Information processing device, information processing method, and program

Abstract

An information processing device according to one aspect of the present disclosure acquires information pertaining to a subject. The information processing device comprises: a selection unit that selects presentation information or question information on the basis of weight information pertaining to the presentation information and the question information, the presentation information indicating presentation of information to the subject and the question information indicating a question for acquiring the information pertaining to the subject; an output unit that outputs, to a terminal used by the subject, the presentation information or the question information selected by the selection unit; and an acquisition unit that, when answer information for the question information is transmitted from the terminal, acquires the answer information as the information pertaining to the subject.

Description

Information processing device, information processing method, and program

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

[0002] In preventing lifestyle-related diseases, it is important to support behavioral change in people who need to improve their behavior. In recent years, under the specific health guidance system, interviews to support behavioral change have been conducted by professionals (e.g., public health nurses, registered dietitians, etc.), but due to reasons such as a shortage of manpower, there is a need to improve the efficiency of behavioral change support.

[0003] Understanding information about the subject before the interview (e.g., lifestyle habits such as whether or not they drink alcohol or smoke) improves the quality of the interview and contributes to the efficiency of behavior change support, but there is a limit to the number of items that can be included in a pre-interview at a clinic, health checkup facility, etc. For this reason, the interviewer draws out information from the subject during the interview that is not included in the interview but is useful for health guidance (e.g., the subject's thoughts about lifestyle habits), and supports the subject's behavior change.

[0004] As a prior art technique for medical interviews, an automatic medical interview system is known that can reduce the burden on patients when entering medical interview items by analyzing a database of previously entered items and deleting, integrating, or adding items (Non-Patent Document 1).

[0005] Ryutaro Arita, Tetsuhiro Yoshino, Yuko Horiba, Hiroaki Hikiami, Yutaka Shimada, Takao Namiki, Eiichi Tahara, Kiyoshi Minamizawa, Shinichi Muramatsu, Kenji Watanabe, "Identifying and solving problems for a patient-centered automated medical interview system," Nitto Medical Journal Kampo Med Vol.69 No.1 pp.82-90, 2018

[0006] However, since there is a wide range of information about the subject, it is difficult to extract much of that information.

[0007] The present disclosure has been made in consideration of the above points, and aims to efficiently obtain information about a subject.

[0008] An information processing device according to one aspect of the present disclosure is an information processing device that acquires information about a subject, and includes: a selection unit that selects presentation information representing the presentation of information to the subject or question information representing a question for acquiring information about the subject based on weight information regarding the presentation information or question information; an output unit that outputs the presentation information or question information selected by the selection unit to a terminal used by the subject; and an acquisition unit that, when answer information to the question information is transmitted from the terminal, acquires the answer information as information about the subject.

[0009] Information about the subject can be obtained efficiently.

[0010] FIG. 1 is a diagram showing an example of the overall configuration of a dialogue system according to the present embodiment; FIG. 2 is a diagram showing an example of the hardware configuration of a dialogue device according to the present embodiment; FIG. 3 is a diagram showing an example of the functional configuration of a dialogue device according to the present embodiment; FIG. 4 is a diagram showing an example of an output information master DB; FIG. 5 is a flowchart showing an example of the operation of a dialogue device according to the present embodiment; FIG. 6 is a diagram showing an example of a subject information management DB; FIG. 7 is a diagram showing an example of a subject dialogue status management DB; FIG. 8 is a flowchart showing an example of dialogue processing according to the present embodiment; FIG. 9 is a diagram showing an example of a UI.

[0011] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

[0012] <Analysis of Interviews in Specific Health Guidance> The inventor of the present invention analyzed interviews for specific health guidance and found a correlation between the information presented by the interviewer and the self-disclosure of the subject. In other words, when the interviewer presents some information, the subject tends to disclose information related to that information.

[0013] For example, if the interviewer introduces himself or herself and explains the purpose of the interview, the subject tends to disclose his or her thoughts during the interview. Also, if the interviewer explains the results of a health checkup, the subject tends to disclose information about his or her own behavior and physical condition.

[0014] Therefore, by using a system that simulates the information presentation of the interviewee, it is believed possible to elicit self-disclosure from the subject and efficiently acquire information about the subject. Hereinafter, as an example, assuming an interview for specific health guidance aimed at preventing lifestyle-related diseases, etc., a dialogue system 1 will be described that interactively acquires information about the subject by outputting presented information and question information to the subject of the interview. Here, presented information refers to information intended to be presented to the other party (e.g., a self-introduction, an explanation of the numerical results of a health check, etc.). On the other hand, question information refers to information intended to elicit a response from the other party (e.g., a question asking about the frequency of exercise, etc.).

[0015] According to the dialogue system 1 of this embodiment, it is possible to efficiently acquire information about the subject (e.g., lifestyle habits and the subject's underlying thoughts, etc.), and therefore, for example, by referring to this information, the interviewer can efficiently provide guidance for behavioral change support, etc.

