JP7650464B2 - Behavioral support system, behavioral support method, and behavioral support program - Google Patents

Description

The present invention relates to a behavior support system, a behavior support method, and a behavior support program.

In recent years, efforts to utilize approaches based on theories of behavioral science, which is the scientific study of human behavior, in service development are spreading in various fields such as public policy, medicine, retail, education, etc. Systems that technically realize support for behavioral change and habit formation of subjects in these various fields are also being considered (for example, Patent Literature 1).

The system described in Patent Document 1 analyzes behavioral data including various data measured on the behavior of multiple subjects, and based on the results of the analysis of the behavioral data, defines a stage index, which is an index serving as a standard for multiple stages that gradually lead to a behavior as a goal of habituation, and each of the multiple stages according to the stage index; identifies a gap between the two stages that make up each pair of adjacent stages; and identifies, for each stage pair, reasons/measures that are at least one of the reason for the existence of the identified gap and measures to cause a subject belonging to the lower stage to change his/her behavior to transition to the higher stage, from relationship information that defines the relationship between the gap and the reasons/measures.
It is described that processing is carried out for the reasons/actions identified for each stage pair.

JP 2020-140596 A

By the way, in order to encourage behavioral change in subjects, the use of nudges based on the subjects' behavioral factors is being considered. Behavioral factors are factors that cause people to take action. However,
Only using nudges based on behavioral factors may not be effective in promoting behavioral change in targets.

Therefore, one of the objects of the present invention is to provide a behavior support system, a behavior support method, and a behavior support program that utilize nudges based on behavioral factors to more effectively support behavioral change in a subject.

The behavior support system according to one aspect of the present invention includes a memory unit that stores a plurality of messages for encouraging behavioral change, each corresponding to a plurality of behavioral factors; a prediction unit that predicts status information indicating a state of a subject for each of the plurality of behavioral factors based on subject information about the subject; and a prediction unit that selects one or more messages from the memory unit based on the status information.
The system includes a generation unit that generates a message set including the one or more messages, and a control unit that controls output of the one or more messages in the message set to the target person.

According to this aspect, status information indicating the status of the subject for each of a plurality of behavioral factors is predicted, and a message set including one or more messages selected based on the status information is generated, so that a message set (i.e., information bundle) optimal for changing the behavior of the subject is generated.
It is possible to generate such information and use nudges based on behavioral factors to promote behavioral change in the target individuals.

In the above aspect, the generation unit may select from the storage unit the one or more messages associated with one or more behavioral factors indicating that the state information is not sufficient for the behavioral change. According to this aspect, a message set (i.e., an information bundle) more appropriate for the behavioral change of the subject can be generated.

In the above aspect, the control unit may control the output of the one or more messages to the 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 responses from the subject, and a behavior change probability predicted by the prediction unit based on the subject information. According to this aspect, the output of messages from a message set (i.e., information bundle) is controlled, so that the subject's behavior change can be more effectively supported.

In the above aspect, the RCT information includes a ranking of time periods for outputting the one or more messages, a ranking of frequencies, a compatibility between the subject information and/or the status information and the message set, and a ranking of an output order of the one or more messages in the message set.
At least one of the following may be indicated.

In the above aspect, the subject information may indicate at least one of the attributes of the subject, the behavioral history of the subject, the risk in the absence of the behavioral change of the subject, and a response from the subject.

In the above aspect, the plurality of behavioral factors may include at least two of experiential attitudes, instrumental attitudes, indicative norms, descriptive norms, sense of behavioral control, self-efficacy, knowledge, skills, importance of behavior, environmental constraints, and habituation.

A behavior support method according to another aspect of the present invention includes a step of a behavior support device predicting status information indicating the subject's state for each of a plurality of behavioral factors based on subject information regarding the subject; a step of the behavior support device selecting one or more messages based on the status information from a memory unit that stores a plurality of messages for encouraging behavioral change in correspondence with each of the plurality of behavioral factors, and generating a message set including the one or more messages; and a step of the behavior support device controlling output of the one or more messages in the message set to the subject.

