteristics. This allows for efficient evaluation of the behavioral change content 52 without using a real-world human population.

[0053] <Examples> Next, we will describe a more specific example. Below, we will illustrate a case where behavioral characteristics are defined based on factors defined in the integrated behavior model (hereinafter referred to as "IBM factors").

[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. The multiple IBM factors may include, for example, at least two of the following: Experiential attitude, Instrumental attitude, Injunctive norm, Descriptive norm, Perceived control, Self-efficacy, Knowledge, Skills, Salience of the behavior, Environmental constraints, and Habit.

[0055] The IBM factors shown in Figure 6 are merely illustrative and not limited to those illustrated. At least two of the IBM factors shown in Figure 6 may be encompassed and defined as higher-level IBM factors. For example, the empirical attitude and instrumental attitude mentioned above may be encompassed under "Attitude." Alternatively, one of the IBM factors shown in Figure 6 may be divided to define multiple lower-level IBM factors. A nudge message may be associated with any level of IBM factor.

[0056] As shown in Figure 6, multiple IBM factors may each be associated with an IBM factor identifier (hereinafter referred to as "IBM ID") and a nudge message. In Figure 6, for example, a nudge message is shown assuming the target is "residents of XX city" and the behavioral change is "encouragement to undergo a specific health checkup (hereinafter referred to as "specific health checkup")." The nudge messages associated with each IBM factor are generated to encourage behavioral change in the target person, taking each IBM factor into consideration. In Figure 6, one nudge message is associated with each IBM factor, but multiple nudge messages may be associated with each IBM factor. Also, the IBM ID that identifies each IBM factor is not limited to those shown. The generated nudge messages may be stored in the storage unit 100.

[0057] <Agent Composition> In this embodiment, the agent generation unit 111 defines behavioral characteristic data 40 based on IBM factors and generates a plurality of first agents 51. The agent generation unit 111 may assign a first agent ID to each of the generated first agents 51.

[0058] Furthermore, the agent generation unit 111 generates at least one second agent 61 having a different role based on predetermined attribute data 41.

[0059] Figure 7 shows an example of behavioral characteristic data 40 according to this embodiment. For example, in Figure 7, behavioral characteristic data 40 is shown for each first agent 51, with the first agent ID and the parameters of each IBM factor associated with it. The parameters assigned to each IBM factor are set in the range of 1 to 10, and the larger the numerical value of the parameter, the higher the contribution rate of the IBM factor to behavioral change, indicating that the IBM factor is more likely to be reflected in the response to the nudge message. Note that the behavioral characteristic data 40 is not limited to what is shown in Figure 7.

[0060] Figure 8 shows an example of attribute data 41 according to this embodiment. For example, in Figure 8, attribute data 41 is shown for each second agent 61, with the second agent ID, a persona representing a typical evaluator profile, and parameters for each IBM factor associated with it. Note that the attribute data 41 is not limited to what is shown in Figure 8. For example, information regarding the attributes of the second agent 61, such as the age and gender of the second agent 61, may be added.

[0061] <Crowd AI> The first agent processing unit 112 acquires each response from the crowd AI 50 as response information 53. Here, the response information 53 is, for example, information indicating the response from the crowd AI 50 to which a nudge message has been attached, and may be a response to the nudge message, a response regarding the situation related to behavioral change (for example, the status of a specific health checkup reservation), a response regarding the results of behavioral change (for example, the results of the specific health checkup), etc.

[0062] When the first agent processing unit 112 determines that a response by a first agent 51 has finished, it may include the total time from the start to the end of the response by the first agent 51, the total number of questions consumed, and the total amount of information in the response information 53.

[0063] Furthermore, the completion of the response of the first agent 51 may be determined, for example, by preparing a final question in the behavior change content 52, and the first agent processing unit 112 determining that a first agent 51 has responded to that final question. Alternatively, the first agent processing unit 112 may include the string "This is the last question" in the behavior change content 52 and determine the completion based on that string.

[0064] <Summary AI> The agent generation unit 111 generates a second agent 61 for use in the second agent processing unit 113 in the generation AI system. The number of agents in the second agent 61 is arbitrary.

[0065] Based on the response information 53, the second agent processing unit 113 instructs the second agent 61 to evaluate the behavioral change content 52 that has been applied to the crowd AI 50, for example, along the following evaluation axis. • 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. The difference in the amount of time or information consumed between the fastest first agent 51 and the slowest first agent 51 among the crowd of AI 50.

