Behavioral support system, behavioral support method, and behavioral support program

Abstract

By using nudges based on behavioral factors, we can more effectively support behavioral change in target individuals. do. The behavior support system of the present invention associates a plurality of behavioral factors with each other and A storage unit 101 for storing a plurality of messages for promoting transformation, and subject information regarding the subject status information indicating the subject's status for each of the plurality of behavioral factors based on the information a prediction unit 102 for predicting the state of the message; and a storage unit 101 for storing one or more messages based on the state information. a generation unit 103 that selects one or more messages and generates a message set including the one or more messages; Controlling the output of the one or more messages in the message set to the target person The control unit 105 is provided.

Description

[Technical field]

[0001] The present invention relates to an action support system, an action support method, and an action support program. [Background technology]

[0002] In recent years, we have developed services that use approaches based on theories of behavioral science, which is the scientific study of human behavior. Efforts to utilize AI for development are spreading in various fields such as public policy, medicine, retail, and education. In addition, we will develop technology to support behavioral change and habit formation for subjects in various fields. Systems that can achieve this are also being considered (for example, Patent Document 1).

[0003] In the system described in Patent Document 1, various data measured on the behavior of multiple subjects are Based on the results of the analysis of the behavioral data, the goal of forming a habit is Stage indicators are indicators that serve as standards for multiple stages leading to the action of the target. defining each of the plurality of stages according to a stage index; For each stage pair, identify the gap between the two stages that make up the pair. The reasons for the identified gaps and the high At least one of the measures to induce behavioral change to transition to the stage of Identify the reasons / measures for the gap from the relationship information that defines the relationship between the gap and the reasons / measures, It is stated that the process for the reason / measures identified for each stage pair will be carried out. There are. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-140596 A Summary of the Invention [Problem to be solved by the invention]

[0005] By the way, in order to encourage behavioral change in subjects, nudges based on the behavioral factors of the subjects are used. Behavioral factors are the factors that cause humans to take action. However, Using only behavioral nudges does not effectively promote behavioral change in targets There is a risk.

[0006] Therefore, the present invention utilizes nudges based on behavioral factors to more effectively change the behavior of subjects. To provide a behavioral support system, a behavioral support method, and a behavioral support program that effectively support This is one of the objectives. [Means for solving the problem]

[0007] The action support system according to one aspect of the present invention is a system for supporting actions by associating each of a plurality of action factors with each other. A memory section stores multiple messages to encourage behavioral change, and a memory section stores information about the subject. Based on the result, status information indicating the status of the subject with respect to each of the plurality of behavioral factors is predicted. a prediction unit for predicting a message size, a prediction unit for predicting a message size, and a prediction unit for predicting a message size; a message set generating unit that generates a message set including the one or more messages; a control unit for controlling output of the one or more messages in the message to the target person; .

[0008] According to this embodiment, status information indicating the status of the subject with respect to each of the plurality of behavioral factors is A message set including one or more messages that are predicted and selected based on the state information. This generates a message set (i.e., information bundle) that is optimal for changing the target person's behavior. It is possible to generate such information and use nudges based on behavioral factors to promote behavioral change in the target individuals.

[0009] In the above aspect, the generation unit is configured to generate a signal from the storage unit, the state information being sufficient to cause the behavioral change. one or more messages each associated with one or more behavioral factors indicating that the According to this embodiment, a message set appropriate for the behavioral change of the subject may be selected. It is possible to generate a set of information (i.e., an information bundle).

[0010] In the above aspect, the control unit is configured to: RCT information on the behavior change environment, environmental information on the behavior change environment, and responses from the subjects Response information regarding the pons, and a prediction made by the prediction unit based on the subject information. The one or more messages to the subject are then sent based on at least one of the predicted behavior change probabilities. According to this embodiment, the message set (i.e., information Since the message output is controlled from within the message bundle, it is possible to more effectively support the behavioral change of the target person. I can help.

[0011] In the above aspect, the RCT information is in the order of time periods when the one or more messages are output. ranking, frequency ranking, the subject information and / or the status information and the message set a message set that is generated based on the message order of the message; At least one of the following may be indicated.

[0012] In the above aspect, the subject information includes attributes of the subject, a behavior history of the subject, The risk of not changing the subject's behavior and the risk of receiving a low response from the subject. At least one may be indicated.