A behavioral support program according to another aspect of the present invention causes a computer to perform the steps of predicting status information indicating the subject's state for each of a plurality of behavioral factors based on subject information about the subject; selecting one or more messages based on the status information from a memory unit that stores a plurality of messages for encouraging behavioral change, each associated with the plurality of behavioral factors; generating a message set including the one or more messages; and controlling the output of the one or more messages in the message set to the subject.

According to the present invention, it is possible to more effectively support a subject's behavioral change by utilizing a nudge based on behavioral factors.

1 is a diagram illustrating an example of a schematic configuration of a behavior support system according to an embodiment of the present invention. 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. 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. FIG. 13 is a diagram illustrating an example of a nudge message according to the embodiment. FIG. 11 is a diagram showing an example of subject information according to the embodiment; FIG. 4 is a diagram showing an example of state information according to the embodiment; FIG. 2 is a diagram illustrating an example of a nudge message set according to the embodiment. 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 The present invention will be described with reference to the accompanying drawings, in which the same reference numerals denote the same or similar configurations.

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

The behavior support device 10 is an information processing device that provides a message using a nudge based on a behavioral factor (hereinafter referred to as a "nudge message") to a terminal 30. The behavior analysis device 20
The terminal 30 is an information processing device that generates a nudge message to be provided to the terminal 30 by the behavior support device 10. The terminal 30 is a terminal used by a target person for behavioral change, and may be, for example, any of various information devices such as a smartphone, a mobile phone, a tablet, or a personal computer.
The terminal 30 has a function for receiving messages such as short messages and e-mails, for example, a LIN
It is assumed that various social networking services (SNS) such as Yahoo! JAPAN Social Networking Service (SNS) and Yahoo! JAPAN Social Networking Service ... are available.

Below, we will use the Integrated Behavioral Model (IB) as the above behavioral factor.
Examples of behavioral factors include those defined by IBM (also called "IBM factors").
The factor may be any factor related to human behavioral intention, such as a factor defined by a behavioral model other than BM.

<Hardware Configuration>
2 is a diagram showing an example of the hardware configuration of devices in the action support system according to the present 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 includes 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.

In this example, the behavior support device 10 and the behavior analysis device 20 are shown as separate devices, but they may be configured as an integrated device. The multiple devices configured as an integrated device may be realized as different operations of a PLC (Programmable Logic Controller), for example. At least one of the behavior support device 10, the behavior analysis device 20, and the terminal 30 may be divided into multiple devices.

The processor 11 is, for example, a CPU (Central Processing Unit) and controls the storage device 1.
The processor 11 is a control unit that controls the execution of the programs stored in the memory 12 and performs calculations and processing of data. The processor 11 receives various input data from the input/output device 14 and/or the communication device 13, and outputs (e.g., displays) the calculation results of the input data to the input/output device 14, stores the calculation results in the memory device 12, or transmits the calculation results via the communication device 13.

The storage device 12 includes a memory, a hard disk drive (HDD), and a solid state drive (SSD).
, at least one of. The storage device 12 of the action support device 10 may store the action support program executed by the processor 11. The storage device 12 may be called a "storage unit" or the like.

The communication device 13 is a device that communicates via a wired and/or wireless network, and may include, for example, a network card, a communication module, a chip, an antenna, etc. When the behavior support device 10 and the behavior analysis device 20 are configured as an integrated device, the communication device 13 may include inter-process communication between a process operating as the behavior support device 10 and a process operating as the behavior analysis device 20. The communication device 13 may be called a "transmitter" or a "receiver", etc.

The input/output device 14 includes, for example, input devices such as a keyboard, a touch panel, a mouse, and/or a microphone, and output devices such as a display and/or a speaker. The input/output device may be called an "input unit" or an "output unit", for example.

The hardware configuration described above is merely an example.
Some of the hardware shown in Fig. 2 may be omitted, or hardware not shown in Fig. 2 may be included. Furthermore, the hardware shown in Fig. 2 may be configured with one or more chips.