[0016] <Example of Overall Configuration of Dialogue System 1> An example of the overall configuration of the dialogue system 1 according to this embodiment is shown in Fig. 1. As shown in Fig. 1, the dialogue system 1 according to this embodiment includes a dialogue device 10, one or more user terminals 20, and one or more target person terminals 30. The dialogue device 10, each user terminal 20, and each target person terminal 30 are communicatively connected via a communication network 40 including the Internet or the like.

[0017] The dialogue device 10 is an information processing device (computer) or information processing system (computer system) that outputs presentation information and question information to the subject terminal 30, thereby interactively acquiring information about the subject operating the subject terminal 30. The dialogue device 10 is realized, for example, by a general-purpose server or a system configured of such a server.

[0018] The user terminal 20 is a terminal of any type that is operated by an interviewee (e.g., a public health nurse, a registered dietitian, etc.) who is a user of the dialogue device 10. The user terminal 20 may be, for example, a personal computer (PC), a smartphone, a tablet terminal, a wearable device, etc.

[0019] The subject terminal 30 is a terminal of any type operated by the subject during the interview with the interviewer. The subject terminal 30 may be, for example, a PC, a smartphone, a tablet terminal, a wearable device, or the like.

[0020] 1 is an example, and is not intended to be limiting. For example, the dialogue system 1 according to this embodiment may include various terminals operated by persons other than the interviewee and the subject (e.g., a doctor who checks the results of the interview, etc.).

[0021] <Example of Hardware Configuration of Dialogue Device 10> An example of the hardware configuration of the dialogue device 10 according to this embodiment is shown in Fig. 2. As shown in Fig. 2, the dialogue device 10 according to this embodiment includes an input device 101, a display device 102, an external I / F 103, a communication I / F 104, a RAM (Random Access Memory) 105, a ROM (Read Only Memory) 106, an auxiliary storage device 107, and a processor 108. Each of these pieces of hardware is connected to each other via a bus 109 so as to be able to communicate with each other.

[0022] The input device 101 is, for example, a keyboard, a mouse, a touch panel, a physical button, etc. The display device 102 is, for example, a display, a display panel, etc. Note that the interactive device 10 does not necessarily have to have at least one of the input device 101 and the display device 102, for example.

[0023] The external I / F 103 is an interface with an external device such as a recording medium 103a. The interactive device 10 can read from and write to the recording medium 103a via the external I / F 103. Examples of the recording medium 103a include a flexible disk, a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), and a USB (Universal Serial Bus) memory card.

[0024] The communication I / F 104 is an interface for connecting to the communication network 40. The RAM 105 is a volatile semiconductor memory (storage device) that temporarily stores programs and data. The ROM 106 is a non-volatile semiconductor memory (storage device) that can store programs and data even when the power is turned off. The auxiliary storage device 107 is a storage device (storage device) such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory. The processor 108 is an arithmetic device such as a CPU (Central Processing Unit).

[0025] The dialogue device 10 according to this embodiment has the hardware configuration shown in Fig. 2 and is therefore capable of performing various processes described below. Note that the hardware configuration shown in Fig. 2 is merely an example, and the hardware configuration of the dialogue device 10 is not limited to this. The dialogue device 10 may, for example, have multiple auxiliary storage devices 107 or multiple processors 108, may not have some of the hardware shown in the figure, or may have various hardware components other than the hardware shown in the figure.

[0026] <Example of Functional Configuration of Dialogue Device 10> An example of the functional configuration of the dialogue device 10 according to this embodiment is shown in FIG. 3. As shown in FIG. 3, the dialogue device 10 according to this embodiment includes a receiving unit 201, a subject management unit 202, a pre-processing unit 203, a dialogue control unit 204, an information output unit 205, an information collection unit 206, and a reliability calculation unit 207. Each of these units is realized, for example, by a process in which one or more programs installed in the dialogue device 10 are executed by the processor 108 or the like. The dialogue device 10 according to this embodiment also includes an output information master DB 301, a subject information management DB 302, and a subject dialogue status management DB 303. Each of these DBs (databases) is realized, for example, by a storage area of ​​the auxiliary storage device 107 or the like. Note that at least one of these DBs may be realized, for example, by a storage area of ​​a storage device (e.g., a storage device included in a database server) communicably connected to the dialogue device 10.

[0027] The receiving unit 201 receives (subject ID, category information) or the subject ID from the user terminal 20. The subject ID is an example of identification information that identifies the subject. The category information is information that indicates the category of information to be acquired from the subject. One or more categories are specified in the category information. Examples of categories include "lifestyle habits," "thoughts," and "emotions." However, this is just one example, and the categories are not limited to "lifestyle habits," "thoughts," and "emotions," and various categories can be specified in the category information.

[0028] The subject management unit 202 uses the output information stored in the output information master DB 301 to create subject information and stores it in the subject information management DB 302. More specifically, when the receiving unit 201 receives (subject ID, category information), the subject management unit 202 uses output information stored in the output information master DB 301 that includes question information and that belongs to a category specified in the category information to create subject information that includes the subject ID and stores it in the subject information management DB 302. On the other hand, when the receiving unit 201 receives only the subject ID, the subject management unit 202 uses output information stored in the output information master DB 301 that includes question information to create subject information that includes the subject ID and stores it in the subject information management DB 302.

