Information processing method, program, and information processing device
The information processing method and apparatus use virtual personalities to analyze and present conversation characteristics, addressing the inadequacies of existing communication technologies by enhancing user interaction through simulated conversations.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- HAIVE INC
- Filing Date
- 2024-12-13
- Publication Date
- 2026-06-18
Smart Images
Figure JP2024044318_18062026_PF_FP_ABST
Abstract
Description
Information Processing Method, Program, and Information Processing Apparatus 【0001】 The present disclosure relates to an information processing method, a program, and an information processing apparatus. 【0002】 Conventionally, techniques related to promoting communication have been known (for example, Patent Document 1). 【0003】 Japanese Patent Application Laid-Open No. 2013-089086 【0004】 However, with the technique described in Patent Document 1, communication cannot be sufficiently promoted. 【0005】 The present disclosure provides an information processing method, a program, and an information processing apparatus for promoting communication. 【0006】 An information processing method according to an aspect of the present disclosure causes a computer to acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set based on information of a first user and a second virtual personality set based on information of a second user, acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log, and execute a process for presenting the acquired characteristics to at least one of the first user and the second user. 【0007】 A program according to another aspect of the present disclosure causes a computer to acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set based on information of a first user and a second virtual personality set based on information of a second user, acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log, and execute a process for presenting the acquired characteristics to at least one of the first user and the second user. 【0008】An information processing device according to another aspect of the present disclosure performs the following actions: acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set up based on information of a first user and a second virtual personality set up based on information of a second user; acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log; and perform processing to present the acquired characteristics to at least one of the first user and the second user. 【0009】 This disclosure can facilitate communication. 【0010】 This is a conceptual diagram of System 1 according to this embodiment. This is a diagram showing an example of the functional configuration of System 1 according to this embodiment. This is a diagram showing an example of the operation of System 1 according to this embodiment. This is a diagram showing an example of the display screen of Terminal Device 3 according to this embodiment. This is a diagram showing an example of the display screen of Terminal Device 3 according to this embodiment. This is a diagram showing an example of the display screen of Terminal Device 3 according to this embodiment. This is a diagram showing an example of the display screen of Terminal Device 3 according to this embodiment. This is a diagram showing an example of the display screen of Terminal Device 3 according to this embodiment. This is a diagram showing an example of the display screen of Terminal Device 3 according to this embodiment. This is a diagram showing an example of the operation of System 1 according to this embodiment. This is a diagram showing an example of the hardware configuration of the devices included in System 1 according to this embodiment. 【0011】 1. Referring to the schematic diagram 1, an overview of System 1 according to this embodiment (hereinafter simply referred to as "System 1") will be described. System 1 can present information to facilitate communication among multiple users by having virtual personalities, each reflecting the information of multiple users, engage in conversations and analyzing the conversation logs. 【0012】System 1 includes a first terminal device 3a used by the first user, a second terminal device 3b used by the second user, and an information processing device 2 (not shown in Figure 1). The first terminal device 3a receives input of first user information from the first user. The first user information includes, for example, information about the first user's hobbies and place of origin. Similarly, the second terminal device 3b receives input of second user information from the second user. The second user information includes, for example, information about the second user's hobbies and place of origin. The information processing device 2 acquires the first user information and the second user information (S1). 【0013】 Next, the information processing device 2 sets up a first virtual personality, which is the virtual personality of the first user, based on the first user information, and also sets up a second virtual personality, which is the virtual personality of the second user, based on the second user information (S2). 【0014】 Next, the information processing device 2 has the first virtual personality and the second virtual personality converse (S3). The information processing device 2 acquires and analyzes the conversation log of the conversation and displays the analysis results on the first terminal device 3a and the second terminal device 3b (S4). These analysis results include, for example, information about topics that were discussed extensively in the conversation between the first virtual personality and the second virtual personality. 【0015】 According to System 1, the first and second users can converse based on the results of an analysis of conversations previously conducted by the virtual personalities. These analysis results may include information that provides insights beyond simply extracting similarities between users, such as topics that were popular among the virtual personalities (i.e., topics that are presumed to be popular among real users as well). In this way, System 1 can facilitate communication between the first and second users, which can be particularly significant when the first and second users are meeting for the first time. 【0016】In the following embodiment, it is assumed that the first user and the second user are meeting for the first time, but the scope of application of this disclosure is not limited to this. Furthermore, in this embodiment, it is assumed that the two virtual personalities of the first user and the second user are made to converse, and that communication between the first user and the second user is facilitated based on the results of the analysis of the conversation log, but the scope of application of this disclosure is not limited to this. This disclosure can also be applied to situations in which the virtual personalities of the first user to the Nth user (where N is a natural number of 3 or more) are made to converse, and that communication between the first user to the Nth user is facilitated based on the results of the analysis of the conversation log. 