Behavior modification device, behavior modification method, and behavior modification program

Abstract

This enables the appropriate implementation of behavioral change. [Solution] The behavior change device 100 inputs the results of a questionnaire based on the user's motivations for behavior, information about the user's profile, and the user's target behavior into a large-scale language model using prompts expressed in natural language text, thereby generating motivational information for the user's behavior change. The behavior change device 100 outputs the motivational information for the user's behavior change.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0001] The present invention relates to a behavior modification device, a behavior modification method, and a behavior modification program.

Background Art

[0002] In order to modify the behavior of a target person, motivation for behavior modification may be provided by presenting information about the person. For example, there is a conventional technique for assisting personal health management by determining a composite abnormality level indicating the degree of abnormality of a health condition based on an individual's health condition so that the individual can improve their own health management and improve their physical and mental state (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] The present invention has the effect of enabling appropriate behavioral change. [Brief explanation of the drawing]

[0007] [Figure 1] Figure 1 is a diagram illustrating the overall process of the behavioral modification device according to the embodiment. [Figure 2] Figure 2 shows the configuration of a behavioral modification device according to an embodiment. [Figure 3] Figure 3 is a table diagram showing an example of personal characteristics information according to the embodiment. [Figure 4] Figure 4 is a table diagram showing an example of the survey results according to the embodiment. [Figure 5] Figure 5 shows an example of a questionnaire according to this embodiment. [Figure 6] Figure 6 shows an example of the process according to the embodiment. [Figure 7] Figure 7 shows an example of the process according to this embodiment. [Figure 8] Figure 8 is a flowchart showing the processing performed by the behavioral modification device according to this embodiment. [Figure 9] Figure 9 is a flowchart showing the processing performed by the behavioral modification device according to this embodiment. [Figure 10] Figure 10 shows an example of the effects according to the embodiment. [Figure 11]Figure 11 shows an example of a cloud server that implements a behavioral change device according to this embodiment. [Modes for carrying out the invention]

[0008] Hereinafter, embodiments for carrying out the present invention (hereinafter referred to as "embodiments") will be described with reference to the drawings. However, each embodiment is not limited to those described below.

[0009] <Overview> (background) In order to change the behavior of a target individual, motivation for behavioral change may be provided by presenting information about that individual. For example, as a reference technology, there is a known technology that notifies individuals of the degree of abnormality in their health condition based on their health status, so that they can improve their own health management and improve their physical and mental condition.

[0010] However, the aforementioned reference technology only motivates individuals to improve their health by informing them of abnormalities based on their health status, without considering individual personalities, preferences, etc., and may not lead to effective behavioral change.

[0011] (Processing by the behavior modification device 100) Therefore, the behavioral change device 100 according to this embodiment uses a large-scale language model to generate "motivations related to the user's behavior," "information about the user's profile" and "target behavior of the user" that will use the service realized by the behavioral change device 100, and motivational information for the user's behavioral change based on these, and outputs them to the user.

[0012] The above-mentioned "motivation related to user behavior" includes "Motivation Outcome Map" etc. (for example, refer to Reference 1). In the Motivation Outcome Map, when plotting the target behavior with the outcome obtained from the behavior on the horizontal axis and the motivation, which is the degree of the feeling of wanting to do it, on the vertical axis, the first quadrant means "having the desire to do it and being able to obtain the outcome", the second quadrant means "having no desire to do it but being able to obtain the outcome", the third quadrant means "having no desire to do it and not being able to obtain the outcome or obtaining a negative outcome", and the fourth quadrant means "having the desire to do it but not being able to obtain the outcome or obtaining a negative outcome".

[0013] The "information related to the user profile" is information related to the user's persona such as the user's personality, values, hobbies, etc., and may be referred to as "personal characteristic information" in the following items. Also, the "information for motivating behavior change of the user" is information that supports the motivation for behavior change for the user, and may be referred to as "motivation information" in the following items.

[0014] Also, the "user's target behavior" is the behavior targeted for behavior change of the user (the user's target behavior), and includes various human activities such as exercise, diet, bathing, shopping, enjoyment of leisure, sleep, work, self-fulfillment, etc. Also, in addition to the above-mentioned "target behavior", the user's behavior without explicitly indicating the target of behavior change is also included in the category of the "user's target behavior".

[0015] And the behavior change device 100 according to the present embodiment can move the RA existing in the second quadrant to the first quadrant by generating "motivation information (motivation message)" that incorporates the element of "behavior (FA) that the user originally likes" into the "behavior (RA) that the user does not like but understands that they should do" existing in the second quadrant based on the motivation related to the user's behavior shown by the Motivation Outcome Map etc. as described above.

