Proposal device and proposal method

Abstract

In order to propose a proposal content that enables a user to image a concrete action and put it into action in a system that assists a user's behavior modification, a proposal device proposes a proposal content for assisting the user's behavior modification. The proposal device includes: a reception unit that receives an activity preferred by the user and input of an action the execution of which by the user is wanted to be promoted; a generation unit that generates a proposal content that prompts the user's intrinsic motivation by partially replacing or modifying the action the execution of which by the user is wanted to be promoted with the activity preferred by the user; and a presentation unit that presents the proposal content to the user.

Description

Proposed device and proposed method

[0001] The present invention relates to a proposal device and a proposal method.

[0002] There are systems that support users in changing their behavior. For example, a technology is known that uses sensing to obtain lifestyle information, such as the user's living environment and lifestyle habits, that can be used to support behavior change, and then suggests recommended behaviors based on the lifestyle information, thereby improving the efficiency of behavior change support (see, for example, Non-Patent Document 1).

[0003] Naoto Abe, Tae Sato, and Reiko Ariga, "Behavioral change support technology that brings about positive psychological change," NTT Technical Journal, May 2021.

[0004] In conventional technology, the system unilaterally presents recommended actions, which means that users are unable to imagine specific actions and are unable to feel motivated to "give it a try," which can prevent them from taking action.

[0005] An embodiment of the present invention has been made in consideration of the above-mentioned problems, and in a system that proposes suggestions to support users in changing their behavior, it is possible to propose suggestions that allow users to imagine specific actions and take action.

[0006] In order to solve the above problems, a suggestion device according to an embodiment of the present invention is a suggestion device that proposes suggestion content to support behavioral change in a user, and includes: a reception unit that receives input of activities preferred by the user and actions that the user wishes to encourage the user to perform; a generation unit that generates suggestion content that stimulates the user's intrinsic motivation by partially replacing or modifying the actions that the user wishes to encourage the user to perform with the activities preferred by the user; and a presentation unit that presents the suggestion content to the user.

[0007] According to an embodiment of the present invention, in a suggestion system that proposes suggestions to support users in changing their behavior, suggestions can be proposed that allow users to imagine specific actions and take action.

[0008] 1 is a diagram illustrating an example of a configuration of a proposal system according to the present embodiment; FIG. 2 is a flowchart illustrating an example of a proposal process according to Example 1; FIG. 3 is a diagram illustrating an example of correspondence information according to Example 1; FIG. 4 is a diagram illustrating an example of an input screen according to Example 1; FIG. 5 is a diagram illustrating an example of correspondence information according to Example 2; FIG. 6 is a diagram illustrating an example of a configuration of a proposal system according to Example 3; FIG. 7 is a diagram illustrating a determination unit according to Example 3; FIG. 8 is a flowchart illustrating an example of a proposal process according to Example 3; FIG. 9 is a diagram illustrating an example of questions in an FA acquisition questionnaire taking frequency and strength into consideration according to Example 3; FIG. 10 is a diagram illustrating an example of responses to an FA acquisition questionnaire taking frequency and strength into consideration according to Example 3; FIG. 11 is a diagram illustrating an example of a generation process of proposal contents according to Example 3; FIG. 12 is a diagram illustrating an example of a prompt for generating a general msg list according to Example 3; FIG. 13 is a diagram illustrating an example of a prompt for generating an FA msg list according to Example 3; FIG. 14 is a diagram illustrating an example of a prompt for generating an FA msg list according to Example 3; FIG. 15 is a diagram illustrating an example of a hardware configuration of a computer;

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The embodiment described below is merely an example, and the embodiment to which the present invention is applied is not limited to the following embodiment.

[0010] The proposal system according to this embodiment is a system that proposes proposal content that supports behavioral change of a user.

[0011] Non-Patent Document 1 is known as a conventional technology for a device that supports behavioral change. Non-Patent Document 1 discloses a technology that improves the efficiency of behavioral change support by using sensing to obtain lifestyle information that can be used to support behavioral change (behavior change support), such as a user's living environment and lifestyle habits, and presenting recommended behaviors based on the lifestyle information.

[0012] In order for a user to have the initiative to carry out a certain action, it is important that they can imagine a specific action and then feel the urge to "give it a try."

[0013] When a behavior triggers a "let's try" response, it triggers responses related to movement and motivation in the body. Neuroscience has shown that when animals are motivated to perform a behavior, dopamine is secreted in the brain. Dopamine is a neurotransmitter that plays a central role in the control of reward behavior, mood, attention, and learning (Reference 1). The behavioral effects of dopamine vary depending on the neural pathways activated, but in all cases, dopamine dynamically assesses whether a behavior is worth investing limited internal resources, such as energy, attention, and time (Reference 2). Recent research has shown that dopamine conveys motivational value and promotes movement even on timescales of a few seconds or less. Thus, dopamine is a key neurotransmitter in motivating animals to perform certain behaviors.

[0014] In recent years, research into measuring dopamine in the human brain has also progressed. These studies, primarily using positron emission tomography (PET), have shown that playing video games increases dopamine levels in the striatum, and that game performance is proportional to the amount of dopamine released (Reference 3). Another study has shown that activation of dopamine neurons in the medial orbitofrontal cortex is related to the intensity of emotional arousal felt when viewing a photo of a romantic partner (Reference 4). Individual differences in dopamine receptor density have also been shown to be related to individual differences in human behavioral tendencies. For example, dopamine D1 receptor density in the striatum has been reported to be related to the tendency to subjectively overestimate low odds, such as winning the lottery (Reference 5). Thus, in humans, dopamine has been shown to be associated with emotions such as pleasure, curiosity, excitement, motivation, and a sense of accomplishment.

[0015] In the technology disclosed in Non-Patent Document 1, the system unilaterally presents recommended actions, which means that the user is unable to imagine specific actions and does not feel motivated to "give it a try," which may prevent the user from taking action.

[0016] Therefore, in this embodiment, in a system that proposes suggestions to support users in changing their behavior, suggestions can be proposed that allow users to imagine specific actions and take action.

[0017] <System Configuration> Fig. 1 is a diagram showing an example of the configuration of a proposal system according to this embodiment. In the example of Fig. 1, the proposal system 1 includes a proposal device 100 and an external server 10 that can communicate with the proposal device 100 via a communication network N.

[0018] (Proposal Device) The proposal device 100 is a user terminal used by a user, such as a smartphone, a tablet terminal, a PC (Personal Computer), etc. The proposal device 100 is a computer provided in the proposal device 100, and executes an application program (hereinafter referred to as an app) corresponding to the proposal system 1, thereby realizing, for example, each functional configuration shown in FIG.

