Decision-making support device, decision-making support method, decision-making support program, and recording medium

Abstract

Provided is a decision-making support device that can address a personnel shortage in personal duty ranges. A decision-making support device according to this disclosure includes a dialogue interface generation unit, a submission acquisition unit, and a response unit. The dialogue interface generation unit generates a dialogue interface by which a proxy existence model and a user interact. The submission acquisition unit acquires user submissions input to the dialogue interface. The response unit causes the proxy existence model mimicking a prescribed target person to generate a response based on the submission, and outputs the response to the dialogue interface. The proxy existence model is a machine-trained model that has been trained using personality information of the target person.

Description

Decision-making support device, decision-making support method, decision-making support program, and recording medium

[0001] The present disclosure relates to a decision-making support device, a decision-making support method, a decision-making support program, and a recording medium.

[0002] In recent years, the decline in the working population has been accelerating in Japan, and there are concerns about the impact on various industries due to a shortage of human resources. Therefore, in order to compensate for the shortage of human resources, efforts have been promoted for human resource development and reskilling. In addition, in efforts such as reskilling, the use of AI (Artificial Intelligence) and RPA (Robotic Process Automation) has been attempted. For example, in Patent Document 1, a server connected to a network has database means, and the database means acquires employee information and information on the future job the employee wants to have, and compares and examines the skills required for each job collected via the network by AI, the current job, and the future job the employee wants to have, and displays the matching degree and required skills for the future job the employee wants to have. An AI reskilling display system is disclosed.

[0003] Japanese Patent Application Laid-Open No. 2023-158767

[0004] However, with current mechanisms such as AI and RPA, it is difficult to use them in personal areas where human decision-making is often involved, and there is a problem that it is difficult to address the shortage of human resources in such areas.

[0005] Therefore, an object of the present disclosure is to provide a decision-making support device, a decision-making support method, a decision-making support program, and a recording medium capable of addressing the shortage of human resources in personal work areas.

[0006] To achieve the above objective, the decision support device of this disclosure includes a dialogue interface generation unit, a post acquisition unit, and a response unit, wherein the dialogue interface generation unit generates a dialogue interface for a proxy existence model and a user to interact, the post acquisition unit acquires user posts input into the dialogue interface, and the response unit causes a proxy existence model that mimics a predetermined target person to generate a response based on the post, and outputs the response to the dialogue interface.

[0007] The decision support method of this disclosure includes a dialogue interface generation step, a post acquisition step, and a response step, wherein the dialogue interface generation step generates a dialogue interface for a user to interact with a proxy existence model; the post acquisition step acquires user posts entered into the dialogue interface; the response step causes a proxy existence model that mimics a predetermined target person to generate a response based on the post; and outputs the response to the dialogue interface, wherein the proxy existence model is a machine learning model that has learned the personality information of the target person, and each step is performed by a computer.

[0008] The decision support program of this disclosure includes a dialogue interface generation procedure, a post acquisition procedure, and a response procedure, wherein the dialogue interface generation procedure generates a dialogue interface for a user to interact with a proxy existence model; the post acquisition procedure acquires a user post entered into the dialogue interface; the response procedure causes a proxy existence model, which mimics a predetermined target person, to generate a response based on the post; and outputs the response to the dialogue interface, wherein the proxy existence model is a machine learning model that has learned the personality information of the target person; and the program is designed to cause a computer to execute each of these procedures.

[0009] The recording medium of this disclosure is a computer-readable recording medium that records a decision support program for causing a computer to execute each of the following procedures: a dialogue interface generation procedure, a post acquisition procedure, and a response procedure, wherein the dialogue interface generation procedure generates a dialogue interface for a user to interact with a proxy existence model; the post acquisition procedure acquires a user post entered into the dialogue interface; the response procedure causes a proxy existence model that mimics a predetermined target person to generate a response based on the post; and outputs the response to the dialogue interface, wherein the proxy existence model is a machine learning model that has learned the personality information of the target person.

[0010] According to this disclosure, it is possible to address the shortage of personnel in personal work areas.

[0011] Figure 1 is a block diagram showing the configuration of an example of the decision support device of this disclosure. Figure 2 is a block diagram showing an example of the hardware configuration of the decision support device of this disclosure. Figure 3 is a flowchart showing an example of processing in the decision support device of this disclosure. Figure 4 is a schematic diagram showing an example of a dialogue screen generated by the decision support device of this disclosure. Figure 5 is a schematic diagram showing an example of a dialogue screen generated by the decision support device of this disclosure. Figure 6 is a block diagram showing the configuration of an example of the decision support device of this disclosure. Figure 7 is a flowchart showing an example of processing in the decision support device of this disclosure. Figure 8 is a block diagram showing the configuration of an example of the proxy existence model manufacturing device of this disclosure. Figure 9 is a block diagram showing an example of the hardware configuration of the proxy existence model manufacturing device of this disclosure. Figure 10 is a flowchart showing an example of processing in the proxy existence model manufacturing device of this disclosure.

[0012] In this disclosure, "personal work domains" refer to fields that involve cognitive, non-routine tasks where human will is central to decision-making. Specific examples of personal work domains include, but are not limited to, fields such as mentoring, counseling, surveys, coaching, teaching, and consulting.

[0013] In this disclosure, the “surrogate presence model” is a machine learning model that has learned the personality information of a subject so that it can behave like a specific subject. The method for manufacturing the surrogate presence model is not particularly limited and can be manufactured by any method, but it can be manufactured, for example, by the method for manufacturing the surrogate presence model described in this disclosure. The surrogate presence model in this disclosure may be a machine learning model that has learned the personality information of a specific subject, such as a predetermined mentor, counselor, researcher, coach, teacher, consultant, etc.

[0014] Next, embodiments of the present disclosure will be described with reference to the drawings. The present disclosure is not limited to the following embodiments. In the following drawings, the same parts are denoted by the same reference numerals. Furthermore, unless otherwise specified, the descriptions of each embodiment can be used interchangeably with those of the others, and unless otherwise specified, the configurations of each embodiment can be combined.

[0015] [Embodiment 1] The decision support device of this embodiment will be described with reference to Figure 1. Figure 1 is a block diagram showing the configuration of an example of the decision support device 10 of this embodiment. As shown in Figure 1, the decision support device 10 (hereinafter also referred to as "this device 10") includes a dialogue interface generation unit 11, a post acquisition unit 12, and a response generation unit 13. In addition, although not shown, this device 10 may also include, for example, an input unit, an output unit, a display unit and / or a storage unit.