[0016] (Reference 1): Preliminary Study on Dopamine Secretion-Promoting Motivation Message Generation, Reiko Araga, Yuri Katagiri, Junji Watanabe, <URL:https: / / www.interaction-ipsj.org / proceedings / 2024 / data / pdf / 1P-87.pdf>, <Search Date: August 20, 2024 (Tuesday)>

[0017] In addition, in this embodiment, "providing prior knowledge" means inputting predetermined information into the large language model in advance, and includes learning and tuning of the large language model, inputting information into the large language model, inserting or substituting information related to the prior knowledge into the prompt input to the large language model, and the like. For example, the behavior modification device 100 according to this embodiment can provide the acquired personal characteristic information, the received questionnaire results, the collected behavior data, etc. to a predetermined large language model.

[0018] Here, the overall image of the processing by the behavior modification device 100 will be described. FIG. 1 is a diagram for explaining the overall image of the processing of the behavior modification device 100 according to the embodiment. The behavior modification device 100 shown in FIG. 1 provides a technology for realizing the following information processing related to behavior modification.

[0019] The behavior modification device 100 inputs the questionnaire results based on the motivation related to the user's behavior, the user's personal characteristic information, and the user's target behavior into the large language model using a prompt expressed in natural language text, and generates motivation information for modifying the user's behavior ((1-1) and (1-2) in FIG. 1).

[0020] The behavior modification device 100 generates per-user motivation information according to the persona of the user that supports modifying the user's behavior by inputting a prompt including the above-mentioned "questionnaire results based on the motivation related to the user's behavior" and the user's personal characteristic information into the large language model.

[0021] The behavior modification device 100 outputs motivational information to the user (Figure 1 (2-1)). For example, the behavior modification device 100 outputs feedback messages, such as motivational messages tailored to the user, which are generated as motivational information (Figure 1 (2-2)).

[0022] In this way, the behavior change device 100 according to this embodiment inputs prompts including the results of a user-specific questionnaire and prompts including the user's persona into a large-scale language model to generate motivational messages tailored to the user. The behavior change device 100 then outputs the generated messages to the user, thereby further enhancing the user's intrinsic motivation. As a result, the behavior change device 100 has the effect of enabling appropriate behavioral change.

[0023] <Description of the behavior modification device 100> The configuration of the behavior modification device 100 according to this embodiment will now be described. Figure 2 is a diagram showing the configuration of the behavior modification device 100 according to this embodiment. As shown in Figure 2, the behavior modification device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0024] Although not shown in Figure 2, the behavioral modification device 100 may be equipped with an input unit such as a keyboard or mouse to receive input such as operations from an administrator. Furthermore, the behavioral modification device 100 may be equipped with a display or the like to show the user's personal characteristics information to an administrator.

[0025] (Communications Department 110) The communication unit 110 performs data communication related to the input of user personal characteristics information and survey results based on the user's motivations for behavior. The communication unit 110 also performs data communication related to the output of generated motivation information.

[0026] The communication unit 110 is implemented using a NIC (Network Interface Card) or the like, and controls communication via telecommunication lines such as a LAN (Local Area Network) or the Internet. The communication unit 110 can be connected to the network via wired or wireless connection as needed, and can send and receive information bidirectionally with terminal devices operated by the user or other external information processing devices.

[0027] (Storage unit 120) The memory unit 120 stores data and programs used for various processes by the control unit 130, as well as various data acquired through the operation of the control unit 130. The memory unit 120 is implemented using semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or storage devices such as hard disks and optical discs. As shown in Figure 2, the memory unit 120 also includes a personal characteristics information DB 121, a questionnaire results DB 122, behavioral data DB 123, and a generation model DB 124.

[0028] (Personal characteristics information DB121) The Personal Characteristics Information DB121 is a database that stores information about the user's personality (personal characteristics information) used to generate motivational information tailored to the user's persona. Specifically, the Personal Characteristics Information DB121 stores information such as user identification information, user attribute information, user psychology information, user health information, and user cognition information (cognitive bias).

[0029] Here, an example of personal characteristics information stored in the personal characteristics information DB121 will be explained using Figure 3. Figure 3 is a table diagram showing an example of personal characteristics information according to the embodiment. As shown in Figure 3, the personal characteristics information DB121 stores information related to each item, such as "No," which is information that identifies individual data included in the personal characteristics information, "user identification information," "attributes," "psychology," "healthcare," and "cognitive bias," in a table format or the like. The letters "A to E" written in each item of the table diagram shown in Figure 3 are legends for the information included in each item.