[0013] In the above aspect, the plurality of behavioral factors include an experiential attitude, an instrumental attitude, an instructional norm, a memory Predicative norms, sense of control, self-efficacy, knowledge, skills, importance of behavior, environmental constraints , habituation.

[0014] A behavior support method according to another aspect of the present invention includes a behavior support device that receives subject information regarding a subject. Based on the above, state information indicating the state of the subject with respect to each of a plurality of behavioral factors is predicted. and the action support device performs a behavioral change in association with each of the plurality of behavioral factors. A storage unit stores a plurality of prompting messages, and outputs one or more messages based on the status information. selecting a message from the one or more messages and generating a message set including the one or more messages; The behavior support device responds to the target of the one or more messages in the message set. and controlling the output of the light source.

[0015] A behavior support program according to another aspect of the present invention includes a computer that executes a program for executing a program for a subject. status information indicating a state of the subject with respect to each of a plurality of behavioral factors based on the subject information and a step of predicting a behavioral change by associating the behavioral factors with each of the behavioral factors. selecting one or more messages from a storage unit that stores the messages based on the status information; generating a message set including the one or more messages; controlling output of the one or more messages in the message bar to the subject; Can. Effect of the Invention

[0016] According to the present invention, a nudge based on behavioral factors is used to more effectively change the behavior of a subject. We can provide support to: [Brief description of the drawings]

[0017] [Figure 1] 1 is a diagram illustrating an example of a schematic configuration of a behavior support system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of an apparatus in the action support system according to the present embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of the functional configuration of an apparatus in the action support system according to the present embodiment. [Figure 4] FIG. 13 is a diagram illustrating an example of a nudge message according to the embodiment. [Diagram 5] FIG. 11 is a diagram showing an example of subject information according to the embodiment; [Figure 6] FIG. 4 is a diagram showing an example of state information according to the embodiment; [Figure 7] FIG. 2 is a diagram illustrating an example of a nudge message set according to the embodiment. [Figure 8] FIG. 8 is a flowchart showing an example of the operation of the action support system according to this embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] An embodiment of the present invention will be described with reference to the accompanying drawings. Those marked with the same symbol have the same or similar configuration.

[0019] (Configuration of the behavior support system) <Outline configuration> FIG. 1 is a diagram showing an example of a schematic configuration of a behavior support system according to the present embodiment. As shown, the behavior support system 1 includes a behavior support device 10, a behavior analysis device 20, and a terminal 30. Includes.

[0020] The behavior support device 10 is a device that provides a message using a nudge based on a behavior factor (hereinafter, “nudge”). The behavior analysis device 20 is an information processing device that provides a terminal 30 with a message (hereinafter referred to as a "message"). An information processing device that generates a nudge message provided to a terminal 30 by the action support device 10 The terminal 30 is a terminal used by a person who is a target of behavioral change, and is, for example, a smartphone. The device may be any of various information devices such as smartphones, mobile phones, tablets, and personal computers. The terminal 30 has a function for receiving messages such as short messages and e-mails, for example, a LIN E (registered trademark) and other social networking services (SNS) are available. It shall be so.

[0021] Below, we will explain the above behavioral factors using the Integrated Behavioral Model (IB). Examples of behavioral factors include those defined by the International Business Machines Organization (IM) (also known as "IBM factors"). What factors related to human behavioral intentions, such as factors stipulated in behavioral models other than BM, This is also possible.

[0022] <Hardware configuration> FIG. 2 shows an example of the hardware configuration of the device in the action support system according to this embodiment. As shown in FIG. 2, each device in the action support system 1 (for example, the action support device 1 Each of the terminals 30, 30, and 40 has a central processing unit (CPU) that corresponds to a computing device. A processor 11 such as a processing unit (SMU), a storage device 12, a communication device 13, and an input / output device 1 These components are connected to each other via a bus so as to be able to transmit and receive data.

[0023] In this example, the behavior support device 10 and the behavior analysis device 20 are shown as separate devices. However, they may be configured as an integrated device. For example, it may be realized as different operations of a PLC (Programmable Logic Controller). In addition, at least one of the behavior support device 10, the behavior analysis device 20, and the terminal 30 may be a plurality of devices. The position may be divided into

[0024] The processor 11 is, for example, a CPU (Central Processing Unit), and 2 is a control unit that controls the execution of the programs stored in the The processor 11 receives various input data from an input / output device 14 and / or a communication device 13. The input data is input to the input / output device 14, and the operation result is output (for example, displayed) to the input / output device 14. The information is stored in the device 12 or transmitted via the communication device 13.