[0019] 1, the proposal device 100 realizes various functional components, such as a reception unit 101, a generation unit 102, a presentation unit 103, a communication unit, and a storage unit 105. Note that at least a part of the above-described functional components may be realized by hardware.

[0020] The receiving unit 101 executes a receiving process for receiving input of activities that a user likes and activities that the user wishes to encourage the user to perform. Here, the activities that the user likes are activities that the user originally likes and that are targets of dopamine secretion promoting behaviors based on neuroscientific findings (FA: Favorite Activities). The activities that the user wishes to encourage the user to perform are activities that the user wishes to encourage the user to perform (target activities = TA: Target Activities).

[0021] The generation unit 102 executes a generation process to generate suggested content that stimulates the user's intrinsic motivation by partially replacing or modifying the behavior (TA) that the user is desired to perform, received by the reception unit 101, with an activity (FA) that the user prefers. For example, the generation unit 102 generates suggested content that stimulates the user's dopamine secretion using a generation AI (artificial intelligence) such as an LLM (Large Language Model) 11.

[0022] The proposal content generated by the generation unit 102 is not limited to text data. The generation unit 102 may use a generation AI other than the LLM to generate proposal content that includes other data related to physical information that can be perceived by the five human senses, such as images, videos, avatars, icons, voice, sounds, music, colors, illuminance, temperature, humidity, or smells.

[0023] The presentation unit 103 executes a presentation process to present the proposal content generated by the generation unit 102 to the user.

[0024] The communication unit 104 connects the proposal device 100 to the communication network N and executes communication processing to communicate with other devices or systems, such as the external server 10. The communication unit 104 can be commonly used by, for example, the reception unit 101, the generation unit 102, and the presentation unit 103.

[0025] The storage unit 105 stores various information, data, programs, and the like that are included in the proposal device 100. The storage unit 105 can be commonly used by, for example, the reception unit 101, the generation unit 102, the presentation unit 103, the communication unit 104, and the like.

[0026] (External Server) The external server 10 is, for example, an information processing device having a computer configuration or a system including multiple computers. The external server 10 realizes an LLM (generation AI) 11, a storage unit 12, etc. by executing a processing program on the computer provided in the external server 10.

[0027] The LLM11 is a language model constructed using a large amount of text data and deep learning technology. In this embodiment, the existing LLM11 is used as is without any special modifications to the LLM11 itself. The LLM11 is an example of generative AI.

[0028] The storage unit 12 is, for example, a database that stores the activities (FA) preferred by the user received by the reception unit 101, the actions (TA) that the user is encouraged to perform, and the proposal content generated by the generation unit 102.

[0029] Note that the configuration example of the proposal system 1 shown in FIG. 1 is just an example. For example, the external server having the LLM 11 and the external server having the storage unit 12 may be different external servers. Furthermore, the LLM 11 may be provided by a cloud service or the like external to the proposal system 1. Furthermore, each functional configuration of the proposal device 100 may be distributed across multiple devices. Furthermore, the proposal device 100 may have the LLM 11, the storage unit 12, etc.

[0030] <Processing Flow> Next, the processing flow of the proposed method according to this embodiment will be described.

[0031] 2 is a flowchart illustrating an example of a proposal process according to Example 1. This process illustrates an example of the proposal process executed by the proposal device 100 described with reference to FIG.

[0032] In step S201, the receiving unit 101 receives input of an activity (hereinafter referred to as FA) that the user prefers and an action (hereinafter referred to as TA) that the user is to be encouraged to perform. Note that the proposal device 100 according to the first embodiment stores, in advance, for example, correspondence information 300 as shown in FIG. 3 in the storage unit 105 (or the storage unit 12) or the like.

[0033] 3 is a diagram illustrating an example of correspondence information according to Example 1. The proposal device 100 stores in advance, for example, in correspondence information 300 as shown in FIG. 3, dopamine secretion promoting actions based on neuroscientific findings and emotions that are thought to occur when the actions are performed.

[0034] In the correspondence information 300, "dopamine secretion-promoting behavior" refers to behavior that promotes dopamine secretion, as clarified in References 3 to 5. Furthermore, "emotion" is an abstract concept representation of the emotion thought to arise when performing a dopamine secretion-promoting behavior. By abstractly conceptualizing, it is thought that FAs other than the dopamine secretion-promoting behavior that induce emotions similar to those induced by the dopamine secretion-promoting behavior can be acquired, without being limited to the dopamine secretion-promoting behavior discussed in Non-Patent Document 1. Here, personal experiences that induce various emotions are defined as activity FAs that the user originally enjoys. The "FA acquisition question" in the correspondence information 300 is a question for eliciting behaviors that have been experienced as eliciting each emotion, i.e., favorite activity FAs.

[0035] Note that the correspondence information 300 shown in FIG. 3 is an example. For example, other neuroscientific findings may be added to "dopamine secretion promoting behavior." "Emotion" may be expressed in an abstract concept other than that described here, or other abstract concept expressions may be added. The "FA acquisition question" may be any question as long as it can elicit behaviors related to the various emotions. Furthermore, the level of abstraction of "emotion" shown in FIG. 3 may be further increased, and a more abstract question such as "Please tell us your favorite activities" may be used to ask about it.

[0036] Based on such correspondence information 300, the receiving unit 101 displays, for example, an input screen 400 as shown in FIG. 4 on the proposing device 100, and receives input of FA and TA by the user.

[0037] FIG. 4 is a diagram illustrating an example of an input screen according to the first embodiment. As illustrated in FIG. 4 , the receiving unit 101 displays an FA acquisition question 401, such as, for example, "Please tell us about an activity that you find enjoyable (multiple answers allowed)," on an input screen 400, and receives an FA input in an answer area 402. The answer area 402 may be, for example, a free-form answer by the user, or may be an area in which the user selects a button or a pull-down menu from among options prepared in advance. When the user selects a registration button 403, the receiving unit 101 stores the received FA in the storage unit 12 (or the memory unit 105), etc.

[0038] 4, the receiving unit 101 displays a TA acquisition question 404, such as "Please tell me about an exercise habit that you think you should do but don't feel like doing (multiple answers allowed)," on the input screen 400, and receives a TA input in an answer area 405. The answer area 405 may be, for example, a place where the user can write their answer freely, or may be a place where the user can select an answer from pre-prepared options using a button or a pull-down menu. When the user selects the register button 406, the receiving unit 101 stores the received TA in the storage unit 12 (or the memory unit 105), etc.

[0039] The TA may be preset by the system, such as "go to the gym three times a week." Alternatively, the TA does not have to be input by the user himself / herself; for example, a doctor or public health nurse may input as TA an action that the user has determined to be beneficial based on the results of a health check.

[0040] 2, the description of the flowchart will be continued. In step S202, the generating unit 102 generates proposal content by partially replacing or modifying the TA received by the receiving unit 101 with the FA.