[0030] The "user identification information" item mentioned above includes information that identifies a user who uses the service implemented by the behavioral modification device 100, and is represented, for example, by a combination of predetermined strings, numbers, symbols, etc. Note that the user identification information may be stored after information that could identify the individual user has been deleted or replaced using publicly known technology.

[0031] The "Attributes" section contains user attribute information, such as the user's age, gender, place of residence, family information, annual income, education level, occupation, height, weight, life events, hobbies and preferences, past experiences, and consumer willingness. The "Psychology" section contains information about the user's psychology, such as the Big Five personality traits (extraversion, conscientiousness, agreeableness, openness, and neuroticism), the Dark Triad, life satisfaction, behavioral synthesis, 10 basic values, and other information that expresses the user's personality tendencies. The "Healthcare" section contains information about the user's health, such as exercise time, number of exercise days, duration of exercise, exercise habits, and other information related to the user's health. The "Cognitive Biases" section contains information about the user's cognition, such as probability weighting, value, loss aversion, time discounting, present bias, and other information related to the user's cognitive biases.

[0032] (Survey results DB122) The survey results DB122 is a database that stores information related to the motivations behind user behavior, based on survey results conducted on users. Specifically, the survey results DB122 stores information such as user identification information, user-preferred activities (FA: Favorite Activity), and activities that users dislike but understand they should perform (RA: Reluctant Activity).

[0033] Here, an example of survey results stored in the survey results DB122 will be explained using Figure 4. Figure 4 is a table diagram showing an example of survey results according to this embodiment.

[0034] The survey results DB122 stores the data in a table format, associating "No," which is information that identifies individual data included in the survey results, with "User Identification Information," "FA," and "RA." For example, as shown in Figure 4, the survey results DB122 can store the survey results identified by No "1," with user identification information "A," FA "Exploration," and RA "Exercise." The survey results described above show that "Exploration" is an activity that user A inherently prefers, and "Exercise" is an activity that user A dislikes but understands they should do.

[0035] (Behavioral data DB123) The behavioral data DB123 is a database that stores behavioral data, including information about behavioral goals and behavioral results entered by the user. The "behavioral goals" mentioned above are goals set by the user themselves regarding what actions they will take, and may include information such as "walk 10,000 steps per day." The "behavioral results" show the results of the user's actual actions in relation to the behavioral goals mentioned above, and may include information such as "On [Month] [Day], I walked 10,000 steps."

[0036] For example, the behavioral data DB123 can store behavioral goals ("daily or weekly exercise goals") and behavioral results ("daily or weekly exercise results") as behavioral data. It should be noted that the "exercise goals and results" mentioned above are merely examples, and the behavioral data in this embodiment is not limited. For example, "behavior" in behavioral data may include various human activities such as eating, bathing, shopping, leisure activities, sleeping, working, and self-actualization.

[0037] (Generative model DB124) The generative model DB124 is a database that stores predetermined generative models used in the generation process by the generation unit 134 described later. For example, the generative model DB124 can store large-scale language models as generative models.

[0038] Specifically, the behavioral modification device 100 according to this embodiment can use at least one of the following as a large-scale language model: "ChatGPT®", a large-scale language model possessing general knowledge, and "tsuzumi®", a predetermined large-scale language model on which adapter tuning is performed (see, for example, references 2 and 3).

[0039] (Reference 2):ChatGPT(OpenAI),<URL:https: / / openai.com / chatgpt> ,<Searched on August 20, 2020> (Reference 3): NTT version of large-scale language model "tsuzumi",<URL:https: / / www.rd.ntt / research / LLM_tsuzumi.html> ,<Searched on August 20, 2020>

[0040] (Control unit 130) Now, let's return to Figure 2 and continue the explanation. The control unit 130 has an internal memory for temporarily storing programs and processing data that define various processing procedures of the behavioral modification device 100, and is realized by electronic circuits such as a CPU (Central Processing Unit) and an MPU (Micro Processing Unit), and integrated circuits such as an ASIC (Application Specific Integrated Circuit) and an FPGA (Field Programmable Gate Array). As shown in Figure 2, the control unit 130 has an acquisition unit 131, a reception unit 132, a collection unit 133, a generation unit 134, and an output unit 135.

[0041] (Acquisition part 131) The acquisition unit 131 acquires the user's personal characteristics information from an external information processing device, etc., via the communication unit 110 described above. The acquisition unit 131 then stores the acquired personal characteristics information in the personal characteristics information DB 121.