[0025] The storage device 12 may be a memory, a hard disk drive (HDD), or a solid state drive (SSD). The memory device 12 of the action support device 10 is a The storage device 12 may be called a "storage unit" or the like. This is also fine.

[0026] The communication device 13 is a device that communicates via a wired and / or wireless network, e.g. For example, it may include a network card, a communication module, a chip, an antenna, etc. When the support device 10 and the behavior analysis device 20 are configured as an integrated device, the communication device 13 A process for operating as the behavioral support device 10 and a process for operating as the behavior analysis device 20 The communication device 13 may be referred to as a "sender" or a "receiver", etc. It's okay to be found out.

[0027] The input / output device 14 is, for example, a keyboard, a touch panel, a mouse, and / or a microphone. It includes input devices and output devices such as a display and / or a speaker. The device may be referred to as an "input section" or an "output section", etc.

[0028] The hardware configuration described above is merely an example. Each device in the action support system 1 is Some of the hardware shown in FIG. 2 may be omitted, or a part not shown in FIG. The hardware shown in FIG. 2 may be one or more chips. The optical fiber may be configured as follows.

[0029] <Functional configuration> FIG. 3 is a diagram illustrating an example of the functional configuration of devices in the action support system according to the present embodiment. Note that FIG. 3 is merely an example, and each device in the action support system 1 has a function not shown. Of course, it is also good.

[0030] ≪Behavior analysis device≫ As shown in FIG. 3, the behavior analysis apparatus 20 includes an acquisition unit 201 and a generation unit 202. At least a part of the functions realized by the acquisition unit 201 is realized by using the communication device 13. In addition, at least a part of the functions realized by the acquisition unit 201 and the generation unit 202 can be The processor 11 executes a program stored in the storage device 12 to realize the above. The program can be stored in a storage medium. The storage medium storing the RAM is a non-transitory computer-readable storage medium. The non-transitory storage medium is not particularly limited. However, it may be a storage medium such as a USB memory or a CD-ROM.

[0031] The acquisition unit 201 acquires information on the process for behavioral change (hereinafter, “behavioral process information”). The behavioral process information includes, for example, the areas in which behavioral change is encouraged, Indicate at least one of the following: the range of interventions for the prevention of behavioral changes, the success rate of behavioral change, and the failure rate of behavioral change. For example, if the area to promote behavior change is "use of medical examinations or health checks," The success rate of behavioral change is the rate of people taking the screening or health check, and the failure rate of behavioral change is the rate of people dropping out of the screening or health check. The acquisition unit 201 may transmit the behavior process information to other devices via the communication device 13. The information may be acquired from the device or via the storage medium.

[0032] The generation unit 202 generates a plurality of Generate multiple nudge messages that correspond to the IBM factors. The message is generated to encourage behavioral change for each IBM factor. For example, the generation unit 202 A trained machine learning model may be used to generate the multiple nudge messages. When the behavioral process information acquired by the acquisition unit 201 is input, the machine learning model Such machine learning models are trained to output a set of neural network-based messages. The network is implemented by using pairs of behavioral process information and nudge messages as training data. It may be trained by supervised learning using the

[0033] FIG. 4 is a diagram showing an example of a nudge message according to the present embodiment. As shown in FIG. A nudge message is associated with each of the multiple IBM factors. The IBM factors are, for example, experiential attitude, instrumental attitude, ental attitude), injunctive norm, descriptive norm , perceived control, self-efficacy, knowledge owledge, skills, salience of the behavior, environmental constraints The criteria may include at least two of the following: environmental constraints, and habit.

[0034] Note that the IBM factors shown in FIG. 4 are merely examples and are not limited to those shown in the figure. At least two of the IBM Factors shown below are subsumed and defined as higher level IBM Factors. For example, the above-mentioned experiential attitude and instrumental attitude are included in "Attitude", The above directive and descriptive norms are included in the "perceived norm" and the above behavioral concept is The sense of control and self-efficacy are included in "Personal Agency" and and technology are included in "Knowledge," and the importance of an action is "Importance." " and environmental constraints may be included in "Friction". A single IBM factor shown in the table may be split up to define multiple lower-level IBM factors. Nudge messages may be associated with any level of IBM factor.

