System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving profile information registered by a user, a means for storing the profile information of the user in a database, a means for receiving a dialog start request from the user, a means for searching and matching other users having common hobbies and interests, and a means for providing a topic of the dialog to the matched users.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conversations with people meeting for the first time can easily lead to awkward silences if they cannot find a common topic to talk about. Finding a common topic is particularly difficult in today's society, where people with diverse backgrounds and interests come together. This results in a lack of dialogue and a lack of interaction. Furthermore, if the topic runs out during a conversation, silences will reoccur, hindering mutual understanding and the building of trust. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, it includes a means for receiving profile information registered by a user and saving it in a database. Next, it provides a means for receiving a request to start a conversation from a user, searching for other users with common hobbies and interests, and performing matching. Furthermore, it constructs a system including a means for providing conversation topics to matched users and generating and providing new topics as the conversation progresses. This allows people who meet for the first time to naturally find common topics and smoothly progress the conversation. By including a means for accepting an operation to request the next topic from a user and a means for generating and providing a new topic based on the request, it is possible for the conversation to continue uninterrupted.

[0006] "User" refers to a person who uses this system to engage in dialogue, registers profile information, and makes a dialogue request.

[0007] "Profile information" refers to personal information registered by a user, such as name, age, gender, hobbies, and interests.

[0008] "Database" refers to a system for storing and managing user profile information.

[0009] A "dialogue start request" refers to an operation in which a user wishes to have a dialogue with another user and conveys that intention to the system.

[0010] "Matching" refers to the process of pairing users who share common hobbies or interests.

[0011] A "topic" refers to a specific topic or theme that allows matched users to start a conversation.

[0012] "Generation" refers to the process by which the system creates new topics and provides them to users.

[0013] A "request" is an action taken by a user to ask the system for a next step or information.

[0014] "Means" refers to specific devices, software, algorithms, etc. used to achieve a particular function.

[0015] "Terminal" refers to a device (e.g., smartphone, PC) that a user uses to access and operate the system. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[0038] 1. User registration and profile settings

[0039] User

[0040] When a user launches the app for the first time, a registration screen will appear.

[0041] Users enter their name, age, gender, hobbies, and interests.

[0042] Terminal

[0043] Collects information entered by the user and sends it to the server.

[0044] server

[0045] The information received from the user is stored in a database.

[0046] 2. Dialogue-initiating request

[0047] User

[0048] Tap the "Start a conversation" button on the app's home screen.

[0049] Terminal

[0050] Send a conversation initiation request to the server.

[0051] server

[0052] A request is received to retrieve information about other online users from a database.

[0053] Search for and match with users who share common hobbies and interests.

[0054] 3. Matching and providing topics

[0055] server

[0056] If a match is made, matching information is sent to both users.

[0057] Generate topics based on common interests or the latest news articles.

[0058] The generated topics are sent to the devices of both matched users.

[0059] Terminal

[0060] The received topic is displayed on the chat screen.

[0061] 4. Dialogue Progress

[0062] User

[0063] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[0064] Terminal

[0065] Sends the message entered by the user to the server.

[0066] server

[0067] The received message is forwarded to the other user's terminal.

[0068] User

[0069] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[0070] Terminal

[0071] Sends a new topic request to the server.

[0072] server

[0073] A new topic is generated and sent to the terminals of both users who performed the match.

[0074] Specific examples

[0075] User registration and profile settings

[0076] User

[0077] Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[0078] Terminal

[0079] Send the registration information to the server.

[0080] server

[0081] The received information is stored in a database.

[0082] Interaction-initiating request

[0083] User

[0084] Tanaka taps the "Start conversation" button.

[0085] Terminal

[0086] Send a conversation initiation request to the server.

[0087] server

[0088] Receives a request and searches for other users who share the common hobby of "watching movies."

[0089] Match with Sato-san.

[0090] Send matching information to Tanaka and Sato.

[0091] Generate a topic related to watching movies (e.g., "recent Marvel movies") and send it to both devices.

[0092] Matching and topic provision

[0093] server

[0094] Generate topics related to watching movies.

[0095] The generated topics are sent to Tanaka and Sato's devices.

[0096] Terminal

[0097] The received topic is displayed on the chat screen.

[0098] Dialogue progress

[0099] User

[0100] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[0101] Sato replies, "Yes, I saw it last week! What about you?"