[0042] (Reception desk 132) The reception unit 132 receives information regarding the results of a survey conducted with the user that is based on the user's motivations related to their actions. The reception unit 132 then stores the information regarding the received survey results in the survey results DB 122 as survey results.

[0043] Specifically, the reception unit 132 displays questions to the user based on natural language text, prompting them to answer a questionnaire about the user's naturally preferred behaviors (FA) and behaviors the user dislikes but understands they should perform (RA). The reception unit 132 then receives the user's input information via their terminal device, etc., in response to the displayed questions as questionnaire results based on the user's motivations for their behavior.

[0044] Here, an example of a question displayed by the reception unit 132 will be explained using Figure 5. Figure 5 is a diagram showing an example of a questionnaire according to the embodiment. Figure 5 shows a question about FA (Figure 5(1)) and a question about RA (Figure 5(2)).

[0045] As shown in Figure 5(1), the reception unit 132 displays questions regarding FA to the user via a terminal device or the like. Specifically, as shown in Figure 5(1-1), the reception unit 132 displays a question prompting the user to input their preferred behavior.

[0046] In the example shown in Figure 5 (1-1), the reception unit 132 displays a question to the user, such as "Please tell us what activities you find enjoyable." Next, the reception unit 132 receives the user's answer, "Exploration," based on the question. Subsequently, the reception unit 132 stores the received answer, "Exploration," in the "FA" field of the survey results DB 122.

[0047] Furthermore, as shown in Figure 5 (2), the reception unit 132 displays questions regarding RA to the user via a terminal device or the like. Specifically, as shown in Figure 5 (2-1), the reception unit 132 displays a question prompting the user to input their preferred behavior.

[0048] In the example shown in Figure 5 (2-1), the reception unit 132 displays a question to the user such as, "Please tell us about activities, exercise habits, and eating habits that you think you should do but are reluctant to do." Next, the reception unit 132 receives the answer "exercise" entered by the user based on the question. Then, the reception unit 132 stores the received answer "exercise" in the "RA" item of the survey results DB 122.

[0049] (Collection Section 133) The collection unit 133 collects behavioral data, including the user's behavioral goals and the results of the user's actions. The collection unit 133 then stores the collected behavioral data in the behavioral data DB 123.

[0050] For example, the collection unit 133 can collect information regarding behavioral goals entered by the user into their terminal device via the communication unit 110 described above. In addition, the collection unit 133 can collect information regarding the results of the user's exercise, diet, sleep, etc., which are automatically collected by the user's terminal device, via the communication unit 110 described above.

[0051] (Generation unit 134) The generation unit 134 inputs predetermined prompts to a large-scale language model in a multi-step process to generate motivational information that corresponds to the user's motivations for behavior.

[0052] Specifically, the generation unit 134 first inputs a prompt, expressed in natural language text, into a large-scale language model. This prompt includes information about the user's personality, which includes at least one of the following: behaviors the user inherently prefers (FA), behaviors the user dislikes but understands they should perform (RA), user attribute information, information about the user's psychology, information about the user's health, and information about the user's cognition, as well as a command to generate a motivational message. The generation unit 134 then generates a motivational message as motivational information.

[0053] Furthermore, the generation unit 134 can use prompts expressed in natural language text such as, "Generate advice to increase motivation to practice the following target behaviors. Target behaviors = ..." Here, the "example of target behavior" mentioned above can be substituted with, for example, "increase the number of steps taken each day."

[0054] Furthermore, the generation unit 134 can generate user-specific motivational information using a large-scale language model provided as prior knowledge from the behavioral data collected by the collection unit 133. As a result, the generation unit 134 can generate motivational information for target users that corresponds to behavioral data such as "behavioral goals and behavioral results."

[0055] (Output section 135) The output unit 135 outputs the motivation information generated by the generation unit 134 to the user. Specifically, the output unit 135 outputs to the user the motivation message included in the motivation information, the behavioral goals set by the user and the degree of achievement of those behavioral goals, and predetermined incentive information.

[0056] The "motivational messages included in the motivational information" mentioned above are messages that enable intrinsic motivation for a user's actions by partially substituting or modifying actions that the user understands they should do but is reluctant to do with actions that the user inherently enjoys.

[0057] For example, the output unit 135 outputs a motivational message to the user, such as "If you stop by places that interest you, your step count will naturally increase, and you may meet other explorers," along with a feedback message that includes the behavioral goal "10,000 steps / day," the degree of achievement "100% (goal achieved)," and incentive information such as "points awarded."

