Information output device, information output method, and program

Abstract

This information output device includes: a determination unit configured to determine, with regard to an interviewee who has undergone an interview by an interviewer, whether a situation with respect to the continuation of a certain behavior or a psychological state regarding the continuation of the behavior satisfies a predetermined condition on the basis of the information obtained from the interviewee; an output information generation unit configured to generate information that serves to cause the interviewer or the interview to be recollected if the predetermined condition is satisfied; and an output unit configured to output the information. With this configuration, the information output device supports a person who suffers from decreased motivation with respect to improving a behavior.

Description

Information output device, information output method, and program

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

[0002] It is important to support behavioral change so that people who need to improve their behavior, such as those who want to prevent lifestyle-related diseases, can take the initiative to do so.

[0003] Previously, systems have been proposed that allow for easy disease prevention without the intervention of a professional (such as a doctor), by setting dietary and exercise goals, recording daily data, comparing results with goals one week later, and providing a review of the results one week later and advice for the following week.

[0004] Ayumi Sugawara, Ryotaro Yoshida, Keizo Yamada, Masanori Takagi, Jun Sasaki, "Proposal of a Lifestyle-Related Disease Prevention Support System", 78th National Convention of Information Processing Society of Japan, 4ZD-05, 4-993-994(2016)

[0005] However, when using such a system to improve lifestyle habits, initiative (proactivity and autonomy in healthy behavior) is expected from those who need prevention, and it is difficult for people who have lost motivation to continue improving their lifestyle habits.

[0006] The present invention has been made in view of the above points, and aims to support people who have lost motivation to improve their behavior.

[0007] In order to solve the above problem, the information output device has a judgment unit configured to judge, based on information obtained from the interviewee with whom an interviewer has conducted an interview, whether the status of continuation of a certain behavior or the psychological state regarding the continuation of the behavior satisfies predetermined conditions; an output information generation unit configured to generate information that evokes the interviewer or the interview when the predetermined conditions are satisfied; and an output unit configured to output the information.

[0008] It can help people who are less motivated to improve their behavior.

[0009] FIG. 1 is a diagram showing an example of the configuration of a behavior change support system in an embodiment of the present invention. FIG. 2 is a diagram showing an example of the hardware configuration of an information output device 10 in an embodiment of the present invention. FIG. 3 is a diagram showing an example of the functional configuration of the information output device 10 in an embodiment of the present invention. FIG. 4 is a flowchart for explaining an example of a processing procedure executed in the behavior change support system. FIG. 5 is a diagram showing an example of the configuration of an interview information DB 121. FIG. 6 is a diagram showing an example of the configuration of a state DB 122. FIG. 7 is a diagram showing an example of the configuration of a template DB 123. FIG. 8 is a diagram showing an example of the configuration of a dialogue log DB 126. FIG. 9 is a diagram showing an example of the configuration of an interviewee encouragement message DB 124. FIG. 10 is a diagram showing an example of the configuration of an interviewee psychology DB 125. FIG. 11 is a diagram showing an example of a message display.

[0010] In a study conducted by the inventors of the present application, a survey on health guidance interviews revealed that if an interviewee (a patient or other person receiving an interview) feels that the interviewer (the person conducting the interview) is thinking carefully about them immediately after the interview, they become motivated to achieve the goals they set during the interview. This embodiment discloses a system (hereinafter referred to as a "behavioral change support system") that supports behavioral change, such as behavior improvement, by evoking this feeling (motivation) and maintaining a relationship with the interviewer.

[0011] The behavioral change support system has the function of detecting either a decline in the rate at which the interviewee implements healthy behaviors or a decline in motivation, and outputting a message.

[0012] The message includes any of the following: information that evokes the situation during the interview (1), information about the psychological state that the interviewer wants to convey to the interviewee (2), information that the interviewer encourages the interviewee (3), and speech information as a behavior change support system (agent) (4). Here, (1) to (3) can be said to be information that evokes the interviewer or the interview.

[0013] The statements made by the behavior change support system are characterized by their personified nature.

[0014] Not only (4), but also (1) to (3) are conveyed by the system in anthropomorphic utterances.

[0015] An embodiment of the present invention will now be described with reference to the accompanying drawings. Fig. 1 shows an example of the configuration of a behavior change support system according to an embodiment of the present invention. In Fig. 1, an interviewee terminal 20 and a subject terminal 30 are connected to an information output device 10 via a network such as the Internet.