<Functional configuration>
Fig. 3 is a diagram showing 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 may of course have a function not shown.

<Behavioral Analysis Device>
As shown in FIG. 3 , the behavior analysis device 20 includes an acquisition unit 201 and a generation unit 202. At least a part of the functions realized by the acquisition unit 201 can be realized using the communication device 13. At least a part of the functions realized by the acquisition unit 201 and the generation unit 202 can be realized using the communication device 13.
The above-mentioned functions can be realized by the processor 11 executing a program stored in the storage device 12. The program can be stored in a storage medium. The storage medium storing the program is a non-transitory computer-readable storage medium (Non-Transitory Storage Medium).
The non-transitory storage medium is not particularly limited, and may be, for example, a storage medium such as a USB memory or a CD-ROM.

The acquisition unit 201 acquires information on the process for behavioral change (hereinafter referred to as "behavioral process information"). The behavioral process information includes information indicating at least one of the following: the field in which behavioral change is encouraged, the range of intervention for the behavioral change, the success rate of behavioral change, and the failure rate of behavioral change. For example, if the field in which behavioral change is encouraged is "use of medical examinations or health checkups," the success rate of behavioral change may be the attendance rate of medical examinations or health checkups, and the failure rate of behavioral change may be the dropout rate of medical examinations or health checkups. The acquisition unit 201 may acquire the behavioral process information from another device via the communication device 13, or via the above-mentioned storage medium.

The generating unit 202 generates a plurality of nudge messages respectively associated with a plurality of IBM factors based on the behavioral process information acquired by the acquiring unit 201. The nudge messages are generated so as to encourage behavioral change for each IBM factor. For example, the generating unit 202
A trained machine learning model may be used to generate the multiple nudge messages.
The machine learning model is trained to output a nudge message when the behavioral process information acquired by the acquisition unit 201 is input. Such a machine learning model may be realized as a neural network and trained by supervised learning using pairs of behavioral process information and nudge messages as training data.

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

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 IBM factors shown in FIG. 4 may be included and defined as a higher level IBM factor. For example, the experiential attitude and the instrumental attitude are included in "Attitude",
The above directive and descriptive norms are included in the "perceived norm," the above sense of control over behavior and self-efficacy are included in the "personal agency," the above knowledge and skills are included in the "knowledge," and the importance of behavior is included in the "importance."
" and environmental constraints may be included in "Friction".
A single IBM factor shown in may be divided to define multiple lower level IBM factors. A nudge message may be associated with an IBM factor at any level.

As shown in FIG. 4, each of the multiple IBM factors is assigned an IBM factor identifier (hereinafter, “
A nudge message may be associated with a specific IBM ID (hereinafter referred to as an "IBM ID") and a nudge message. In FIG. 4, for example, a nudge message is shown assuming that a subject is a "resident of XX city" and a behavioral change is "recommended to undergo a specific health checkup (hereinafter referred to as a "specific health checkup"). A nudge message associated with each IBM factor is generated so as to encourage a behavioral change in the subject, taking into consideration each IBM factor. In FIG. 4, one nudge message is associated with each IBM factor, but multiple nudge messages may be associated with each IBM factor. In addition, each IBM factor may be associated with a nudge message.
The IBM ID for identifying the M factor is not limited to the one shown in the figure.

The nudge message generated by the generation unit 202 may be transmitted to the action support device 10 by 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.

<Action Support Device>
As shown in FIG. 3, the action support device 10 includes a storage unit 101, a prediction unit 102, and a generation unit 103.
, an acquisition unit 104, and a transmission control unit 105. At least a part of the functions realized by the acquisition unit 104 can be realized by using the communication device 13.
The generation unit 103 and the transmission control unit 105 can be realized by the processor 11 executing the action support program stored in the storage device 12. The action support program can be stored in the storage medium. The storage unit 101 can be realized by the storage device 12.
This can be achieved using 2.