[0041] The concept of generating proposal content in the generation unit 102 is to perform the following processing when the input is FA and TA, the output message is msg(FA'), and the conversion algorithm that converts TA into an activity FA' that is close to FA is F(FA, TA): msg(FA') = F(FA, TA) There are several possible methods for the generation unit 102 to generate proposal content.

[0042] (First Method) As a first method, a combination of FAs and TAs is presented to the user to give the user an idea and encourage the user to create an action plan on his or her own. For example, the generation unit 102 generates a suggestion content such as, "Can you think of any way to do the activity "TA" while doing the activity "FA"?" by combining the input of FAs and TAs received by the receiving unit 101 in a sentence. As a specific example, as shown in FIG. 4 , when the generation unit 102 receives the FAs "Go to the nearby beach" and "Gardening" and the TAs "Muscle training" and "Walk more," the generation unit 102 generates the following suggestion content (message) as shown in (1) to (3): (1) Can you think of any way to do the activity "muscle training" while doing the activity "go to the nearby beach"? (2) Why not consider doing the activity "muscle training" at the same time as doing the activity "go to the nearby beach"? (3) Let's consider an activity that combines the activity "go to the nearby beach" with the activity "muscle training."

[0043] The generation unit 102 may provide a function for the user to think of and input a response to the messages (1) to (3), or may simply present the message and encourage the user to write their thoughts in a notepad. By presenting a message that combines FA and TA in this way, it is expected that the user will be encouraged to create their own action plan and take initiative in the action plan. Furthermore, compared to simply having the user create an action plan related to a TA, having the user create an action plan while recognizing an activity FA that the user originally enjoys can help create an action plan that incorporates elements that promote dopamine secretion and encourages intrinsic motivation.

[0044] The generator 102 can generate a variety of messages by substituting other FAs and TAs into the parentheses of the messages (1) to (3).

[0045] (Second Method) The second method is a method in which, for the obtained FA and TA, characteristics of the component α included in these activities are determined, and these characteristics are used as a parameter v_α to generate an activity FA' that is more natural in the context of human behavior. For example, the generation unit 102 performs characteristic determination of the component α in the first FA (hereinafter referred to as FA1) and the second FA (hereinafter referred to as FA2) received by the reception unit 101 using the LLM 11, and obtains the output results v_α(FA1) and v_α(FA2). The generation unit 102 also performs characteristic determination of the component α in the first TA (hereinafter referred to as TA1) using the LLM 11, and obtains the output result v_α(TA1). Furthermore, the generation unit 102 selects the activity v_α(FA1) or v_α(FA2) that is closer to v_α(TA1) as the activity to convert TA1.

[0046] As a specific example, consider setting a motion state v_motion as a parameter, for example, representing the motion state that accounts for the majority of the activity. Here, possible values ​​for v_motion are {stationary, walking, running, cycling, swimming, or other sports} (multiple selections are possible). If the second TA is TA2, the generation unit 102 calculates, from the perspective of the motion state v_motion, whether it is appropriate to use FA1 = {going to the nearby beach} or FA2 = {gardening} in order to convert TA2 = {walking more} into an activity FA' that is closer to the originally preferred activity FA. The generation unit 102 calculates, using the LLM 11, which of the possible values ​​for v_motion is most appropriate for the motion state in the activity of each FA and TA. For example, let us assume that the calculated v_motions are v_motion(FA1) = {walking}, v_motion(FA2) = {stationary}, and v_motion(TA2) = {walking}. In this case, the generator 102 uses FA1 as the conversion element for TA2 because v_motion(FA1) is closest to v_motion(TA2).

[0047] When generating a suggestion, the generation unit 102 substitutes FA1 and TA2 into a template such as "When doing an activity called 'FA', why not try adding an activity called 'TA'?". This allows the generation unit 102 to generate a suggestion (message) such as "When doing an activity called 'going to the beach nearby, why not try adding an activity called 'walking more'?"

[0048] Furthermore, the generation unit 102 can instruct the LLM 11 to make the sentence even more natural, thereby obtaining a more natural sentence such as, "When you go to the nearby beach, why not try taking a different route and a longer detour?"

[0049] Here, the method of utilizing parameters is not limited to this, and multiple parameters may be used. Also, in the above example, a single FA converts the input of a single TA and outputs a single FA', but multiple FAs, TAs, and FA's may be combined.

[0050] Although v_motion is used as an example of a specific parameter here, other parameters are possible, such as the typical activity location v_place where the activity is performed, and the ordinariness v_ordinary, which indicates how common or special performing the activity is. Other parameters are also possible, such as the required time v_time_required, which indicates how much time is generally required, and the travel distance v_distance, which indicates how far from a base the activity is performed. Other parameters are also possible, such as the activity companion v_companion, which indicates whether the activity is generally performed with a companion, and the posture v_posture, which is the majority of the posture when performing the activity. Possible values ​​for each parameter are, for example, as follows (multiple selections are possible):

[0051] Activity location v_place = {indoor: home, indoor: commercial facility, outdoor: home, outdoor: commercial facility, outdoor: park, outdoor: nature (sea, river, mountain, forest, woods)} Ordinary level v_ordinary = {workday, holiday, short vacation, long vacation} Activity companion v_companion = {alone, family, friends, colleagues, unspecified number of people} Posture v_posture = {lying down, sitting, standing} Exercise status = {stationary, walking, running, cycling, swimming, other sports} Note that the required time v_time_required may be flexibly expressed in terms of minutes, hours, days, etc. Similarly, the travel distance v_distance may be flexibly expressed in terms of kilometers, etc., or a specific distance may be substituted if the location information of the home, workplace, or the location where FA or TA is performed is known.

[0052] Here, parameters and their possible values ​​may be other than those shown here. Furthermore, although the above parameters do not include human psychological aspects, parameters including psychological information may also be used. For example, the reception unit 101 may obtain psychological information about the FA or TA in the form of, for example, "What do you enjoy about this activity?" or "What do you dislike about this activity?", and use this as a parameter.

[0053] (Third Method) In the third method, the generation unit 102 uses an LLM (Large Scale Language Model) 11 to generate a proposal. For example, the generation unit 102 substitutes FA and TA into a prepared prompt, inputs the substituted prompt to the LLM 11, and outputs a proposal (message) in which TA is partially replaced or modified by FA. The prepared prompt contains information about the number of characters in the proposal to be output and the number N of proposals (N is an integer equal to or greater than 1). The generation unit 102 stores the proposal (message) generated by the LLM 11 in the storage unit 12 (or the memory unit 105), etc.

[0054] As described above, three methods for generating the proposal content (message generation) have been shown, but the method for generating the proposal content may be other methods as long as the TA is partially replaced or modified by the FA and an FA' is generated.