[0035] As shown in Figure 4, each of the multiple IBM factors has an IBM factor identifier (hereinafter, The IBM ID and the nudge message may be associated with each other. For example, the target group may be "residents of a certain city" and the behavioral change group may be "specific health checkups (hereinafter, "specific A nudge message is displayed that assumes the recommendation to undergo a regular health check. The corresponding nudge message is designed to encourage behavioral change in the target person by taking into account each IBM factor. In Figure 4, one nudge message is associated with each IBM factor. However, multiple nudge messages may be associated with each IBM factor. The IBM ID for identifying the M factor is not limited to the one illustrated.

[0036] The nudge message generated by the generation unit 202 is transmitted to the action support device 13 via the communication device 13. Alternatively, the nudge message may be output to the storage medium, The information may be input to the action support device 10 via the storage medium.

[0037] ≪Behavior support device≫ As shown in FIG. 3, the action support apparatus 10 includes a storage unit 101, a prediction unit 102, a generation unit 103, and a The device includes an acquisition unit 104 and a transmission control unit 105. The functions realized by the acquisition unit 104 are as follows: At least a part of the above can be realized by using the communication device 13. The generation unit 103 and the transmission control unit 105 are configured as follows: This can be realized by executing a behavioral support program. The program can be stored in the above-mentioned storage medium. This can be achieved using 2.

[0038] The storage unit 101 stores a plurality of nudge messages ( For example, the nudge messages shown in FIG. 4 are stored. The nudge messages are generated by the behavior analysis device 20. Alternatively, the information may be input from the input / output device 14 of the action support device 10. good.

[0039] The storage unit 101 stores information about the subject (hereinafter, referred to as "subject information"), Environmental information for the purpose of T) (hereinafter referred to as "RCT information") do.

[0040] Here, the subject information stored in the storage unit 101 includes identification information of the subject, attributes of the subject, Information regarding the Target Person's behavior history (hereinafter referred to as "attribute information"), information on the risk if the subject does not change his / her behavior (hereinafter (hereinafter, "Risk Information") and information regarding responses from the subjects (hereinafter, "Response Information") The method may include at least one of the following:

[0041] FIG. 5 is a diagram showing an example of subject information according to the present embodiment. For example, in FIG. The target person is a "resident of XX city" and the behavioral change is "taking a specific health check (e.g., a medical examination)." Examples of subject information are shown below.

[0042] In FIG. 5, the subject information includes, as identification information of the subject, information indicating the subject ID, The attribute information of the subject may include, for example, information indicating age and gender, and the behavior history information may include, for example, For example, information showing the history of specific health checkups of the subject, risk information, Information indicating the risk of a person contracting a particular disease (hereinafter referred to as "disease risk") and For example, the responses to the questionnaire given to the subjects (hereinafter referred to as "questionnaire responses") may be used as response information. Information showing the same may be included.

[0043] The subject information is not limited to that shown in FIG. 5. For example, in FIG. 5, The history of specific health checkups for the most recent specified number of years is shown as the "special health checkup history", but the behavioral history of the subject is not shown. Any information is acceptable. Attribute information is not limited to the subject's age and gender. It can be any information related to the attributes of the subject. Some of the information may not be included, or information not shown about the subject may be included.

[0044] In addition, the environmental information stored in the storage unit 101 may be, for example, information about a specific administrative unit (e.g., If the target population is residents of a city, and the behavioral change is to undergo a specific health checkup, the date and time of the specific health checkup The information may be, for example, information indicating a medical institution where the specific medical examination can be performed. The boundary information includes the maximum number of times a nudge message is sent to the target person and the reward for behavioral change. The remuneration information may include, for example, information on the subject If the target is "residents of a certain administrative unit" and the behavioral change is "participating in a specific health checkup," the target is expected to It may be the expected life extension effect, the expected tax amount, etc.

[0045] In addition, the RCT information is ranked by sending date (e.g., weekdays, Monday to Sunday, holidays, etc.), Prioritization of transmission time periods (e.g., morning, afternoon, night, etc.), and transmission frequency (e.g., monthly, biweekly, monthly, etc.), compatibility of target information with nudge message set, nudge message and a transmission order of the nudge messages in the nudge set. .

[0046] The prediction unit 102 predicts each of the plurality of IBM factors based on the subject information about the subject. The information indicating the subject's condition (hereinafter referred to as "condition information") is predicted. 6 is a diagram showing an example of state information according to the present embodiment. As shown in FIG. It may also indicate for each IBM factor whether the subject's condition is sufficient for behavior change.