The storage unit 101 stores a plurality of nudge messages (
For example, the nudge message storage device 20 may store the nudge messages shown in FIG. 4. The nudge messages may be generated by the behavior analysis device 20, or may be input from the input/output device 14 of the behavior support device 10.

The storage unit 101 stores information about a subject (hereinafter referred to as "subject information"), information about the environment for behavioral change (hereinafter referred to as "environmental information"), and an exploratory randomized controlled trial (RC
The RCT information includes at least one piece of information related to the results of the RCT.

Here, the subject information stored in the storage unit 101 includes identification information of the subject, information on the subject's attributes (hereinafter referred to as "attribute information"), information on the subject's behavior history (hereinafter referred to as "behavior history information"), information on the risk in the case where the subject's behavior does not change (hereinafter referred to as "risk information"), and information on the responses from the subject (hereinafter referred to as "response information").
The method may include at least one of the following:

Fig. 5 is a diagram showing an example of subject information according to the present embodiment. For example, Fig. 5 illustrates subject information assuming that the subject is a "resident of XX city" and the behavioral change is "attending a specific health checkup (e.g., a medical checkup)."

The subject information in Figure 5 may include, as identification information of the subject, for example, information indicating the subject ID, as attribute information of the subject, for example, information indicating age and gender, as behavioral history information, for example, information indicating the subject's history of undergoing specific health checkups, as risk information, for example, information indicating the subject's risk of contracting a specific disease (hereinafter referred to as "morbidity risk"), and as response information, for example, information indicating the subject's responses to a questionnaire (hereinafter referred to as "questionnaire responses").

The subject information is not limited to that shown in Fig. 5. For example, in Fig. 5, the behavioral history information shows the history of specific health checkups for a certain number of years in the most recent period, but any information related to the subject's behavioral history may be used. In addition, the attribute information is not limited to the subject's age and sex, and may be any information related to the subject's attributes. In addition, it is not necessary to include at least some of the information shown in Fig. 5, and it may include information not shown related to the subject.

Furthermore, the environmental information stored in the memory unit 101 may be, for example, information indicating the date and time of the specific health check, information indicating medical institutions that can receive the specific health check, etc., when the subjects are residents of a specific administrative unit (e.g., city X) and the behavioral change is taking a specific health check. Furthermore, the environmental information may include the maximum number of times a nudge message is sent to the subjects, information regarding rewards for behavioral change (hereinafter referred to as "reward information"), etc. For example, when the subjects are "residents of a certain administrative unit" and the behavioral change is "taking a specific health check," the reward information may be the life extension effect expected of the subjects, the expected amount of tax paid, etc.

In addition, the RCT information includes the ranking of the sending date (e.g., weekdays, Monday to Sunday, holidays, etc.),
The information may include at least one of the following: ranking of transmission times (e.g., morning, afternoon, night, etc.), ranking of transmission frequency (e.g., monthly, biweekly, monthly, etc.), compatibility between the target information and the nudge message set, and the order in which the nudge messages in the nudge message set are sent.

The prediction unit 102 predicts information indicating the state of the subject for each of the IBM factors (hereinafter referred to as "state information") based on the subject information on the subject. Fig. 6 is a diagram showing an example of state information according to this embodiment. As shown in Fig. 6, the state information may indicate whether the state of the subject is sufficient for behavioral modification for each IBM factor.

For example, the status information shown in FIG. 6 indicates whether or not the status of each subject is sufficient for behavioral change (e.g., taking a specific health check) for each of a number of IBM factors (here, experiential attitude, instrumental attitude, indicative norm, descriptive norm, sense of behavioral control, self-efficacy, knowledge and skills, importance of behavior, environmental constraints, and habituation). For example, in the case of subject ID "3" in FIG.
The status information of the subject in "Subject #3" (hereinafter referred to as "Subject #3") indicates that the three IBM factors "experiential attitude,""knowledge and skills," and "environmental constraints" are insufficient for behavioral change, and indicates that the other IBM factors are sufficient for behavioral change. Note that status information indicating that the subject's status is insufficient for behavioral change may be called insufficient information. Also, FIG. 6 is merely an example, and only some items (e.g., IBM ID, major items, medium items, etc.)
may be omitted.