[0016] The device 10 may be, for example, a single device including the aforementioned parts, or it may be a device in which the aforementioned parts can be connected via a communication network. Furthermore, the device 10 can be connected to an external device described later via a communication network. The communication network is not particularly limited and a known network can be used, for example, it may be wired or wireless. Examples of communication networks include the Internet, WWW (World Wide Web), telephone lines, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), LPWA (Low Power Wide Area), L5G (Local 5G), etc. Examples of wireless communication include Wi-Fi®, Bluetooth®, Local 5G, LPWA, etc. The aforementioned wireless communication may be in the form of direct communication between devices (Ad Hoc communication), infrastructure communication, or indirect communication via an access point. The device 10 may, for example, be incorporated into a server as a system. The device 10 may also be, for example, a personal computer (PC, e.g., desktop or notebook), smartphone, tablet terminal, etc., on which the program disclosed herein is installed. Furthermore, the device 10 may be in the form of cloud computing or edge computing, for example, in which at least one of the aforementioned parts is on a server and the other parts are on a terminal.

[0017] Figure 2 illustrates a block diagram of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit 101, memory 102, bus 103, storage device 104, input device 105, output device 106, communication device (communication unit) 107, etc. Each part of the device 10 is interconnected via the bus 103 through its respective interface (I / F).

[0018] The central processing unit 101 operates in coordination with other components via controllers (system controller, I / O controller, etc.) and is responsible for the overall control of the device 10. In the device 10, the central processing unit 101 executes, for example, the program disclosed herein or other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 101 functions as a dialogue interface generation unit 11, a post acquisition unit 12, and a response generation unit 13. The device 10 may also include other computing devices such as a CPU, GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), or a combination thereof as its computing device.

[0019] Bus 103 can also be connected to external devices, for example. Examples of such external devices include external storage devices (external databases, etc.), electrocardiographs, printers, external input devices, external display devices, audio output devices such as speakers, external imaging devices such as cameras, and various sensors such as acceleration sensors, geomagnetic sensors, and direction sensors. The device 10 can be connected to an external network (the aforementioned communication network) by a communication device 107 connected to bus 103, for example, and can also be connected to other devices via the external network.

[0020] Memory 102 may be, for example, main memory. When the central processing unit 101 performs processing, memory 102 reads various operational programs, such as the program of this disclosure, stored in the storage device 104 (described later), and the central processing unit 101 receives data from memory 102 and executes the program. The main memory may be, for example, RAM (random access memory). Alternatively, memory 102 may be, for example, ROM (read-only memory).

[0021] The storage device 104 is also called an auxiliary storage device, for example, in relation to the main memory (primary memory). As described above, the storage device 104 stores an operating program including the program of this disclosure. The storage device 104 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited and may be internal or external, for example, an HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc. The storage device 104 may be, for example, a hard disk drive (HDD) in which the recording medium and the drive are integrated, or a solid state drive (SSD). If the device 10 includes, for example, the storage device 104 functions as the storage unit.

[0022] In this device 10, the memory 102 and storage device 104 can also store various types of information, such as log information, information obtained from an external database (not shown) or external devices, information generated by this device 10, and information used by this device 10 when executing processing. At least some of the information may be stored on an external server other than the memory 102 and storage device 104, or it may be stored in a distributed manner across multiple terminals using blockchain technology or the like.

[0023] The device 10 further includes, for example, an input device 105 and an output device 106. The input device 105 may include, for example, a pointing device such as a touch panel, trackpad, or mouse; a keyboard; imaging means such as a camera or scanner; a card reader such as an IC card reader or magnetic card reader; an audio input means such as a microphone; and so on. The output device 106 may include, for example, a display device such as an LED display or liquid crystal display; an audio output device such as a speaker; a printer; and so on. In this embodiment 1, the input device 105 and the output device 106 are configured separately, but the input device 105 and the output device 106 may be configured as an integrated unit, such as a touch panel display.

[0024] Next, an example of the decision support method of this embodiment will be described based on the flowchart in Figure 3. The decision support method of this embodiment can be implemented, for example, using the decision support device 10 shown in Figures 1 and 2, as follows. Note that the decision support method of this embodiment is not limited to the use of the decision support device 10 shown in Figures 1 and 2.

[0025] The dialogue interface generation unit 11 generates a dialogue interface for the proxy existence model and the user to interact (S1, dialogue interface generation step). The type of the dialogue interface is not particularly limited as long as it is an interface that enables the proxy existence model and the user to interact. As a specific example, the dialogue interface generation unit 11 generates a dialogue interface that includes a dialogue screen for the proxy existence model and the user to interact. The dialogue screen is not particularly limited and may include, for example, a function for inputting user posts and a function for displaying the proxy existence model's responses, as described later. The dialogue screen may include, for example, a subject input field, a chat display field, and a dialogue input field. The subject input field is, for example, a field for inputting information that will be the subject of the user's post. The subject of the post may be, for example, one or more. The chat display field is, for example, a field for displaying the user's post and the proxy existence model's response. The dialogue input field is, for example, a field for inputting dialogue posts with the proxy existence model in the user's post.

[0026] The dialogue interface generation unit 11 may, for example, have a proxy existence model selection function as the dialogue interface. In this case, the dialogue interface generation unit 11 can, for example, display a list of proxy existences that the user can interact with, and generate a dialogue interface that includes a dialogue screen between the proxy existence selected from the list and the corresponding proxy existence model.

[0027] The post acquisition unit 12 acquires user posts entered into the dialogue interface (S2, post acquisition step). The posts are not particularly limited and may be, for example, text information, audio information, image information, or a combination thereof. If the posts are information other than text information, the post information acquisition unit 12 may, for example, convert the posts into text information. The post acquisition unit 12 may, for example, monitor user input to the dialogue interface and acquire the input as user posts. Also, if the dialogue screen includes a subject input field and a dialogue input field, the post acquisition unit 12 may, for example, acquire at least one of the subject entered in the subject input field and the dialogue post entered in the dialogue input field as user posts. The post acquisition unit 12 may, for example, record the acquired user posts in the storage unit of the device 10.

[0028] The response unit 13 causes a proxy existence model, which mimics a predetermined target person, to generate a response based on the post, and outputs the response to the dialogue interface (S3, response step). Specifically, the response unit 13 generates instruction information for generating a dialogue themed on the subject. This instruction information is also called a prompt for generating a response to the proxy existence model. The response unit 13 can generate this instruction information by, for example, inputting the subject acquired in S2 into a pre-recorded instruction information template. An example of such an instruction information template is the following text. The response unit 13 can generate this instruction information by, for example, inputting the subject 112A into the "objective" field and the action 112B into the "action for the objective" field in the following template. "The subject of our dialogue is '[objective]' and the '[means]' to achieve that objective. We would like to focus on questions and topics related to this subject and discuss what means are most effective in achieving the objective, as well as specific action plans and strategies. Please be careful not to stray from the subject. If you need any relevant information or advice, please support us to that extent."