[0047] For example, the state information shown in Figure 6 is based on multiple IBM factors (here, experiential attitude, instrumental attitude, etc.). degree, indicative norms, descriptive norms, sense of control, self-efficacy, knowledge and skills, behavior For each of the three categories (importance, environmental constraints, and habituation), the state of each subject is related to behavioral change (e.g. For example, the subject ID in Figure 6, "3" indicates whether the The state information of the subject of "Subject #3" was based on three IBM factors: "Experienced State" "Level of competence," "knowledge and skills," and "environmental constraints" are insufficient for behavioral change. It shows that other IBM factors are sufficient for behavioral change. State information that indicates that the state of affairs is not sufficient for behavior change may be called missing information. Also, Figure 6 is only an example, and some items (e.g., IMB ID, major items, medium items, etc.) may be omitted.

[0048] The prediction unit 102 receives the above-mentioned state information in addition to the subject information acquired by the acquisition unit 104. Information regarding responses from subjects (hereinafter referred to as "Response Information") (c) The prediction may be based on at least one of environmental information and RCT information. The unit 102 may generate the above-mentioned state information by using a trained machine learning model. The machine learning model uses the above subject information (as well as response information, environmental information, and R The system is trained to output the above status information when the user inputs at least one of the following: Such a machine learning model is realized as a neural network, and the above subject information is used information (and at least one of response information, environment information, and RCT information) and status information It may be trained by supervised learning using the pairs as training data.

[0049] In addition, the prediction unit 102 predicts a behavioral change of the subject based on the subject information of the subject. The probability of a behavior change occurring may be predicted based on, for example, The probability that a subject will achieve behavioral change without any intervention for that subject's behavior change (hereinafter, For example, the probability of non-intervention behavior of subject #3 in FIG. 6 is 70 % and, if no behavior change intervention is implemented, there is a 70% chance of behavior change being achieved. The probability of behavioral change is not limited to this, and it is possible to estimate the probability of behavioral change without the above intervention. The probability of not achieving the intervention, and whether or not the subject achieves behavioral change when the intervention is administered. It may be a probability or the like.

[0050] In addition, the prediction unit 102 adds the above-mentioned behavior change probability to the subject information and acquires the behavior change probability from the acquisition unit 10 A prediction is made based on at least one of the response information, the environmental information, and the RCT information obtained in 4. The prediction unit 102 may predict the above-mentioned behavior change probability using a trained machine learning method. The machine learning model may be generated using the subject information (and When at least one of the following information is entered, the behavioral changes Such machine learning models are trained to output probability of success. The above subject information (as well as response information, environmental information, and RCT information) A pair of the behavior change probability and the behavior change probability is used as training data. So you may be trained.

[0051] The generation unit 103 stores the state information in the storage unit 203 based on the state information predicted by the prediction unit 102. A set of one or more nudge messages (hereinafter, “nudge messages”) that can be delivered to the target person is selected from the Specifically, the generation unit 103 selects a message set (hereinafter referred to as a “message set”) based on the state information. Nudge messages associated with IBM factors that indicate insufficient conditions for behavioral change A nudge message set is generated that includes at least the nudge message.

[0052] FIG. 7 is a diagram showing an example of a nudge message set according to the present embodiment. Thus, the nudge message set for subject #3 is nudge messages #1 to #4. Nudge messages #2 to #4 are used to change the behavior of subject #3 based on the state information. The three IBM factors that were shown to be insufficient were "experience, attitude," "knowledge and skills," and " On the other hand, nudge message #1 corresponds to "techniques" and "environmental constraints", respectively. The nudge message set is not related to the IBM factor. , and are associated with IBM factors that indicate that the state information is insufficient for behavioral change. The nudge message may include not only the nudge message but also other nudge messages.

[0053] The acquisition unit 104 acquires response information from the subject. Here, the response information is For example, the nudge message is information showing the response from the target person who viewed the message. Regarding the use of short messages (SM) and e-mails, including message messages, and behavioral changes The situation in which the patient is diagnosed (e.g., reservation status for a specific health checkup), the results of behavioral changes (e.g., results of taking a specific health checkup) The acquisition unit 104 may receive the response information from the terminal 30 of the target person in real time. It may also be obtained by time.