[0102] Terminal

[0103] Each message is sent to the server, which then forwards it to the other user's terminal.

[0104] User

[0105] Tanaka taps the "Request next topic" button.

[0106] Terminal

[0107] Send Tanaka's request to the server.

[0108] server

[0109] A new topic "Recent Sporting Events" is created and sent to Tanaka and Sato.

[0110] This system allows people meeting for the first time to naturally find common topics and start a conversation, and by offering new topics as the conversation progresses, it keeps the conversation flowing.

[0111] The processing flow will be explained below.

[0112] Step 1:

[0113] User

[0114] When a user launches the app for the first time, they are presented with a registration screen.

[0115] The user enters their name, age, gender, hobbies, and interests.

[0116] Step 2:

[0117] Terminal

[0118] The profile information entered by the user is sent to the server.

[0119] Step 3:

[0120] server

[0121] The received profile information is stored in a database.

[0122] Step 4:

[0123] User

[0124] The user taps the "Start a conversation" button on the app's home screen.

[0125] Step 5:

[0126] Terminal

[0127] Send a conversation initiation request to the server.

[0128] Step 6:

[0129] server

[0130] A request to start a conversation is received, and information on other online users is obtained from a database.

[0131] Search for and match with users who share common hobbies and interests.

[0132] Step 7:

[0133] server

[0134] If a match is made, matching information is sent to both users.

[0135] Generate conversation topics based on common interests or the latest news stories.

[0136] Step 8:

[0137] server

[0138] The generated topics are sent to the devices of both matched users.

[0139] Step 9:

[0140] Terminal

[0141] The received topic is displayed on the chat screen.

[0142] Step 10:

[0143] User

[0144] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[0145] Step 11:

[0146] Terminal

[0147] Sends messages sent by users to the server.

[0148] Step 12:

[0149] server

[0150] The received message is forwarded to the other user's terminal.

[0151] Step 13:

[0152] User

[0153] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[0154] Step 14:

[0155] Terminal

[0156] Sends a new topic request to the server.

[0157] Step 15:

[0158] server

[0159] A new topic is generated and sent to the devices of both matched users.

[0160] Example 1

[0161] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0162] In today's online communication environment, it is difficult for users who meet for the first time to naturally progress a conversation. In particular, if they cannot find a common topic, the conversation tends to stall. To solve this problem, a system is needed that matches users based on common hobbies and interests and provides appropriate topics. Furthermore, it is desirable to provide new topics in a timely manner while the conversation is in progress, ensuring uninterrupted communication.

[0163] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0164] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for generating conversation topics based on common hobbies and recent topics using a generative AI model, means for providing conversation topics to matched users, and means for transmitting the matching information and the generated conversation topics to a user terminal. This enables users to naturally find common topics and start a conversation, and to provide new topics as the conversation progresses.

[0165] "User" refers to an individual user of the system.

[0166] "Profile information" refers to personal information such as name, age, gender, hobbies, and interests that a user registers in the system.

[0167] "Database" refers to a storage device and its management system for storing user profile information and other data.

[0168] A "dialogue initiation request" refers to a request sent by a user to begin a dialogue.

[0169] "Matching" refers to the process of connecting users who share common hobbies or interests.

[0170] "Generative AI model" refers to a software model that uses artificial intelligence to generate conversation topics based on shared interests and current topics.

[0171] "Topics" refer to themes or topics related to common interests or the latest news that are generated by the server to encourage dialogue between users.

[0172] "Matching information" refers to data containing information about users who have been matched.

[0173] "User terminal" refers to an electronic device (e.g., smartphone, tablet, computer) used by a user to access the system.

[0174] "Means for receiving" refers to the functions and processes for receiving data from a user.

[0175] "Transmitting means" refers to the functions or processes for sending data to other devices or systems.

[0176] "Storage means" refers to the functions and processes for retaining data for long periods of time.

[0177] "New topics" refer to new themes or topics that are presented as the dialogue progresses.

[0178] The system for implementing this invention stores profile information registered by users, matches users with other users who share common hobbies and interests, and provides appropriate topics of conversation to facilitate smooth dialogue. In a specific implementation, the server, terminals, and users each have different roles and work together to form the system.

[0179] 1. User registration and profile settings

[0180] User

[0181] When a user launches the app, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[0182] Terminal

[0183] The terminal collects the profile information entered by the user, encrypts it, and transmits it to the server.