[0029] The pre-processing unit 203 executes pre-processing. That is, the pre-processing unit 203 acquires, for example, pre-information (e.g., information indicating answers to questionnaires or medical interview items, information indicating health checkup results, log information on exercise, sleep, etc.) and sets the pre-information for answers included in the subject information stored in the subject information management DB 302. Furthermore, the pre-processing unit 203 adds necessary subject information to the subject information management DB 302 based on, for example, the pre-information.

[0030] The dialogue control unit 204 controls whether presentation information or question information is to be output in the dialogue with the subject operating the subject terminal 30. That is, the dialogue control unit 204 determines whether presentation information or question information is to be output to the subject terminal 30, using weight information included in the subject dialogue status stored in the subject dialogue status management DB 303. Furthermore, if the dialogue control unit 204 determines to output presentation information, it selects the presentation information to be output to the subject terminal 30. If the dialogue control unit 204 determines to output question information, it selects the question information to be output to the subject terminal 30. Note that the weight information is information that represents a weight for controlling whether presentation information or question information is to be output.

[0031] The information output unit 205 outputs (transmits) the presentation information or question information selected by the dialogue control unit 204 to the subject terminal 30. As a result, the presentation information or question information is visualized in a UI (user interface) displayed on the display of the subject terminal 30.

[0032] When question information is output to the subject terminal 30 by the information acquisition unit 205 and answer information to the question information is input by the subject, the information collection unit 206 collects (acquires) the answer information.

[0033] The reliability calculation unit 207 calculates an index value called reliability, which indicates the degree to which the subject trusts the dialogue device 10 (or the provider of the dialogue device 10). The reliability is stored, for example, as information included in the subject dialogue status stored in the subject dialogue status management DB 303, and is used to update the weight information.

[0034] The output information master DB 301 stores output information including presentation information or question information. A specific example of the output information master DB 301 will be described later.

[0035] The subject information management DB 302 stores, for each subject ID, subject information for that subject ID. A specific example of the subject information management DB 302 will be described later.

[0036] The subject dialogue status management DB 303 stores the subject dialogue status of each subject ID. The subject dialogue status includes, for example, weight information for the subject of the subject ID, the number of responses from the subject to question information, and the reliability of the subject. Specific examples of the subject dialogue status management DB 303 will be described later.

[0037] <<Specific Example of Output Information Master DB 301>> An example of the output information master DB 301 is shown in Fig. 4. As shown in Fig. 4, the output information master DB 301 stores one or more pieces of output information, and each piece of output information includes an "information number," a "presentation / question," a "category," a "keyword / question item," an "output order," and "presentation information / question information."

[0038] "Information No." is set to an information number that is identification information for identifying the output information. "Presentation / Question" is set to information indicating whether the output information contains presentation information or question information (e.g., "Presentation" if presentation information is included, and "Question" if question information is included). "Category" is set to a category of question information if the output information contains question information. "Keyword / Question Item" is set to a keyword related to the presentation information if the output information contains presentation information (or "-" (hyphen) if there is no keyword), or a question item to which the question information belongs if the output information contains question information. "Output Order" is set to a number indicating the output order or "Optional" indicating that any output order is acceptable. "Presentation Information / Question Information" is set to a sentence (text, etc.) indicating the presentation information or question information included in the output information.

[0039] In this way, all output information including presentation information or question information is stored in the output information master DB 401. It should be noted that the output information master DB 301 shown in Fig. 4 is merely an example and is not limited to this.

[0040] <Example of Operation of Dialogue Device 10> An example of operation of the dialogue device 10 according to this embodiment will be described below with reference to FIG.

[0041] The receiving unit 201 receives (subject ID, category information) or the subject ID from the user terminal 20 (step S101). Note that the (subject ID, category information) or the subject ID is specified by, for example, a user operating the user terminal 20.

[0042] The subject management unit 202 determines whether or not category information has been received in the above step S101 (step S102).

[0043] If it is determined in step S102 above that category information has been received (i.e., if (subject ID, category information) has been received in step S101 above), the subject management unit 202 uses output information stored in the output information master DB 301 that includes question information and that belongs to a category specified in the category information to create subject information that includes the subject ID, and stores the created subject information in the subject information management DB 302 (step S103). More specifically, the subject management unit 202 executes, for example, the following steps 1-1 to 1-4.

[0044] Step 1-1: The subject management unit 202 identifies output information stored in the output information master DB 301 in which the question is set to "presentation / question" and the category included in the category information received in step S101 above is set to "category."

[0045] Step 1-2: The subject management unit 202 defines the "keyword / question item" included in the output information identified in step 1-1 above as the "question item," and then extracts the "information number," "category," and "question item" from the output information. This results in information in the format (information number, category, question item).

[0046] Step 1-3: The subject management unit 202 adds to the information extracted in step 1-2 above a "subject ID" to which the subject ID received in step S101 above is set, an "answer" to which NULL is set, and a "priority flag" to which a "-" (hyphen) is set. This results in information in the format (subject ID, information No., category, question item, answer, priority flag). The priority flag is flag information that is set to "1" for subject information corresponding to a question that needs to be output preferentially to the subject terminal 30.