[0058] (An example of processing) From here, an example of processing by the behavior modification device 100 will be described using Figures 6 and 7. Figures 6 and 7 are diagrams illustrating an example of processing according to the embodiment. Figure 6 is a diagram illustrating an example of the generation and output of a motivational message by the behavior modification device 100. Figure 7 is a diagram illustrating an example of the generation and output of a feedback message using behavioral data by the behavior modification device 100.

[0059] (Example 1) First, we will use Figure 6 to explain an example of generating and outputting motivational messages.

[0060] The behavioral change device 100 (acquisition unit) acquires personal characteristic information of the target user, such as "male in his 30s," "extroversion," "lack of exercise," and "loss aversion" (Figure 6 (1-1)). Next, the behavioral change device 100 (reception unit) receives FA "exploration" and RA "exercise" as questionnaire results based on the user's motivations for behavior (Figure 6 (1-2)).

[0061] The behavioral modification device 100 (generation unit) inputs prompts into a large-scale language model that include information such as "Considering individual characteristics information, partially replace or modify the user's 'exercise (RA)' with 'exploration (FA)' to generate motivational information" (Figure 6 (2)).

[0062] The behavioral change device 100 (generation unit) then generates motivational messages such as "If you stop by places that interest you, your step count will naturally increase, and you will also meet other explorers" as motivational information for each user (Figure 6 (3)).

[0063] The behavioral change device 100 (output unit) outputs the generated motivational message to the user (Figure 6 (4)).

[0064] Through the processing described above, the behavior modification device 100 in the first example can enhance dopamine-related pleasure factors and intrinsically motivate the user's behavior by outputting messages to the user that are expected to stimulate dopamine secretion based on each user's FA and RA.

[0065] (Second example) Next, an example of generating and outputting feedback messages using behavioral data will be explained using Figure 7. Specifically, the behavioral change device 100 (generation unit) receives prompts that include commands to generate motivational information for user behavior change based on the discrepancy between the user's behavioral goals and the user's behavioral results, in response to the large-scale language model for which behavioral data is provided as prior knowledge, and generates motivational information based on behavioral data.

[0066] For example, the behavior change device 100 generates motivational information using personal characteristic information and questionnaire results, similar to the first example (Figure 7 (1-1)). At that time, the behavior change device 100 also generates periodic feedback messages using the "behavioral goals" and "behavioral results" entered by the user (Figure 7 (1-2)).

[0067] As an example, the behavioral change device 100 (reception unit) receives a behavioral goal from the user, "10,000 steps / day (walk)" (Figure 7 (2-1)). The user then performs the actions for the first month in order to achieve the behavioral goal they set for themselves (Figure 7 (2-2)).

[0068] The behavioral change device 100 (collection unit) collects information on behavioral results from the user's terminal device, etc., which has set behavioral goals (Figure 7 (3)). Next, the behavioral change device 100 (generation unit) compares the accepted behavioral goals with the collected behavioral results to determine the degree of deviation. For example, the behavioral change device 100 (generation unit) compares the behavioral goal "10,000 steps / day (walk)" with the behavioral result "10,000 steps / day (walk)" and determines "no deviation (goal achieved)". Then, the behavioral change device 100 (generation unit) generates motivational information based on the determination result.

[0069] The behavior modification device 100 (output unit) outputs a generated motivational message (feedback message) for "Person A" (Figure 7 (4-1)). Furthermore, the behavior modification device 100 performs the above-described process at predetermined intervals (month 1, month 2, etc.) to periodically generate and output feedback messages (Figure 7 (4-2)).

[0070] Through the process described above, the behavioral change device 100 in the second example can provide intrinsic motivation for the user's behavior by periodically outputting feedback messages to the user based on whether or not the behavioral results are in line with the behavioral goals set by the user.

[0071] (Procedure for processing by the behavior modification device 100) Next, the processing procedure implemented by the behavioral modification device 100 according to this embodiment will be explained using Figures 8 and 9. Figures 8 and 9 are flowcharts showing the processing performed by the behavioral modification device 100 according to this embodiment. Figure 8 is a flowchart related to the storage of personal characteristic information, questionnaire results, behavioral data, etc. Figure 9 is a flowchart related to the generation and output of motivational information for each user.

[0072] First, Figure 8 will be used to explain the flowchart related to the storage of personal characteristics information, questionnaire results, behavioral data, etc. The acquisition unit 131 acquires personal characteristics information from an external information processing device, etc., and stores it in the personal characteristics information DB (S101). Next, the reception unit 132 receives the questionnaire results and stores them in the questionnaire results DB (S102).