[0029] The response unit 13 can, for example, input the instruction information and the dialogue post to the proxy existence model and cause the proxy existence model to generate a response based on the instruction information and the dialogue post. The response unit 13 may, for example, cause the proxy existence model to generate a question regarding the post as the response.

[0030] The post acquisition unit 12 may separately acquire the subject entered in the subject input field and the dialogue post entered in the dialogue input field, and before inputting them into the proxy existence model, convert the subject and dialogue post into a predetermined format of token sequence or vector sequence. Specifically, the post acquisition unit 12 converts the subject into a token sequence as metadata representing the purpose and preconditions of the entire dialogue, and converts the dialogue post into a token sequence representing the user's specific question or situation. The response unit 13 then assigns a high weight to the subject token sequence as metadata and a relatively low weight to the token sequence of the dialogue post, and inputs this into the proxy existence model, thereby enabling the proxy existence model to generate a response while maintaining the constraints based on the subject.

[0031] The surrogate existence model is a machine learning model that has learned the personality information of the subject. The method for manufacturing the surrogate existence model will be described later in Embodiment 4. Because the surrogate existence model has learned the personality information of the subject, it can, for example, generate and output responses as the subject. For example, if the subject is an expert in philosophical dialogue, the surrogate existence model can behave as an expert in philosophical dialogue and generate and output philosophical dialogue questions regarding the subject of the user's post. Examples of such philosophical dialogue questions include questions asking for specific examples, questions asking for counter-examples, questions asking for differences from similar events, questions asking for hypotheses such as "what if...", and questions asking for scope.

[0032] The post acquisition unit 12 may, for example, determine whether an additional post has been input from the user (S2A). If an additional post has been input (S2A, Yes), the post acquisition unit 12 acquires the additional post, and the response unit 13 may cause the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response.

[0033] According to this disclosure, the dialogue interface generation unit generates a dialogue interface for a user to interact with a proxy existence model, the post acquisition unit acquires user posts entered into the dialogue interface, and the response unit causes a proxy existence model, which mimics a predetermined target person, to generate a response based on the post and outputs the response to the dialogue interface. Therefore, according to this disclosure, a user can interact with a proxy existence model that mimics a predetermined target person. Unlike ordinary large-scale language models, the proxy existence model learns the personality information of the target person, and is therefore able to act as a proxy for the target person. Thus, according to this disclosure, by using a proxy existence model that acts as a proxy for personnel in a personal field, it is possible to address the shortage of personnel in a personal field.

[0034] The following describes an example of how to use the device 10, with specific examples. In the following description, the proxy existence model is a trained model that has learned the personality information of a specific mentor. The device 10 functions as a web application, and the user accesses the device 10 via a web browser application on their terminal (e.g., a smartphone). The description will use the device 10's services, which involve dialogue with a mentor AI, to discuss the prospects of their business, as an example. However, this disclosure is not limited to the following description.

[0035] First, the user accesses the device 10 using their smartphone. The dialogue interface generation unit 11 of the device 10 generates a dialogue screen 111 as a dialogue interface, as shown in Figure 4, and displays it on the user's smartphone. Note that the dialogue screen in this disclosure is not limited to the screen shown in Figure 4. The dialogue screen 111 shown in Figure 4 includes, for example, a subject input field 112, a chat display field 113, and a dialogue input field 114. The subject input field 112 is a field in which the user inputs information that will be the subject of their post. The subject of the post may be, for example, one or more. In the example shown in Figure 4, the subject input field 112 includes a target input field 112A and an action input field 112B.

[0036] The user enters Goal 112A ("I want to increase the number of student entrepreneurs.") and Action 112B ("I will hold a seminar to teach entrepreneurship know-how to students.") in the Subject Input Field 112, and enters "I have entered what I would like to discuss." as a dialogue post in the Dialogue Input Field 114. The Post Acquisition Unit 12 of this device 10 acquires Goal 112A and Action 112B as the subject of the user's post, and acquires "I have entered what I would like to discuss." entered in the Dialogue Input Field 114 as the user's dialogue post.

[0037] The response unit 13 generates a prompt based on the subject of the user's post ("The subject of our conversation is '[Goal]: We want to increase the number of student entrepreneurs,' and the '[Means]' to achieve that goal is 'We will hold seminars to teach entrepreneurial know-how to students.' We would like to focus on questions and topics related to this subject and discuss what means are most effective in achieving the goal, as well as specific action plans and strategies. Please be careful not to stray from the subject. If you need any relevant information or advice, please support us to the extent that.") and inputs it into the surrogate existence model along with the conversation post. At this time, the response unit 13 may also input instruction information (prompts) to the surrogate existence model, for example, instructing it to generate a response by weighting the conversation post based on personality information. Specific examples of prompts include, but are not limited to, "When generating text, follow the following rules: Weight the content of the post based on personality information and generate a response according to the weights." The response unit 13 then retrieves the response generated by the surrogate existence model and outputs (displays) it on the conversation screen 111. Figure 5 shows a specific example of a response from the proxy existence model output (displayed) on the dialogue screen 111 by the response unit 13. The response unit 13 can, for example, display the response 113B from the proxy existence model in the chat display field 113 of the dialogue screen 111.

[0038] The response unit 13 may, for example, control context management during the generation process in the surrogate existence model by providing the surrogate existence model with instruction information based on the subject. For example, the response unit 13 can assign a weight to each post in the dialogue history in association with the subject, and based on the weight, limit the range of past posts referenced by the surrogate existence model to posts related to the subject. By controlling the reference context through subject-based weighting in this way, deviations from the subject in the surrogate existence model's responses can be suppressed, reducing the processing of unnecessary tokens and lowering the consumption of computational resources compared to inputting the entire dialogue history as is. Furthermore, the generation of hallucinational responses based on information unrelated to the subject of the dialogue can be suppressed, improving the consistency and reliability of the generated responses.

[0039] Furthermore, the response unit 13 can, for example, distinguish and weight each description in the user's post based on the personality information learned by the proxy existence model, distinguishing between descriptions that the target person would consider important and descriptions that the target person would consider disregarding. This allows the proxy existence model to prioritize outputting judgments and questions that are characteristic of the target person, without excessively emphasizing parts of the information included in the user's post that are inconsistent with the target person's personality. In other words, the responses generated through the dialogue interface of this embodiment, when combined with the personality model / explicit knowledge model configuration described later in Embodiment 4, can suppress personal hallucination—saying things that the target person would not say—while presenting information necessary for decision-making support with high consistency.

[0040] As mentioned above, the surrogate presence model in this example is a machine learning model that has learned the personality information of the mentor as the target. Therefore, users of this device 10 can deepen their introspection about the content of their posts, just as they would if they were asked questions during a face-to-face meeting with a mentor.

[0041] [Embodiment 2] Embodiment 2 is another example of a decision support device.

