Persona model system, persona model processing method, and persona model program

Abstract

To allow those who wish to ask questions to easily obtain answers to questions directed at real people. [Solution] The persona model system 1 comprises one or more persona models 107 that have been trained using machine learning to capture the thinking characteristics of at least one subject U, and an answer generation unit 105 that inputs input data including questions into the persona model 107 and outputs output data including answers that reflect the thinking characteristics of the subject U. The persona model 107 is generated on the condition that the subject U is authenticated as a real person.

Description

Technical Field

[0001] Embodiments of the present invention relate to a persona model system, a persona model processing method, and a program for a persona model.

Background Art

[0002] Conventionally, for the purpose of improving conversation skills and assisting in conversations with users, there is a known technique of setting an imaginary person called a persona and conducting conversations according to the attributes of the conversation partner using a large language model. Also, in health consultations and the like, there is a known technique that enables a learned model to present health information and the like to a target person instead of a predetermined counselor giving advice to the target person.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] Even if a persona capable of conversation using a large language model or the like is constructed, since it is not a conversation with a real person, a real answer cannot be obtained. In particular, when seeking opinions from a real target person, it is necessary to directly ask the target person, which takes a lot of time and human costs and becomes a burden on the person who wants to ask the question. Also, when the number of questions is large, there is a problem that it also becomes a burden on the target person.

[0005] As an example of the problems to be solved by the present invention, it is to enable a person who wants to ask a question to easily obtain an answer to the question for a real target person.

Means for Solving the Problems

[0006] The invention according to this embodiment is, One or more persona models that have been trained using machine learning to capture the thinking characteristics of at least one subject, The persona model is provided with an answer generation unit that takes input data including questions and outputs output data including answers that reflect the characteristics of the target person's thinking, The identity verification department, Equipped with, The aforementioned identity verification unit intervenes between the identity verification medium issued by a public institution and the public personal authentication service in order to verify that the subject is a real individual, and either performs identity verification of the subject by the public personal authentication service or by performing identity verification of the subject by the subject's card substitute electronic record. The aforementioned persona model is The aforementioned identity verification unit, This is generated on the condition that the aforementioned subject is verified to be a real individual. 、 Identification information that allows for the individual identification of the aforementioned persona model is registered in association with the identification information that allows for the individual identification of the aforementioned person, along with the identity verification information of the aforementioned person. If a persona model already exists that has been trained using machine learning to capture the thinking characteristics of the person whose identity has been verified, then the training data for training the thinking characteristics of that person will be acquired, and the existing persona model will be updated. It is a persona model system.

[0007] The invention according to this embodiment is, One or more computers that implement the persona model system, A process in which input data, including questions, is input to one or more persona models that have been trained using machine learning to capture the thinking characteristics of at least one subject, and output data, including answers that reflect the thinking characteristics of the subject, is output. and, Identity verification process, Execute , a persona model processing method, The aforementioned identity verification process includes, in order to verify that the subject is a real individual, intervening between the subject's verifiable medium issued by a public institution and a public personal authentication service, and having the public personal authentication service verify the subject's identity, or verifying the subject's identity using the subject's card substitute electronic record, The aforementioned persona model is Through the aforementioned identity verification process, This is generated on the condition that the aforementioned subject is verified to be a real individual. 、 Identification information that allows for the individual identification of the aforementioned persona model is registered in association with the identification information that allows for the individual identification of the aforementioned person, along with the identity verification information of the aforementioned person. , If a persona model already exists that has been trained using machine learning to capture the thinking characteristics of the person whose identity has been verified, then the training data for training the thinking characteristics of that person will be acquired, and the existing persona model will be updated. This is a persona model processing method.

[0008] The invention according to this embodiment is, One or more computers to implement the persona model system, A process of inputting input data including a question into one or more persona models that have learned the characteristics of the thinking of at least one subject, and outputting output data including an answer reflecting the characteristics of the thinking of the subject and, Identity verification process, to execute , a program for persona models, The aforementioned identity verification process includes, in order to verify that the subject is a real individual, intervening between the subject's verifiable medium issued by a public institution and a public personal authentication service, and having the public personal authentication service verify the subject's identity, or verifying the subject's identity using the subject's card substitute electronic record, The persona model is Through the aforementioned identity verification process, generated on the condition that it is authenticated that the subject is an existing individual 、 Identification information that allows for the individual identification of the aforementioned persona model is registered in association with the identification information that allows for the individual identification of the aforementioned person, along with the identity verification information of the aforementioned person. If a persona model already exists that has been trained using machine learning to capture the thinking characteristics of the person whose identity has been verified, then the training data for training the thinking characteristics of that person will be acquired, and the existing persona model will be updated. and is a program for the persona model