The prediction unit 102 may predict the above-mentioned state information based on at least one of information on a response from the subject acquired by the acquisition unit 104 (hereinafter referred to as "response information"), environmental information, and RCT information, in addition to the subject information. The prediction unit 102 may generate the above-mentioned state information using a trained machine learning model. The machine learning model may generate the above-mentioned state information based on the subject information (as well as the response information, environmental information, and RCT information).
The machine learning model is trained to output the state information when the subject information (and at least one of the response information, the environmental information, and the RCT information) is input. Such a machine learning model may be realized as a neural network and trained by supervised learning using pairs of the subject information (and at least one of the response information, the environmental information, and the RCT information) and the state information as training data.

The prediction unit 102 may also predict a probability of a behavior change of the subject (hereinafter, referred to as a "behavior change probability") based on the subject information on the subject. The behavior change probability is, for example, the probability that the subject will achieve a behavior change without an intervention for the subject's behavior change (hereinafter, referred to as a "probability of behavior change").
For example, the probability of non-intervention behavior for subject #3 in FIG.
%, and if no intervention for behavior change is made, there is a 70% probability that behavior change will be achieved. Note that the probability of behavior change is not limited to this, and may be the probability that the subject will not achieve behavior change without the above intervention, the probability that the subject will achieve or not achieve behavior change with the above intervention, etc.

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
The prediction unit 102 may make a prediction based on at least one of the response information, the environmental information, and the RCT information acquired in 4. The prediction unit 102 may generate the above-mentioned behavior change probability by using a trained machine learning model. The machine learning model is trained to output the behavior change probability when the subject information (and at least one of the response information, the environmental information, and the RCT information) is input. Such a machine learning model may be realized as a neural network and trained by supervised learning using a pair of the subject information (and at least one of the response information, the environmental information, and the RCT information) and the behavior change probability as training data.

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 including one or more nudge messages to be delivered to the target person (hereinafter, referred to as a "nudge message set") is selected from the above. Specifically, the generation unit 103 generates a nudge message set including at least a nudge message associated with an IBM factor indicating that the state information is insufficient for behavioral modification.

7 is a diagram showing an example of a nudge message set according to this embodiment. As shown in FIG. 7, the nudge message set for subject #3 includes nudge messages #1 to #4. Nudge messages #2 to #4 are associated with the three IBM factors "experiential attitude,""knowledge and skills," and "environmental constraints," which are indicated to be insufficient for behavioral change by the status information of subject #3. On the other hand, nudge message #1 is
In this manner, the nudge message set may include not only a nudge message associated with an IBM factor indicating that the state information is not sufficient for behavior change, but also other nudge messages.

The acquisition unit 104 acquires response information from the subject. Here, the response information is, for example, information indicating a response from the subject who viewed the nudge message, and may be whether or not a short message (SM) or email containing the nudge message was viewed, a situation regarding behavioral change (for example, a reservation status for a specific health checkup), a result of behavioral change (for example, a result of taking the specific health checkup), etc. The acquisition unit 104 may acquire the response information from the subject's terminal 30 in real time.

The transmission control unit 105 controls the transmission to the subject of one or more nudge messages in the nudge message set selected by the generation unit 103. Under the control of the transmission control unit 105, the communication device 13 of the action support device 10 transmits the nudge message to the terminal 30 of the subject.

Specifically, the transmission control unit 105 receives the RCT information, the environmental information,
and controls transmission of the one or more nudge messages to the target person based on at least one of the response information acquired by the acquisition unit 104. Here, the control of the transmission of the nudge messages may include, for example, control of the order of transmission of multiple nudge messages in the nudge message set, the transmission date of each nudge message, the transmission time zone of each nudge message, the time interval (transmission frequency) for transmitting the multiple nudge messages, suspension of transmission of each nudge message, the number of times each nudge message is transmitted, etc.