【0017】 Furthermore, in this embodiment, when the first user and the second user are not distinguished, or when they are referred to collectively, they are simply referred to as "users." Similarly, when the first virtual personality and the second virtual personality are not distinguished, or when they are referred to collectively, they are simply referred to as "virtual personality." When the first user information and the second user information are not distinguished, or when they are referred to collectively, they are simply referred to as "user information." 【0018】 2 Functional Configuration 2.1 The functional configuration of System 1 will be described with reference to the overview diagram 2 of the functional configuration. System 1 includes an information processing device 2, a first terminal device 3a, a second terminal device 3b, an LLM (Large Language Model) server device 4, and a communication network 5. Hereinafter, when the first terminal device 3a and the second terminal device 3b are not specifically distinguished or are referred to collectively, they will be referred to as "terminal device 3". The information processing device 2, terminal devices 3, and LLM server device 4 are configured to communicate with each other via the communication network 5. 【0019】 2.2 Terminal Device 3 Terminal device 3 is a communication device used by the user. Terminal device 3 is, for example, a smartphone, a personal computer, a tablet device, or a wearable device. Terminal device 3 may be equipped with an input interface, an output interface, and a communication interface. 【0020】The input interface is an interface that allows the terminal device 3 to receive input from the user. The input interface may be a touch panel, microphone, camera, keyboard, mouse, etc. 【0021】 The output interface is an interface for transmitting information to the user through images, sound, etc. The output interface includes a display (which may also function as a touch panel) and speakers. 【0022】 The communication interface is an interface for enabling communication with other devices via the communication network 5. The communication interface may be a wireless communication interface or a wired communication interface. 【0023】 Terminal device 3 may, for example, access services provided by information processing device 2 via a web browser, or it may access such services by installing dedicated software. 【0024】 2.3 LLM Server Device 4 The LLM server device 4 is a device that provides services using LLM. LLM may be a deep learning model that has hundreds of millions of parameters and has learned hundreds of gigabytes or more of natural language data. An example of LLM is gpt-4o. In one example, the LLM server device 4 provides services using LLM via API (Application Programming Interface). 【0025】 In one embodiment, the LLM server device 4 receives an instruction (which can also be called a prompt) from another device and returns a response to that other device in accordance with the instruction. In one example, both the instruction and the response are in text format. 【0026】 2.4 Information Processing Device 2 The information processing device 2 controls conversations by virtual personalities and the analysis of those conversation logs. 【0027】In one embodiment, the information processing device 2 is a server device when the terminal device 3 is a client device. That is, the information processing device 2 receives a request from the terminal device 3 (for example, an HTTP request) and sends a response (for example, an HTTP response) accordingly. 【0028】 In one embodiment, the information processing device 2 is a client device to the LLM server device 4. That is, the information processing device 2 sends a request to the LLM server device 4 and receives a response accordingly. 【0029】 In one embodiment, the information processing device 2 is a cloud server device. The information processing device 2 may be a device that includes, for example, one or more virtual or physical web server devices and one or more virtual or physical database server devices. 【0030】 The information processing device 2 comprises a control unit 10, a storage unit 12, a network interface unit 14, and a bus 16. The control unit 10, the storage unit 12, and the network interface unit 14 are electrically connected via the bus 16. 【0031】 2.4.1 Control Unit 10 The control unit 10 can function as an acquisition unit 100, an analysis unit 102, and a display control unit 104 by executing various programs stored in the storage unit 12, which will be described later. 【0032】 2.4.1.1 Acquisition Unit 100 The acquisition unit 100 acquires conversation logs corresponding to the simulation of conversations between the first virtual personality, which is set based on the first user information, and the second virtual personality, which is set based on the second user information. Hereinafter, the simulation of conversations between the first and second virtual personalities may be simply referred to as "conversations between the first and second virtual personalities." 【0033】User information may include, for example, name, gender, age, height, occupation, place of birth and upbringing, places lived, educational background, work history, personality, personality indicators such as MBTI (Myers-Briggs type indicator), habits, hobbies, interests, values, family structure, friendships, position and relationships at work, how one spends their weekdays, food preferences, personal news, influential people or events, and important memories. User information can also be called a "persona" in that it may reflect what kind of person the user is and what kind of decisions they are capable of making. 【0034】 In one embodiment, the acquisition unit 100 acquires a conversation log corresponding to a conversation between a first chatbot (an example of a first virtual personality) that can access first user information and a second chatbot (an example of a second virtual personality) that can access second user information. 【0035】 In one example, the acquisition unit 100 can control the first chatbot to ask the second chatbot a predetermined question. The predetermined question is, for example, "What are the second user's hobbies?" Furthermore, the acquisition unit 100 can control the second chatbot to answer the predetermined question from the first chatbot and also ask the first chatbot other predetermined questions. The answer is, for example, "The second user's hobby is tennis." The other predetermined question is, for example, "Where is the first user from?" In this example, the acquisition unit 100 can acquire a conversation log by having the first chatbot and the second chatbot converse in this way. 【0036】 In one embodiment, the acquisition of a conversation log by the acquisition unit 100 includes inputting conversation instructions to the LLM regarding the execution of a simulation of a conversation between the first virtual personality and the second virtual personality. 