[0184] server

[0185] The server stores the received profile information in a database, such as MySQL.

[0186] Examples:

[0187] Tanaka uses the app to enter and submit her profile information.

[0188] 2. Dialogue-initiating request

[0189] User

[0190] The user taps the "Start a conversation" button on the app's home screen.

[0191] Terminal

[0192] The terminal sends a dialogue start request to the server in real time.

[0193] server

[0194] The server receives the request, retrieves information about other online users from a database, and matches users together based on common interests.

[0195] Examples:

[0196] Tanaka taps the "Start conversation" button, a request to start a conversation is sent to the server, and the server matches him with Sato.

[0197] 3. Matching and providing topics

[0198] server

[0199] The server uses a generative AI model to generate conversation topics based on common interests and the latest news, for example using the OpenAI GPT series.

[0200] The generated topics are sent to the devices of both matched users.

[0201] Terminal

[0202] The device displays the received topics on the chat screen.

[0203] Examples:

[0204] The server generates a topic about "recent Marvel movies" and sends it to Tanaka and Sato's devices, which then display it on their chat screens.

[0205] 4. Dialogue Progress

[0206] User

[0207] The user enters a message based on the provided topic and starts a conversation.

[0208] Terminal

[0209] The terminal sends the message entered by the user to the server, which then forwards it to the other user's terminal.

[0210] server

[0211] As the conversation progresses, if the user taps the "Request next topic" button, a new topic will be generated and sent to the user's device again.

[0212] Examples:

[0213] Tanaka sends a message asking, "Have you seen the latest Marvel movie?", to which Sato replies, "Yes, I saw it last week! How about you?"

[0214] Tanaka taps the "Request next topic" button, and the server generates a new topic about "recent sporting events" and sends it to both devices.

[0215] Example prompt sentence:

[0216] "Start conversations with other users who share your interests, and if you match, offer topics based on those interests."

[0217] By implementing this invention, the system allows users to naturally find common topics and start a conversation, and new topics can be suggested as the conversation progresses. This system provides powerful support for smooth communication between people meeting for the first time.

[0218] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0219] Step 1: The user launches the app and is presented with a registration screen.

[0220] Input: The user launches the app for the first time.

[0221] Output: The registration screen is displayed.

[0222] Specific operation: When a user launches the app for the first time, the device checks the first-time launch flag built into the system. At first launch, the registration screen is displayed to the user.

[0223] Step 2: User enters required information

[0224] Input: The user enters their name, age, gender, hobbies, and interests on the registration screen.

[0225] Output: The information entered by the user.

[0226] Specific operation: The user enters their name, age, gender, hobbies, and interests in the fields displayed on the app's registration screen. For example, they might enter "Name: Tanaka, Age: 30, Gender: Male, Hobbies: Watching movies and sports."

[0227] Step 3: The device sends the entered information to the server

[0228] Input: Profile information entered by the user.

[0229] Output: Encrypted user information sent from the device to the server.

[0230] How it works: The device collects and encrypts the information entered by the user in real time, then sends the encrypted data to the server.

[0231] Step 4: The server receives the information and stores it in a database

[0232] Input: Encrypted user information sent from the device.

[0233] Output: User profile information stored in a database.

[0234] What happens: The server receives the encrypted data, decrypts it, verifies the information received, checks its integrity, and then stores it in a secure database (e.g., MySQL).

[0235] Step 5: User taps the "Start conversation" button

[0236] Input: A request from the user to initiate a conversation.

[0237] Output: A conversation initiation request.

[0238] What happens: The user finds the "Start a conversation" button on the app's home screen and taps it, which generates a conversation start request.

[0239] Step 6: The device sends a conversation start request to the server

[0240] Input: A request from the user to initiate a conversation.

[0241] Output: The conversation initiation request sent to the server.

[0242] Specific operation: The device sends a request to start a conversation tapped by the user to the server in real time.

[0243] Step 7: The server receives the request and retrieves other user information

[0244] Input: A conversation initiation request sent from the device.

[0245] Output: Information about other users with common hobbies and interests.

[0246] Specific operation: When the server receives a request to start a conversation, it retrieves information about other online users from the database, and then searches for matches based on common hobbies and interests.

[0247] Step 8: The server matches users based on common interests.