[0042] The decision support device of this embodiment is the same as the decision support device 10 of Embodiment 1, except that it includes a dialogue history management unit 14 in addition to the configuration of the decision support device 10 of Embodiment 1, and the description thereof can be applied accordingly.

[0043] Figure 6 is a block diagram showing an example configuration of the decision support device 10A of this embodiment. As shown in Figure 6, the decision support device 10A includes a dialogue history management unit 14 in addition to the configuration of the decision support device 10 of Embodiment 1. The hardware configuration of the decision support device 10A is the same as that of the decision support device 10 in Figure 2, except that the central processing unit 101 has the configuration of the decision support device 10A in Figure 6 instead of the configuration of the decision support device 10 in Figure 1.

[0044] Hereinafter, the processing of the dialogue history management unit 14 will be described using FIG. 7. The processing of the dialogue history management unit 14 can be appropriately inserted at an arbitrary position in the flowchart of FIG. 3 described in the first embodiment, for example.

[0045] First, in the same manner as S1 to S3 in the first embodiment, S1 to S3 are implemented.

[0046] The dialogue history management unit 14 records, for example, the dialogue history between the user and the proxy presence model (S4, dialogue history management step). The dialogue history is a record of the user's posts and the responses of the proxy presence model, and is also referred to as a chat log. The dialogue history may be, for example, a record of all posts and responses during the dialogue, or a partial record. The dialogue history management unit 14 may record the dialogue history in the storage unit of the apparatus 10A, or may record the dialogue history in a recording medium external to the apparatus 10A. The dialogue history management unit 14 may be able to output the dialogue history, for example. The output destination of the dialogue history is not particularly limited, and may be the dialogue interface or a device external to the apparatus 10. The dialogue history management unit 14 may generate, for example, a summary of the dialogue history for each user and be able to output the summary.

[0047] In addition, the dialogue history management unit 14 may not only record the dialogue history for each user, but also generate a summary of the dialogue history prior to input to the proxy presence model and input the summary as the context of the proxy presence model. In this case, since the proxy presence model can generate a response based on the summarized dialogue history without directly processing the entire long dialogue history, it is possible to prevent an increase in the calculation cost while suppressing information loss even in a large language model with a context length constraint.

[0048] [Embodiment 3] The decision-making support program of this embodiment is a program for causing a computer to execute each step of the decision-making support method described above. Specifically, the decision-making support program of this embodiment is a program for causing a computer to execute a dialogue interface generation procedure, a post acquisition procedure, and a response procedure.

[0049] The dialogue interface generation procedure generates a dialogue interface for a proxy existence model and a user to interact; the post acquisition procedure acquires a user post entered into the dialogue interface; the response procedure causes a proxy existence model, which mimics a predetermined target person, to generate a response based on the post; and outputs the response to the dialogue interface. The proxy existence model is a machine learning model that has learned the personality information of the target person.

[0050] Furthermore, the decision support program of this embodiment can also be described as a program that causes a computer to function as a dialogue interface generation procedure, a submission retrieval procedure, and a response procedure.

[0051] The decision support program of this embodiment can be adapted from the descriptions in the decision support apparatus and decision support method of the present disclosure. Each of the aforementioned steps can be read as, for example, a "step" instead of a "process". The program of this embodiment may also be recorded on, for example, a computer-readable recording medium. The recording medium is not particularly limited and includes, for example, random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (e.g., SSD (Solid State Drive), USB flash memory, SD / SDHC card, etc.), optical disc (e.g., CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy disk (FD), etc. The decision support program of this embodiment (also referred to as, for example, a programming product or a decision support program product) may also be delivered, for example, from an external computer. The aforementioned "distribution" may be, for example, distribution via a communication network, or distribution via a wired connected device. The decision support program of this embodiment may be installed and executed on the distributed device, or it may be executed without being installed.

[0052] [Embodiment 4] The proxy existence model manufacturing apparatus of this embodiment will be described with reference to Figure 8. Figure 8 is a block diagram showing the configuration of an example of the proxy existence model manufacturing apparatus 20 of this embodiment. As shown in Figure 8, the proxy existence model manufacturing apparatus 20 (hereinafter also referred to as "this apparatus 20") includes a knowledge information acquisition unit 21, a construction information extraction unit 22, and a model construction unit 23. In addition, although not shown, this apparatus 20 may also include, for example, an input unit, an output unit, a display unit and / or a storage unit.

[0053] The device 20 may be, for example, a single device including the aforementioned parts, or it may be a device in which the aforementioned parts can be connected via a communication network. Furthermore, the device 20 can be connected to an external device described later via a communication network. The communication network is not particularly limited and a known network can be used, for example, it may be wired or wireless. Examples of communication networks include the Internet, WWW (World Wide Web), telephone lines, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), LPWA (Low Power Wide Area), L5G (Local 5G), etc. Examples of wireless communication include Wi-Fi®, Bluetooth®, Local 5G, LPWA, etc. The aforementioned wireless communication may be in the form of direct communication between devices (Ad Hoc communication), infrastructure communication, or indirect communication via an access point. The device 20 may, for example, be incorporated into a server as a system. Alternatively, the device 20 may be, for example, a personal computer (PC, e.g., desktop or notebook), smartphone, or tablet terminal on which the program disclosed herein is installed. Furthermore, the device 20 may be in the form of cloud computing or edge computing, for example, in which at least one of the aforementioned parts is on a server and the other parts are on a terminal.

[0054] Figure 9 illustrates a block diagram of the hardware configuration of the device 20. The device 20 includes, for example, a central processing unit 201, memory 202, bus 203, storage device 204, input device 205, output device 206, communication device (communication unit) 207, etc. Each part of the device 20 is interconnected via the bus 203 through its respective interface (I / F).

[0055] The central processing unit 201 operates in coordination with other components via controllers (system controller, I / O controller, etc.) and is responsible for the overall control of the device 10. In the device 20, the central processing unit 201 executes, for example, the program of this disclosure and other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 201 functions as a knowledge information acquisition unit 21, a construction information extraction unit 22, and a model construction unit 23. The device 20 may also include other computing devices such as a CPU, GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), or a combination thereof as computing devices.

[0056] Bus 203 can also be connected to external devices, for example. Examples of such external devices include external storage devices (external databases, etc.), electrocardiographs, printers, external input devices, external display devices, audio output devices such as speakers, external imaging devices such as cameras, and various sensors such as acceleration sensors, geomagnetic sensors, and direction sensors. The device 20 can be connected to an external network (the aforementioned communication network) by a communication device 207 connected to bus 203, for example, and can also be connected to other devices via the external network.