[0054] The transmission control unit 105 selects one of the nudge message sets selected by the generation unit 103. The transmission of the above nudge messages to the target person is controlled by the transmission control unit 105. Then, the communication device 13 of the action support device 10 transmits a nudge message to the terminal 30 of the subject. Send.

[0055] Specifically, the transmission control unit 105 receives the RCT information, the environmental information, And, based on at least one of the response information acquired by the acquisition unit 104, The system controls the transmission of one or more nudge messages to a target person. The sending control of messages can include, for example, sending multiple nudge messages in a nudge message set. The order, the date and time of each nudge message, the time period in which each nudge message was sent, The time interval between sending nudge messages (frequency of sending), the time to stop sending each nudge message, This may include control of the number of times a message is sent.

[0056] For example, in the case of the nudge message set for target person #3 shown in FIG. 05 provides nudges based on at least one of RCT information, environmental information, and response information. Send nudge messages to target person #3 in the order of messages #1, #2, #3, and #4. In addition, the transmission control unit 105 determines whether the RCT information, the environment information, and the response information Based on at least one of the above, the sending date, sending time period, and sending time of nudge messages #1 to #4 are At least one of the interval, transmission suspension, and transmission count is determined.

[0057] For example, the transmission control unit 105 transmits the nudge messages #1 to #3 in FIG. If the acquisition unit 104 subsequently acquires response information that is positive about the behavioral change, On the other hand, a user may stop sending negative nudge messages in response to a nudge message. If response information is obtained, the transmission control unit 105 retransmits the nudge message. Alternatively, a subsequent nudge message may be sent.

[0058] Thus, instead of sending a set of nudge messages for target #3 to target #3 at once, In addition, multiple nudge messages in the nudge message set are distributed multiple times to Even if a single nudge message is rich in information, humans may overlook it. Therefore, multiple nudge messages may be more effective in promoting behavioral change. Therefore, by distributing the nudge message multiple times, the Nudge messages have the effect of promoting behavioral change among target groups that do not change their behavior. It can be improved.

[0059] In addition, the transmission control unit 105 performs a transmission based on the response information acquired by the acquisition unit 104. Specifically, the prediction unit 102 may transmit a subsequent nudge message updated based on the received nudge message. The state information is updated based on the response information, and the generating unit 103 generates the state information based on the updated state information. The nudge message set may be updated based on the target person's response information. By updating the nudge message sent to the target person based on the This allows for more effective nudge messages to be sent by encouraging participation.

[0060] In addition, the transmission control unit 105 performs the following on the basis of the behavior change probability predicted by the prediction unit 102: One or more nudge messages in the nudge message set generated by the generation unit 103 For example, the transmission control unit 105 may control the transmission of the non-intervention behavior message when the non-intervention behavior probability meets a predetermined condition ( For example, for subjects who meet a certain threshold, the Alternatively, the number of transmissions or the frequency of transmissions may be increased. , a target whose non-intervention behavior probability satisfies a predetermined condition (e.g., greater than or equal to a predetermined threshold, etc.) For those who receive nudge messages, we will send them less frequently or less frequently. This is also fine.

[0061] In addition, the transmission control unit 105 detects information that changes due to various factors (hereinafter, referred to as "changed information"). Based on the nudge message set generated by the generation unit 103, one or more The sending of nudge messages may be controlled. For example, the change information may be, for example, The information may be the stock status of Kuching, the availability of appointments for health checkups or medical examinations, or free time. The transmission control unit 105 receives information about the convenience of the subject (for example, information about the convenience of the subject The generated name is generated by the generating unit 103 based on the time and / or place of the The nudge message set may control the sending of one or more nudge messages in the nudge message set.

[0062] The above-described transmission control by the transmission control unit 105 is realized by solving a resource allocation problem. For example, the state information and the behavior change probability predicted by the prediction unit 102, Environmental information stored in the storage unit 101, and a nudge message generated by the generation unit 103 At least one of the sets may be used to initialize the resource allocation problem. The control unit 105 regards all nudge messages and all target persons stored in the storage unit 101 as an environment, The total number of nudge messages is treated as a solution space, and the maximum number of times that a nudge message is sent to each target is calculated. The number of players is set as a budget, and the total reward obtained during the target period is set as the cumulative reward to solve the resource allocation problem. The transmission control may be performed by the above.

[0063] (Behavioral Support System Operation) FIG. 8 is a flowchart showing an example of the operation of the action support system according to this embodiment. Note that the operation of the action support system shown in FIG. 8 is merely an example and is not limited to the illustrated example. .