Brief Description of Drawings

[0009] [Figure 1] It is a system configuration diagram showing the overall image of the persona model system [Figure 2] It is an explanatory diagram showing the mode of questionnaire or interview [Figure 3] It is a block diagram showing the persona model system [Figure 4] It is a block diagram showing the hardware configuration of a computer [Figure 5] It is an explanatory diagram showing the content registered in the information management database [Figure 6] It is a flowchart showing the persona model generation process [Figure 7] It is a flowchart showing the answer generation process

Modes for Carrying Out the Invention

[0010] The present invention will be described below through embodiments of the invention, but the invention claimed is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential as means of solving the problem. For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary.

[0011] (Persona Model System 1) The configuration overview of Persona Model System 1 will be explained with reference to Figure 1. Persona model processing is performed using Persona Model System 1. Furthermore, the persona model processing method in this embodiment is realized by having a computer execute various programs.

[0012] Figure 2 illustrates the format of a questionnaire or interview. Persona model system 1 is a system in which a predetermined learning model responds to a questionnaire or interview on behalf of a predetermined user U when a predetermined business B wants to conduct a questionnaire or interview with a large number of users U or a specific individual user U.

[0013] This embodiment illustrates a scenario involving multiple users U. Suppose business operator B wishes to conduct a survey of multiple users U, or to interview a specific user U. However, conducting a survey or interview with actual users U would be time-consuming and burdensome for both business operator B and user U. Therefore, this embodiment pre-trains a machine learning model to capture the thinking characteristics of user U, the target of the survey or interview. This machine learning model is then used to generate the survey responses, which are provided to business operator B.

[0014] The learning model has been pre-trained using training data related to user U. Furthermore, each time the learning model provides an answer, user U receives a predetermined reward, such as points, from service provider B.

[0015] Although this embodiment illustrates a configuration with multiple users U, it may also be a configuration with only one user U, or a configuration in which business operator B conducts an interview with that user U.

[0016] As shown in Figure 1, the persona model system 1 primarily comprises at least an information management server 10. The information management server 10 is a computer owned by a designated organization established for conducting surveys or interviews. Furthermore, the persona model system 1 includes a certificate verification server 20, a resident information management platform 50, a business terminal 30, a user terminal 40, an identity verification medium 41, and various server groups 60.

[0017] The information management server 10 is located in the cloud. The information management server 10 is connected to a predetermined network N, such as the internet, in a way that allows communication. Note that network N is not limited to the internet; it may also be a LAN (Local Area Network), WAN (Wide Area Network), mobile communication network, etc.

[0018] The certificate verification server 20, resident information management platform 50, business terminal 30, and user terminal 40, all acting as computers, are connected to the information management server 10 via network N.

[0019] The certificate verification server 20 is a computer located in the cloud. The certificate verification server 20 verifies the validity of the digital certificate stored in the identity verification medium 41. The certificate verification server 20 is provided by the information management server 10 to enable the resident information management platform 50 to perform identity verification authentication (resident verification authentication) of user U using the public personal authentication service. For example, if the digital certificate stored in the identity verification medium 41 is valid, the information management server 10 can access the resident information management platform 50.

[0020] The information management server 10 intervenes between the identity verification medium 41 owned by user U and the public personal authentication service to allow the public personal authentication service to verify the identity of user U. Alternatively, the information management server 10 may verify the identity of user U using a card-alternative electronic record.

[0021] Card-alternative electronic records are stored on designated devices such as smartphones. Card-alternative electronic records are essentially mobile documents (mdocs) that store My Number Card information on smartphones, allowing for identity verification without the need for a physical card.

[0022] The certificate verification server 20 is responsible for at least part of the function of verifying the electronic certificate obtained from the identity verification medium 41 in the public personal authentication service. Specifically, the certificate verification server 20 provides information on the revocation of the electronic certificate.

[0023] The certificate verification server 20 may, for example, be one that performs authentication for the public personal authentication service operated by the Japan Local Government Information Systems Organization (J-LIS). The public personal authentication service is a means of identity verification used when performing administrative procedures such as online applications and notifications via the internet.

[0024] The resident information management platform 50 is a computer. When the information management server 10 accesses the resident information management platform 50, it performs identity verification authentication (resident verification authentication) of user U.