[0073] If behavioral data is to be collected (Yes in S103), the collection unit 133 performs the collection of behavioral data and stores the collected behavioral data in the behavioral data DB (S104). Then, the behavioral modification device 100 terminates processing. On the other hand, if behavioral data is not to be collected (No in S103), the behavioral modification device 100 skips step S104 and terminates processing.

[0074] Next, using Figure 9, we will explain the flowchart related to the generation and output of motivational information for each user. The behavioral change device 100 receives a command to generate motivational information (S201).

[0075] The generation unit 134 generates user-specific motivation information (S202) based on the survey results stored in the survey results DB, personal characteristics information, and prompts including commands to generate motivation information.

[0076] The output unit 135 outputs the generated motivational information for each user (S203). Then, the behavioral modification device 100 terminates processing.

[0077] (effect) Next, we will explain the effects of the behavioral change device 100 according to this embodiment. Conventionally, in order to change the behavior of a target person, motivation for behavioral change is sometimes achieved by presenting information about that person. However, when providing motivation, the personality and preferences of each person are not taken into consideration, and this does not lead to effective behavioral change.

[0078] Therefore, the generation unit 134 of the behavior change device 100 according to this embodiment inputs the results of a questionnaire based on the user's motivations for behavior, the user's personal characteristics information, and the user's target behavior into a large-scale language model using prompts expressed in natural language text, thereby generating motivational information for the user's behavior change. The output unit 135 of the behavior change device 100 outputs the motivational information.

[0079] The above-described process enables the behavioral change device 100 according to this embodiment to appropriately achieve behavioral change. For example, the behavioral change device 100 generates and transmits feedback messages to each user that are expected to promote dopamine secretion in that user, according to the personality and characteristics of that user. This allows users to change their behavior more effectively than before and improves their motivation to continue the changed behavior.

[0080] Furthermore, the behavioral modification device 100 according to this embodiment achieves predetermined effects by performing the processes described below.

[0081] The reception unit 132 displays questions to the user based on natural language text, prompting them to answer a questionnaire about the behaviors the user inherently prefers and the behaviors the user dislikes but understands they should perform. The reception unit 132 receives the user's input in response to the displayed questions as questionnaire results based on the user's motivations for their behavior.

[0082] The process described above enables the behavioral change device 100 to appropriately understand the user's characteristics in order to appropriately change the user's behavior based on behavioral economics.

[0083] The generation unit 134 inputs a prompt into a large-scale language model in which the parameters of the same prompt are substituted with information about the user's personality, which includes at least one of the following: behaviors that the user inherently likes (FA), behaviors that the user dislikes but understands they should do (RA), based on the results of a questionnaire based on the user's motivations for behavior, information about the user's personality, information about the user's psychology, information about the user's health, and information about the user's cognition, and a command to generate a motivational message, thereby generating a motivational message as motivational information for each user.

[0084] Here, an example of the effects achieved by the behavioral modification device 100 according to this embodiment will be explained using Figure 10. Figure 10 is a diagram showing an example of the effects according to this embodiment. The message shown in Figure 10(1) is an example of a message generated based on conventional technology. The message shown in Figure 10(2) is a message generated by the behavioral modification device 100 according to this embodiment.

[0085] For example, in conventional technology, when generating feedback messages for a user, general and generic feedback messages such as "Walking while getting a sense of distance makes walks more enjoyable and increases your step count" are generated (Figure 10 (1-1)). On the other hand, the behavioral change device 100 according to this embodiment can generate user-specific feedback messages that take into account the user's FA "exploration" and RA "walking," such as "Other people are also increasing their daily step count by exploring new towns!" (Figure 10 (2-1)).

[0086] Therefore, the behavioral change device 100 can appropriately achieve behavioral change by enabling the generation of appropriate feedback messages for each user that take into account the user's personality and characteristics, which was difficult to generate with conventional technology.

[0087] The collection unit 133 collects behavioral data, including the user's behavioral goals and the user's behavioral results. The generation unit 134 receives prompts from a large-scale language model, which is provided with the behavioral data collected by the collection unit 133 as prior knowledge, including commands to generate motivational information based on the discrepancy between the user's behavioral goals and the user's behavioral results, and generates user-specific motivational information based on the behavioral data.

[0088] Through the process described above, the behavior change device 100 can generate feedback messages that provide appropriate motivation for the user to achieve the behavioral goals they have set, based on the discrepancy between the user's set behavioral goals and the results of their actions toward those goals. Therefore, the behavior change device 100 has the effect of enabling appropriate behavioral change.