[0055] 2, the description of the flowchart will be continued. In step S203, the presentation unit 103 presents the proposal contents generated by the generation unit 102 to the user. For example, the presentation unit 103 displays the N proposal contents (messages) generated by the generation unit 102 on a display screen or the like of the proposal device 100.

[0056] Through the above processing, the suggestion system 1, which proposes suggestions to support users in changing their behavior, can propose suggestions that allow users to imagine specific actions and take action.

[0057] Second Embodiment In the first embodiment, the receiving unit 101 sets a question about an FA, which is an activity that the user likes, as a question that is not an emotionally evocative question such as "Please tell me your favorite activity."

[0058] In Example 2, in order to construct a question that evokes a past experience of feeling a certain emotion, emotional expressions (onomatopoeia, mimetic words, exclamations, etc.) are used in the question to acquire FA. Emotional expressions are words that express the physical sensations that occur inside a person when feeling a certain emotion, and it is believed that using these words makes it possible to more specifically recall a past experience of feeling that emotion.

[0059] The proposing device 100 according to the second embodiment stores, for example, correspondence information 500 as shown in FIG. 5 in advance in the storage unit 105 (or the storage unit 12) or the like.

[0060] FIG. 5 is a diagram illustrating an example of correspondence information according to Example 2. In the correspondence information 500 illustrated in FIG. 5, "dopamine secretion-promoting behavior," "emotion," and "emotion expression words" are stored in association with each other. Of these, the "dopamine secretion-promoting behavior" and "emotion" are similar to the "dopamine secretion-promoting behavior" and "emotion" in the correspondence information 300 described in FIG. 3. The "emotion expression words" are emotion expression words such as onomatopoeia, mimetic words, or exclamations that correspond to the "emotions." In the correspondence information 500, a certain emotion expression word may express a plurality of emotions, such as "excited" or "great, great, relieved."

[0061] The receiving unit 101 uses the "emotion expression words" in the correspondence information 500 to create FA questions such as those shown in the following (1) or (2), and displays them on the input screen 400 as shown in Fig. 4. (1) Please tell me about an exciting activity. (2) Please tell me about an activity that makes you feel the following emotions.

[0062] (a) Exciting (b) Happy, lively, happy (c) Good, all right, relieved (d) Wow, yay. Note that Example 2 is the same as Example 1 except that it uses correspondence information 500 instead of correspondence information 300 in Example 1, and uses an input screen including an FA question sentence using the above-mentioned emotional expression words instead of input screen 400 in Example 1.

[0063] In this way, the proposed system 1 according to Example 2 is expected to have the effect of acquiring FA-related activities that are closer to the physical sensations experienced when dopamine secretion is promoted, by using questions that evoke past experiences of feeling a certain emotion.

[0064] (Supplementary Note) In each of the above embodiments, the reception unit 101 is described assuming that the user inputs via a mobile terminal, etc. However, this is not limited to this, and the reception unit 101 may automatically detect the user's preferred activity FA by analyzing conversation data with a chatbot or a smart speaker, etc., actual conversation data from a health guidance interview, etc., device usage log data from a smartphone, etc., behavior log data from a wearable device, etc., or various other life log data, etc.

[0065] Furthermore, in each of the above embodiments, an approach is described in which the generator 102 generates a message as a suggestion using the LLM 11. However, the present invention is not limited to this, and the generator 102 may generate other data related to physical information that can be perceived by the five human senses, such as images, videos, avatars, icons, voices, sounds, music, colors, illuminance, temperature, humidity, and / or smells, as a suggestion.

[0066] Similarly, in each of the above embodiments, an approach is described in which a text message is displayed on a mobile terminal or the like by the presentation unit 103. However, the presenting unit 103 is not limited to this, and may present, as the suggestion content, data related to physical information that can be perceived by the five senses of a person, such as an image, a video, an avatar, an icon, a voice, a sound, music, a color, illuminance, a temperature, a humidity, and / or a smell.

[0067] Furthermore, in each of the above-described embodiments, an example is described in which the generation unit 102 uses the input FA and TA as user information. However, this is not limited to this, and the generation unit 102 may use, as additional information, information such as the user's location information, weather information, physical condition, etc., the user's internal condition, the user's external condition, context, and / or constraints to generate suggested content that is more tailored to the user's situation. For example, as an example of using weather information, if the user has registered jogging and yoga as FAs, the generation unit 102 may preferentially present content related to yoga, which is an indoor activity, if the weather is rainy.

[0068] [Example 3] (Summary) In Example 3, by understanding the intensity of the positive emotions and / or impulse-inducing properties of an activity FA that the user originally prefers and the frequency of occurrence of the FA, it is possible to select suggestions that correspond to the user's daily motivation and / or level of busyness for the behavior TA that the user is desired to encourage the user to perform.

[0069] Exciting events (examples of activities that users enjoy) do not occur frequently. For example, events with high levels of excitement have the aspect of being unlikely to occur in everyday life. Examples of such events include traveling abroad and mountain climbing. Also, events with high levels of excitement have the aspect of being high in excitement because they cannot be done frequently. Examples of events with low levels of excitement are activities that can be done to change mood even on a work day, such as taking a walk around the neighborhood or making coffee. These activities provide a low level of excitement to the user, but occur frequently in everyday life.

[0070] However, it is believed that a user's motivation for an action TA, which is a target for encouraging the user to perform, and the user's life situation (such as how busy they are) when performing the TA, fluctuate from day to day. For example, when a motivational message is generated to encourage the user to perform an action TA on a busy day by partially replacing or modifying the action TA, which is a target for encouraging the user to perform, with an activity FA that the user originally prefers, as in Examples 1 and 2, if the FA to be combined with the TA is a fun activity that occurs infrequently and can only be done when the user has time, the generated suggestion content will be unlikely to be realized by the user. As another example, when a user is not motivated, if a suggestion content is generated using a FA that is not very exciting, the suggestion content will not be very motivating.

[0071] (Processing Overview) Therefore, in Example 3, the user's positive emotions and / or the intensity of the degree to which the user's impulse is induced regarding an activity FA that the user originally prefers (hereinafter referred to as the FA intensity), and the frequency of occurrence of the FA are grasped in advance, and the user's daily motivation and / or degree of busyness regarding the behavior TA that the user is intended to encourage the user to perform are obtained, thereby making it possible to provide the user with suggestions that correspond to the user's motivation and busyness at that time.

[0072] The means for grasping the intensity of an activity FA originally preferred by the user and the frequency of occurrence of the FA may be, for example, a questionnaire. For example, the proposal system 1 may grasp the above-mentioned intensity and frequency of occurrence based on the user's answers to a plurality of questions (questions 1, 2, 3, etc.) that differ in the intensity, frequency of occurrence, or feasibility of an emotion, impulse, etc., as shown in Fig. 6. Alternatively, the proposal system 1 may ask the user about the frequency and intensity of an activity FA originally preferred by the user, and grasp the above-mentioned intensity and frequency of occurrence based on the user's answers, as shown in Fig. 7.