[0057] Memory 202 may be, for example, main memory. When the central processing unit 201 performs processing, memory 202 reads various operational programs, such as the program of this disclosure, stored in the storage device 204 (described later), and the central processing unit 201 receives data from memory 202 and executes the program. The main memory may be, for example, RAM (random access memory). Alternatively, memory 202 may be, for example, ROM (read-only memory).

[0058] The storage device 204 is also called an auxiliary storage device, for example, in relation to the main memory (primary memory). As described above, the storage device 204 stores an operating program including the program of this disclosure. The storage device 204 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited and may be internal or external, for example, an HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc. The storage device 104 may be, for example, a hard disk drive (HDD) in which the recording medium and the drive are integrated, or a solid state drive (SSD). If the device 20 includes, for example, the storage device 204 functions as the storage unit.

[0059] In this device 20, the memory 202 and storage device 204 can also store various types of information, such as log information, information obtained from an external database (not shown) or external devices, information generated by this device 20, and information used by this device 20 when executing processing. At least some of the information may be stored, for example, on an external server other than the memory 202 and storage device 204, or distributed and stored across multiple terminals using blockchain technology or the like.

[0060] The device 20 further includes, for example, an input device 205 and an output device 206. The input device 205 may include, for example, a pointing device such as a touch panel, trackpad, or mouse; a keyboard; imaging means such as a camera or scanner; a card reader such as an IC card reader or magnetic card reader; an audio input means such as a microphone; and so on. The output device 206 may include, for example, a display device such as an LED display or liquid crystal display; an audio output device such as a speaker; a printer; and so on. In this embodiment 3, the input device 205 and the output device 206 are configured separately, but the input device 205 and the output device 206 may be configured as an integrated unit, such as a touch panel display.

[0061] Next, an example of the proxy existence model manufacturing method of this embodiment will be described based on the flowchart in Figure 10. The proxy existence model manufacturing method of this embodiment can be carried out as follows, for example, using the proxy existence model manufacturing apparatus 20 shown in Figures 8 and 9. Note that the proxy existence model manufacturing method of this embodiment is not limited to the use of the proxy existence model manufacturing apparatus 20 shown in Figures 8 and 9.

[0062] First, the knowledge information acquisition unit 21 acquires the subject's knowledge information (S21, knowledge information acquisition step). The format of the knowledge information is not particularly limited; for example, it may be text information, image information, audio information, or a combination thereof. The knowledge information is, for example, information linked to predetermined information and subject identification information that identifies the creator of the information (the subject). The predetermined information is, for example, information that includes the subject's personality information and explicit knowledge information. The personality information is, for example, information that represents the subject's thoughts from the knowledge information. The personality information is also called, for example, a partial stance. The explicit knowledge information is, for example, the part of the knowledge information excluding the personality information, and includes objective knowledge. If the knowledge information is a book, paper, etc., the explicit knowledge information may, for example, be information such as technical terms and experimental results, but is not limited to these. The subject identification information may, for example, be a name, address, telephone number, email address, identification number (for example, My Number (individual number), etc.). Specific examples of the aforementioned knowledge information include, but are not limited to, books and papers written by the subject, video data of lectures given by the subject, audio data of lectures given by the subject, and image data created by the subject. The knowledge information acquisition unit 21 may, for example, acquire knowledge information recorded in the storage unit of the device 20, or it may acquire the aforementioned knowledge information from outside the device 20 via the input device 205. The knowledge information acquisition unit 21 may, for example, acquire one type of knowledge information of the subject, or it may acquire two or more types. The knowledge information acquisition unit 21 may, for example, record the acquired knowledge information in the storage unit of the device 20.

[0063] The information extraction unit 22 for construction extracts personality information of the subject from the knowledge information (S22, information extraction step for construction). The information extraction unit 22 for construction may also, for example, further extract explicit knowledge information from the knowledge information of the subject. The information extraction unit 22 for construction may, for example, use known natural language processing techniques to extract at least one of the personality information and explicit knowledge information of the subject, or use a large-scale language model to extract at least one of the personality information and explicit knowledge information of the subject. If the knowledge information is textual information such as a book or a paper, the information extraction unit 22 for construction can, for example, extract the personality information or explicit knowledge information based on the end of a sentence in a document, the chapter structure of a book, etc. The information extraction unit 22 for construction may, for example, record at least one of the extracted personality information and explicit knowledge information in the storage unit of the device 20. In this case, the information extraction unit 22 for construction can, for example, record personality information and explicit knowledge information, the knowledge information from which they were extracted, and the creator identification information of the knowledge information in a linked manner.

[0064] The information extraction unit 22 for construction can, for example, analyze the knowledge information and extract sentences whose sentence ends with a word that expresses the author's thoughts as the personality information. Examples of words that express the author's thoughts include, but are not limited to, words such as "I want to," "I think," "I believe," and "I want." The information extraction unit 22 for construction can also analyze the knowledge information and extract sentences whose sentence ends with a word that indicates explicit knowledge as the explicit knowledge information. Examples of words that indicate explicit knowledge include, but are not limited to, words such as "It is," "It was," and "As a result."

[0065] The information extraction unit 22 for construction may, for example, analyze the knowledge information and extract sentences contained in chapters that describe the author's ideas as personality information. Examples of chapters that describe the author's ideas include the "preface," "introduction," and "afterword."

[0066] The information acquisition unit 22 for construction may, for example, use AI to extract personality information and explicit knowledge information from knowledge information. In this disclosure, AI may refer to, for example, a large-scale learning model called a "foundation model." The foundation model is a machine learning model pre-trained on predetermined big data and is not limited to a large-scale language model (LLM) that has learned natural language, but may also include a large-scale model for speech, a large-scale model for images, and a multimodal model (such as a visual language model) that handles language, images, speech, and video across the board. Furthermore, a configuration may be adopted in which a small-scale language model (SLM) is placed on the terminal side and cooperates with the large-scale model on the cloud side, a configuration that includes search extension generation (RAG) using an external knowledge source, tool execution / function call, agent-oriented control logic, etc. The providers of large-scale language models are not particularly limited. Examples include, but are not limited to, various LLM / multimodal models provided by companies such as OpenAI, Anthropique, Alphabet (Google), META, Microsoft, Cohere, Mistral, xAI, NEC Corporation, and NTT.

[0067] When the information acquisition unit 22 for construction uses AI to extract personality information and explicit knowledge information from knowledge information, the information acquisition unit 22 can cause the AI ​​to extract the user's personality information and explicit knowledge information by inputting extraction instruction information, which instructs the AI ​​to extract personality information and explicit knowledge information, along with the knowledge information. The extraction instruction information may be recorded in the storage unit of the device 10, stored externally, or input by the user each time. Specific examples of the extraction instruction information include, for example, "classifying information into the following two categories: sentences and paragraphs that show the author's thoughts and opinions, and sentences and paragraphs that show knowledge, such as scientific verification results and historical facts." This disclosure is not limited to the above examples.