【0037】In one example, the acquisition unit 100 sends a conversation instruction to the LLM server device 4 containing first user information, second user information, and the text: "We will give you user information for two people. Based on detailed personal information such as their background, MBTI, hobbies and preferences, pretend to be the two people and have a conversation, and output the conversation log. However, the two people are assumed to be meeting for the first time and know nothing about each other." As a result, the LLM server device 4 sets up a first virtual personality based on the first user information, sets up a second virtual personality based on the second user information, and simulates a conversation between the first and second virtual personalities. 【0038】 It should be noted that the establishment of a virtual personality is not limited to the explicit definition of the virtual personality. If the conversation log contains text that simulates the content of the first user's statements, it can be said that a first virtual personality has been established, at least implicitly. Similarly, if the conversation log contains text that simulates the content of the second user's statements, it can be said that a second virtual personality has been established, at least implicitly. 【0039】 In one embodiment, inputting a conversation command to the LLM includes inputting a command to the first LLM to cause it to engage in conversation based on a first virtual personality, and inputting a command to the second LLM, which is different from the first LLM, to cause it to engage in conversation based on a second virtual personality. Both the first LLM and the second LLM may be hosted on the LLM server device 4, or one of them may be hosted on another LLM server device. 【0040】 In one example, the acquisition unit 100 inputs the text "We will give you user information. Based on the detailed personal information of this person, such as their background, MBTI, hobbies, and preferences, please output text that assumes you are speaking as this person." to both the first LLM and the second LLM. The acquisition unit 100 can also input first user information to the first LLM and second user information to the second LLM. Furthermore, the acquisition unit 100 can control one of the first LLMs to initiate a conversation with the other. This allows the acquisition unit 100 to acquire a conversation log related to the conversation between the first LLM and the second LLM. 【0041】 In one embodiment, a conversation log is acquired based on short-range wireless communication being performed between the first terminal device 3a and the second terminal device 3b. The short-range wireless communication can be communication possible within a range of several millimeters to several meters. The short-range wireless communication can be, for example, Bluetooth, NFC (Near Field Communication), Wi-Fi, or the like. 【0042】 In one example, communication by NFC is performed based on the first terminal device 3a and the second terminal device 3b coming into contact (for example, the distance between the first terminal device 3a and the second terminal device 3b becoming about 0 cm to 3 cm), and based on the communication, the acquisition unit 100 executes processing related to acquiring the conversation log. 【0043】 According to this configuration, the first user can easily identify the second user, and the second user can easily identify the first user. As a result, promoting communication is smoothed. 【0044】 2.4.1.2 Analysis Unit 102 The analysis unit 102 acquires characteristics of a conversation by the first virtual personality and the second virtual personality based on the conversation log. The characteristics of the conversation can be any information that can be specified based on the conversation log. In one example, the characteristics of the conversation can be a topic in which at least one of the first user and the second user is interested. In another example, the characteristics of the conversation can include information regarding the organization to which at least one of the first user and the second user belongs. In another example, the characteristics of the conversation can include information regarding the skills or abilities of at least one of the first user and the second user. In another example, the characteristics of the conversation include information regarding words included in the conversation log a predetermined number of times or more. In another example, the characteristics of the conversation include a summary of the conversation log. In another example, the characteristics of the conversation are the difference between the amount of speech by the first virtual personality and the amount of speech by the second virtual personality. 【0045】In one embodiment, obtaining the characteristics of the conversation between the first virtual personality and the second virtual personality includes inputting an analysis instruction regarding obtaining the characteristics based on the conversation log into the LLM. In one example, the analysis unit 102 may input an analysis instruction including at least a part of the conversation log and text such as "Please extract 10 words that frequently appear from this conversation log." into the LLM server device 4. In another example, the analysis unit 102 may input an analysis instruction including the conversation log and text such as "Please summarize this conversation log." into the LLM server device 4. 【0046】 In one embodiment, obtaining the characteristics of the conversation between the first virtual personality and the second virtual personality includes obtaining the topics that became lively in the conversation between the first virtual personality and the second virtual personality. In one example, the analysis unit 102 may input an analysis instruction including the conversation log and text such as "Please extract 4 topics that are considered to have become lively from the perspectives of the two parties from this conversation log." into the LLM server device 4. In another example, the analysis unit 102 may extract the words with a high appearance frequency in the conversation log as the lively topics. 【0047】 In one embodiment, obtaining the characteristics of the conversation between the first virtual personality and the second virtual personality includes obtaining at least one of the topics that are presumed to become lively in the conversation between the first user and the second user. In one example, the analysis unit 102 may input an analysis instruction including the conversation log and text such as "Please extract 4 topics that are considered insufficient to talk about when standing from the positions of the two parties from this conversation log." into the LLM server device 4. 【0048】 2.4.1.3 Display control unit 104 The display control unit 104 executes a process for presenting the characteristics of the conversation obtained by the analysis unit 102 to at least one of the first user and the second user. In one example, the display control unit 104 displays the characteristics of the conversation on a display that can be commonly browsed by the first user and the second user. 