[0064] As shown in FIG. 8, in step S101, the action support apparatus 10 Based on the above, the action support device 10 predicts the state information of the subject (for example, FIG. 6). Based on the subject information, the probability of behavior change (e.g., the probability of non-intervention behavior) may be predicted. The action support device 10 receives the nudge message transmitted by the transmission control in step S103. Based on at least one of the response information to the message, the environmental information, and the RCT information, The behavioral information and / or behavior change probability may be predicted or updated.

[0065] In step S102, the action support apparatus 10 calculates the state predicted in step S101. Based on the information, a set of nudge messages (e.g., FIG. 7) is generated for the subject.

[0066] In step S103, the action support apparatus 10 The behavior support device 10 controls the transmission of one or more nudge messages in the nudge message set. is the response information, environment information, and RCT information for the previously sent nudge message. The sending of the one or more nudge messages may be controlled based on at least one of:

[0067] According to the action support system 1 of this embodiment, by using nudges based on action factors, It is possible to more effectively support the behavioral change of the subject. More specifically, the behavioral support system 1 In this case, the state information indicating the state of the subject for each of the multiple IBM factors is predicted, and a nudge message set including one or more nudge messages selected based on the state information; This generates a set of nudge messages (i.e. It is possible to generate a set of information (i.e., information bundle).

[0068] In addition, in the above-mentioned action support system 1, a nudge message set as shown in FIG. Instead of sending multiple nudge messages to a target person at once, multiple nudge messages in a nudge message set are sent to the target person. By distributing the message to the target person in multiple parts, the effect of promoting behavioral change in the target person can be increased. In addition, the subsequent actions can be determined based on the response information to the nudge message. By controlling the sending of nudge messages and / or updating the content, the target person’s actions can be This can support dynamic transformation more effectively.

[0069] The above-described embodiment is intended to facilitate understanding of the present invention and does not limit the present invention. The elements of the embodiment and their arrangements, materials, conditions, etc. The shape and size are not limited to those shown in the examples and can be changed as appropriate. In addition, configurations shown in different embodiments may be partially substituted or combined. It is Noh.

[0070] For example, in the above embodiment, the subject is “residents of XX city” and the behavior change is The assumption is made that "particular medical examinations (e.g., medical examinations) will be taken," but this is not limited to this. This is not limited to users of the service, but may also include users of various other services such as English conversation and qualification examinations. In addition, behavioral change is not limited to the use of government services, but also includes continuing learning, taking advantage of various services, etc. It may be for use etc.

[0071] In the above embodiment, R The sending of one or more messages to a target person is controlled based on the CT information. The causal inference methods used to control message transmission are not limited to exploratory RCTs. As the causal inference method, for example, other methods such as propensity score matching may be used. In addition, an exploratory RCT can also be called a trial and / or small-scale RCT, and the message sent Any pilot for parameter setting used in signal control. This is also fine.

[0072] In addition, the nudge message in the above embodiment is in a text format including character strings and symbols. However, the information may be predetermined information including audio, video, images, etc. In this case, the transmission control unit 105 of the action support device 10 controls the transmission of the nudge message. However, the present invention is not limited to this, and the action support apparatus 10 may output a nudge message (for example, In addition, a control unit for controlling the display, audio output, etc. may be provided. In the embodiment, the "transmission" of the nudge message may be replaced with display, audio output, output, etc. In addition, the terminal 30 is not limited to a terminal used by a specific person, but may be used by an unspecified person. The display may be a signage, an electronic bulletin board, a speaker, etc. that outputs information for users.

[0073] For example, the action support device 10 detects the population density in a specific space (such as a train station or a restaurant) When the probability of non-intervention is high and exceeds a certain level, a nudge message that "disperses people" The message is transmitted to a terminal 30 (for example, a signage, an electronic bulletin board, a speaker, etc.) and The action support device 10 may output (for example, display, audio output, etc.) from the terminal 30. Even if the terminal 30 that outputs the nudge message to the target person is provided as an integrated device, The action support device 10 often transmits a nudge message to the terminal 30. It may also be for internal communication within a body-type device. [Explanation of symbols]

[0074] 1... behavior support system, 10... behavior support device, 20... behavior analysis device, 30... terminal, 11... Processor, 12... storage device, 13... communication device, 14... input / output device, 101... storage unit, 1 02: prediction unit, 103: generation unit, 104: acquisition unit, 105: transmission control unit, 201: acquisition unit , 202...Generation section, 203...Storage section