[0068] Furthermore, the AI ​​may be, for example, a model finely tuned to extract personality information and explicit knowledge information from knowledge information. In this case, for example, fine tuning for extracting personality information and explicit knowledge information from knowledge information can be performed by training the AI ​​with knowledge information and a set of personality information and explicit knowledge information previously extracted from the knowledge information. In this case, the AI ​​may be, for example, a multilayer neural network model having a large number of parameters (e.g., 100,000 or more, and in some cases, several million or more). Such fine tuning processing requires the rapid and repeated execution of a huge amount of numerical calculations, making it practically impossible for a human to perform it in their head or with paper and pencil, and thus relies on automated processing by electronic computers such as processors and GPUs. During the fine tuning, in order to suppress overfitting of the training data, known regularization methods such as L2 regularization, dropout, and early stopping may be combined and applied. This makes it possible to obtain a model that can extract personality information and explicit knowledge information with high generalization performance even from unknown knowledge information, and improves the accuracy and robustness of information extraction compared to simple threshold judgment or rule-based processing.

[0069] Furthermore, the information extraction unit 22 for construction may extract the personality information of the subject by, for example, providing a large-scale language model with the subject's knowledge information and instruction information that instructs the model to extract the subject's personality information from the knowledge information based on the subject's knowledge information, thereby causing the model to extract the personality information from the knowledge information. The large-scale language model is not particularly limited and includes, but is not limited to, OpenAI®'s GPT-3®, GPT-4®, Alphabet Inc. (Google®)'s BERT, LaMDA, PaLM2, META®'s LlaMA, NEC Corporation's LLM, NTT®'s LLM, etc. The instruction information that instructs the model to extract the subject's personality information from the knowledge information based on the subject's knowledge information is not particularly limited as long as it is a document that instructs the model to divide the knowledge information into parts that contain thoughts and parts that contain knowledge. Specific examples of instruction information that instructs the extraction of personality information of the subject from the knowledge information of the subject include, but are not limited to, documents such as, "Classify the information into the following two categories: - Sentences and paragraphs that show the author's thoughts and opinions, such as the author's ideas; - Sentences and paragraphs that show knowledge, such as scientific verification results and historical facts."

[0070] The information extraction unit 22 for construction may, for example, preprocess the knowledge information and extract personality information and explicit knowledge information. Specifically, for example, the information extraction unit 22 for construction may convert the knowledge information into a vectorized embedding vector sequence for each unit text, and then classify or group the knowledge information into personality information and explicit knowledge information based on the embedding vector sequence, thereby extracting personality information and explicit knowledge information based on the knowledge information. The embedding vectors may, for example, contain hundreds to thousands of real-valued elements for each unit text. For this reason, for example, a large number of embedding vectors are generated for the entire knowledge information, and the classification or grouping process consists of a large number of numerical operations, mainly matrix operations, which is a process that is practically impossible for a human to perform in their head or with paper and pencil.

[0071] The model building unit 23 constructs a surrogate existence model that mimics the target person based on the personality information (S23, model building step). The model building unit 23 can construct the surrogate existence model by, for example, providing a large-scale learning model with the personality information and instruction information that instructs the large-scale learning model to construct a surrogate existence model that mimics the target person based on the personality information. The large-scale learning model is, for example, a machine learning model that has been trained using predetermined big data. The large-scale learning model may be, for example, a model that has been trained on big data of natural language (large-scale language model), a model that has been trained on big data of speech (large-scale speech model), or a model that has been trained on big data of images (large-scale image model). The model building unit 23 can construct the surrogate existence model by, for example, providing a large-scale language model, as the large-scale learning model, with the personality information and instruction information that instructs the large-scale learning model to construct a surrogate existence model that mimics the target person based on the personality information. The instruction information is, for example, instruction information (prompt) for generating the behavior of a person handling knowledge. Examples of the aforementioned instructional information include, but are not limited to, documents such as, "When generating text, follow the rules below: - Describe examples that reflect personal information. - Do not reflect personal information in terms of knowledge. - Structure the text such that, for example, you state a fact that is correct as knowledge, and then express an opinion on that fact as personal information."

[0072] Furthermore, the model building unit 23 may generate multiple sets of training data showing the correspondence between the subject's input information and responses based on the extracted personality information. The model building unit 23 may input the training data in mini-batch units into a large-scale learning model, calculate a loss function based on the error between the model's output for the training data and the response, and train a personality model capable of outputting behavior that mimics the subject by iteratively updating a large number of model parameters using gradient descent or a modified algorithm thereof.

[0073] Furthermore, the model building unit 23 may, for example, construct an explicit knowledge model by further training a large-scale language model with the explicit knowledge information. The model building unit 23 can construct the explicit knowledge model by, for example, providing the explicit knowledge information to the large-scale language model and fine-tuning it. The explicit knowledge model is also called, for example, a large-scale language model with domain knowledge.

[0074] The aforementioned surrogate existence model is, for example, a model that has learned the personality information of the subject from the information that constitutes the knowledge information. Therefore, the surrogate existence model has learned, for example, the subject's way of thinking and understanding when handling knowledge, values ​​such as thoughts and beliefs, and how they interact with others (personality). For this reason, the surrogate existence model manufacturing method of this disclosure makes it possible to easily manufacture a model that reflects the thoughts of the information creator. Furthermore, the surrogate existence model manufactured by the surrogate existence model manufacturing method of this disclosure is capable of outputting products that are characteristic of the subject. In other words, according to this disclosure, for example, it becomes possible to construct a model that suppresses personal hallucination. Personal hallucination refers to, for example, a hallucination (illusion) of how to handle knowledge and output policies that the creator of the knowledge information would not say. Therefore, according to the surrogate existence model of this disclosure, for example, it becomes possible to more accurately extract and output the knowledge that knowledge information (e.g., a book) explicitly or implicitly contains. The output that is characteristic of the target person is not particularly limited and may be, for example, text output, voice output, or instructions to a designated machine.

[0075] The model building unit 23 may, for example, use extracted personality information to train a personality model capable of outputting behavior that mimics the subject by iteratively updating the parameters of a large-scale learning model having many parameters based on gradient descent to reproduce the correspondence between the subject's past input information and responses. Similarly, the model building unit 23 may, for example, use extracted explicit knowledge information to train an explicit knowledge model that outputs explicit knowledge information contained in the knowledge information. In this case, the model building unit 23 can, for example, generate proxy behavior information consistent with the subject's personality and output the proxy behavior information by coordinating the trained personality model and the explicit knowledge model. By configuring the personality model and the explicit knowledge model separately in this way, and coordinating the output of explicit knowledge based on the knowledge information with the output based on the personality information, it is possible to reduce the inclusion of personal expressions not included in the knowledge information and improve the consistency and reliability of the generated responses, compared to, for example, simply providing prompts to a general-purpose large-scale language model.