【0049】In one embodiment, the process of presenting the conversation features acquired by the analysis unit 102 to at least one of the first user and the second user includes transmitting display information for displaying the conversation features to at least one of the first terminal device 3a and the second terminal device 3b. 【0050】 In one example, the display control unit 104 transmits common display information to both the first terminal device 3a and the second terminal device 3b. The common display information includes, for example, information about topics that were popular in the conversation between the first and second virtual personalities and were common topics for both of them. 【0051】 In another example, the display control unit 104 transmits first display information to the first terminal device 3a and second display information different from the first display information to the second terminal device 3b. The first display information includes, for example, information about topics that were discussed enthusiastically in a conversation between the first and second virtual personalities, where the second virtual personality actively disclosed information (including answers to questions). In contrast, the second display information includes, for example, information about topics that were discussed enthusiastically in a conversation between the first and second virtual personalities, where the first virtual personality actively disclosed information (including answers to questions). 【0052】 2.4.2 Storage Unit 12 The storage unit 12 stores various information necessary for the operation of the information processing device 2. In one embodiment, the storage unit 12 stores a program to be executed by the control unit 10. 【0053】 2.4.3 Network Interface Unit 14 The network interface unit 14 enables communication with other devices via the communication network 5. 【0054】 2.5 Communication Network 5 The communication network 5 enables communication between each device included in System 1. In one example, the communication network 5 enables such communication based on the TCP / IP protocol. 【0055】3 Operation 3.1 The overall sequence diagram 3 is a sequence diagram showing an example of the overall operation of System 1. First, the first terminal device 3a receives input of first user information (S100). At this time, the first terminal device 3a may, for example, sequentially display a number of questions and receive answers from the first user for each of the number of questions. The first user information includes these answers. Next, the first terminal device 3a transmits the first user information to the information processing device 2 (S102). In response, the information processing device 2 acquires the first user information. 【0056】 Similarly, the second terminal device 3b receives input of second user information (S104) and transmits the second user information to the information processing device 2 (S106). In response, the information processing device 2 acquires the second user information. 【0057】 Next, the first terminal device 3a performs short-range wireless communication with the second terminal device 3b based on the operation of the first user (S108). In this example, the first terminal device 3a obtains the identification information of the second user (e.g., user ID) via short-range wireless communication with the second terminal device 3b. Similarly, the second terminal device 3b obtains the identification information of the first user via short-range wireless communication with the first terminal device 3a. 【0058】 Figure 4 shows an example of a display screen that may be displayed on the terminal device 3 immediately before step S108. In the example display screen of Figure 4, an icon d100 is displayed. The icon d100 is an image that prompts the first terminal device 3a and the second terminal device 3b to make contact. When the first terminal device 3a and the second terminal device 3b perform short-range wireless communication by making contact with each other, such an icon d100 can be used to prompt the execution of short-range wireless communication. 【0059】Returning to Figure 3, the first terminal device 3a transmits the identification information of the second user, obtained from the second terminal device 3b via short-range wireless communication, to the information processing device 2 (S110). The second terminal device 3b also transmits the identification information of the first user, obtained from the first terminal device 3a, to the information processing device 2 (S111). The information processing device 2 acquires the identification information of the first user and the identification information of the second user. 【0060】 Figure 5A shows an example of a display screen that may be displayed on the first terminal device 3a immediately after step S110. Similarly, Figure 5B shows an example of a display screen that may be displayed on the second terminal device 3b immediately after step S110. 【0061】 Figure 5A displays an icon d200, keywords d202, a self-introduction text d204, and progress status d206. In the example screen of Figure 5A, icon d200 shows the first user playing tennis. Keywords d202 indicate that the first user's particular interests are "AI," "entrepreneurship," and "tennis." The self-introduction text d204 displays "○○ University," "I want to connect with people like this," "People who are entrepreneurs," "People interested in internships," and "People who like sports." In this example, keywords d202 and the self-introduction text d204 are considered to be part of the first user's information. 【0062】 Figure 5B displays an icon d300, keywords d302, a self-introduction text d304, and progress status d306. In the example screen of Figure 5B, icon d300 shows the second user dancing. Keywords d302 indicate that the second user's particular interests are "AI," "music," and "dance." The self-introduction text d304 displays "I like dancing and music," "I am researching AI-based technology at university," and "I am interested in entrepreneurship." In this example, keywords d302 and the self-introduction text d304 are considered part of the second user's information. 【0063】In Figure 5A, progress status d206 and in Figure 5B, progress status d306, the message "Analyzing the trending topic..." is displayed. These may be displayed to inform the user that the information processing device 2 and the LLM server device 4 are generating and analyzing the conversation log at that time. 【0064】 Returning to Figure 3, the information processing device 2 identifies the first user information and the second user information based on the acquired identification information of the first user and the identification information of the second user, respectively. Next, the information processing device 2 sets up the first virtual personality based on the first user information and sets up the second virtual personality based on the second user information (S112). 【0065】 As described above, the first user information includes the information displayed in the keyword d202 and self-introduction text d204 in Figure 5A (i.e., the first user's particular interests are "AI," "entrepreneurship," and "tennis," their alma mater is "XX University," and they "want to connect" with "people who are entrepreneurs," "people interested in internships," and "people who like sports"). Therefore, these characteristics may be reflected in the first virtual personality. 