[0025] The Resident Information Management Platform 50 is a platform for national or local governments to manage resident information. The Resident Information Management Platform 50 networks the four basic pieces of information from the Basic Resident Register (name, address, gender, and date of birth), which form the basis of various administrative services, as well as individual numbers, resident registration codes, and information on changes to these. This Resident Information Management Platform 50 is a platform that enables nationwide electronic identity verification. Furthermore, the Resident Information Management Platform 50 may include, for example, the functions of the Digital Agency's My Number Portal API.

[0026] The Resident Information Management Platform 50 manages various types of information, including residents' taxes, income, vaccinations, and pensions. The Resident Information Management Platform 50 accepts access from residents who have successfully authenticated using the public personal authentication service. Typically, the Resident Information Management Platform 50 plays a role in providing administrative information to residents through the My Number Portal, an administrative service operated by the government. In other words, the Resident Information Management Platform 50 may be envisioned as a national or local government resident information management infrastructure, including the My Number Portal API.

[0027] The business terminal 30 is, for example, a computer such as a personal computer owned by a designated business operator B. Business operator B uses the business terminal 30 to access the information management server 10 and conduct surveys or interviews.

[0028] The user terminal 40 is, for example, a computer such as a smartphone. The user terminal 40 may also be a tablet computer or a personal computer. User U has the user terminal 40 read their personal identification medium 41. The information management server 10 uses the resident information management platform 50 to perform identity verification authentication (resident verification authentication) for user U.

[0029] The user terminal 40 includes a media reader (not shown) that reads the identity verification medium 41. This media reader reads the electronic certificate embedded in the integrated circuit built into the identity verification medium 41. The media reader also has, for example, a short-range wireless communication function that conforms to a predetermined standard. The media reader may be located outside the user terminal 40, or it may be connected to the user terminal 40 when in use.

[0030] Furthermore, the user terminal 40 may have a function for card-alternative electronic recording that replaces the identity verification medium 41. If the user terminal 40 has a card-alternative electronic recording function, the configuration of the medium reader unit may be omitted. Also, user U does not need to possess the identity verification medium 41.

[0031] The identity verification medium 41 is, for example, a My Number Card. The identity verification medium 41 can be any medium that can verify the identity of user U, such as a driver's license, passport, or residence card. These mediums are equipped with an IC chip that stores electronic certificates, etc.

[0032] The My Number Card is an IC card that can be used as an identification document for identity verification, as well as for various services such as local government services and electronic applications using electronic certificates, such as e-Tax. The My Number Card has the My Number (individual number), which is limited by law to the types of administrative tasks for which it can be used, printed on the card face, and is equipped with an IC chip that stores electronic certificates and applications (APs) that can be widely used, including by private businesses. This IC chip stores digital signature certificates and digital user authentication certificates, among others. Digital signature certificates are used when creating and sending electronically signed electronic documents over the internet. Digital user authentication certificates are used when logging into websites for various services provided by the government and private sector. Users of the My Number Card can use these electronic certificates after being authenticated by the certification authority by entering the PIN set for each electronic certificate. The identity verification medium 41 may include at least one of the following: a My Number Card, a smartphone equipped with a prescribed electronic certificate (so-called smartphone JPKI), and a smartphone on which a card substitute electromagnetic record is recorded.

[0033] The various server clusters 60, acting as computers, are located on the cloud. These server clusters 60 include, for example, a distribution server, a mail server, a communication application server, a social networking service server, and an e-book server. The server clusters 60 store data such as user U's recorded or video data, email software history, communication application history, social networking service history, books written by user U, blog posts created by user U, and diaries written by user U.

[0034] Next, a block diagram illustrating Persona Model System 1 will be described with reference to Figure 3. Note that each component of Persona Model System 1 represents a functional block, not a hardware-level configuration. Each component is implemented through any combination of hardware and software, centering on the CPU, memory, programs loaded into memory, storage media such as a hard disk for storing those programs, and a network connection interface. Furthermore, there are various variations in the implementation method and apparatus.

[0035] In this embodiment, we illustrate a configuration in which each component of the persona model system 1 is provided on the information management server 10.

[0036] The information management server 10 includes an authentication unit 101, a feature acquisition unit 102, a model generation unit 103, a question reception unit 104, an answer generation unit 105, a reward granting unit 106, and multiple persona models 107. These are realized by programs stored in memory or an HDD (Hard Disk Drive) being executed by a CPU (Central Processing Unit).

[0037] Furthermore, each of the multiple persona models 107 includes a large-scale language model 108 and an extension generation unit 109. Multiple persona models 107 are generated corresponding to each of the multiple users U.