[0016] The interviewer terminal 20 is a terminal used by the interviewer. For example, a PC (Personal Computer), a tablet terminal, or a smartphone may be used as the interviewer terminal 20. An interviewer is a person who interviews a person (interviewee) who is trying to change their behavior to prevent lifestyle-related diseases, for example, and supports the subject's behavioral change. The interviewer terminal 20 inputs information about the interview during the interview, etc., and transmits the information to the information output device 10.

[0017] The information output device 10 is one or more computers that execute a process for supporting the interviewee in continuing to change his / her behavior during the interview. For example, the information output device 10 transmits information for supporting the subject's behavior change (e.g., information that evokes the interviewer or the interview) to the subject terminal 30 at a predetermined timing.

[0018] The subject terminal 30 is a terminal used by one interviewee (hereinafter referred to as the "subject") who is the focus of attention in this embodiment among the interviewees. For example, a PC, a tablet terminal, a smartphone, or the like may be used as the subject terminal 30.

[0019] 2 is a diagram showing an example of the hardware configuration of the information output device 10 according to an embodiment of the present invention. The information output device 10 in FIG. 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a processor 104, and an interface device 105, all of which are interconnected via a bus B.

[0020] A program that realizes processing in the information output device 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program does not necessarily have to be installed from the recording medium 101, but may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program as well as necessary files, data, etc.

[0021] When an instruction to start a program is received, the memory device 103 reads the program from the auxiliary storage device 102 and stores it. The processor 104 is a CPU or a GPU (Graphics Processing Unit), or a CPU and a GPU, and executes functions related to the information output device 10 in accordance with the program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

[0022] FIG. 3 is a diagram illustrating an example of the functional configuration of an information output device 10 according to an embodiment of the present invention. In FIG. 3, the information output device 10 includes an interview information generation unit 11, a determination unit 12, an output information generation unit 13, and an output unit 14. These units are implemented by a processor 104 executing one or more programs installed in the information output device 10. The information output device 10 also utilizes storage units such as an interview information DB 121, a status DB 122, a template DB 123, an interviewee encouragement message DB 124, an interviewee psychology DB 125, and a dialogue log DB 126. Each of these databases (storage units) can be implemented using, for example, an auxiliary storage device 102 or a storage device connectable to the information output device 10 via a network.

[0023] The processing steps executed in the behavior change support system will be described below. Fig. 4 is a flowchart for explaining an example of the processing steps executed in the behavior change support system.

[0024] When the interviewer conducts a face-to-face or online interview with the subject and the interview ends, the processing procedure of FIG. 4 starts.

[0025] In step S101, the interview information generation unit 11 registers information received from the interviewer terminal 20 of the interviewer who conducted the interview (hereinafter referred to as "received information") in the interview information DB 121.

[0026] 5 is a diagram showing an example of the configuration of the interview information DB 121. The interview information DB 121 stores interview information for each interview, including an interview ID, an interviewee ID, an interviewer ID, "statements that interested the interviewee," "summary," "action plan," etc.

[0027] The interview ID is identification information for each interview, and may be assigned, for example, when the interview information generation unit 11 adds a record to the interview information DB 121.

[0028] The interviewee ID is identification information of the interviewee in the interview, and is included in the received information, for example.

[0029] The interviewer ID is identification information of the interviewer in the interview, and is included in the received information, for example.

[0030] "Statements that interested the interviewee" is text that indicates statements that interested the interviewee during the interview.

[0031] "Summary" is text that summarizes the contents of the interview.

[0032] "Action Plan" is text that shows the interviewee's plan of action made during the interview.

[0033] The "statements that interested the interviewee," "summary," and "action plan" can be extracted from the interview data included in the received information. The interview data is audio data or video data that is a recording of the interview.

[0034] The "statements that interested the interviewee" may be obtained by the interview information generation unit 11 identifying a time when the interviewee was relatively interested based on the degree of the interviewee's responses in the interview data (video) and the strength of interest estimated from facial images (pupil measurement), and then converting the interviewee's statements before and after that time into text.

[0035] The "summary" may be obtained by the interview information generation unit 11 converting the speech contained in the interview data into text (hereinafter referred to as "interview text") using voice recognition, and summarizing the interview text using publicly known generation AI or natural language processing technology.

[0036] The "action plan" may be obtained by the interview information generation unit 11 detecting a specified keyword related to the action plan (e.g., "action plan," "future plan," etc.) from the interview text and extracting a well-defined part (e.g., one sentence) before, after, or after the specified keyword.