[0076] According to this disclosure, it is possible to create models that reflect the thoughts of the information creators. Therefore, according to this disclosure, for example, it is possible to construct surrogate models for individuals with limited human resources (e.g., busy researchers, supervisors, managers, teachers, etc.), thereby reducing the burden on those individuals.

[0077] While the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure.

[0078] This application claims priority based on Japanese Patent Application No. 2024-229566, filed on 26 December 2024, and incorporates all of its disclosures herein.

[0079] <Note> Some or all of the above embodiments may be described as follows, but are not limited to the following. (Note 1) A decision support device comprising a dialogue interface generation unit, a post acquisition unit, and a response unit, wherein the dialogue interface generation unit generates a dialogue interface for a proxy existence model and a user to interact, the post acquisition unit acquires user posts input into the dialogue interface, the response unit causes a proxy existence model that mimics a predetermined target person to generate a response based on the post, and outputs the response to the dialogue interface, and the proxy existence model is a machine learning model that has learned the personality information of the target person. (Note 2) The decision support device according to Note 1, wherein the dialogue interface generation unit generates a dialogue interface including a dialogue screen for a proxy existence model and a user to interact, the dialogue screen includes a subject input field and a dialogue input field, the post acquisition unit acquires at least one of a subject entered in the subject input field and a dialogue post entered in the dialogue input field as a user post, the response unit generates instruction information for generating a dialogue on the subject, and causes the proxy existence model to generate a response based on the instruction information and the dialogue post, etc. (Note 3) The decision support device according to Note 2, wherein the post acquisition unit determines whether an additional post has been input from the user, and the response unit, if an additional post has been input, causes the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response. (Note 4) The decision support device according to any one of Notes 1 to 3, wherein the response unit causes the proxy existence model to generate a question relating to the post as the response. (Note 5) A decision support device according to any one of Notes 1 to 4, including a dialogue history management unit, wherein the dialogue history management unit records the dialogue history between the user and the proxy existence model. (Note 6) A decision support device according to Note 5, wherein the dialogue history management unit outputs the dialogue history. (Note 7) A decision support device according to Note 6, wherein the dialogue history management unit generates a summary of the dialogue history for each user and outputs the summary.(Note 8) A decision support method comprising a dialogue interface generation step, a post acquisition step, and a response step, wherein the dialogue interface generation step generates a dialogue interface for a proxy existence model and a user to interact, the post acquisition step acquires user posts entered into the dialogue interface, the response step causes a proxy existence model that mimics a predetermined target person to generate a response based on the post, and outputs the response to the dialogue interface, the proxy existence model is a machine learning model that has learned the personality information of the target person, and each step is performed by a computer. (Note 9) The decision support method according to Note 8, wherein the dialogue interface generation step generates a dialogue interface including a dialogue screen for a proxy existence model and a user to interact, the dialogue screen includes a subject input field and a dialogue input field, the post acquisition step acquires at least one of a subject entered in the subject input field and a dialogue post entered in the dialogue input field as a user post, the response step generates instruction information for generating a dialogue themed on the subject, and causes the proxy existence model to generate a response based on the instruction information and the dialogue post, etc. (Note 10) The decision support method according to Note 9, wherein the post acquisition step determines whether an additional post has been entered by the user, and the response step, if an additional post has been entered, causes the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response. (Note 11) The decision support method according to any one of Notes 8 to 10, wherein the response step causes the proxy existence model to generate a question relating to the post as the response. (Note 12) A decision support method according to any one of Notes 8 to 11, comprising a dialogue history management step, wherein the dialogue history management step records the dialogue history between the user and the proxy existence model. (Note 13) A decision support method according to Note 12, wherein the dialogue history management step outputs the dialogue history. (Note 14) A decision support method according to Note 13, wherein the dialogue history management step generates a summary of the dialogue history for each user and outputs the summary.(Note 15) A decision support program for causing a computer to execute each of the following steps: a dialogue interface generation procedure, a post acquisition procedure, and a response procedure, wherein the dialogue interface generation procedure generates a dialogue interface for a proxy existence model to interact with a user, the post acquisition procedure acquires a user post entered into the dialogue interface, the response procedure causes a proxy existence model that mimics a predetermined target person to generate a response based on the post, and outputs the response to the dialogue interface, and the proxy existence model is a machine learning model that has learned the personality information of the target person. (Note 16) The decision support program according to Note 15, wherein the dialogue interface generation procedure generates a dialogue interface including a dialogue screen for a proxy existence model and a user to interact, the dialogue screen includes a subject input field and a dialogue input field, the post acquisition procedure acquires at least one of a subject entered in the subject input field and a dialogue post entered in the dialogue input field as a user post, the response procedure generates instruction information for generating a dialogue on the subject, and causes the proxy existence model to generate a response based on the instruction information and the dialogue post, etc. (Note 17) The decision support program according to Note 16, wherein the post acquisition procedure determines whether an additional post has been entered by the user, and the response procedure, if an additional post has been entered, causes the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response. (Note 18) The decision support program according to any one of Notes 15 to 17, wherein the response procedure causes the proxy existence model to generate a question relating to the post as the response. (Note 19) A decision support program according to any one of Notes 15 to 18, which includes a dialogue history management procedure, wherein the dialogue history management procedure records the dialogue history between the user and the proxy existence model. (Note 20) A decision support program according to Note 12, wherein the dialogue history management procedure outputs the dialogue history. (Note 21) A decision support program according to Note 20, wherein the dialogue history management procedure generates a summary of the dialogue history for each user and outputs the summary.(Note 22) A computer-readable recording medium that records a decision support program for causing a computer to execute each of the following procedures: a dialogue interface generation procedure, a post acquisition procedure, and a response procedure, wherein the dialogue interface generation procedure generates a dialogue interface for a proxy existence model to interact with a user; the post acquisition procedure acquires a user post entered into the dialogue interface; the response procedure causes a proxy existence model that mimics a predetermined target person to generate a response based on the post; and outputs the response to the dialogue interface, wherein the proxy existence model is a machine learning model that has learned the personality information of the target person. (Note 23) The recording medium according to Note 22, wherein the dialogue interface generation procedure generates a dialogue interface including a dialogue screen for a proxy existence model and a user to interact, the dialogue screen includes a subject input field and a dialogue input field, the post acquisition procedure acquires at least one of a subject entered in the subject input field and a dialogue post entered in the dialogue input field as a user post, the response procedure generates instruction information for generating a dialogue themed on the subject, and causes the proxy existence model to generate a response based on the instruction information and the dialogue post, etc. (Note 24) The recording medium according to Note 23, wherein the post acquisition procedure determines whether an additional post has been entered by the user, and the response procedure, if an additional post has been entered, causes the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response. (Note 25) The recording medium according to any one of Notes 22 to 24, wherein the response procedure causes the proxy existence model to generate a question relating to the post as the response. (Note 26) A recording medium according to any one of Notes 22 to 25, which includes a dialogue history management procedure, wherein the dialogue history management procedure records the dialogue history between the user and the proxy existence model. (Note 27) A recording medium according to Note 26, wherein the dialogue history management procedure outputs the dialogue history. (Note 28) A recording medium according to Note 27, wherein the dialogue history management procedure generates a summary of the dialogue history for each user and outputs the summary.