[0038] This embodiment illustrates a configuration in which the information management server 10 has multiple persona models 107, but it is sufficient to have at least one persona model 107.

[0039] At least one persona model 107 is a machine learning model that captures the thinking characteristics of at least one user U as the target. Persona model 107 is generated on the condition that user U is verified to be a real individual.

[0040] The large-scale language model 108 is pre-trained with general characteristics of question and answer trends. The large-scale language model 108 is a learning model that learns from large amounts of text data using deep learning, enabling it to understand and generate natural-sounding sentences like a human. The large-scale language model 108 is also called an LLM (large language model). Note that other learning models, such as small language models (SLMs), may be used instead of the large-scale language model 108.

[0041] The augmented generation unit 109 has the function of memorizing the characteristics of the responses of the target user U and incorporating them into the large-scale language model 108. In this way, the accuracy of the response results can be improved. The augmented generation unit 109 has the function of RAG (Retrieval Augmented Generation).

[0042] For example, the extended generation unit 109 searches for information related to the question from the characteristic data of the target user U. The extended generation unit 109 adds the relevant information found in the search to the large-scale language model 108. In other words, the extended generation unit 109 extends the functionality of the large-scale language model 108. In this way, the large-scale language model 108 can generate more accurate answers that are closer to the real answers of user U by combining the extended information with the learned knowledge.

[0043] Furthermore, a single large-scale language model 108 may be used in common across multiple persona models 107. Since the characteristics of the responses of multiple users U are stored in multiple extension generation units 109, a response for a specific user U can be generated by combining a specific extension generation unit 109 with a common large-scale language model 108.

[0044] Furthermore, the information management server 10 includes an information management database 110. This information management database 110 is a collection of information that is stored in memory, HDD, or cloud computing resources and organized so that it can be searched or stored.

[0045] Furthermore, the configuration of Persona Model System 1 does not necessarily have to be implemented on a single information management server 10. For example, one Persona Model System 1 may be implemented on multiple computers connected to each other via a network N.

[0046] For example, each component of the persona model system 1 may be provided on the operator terminal 30 or the user terminal 40.

[0047] The user authentication unit 101 authenticates that the target user U is a real individual when generating the persona model 107.

[0048] The persona model 107 in this embodiment is authenticated by a public personal authentication service using an identity verification medium 41 issued by a public institution or by a card-alternative electronic record. In this way, the proliferation of persona models 107 is suppressed, and results similar to those obtained when conducting surveys or interviews with real people can be obtained.

[0049] Furthermore, one persona model 107 is authenticated for each user U. In other words, one persona model 107 is generated for each user U. This allows for responses from real users U and improves the accuracy of the aggregated results.

[0050] The feature acquisition unit 102 acquires the characteristics of the thoughts of the target user U. For example, the feature acquisition unit 102 acquires information such as user U's recorded or video data, email software history, communication app history, social networking service history, books written by user U, blog posts created by user U, and diaries written by user U. This information can be obtained from various server groups 60 (Figure 1). The training data may also be input by user U.

[0051] Furthermore, this information is registered in the information management database 110 as training data. The feature acquisition unit 102 acquires the characteristics of user U's thinking based on at least one of this information. The characteristics of thinking are registered in the information management database 110 as feature data. This feature data is set in the extension generation unit 109 of the persona model 107, and becomes the data that the extension generation unit 109 uses for searching, extending, and generating.

[0052] The persona model 107 outputs output data, including the answer, based on the characteristics of user U's thinking acquired by the feature acquisition unit 102. In this way, data for obtaining the characteristics of user U's thinking can be acquired, enabling efficient machine learning.

[0053] The model generation unit 103 generates a persona model 107 based on the training data. The model generation unit 103 may also generate feature data to be set in the extension generation unit 109 of the persona model 107.

[0054] The question reception unit 104 receives questions related to the survey or interview from the business terminal 30.

[0055] The response generation unit 105 inputs input data, including questions, into the persona model 107 and causes it to output output data, including answers that reflect the thinking characteristics of the target user U. The response generation unit 105 then transmits the answers generated by the persona model 107 to the business terminal 30.

[0056] The reward distribution unit 106 distributes a reward from business operator B, who asks the question, to user U each time an answer is generated from the persona model 107. The reward is a predetermined number of points or the like. In this way, user U receives a reward each time the persona model 107 answers a question, thus providing an incentive for user U to generate the persona model 107. The reward is distributed to user U via the information management server 10.