[0047] Step 1-4: The subject management unit 202 stores the information obtained in step 1-3 above as subject information in the subject information management DB 302. As a result, subject information in the format of (subject ID, information No., category, question item, answer, priority flag) is stored in the subject information management DB 302.

[0048] On the other hand, if it is determined in step S102 above that category information has not been received (i.e., if only the subject ID has been received in step S101 above), the subject management unit 202 uses output information that includes question information from the output information stored in the output information master DB 301 to create subject information that includes the subject ID, and stores the created subject information in the subject information management DB 302 (step S104). More specifically, the subject management unit 202 executes, for example, the following steps 2-1 to 2-4.

[0049] Step 2-1: The subject management unit 202 identifies output information stored in the output information master DB 301 in which the question is set to "presentation / question."

[0050] Step 2-2: The subject management unit 202 defines the "keyword / question item" included in the output information identified in step 2-1 above as the "question item," and then extracts the "information number," "category," and "question item" from the output information. This results in information in the format of (information number, category, question item).

[0051] Step 2-3: The subject management unit 202 adds to the information extracted in step 2-2 above the subject ID set in "Subject ID," the "Answer" set to NULL, and the "Priority Flag" set to "-" (hyphen). This results in information in the format (Subject ID, Information No., Category, Question, Answer, Priority Flag).

[0052] Step 2-4: The subject management unit 202 stores the information obtained in step 2-3 above as subject information in the subject information management DB 302. As a result, subject information in the format of (subject ID, information No., category, question item, answer, priority flag) is stored in the subject information management DB 302.

[0053] Following step S103 or S104, the pre-processing unit 203 executes pre-processing (step S105). As the pre-processing, the pre-processing unit 203 executes, for example, the following steps 3-1 to 3-3.

[0054] Step 3-1: The pre-processing unit 203 acquires pre-information about the subject whose subject ID was received in step S101 from an external source (e.g., the subject terminal 30, an external server storing data on services used by the subject, etc.). Examples of the pre-information include information indicating answers to questionnaires and medical interview items, information indicating health checkup results, and log information on exercise, sleep, etc.

[0055] Step 3-2: The pre-processing unit 203 refers to the "question item" of the subject information of the subject ID received in step S101 above among the subject information stored in the subject information management DB 302, and if the information to be set as the "answer" corresponding to that "question item" is included in the pre-information, sets that information to the "answer" as answer information.

[0056] For example, suppose that, with respect to the subject information of the subject ID, subject information in which "exercise timing" is set as a "question item" and subject information in which "type of exercise" is set as a "question item" are stored in the subject information management DB 302. At this time, suppose that log information indicating that the subject takes a walk in the morning is acquired as prior information from the subject terminal 30 in the above step 3-1. In this case, the prior processing unit 203 sets "morning" as the answer information to the "answer" of the subject information in which "exercise timing" is set as a "question item," and sets "walk" as the answer information to the "answer" of the subject information in which "type of exercise" is set as a "question item."

[0057] Step 3-3: When the preliminary information includes a medical checkup result for which a value exceeding a predetermined reference value is set, the pre-processing unit 203 may obtain output information from the output information master DB 301 in which a question item corresponding to the medical checkup result is set in "Keyword / Question Item," and create subject information from the output information and add it to the subject information management DB 302. At this time, the pre-processing unit 203 creates subject information in which the subject ID received in step S101 above is set in "Subject ID," NULL is set in "Answer," and "Priority Flag" is set to "1."

[0058] For example, if the preliminary information includes a medical checkup result in which HbA1c, one of the basic test items in a medical checkup, exceeds a reference value, the preliminary processing unit 203 acquires output information from the output information master DB 301 in which HbA1c or a question related thereto is set in the "Keyword / Question Item" field. The preliminary processing unit 203 then creates subject information from the output information and stores it in the subject information management DB 302. At this time, the preliminary processing unit 203 creates subject information in which the "Subject ID" field is set to the subject ID, the "Information No." field is set to the same information number as the output information, the "Question Item" field is set to HbA1c or a question related thereto, the "Answer" field is set to NULL, and the "Priority Flag" field is set to "1." The "Category" field may be set to the same category as the output information, or a "-" (hyphen), for example. This enables question information for asking about the HbA1c value to be output to the subject preferentially.

[0059] It is possible that the output information in which the question item corresponding to the medical checkup result is set in "Keyword / Question Item" does not exist in the output information master DB 301. In this case, the pre-processing unit 203 may generate an information number, and then create subject information in which the subject ID is set in "Subject ID," the information number is set in "Information No.", a "-" (hyphen) is set in "Category," HbA1c is set in "Question Item," NULL is set in "Answer," and "1" is set in "Priority Flag," and store the created subject information in the subject information management DB 302.

[0060] Following step S105 above, the dialogue control unit 204 determines whether or not to execute dialogue processing with the subject terminal 30 operated by the subject of the subject ID received in step S101 above (step S106). The dialogue control unit 204, for example, refers to the subject information of the subject ID among the subject information stored in the subject information management DB 302, and determines to execute dialogue processing if subject information in which NULL is set in the "answer" field exists, but not to execute dialogue processing if subject information in which NULL is set in the "answer" field does not exist.