For example, in the case of the nudge message set for subject #3 shown in FIG.
Based on at least one of the RCT information, the environmental information, and the response information, the transmission control unit 105 determines to transmit nudge messages to the target person #3 in the order of nudge messages #1, #2, #3, and #4. Also, based on at least one of the RCT information, the environmental information, and the response information, the transmission control unit 105 determines at least one of the transmission date, the transmission time zone, the transmission interval, the transmission suspension, the number of transmissions, etc. of the nudge messages #1 to #4.

For example, if positive response information regarding behavioral change is acquired by acquisition unit 104 after transmitting each of nudge messages #1 to #3 in Fig. 7, transmission control unit 105 may cancel transmission of the subsequent nudge message. On the other hand, if negative response information is acquired in response to a nudge message, transmission control unit 105 may resend the nudge message or may transmit the subsequent nudge message.

In this way, instead of sending the nudge message set for subject #3 all at once, multiple nudge messages included in the nudge message set can be sent to subject #3 in a distributed manner multiple times. Even if a single nudge message contains a lot of information, humans may overlook it, so it can be said that multiple nudge messages are more effective at promoting behavioral change. Therefore, by sending multiple nudge messages in a distributed manner, it is possible to increase the promotion effect of behavioral change for subjects who are not likely to change their behavior with a single nudge message.

In addition, the transmission control unit 105 may transmit a subsequent nudge message updated based on the response information acquired by the acquisition unit 104. Specifically, the prediction unit 102
The state information may be updated based on the response information, and the generating unit 103 may update the nudge message set based on the updated state information. Furthermore, by updating the nudge message to be sent to the subject based on the response information of the subject, it is possible to send a nudge message that is more effective in promoting behavioral change of the subject.

Furthermore, the transmission control unit 105 may control the transmission of one or more nudge messages in the nudge message set generated by the generation unit 103 based on the behavior change probability predicted by the prediction unit 102. For example, the transmission control unit 105 may control the transmission of one or more nudge messages in the nudge message set generated by the generation unit 103 based on the behavior change probability predicted by the prediction unit 102.
For a subject whose non-intervention behavior probability satisfies a predetermined condition (e.g., equal to or less than a predetermined threshold), the transmission control unit 105 may increase the number of times each nudge message is transmitted or increase the frequency of transmission. On the other hand, for a subject whose non-intervention behavior probability satisfies a predetermined condition (e.g., equal to or greater than a predetermined threshold), the transmission control unit 105 may decrease the number of times each nudge message is transmitted or decrease the frequency of transmission.

Furthermore, the transmission control unit 105 may control the transmission of one or more nudge messages in the nudge message set generated by the generation unit 103 based on information that changes due to various factors (hereinafter referred to as "change information"). For example, the change information may be, for example, the arrival status of a particular vaccine, the availability of appointments for health checkups or medical examinations, free time, etc.
The transmission control unit 105 may control the transmission of one or more nudge messages in the nudge message set generated by the generation unit 103 based on information regarding the subject's convenience (e.g., whether the time and/or place is convenient for the subject, etc.).

The transmission control by the transmission control unit 105 as described above may be implemented by solving a resource allocation problem. For example, the state information and the behavior change probability predicted by the prediction unit 102,
The resource allocation problem may be initialized using at least one of the environmental information stored in the storage unit 101 and the nudge message set generated by the generation unit 103. In addition, the transmission control unit 105 sets all nudge messages and all target persons stored in the storage unit 101 as the environment,
The above-mentioned transmission control may be implemented by solving a resource allocation problem, with all the nudge messages as the solution space, the maximum number of times that nudge messages are sent to each target person as the budget, and the sum of rewards obtained during the target period as the cumulative reward.

(Operation of the behavior support system)
8 is a flow chart showing an example of the operation of the action support system according to the present 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.