【0066】 Furthermore, the second user information includes the information displayed in the keyword d302 and self-introduction text d304 in Figure 5B (i.e., the second user's particular interests are "AI," "music," and "dance," the second user "likes dance and music," "is researching AI-based technology at university," and "is interested in entrepreneurship"). Therefore, these characteristics may be reflected in the second virtual personality. 【0067】 Next, the information processing device 2 sends a conversation instruction to the LLM server device 4 regarding the execution of a conversation simulation between the first virtual personality and the second virtual personality (S114). In response, the LLM server device 4 generates a conversation log corresponding to the conversation simulation and returns it to the information processing device 2 (S116). The information processing device 2 acquires the conversation log. 【0068】The conversation log obtained in this example could be in the following format and content: "First virtual persona: Nice to meet you, my name is XX. I graduated from XX University and now I run an AI-related company that I founded. Second virtual persona: Nice to meet you, my name is □□. I love AI and I do research using AI at university. First virtual persona: Really! What kind of research are you doing? Second virtual persona: Right now I'm researching how to improve the accuracy of image recognition. What kind of AI is your company developing, XX? First virtual persona: My company mainly develops AI using natural language processing. For example, an automatic text summarization system. Second virtual persona: Wow, that sounds interesting! Actually, I'm thinking of starting my own business in the future and I want to launch an AI-based service. First virtual persona: I see! Starting a business can be tough, but being able to turn your ideas into reality and put them out into the world is really rewarding. (continues below)" 【0069】 Next, the information processing device 2 sends an analysis instruction to the LLM server device 4 regarding the acquisition of conversation characteristics based on the conversation log (S118). The analysis instruction here may include, for example, the conversation log as described above, and text such as, "This conversation log shows a conversation between a first virtual personality that reflects the characteristics of the first user (e.g., personality, knowledge, etc.) and a second virtual personality that reflects the characteristics of the second user. Based on this conversation log, extract two engaging topics for the first user and two engaging topics for the second user. When doing so, for example, extract common topics between the first and second virtual personalities, and topics that elicited a strong reaction from the other party." 【0070】 In response, the LLM server device 4 analyzes and acquires the characteristics of the conversation from the conversation log and returns them to the information processing device 2 as a response (S120). The response here may include text such as, for example, "Topics that will get the first user excited: 'AI' and 'Company services', Topics that will get the second user excited: 'AI' and 'Difficulties in starting a business'". 【0071】Next, the information processing device 2 generates first display information and second display information based on the acquired response (S122). In this example, the first display information includes information about popular topics for the first user, and the second display information includes information about popular topics for the second user. The information processing device 2 transmits the first display information to the first terminal device 3a (S124) and the second display information to the second terminal device 3b (S126). 【0072】 Figure 6A shows an example of a display screen that may be displayed on the first terminal device 3a immediately after step S124. Compared with the example display screen in Figure 5A, the example display screen in Figure 6A shows a confirmation button d208. The confirmation button d208 is a button that can display the first display information on the first terminal device 3a. 【0073】 Figure 6B shows an example of a display screen that may be displayed on the second terminal device 3b immediately after step S126. Compared with the example display screen in Figure 5B, the example display screen in Figure 6B shows a confirmation button d308. The confirmation button d308 is a button that can display second display information on the second terminal device 3b. 【0074】 The display of confirmation buttons d208 and d308 allows the user to recognize that the generation and analysis of the conversation log by the information processing device 2 and the LLM server device 4 has been completed. 【0075】 In response to the press of confirmation button d208, the first terminal device 3a displays the first display information (S128). In response to the press of confirmation button d308, the second terminal device 3b displays the second display information (S130). 【0076】 Figure 7A shows an example of a display screen that may be displayed on the first terminal device 3a in step S128. Similarly, Figure 7B shows an example of a display screen that may be displayed on the second terminal device 3b in step S130. 【0077】Figure 7A shows an example of the display screen, where the feature display area d400 is shown. The feature display area d400 displays the topics "AI" and "Company Services." These are examples of topics that would be engaging for a first-time user. 【0078】 Figure 7B shows an example of the display screen, with the feature display area d500 shown. The feature display area d400 displays the topics "AI" and "Challenges of Starting a Business." These are examples of topics that can generate interest among second-party users. 【0079】 3.2 Sequence diagram 8 relating to the generation of conversation logs is a sequence diagram for explaining in detail the generation of conversation logs by the LLM server device 4 (corresponding to steps S114 to S116 in Figure 3). In Figure 8, the LLM server device 4 includes a first LLM 4a and a second LLM 4b. 【0080】 First, the information processing device 2 transmits a conversation instruction containing first user information to the first LLM 4a (S200), and transmits a conversation instruction containing second user information to the second LLM 4b (S202). As a result, the first virtual personality is set in the first LLM 4a, and the second virtual personality is set in the second LLM 4b. Steps S200 to S202 may correspond to step S114 in Figure 3. 