[0061] If it is determined in step S106 above that the dialogue processing is to be executed, the dialogue device 10 executes the dialogue processing with the subject terminal 30 operated by the subject of the subject ID (step S107), and returns to step S106 above. In the dialogue processing, either presentation information or question information is output to the subject terminal 30 using weight information included in the subject dialogue status of the subject ID, and if question information is output, answer information to the question information is acquired from the subject terminal 30. Details of the dialogue processing will be described later.

[0062] On the other hand, if it is determined in step S106 that the dialogue process is not to be executed, the dialogue device 10 ends the process. In this case, the answer information acquired from the subject is set in the "answer" field of all the subject information of the subject ID among the subject information stored in the subject information management DB 302.

[0063] <<Specific Example of Subject Information Management DB 302>> A specific example of the subject information management DB 302 after the pre-processing in step S105 is performed is shown in Fig. 6. As shown in Fig. 6, the subject information management DB 302 stores one or more pieces of subject information, and each piece of subject information includes a "subject ID," an "information number," a "category," a "question item," an "answer," and a "priority flag."

[0064] The "Subject ID" is set to the subject ID of the subject to whom the subject information is to be output. The "Information No." is set to the information No. of the subject information. The "Category" and "Question Item" are set to the question item to which the subject information belongs. The "Answer" is set to answer information representing the answer to the subject information (or NULL if no answer information is set). The "Priority Flag" is set to "1" if question information related to the subject information needs to be output preferentially, or "-" (hyphen) if not.

[0065] 6, answer information is set for "Answer" in the subject information for "Info_06" and "Info_08" with "Information No." This is because the information included in the prior information was set as answer information in step 3-2 above.

[0066] 6, the "priority flag" of the subject information having the "information number" of "Info_101" is set to "1." This is because the subject information created from the prior information in step 3-3 above has been added to the subject information management DB 302.

[0067] In this way, for each subject ID, subject information related to the subject of that subject ID is stored in the subject information management DB 302. It goes without saying that the subject information management DB 302 shown in Fig. 6 is an example and is not limited to this.

[0068] <<Specific Example of Target Dialogue Status Management DB 303>> A specific example of the target dialogue status management DB 303 at a certain point in time is shown in Fig. 7. As shown in Fig. 7, the target dialogue status management DB 303 stores one or more target dialogue statuses, and each target dialogue status includes a "target ID," a "first weight," a "second weight," a "number of responses," and a "reliability."

[0069] The "subject ID" is set to the subject ID of the subject corresponding to the subject dialogue status. The "first weight" is set to a first weight representing the weight for the presented information. The "second weight" is set to a second weight representing the weight for the question information. The "number of answers" is set to the number of times the subject has sent answer information in response to the question information. The "reliability" is set to the reliability of the subject. The first weight and second weight set in the "first weight" and "second weight" respectively are weight information.

[0070] In this way, for each subject ID, the subject dialogue status related to the subject of that subject ID is stored in the subject dialogue status management DB 303. It goes without saying that the subject dialogue status management DB 303 shown in Fig. 7 is an example and is not limited to this.

[0071] Hereinafter, the number of times that a dialogue process has been executed between a subject having a certain subject ID and the subject terminal 30 operated by the subject is defined as i, and the first weight at the start of the i-th dialogue process is defined as w ｐ（ｉ） , the second weight is w ｑ（ｉ） Similarly, the number of answers at the start of the i-th dialogue process is a ｉ , confidence level t ｉ In addition, 0≦w ｐ（ｉ） ≦1, w ｑ（ｉ） = 1 - w ｐ（ｉ） The first weight w ｐ（ｉ） , the second weight w ｑ（ｉ） , confidence level t ｉ are initialized to appropriate values, and the number of responses a ｉ The initial value of is assumed to be 0.

[0072] The first weight w ｐ（ｉ） The initial value of the second weight w ｑ（ｉ） This is because it is preferable to output a large amount of presented information in the early stages of a dialogue in order to encourage the subject to self-disclosure.

[0073] <Dialogue Processing> An example of the dialogue processing in step S107 in Fig. 5 will be described below with reference to Fig. 8. As an example, the i-th (where i≧1) dialogue processing between the subject terminal 30 operated by the subject whose subject ID is "001" will be described below.

[0074] The dialogue control unit 204 acquires the weight information of the subject ID "001" from the subject dialogue status management DB 303 (step S201).

[0075] The dialogue control unit 204 selects presentation information or question information using the weight information acquired in step S201 (step S202). More specifically, the dialogue control unit 204 executes the following steps 4-1 to 4-5.

[0076] Step 4-1: The dialogue control unit 204 acquires the information number of the subject information stored in the subject information management DB 302, which is the subject information with subject ID "001" and for which "Answer" is set to NULL.

[0077] Step 4-2: The dialogue control unit 204 determines whether to select the presentation information or the question information in accordance with the weight information. That is, the dialogue control unit 204 selects the first weight w ｐ（ｉ） is the occurrence probability of the presented information, and the second weight w ｑ（ｉ） is regarded as the occurrence probability of the question information, and the first weight w ｐ（ｉ） and the second weight w ｑ（ｉ） It is determined whether the presentation information or the question information is generated according to the above.