[0057] The information management database 110 is a collection of information organized to be stored in memory, HDD, or cloud computing resources, and to be searchable or stored. The information management database 110 stores the data necessary to generate the persona model 107. It also stores the data necessary to generate answers to questions using the persona model 107.

[0058] Figure 5 shows the contents registered in the information management database 110. The User ID field registers a User ID, which is an identifier that allows each user U to be individually identified. This User ID serves as the primary key for the tables registered in the information management database 110. Each user U is assigned a User ID. Various information is registered using this User ID as the primary key.

[0059] For example, information such as personal identification information, persona ID, learning data, feature data, and points are registered in the information management database 110, associated with the user ID.

[0060] The identity verification information will include four basic pieces of information necessary for verifying the identity of user U (name, address, gender, and date of birth). Note that the identity verification information may also include other information.

[0061] The persona ID is identification information that can individually identify each persona model 107. When a single large-scale language model 108 is used in common, the persona ID may also be identification information that can individually identify the extension generation unit 109.

[0062] The "Training Data" field registers the feature data necessary for machine learning of Persona Model 107. The "Feature Data" field registers feature data that indicates the characteristics of User U's thinking. The "Points" field registers the number of points assigned to User U.

[0063] (Example hardware configuration) The information management server 10, which is a computer, may have the configuration shown in Figure 4. The information management server 10 has a bus 1010, a processor 1020, memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

[0064] Bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060 to send and receive data to and from each other. However, the method of connecting the processor 1020 and the other components to each other is not limited to bus connection.

[0065] Processor 1020 is a circuit that includes arithmetic units such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit).

[0066] Memory 1030 is a main memory device implemented using RAM (Random Access Memory), etc.

[0067] The storage device 1040 is a removable media such as an HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, or memory card, or an auxiliary storage device such as ROM (Read Only Memory), and has a recording medium. The recording medium of the storage device 1040 stores programs that realize each function of the information management server 10.

[0068] The processor 1020 reads this program into memory 1030 and executes it. This causes the processor 1020 to perform the function corresponding to this program. In other words, the program stored in memory 1030 causes the information management server 10 to perform a predetermined function.

[0069] The input / output interface 1050 connects the information management server 10 to a predetermined input / output device. The input / output device is, for example, an input device such as a keyboard, an output device such as a display, or an input / output device in which a touch panel is superimposed on a display.

[0070] The network interface 1060 is an interface for connecting the information management server 10 to a predetermined communication network. This communication network may be, for example, the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network). The method by which the network interface 1060 connects to the communication network may be wireless or wired.

[0071] The information management server 10 has been described above. In addition to the above configuration, the information management server 10 may have an information input device for user U to input various information into the information management server 10 through operation. The information input device may be, for example, a keyboard, mouse, or touch panel. The information management server 10 may also have a display, speaker, vibration motor, or LED (light-emitting diode) for showing various information to user U.

[0072] The Persona Model System 1 does not necessarily have to be configured on a single information management server 10. For example, one Persona Model System 1 may be implemented using multiple computers connected to each other via a network N.

[0073] (Persona model generation process) Next, the persona model generation process will be explained using the flowchart in Figure 6. The aforementioned diagram will be used as a reference as appropriate. The following steps represent at least some of the processes included in the persona model generation process; other steps may also be included.

[0074] First, in step S1, the user authentication unit 101 of the information management server 10 performs user authentication processing when there is access from the user terminal 40 and when the generation of the persona model 107 is executed.

[0075] In the next step S2, the user authentication unit 101 of the information management server 10 determines whether or not the persona model 107 has already been generated. If the persona model 107 has already been generated (YES in step S2), the process proceeds to step S3. On the other hand, if the persona model 107 has not already been generated (NO in step S2), the process proceeds to step S4.

[0076] In step S3, the model generation unit 103 of the information management server 10 starts updating the existing persona model 107 and proceeds to step S5.

[0077] In step S4, the model generation unit 103 of the information management server 10 starts generating a new persona model 107 and proceeds to step S5.

[0078] In step S5, the feature acquisition unit 102 of the information management server 10 acquires training data.

[0079] In the next step S6, the extended generation unit 109 of the information management server 10 executes an extended generation process. This extended generation unit 109 stores the characteristics of the responses of the target user U and makes them available for incorporation into the large-scale language model 108. For example, the extended generation unit 109 generates feature data from the training data.

[0080] In the next step S7, the model generation unit 103 of the information management server 10 stores the updated or newly generated persona model 107 associated with the user ID. Specifically, the model generation unit 103 registers the updated or newly generated information in the information management database 110. Then, the persona model generation process is completed.