【0081】 Next, the information processing device 2 transmits a conversation start instruction to the first LLM 4a (S204). The first LLM 4a receives the conversation start instruction. The conversation start instruction may include, for example, an instruction that a text including a greeting should be sent from the first LLM 4a to the second LLM 4b, and an instruction regarding the termination conditions of the exchange between the first LLM 4a and the second LLM 4b. In one example, the termination condition includes a condition that the number of responses from the second LLM 4b to the first LLM 4a (or from the first LLM 4a to the second LLM 4b) reaches a predetermined threshold. In another example, the termination condition includes a condition that the response from the second LLM 4b to the first LLM 4a (or from the first LLM 4a to the second LLM 4b) includes a phrase indicating the end of the conversation. The phrase indicating the end of the conversation may be, for example, "goodbye" and "see you later." 【0082】The first LLM 4a sends a text message including a greeting to the second LLM 4b in response to the instruction to start a conversation (S206). The second LLM 4b sends a response to the greeting to the first LLM 4a (S208). The first LLM 4a sends a further response to that response to the second LLM 4b (S210). The second LLM 4b sends a further response to that response to the first LLM 4a (S212). 【0083】 Next, the first LLM 4a determines whether the termination condition has been met (S214). If it is determined that the termination condition has not been met (S214 NO), the first LLM 4a sends a further response to the response obtained in the most recent step S212 to the second LLM 4b (S210). If it is determined that the termination condition has been met (S214 YES), the first LLM 4a sends the conversation log up to that point to the information processing device 2 (S216). Step S216 may correspond to step S116 in Figure 3. 【0084】 4. Referring to Hardware Configuration Diagram 9, an example of a hardware configuration when the devices included in System 1 described above are implemented by the computer 70 will be explained. Note that the functions of each device can also be implemented by dividing them among multiple devices. 【0085】 As shown in Figure 9, the computer 70 includes a processor 700, a storage device 702, an input interface 704, a data interface 706, a communication interface 708, and a display device 710. 【0086】 The processor 700 controls various processes in the computer 70 by executing programs stored in the storage device 702. For example, each functional unit of the control unit 10 of the information processing device 2 can be realized by the processor 700 executing programs stored in the storage device 702. 【0087】 The storage device 702 is a storage medium such as RAM (Random Access Memory). RAM temporarily stores the program code of the program executed by the processor 700, as well as data required when the program is executed. 【0088】 The storage device 702 can also be a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 702 stores the operating system and various programs for realizing the above configurations. The storage medium storing these various programs may be a computer-readable non-temporary storage medium (non-transitor computer-readable medium). In addition, the storage device 702 can also store tables for registering various information and a database (DB) for managing these tables. Such programs and data are loaded into the storage device 702 as needed and accessed by the processor 700. 【0089】 The input interface 704 is a device for receiving input from the user. Specific examples of the input interface 704 include cameras, buttons, microphones, keyboards, mice, touch panels, various sensors, and wearable devices. The input interface 704 may be connected to the computer 70 via an interface such as USB (Universal Serial Bus). 【0090】 The data interface 706 is a device for inputting data from outside the computer 70. Specific examples of the data interface 706 include drive devices for reading data stored on various storage media. The data interface 706 may also be located outside the computer 70. In that case, the data interface 706 would be connected to the computer 70 via an interface such as USB. 【0091】 The communication interface 708 is a device for performing data communication with external devices of the computer 70 via a communication network 5, either by wire or wireless connection. The communication interface 708 may also be located outside the computer 70. In that case, the communication interface 708 is connected to the computer 70 via an interface such as USB. 【0092】The display device 710 is a device for displaying various types of information. Specific examples of the display device 710 include liquid crystal displays, organic EL (Electro-Luminescence) displays, and displays for wearable devices. The display device 710 may be located outside the computer 70. In that case, the display device 710 is connected to the computer 70 via, for example, a display cable. Furthermore, if a touch panel is used as the input I / F 704, the display device 710 can be configured as an integrated unit with the input I / F 704. 【0093】 Furthermore, the components of the device included in the system 1 described above are such that a program stored in the storage device 702 is executed by the processor 700, thereby realizing a defined process in cooperation with other hardware. In other words, these components can be envisioned as software or firmware, or as corresponding hardware, and in both concepts, they can be described and interpreted as "function," "means," "part," "processing circuit," "unit," or "module," etc. 【0094】 5. Modifications The embodiments described above are provided to facilitate understanding of the Disclosure and are not intended to limit the Disclosure. The configurations that the embodiments may have are not limited to those exemplified and can be modified as appropriate. Furthermore, it is possible to partially substitute or combine configurations shown in different embodiments. 【0095】 At least one of the multiple components described above as being provided by the information processing device 2 (for example, the acquisition unit 100, the analysis unit 102, and the display control unit 104, etc.) may be provided by the terminal device 3. 【0096】In the above embodiment, the information processing device 2 and the LLM server device 4 were described as separate devices, but this is not limited to them. The information processing device 2 may include at least some of the multiple configurations described as being provided by the LLM server device 4 in the above embodiment. Similarly, the terminal device 3 may include at least some of the multiple configurations described as being provided by the LLM server device 4 in the above embodiment. 【0097】 In the above embodiment, an example has been described in which the acquisition and analysis of conversation logs are performed based on short-range wireless communication between a first terminal device 3a and a second terminal device 3b, but the invention is not limited thereto. In one example, the first terminal device 3a may send a predetermined request to the second terminal device 3b, and based on the second terminal device 3b receiving an operation from a second user acknowledging the predetermined request, the information processing device 2 and the LLM server device 4 may perform the acquisition and analysis of conversation logs (for example, periodically) without receiving any special operation from the first user and / or the second user, and transmit the analysis results to the first terminal device 3a and the second terminal device 3b. Thus, the trigger for the acquisition and analysis of conversation logs can be arbitrarily set based on the knowledge of those skilled in the art. 