[0037] In step S101, a new record including the interviewee ID of the subject and the interviewer ID of the interviewer who conducted the interview with the subject is registered in the interview information DB 121.

[0038] The interviewer terminal 20 may start recording interview data in response to a predetermined operation by the interviewer or automatic detection of a speech indicating the start of the interview (keywords such as "Hello. Please have a seat" or "Thank you in advance"), and may end recording interview data in response to a predetermined operation by the interviewer or automatic detection of the end of the interview (when the audio of the conversation has stopped or when keywords such as "End" or "Thank you" are detected). The interviewer terminal 20 may also have an interview information generation unit 11. In this case, the interview information generation unit 11 may register the interview information in the interview information DB 121 via a network.

[0039] When new interview information is registered in the interview information DB 121, the determination unit 12 starts monitoring the subject's condition (continuation status of the action plan established in the interview) (S102).

[0040] Steps S103 and subsequent steps are executed for each interviewee whose status is being monitored. For convenience, a single interviewee will be described here, but if there are multiple interviewees whose status is being monitored, the same processing procedure may be executed for each interviewee.

[0041] In step S103, the judgment unit 12 judges, periodically or when predetermined conditions are met, whether the status of continuation of the behavior set out in the behavior plan for the interview or the subject's psychological state (motivation) regarding the continuation of the behavior meets predetermined conditions based on information obtained from the subject. Hereinafter, the status of continuation of the behavior set out in the behavior plan for the interview or the subject's psychological state regarding the continuation of the behavior will be referred to as the "interviewee state," and the subject's interviewee state will be referred to as the "subject state." The judgment of the subject state refers to the judgment of the subject's motivation regarding the behavior related to the behavior plan. "Periodic" means, for example, once a day at a fixed time or once a week at an arbitrary time. The predetermined condition is, for example, when a client-side application (hereinafter referred to as the "client app") corresponding to the behavior change support system has not been launched for a predetermined period (e.g., one week) or more.

[0042] The determination of the continuation status of an action may be performed, for example, based on a change in the rate of execution of the action. The determination unit 12 may, for example, compare the rate of execution of the action for a predetermined period (e.g., the past week, the past three days, etc.) with the previous period. The action refers to an action defined in an action plan. For example, the action plan of the first record in FIG. 5 includes the action "15-minute walk." Therefore, in this case, the rate of execution of 15-minute walks (the percentage of days on which 15-minute walks were performed) for the predetermined period may be compared with the previous period. Note that the amount of execution may be used instead of the rate of execution. The execution or non-execution of an action may be determined, for example, using a measurement result obtained by a sensor or the like included in the subject terminal 30. For example, a client app may periodically (e.g., once a day) upload the subject's step count for that period to the information output device 10. Alternatively, the subject may launch a client app every day and input whether or not the subject has performed the action related to the day's action plan, and the client app may upload the input information to the information output device 10. The determination unit 12 may determine a change in the rate of performing a behavior based on the history of information uploaded in this manner.

[0043] The psychological state (motivation) of the subject regarding the continuation of the action set in the action plan may be determined, for example, by the determination unit 12 displaying a question such as "How motivated are you regarding the action plan?" on the subject terminal 30. The answer to the question is multiple choice, and a label indicating "remains high" or "decreasing" is assigned to each option in advance.

[0044] Figure 6 is a diagram showing an example of the configuration of the state DB 122. The state DB 122 stores, for each interviewee, the interviewee ID, interviewer ID, interview ID, behavior, motivation, and last measurement date and time, etc. The interviewee ID, interviewer ID, and interview ID correspond to the interview information DB 121. In this embodiment, it is assumed that a single interview has been conducted with the subject. If multiple interviews have been conducted with the subject, the interviewer ID and interview ID may be set to values ​​corresponding to the most recent interview. The behavior is the result of determining the change in the rate of implementation of the behavior. The motivation is the result of determining motivation based on the motivation determination method described above. The last measurement date and time is the date and time when the record was last updated.

[0045] In the present embodiment, an example has been shown in which a change in the rate of behavior implementation and motivation are determined, but only one of them may be determined. In particular, when it is difficult to grasp the rate of behavior implementation, only motivation may be determined based on a questionnaire given to the subject.

[0046] The subject's state in which at least one of the rate of behavior implementation and motivation has decreased is referred to as "decreased," while the subject's state in which neither of the rate of behavior implementation and motivation has decreased is referred to as "continued."

[0047] Next, the output information generating unit 13 branches the process depending on whether the subject's condition is "deteriorated" or not (S104).