[0080] According to this disclosure, users can interact with a surrogate existence model that mimics a designated person. Unlike typical large-scale language models, the surrogate existence model learns the personality information of the individual person, enabling it to act as a surrogate for that person. As a result, according to this disclosure, by utilizing a surrogate existence model that acts as a proxy for personnel in personal work environments, it is possible to address the shortage of personnel in those personal work environments. Therefore, this disclosure is useful, for example, in a wide range of industries where personal work environments exist.

[0081] 10 Decision support device 11 Dialogue interface generation unit 12 Post acquisition unit 13 Response unit 14 Dialogue history management unit 101 Central processing unit 102 Memory 103 Bus 104 Storage device 105 Input device 106 Output device 107 Communication device 20 Proxy existence model manufacturing device 21 Knowledge information acquisition unit 22 Information extraction unit for construction 23 Model construction unit 201 Central processing unit 202 Memory 203 Bus 204 Storage device 205 Input device 206 Output device 207 Communication device

Claims

1. A decision support device comprising a dialogue interface generation unit, a post acquisition unit, and a response unit, wherein the dialogue interface generation unit generates a dialogue interface for a user to interact with a proxy existence model, the post acquisition unit acquires user posts input into the dialogue interface, the response unit causes a proxy existence model that mimics a predetermined target person to generate a response based on the post, and outputs the response to the dialogue interface, and the proxy existence model is a machine learning model that has learned the personality information of the target person.

2. The decision support device according to claim 1, wherein the dialogue interface generation unit generates a dialogue interface including a dialogue screen for a proxy existence model and a user to interact, the dialogue screen includes a subject input field and a dialogue input field, the post acquisition unit acquires at least one of a subject entered in the subject input field and a dialogue post entered in the dialogue input field as a user post, the response unit generates instruction information for generating a dialogue on the subject, and causes the proxy existence model to generate a response based on the instruction information and the dialogue post, etc.

3. The decision support device according to claim 2, wherein the post acquisition unit determines whether an additional post has been input from the user, and the response unit, if an additional post has been input, causes the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response.

4. The decision support device according to any one of claims 1 to 3, wherein the response unit causes the proxy existence model to generate a question regarding the post as a response.

5. The decision support device according to any one of claims 1 to 4, comprising a dialogue history management unit, wherein the dialogue history management unit records the dialogue history between the user and the proxy existence model.

6. The decision support device according to claim 5, wherein the dialogue history management unit outputs the dialogue history.

7. The decision support device according to claim 6, wherein the dialogue history management unit generates a summary of the dialogue history for each user and outputs the summary.

8. A decision support method comprising a dialogue interface generation step, a post acquisition step, and a response step, wherein the dialogue interface generation step generates a dialogue interface for a user to interact with a proxy existence model; the post acquisition step acquires user posts entered into the dialogue interface; the response step causes a proxy existence model that mimics a predetermined target person to generate a response based on the post; and outputs the response to the dialogue interface; the proxy existence model is a machine learning model that has learned the personality information of the target person, and each step is performed by a computer.

9. The decision support method according to claim 8, wherein the dialogue interface generation step generates a dialogue interface including a dialogue screen for a proxy existence model and a user to interact, the dialogue screen includes a subject input field and a dialogue input field, the post acquisition step acquires at least one of a subject entered in the subject input field and a dialogue post entered in the dialogue input field as a user post, the response step generates instruction information for generating a dialogue on the subject, and causes the proxy existence model to generate a response based on the instruction information and the dialogue post, etc.

10. The decision support method according to claim 9, wherein the post acquisition step determines whether an additional post has been input from the user, and the response step, if an additional post has been input, causes the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response.

11. The decision support method according to any one of claims 8 to 10, wherein the response step causes the proxy existence model to generate a question regarding the post as the response.

12. A decision support method according to any one of claims 8 to 11, comprising a dialogue history management step, wherein the dialogue history management step records the dialogue history between the user and the proxy existence model.

13. The decision support method according to claim 12, wherein the dialogue history management step outputs the dialogue history.

14. The decision support method according to claim 13, wherein the dialogue history management step generates a summary of the dialogue history for each user and outputs the summary.

15. A decision support program for causing a computer to execute each of the following steps: a dialogue interface generation step, a post retrieval step, and a response step, wherein the dialogue interface generation step generates a dialogue interface for a user to interact with a proxy existence model; the post retrieval step retrieves a user post entered into the dialogue interface; the response step causes a proxy existence model, which mimics a predetermined target, to generate a response based on the post; and outputs the response to the dialogue interface, wherein the proxy existence model is a machine learning model that has learned the personality information of the target.

16. The decision support program according to claim 15, wherein the dialogue interface generation procedure generates a dialogue interface including a dialogue screen for a proxy existence model and a user to interact, the dialogue screen includes a subject input field and a dialogue input field, the post acquisition procedure acquires at least one of a subject entered in the subject input field and a dialogue post entered in the dialogue input field as a user post, the response procedure generates instruction information for generating a dialogue on the subject, and causes the proxy existence model to generate a response based on the instruction information and the dialogue post, etc.

17. The decision support program according to claim 16, wherein the post acquisition procedure determines whether an additional post has been input from the user, and the response procedure, if an additional post has been input, causes the proxy existence model to generate a response relating to at least one selected from the group consisting of the post, the additional post, and the response.

18. The decision support program according to any one of claims 15 to 17, wherein the response procedure causes the proxy existence model to generate a question relating to the post as the response.

19. A decision support program according to any one of claims 15 to 18, comprising a dialogue history management procedure, wherein the dialogue history management procedure records a dialogue history between the user and the surrogate existence model.

20. A computer-readable recording medium that records a decision support program for causing a computer to execute each of the following steps: a dialogue interface generation procedure, a post retrieval procedure, and a response procedure, wherein the dialogue interface generation procedure generates a dialogue interface for a user to interact with a proxy existence model; the post retrieval procedure retrieves a user post entered into the dialogue interface; the response procedure causes a proxy existence model, which is modeled after a predetermined target, to generate a response based on the post; and outputs the response to the dialogue interface, wherein the proxy existence model is a machine learning model that has learned the personality information of the target.

Images