【0098】 In the above embodiment, an example was described in which conversation logs are generated and analyzed based on short-range wireless communication between the first terminal device 3a and the second terminal device 3b, but the embodiment is not limited to this. For example, the first terminal device 3a may display an image code, and the second terminal device 3b may read the image code with a camera to generate and analyze the conversation logs. 【0099】 In the above embodiment, the first LLM4a and the second LLM4b may be hosted on hardware-independent devices, or they may be hosted on common hardware. When the first LLM4a and the second LLM4b are hosted on common hardware, independent virtual resources (e.g., virtual CPU and virtual memory, etc.) may be allocated to each, or common virtual resources may be allocated on a time-sharing basis. 【0100】The system 1 described in the above embodiment can be applied to various services. For example, the system 1 described in the above embodiment can be applied to a service that matches the compatibility of personalities and values between users. In this case, the system 1 can perform a simulation of a conversation between a first user and each of several other users through a virtual personality. In one embodiment, the information processing device 2 may acquire a conversation log corresponding to the simulation of a conversation between a first virtual personality set based on first user information and an nth virtual personality set based on nth user information for n = 2, ..., N (where N is a natural number of 3 or more), acquire the characteristics of the conversation between the first virtual personality and the nth virtual personality based on the conversation log, and perform processing to present the acquired characteristics to the first user. As a result, the first user can grasp the characteristics of conversations with each of the second to nth users, and as a result may be able to discover other users who seem to be compatible with them. 【0101】 When System 1 is applied to a service that matches the compatibility of personalities and values between users, System 1 can highly evaluate the compatibility between the first and second virtual personalities if the conversation between the first and second virtual personalities is prolonged. This evaluation may be included in the characteristics of the conversation. Note that "a long conversation" may refer to a large number of responses being sent and received between the virtual personalities, or a large number of characters in the conversation between the virtual personalities. 【0102】 6. Supplementary Information The wording in this embodiment may be understood as follows, to the extent that no contradiction arises. 【0103】 In this embodiment, "performing a predetermined process based on predetermined information" may mean performing the predetermined process based on at least a portion of the predetermined information, performing the predetermined process based on at least the predetermined information, or performing the predetermined process probabilistically based on the predetermined information. In other words, "performing a predetermined process based on predetermined information" is not limited to performing the predetermined process based solely on the predetermined information. 【0104】 In this embodiment, "executing another process based on a predetermined process" may mean any of the following: executing the other process after the predetermined process has been executed; executing the predetermined process and the other process consecutively; executing the other process based on information determined by the predetermined process; executing the other process on the condition that the predetermined process has been executed; or executing the other process by means of the predetermined process. Furthermore, "executing another process by a predetermined process" may be understood in the same way as "executing another process based on a predetermined process." 【0105】 In this embodiment, "the predetermined information includes other information" may mean either that at least a portion of the predetermined information is the other information, or that the other information can be obtained based on the predetermined information. 【0106】 In this embodiment, "a predetermined process includes other processes" may mean either that at least a part of the predetermined process is the other process (i.e., the other process is performed in the process of obtaining the result of the predetermined process), or that one aspect of the predetermined process is the other process. 【0107】 In this embodiment, "a predetermined object and another object correspond" may mean that there is a one-to-one relationship between the predetermined object and the other object, that the other object is included in a predetermined set identified based on the predetermined object, or that the other object can be identified based on the predetermined object. Furthermore, "a predetermined object and another object corresponding" is not limited to being managed, for example, in a database. Also, "a predetermined object and another object being associated" may be understood in the same way as "a predetermined object and another object corresponding." 【0108】In this embodiment, "acquiring information" includes making the information processable by the control unit 10. "Acquiring information" may include, for example, receiving the information from another device, obtaining the information through predetermined processing, and reading the information from the storage unit 12. 【0109】 In this embodiment, "generating information" may mean either making the information obtained by a predetermined process processable in the control unit 10, or storing the information obtained by the predetermined process in the storage unit 12. 【0110】 In this embodiment, "determining information" may mean either selecting at least one piece of information from one or more pieces of information, or generating new information. 【0111】 In this embodiment, "outputting information" may mean either transmitting the information to another device or outputting the information as audio or video. 【0112】 7. Configuration Examples This disclosure includes the following technologies: 【0113】 [Note 1] An information processing method that causes a computer 70 to perform the following actions: acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set based on information of a first user and a second virtual personality set based on information of a second user; acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log; and perform processing to present the acquired characteristics to at least one of the first user and the second user. 