[0248] Input: Other user information obtained.

[0249] Output: The combination of users who matched.

[0250] Specific operation: The server analyzes the acquired information of other users and matches users with common hobbies and interests. For example, Tanaka and Sato, who share the hobby of "watching movies," are matched.

[0251] Step 9: The server generates a conversation topic using the generative AI model.

[0252] Input: Common interests and latest news information of matched users.

[0253] Output: The generated conversation topics.

[0254] How it works: The server uses a generative AI model (such as the OpenAI GPT series) to generate conversation topics based on shared interests and the latest news. For example, the topic "Recent Marvel Movies" might be generated.

[0255] Step 10: The server sends the conversation topic to the matching user's device.

[0256] Input: The topic of the generated conversation.

[0257] Output: Topics sent to the matched users' devices.

[0258] Specific operation: The server sends the generated conversation topic to the matched users' devices. For example, the topic of "recent Marvel movies" is sent to Tanaka and Sato's devices.

[0259] Step 11: Display the topic received by the device on the chat screen

[0260] Input: The conversation topic sent by the server.

[0261] Output: Topics displayed on the chat screen.

[0262] Specific operation: The device will display the received topic on the chat screen. For example, "Recent Marvel movies" will be displayed on the chat screen.

[0263] Step 12: The user types a message based on the provided topic and starts the conversation.

[0264] Input: Topics displayed on the chat screen.

[0265] Output: The message entered by the user.

[0266] Specific operation: The user starts a conversation by typing a message based on the topic displayed on the chat screen. For example, Tanaka types and sends a message saying, "Have you seen the latest Marvel movie?"

[0267] Step 13: The device sends a message to the server, which forwards it to the other user's device.

[0268] Input: The message entered by the user.

[0269] Output: The message forwarded to the other user's device.

[0270] Specific operation: The device sends the message entered by the user to the server, and the server forwards the message to the other user's device. For example, Tanaka's message "Have you seen the latest Marvel movie?" is forwarded to Sato's device.

[0271] Step 14: User taps the "Request next topic" button

[0272] Input: A user's request for a new topic.

[0273] Output: Next topic request.

[0274] What it does: When a user taps the "Request next topic" button, a request is made for a new topic. For example, Tanaka taps this button to rekindle the conversation.

[0275] Step 15: The device sends a new topic request to the server

[0276] Input: A new topic request from a user.

[0277] Output: New topic request sent to the server.

[0278] Specific operation: The terminal sends requests for new topics from the user to the server in real time.

[0279] Step 16: The server generates a new topic and sends it to the matching user's device.

[0280] Input: New topic request.

[0281] Output: The new topics generated.

[0282] Specific operation: The server generates a new topic and sends it to the devices of the matched users. For example, the server generates a topic about "recent sporting events" and sends it to the devices of Tanaka and Sato.

[0283] In this way, the system receives specific input at each step, processes and calculates the data, and links the output to the next step, allowing users to smoothly advance their dialogue.

[0284] (Application example 1)

[0285] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0286] Conventional conversation support systems lacked an appropriate mechanism for promoting conversations between visitors and staff in physical stores. They also had difficulty providing specific topics related to store-specific menus and services. This resulted in problems such as first-time customers feeling uncomfortable in the store, which did not contribute to improving the store experience.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0288] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for providing conversation topics to matched users, means for identifying users in a physical store and supporting conversations between store staff and customers, means for generating topics related to menus and services offered by the store, means for generating and providing new topics according to the content of the conversation, and means for using prompt sentences to prompt the generative AI model to promote the conversation.This makes it easier for customers who meet for the first time in a physical store, or between customers and staff, to find common topics, enabling natural conversations to be started and continued.

[0289] The "means for receiving profile information registered by a user" refers to the means by which the system receives information such as name, age, gender, hobbies, and interests that a user inputs through an application.

[0290] The "means for saving user profile information in a database" refers to a means for storing received user profile information in a database so that it can be referenced later.

[0291] The "means for receiving a dialogue start request from a user" refers to the means by which the system receives a request when a user wishes to start a dialogue.

[0292] "Means for searching for and matching with other users who share common hobbies and interests" refers to a means for searching for other users who share common hobbies and interests based on the received user profile information, and selecting those users as conversation partners.