[0089] The output unit 135 outputs to the user the motivational messages included in the user-specific motivational information generated by the generation unit 134, the behavioral goals set by the user, the degree of achievement of those behavioral goals, and predetermined incentive information.

[0090] Through the processing described above, the behavior change device 100 can output a message to motivate the user, along with the degree of achievement and incentive information, in order to change the user's behavior. As a result, it has the effect of enabling appropriate behavioral change in the user through motivation from the user understanding the deviation from the behavioral goals they have set for themselves, and motivation from the incentives obtained by achieving the goals.

[0091] <Variation> The following describes modifications that can be implemented by the behavioral modification device 100 according to this embodiment.

[0092] (Data, etc.) The personal characteristics information, behavioral data, questionnaire results, personas, prompts, motivational information, motivational messages, feedback messages, FA, RA, names of the functional parts of the behavioral change device 100, steps, processes, names of steps or processes, etc., used in the description of the above embodiment are merely examples and can be changed at will.

[0093] (Regarding the use of generative models) In this embodiment, the generative model (large-scale language model) used by the behavior modification device 100 is described as being stored in the generative model DB 124 of the memory unit 120, but this is not limited to this. For example, the behavior modification device 100 can access an external information processing device (server, etc.) and use a predetermined generative model.

[0094] (Regarding other processing examples) In this embodiment, the generation and output processes of motivational information that modifies user behavior were described using "exercise" as an example, but the embodiment is not limited to this. For example, the behavior modification device 100 can support behavioral changes based on various human activities such as eating, bathing, shopping, leisure activities, sleeping, working, and self-actualization.

[0095] Here, we will explain the processing by the behavior modification device 100 using the example of a user whose FA (Functional Agenda) is "to see beautiful scenery" and RA (Reasonable Action) is "to shop for necessities." In other words, this is an example of how the behavior modification device 100 generates and outputs motivational information to change the behavior of a user who "has to go shopping for necessities but doesn't feel like it" but "likes to see beautiful scenery."

[0096] The behavioral change device 100 (reception unit) receives the user's motivational response (FA) "to see beautiful scenery" and the user's motivational response (RA) "to shop for necessities" as survey results. Next, the behavioral change device 100 (generation unit) inputs the FA "to see beautiful scenery," the RA "to shop for necessities," the user's personal characteristics information, and a prompt including a command to generate a motivational message into a large-scale language model to generate a motivational message such as "The route XX for going shopping for necessities is said to have very beautiful scenery!"

[0097] As described above, the behavior change device 100 can efficiently generate motivational messages tailored to the user by inputting prompts into which the content of FA and RA, along with the user's personal characteristics information, have been substituted for each user. In other words, the behavior change device 100 can generate appropriate motivational information according to the "behavioral change" desired by the user, in addition to the aforementioned "exercise" and "shopping."

[0098] (Flowcharts, etc.) In flowcharts, each step may be rearranged as long as it does not create inconsistencies, and some steps may be omitted. Furthermore, conjunctions such as "next," "continue," "in addition," "at this time," and "on this occasion" in flowchart descriptions do not limit the order or timing of the processes in the flowchart.

[0099] <Hardware Configuration> Each component of the illustrated device is a functional concept and does not necessarily have to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions. Furthermore, each processing function performed by each device can be implemented, all or any part of it, by a CPU and the program that is analyzed and executed by that CPU, or by hardware using wired logic.

[0100] Furthermore, among the processes described in this embodiment, all or part of those described as being performed automatically can be performed manually using known methods. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the drawings can be arbitrarily changed unless otherwise specified.

[0101] <Program> In one embodiment, the various devices constituting the behavioral change device 100 can be implemented by installing a behavioral change program as packaged software or online software on a desired cloud server. For example, by having the above-mentioned behavioral change program executed on an information processing device, it can function as various devices constituting the behavioral change device 100. The cloud server referred to here includes desktop or notebook personal computers. In addition, the cloud server also includes mobile communication terminals such as smartphones and mobile phones, as well as slate terminals such as PDAs (Personal Digital Assistants).

[0102] Figure 11 shows an example of a cloud server that implements the behavioral change device 100 according to the embodiment. The cloud server 1000 has, for example, memory 1010 and CPU 1020. The cloud server 1000 also has a hard disk drive interface 1030, a disk drive interface 1040, a USB port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0103] Memory 1010 includes ROM (Read Only Memory) 1011 and RAM 1012. ROM 1011 stores, for example, a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090. The disk drive interface 1040 is connected to the disk drive 1100. For example, a removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The USB port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, a display 1130.