[0073] However, without being limited to this, the proposed system 1 may estimate the intensity and occurrence frequency described above from an action log in real space or cyberspace and / or a biological signal, or may acquire information indicating the intensity and occurrence frequency described above from an external system. In this embodiment, the method for determining the intensity and occurrence frequency described above may be any method.

[0074] As an example, the proposal system 1 measures the user's motivation (e.g., lack of motivation, boredom, etc.) for a target behavior (TA) that the user is to be encouraged to perform at a certain point in time. The proposal system 1 also determines which proposal content to present based on the level of the user's motivation. For example, when the user's motivation is low, the proposal device 100 may suggest more intense content.

[0075] As another example, the proposal device 100 measures the busyness of the user at a certain point in time (for example, busy to relaxed, etc.). Furthermore, the proposal device 100 determines which proposal content to present depending on the busyness of the user. For example, when the user is busy, the proposal device 100 may suggest content that is frequently used.

[0076] In this way, in Example 3, the proposal system 1 grasps in advance the frequency of occurrence of the user's preferred activities and the strength of the positive emotions and impulses induced in the user by the user's preferred activities, and takes this into consideration when selecting the FA to incorporate into the proposal content, thereby making it possible to provide the user with proposal content that corresponds to the user's motivation and / or level of busyness at a given point in time for the behavior that the user is desired to encourage the user to perform.

[0077] <System Configuration> Fig. 8A is a diagram illustrating a configuration example of a proposal system according to Example 3. The proposal system 1 according to Example 3 includes, for example, a proposal device 100 and an external server 10 that can communicate with the proposal device 100 via a communication network N, similar to the proposal system 1 described in Fig. 1 .

[0078] (Proposal Device) The proposal device 100 according to Example 3 realizes, for example, each functional configuration as shown in Fig. 8A by executing an app corresponding to the proposal system 1 on a computer included in the proposal device 100. The proposal device 100 according to Example 3 has an acquisition unit 801, a determination unit 802, a determination unit 803, and the like in addition to each functional configuration of the proposal device 100 described in Fig. 1.

[0079] The reception unit 101 executes a reception process for receiving input of a user's preferred activity (FA) and a behavior (TA) that the user is desired to promote. The reception unit 101 may further receive information indicating the intensity and frequency of the FA. In this case, the reception unit 101 receives the information indicating the intensity and frequency of the FA through a questionnaire or the like including the questions described in FIG. 6 or FIG. 7.

[0080] The acquisition unit 801 executes an acquisition process to acquire information indicating the strength of the FA (the strength of the user's positive emotions and / or the degree to which the FA induces the user's impulse regarding the activity FA that the user originally prefers) and the frequency of the FA. The acquisition unit 801 acquires information indicating the strength and frequency of the FA accepted by the acceptance unit 101 from the acceptance unit 101. Alternatively, the acquisition unit 801 may acquire the information indicating the strength and frequency of the FA by estimating the strength and occurrence frequency of the FA from an action log in real space or cyberspace and / or a biological signal, etc. Furthermore, the acquisition unit 801 may acquire information indicating the strength and frequency of the FA from an external system.

[0081] The determination unit 802 executes a determination process to determine the user's state, including the user's motivation for the activity TA that the user wishes to encourage the user to perform, or the user's busyness. For example, the determination unit 802 determines the user's state using a questionnaire 820 as shown in FIG. 8B. Here, the example shown in FIG. 8B is a case where the activity TA that the user wishes to encourage the user to perform is "muscle training." However, this is not limited to this, and the determination unit 802 may determine the user's state based on the user's schedule information, work information, biological information, etc. In this case, the user's motivation at a certain time t for the activity TA that the user wishes to encourage the user to perform is expressed as U. motivation (t), the user's status including busyness is represented by U busyness (t), the motivation threshold is T motivation , the busyness threshold is T busyness In addition, the strength of the nth FA registered multiple times is I(n), the occurrence frequency of the nth FA registered multiple times is F(n), and the threshold of the FA strength is T intensity , the threshold for the occurrence frequency of FA is T frequency Let's say.

[0082] The determination unit 803 executes a determination process to determine an FA that partially replaces or modifies the TA based on the state of the user determined by the determination unit 802. For example, the determination unit 803 determines an FA that partially replaces or modifies the TA depending on the level of the user's motivation. For example, when the user's motivation is low, the determination unit 803 may select an FA with a higher intensity. For example, when performing control based on a threshold, the determination unit 803 may select an FA with a higher intensity. motivation (t)<T motivation If T intensity An FA equal to or greater than this may be selected.

[0083] Alternatively, the determination unit 803 determines an FA that partially replaces or modifies the TA depending on the degree of busyness of the user. For example, when the user is busy, the determination unit 803 may select an FA that is used more frequently. For example, when controlling based on a threshold, U busyness (t)>T busyness If T frequency An FA equal to or greater than this may be selected.

[0084] The generation unit 102 executes a generation process to generate a suggestion content that promotes the user's intrinsic motivation by partially replacing or modifying the TA with the FA determined by the determination unit 803. For example, the generation unit 102 generates the suggestion content to promote the user's secretion of dopamine using a generation AI 811 such as ChatGPT or LLM11.

[0085] The proposal content generated by the generation unit 102 is not limited to text data. The generation unit 102 may generate proposal content including other data related to physical information that can be perceived by the five senses of a person, such as an image, a video, an avatar, an icon, a voice, a sound, music, a color, illuminance, a temperature, a humidity, or a smell.

[0086] The presentation unit 103 executes a presentation process to present the proposal content generated by the generation unit 102 to the user.

[0087] The communication unit 104 connects the proposal device 100 to the communication network N and executes communication processing to communicate with, for example, another device or system such as the external server 10. The communication unit 104 can be commonly used by, for example, the reception unit 101, the generation unit 102, the presentation unit 103, the acquisition unit 801, the determination unit 802, and the determination unit 803.

[0088] The storage unit 105 stores various information, data, programs, and the like that are included in the proposal device 100. The storage unit 105 can be commonly used by, for example, the reception unit 101, the generation unit 102, the presentation unit 103, the acquisition unit 801, the determination unit 802, the decision unit 803, and the like.

[0089] (External Server) The external server 10 according to the third embodiment has a generation AI 811 such as ChatGPT instead of (or in addition to) the LLM 11 described in Fig. 1. Here, the following description will be given assuming that the generation AI 811 is ChatGPT. Note that in the third embodiment, the existing generation AI 811 is used as is without any special modifications to the generation AI 811 itself.