[0293] The "means for providing conversation topics to matched users" refers to a means for generating and providing topics based on common hobbies and interests in order to promote conversation between matched users.

[0294] "Means for identifying users in a physical store and supporting interactions between store staff and customers" refers to means for identifying users who visit a physical store and supporting smooth interactions between store staff and users.

[0295] The "means for generating topics related to the menus and services offered by the store" refers to a means for generating conversation topics based on information about the menus and services offered in the store.

[0296] The "means for generating and providing new topics according to the content of the dialogue" refers to a means for generating new appropriate topics according to the content of the ongoing dialogue and providing them to the user.

[0297] "Means for using prompt sentences to encourage dialogue in a generative AI model" refers to means for using prompt sentences to enable a generative AI model to generate appropriate responses or questions to encourage dialogue.

[0298] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[0299] 1. User registration and profile settings

[0300] User

[0301] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[0302] Terminal

[0303] Collects information entered by the user and sends it to the server.

[0304] server

[0305] The information received from the user is stored in a database.

[0306] 2. Dialogue-initiating request

[0307] User

[0308] Tap the "Start a conversation" button on the application's home screen.

[0309] Terminal

[0310] Send a conversation initiation request to the server.

[0311] server

[0312] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[0313] 3. Matching and providing topics

[0314] server

[0315] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[0316] Terminal

[0317] The received topic is displayed on the chat screen.

[0318] 4. Dialogue Progress

[0319] User

[0320] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[0321] Terminal

[0322] Sends the message entered by the user to the server.

[0323] server

[0324] The received message is forwarded to the other user's terminal.

[0325] User

[0326] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[0327] Terminal

[0328] Sends a new topic request to the server.

[0329] server

[0330] A new topic is generated and sent to the terminals of both users who performed the match.

[0331] Hardware and software used

[0332] Hardware

[0333] Server (e.g. AWS or GCP)

[0334] User's smartphone

[0335] software

[0336] Flask (Python framework)

[0337] Python

[0338] Database (e.g. PostgreSQL or MySQL)

[0339] Specific examples

[0340] User registration and profile settings

[0341] User

[0342] A visitor comes to the cafe, launches the application, and registers his name "A," age "30," gender "male," and hobby "reading."

[0343] Terminal

[0344] Send the registration information to the server.

[0345] server

[0346] The received information is stored in a database.

[0347] Interaction-initiating request

[0348] User

[0349] The user taps the "Start conversation" button.

[0350] Terminal

[0351] Send a conversation initiation request to the server.

[0352] server

[0353] Receive requests and search for other users who share the common hobby of reading.

[0354] A match is made and the matching information is sent to both users.

[0355] Generate a reading topic (e.g., "recent bestselling books") and send it to both devices.

[0356] Matching and topic provision

[0357] server

[0358] Matching and generating common topics.

[0359] The generated topic is sent to the user's terminal.

[0360] Terminal

[0361] The received topic is displayed on the chat screen.

[0362] Dialogue progress

[0363] User

[0364] Send a message saying, "Want to talk about the latest bestselling book?"

[0365] The other person replies, "Yes, please!"

[0366] Terminal

[0367] The message is sent to the server, which then forwards it to the other user's device.

[0368] User

[0369] Tap the "Request next topic" button.

[0370] Terminal

[0371] Send the request to the server.

[0372] server

[0373] Generate new topics such as "Recent Limited Drinks" and send them to both devices.

[0374] Prompt Sentence Examples

[0375] "Have you seen the latest Marvel movie?"

[0376] This system makes it easier for customers meeting for the first time in a physical store, or between customers and staff, to find common topics of conversation, allowing them to start and continue natural conversations.

[0377] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0378] Step 1:

[0379] User registration and profile settings

[0380] User

[0381] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[0382] Input: Name, age, gender, hobbies, interests

[0383] Output: Entered profile information

[0384] Terminal

[0385] Collects information entered by the user and sends it to the server.

[0386] Input: User profile information

[0387] Data processing: Convert to JSON format

[0388] Output: Data sent to the server

[0389] server

[0390] The information received from the user is stored in a database.

[0391] Input: User profile information received from the device

[0392] Data processing: Save to database

[0393] Output: Information stored in the database

[0394] Step 2:

[0395] Interaction-initiating request

[0396] User

[0397] Tap the "Start a conversation" button on the application's home screen.