As shown in Fig. 8, in step S101, the action support device 10 predicts the subject's state information (e.g., Fig. 6) based on the subject information. The action support device 10 may also predict a behavior change probability (e.g., a non-intervention behavior probability) based on the subject information. The action support device 10 may also predict or update the state information and/or the behavior change probability based on at least one of the response information, the environmental information, and the RCT information in response to the nudge message transmitted by the transmission control in step S103.

In step S102, the action support apparatus 10 generates a nudge message set (for example, FIG. 7) for the subject based on the state information predicted in step S101.

In step S103, the action support device 10 controls the transmission of one or more nudge messages in the nudge message set generated in step S102.
may control the transmission of the one or more nudge messages based on at least one of response information, environmental information, and RCT information to a previously transmitted nudge message.

According to the action support system 1 of this embodiment, a nudge based on a behavioral factor is used to:
It is possible to more effectively support the behavioral change of the subject. More specifically, the behavioral support system 1
In the method, state information indicating the state of a subject with respect to each of a plurality of IBM factors is predicted, and a nudge message set including one or more nudge messages selected based on the state information is generated. Therefore, it is possible to generate a nudge message set (i.e., information bundle) optimal for changing the behavior of the subject.

In addition, in the above-mentioned behavior support system 1, instead of sending a nudge message set such as that illustrated in Fig. 7 to the subject all at once, multiple nudge messages in the nudge message set are distributed and sent to the subject multiple times, thereby enhancing the effect of promoting behavior change in the subject. Furthermore, by controlling the sending of subsequent nudge messages and/or updating the contents based on response information to the nudge messages, it is possible to more effectively support the behavior change of the subject.

The above-described embodiments are intended to facilitate understanding of the present invention, and are not intended to limit the present invention. The elements of the embodiments, as well as their arrangements, materials, conditions, shapes, sizes, etc., are not limited to those shown as examples and can be changed as appropriate. In addition, configurations shown in different embodiments can be partially substituted or combined with each other.

For example, in the above embodiment, the subject is assumed to be a "resident of XX city" and the behavioral change is assumed to be "attending a specific health checkup (e.g., medical examination)", but this is not limited to this. The subject is not limited to users of government services, but may be users of various services such as English conversation or qualification exams. Furthermore, the behavioral change is not limited to the use of government services, but may be continued learning, use of various services, etc.

In the above embodiment, RCT results are
The transmission of one or more messages to a subject is controlled based on the CT information.
The causal inference method used to control the transmission of messages is not limited to exploratory RCT, and other methods such as propensity score matching may be used as the causal inference method.
In addition, the exploratory RCT may also be referred to as a trial and/or small-scale RCT, and may be any pilot for setting parameters used to control the transmission of the message.

Furthermore, the nudge message in the above embodiment is not limited to a text format including character strings and symbols, and may be predetermined information including audio, video, images, or the like. Furthermore, in the above embodiment, the transmission control unit 105 of the action support device 10 controls the transmission of the nudge message, but this is not limited thereto, and the action support device 10 may be provided with a control unit that controls the output of the nudge message (e.g., including not only transmission but also display, audio output, etc.). That is, the "transmission" of the nudge message in the above embodiment may be rephrased as display, audio output, output, etc. Furthermore, the terminal 30 is not limited to a terminal used by a specific target person, and may be a signage, electronic bulletin board, speaker, etc. that outputs information for unspecified targets.

For example, in a situation where the population density in a specific space (inside a train station or a restaurant) exceeds a certain level and the probability of non-intervention behavior is high, the action support device 10 may transmit a nudge message to "disperse people" to a terminal 30 (e.g., a signage, electronic bulletin board, or speaker, etc.) and output (e.g., display, audio output, etc.) from the terminal 30. Furthermore, the action support device 10 and the terminal 30 that outputs the nudge message to the subject may be provided as an integrated device, and the action support device 10 transmitting the nudge message to the terminal 30 may be internal communication within the integrated device.

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 unit, 203: storage unit

Claims (8)

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 modification for each of the plurality of behavioral factors; and
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. 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 . 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. 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 . 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. 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. 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. 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