[0090] 8A is just an example. The generation AI 811 may be provided by a cloud service or the like external to the proposal system 1. Furthermore, each functional configuration of the proposal device 100 may be distributed across multiple devices.

[0091] <Processing Flow> Next, the processing flow of the proposed method according to the third embodiment will be described.

[0092] 9 is a flowchart illustrating an example of a proposal process according to Example 3. This process illustrates an example of the proposal process executed by the proposal device 100 described with reference to FIG.

[0093] In step S901, the receiving unit 101 receives an activity FA that the user originally likes, a behavior TA that the user is encouraged to perform, and the intensity and frequency of the FA. For example, the receiving unit 101 receives the user's FA by conducting an FA acquisition questionnaire including multiple questions (FA10, FA20, FA30, ...) as shown in FIG.

[0094] Furthermore, the receiving unit 101 can receive the intensity and frequency of an FA by making these questions into a plurality of questions with different intensities of emotions, impulses, etc. (intensity of FA) and different occurrence frequencies or feasibility (frequency of FA), as described in Fig. 6. Alternatively, the receiving unit 101 may receive the intensity and frequency of an FA by asking a question 700 for each FA, as shown in Fig. 7.

[0095] Furthermore, the receiving unit 101 displays a TA acquisition question 404 on the input screen 400 as shown in FIG. 4, for example, and receives the input of a TA based on the user's answer in the answer area 405.

[0096] In step S902, the determination unit 802 determines the user's motivation for the TA or the user's state, including how busy they are. For example, the determination unit 802 acquires responses to a questionnaire 820, such as that shown in FIG. 8B , from the reception unit 101, and determines whether the user's motivation for the TA at that time is high or low and / or how busy they are, based on the acquired questionnaire responses, etc.

[0097] FIG. 11 is a diagram showing example responses to an FA acquisition questionnaire that takes frequency and intensity into consideration according to Example 3. In FIG. 11, the categories "FA10," "FA20," "FA30," and "FA41 to FA44" are, for example, as described in FIG. 6, multiple questions and their answers that differ in the intensity of emotion, impulse, etc. (FA intensity) and the frequency of occurrence or feasibility (FA frequency). The category "persona" is, for example, questions and their answers regarding an individual's personality, such as the Big Five (openness, conscientiousness, extroversion, agreeableness, and neuroticism). The category "TA" is questions and their answers regarding TA.

[0098] In step S903, the determination unit 803 executes a determination process to determine an activity FA that is originally preferred by the user and that partially replaces or modifies the behavior TA that the user is encouraged to perform, based on the user's state determined by the determination unit 802. For example, the determination unit 803 determines an FA that partially replaces or modifies the TA depending on the level of the user's motivation. Alternatively, the determination unit 803 determines an FA that partially replaces or modifies the TA depending on the user's level of busyness.

[0099] In step S904, the generation unit 102 generates a suggestion content that encourages the user's intrinsic motivation by partially replacing or modifying the behavior TA that the generation unit 102 wants the user to perform with the activity FA that the user originally prefers, which has been determined by the determination unit 803. The process of generating the suggestion content will be described later.

[0100] In step S905, the presentation unit 103 presents to the user the proposal content generated by the generation unit 102. For example, the presentation unit 103 displays the proposal content generated by the generation unit 102 on a display screen of the proposal device 100 or the like.

[0101] <Proposal Content Generation Process> Here, an example of proposal content generation process executed by the generation unit 102 in step S904 of FIG. 9 will be described.

[0102] (First Method) Fig. 12 is a diagram for explaining an example of a process for generating proposal content according to the third embodiment. In Fig. 12, it is assumed that u_data 1201 stores, for example, the response 1100 to the FA acquisition questionnaire as shown in Fig. 11, the FA determined by the determination unit 803 in step S903 of Fig. 9, and identification information for identifying the user. Note that u_data 1201 may be stored, for example, in the storage unit 105 of the proposal device 100 or in the storage unit 12 of the external server 10.

[0103] The generation unit 102 generates a list of general motivational messages for practicing the behavioral TA that the user is desired to be encouraged to perform, for example, by using a prompt 1202 for generating a general msg list, as shown in Fig. 13. Specifically, the generation unit 102 acquires the user's TA from u_data 1201 and inputs the acquired TA into TA = {...} of the prompt 1202 for generating a general msg list. The generation unit 102 also inputs the prompt 1202 for generating a general msg list, into which the TA has been input, to a generation AI 811 such as ChatGPT.

[0104] This allows the generation unit 102 to cause the generation AI 811 to generate a General msg list 1203, which is a list of general motivational messages for practicing the TA. For example, if the TA is "increase the amount of daily activity," the General msg list 1203 includes general motivational messages for practicing the TA, such as "try climbing up and down a step stool," "try using the stairs more," and "try walking one station."

[0105] In order to generate content that is acceptable to many people, the prompt 1202 for generating a general message list is preferably created in advance, including constraints on the content to be generated. For example, the prompt 1202 for generating a general message list preferably includes a constraint that takes into consideration not generating content that involves dangerous behavior, such as walking while using a smartphone, or behavior that may be a nuisance to others. The prompt 1202 for generating a general message list is preferably created in advance to not generate content that includes children and pets. This is because some users do not have children or pets. The prompt 1202 for generating a general message list preferably includes a constraint that takes into consideration the ease of understanding of the generated content, such as not including technical terms written in katakana. The prompt 1202 for generating a general message list preferably includes a constraint that takes into consideration the feasibility of generating content that is not discreet, such as generating content that is not discreet to others, so that users will not be hesitant to use the content in public places. Preferably, the prompt 1202 for generating a General msg list includes constraints that allow the user to easily understand that the proposal includes the FA to which the user responded, such as explicitly including elements of the original FA in the generated text.

[0106] Preferably, the prompt 1202 for generating the general message list emphasizes the time constraint. This allows for the generation of motivational messages that do not require much time and are easy for the user to follow. The time constraint may be customized to suit the user. For example, it may include lifestyle factors such as employment status, work environment, home environment, and childcare / nursing care situation. These lifestyle factors may be obtained in advance through a questionnaire or estimated from activity logs in the real world and / or cyberspace.

[0107] 14 , the generation unit 102 modifies and / or converts the contents of the General msg list 1203 with the FA determined by the determination unit 803. Specifically, the generation unit 102 acquires the FA determined by the determination unit 803 from u_data 1201, and inputs the acquired FA into FA{...} of the prompt 1204 for generating the FA msg list. The generation unit 102 also inputs the prompt 1204 for generating the FA, into which the FA has been input, to a generation AI 811 such as ChatGPT.