[0104] The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, the programs that define each process of the various devices constituting the behavioral modification device 100 are implemented as program modules 1093 in which executable code is written by the cloud server. The program modules 1093 are stored, for example, in the hard disk drive 1090. For example, a program module 1093 for performing the same processes as the functional configurations of the various devices constituting the behavioral modification device 100 is stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced by an SSD (Solid State Drive).

[0105] Furthermore, the configuration data used in the processing of the embodiment described above is stored as program data 1094 in, for example, memory 1010 or hard disk drive 1090. The CPU 1020 then reads the program module 1093 and program data 1094 stored in memory 1010 or hard disk drive 1090 into RAM 1012 as needed and executes the processing of the embodiment described above.

[0106] Furthermore, the program module 1093 and program data 1094 are not limited to being stored on the hard disk drive 1090; for example, they may be stored on a removable storage medium and read by the CPU 1020 via a disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored on another cloud server connected via a network (LAN, WAN (Wide Area Network), etc.). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other cloud server via the network interface 1070.

[0107] <Other> Although this embodiment has been described above, this embodiment is not limited by the description and drawings that constitute part of the disclosure. That is, all other embodiments, examples, and operational techniques made by those skilled in the art based on this embodiment are included in the scope of this embodiment. [Explanation of Symbols]

[0108] 100 Behavioral modification devices 110 Communications Department 120 Storage section 121 Personal characteristics information DB 122 Survey Results Database 123 Behavioral Data Database 124 Generative Model DB 130 Control Unit 131 Acquisition Department 132 Reception Department 133 Collection Department 134 Generation part 135 Output section

Claims

1. A generation unit that inputs the results of a survey based on the user's motivations for behavior, information about the user's profile, and the user's target behavior into a large-scale language model using prompts expressed in natural language text to generate motivational information for the user's behavioral change. An output unit that outputs motivational information for the user's behavioral change, A behavioral modification device characterized by having [a certain feature].

2. The generating unit is Based on the results of a questionnaire regarding the user's motivations for behavior, the system inputs a prompt, expressed in natural language text, into a large-scale language model. This prompt includes information about the user's personality, at least one of the following: behaviors the user inherently prefers, behaviors the user dislikes but understands they should perform, the user's attribute information, information about the user's psychology, information about the user's health, and information about the user's cognition, along with a command to generate a motivational message. The motivational message is then generated as motivational information for the user's behavioral change. The behavioral modification device according to feature 1.

3. It further includes a data collection unit that collects behavioral data, including user behavioral goals and user behavioral results. The generating unit is The behavioral data collected by the collection unit is provided as prior knowledge to a large-scale language model, and the prompt is input to the model, which includes a command to generate motivational information for the user's behavioral change based on the discrepancy between the user's behavioral goals and the user's behavioral results. Based on the aforementioned behavioral data, the system generates motivational information for the user's behavioral change. The behavioral modification device according to feature 2.

4. The output unit is, The motivational messages included in the motivational information for user behavior change generated by the generation unit, The system outputs to the user the behavioral goals set by the user, the degree to which those behavioral goals were achieved, and predetermined incentive information. A behavioral modification device according to any one of claims 1 to 3.

5. The system displays questions to the user, based on natural language text, prompting them to answer a survey about the behaviors they inherently prefer and the behaviors they dislike but understand they should perform. The system further includes a reception unit that receives the user's input information in response to the displayed question as survey results based on the user's motivations for their actions. A behavioral modification device according to any one of claims 1 to 3.

6. The generating unit is As the aforementioned large-scale language model, at least one of the following is used: a large-scale language model possessing general knowledge, and a predetermined large-scale language model on which adapter tuning is performed. A behavioral modification device according to any one of claims 1 to 3.

7. A method of behavioral change to be implemented by a behavioral change device, A generation process involves inputting survey results based on the user's motivations for behavior, information about the user's profile, and the user's target behavior into a large-scale language model using prompts expressed in natural language text to generate motivational information for the user's behavioral change. An output process that outputs motivational information for the user's behavioral change, A method for changing behavior, characterized by including [a specific element].

8. A generation step involves inputting survey results based on the user's motivations for behavior, information about the user's profile, and the user's target behavior into a large-scale language model using prompts expressed in natural language text to generate motivational information for the user's behavioral change. An output step that outputs motivational information for the user's behavioral change, A behavioral change program that runs on a cloud server.

Images