[0081] (Answer generation process) Next, the response generation process will be explained using the flowchart in Figure 7. The aforementioned diagrams will be used as references as appropriate. The following steps represent at least some of the processes included in the response generation process; other steps may also be included.

[0082] First, in step S11, the question reception unit 104 of the information management server 10 determines whether business operator B wishes to ask a question about persona model 107 when accessed from business operator terminal 30. In other words, the question reception unit 104 determines that business operator B does not wish to ask a question directly to user U.

[0083] For example, the information management server 10 displays a prompt on the display of the business terminal 30, such as "Do you wish to ask questions to the individual?" or "Do you wish to ask questions to persona model 107?", to confirm the business operator B's preference.

[0084] If Company B wishes to be asked questions about Persona Model 107 (if the answer is YES in step S11), proceed to step S12. On the other hand, if Company B does not wish to be asked questions about Persona Model 107 (if the answer is NO in step S11), proceed to step S21, which will be described later.

[0085] In step S12, the question receiving unit 104 of the information management server 10 executes question receiving processing. Here, the question receiving unit 104 receives input of questions related to the questionnaire or interview from the business terminal 30.

[0086] In the next step S13, the question receiving unit 104 of the information management server 10 determines whether business operator B wishes to ask a question about a specific individual. If the question is about a specific individual (YES in step S13), the process proceeds to step S14. On the other hand, if the question is not about a specific individual (NO in step S13), the process proceeds to step S15.

[0087] In step S14, the response generation unit 105 of the information management server 10 inputs the question into the persona model 107 corresponding to a specific individual, and proceeds to step S18, which will be described later.

[0088] In step S15, the question reception unit 104 of the information management server 10 receives the range of the target person from the business terminal 30. For example, the question reception unit 104 receives input of information about the person's attributes, such as gender, age group, place of residence, and occupation.

[0089] In the next step S16, the response generation unit 105 of the information management server 10 selects a persona model 107 that corresponds to the range of target individuals.

[0090] In the next step S17, the response generation unit 105 of the information management server 10 inputs the question into the selected persona model 107 and proceeds to step S18.

[0091] In step S18, the response generation unit 105 of the information management server 10 causes the persona model 107 to generate a response. In other words, the response generation unit 105 inputs input data, including a question, into one or more persona models 107 that have been trained to capture the thinking characteristics of at least one target user U, and outputs output data that includes a response reflecting the thinking characteristics of user U.

[0092] In the next step S19, the response generation unit 105 of the information management server 10 sends the response to the business terminal 30 and outputs (displays) the response on the display of the business terminal 30.

[0093] In the next step S20, the reward distribution unit 106 of the information management server 10 awards points, which have been set in advance by business operator B, to user U, which corresponds to the persona model 107 that generated the response. Then the response generation process ends.

[0094] In step S21, which proceeds if the answer in step S11 is NO, the information management server 10 executes the real person question processing and terminates the answer generation processing.

[0095] In the processing of questions about real people, the information management server 10 configures communication between the business terminal 30 and the user terminal 40 so that questions and answers can be exchanged. Business operator B directly conducts a questionnaire or interview with user U. User U responds to the questionnaire or interview.

[0096] For example, the information management server 10 determines whether business operator B wishes to ask questions about a specific individual. If business operator B wishes to ask questions about a specific individual, the information management server 10 outputs (displays) the questions on the display of the corresponding user U's user terminal 40. If business operator B does not wish to ask questions about a specific individual, the information management server 10 accepts a range of people to be questioned. The information management server 10 also outputs (displays) the questions on the displays of the user terminals 40 corresponding to multiple users U who are the people to be questioned. When answers are entered into the user terminals 40, the information management server 10 aggregates the results of those answers and sends them to the business operator terminal 30.

[0097] In this embodiment, a persona model 107, which has been trained using machine learning to capture the characteristics of a subject's thinking, is generated on the condition that the subject is verified to be a real individual. This persona model 107 is then used in a questionnaire or interview. In this way, those who wish to ask questions can easily obtain answers to questions from real subjects.

[0098] In particular, at least one (or more) persona models 107, which are machine-learned to capture the thinking characteristics of at least two different subjects, are used. This makes it easy to conduct surveys or interviews with a large number of subjects and improves the accuracy of the responses.

[0099] In the above-described embodiment, one persona model 107 is generated for one user U, but other embodiments are also possible. For example, multiple persona models 107 may be generated for one user U. That is, multiple persona models 107 may be generated that have been trained using machine learning to capture the thinking characteristics of one user U. Alternatively, one persona model 107 may be generated for multiple users U. That is, one persona model 107 may be generated that has been trained using machine learning to capture the thinking characteristics of multiple users U.