[0398] Input: Dialogue-initiating request

[0399] Output: Request signal

[0400] Terminal

[0401] Send a conversation initiation request to the server.

[0402] Input: Dialogue-initiating request

[0403] Data processing: Convert to JSON format

[0404] Output: Request sent to the server

[0405] server

[0406] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[0407] Input: Dialogue-initiating request

[0408] Data operations: database lookup, search for users with common hobbies and interests, and matching

[0409] Output: Matching information

[0410] Step 3:

[0411] Matching and topic provision

[0412] server

[0413] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[0414] Input: Matching information, common hobbies, store service information

[0415] Data Computing: Creating Common Sense

[0416] Output: Generated topics

[0417] Terminal

[0418] The received topic is displayed on the chat screen.

[0419] Input: Topics received from the server

[0420] Data processing: Converting to a format that can be displayed on the chat screen

[0421] Output: Topics displayed

[0422] Step 4:

[0423] Dialogue progress

[0424] User

[0425] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[0426] Input: Provided topic

[0427] Output: The message to be sent

[0428] Terminal

[0429] Sends the message entered by the user to the server.

[0430] Input: The message entered by the user

[0431] Data processing: Convert to JSON format

[0432] Output: Message sent to the server

[0433] server

[0434] The received message is forwarded to the other user's terminal.

[0435] Input: The message sent by the user

[0436] Data processing: Identifying the destination user, forwarding messages

[0437] Output: Forwarded message

[0438] User

[0439] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[0440] Input: Next topic request

[0441] Output: Request signal

[0442] Terminal

[0443] Sends a new topic request to the server.

[0444] Input: Next topic request

[0445] Data processing: Convert to JSON format

[0446] Output: Request sent to the server

[0447] server

[0448] A new topic is generated and sent to the terminals of both users who performed the match.

[0449] Input: Next topic request

[0450] Data calculation: Generate new topics and send them to the terminal

[0451] Output: The new topics generated

[0452] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0453] An embodiment of this invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system not only provides specific topics for the user to smoothly advance a dialogue with someone they meet for the first time, but also has the function of the emotion engine analyzing the user's emotions and adjusting the content of the dialogue accordingly.

[0454] 1. User registration and profile settings

[0455] User

[0456] When a user launches the app for the first time, a registration screen appears where they can enter their name, age, gender, hobbies, and interests.

[0457] Terminal

[0458] The profile information entered by the user is sent to the server.

[0459] server

[0460] The received profile information is stored in a database.

[0461] 2. Dialogue-initiating request

[0462] User

[0463] Tap the "Start a conversation" button on the app's home screen.

[0464] Terminal

[0465] Send a conversation initiation request to the server.

[0466] server

[0467] A request to start a conversation is received, and information on other online users is obtained from a database.

[0468] Search for and match with users who share common hobbies and interests.

[0469] 3. Analysis by Emotion Engine

[0470] server

[0471] The emotion engine analyzes the profile information of the matched user and the user's initial emotions at the start of the conversation.

[0472] The emotion engine analyzes the user's emotions and selects the most appropriate topic at the start of the conversation.

[0473] 4. Matching and providing topics

[0474] server

[0475] If a match is made, matching information is sent to both users.

[0476] Based on the analysis results of the emotion engine, a topic of conversation appropriate to the user's emotions is generated.

[0477] The generated topics are sent to the devices of both matched users.

[0478] Terminal

[0479] The received topic is displayed on the chat screen.

[0480] 5. Dialogue Progress

[0481] User

[0482] Start a conversation based on the topic provided. For example, if a user likes movies, send them a message saying, "Have you seen the latest Marvel movie?"

[0483] Terminal

[0484] Sends messages sent by users to the server.

[0485] server

[0486] The received message is forwarded to the other user's terminal.

[0487] 6. Providing new topics

[0488] User

[0489] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[0490] Terminal

[0491] Sends a new topic request to the server.

[0492] server

[0493] The request is received and the emotion engine reanalyzes the current dialogue progress and emotional state.

[0494] A new topic is generated and sent to the devices of both matched users.

[0495] Specific examples

[0496] User registration and profile settings

[0497] User

[0498] Mr. Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[0499] Terminal

[0500] Send the registration information to the server.

[0501] server

[0502] The received information is stored in a database.

[0503] Interaction-initiating request

[0504] User

[0505] Tanaka taps the "Start conversation" button.