[0048] If the subject's condition is not "deteriorated" (i.e., if it is estimated that the subject has not lost motivation) (No in S104), the output information generation unit 13 generates information (message) for maintaining the subject's motivation (S105). The message is generated using, for example, a template registered in the template DB 123.

[0049] 7 is a diagram showing an example of the configuration of the template DB 123. The template DB 123 stores in advance a template ID, a template, a type, and an interviewee status for each template.

[0050] The template ID is identification information for the template. The template is a message template. In a template, a character string enclosed in square brackets [ ] is a portion to be replaced with the value indicated by the character string. For example, the [Number of days of activity duration] included in a template with a template ID of "C0001" is replaced with the number of days the activity has been continuing, the [Number of steps] included in a template with a template ID of "C0002" is replaced with the number of steps, and the [Interviewee] is replaced with the interviewee ID. These values ​​can be obtained from the interview information DB 121 ( FIG. 5 ), the status DB 122 ( FIG. 6 ), etc. However, the number of steps may be obtained from information uploaded from the subject terminal 30. Furthermore, the [Statement that interested the interviewee] included in a template with a template ID of "C0005" can be obtained from the "Statement that interested the interviewee" in the record corresponding to the subject in the interview information DB 121.

[0051] The type is the type of message generated by the template. In this embodiment, messages are classified into either an "agent-based sentence" or an "interviewer message." An "agent-based sentence" is a message that is spoken by the agent (information output device 10). An agent's statement refers to encouragement from the agent or a statement that shows the agent's reflections on the interview with the subject. An "interviewer message" is a message in a format in which the agent conveys to the subject a message of encouragement or feelings toward the subject that have been registered in advance by the interviewer who conducted the interview with the subject. An "interviewer message" message is a variation of a message from the interviewer that is basically output when the subject loses motivation (healthy behavior decreases).

[0052] The interviewee status is an item that indicates which subject status the message generated by the template corresponds to.

[0053] In step S105, a message of type "agent-subject sentence" is generated. Step S105 is also executed when the interviewee state is "continued." Therefore, the output information generation unit 13 randomly selects one of the templates of type "agent-subject sentence" and of which the interviewee state is "continued," and generates a message based on the selected template. For example, a message such as "You've been continuing this behavior for x days. That's amazing!" is generated.

[0054] In addition, the example of Figure 7 also includes templates related to specific activities (walking), such as "You walked [number of steps] steps today. I'll let [interviewee] know about your efforts." As such, messages based on templates related to specific activities may be off-target if the subject does not consider the activity to be a goal (action plan). To avoid this, for example, an "activity type" field corresponding to the action plan may be added to the interview information DB 121 (Figure 5) and the template DB 123. The value of the "activity type" field in the interview information DB 121 (Figure 5) may be set to, for example, "exercise - steps," "exercise - time," "meal - fried food," "meal - carbohydrates," etc., depending on the action plan. The value of the "activity type" field in the template DB 123 may be set to, for example, "exercise - steps," "exercise - time," "meal - fried food," "meal - carbohydrates," etc., for templates corresponding to specific activities. The output information generation unit 13 may select templates that are associated with the same value as the value of "behavior type" corresponding to the subject's record in the interview information DB 121 as selection candidates.

[0055] Next, the output unit 14 transmits (outputs) the information (message) generated by the output information generation unit 13 to the subject terminal 30 (S110).

[0056] Next, the output unit 14 registers (saves) information about the message in the dialogue log DB 126 (S111).

[0057] 8 is a diagram showing an example of the configuration of the dialogue log DB 126. The dialogue log DB 126 stores a dialogue log ID, an interviewee ID, a template ID, a type, a transmission date and time, etc. for each message that the information output device 10 outputs to the interviewee to support behavioral modification of the subject terminal 30 (a dialogue that the information output device 10 has with the interviewee).

[0058] The dialogue log ID is identification information for each message. The interviewee ID is the interviewee ID of the interviewee to whom the message is output. The template ID is identification information for the template from which the message was generated. The type is the type of the message.

[0059] In step S111, a record including the interviewee ID of the target person, the template ID of the template used to generate the message output to the target person, the type of the template being "agent-subject sentence," and the current date and time as the sending date and time is added to the dialogue log DB 126.

[0060] On the other hand, if the subject's condition is "deteriorating" (i.e., if the subject is estimated to have lost motivation) (Yes in S104), the output information generation unit 13 refers to the dialogue log DB 126 (Figure 8) and calculates the occurrence rate of "interviewer messages" for the subject (S106).