[0066] Furthermore, if there are multiple second agents 61, the second agent processing unit 113 may have each second agent 61 perform evaluations according to different evaluation axes. For example, second agent 61A of a certain second agent 61 may be made to evaluate the number of agents that were able to complete the target action. Alternatively, second agent 61B of a different second agent 61 may be made to evaluate the difference in the amount of time or amount of information consumed between the fastest and slowest first agent 51 in the first agent group 51. Additionally, second agent 61C of a different second agent 61 may be made to comprehensively evaluate the advantages and disadvantages of each according to the evaluation axes.

[0067] Furthermore, the second agent processing unit 113 may, for example, analyze whether or not there was a response to the nudge message and evaluate the validity of the text used in the nudge message by comparing texts with a high response rate with texts with a low response rate. <Processing flow> Next, an example of a process performed by the information processing device 10 will be explained with reference to the flowchart shown in Figure 9.

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

[0069] In step S102, the first agent processing unit 112 applies the same behavioral modification content 52 to each of the first agents 51 that make up the crowd AI 50, and obtains response information 53 from each of them as a result of the application.

[0070] In step S103, the agent generation unit 111 generates a second agent 61 having predetermined attributes, i.e., a combined AI 60.

[0071] In step S104, the second agent processing unit 113 instructs the summarizing AI 60 to evaluate the behavioral change content 52 based on the response information 53 obtained from the crowd AI 50.

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

[0073] Based on the above, in this embodiment, the second agent 61 evaluates the response information 53 obtained from multiple first agents 51 having different behavioral characteristics, thereby enabling the evaluation of the behavioral change content 52. This reduces predetermined costs such as time and effort without using a real-world group of people.

[0074] For example, on the information processing system 1, a questionnaire regarding aversion to vaccination is adopted as behavioral change content 52, and the crowd AI 50 is prompted to respond to this behavioral change content 52. Then, the summarizing AI 60 evaluates the time budget and the mental burden budget, which can be used to improve the architecture of the behavioral change content 52.

[0075] Furthermore, on the information processing system 1, a simulation space modeled after human society is generated, crowd AIs 50 are placed, and behavioral change content 52 is triggered based on the reflected behavioral changes. Then, the summary AI 60 evaluates the obtained reaction information 53, which allows for a more efficient evaluation of the behavioral change content 52.

[0076] Furthermore, each of the multiple first agents 51 belonging to the crowd AI 50 may be an agent that reflects multiple independent concepts included in a predetermined classification method for behavioral change methods without overlapping with each other, or it may be an agent that comprehensively reflects them.

[0077] Based on the above, each of the multiple first agents 51 can comprehensively generate a crowd AI 50 that mimics a specific concept of an academic classification method for behavioral change techniques, without duplication. As a result, by having the crowd AI 50 respond to behavioral change content 52, response information 53 can be obtained comprehensively from each first agent 51 without duplication. Furthermore, the summarizing AI 60 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 a user, and the second agent 61 may be an agent that reflects the predetermined specifications from the user received from the receiving unit 114.

[0079] The reception unit 114 may, for example, receive instructions from the user to request more detailed analysis results for the evaluation result 70 of the summary AI 60, and the second agent processing unit 113 may acquire these instructions and the summary AI 60 may perform the evaluation again in accordance with the user's instructions. Furthermore, the evaluation method and output method of the summary AI 60 may be changed according to instructions from the user. For example, the user may instruct the summary AI 60 to calculate the total amount of time spent by a particular first agent 51, and the second agent processing unit 113 may calculate the contents of that calculation.

[0080] Furthermore, the reception unit 114 may receive instructions from the user regarding the attributes of the second agent 61, and the agent generation unit 111 may reflect the received attributes in the second agent 61 according to those instructions. The instructions received by the reception unit 114 may be, for example, provided by inputting configuration instructions as prompts.

[0081] Based on the above, this configuration allows the system to receive instructions from the user and reflect those instructions in the crowd AI 50 and the summarizing AI 60, thereby enabling the system to carry out what the user wants and increasing user satisfaction.