[0108] As a result, the generation unit 102 can cause the generation AI 811 to generate an FA msg list 1205 by modifying and / or converting the contents of the general msg list 1203 with the FA determined by the determination unit 803. In the example of Fig. 12, the FA msg list 1205 includes an FA message "Let's go up and down the step stool while watching a movie commentary video" obtained by modifying the general motivation message "Let's go up and down the step stool" with the FA "Watch a movie commentary video." The FA msg list 1205 also includes an FA message "Let's go up and down the stairs at your favorite nature spot" obtained by converting the general motivation message "Let's use the stairs more" with the FA "Take a walk in a pleasant nature park."

[0109] In the first method, the proposal system 1 associates the General msg list 1203 and the FA msg list 1205 generated by the generation unit 102, and stores and manages them in the storage unit 12, the memory unit 105, or the like. This allows the proposal system 1 to propose to the user, as proposal content, a general motivational message or a motivational message obtained by modifying or converting a general motivational message with an FA, depending on, for example, the user's preferences or situation.

[0110] Note that because the generation AI 811 is subject to fluctuations, if the General msg list 1203 and the FA msg list 1205 are generated simultaneously using the same prompt, messages that do not necessarily correspond to each other may be generated. In other words, the correspondence between the contents of the General msg list 1203 and the FA msg list 1205 cannot be guaranteed, making it impossible to provide a general motivational message or a motivational message modified or converted by FA according to the user's preferences and circumstances. For example, if a row in the General msg list contains an activity related to "step-up and step-down," the corresponding row in the FA msg list should contain an activity obtained by converting "step-up and step-down" using FA. However, if a mismatch occurs, a situation may arise in which, even though a row in the General msg list contains an activity related to "step-up and step-down," the corresponding row in the FA msg list contains an activity obtained by converting "step-up and step-down" using FA, which is unrelated to "step-up and step-down." On the other hand, in the first method, the FA msg list 1205 is generated in a separate process using the general msg list 1203, so that inconsistencies in the correspondence between messages in the general msg list 1203 and the FA msg list 1205 can be avoided.

[0111] (Second Method) Fig. 15 is a diagram illustrating an example of a process for generating a proposal according to the third embodiment. In the second method, the generation unit 102 generates an FA msg list 1502 in which a TA is partially replaced or modified with the FA determined by the determination unit 803, using a prompt 1501 for generating an FA msg list, as shown in Fig. 16, for example. Specifically, the generation unit 102 acquires the user's TA and the FA determined by the determination unit 803 from u_data 1201, and inputs the acquired TA and FA into TA = {...} and FA {...} in the prompt 1501 for generating an FA msg list. In the prompt 1501, for example, it is specified to generate advice to practice the TA while performing a favorite activity FA. Furthermore, the generation unit 102 inputs a prompt 1501 for generating an FA msg list, to which the TA and FA have been input, to a generation AI 811 such as ChatGPT.

[0112] As a result, the generation unit 102 can cause the generation AI 811 to generate an FA msg list 1502, which is a suggested content obtained by partially replacing or modifying the behavior TA that the user is desired to perform with the activity FA that the user originally prefers, as determined by the determination unit 803. In the example of Fig. 15, the FA msg list 1502 includes a suggested content of "Let's go shopping for movie merchandise on foot," which is generated from the TA of "Increase the amount of daily activity" and the FA of "Go shopping for movie merchandise." The FA msg list 1502 also includes a suggested content of "Let's go for a light jog in a pleasant nature park," which is generated from the TA of "Increase the amount of daily activity" and the FA of "Take a walk in a pleasant nature park."

[0113] Preferably, the prompt 1501 for generating the FA msg list is prepared in advance to avoid generating content that involves dangerous behavior, such as walking while using a smartphone, or behavior that may be a nuisance to others. Preferably, the prompt 1501 for generating the FA msg list may emphasize a time constraint to facilitate user execution, as in the first method. Preferably, the prompt 1501 for generating the FA msg list includes constraints that consider ease of understanding and feasibility, such as not including technical terms written in katakana or generating content that is not distracting to others. Preferably, the prompt 1501 for generating the FA msg list includes constraints that consider ease of understanding and feasibility, such as explicitly including elements of the original FA in the generated text, to enable the user to easily understand that the proposed content includes the FA that the user answered.

[0114] As described above, according to Example 3, the suggestion system 1 that proposes suggestions to support a user's behavioral change can propose suggestions that take into account the balance between the frequency of the user's preferred activities and the strength of the positive emotions and impulses induced in the user by the preferred activities. In this example, the message is generated after selecting an FA to be used for message generation, but the processing process is not limited to this. For example, as another processing process, messages using each FA acquired in advance are generated in advance and stored on a server, etc., and when the time to present the message arrives, the user's state at that time is grasped. Alternatively, an FA that matches the user's state at that time may be selected and a message using that FA may be read. The order of processing is not important as long as a message using an FA that matches the user's state at a certain time is presented. Furthermore, in Examples 1 and 2, a third method for generating a message using the generation AI 811 was described. However, as in the first method described in this example, a general motivational message may first be generated, and then the message list may be modified with an FA. Furthermore, similar to the (second method) described in this embodiment, activities similar to TA that can be done as an extension of FA may be generated as proposals.

[0115] <Hardware Configuration> The proposed device 100 according to this embodiment can be realized, for example, by causing a computer to execute a program. This computer may be a physical computer (physical machine) or a virtual machine on the cloud.

[0116] That is, the proposed device 100 can be realized by using hardware resources such as a CPU (Central Processing Unit) and memory built into a computer to execute a program corresponding to the processing performed by the proposed device 100. The program can be recorded on a computer-readable recording medium (such as a portable memory) and can be saved or distributed. The program can also be provided via a network such as the Internet or email.

[0117] Fig. 17 is a diagram showing an example of the hardware configuration of the computer. In the example of Fig. 17, the computer 1700 includes a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, and an output device 1008, all of which are interconnected by a bus B. The computer 1700 may further include a GPU (Graphics Processing Unit) or the like.

[0118] A program for implementing processing on the computer 1700 is provided by a recording medium 1001, such as a CD-ROM or a memory card. When the recording medium 1001 storing the program is set in the drive device 1000, the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000. However, the program does not necessarily have to be installed from the recording medium 1001, but may be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program as well as necessary files, data, etc.

[0119] The memory device 1003 reads and stores the program from the auxiliary storage device 1002 when an instruction to start the program is received. The CPU 1004 realizes functions related to the proposed device 100 in accordance with the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network, etc. The display device 1006 displays a GUI (Graphical User Interface) or the like according to the program. The input device 1007 is composed of a keyboard, mouse, buttons, and / or a touch panel, etc., and is used to input various operation instructions. The output device 1008 outputs the results of calculations.

[0120] The external server 10 has, for example, the hardware configuration of a computer 1700 as shown in Fig. 17. Alternatively, the external server 10 may be realized by a plurality of computers 1700.