[0078] Step 4-3: If the dialogue control unit 204 determines to select presentation information in step 4-2 above, it randomly selects output information for which "presentation" is set in "presentation / question" from the output information master DB 301, and selects the text set in "presentation information / question information" of that output information as the presentation information. However, if there is output information for which "presentation" is set in "presentation / question" and "i" is set in "output order," the dialogue control unit 204 selects the text set in "presentation information / question information" of that output information as the presentation information.

[0079] In addition, when randomly selecting output information in step 4-3 above, if there is output information that has already been output in the past to the subject with subject ID "001," the dialogue control unit 204 may exclude that output information before randomly selecting it.

[0080] Step 4-4: If the dialogue control unit 204 determines to select question information in step 4-2 above, it randomly selects output information stored in the output information master DB 301 for which the information No. acquired in step 4-1 above is set in "Information No.", and selects the text set in "Presentation Information / Question Information" of that output information as the question information. However, if there is output information for which "i" is set in "Output Order" among the output information for which the information No. acquired in step 4-1 above is set in "Information No.", the dialogue control unit 204 selects the text set in "Presentation Information / Question Information" of that output information as the question information.

[0081] If the information numbers acquired in step 4-1 above include an information number of subject information whose "priority flag" is set to "1," the dialogue control unit 204, when selecting question information in step 4-4 above, preferentially selects the sentence set in the "presentation information / question information" field of the output information of that information number as the question information. However, it is possible that the information number of subject information whose "priority flag" is set to "1" does not exist in the output information master DB 301. In this case, the dialogue control unit 204 may generate question information using a known method (e.g., a sentence generation method using machine learning, etc.) or an external service (e.g., a generation AI service, etc.) based on the question item set in the "question item" of the subject information whose "priority flag" is set to "1."

[0082] Following step S202, the dialogue control unit 204 determines whether presentation information or question information was selected in step S202 (step S203).

[0083] If it is determined in step S203 that the presentation information has been selected, the information output unit 205 outputs the presentation information selected in step S202 to the subject terminal 30 operated by the subject with subject ID "001" (step S204). As a result, the presentation information is visualized in the UI displayed on the display of the subject terminal 30. Specific examples of the UI displayed on the display of the subject terminal 30 will be described later.

[0084] On the other hand, if it is determined in step S203 that the question information has been selected, the information output unit 205 outputs the question information selected in step S202 to the subject terminal 30 operated by the subject with subject ID "001" (step S205). As a result, the question information is visualized in the UI displayed on the display of the subject terminal 30.

[0085] Hereinafter, it is assumed that the answer information to the question information is input by the subject operating the subject terminal 30. As a result, the answer information is transmitted from the subject terminal 30 to the dialogue device 10.

[0086] The information collecting unit 206 receives the response information transmitted from the subject terminal 30 (step S206).

[0087] The information collecting unit 206 sets the answer information received in step S206 to the "answer" of the subject information of the subject information with subject ID "001" and information No. included in the output information selected in step 4-4 above (step S207), among the subject information stored in the subject information management DB 302. As a result, the answer information to the question information output in step S205 above is set to the "answer" of the corresponding subject information.

[0088] Following step S204 or step S207, the dialogue control unit 204 determines whether to calculate the reliability t (step S208). Note that the dialogue control unit 204 may, for example, determine to calculate the reliability t every time, or may calculate the reliability t only when some trigger occurs or when a condition is satisfied (e.g., when a response is received to a subjective questionnaire, which will be described later).

[0089] If it is determined in step S208 that the reliability t should be calculated, the reliability calculation unit 207 calculates the reliability t (step S209). The reliability calculation unit 207 may calculate the reliability t by, for example, one of the following reliability calculation methods 1 to 4.

[0090] Reliability calculation method 1: The reliability calculation unit 207 irregularly or regularly sends a subjective questionnaire such as "Do you feel that the system (interactive device 10) is thinking about you?" to the subject terminal 30. Then, the reliability calculation unit 207 calculates the reliability t of the subject ID "001" based on the response to this subjective questionnaire. For example, if the response to the subjective questionnaire is "I totally agree," it is assigned 2 points, if it is "I agree," it is assigned 1 point, and if it is "I don't agree," "I don't agree," or "I totally disagree," it is assigned 0 points, and the scores are calculated as the reliability t.

[0091] Reliability calculation method 2: The reliability calculation unit 207 calculates the current number of responses a ｉ is calculated as the reliability t of the target person ID "001." This is because if the target person transmits answer information in response to question information, the target person can be considered to trust the system (the dialogue device 10).

[0092] Reliability calculation method 3: The reliability calculation unit 207 uses the scores obtained for multiple subjects using the above reliability calculation method 1 to calculate a relative value with respect to other subjects (e.g., difference from the average score of other subjects, standard deviation, etc.) as the reliability t of subject ID "001".