[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 are not intended to limit it. The present invention can be modified or improved without departing from its spirit, and equivalents thereof are also included. Furthermore, the present invention can form various disclosures by appropriately combining the multiple components disclosed in the above embodiments or examples. For example, some components may be deleted from all the components shown in the embodiments. Furthermore, components may be appropriately combined in different embodiments. For example, in this embodiment, agent generation is performed on the generation AI system, but the method of generating agents is not limited to the generation AI system. Various proposals have been made for AI capable of generating text etc. based on predetermined information, and the agent generation unit 111 in this embodiment is not limited to known AI capable of generating text.

[0085] The AI ​​may be either machine learning-based or non-machine learning-based (rule-based). Furthermore, the AI ​​that generates the agent may be present in the information processing device 10, or, as in this embodiment, a generation AI system provided by an external system may be used. Examples of generation AI systems provided by external systems include ChatGPT, Google Bard®, and Claude®.

[0086] <Behavioral Characteristics Data and Other Examples> In the modified example, the Health Belief Model (HBM) is used as an example to explain a specific concept in the academic classification of behavior change methods. The Health Belief Model is a theory of health behavior in which the main factors that increase the likelihood of a person engaging in healthy behaviors are the perception of threats and the balance between benefits and drawbacks.

[0087] Recognizing a threat means feeling a sense of crisis that things are "not good" if they continue as they are. To feel such a sense of crisis, one must recognize both the "possibility" and the "seriousness" of the situation. Recognizing the possibility means feeling that there is a high probability that one will develop an illness or complications if things continue as they are. Recognizing the seriousness means feeling that if one were to develop an illness or complications, the consequences would be serious in terms of health, finances, society, etc. Balancing the benefits and drawbacks means that when considering the benefits of taking healthy actions and the drawbacks of taking those actions, one feels that the benefits outweigh the drawbacks.

[0088] The memory unit 100 may store behavioral characteristic data 40 to be reflected in each agent, which is data for each different behavioral characteristic of the factors defined in the Health Belief Model (HBM).

[0089] For example, a nudge message is a message intended for "residents of XX city" as the target and "encouraging participation in a specific health checkup (hereinafter referred to as "specific health checkup")" as the behavioral change. Nudge messages, which correspond to the factors defined in each health belief model (HBM), are generated to encourage behavioral change in the target, taking into account the factors defined in each health belief model (HBM). The memory unit 100 may store nudge messages that have been generated in advance.

[0090] For example, the target group was assumed to be "residents of XX city," and the behavioral change was assumed to be "receiving a specific health checkup (e.g., a medical examination)," but this is not limited to these examples. The target group is not limited to users of administrative services; they could also be users of various services such as English conversation classes or qualification exams. Furthermore, the behavioral change is not limited to the use of administrative services; it could also be the continuation of learning, the use of various services, etc. <Behavioral Characteristics Data BCTTv1>

[0091] The behavior change content 52, behavioral characteristic data 40, and / or attribute data 41 may be generated, for example, based on a behavior change technique (BCT). 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. However, the definition of BCTs is not limited to BCTTv1, and they may be defined in any way as long as they comprehensively cover behavior change techniques.

[0092] BCTTv1 defines 16 BCT groups: 1. Goals and planning, 2. Feedback and monitoring, 3. Social support, 4. Shaping knowledge, 5. Natural consequences, 6. Comparison of behavior, 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.

[0093] Figure 10 shows an example of BCT classification. In BCTTv1, each of the 16 BCT groups shown in Figure 10 contains one or more BCTs. For example, BCT group "5. Natural consequences" contains BCTs such as "5.5. Anticipated regret." Similarly, BCT group "10. Reward and threat" contains BCTs such as "10.11. Future punishment." Although not shown, other groups also contain one or more BCTs.

[0094] Furthermore, each BCT may have components, and the degree to which each BCT is present in a given content may be shown as a component value. Additionally, 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.

[0095] The behavioral changes promoted by the behavioral change content 52, behavioral characteristic data 40, and / or attribute data 41 are not limited to, but may include, for example, language learning, dieting, purchasing financial products offered by financial institutions, regular medical checkups, or use of public services. Furthermore, the behavioral change content 52 is not limited to being provided to the user by electronic means such as applications installed on the terminal, web pages, email, or short messages, but may also be provided to the user by other means (e.g., customer service, mail, etc.). In addition, the behavioral change content 52 may include, for example, text information related to a specific service (e.g., chat logs), videos, still images, audio of conversations, or data related to applications, but is not limited to these; it may be any information related to the content of the behavioral change.