[0121] <Effects of the embodiment> According to the present embodiment, in the proposal system 1 that proposes proposal content to support the user's behavioral change, it becomes possible to propose proposal content that allows the user to imagine specific actions and put them into action.

[0122] For example, the suggestion system 1 can automatically generate suggestion content that allows the user to imagine specific actions and promotes the secretion of dopamine by partially replacing or modifying the target action TA with an activity FA that the user originally enjoys.

[0123] Furthermore, according to Example 3, in the proposal system 1 that proposes proposal content to support the user's behavioral change, it becomes possible to propose proposal content that takes into consideration the balance between the frequency of occurrence of the user's preferred activities and the intensity of the positive emotions and impulses induced within the user by the user's preferred activities.

[0124] Summary of Embodiments This specification discloses at least the following proposal devices, proposal systems, proposal methods, and programs. (Item 1) A proposal device that proposes proposal content to support a user's behavioral change, comprising: a receiving unit that receives input of the user's preferred activities and activities that the user wishes to encourage the user to perform; a generating unit that generates proposal content that stimulates the user's intrinsic motivation by partially replacing or modifying the activities the user wishes to encourage the user to perform with the user's preferred activities; and a presenting unit that presents the proposal content to the user. (Item 2) The proposal device described in Item 1, wherein the user's preferred activities are activities that the user inherently enjoys and that are targets of dopamine-stimulating behavior based on neuroscientific findings, and the generating unit generates the proposal content that stimulates the user's dopamine secretion. (Item 3) The proposal device described in Item 1 or 2, wherein the receiving unit receives a response about the user's preferred activities using a question including a phrase that expresses an emotion corresponding to the dopamine-stimulating behavior. (4) The suggestion device according to paragraph 1 or 2, comprising: a determination unit that determines the user's motivation for a behavior that the user is desired to be encouraged to perform, or the user's state, including how busy the user is; and a determination unit that determines, based on the user's state, an activity preferred by the user that partially replaces or modifies the behavior that the user is desired to be encouraged to perform. (5) The suggestion device according to paragraph 4, comprising: an acquisition unit that acquires information indicating the user's positive feelings about the activity preferred by the user and / or the intensity of the degree to which the activity induces urges in the user, and a frequency of the activity preferred by the user, wherein the determination unit determines the user's state based on the information. (6) A suggestion system that proposes suggestions to support a user's behavior change, comprising: a reception unit that accepts input of the activity preferred by the user and the activity that the user is desired to be encouraged to perform; a generation unit that generates suggestion content that stimulates the user's intrinsic motivation by partially replacing or modifying the behavior that the user is desired to be encouraged to perform with the activity preferred by the user; and a presentation unit that presents the suggestion content to the user.(Clause 7) A suggestion method, in which a suggestion system that suggests suggestions to support a user's behavior change performs the following processes: accepting input of activities that a user likes and actions that the user wants to encourage the user to perform, generating suggestion content that stimulates the user's intrinsic motivation by partially replacing or modifying the actions the user wants to encourage the user to perform with the user's preferred activities, and presenting the suggestion content to the user. (Clause 8) A program, or a storage medium that stores a program, that causes a computer that suggests suggestions to support a user's behavior change to perform the following processes: accepting input of activities that a user likes and actions the user wants to encourage the user to perform, generating suggestion content that stimulates the user's intrinsic motivation by partially replacing or modifying the actions the user wants to encourage the user to perform with the user's preferred activities, and presenting the suggestion content to the user.

[0125] Although the present embodiment has been described above, the present invention is not limited to such a specific embodiment, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

[0126] This application claims priority from PCT / JP2024 / 017631, filed May 13, 2024, the entire contents of which are incorporated herein by reference.

[0127] (References) Reference 1: Ayano, G., "Dopamine: Receptors, Functions, Synthesis, Pathways, Locations and Mental Disorders: Review of Literatures", Journal of Mental Discorders and Treatment. 2016, vol. 2, issue 2, 1000120. Reference 2: Berke, JD, "What does dopamine mean?", Nature Neuroscience. 2018, vol. 21, no. 6, p. 787-793. Reference 3: Koepp, MJ et al., "Evidence for striatal dopamine release during a video game", Nature. 1998, vol. 393, p. 266-268. Reference 4: Takahashi, K. et al., "Imaging the passionate stage of romantic love by dopamine dynamics", Frontiers in human neuroscience. 2015, vol.9, 191. Reference 5: Takahashi, H. et al., "Dopamine D1 Receptors and Nonlinear Probability Weighting in Risky Choice", Journal of Neuroscience. 2010, vol. 30, issue 49, p. 16567-16572.

[0128] 1 Proposal module 10 External module 11 LLM (Generation AI) 12 Acceptance part 100 Proposal device 101 Payment part 102 Generation part 103 Presentation part 801 Acquisition part 802 Judgment part 803 Decision part 811 Generate AI 1700 コンピュータ

Claims

1. A suggestion device that proposes suggestions to support a user's behavioral change, comprising: a receiving unit that receives input of activities preferred by the user and actions that the user wishes to encourage the user to perform; a generating unit that generates suggestion content that stimulates the user's intrinsic motivation by partially replacing or modifying the actions that the user wishes to encourage the user to perform with the activities preferred by the user; and a presenting unit that presents the suggestion content to the user.

2. The suggestion device of claim 1, wherein the activity preferred by the user is an activity that the user naturally enjoys and that is the target of dopamine secretion-promoting behavior based on neuroscientific knowledge, and the generation unit generates the suggestion content that promotes the user's dopamine secretion.

3. The suggestion device according to claim 1 or 2, wherein the reception unit receives answers regarding the user's preferred activities using questions including words that express emotions corresponding to dopamine secretion-promoting behaviors.

4. A suggestion device as described in claim 1 or 2, comprising: a judgment unit that judges the user's state, including the user's motivation for the behavior that the user is desired to be encouraged to perform, or the user's busyness; and a decision unit that determines an activity preferred by the user that partially replaces or modifies the behavior that the user is desired to be encouraged to perform, based on the user's state.

5. A suggestion device as described in claim 4, further comprising an acquisition unit that acquires information indicating the user's positive emotions and / or the intensity of the degree to which the activity preferred by the user induces impulses in the user, and the frequency of the activity preferred by the user, and the determination unit determines the state of the user based on the information.

6. A proposal method in which a proposal system that proposes proposals to support a user's behavioral change performs the following processes: accepting input of activities preferred by the user and actions that the user wishes to encourage the user to perform; generating proposals that stimulate the user's intrinsic motivation by partially replacing or modifying the actions that the user wishes to encourage the user to perform with the activities preferred by the user; and presenting the proposals to the user.

Images