[0093] Reliability calculation method 4: The reliability calculation unit 207 calculates the reliability based on the number of responses a ｉ Relative value to the number of responses of other subjects a ｉ The reliability t of the subject ID "001" is calculated by subtracting the average value of the test result from the test result (difference from the average value, standard deviation, etc.).

[0094] Following step S209 above, or if it is not determined in step S208 above that the reliability t should be calculated, the dialogue control unit 204 updates the weight information (first weight and second weight), the number of responses, and the reliability included in the subject dialogue status of the subject ID "001" among the subject dialogue statuses stored in the subject dialogue status management DB 303 (step S210). That is, the dialogue control unit 204 executes, for example, the following steps 5-1 to 5-3.

[0095] Step 5-1: If step S209 is executed, the dialogue control unit 204 ｉ＋１ ←t, if step S209 above has not been executed, t ｉ＋１ ←t ｉ The reliability t included in the subject dialogue status of the subject ID “001” is ｉ t ｉ＋１ Update to.

[0096] Step 5-2: If the dialogue control unit 204 receives answer information in step S206, ｉ＋１ ←a ｉ +1, otherwise a ｉ＋１ ←a ｉ The number of responses a included in the dialogue status of the subject ID “001” is ｉ A ｉ＋１ Update to.

[0097] Step 5-3: The dialogue control unit 204 ｐ（ｉ＋１） ←(1 / t ｉ＋１ ) ×w ｐ（ｉ） , w ｑ（ｉ＋１） ←1-w ｐ（ｉ＋１） The first weight w included in the subject dialogue status of the subject ID “001” is ｐ（ｉ） and the second weight w ｑ（ｉ） respectively ｐ（ｉ＋１） and w ｑ（ｉ＋１） This makes it possible to reduce the first weight, which is the weight of the presented information, as the reliability increases.

[0098] <<Specific Example of UI>> Fig. 9 shows a specific example of a UI displayed on the display of the subject terminal 30. As shown in Fig. 9, the UI 1000 displayed on the display of the subject terminal 30 visualizes the presentation information or question information output from the dialogue device 10. Furthermore, when answer information is input by the subject, the answer information is also visualized on the UI 1000. In the example shown in Fig. 9, presentation information M1001, question information M1002, and answer information 1003 to the question information M1002 are visualized on the UI 1000. The subject can input the answer information by any method (e.g., input using a software keyboard, voice input, etc.).

[0099] <Modifications> Modifications of the above embodiment will be described below. Note that the following modifications can be combined as appropriate as long as they do not contradict each other.

[0100] Modification 1 In the above embodiment, the first weight w ｐ（ｉ） and the second weight w ｑ（ｉ） However, weights for question information may be present for each category. For example, if categories such as "lifestyle" and "thoughts" exist, the following weights may be present:

[0101] w ｐ（ｉ） : Weight for presented information w ｑｌ（ｉ） : Weight for question information in the category "lifestyle" w ｑｔ（ｉ） : Weight for question information in the category "Thoughts" w ｑｏ（ｉ） : Weight for question information in other categories, where 0≦w ｐ（ｉ） ≦1, 0≦w ｑｌ（ｉ） ≦1, 0≦w ｑｔ（ｉ） ≦1, 0≦w ｑｏ（ｉ） ≦1, w ｐ（ｉ） +w ｑｌ（ｉ） +w ｑｔ（ｉ） +w ｑｏ（ｉ） = 1 is satisfied.

[0102] In this case, in step 4-2 above, ｐ（ｉ） is the occurrence probability of the presented information, w ｑｌ（ｉ） is the occurrence probability of question information in the category "lifestyle habits", w ｑｔ（ｉ） is the occurrence probability of question information in the category "thoughts", w ｑｏ（ｉ） is regarded as the occurrence probability of question information in other categories, and it is determined whether presented information, question information in the category "lifestyle habits", question information in the category "thoughts", or question information in other categories will occur.

[0103] As a result, if it is determined that question information in the category "lifestyle" will occur, question information in the category "lifestyle" can be selected. Similarly, if it is determined that question information in the category "thought" will occur, question information in the category "thought" can be selected, and if it is determined that question information in other categories will occur, question information in other categories can be selected. Note that when updating the weight, the reliability t ｉ＋１ It can be updated using

[0104] Modification 2 Generally, in interviews for specific health guidance, answers to questions in the category "lifestyle" are often considered more important than answers to questions in the category "thoughts." For this reason, in the above modification 1, the weight w ｑｌ（ｉ） While increasing the weight of question information in the category "thoughts", ｑｔ（ｉ） It is preferable to make the weight w for the question information in the category "lifestyle" small. Also, as the dialogue progresses (as the value of i increases), ｑｌ（ｉ） While reducing the weight w for question information in the category "thoughts," ｑｔ（ｉ） It is preferable to increase

[0105] Therefore, in the second modification, when updating the weight in the above step 5-3, as i becomes larger, w ｑｔ（ｉ） As i gets larger, w ｑｔ（ｉ） is updated so that it approaches 1. This makes it possible to collect answer information about the subject's lifestyle habits in the early stages of the dialogue, and to collect answer information about the subject's thoughts as the dialogue progresses.