[0100] In the above-described embodiment, multiple persona models 107 are generated to correspond to multiple users U, but other embodiments are also possible. For example, in an embodiment where only one persona model 107 is generated to correspond to only one user U, this is also possible.

[0101] In the flowchart of the embodiment described above, the steps are shown as being executed in series, but the order of the steps is not necessarily fixed, and the order of some steps may be reversed. Also, some steps may be executed in parallel with other steps. Furthermore, the steps included in the flowchart described above are at least some of the steps, and other steps may be included in the flowchart described above.

[0102] The aforementioned system may include a computer equipped with artificial intelligence (AI) for machine learning. Furthermore, the aforementioned system may include a deep learning unit that extracts specific patterns from multiple patterns based on deep learning.

[0103] The aforementioned computer-based analysis can utilize analytical techniques based on artificial intelligence learning. For example, it can use learning models generated by machine learning using neural networks, learning models generated by other machine learning methods, deep learning algorithms, and mathematical algorithms such as regression analysis. Furthermore, forms of machine learning include clustering and deep learning.

[0104] The aforementioned system includes a computer equipped with artificial intelligence that performs machine learning. For example, this system may consist of one computer equipped with a neural network, or it may consist of multiple computers equipped with neural networks.

[0105] Here, a neural network is a mathematical model that represents the characteristics of brain function through computer simulation. For example, it shows a model in which artificial neurons (nodes) that form a network through synaptic connections change the strength of their synaptic connections through learning and acquire problem-solving abilities. Furthermore, neural networks acquire problem-solving abilities through deep learning.

[0106] For example, a neural network may have multiple layers, each consisting of several units. By pre-training a multi-layer neural network with training data (supervised data), it is possible to automatically extract features from patterns of changes in the state of a circuit or system. Furthermore, the number of hidden layers, units, learning rate, number of training iterations, and activation function of a multi-layer neural network can be set arbitrarily via the user interface.

[0107] Furthermore, a reward function may be set for each information item to be learned, and deep reinforcement learning, in which the information item with the highest value is extracted based on the reward function, may be used in the neural network.

[0108] Furthermore, there are various machine learning techniques, such as autoencoders, LSTM (Long Short-Term Memory), SDF (Signed Distance Function), GAN (Generative Adversarial Network), and RNN (Recurrent Neural Network). These techniques may be applied to the machine learning in this embodiment.

[0109] A learning model includes an input layer, a hidden layer, and an output layer. The input layer receives the input data. The hidden layer's parameters are pre-trained using the training data. The output layer outputs output data that shows the results of processing in the hidden layer in response to the input data received by the input layer.

[0110] Each of the aforementioned components of the system may be implemented with dedicated hardware. Furthermore, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, or combinations thereof. These may be comprised of a single chip or multiple chips connected via a bus. Some or all of each component may be implemented by a combination of the aforementioned circuits and programs. Additionally, a CPU (Central Processing Unit), GPU (Graphics Processing Unit), etc., can be used as the processor. Moreover, at least some of the functions of this embodiment may be provided in the form of IaaS (Infrastructure as a Service), PaaS (Platform as a Service), or SaaS (Software as a Service).

[0111] The aforementioned program, when loaded into a computer, includes a set of instructions (or software code) for causing the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include computer-readable mediums or physical storage mediums such as RAM (random-access memory), ROM (read-only memory), flash memory, SSD (solid-state drive), or other memory technologies. Examples, but not limited to, include CD-ROMs, DVDs (digital versatile discs), Blu-ray discs, or other optical disc storage. Examples, but not limited to, include magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable mediums or communication mediums such as electrical, optical, acoustic, or other forms of propagating signals.

[0112] The embodiments have been described above, but the configurations of the embodiments described above may be combined with each other, or some of the configurations may be replaced with other configurations. Furthermore, the configurations of the embodiments described above may be modified in various ways without departing from the spirit of the invention.