Claims

1. a storage unit that stores a plurality of messages for encouraging behavioral change in association with a plurality of behavioral factors; a prediction unit that inputs subject information about a specific subject into a machine learning model based on supervised learning that uses, as training data, pairs of subject information about a specific subject and status information indicating whether or not the status of the specific subject is sufficient for the behavioral change for each of the multiple behavioral factors, and predicts status information indicating whether or not the status of the specific subject is sufficient for the behavioral change for each of the multiple behavioral factors; a generation unit that, when the predicted state information indicates that the state of the specific subject is not sufficient for the behavioral change with respect to one or more of the plurality of behavioral factors, selects one or more messages associated with the one or more behavioral factors in the storage unit, and generates a message set including a plurality of messages including the one or more messages and messages not associated with the one or more behavioral factors; a control unit that controls output of the plurality of messages in the message set to the specific target person, The control unit outputs, to the specific target person, the message not associated with the one or more behavioral factors and the one or more messages associated with the one or more behavioral factors. Behavioral support system.

2. An acquisition unit that acquires response information from the specific target person in response to the output message, The prediction unit updates the state information based on the response information; The control unit updates subsequent messages to be sent to the specific target person based on the updated status information. The behavior support system according to claim 1 .

3. The control unit controls the output of the plurality of messages to the specific subject based on at least one of: RCT information on the results of an exploratory randomized controlled trial (RCT); environmental information on the environment for the behavior change; response information on a response from the subject; and a behavior change probability predicted by the prediction unit based on the subject information. The behavior support system according to claim 1 or 2.

4. The RCT information indicates at least one of a ranking of time periods for outputting the plurality of messages, a ranking of frequency, a compatibility between the subject information and / or the status information and the message set, and a ranking of an output order of the plurality of messages in the message set. The behavior support system according to claim 3 .

5. The subject information indicates at least one of the attributes of the subject, the behavioral history of the subject, the risk of the subject not changing his / her behavior, and a response from the subject. The behavior support system according to any one of claims 1 to 4.

6. The plurality of behavioral factors include at least two of experiential attitudes, instrumental attitudes, directive norms, descriptive norms, sense of behavioral control, self-efficacy, knowledge, skills, importance of behavior, environmental constraints, and habituation; The behavior support system according to any one of claims 1 to 5.

7. a step in which a behavior support device inputs subject information about a specific subject into a machine learning model based on supervised learning using, as training data, a pair of subject information about the subject and status information indicating whether or not the status of the specific subject is sufficient for behavioral change for each of a plurality of behavioral factors, and predicts status information indicating whether or not the status of the specific subject is sufficient for behavioral change for each of the plurality of behavioral factors; a step of the behavior support device, when the predicted state information indicates that the state of the specific subject is not sufficient for the behavioral change with respect to one or more of the plurality of behavioral factors, selecting one or more messages associated with the one or more behavioral factors in a storage unit that stores a plurality of messages for encouraging behavioral change in association with the plurality of behavioral factors, and generating a message set including the one or more messages and a message not associated with the one or more behavioral factors; The action support device controls output of the plurality of messages in the message set to the specific target person, In the controlling step, the action support device outputs, to the specific subject, the message not associated with the one or more behavioral factors and the one or more messages associated with the one or more behavioral factors. Behavioral support methods.

8. On the computer, A process of inputting subject information about a specific subject into a machine learning model based on supervised learning that uses pairs of subject information about a subject and status information indicating whether or not the status of the specific subject is sufficient for behavioral modification for each of a plurality of behavioral factors as training data, and predicting status information indicating whether or not the status of the specific subject is sufficient for behavioral modification for each of the plurality of behavioral factors; a step of selecting one or more messages associated with the one or more behavioral factors in a storage unit that stores a plurality of messages for encouraging behavioral change in association with the plurality of behavioral factors, respectively, when the predicted state information indicates that the state of the specific subject is not sufficient for the behavioral change, and generating a message set including the one or more messages and a message not associated with the one or more behavioral factors; controlling output of the plurality of messages in the message set to the particular target audience; In the controlling step, the computer outputs, to the specific target person, the message not associated with the one or more behavioral factors and the one or more messages associated with the one or more behavioral factors; A behavioral support program to help people achieve these goals.

Images