[0506] Terminal

[0507] Send a conversation initiation request to the server.

[0508] server

[0509] The request is received, other users who share the common hobby of "watching movies" are searched for, and a match is made with Sato.

[0510] Send matching information to Tanaka and Sato.

[0511] Emotion engine analysis

[0512] server

[0513] The profile information of Tanaka and Sato is analyzed using an emotion engine to evaluate their initial emotions.

[0514] Generate optimal movie-watching topics like "Recent Marvel Movies" and adjust them according to each user's emotional state.

[0515] Matching and topic provision

[0516] server

[0517] Generates topics related to movie viewing and reflects the analysis results of the emotion engine.

[0518] The generated topics are sent to Tanaka and Sato's devices.

[0519] Terminal

[0520] The received topic is displayed on the chat screen.

[0521] Dialogue progress

[0522] User

[0523] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[0524] Sato replies, "Yes, I saw it last week! What about you?"

[0525] Terminal

[0526] Messages from Tanaka and Sato are sent to their respective devices, and the contents of the conversation are updated on the server.

[0527] Providing new topics

[0528] User

[0529] While the conversation is in progress, Tanaka taps the "Request next topic" button.

[0530] Terminal

[0531] Sends a new topic request to the server.

[0532] server

[0533] The emotion engine is used again to analyze Tanaka and Sato's current emotional states and the state of their conversation.

[0534] A new topic "Recent Sporting Events" is created and sent to both devices.

[0535] This system allows people meeting for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation flowing.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] User

[0539] When a user launches the app for the first time, they are presented with a registration screen.

[0540] The user enters their name, age, gender, hobbies, and interests.

[0541] Step 2:

[0542] Terminal

[0543] The profile information entered by the user is sent to the server.

[0544] Step 3:

[0545] server

[0546] The received profile information is stored in a database.

[0547] Step 4:

[0548] User

[0549] The user taps the "Start a conversation" button on the app's home screen.

[0550] Step 5:

[0551] Terminal

[0552] Send a conversation initiation request to the server.

[0553] Step 6:

[0554] server

[0555] A request to start a conversation is received, and information on other online users is obtained from a database.

[0556] Search for and match with users who share common hobbies and interests.

[0557] Step 7:

[0558] server

[0559] Matching is performed, and the profile information of both users and their emotional data at the start of the interaction are sent to the emotion engine.

[0560] Step 8:

[0561] Emotion Engine

[0562] Profile information and initial sentiment data are analyzed to select conversation topics that are appropriate for both users.

[0563] Step 9:

[0564] server

[0565] Topics selected by the emotion engine are sent to both users.

[0566] Step 10:

[0567] Terminal

[0568] The received topic is displayed on the chat screen.

[0569] Step 11:

[0570] User

[0571] Start a conversation based on a topic provided and type a message (e.g., "Have you seen the latest Marvel movie?").

[0572] Step 12:

[0573] Terminal

[0574] Sends the message entered by the user to the server.

[0575] Step 13:

[0576] server

[0577] The received message is forwarded to the other user's terminal.

[0578] Step 14:

[0579] User

[0580] The other user receives the message and replies in the same way (e.g., "Yes, I saw it last week! How about you?").

[0581] Step 15:

[0582] Terminal

[0583] A reply message is sent to the server and forwarded to the other party's terminal.

[0584] Step 16:

[0585] User

[0586] If you need a new topic during an ongoing conversation, tap the "Request next topic" button.

[0587] Step 17:

[0588] Terminal

[0589] Sends a new topic request to the server.

[0590] Step 18:

[0591] server

[0592] After receiving the request, the emotion engine is again sent the current emotion data of both users to select a new topic.

[0593] Step 19:

[0594] Emotion Engine

[0595] Analyze the emotional state of both users and select appropriate new topics.

[0596] Step 20:

[0597] server

[0598] The newly generated topic is sent to the devices of both matched users.

[0599] Step 21:

[0600] Terminal

[0601] Display new topics on the chat screen.

[0602] In this way, the user, terminal, server, and emotion engine cooperate to advance the process at each step, ensuring smooth dialogue. Furthermore, the emotion engine analyzes the user's emotions, providing conversation topics more suited to each individual user.