[0106] For example, w ｑｔ（ｉ） is a monotonically decreasing sigmoid function, w ｑｔ（ｉ） It is conceivable that the values ​​can be updated according to a sigmoid function that has monotonically increasing properties. However, it goes without saying that this is just one example.

[0107] Variation 3: In step 4-3 above, the presentation information included in the output information is selected, and in step 4-4 above, the question information included in the output information is selected. However, the presentation information or the question information may be generated using a known method (e.g., a text generation method using machine learning, etc.) or an external service (e.g., a generation AI service, etc.).

[0108] For example, the generation AI may generate presentation information using the keywords set in the "Keywords / Question Items" of the output information as input, or similarly, the generation AI may generate question information using the question items set in the "Keywords / Question Items" of the output information as input.

[0109] As described above, the dialogue device 10 according to the present embodiment outputs presentation information or question information to the subject terminal 30 using weight information that is dynamically updated according to the subject's reliability, the passage of time, etc. This encourages the subject to self-disclose in response to the question information, making it possible to efficiently acquire information about the subject. This allows the interviewer to, for example, efficiently provide guidance to support the subject's behavioral change by referring to the information disclosed by the subject.

[0110] <Other Application Examples> In the above embodiment, the dialogue system 1 is described assuming an interview for specific health guidance and interactively acquiring information about the subject of the interview, but the dialogue system 1 according to this embodiment can be applied to other purposes besides interviews for specific health guidance.

[0111] Examples of applications of the dialogue system 1 according to the present embodiment include mental health and interviews between teachers and students in educational settings. Another example of applications of the dialogue system 1 according to the present embodiment includes dialogues between caregivers, volunteers, and local elderly people (e.g., dialogues to promote community participation). However, these are merely examples, and the dialogue system 1 according to the present embodiment can be applied to cases where, when a dialogue is taking place between two or more parties, information about the participants in the dialogue is acquired.

[0112] The present invention is not limited to the above-described specifically disclosed embodiments, and various modifications, changes, and combinations with known technologies are possible without departing from the scope of the claims.

[0113] 1 Dialogue system 10 Dialogue device 20 User terminal 30 Target person terminal 40 Communication network 101 Input device 102 Display device 103 External I / F 103a Recording medium 104 Communication I / F 105 RAM 106 ROM 107 Auxiliary storage device 108 Processor 109 Bus 201 Receiving unit 202 Target person management unit 203 Pre-processing unit 204 Dialogue control unit 205 Information output unit 206 Information collection unit 207 Reliability calculation unit 301 Output information master DB 302 Target person information management DB 303 Target person dialogue status management DB

Claims

1. An information processing device that acquires information about a subject, comprising: a selection unit that selects presentation information representing the presentation of information to the subject and question information representing a question for acquiring information about the subject based on weight information regarding the presentation information or question information; an output unit that outputs the presentation information or question information selected by the selection unit to a terminal used by the subject; and an acquisition unit that, when answer information to the question information is transmitted from the terminal, acquires the answer information as information about the subject.

2. The information processing device described in claim 1, wherein the weight information includes a first weight representing the occurrence probability of the presented information and a second weight representing the occurrence probability of the question information, and the selection unit selects the presented information or the question information according to the first weight and the second weight.

3. The information processing device described in claim 1, wherein the weight information includes a first weight representing the occurrence probability of the presented information and a second weight representing the occurrence probability of the question information for each category of the question, and the selection unit selects the presented information or the question information according to the first weight and the second weight.

4. An information processing device as described in claim 2 or 3, having an update unit that updates the weight information based on the reliability of the subject, wherein the update unit updates the first weight and the second weight so that the higher the reliability, the lower the value of the first weight and the higher the value of the second weight.

5. An information processing device as described in claim 4, further comprising a calculation unit that calculates the reliability based on the number of times answer information is sent from the terminal or information representing the subjective opinion of the subject, and the update unit updates the weight information based on the reliability calculated by the calculation unit.

6. The information processing device of claim 3, further comprising an update unit that updates the first weight and the second weight so that, as the presented information or the question information is output, the value of the second weight representing the probability of occurrence of the question information related to the lifestyle habits decreases and the value of the second weight representing the probability of occurrence of the question information related to the thoughts increases, wherein the categories include lifestyle habits and thoughts behind the lifestyle habits.

7. An information processing method in which an information processing device that acquires information about a subject executes the following steps: a selection step of selecting presentation information that represents the presentation of information to the subject and question information that represents a question for acquiring information about the subject based on weight information regarding the presentation information or question information; an output step of outputting the presentation information or question information selected in the selection step to a terminal used by the subject; and an acquisition step of acquiring, when answer information to the question information is transmitted from the terminal, the answer information as information about the subject.

8. A program that causes an information processing device that acquires information about a subject to execute the following steps: a selection step of selecting presentation information that represents the presentation of information to the subject and question information that represents a question for acquiring information about the subject based on weight information regarding the presentation information or question information; an output step of outputting the presentation information or question information selected in the selection step to a terminal used by the subject; and an acquisition step of acquiring, when answer information to the question information is transmitted from the terminal, the answer information as information about the subject.

Images