[0061] The occurrence rate of "interviewer messages" for a target person refers to the rate of messages of the type "interviewer messages" among the set of messages in the dialogue log DB 126 whose interviewee ID corresponds to the target person.

[0062] Next, the output information generation unit 13 determines whether the occurrence rate of the "interviewee message" for the subject is less than a threshold value α (e.g., 50%) predetermined by the administrator of the behavioral change support system (S107).

[0063] If the occurrence rate of "interviewer message" for the target person is less than the threshold value α (Yes in S107), the output information generation unit 13 randomly selects one template from the templates in the template DB 123 (FIG. 7) whose "Type" value is "interviewer message" and generates a message based on the selected template (S108). Note that among the templates whose "Type" value is "interviewer message," some templates contain strings that should be replaced with values ​​registered in the interviewer support message DB 124 or the interviewer psychology DB 125. For example, in the template DB 123 of FIG. 7, the template with the template ID "C0003" (hereinafter referred to as "template C0003"; other templates are identified by the same naming convention) contains the string "support message." Furthermore, template C0004 contains the string "mental state that the interviewer wants to convey to the interviewee." When the output information generation unit 13 selects one of these templates, it refers to the interviewer support message DB 124 or the interviewer psychology DB 125 to identify the string to be replaced with the ``support message'' or the ``psychological state that the interviewer wants to convey to the interviewee.''

[0064] 9 is a diagram showing an example of the configuration of the interviewee support message DB 124. The interviewee support message DB 124 stores an interview ID, an interviewee ID, an interviewer ID, and a support message for each interview.

[0065] The interview ID, interviewee ID, and interviewer ID are the same as those in the interview information DB 121 (Figure 5). The support message is a string (sentence) indicating support from the interviewer associated with the interviewer ID to the interviewee associated with the interviewee ID.

[0066] The output information generation unit 13 generates a message by replacing the [support message] in the template with the value of the "support message" in the record corresponding to the subject in the interviewee support message DB 124.

[0067] 10 is a diagram showing an example of the configuration of the interviewer psychology DB 125. The interviewer psychology DB 125 stores, for each interview, an interview ID, an interviewee ID, an interviewer ID, and the "psychological state that the interviewer wants to convey to the interviewee."

[0068] The interview ID, interviewee ID, and interviewer ID are the same as those in the interview information DB 121 (Figure 5). "The psychological state that the interviewer wants to convey to the interviewee" is a string of characters indicating the message that the interviewer wants to convey to the interviewee after the interview if the interviewee loses motivation.

[0069] The output information generation unit 13 generates a message by replacing the template's [Mental state that the interviewer wants to convey to the interviewee] with the value of the [Mental state that the interviewer wants to convey to the interviewee] in the record corresponding to the subject in the interviewer psychology DB 125.

[0070] For example, if template C0003 is selected and the subject's interviewee ID is "001," the output information generation unit 13 applies the support message of the record in the interviewer support message DB 124 (Figure 9) with the interviewee ID "001" to template C0003, thereby generating a message such as "Mr. / Ms. XX said, 'I know you're busy at work, but I'm supporting you in changing your meal plans.'"

[0071] In addition, records including "encouragement messages" in the interviewer support message DB 124 and records including "mental state that the interviewer wants to convey to the interviewee" in the interviewer psychology DB 125 are, for example, registered by the interviewer using the interviewer terminal 20 after the end of the interview as "encouragement messages" or "mental state that the interviewer wants to convey to the interviewee" in the interviewer support message DB 124 or the interviewer psychology DB 125, in order to continue the actions related to the action plan. As a user interface at this time, a screen is displayed that asks the interviewer about the "encouragement messages" or the "mental state that the interviewer wants to convey to the interviewee", and these values ​​may be input via the screen.

[0072] In addition, to avoid the "encouraging messages" and "psychological state that the interviewer wants to convey to the interviewee" becoming monotonous, the interviewer may update these values ​​periodically, rather than just immediately after the interview.

[0073] On the other hand, if the occurrence rate of "interviewee message" for the target person is equal to or greater than the threshold value α (No in S107), the output information generation unit 13 randomly selects one template from among the templates in the template DB 123 ( FIG. 7 ) for which the value of "type" is "agent-subject sentence" and the value of "interviewee state" is "deterioration," and generates a message based on the selected template ( S109). In FIG. 7 , the value of "type" for template C0005 is "agent-subject sentence" and the value of "interviewee state" is "deterioration." Template C0005 includes the character string "a statement that interested the interviewee," but the output information generation unit 13 generates a message by replacing the character string with "a statement that interested the interviewee" (i.e., a statement made by the target person during the interview) in a record corresponding to the target person in the interview information DB 121. For example, if the interviewee ID of a former resident is "002", the output information generating unit 13 generates a message saying, "During the interview, we talked about what you want to be like in the next 10 years."