[0096] When generating and evaluating behavioral change content 52, behavioral characteristic data 40, and / or attribute data 41, a coordinate system is generated with multiple behavioral change factors as axes, and a target coordinate or target area (hereinafter collectively referred to as the target area) is set in this coordinate system. Whether or not a user has undergone behavioral change may be evaluated by whether or not the user's coordinate in the coordinate system has approached the target area. Hereinafter, the distance calculated in this coordinate system will be referred to as the "Behavioral Scientific Distance (BSD)".

[0097] In this coordinate system, by setting the current coordinate and the target area that the intervention should aim for for each user, the behavioral science distance from the current coordinate to the target area can be represented by a multidimensional vector. Furthermore, it becomes possible to objectively and clearly visualize the behavioral change strategies (BCTs) that should be adopted to bridge this distance. In other words, a higher quality behavioral change content 52 is, for example, a behavioral change content 52 that further reduces the behavioral science distance from the current coordinate to the target area.

[0098] Furthermore, behavioral change factors may also be factors that motivate users to take target actions. Multiple behavioral change factors in the target field can be identified based on academic surveys or opinion surveys, theories of behavioral science, user persona development, or behavioral process maps. Examples of behavioral change factors include "Capacity," "Opportunity," and "Motivation" in the COM-B model, which is commonly used in behavioral science.

[0099] The IBM factors described above are merely examples, and higher-level factors encompassing the above IBM factors may be identified as behavioral change factors. For example, the above empirical attitude and instrumental attitude may be included in "Attitude." The above directive norms and descriptive norms may be included in "Perceived norm." The above sense of control over behavior and self-efficacy may be included in "Personal Agency." The above knowledge and skills may be included in "Knowledge." The importance of behavior may be included in "Importance," and environmental constraints may be included in "Friction." Alternatively, lower-level factors obtained by dividing the above IBM factors may be identified as behavioral change factors. In this embodiment, any factors related to human behavioral will may be adopted as behavioral change factors, such as factors defined in the COM-B model or behavioral models other than IBM.

[0100] The ease with which users respond to behavioral change factors can vary from person to person. That is, in some users, behavioral change may be more likely to occur due to behavioral change content 52 that strongly influences the first behavioral change factor, while in other users, behavioral change may be more likely to occur due to behavioral change content 52 that strongly influences the second behavioral change factor. Furthermore, even within the same user, the ease with which users respond to behavioral change factors can vary depending on the passage of time, the time and environment in which the behavioral change content 52 is presented, and the target behavior and the content of the behavioral change. This ease with which users respond to behavioral change factors can be described as a user's behavioral characteristic. Thus, the behavioral scientific distance at which behavioral change content 52 can exert its effect can vary depending on the user's behavioral characteristics. [Explanation of symbols]

[0101] 1…Information processing system, 10…Information processing device, 11…Processor, 12…Storage device, 13…Communication interface, 14…Input device, 15…Output device, 20…Information processing terminal, 40…Behavioral characteristics data, 41…Attribute data, 50…Crowd AI, 51…First agent, 52…Behavioral 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. A first agent processing unit that acquires multiple responses obtained from each of a plurality of first agents having different behavioral characteristics as a result of applying the same behavioral modification content to each of the plurality of first agents, A second agent processing unit that causes a second agent having predetermined attributes to evaluate the behavioral change content based on a plurality of responses obtained from each of the plurality of first agents, 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 an agent that reflects multiple independent concepts included in a predetermined classification method for behavioral change methods, without overlapping with each other. The information processing apparatus according to claim 1.

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

5. An acquisition step of obtaining multiple responses obtained from each of multiple first agents, each having different behavioral characteristics, as a result of applying the same behavioral modification content to each of the multiple first agents, An evaluation step in which a second agent having predetermined attributes evaluates the behavioral change content based on a plurality of responses obtained from each of the plurality of first agents, The output step includes outputting the evaluation results of the behavioral change content, An information processing method performed by an information processing device.

6. An acquisition step of obtaining multiple responses obtained from each of multiple first agents, each having different behavioral characteristics, as a result of applying the same behavioral modification content to each of the multiple first agents, An evaluation step in which a second agent having predetermined attributes evaluates the behavioral change content based on a plurality of responses obtained from each of the plurality of first agents, An output step that outputs the evaluation results of the behavioral change content, A program that causes a computer to execute something.

Images