【0114】 [Note 2] The information processing method described in Note 1, wherein obtaining a conversation log includes inputting conversation instructions relating to performing a simulation of a conversation between the first virtual personality and the second virtual personality into a large-scale language model (LLM server device 4). 【0115】[Note 3] The information processing method described in Note 2, wherein inputting conversational instructions into a large-scale language model includes inputting an instruction to the first large-scale language model (first LLM4a) to cause it to engage in conversation based on the first virtual personality, and inputting an instruction to the second large-scale language model (second LLM4b), which is different from the first large-scale language model, to cause it to engage in conversation based on the second virtual personality. 【0116】 [Appendix 4] The information processing method described in any one of Appendix 1 to 3, wherein the acquisition of conversational characteristics by the first virtual personality and the second virtual personality includes inputting analysis instructions for acquiring characteristics based on conversation logs into a large-scale language model (LLM server device 4). 【0117】 [Note 5] The information processing method described in any one of Notes 1 to 4, wherein the acquisition of characteristics of conversations between the first virtual personality and the second virtual personality includes acquiring at least one of the topics that were discussed in conversations between the first virtual personality and the second virtual personality and the topics that are presumed to be discussed in conversations between the first user and the second user. 【0118】 [Appendix 6] The information processing method according to any one of Appendices 1 to 5, wherein the process for presenting the acquired features to at least one of the first user and the second user includes transmitting information for displaying the acquired features to at least one of the terminal device of the first user and the terminal device of the second user. 【0119】 [Appendix 7] An information processing method according to any one of Appendix 1 to 6, which acquires a conversation log based on the fact that short-range wireless communication has taken place between the terminal device of the first user and the terminal device of the second user. 【0120】[Note 8] A program that causes computer 70 to perform the following actions: acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set based on information of the first user and a second virtual personality set based on information of the second user; acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log; and perform processing to present the acquired characteristics to at least one of the first user and the second user. 【0121】 [Note 9] Information processing device 2 performs the following actions: acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set based on the information of the first user and a second virtual personality set based on the information of the second user; acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log; and perform processing to present the acquired characteristics to at least one of the first user and the second user. 【0122】 1...System, 2...Information processing device, 3...Terminal device, 3a...First terminal device, 3b...Second terminal device, 4...LLM server device, 4a...First LLM, 4b...Second LLM, 10...Control unit, 12...Storage unit, 70...Computer, 100...Acquisition unit, 102...Analysis unit, 104...Display control unit, 700...Processor
Claims
1. An information processing method that causes a computer to perform the following actions: acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set based on information of a first user and a second virtual personality set based on information of a second user; acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log; and perform processing to present the acquired characteristics to at least one of the first user and the second user.
2. The information processing method according to claim 1, wherein obtaining the conversation log includes inputting conversation instructions relating to performing a simulation of a conversation between the first virtual personality and the second virtual personality into a large-scale language model.
3. The information processing method according to claim 2, wherein inputting the conversation instructions into a large-scale language model includes: inputting an instruction to cause a first large-scale language model to engage in conversation based on the first virtual personality; and inputting an instruction to cause a second large-scale language model, which is different from the first large-scale language model, to engage in conversation based on the second virtual personality.
4. The information processing method according to claim 1, wherein acquiring the characteristics of conversations between the first virtual personality and the second virtual personality includes inputting analysis instructions to a large-scale language model regarding the acquisition of characteristics based on the conversation log.
5. The information processing method according to claim 1, wherein acquiring the characteristics of conversations between the first virtual personality and the second virtual personality includes acquiring at least one of topics that were discussed in conversations between the first virtual personality and the second virtual personality and topics that are presumed to be discussed in conversations between the first user and the second user.
6. The information processing method according to claim 1, wherein the process for presenting the acquired features to at least one of the first user and the second user includes transmitting information for displaying the acquired features to at least one of the terminal device of the first user and the terminal device of the second user.
7. The information processing method according to claim 1, which acquires the conversation log based on the fact that short-range wireless communication was performed between the terminal device of the first user and the terminal device of the second user.
8. A program that causes a computer to: acquire a conversation log corresponding to a simulation of a conversation between a first virtual personality set up based on information of a first user and a second virtual personality set up based on information of a second user; acquire characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log; and perform processing to present the acquired characteristics to at least one of the first user and the second user.
9. An information processing device that performs the following: acquiring a conversation log corresponding to a simulation of a conversation between a first virtual personality set based on information of a first user and a second virtual personality set based on information of a second user; acquiring characteristics of the conversation between the first virtual personality and the second virtual personality based on the conversation log; and performing processing to present the acquired characteristics to at least one of the first user and the second user.