[0074] The branching of step S107 is a process to prevent messages output to the subject from being biased toward "interviewer messages." When step S107 is executed, it is possible that the subject has lost motivation, so it is considered more effective to output "interviewer messages," which are messages from the interviewer, to the subject. However, there is also a possibility that the subject may become accustomed to it and the effect may be reduced. Therefore, in this embodiment, the branching of step S107 is provided so that "agent-subjected sentences" are also output appropriately. However, it is also possible to always execute step S108 without providing the branching of step S107.

[0075] Following step S108 or S109, steps S110 and S111 are executed. The contents of steps S110 and S111 are as described above.

[0076] In addition, when generating the "agent-subject sentence" in step S105 or S109, the output information generation unit 13 may use a machine learning model such as a generation AI. In step S105, since it is estimated that the subject's motivation remains, the output information generation unit 13 may input an instruction (prompt) to the generation AI such as, "Please generate a supportive message of 50 characters or less for people who remain motivated to engage in health behavior." In step S109, since it is estimated that the subject's motivation has decreased, the output information generation unit 13 may input an instruction (prompt) to the generation AI such as, "Please generate a supportive message of 50 characters or less for people who have lost motivation to engage in health behavior." The output unit 14 may output the message generated by the generation AI.

[0077] The subject terminal 30 receives the message output (transmitted) from the output unit 14 and displays the message. The message may be displayed, for example, as shown in FIG. 11. In FIG. 11, the speech bubble on the left side indicates a message (interviewer message or agent-centered message) from the information output device 10. If the subject is demotivated, the message includes information that reminds the subject of the interviewer or the interview. Therefore, it is possible to expect the subject's motivation to return. Note that the speech bubble on the right side in FIG. 11 indicates an example of a message input by the subject. In other words, it may be possible to input a message by choosing between taking and rejecting.

[0078] As described above, according to this embodiment, when it is estimated that a subject has lost motivation (lost initiative (proactivity and autonomy in health behavior)), it is possible to support the person who has lost motivation to improve their behavior by evoking their impressions of the interview and the interviewer.

[0079] This embodiment may be applied to purposes other than health guidance. For example, it may be applied to mental health or teacher-student interviews in educational settings, or to community participation promotion dialogues for caregivers and volunteers with local elderly people.

[0080] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

[0081] REFERENCE SIGNS LIST 10 Information output device 11 Interview information generation unit 12 Determination unit 13 Output information generation unit 14 Output unit 20 Interviewer terminal 30 Target person terminal 100 Drive device 101 Recording medium 102 Auxiliary storage device 103 Memory device 104 Processor 105 Interface device 121 Interview information DB 122 Status DB 123 Template DB 124 Interviewer encouragement message DB 125 Interviewer psychology DB 126 Dialogue log DB B Bus

Claims

1. An information output device comprising: a judgment unit configured to judge, based on information obtained from an interviewee interviewed by an interviewer, whether the status of continuation of a certain behavior or the psychological state regarding the continuation of said behavior satisfies predetermined conditions; an output information generation unit configured to generate information that evokes the interviewer or the interview when the predetermined conditions are met; and an output unit configured to output the information.

2. The information output device according to claim 1, characterized in that the information includes feelings that the interviewer wants to convey to the interviewee in order to continue the behavior, which are registered by the interviewer after the interview.

3. The information output device according to claim 1, wherein the information includes statements made by the interviewee during the interview.

4. An information output method characterized in that a computer executes the following steps: a determination step for determining, based on information obtained from an interviewee interviewed by an interviewer, whether the status of continuation of a certain behavior or the psychological state regarding the continuation of said behavior satisfies predetermined conditions; an output information generation step for generating information that evokes the interviewer or the interview when the predetermined conditions are met; and an output step for outputting said information.

5. A program for causing a computer to execute the following steps: a determination procedure for determining, based on information obtained from an interviewee interviewed by an interviewer, whether the status of continuation of a certain behavior or the psychological state regarding the continuation of said behavior satisfies specified conditions; an output information generation procedure for generating information that evokes the interviewer or the interview when the specified conditions are met; and an output procedure for outputting the information.

Images