[0113] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments rather than with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create embodiments not explicitly illustrated or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate. [Explanation of Symbols]

[0114] 1. Persona Model System 10. Information Management Server 20 Certificate Verification Servers 30. Carrier terminals 40 User terminals 41 Identity verification medium 50 Resident Information Management Platform 60 Various Server Groups 101 Identity Verification Department 102 Feature Acquisition Unit 103 Model Generation Unit 104 Question Reception Department 105 Answer generation part 106 Reward Distribution Department 107 Persona Models 108 Large-scale language models 109 Extended generation unit 110 Information Management Database 1010 Bus 1020 Processor 1030 memory 1040 Storage Devices 1050 Input / Output Interface 1060 Network Interfaces B Business N Network U User

Claims

1. One or more persona models that have been trained using machine learning to capture the thinking characteristics of at least one subject, The persona model is provided with an answer generation unit that takes input data including questions and outputs output data including answers that reflect the characteristics of the target person's thinking, The identity verification department, Equipped with, The aforementioned identity verification unit intervenes between the identity verification medium issued by a public institution and the public personal authentication service in order to verify that the subject is a real individual, and either performs identity verification of the subject by the public personal authentication service or by performing identity verification of the subject by the subject's card substitute electronic record. The aforementioned persona model is generated on the condition that the subject is authenticated by the identity authentication unit as a real individual. Identification information that allows for the individual identification of the aforementioned persona model is registered in association with the identification information that allows for the individual identification of the aforementioned person, along with the identity verification information of the aforementioned person. A persona model system that, when an existing persona model exists that has been trained using machine learning to capture the characteristics of the thinking of the person whose identity has been authenticated, acquires training data to train the person's thinking characteristics and updates the existing persona model.

2. In the persona model system described in claim 1, The aforementioned identity verification information of the subject includes the subject's name, address, gender, and date of birth, as part of a persona model system.

3. In the persona model system according to claim 1 or claim 2, A persona model system in which one persona model is authenticated for one of the aforementioned target individuals.

4. In the persona model system according to claim 1 or claim 2, The aforementioned persona model is The general characteristics of the trends in the aforementioned questions and answers are pre-trained in a large-scale language model, An extension generation unit for storing the characteristics of the aforementioned responses of the subject and incorporating them into the large-scale language model, A persona model system, including [this].

5. In the persona model system according to claim 1 or claim 2, The system includes a rewarding unit that provides a reward to the target person from the business that asks the question each time the answer is generated from the persona model, A persona model system in which the rewards granted by the reward granting unit are registered in association with the identification information that can identify the target person.

6. In the persona model system according to claim 1 or claim 2, The system includes a feature acquisition unit that acquires the characteristics of the subject's thinking based on at least one of the following: audio or video data of the subject, email software history, communication app history, social networking service history, books written by the subject, blog posts created by the subject, or diaries written by the subject. The persona model system outputs the output data, including the answers, based on the characteristics of the subject's thinking acquired by the feature acquisition unit.

7. One or more computers that implement the persona model system, A process that involves inputting input data, including questions, into one or more persona models that have been trained to capture the thinking characteristics of at least one subject, and outputting output data, including answers that reflect the thinking characteristics of the subject; Identity verification process, A persona model processing method that performs the following: The aforementioned identity verification process includes, in order to verify that the subject is a real individual, intervening between the subject's verifiable medium issued by a public institution and a public personal authentication service, and having the public personal authentication service verify the subject's identity, or verifying the subject's identity using the subject's card substitute electronic record, The aforementioned persona model is generated on the condition that the subject is authenticated as a real individual through the aforementioned identity authentication process. Identification information that allows for the individual identification of the aforementioned persona model is registered in association with the identification information that allows for the individual identification of the aforementioned person, along with the identity verification information of the aforementioned person. A persona model processing method that, when an existing persona model exists that has been trained using machine learning to capture the characteristics of the thinking of the subject whose identity has been authenticated, acquires training data for training the characteristics of the thinking of the subject and updates the existing persona model.

8. One or more computers to implement the persona model system, A process that involves inputting input data, including questions, into one or more persona models that have been trained to capture the thinking characteristics of at least one subject, and outputting output data, including answers that reflect the thinking characteristics of the subject; Identity verification process, A program for persona models that executes the following: The aforementioned identity verification process includes, in order to verify that the subject is a real individual, intervening between the subject's verifiable medium issued by a public institution and a public personal authentication service, and having the public personal authentication service verify the subject's identity, or verifying the subject's identity using the subject's card substitute electronic record, The aforementioned persona model is generated on the condition that the subject is authenticated as a real individual through the aforementioned identity authentication process. Identification information that allows for the individual identification of the aforementioned persona model is registered in association with the identification information that allows for the individual identification of the aforementioned person, along with the identity verification information of the aforementioned person. A persona model program that, when an existing persona model exists that has been trained using machine learning to capture the characteristics of the thinking of the person whose identity has been verified, acquires training data for training the characteristics of the thinking of the person and updates the existing persona model.

Images