[0603] Example 2

[0604] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0605] Conventional technologies have had difficulty initiating a smooth dialogue between users who have just met and providing appropriate topics to advance the dialogue. Higher accuracy is particularly required for providing topics that take the user's emotions into account. A system that can provide appropriate dialogue topics based on the user's emotions and allow the dialogue to progress naturally is needed.

[0606] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0607] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a dialogue from a user, means for searching for and matching with other users who share common hobbies and interests, means for analyzing the user's emotions using a generative AI model and providing optimal conversation topics, means for providing conversation topics to matched users, means for starting a dialogue based on the provided conversation topic and generating and providing new topics as the dialogue progresses, means for receiving an operation from the user to request the next topic, and means for generating and providing new topics based on the request. This allows for the provision of appropriate topics that take the user's emotions into consideration, enabling the dialogue to proceed smoothly.

[0608] A "user" is an individual who uses the system, registers profile information, and is involved in initiating and progressing interactions.

[0609] "Profile information" is information about a user, including data such as name, age, gender, hobbies, and interests.

[0610] A "dialogue start request" is a request sent by a user to indicate their desire to start a dialogue.

[0611] A "generative AI model" is a technology that uses artificial intelligence algorithms to analyze a user's profile information and emotions and generate optimal conversation topics.

[0612] An "emotion engine" is a combination of software or hardware for analyzing user emotions and is a system that includes a generative AI model.

[0613] "Matching" is the process of searching for other users who share common hobbies and interests and pairing them with suitable users to interact with.

[0614] A "topic" is a specific topic or theme that is generated for users to use during a conversation.

[0615] "Dialogue progression" refers to the process in which users exchange messages based on provided topics and continue the conversation.

[0616] "New topics" are additional topics or themes that are provided during the course of a conversation and are generated based on the user's emotions and the context of the conversation.

[0617] A "request" is an operation performed by a user to find the next topic and the request.

[0618] This invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system provides specific topics to help the user smoothly advance a dialogue with someone they meet for the first time, and the emotion engine has the function of analyzing the user's emotions and adjusting the content of the dialogue.

[0619] First, the user installs and launches the application. When the user launches the app for the first time, a registration screen appears where the user enters profile information such as name, age, gender, hobbies, and interests. The device encodes the profile information entered by the user into a data packet and sends it to the server. The server deserializes the received profile information and stores it in a database such as MySQL.

[0620] Next, when the user taps the "Start conversation" button on the application's home screen, the device generates a data packet for a conversation start request and sends it to the server. When the server receives the request, it searches its database for other users who share common hobbies and interests and performs matching. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[0621] The server passes the profile information of the matched users to an emotion engine (for example, IBM Watson emotion analysis API) to begin analysis. The emotion engine generates a prompt, which includes a format such as "User A's profile is..., User B's profile is..., please suggest a common topic." The emotion engine analyzes the user's emotions and profile information and provides the most appropriate conversation topic.

[0622] The generated topics are notified to both users by the server. The devices display the received topics on the chat screen, and users can start a conversation based on the provided topics. For example, a user can send a message saying, "Have you seen the latest Marvel movie?" The device converts this message into a data packet and sends it to the server. The server receives the message and forwards it to the other user's device.

[0623] If a new topic is needed as the conversation progresses, the user taps the "Request next topic" button. The device sends a request for a new topic to the server, and the server again generates and sends a prompt to the emotion engine. The emotion engine reanalyzes the progress and emotional state of the current conversation and generates a new topic. For example, it suggests a topic about "recent sporting events," and the server notifies both users of the new topic.

[0624] This system allows people who meet for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation moving smoothly. As a concrete example, the following prompt sentence is used:

[0625] "Generate a new conversation topic. User A's emotion is 'excited', and User B's emotion is 'calm'. They both like watching movies."

[0626] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0627] Step 1:

[0628] User registers profile information

[0629] Users launch the application and enter their profile information, including name, age, gender, hobbies and interests.

[0630] Input: Profile information entered by the user (name, age, gender, hobbies, interests)

[0631] Output: The profile information you entered is encoded into a data packet and ready to be sent.

[0632] Step 2:

[0633] The device sends profile information to the server

[0634] The terminal encodes the profile information entered by the user into a data packet and transmits it to the server.

[0635] Input: Profile information entered by the user

[0636] Output: Information is encoded and sent as a data packet to the server

[0637] Step 3:

[0638] The server stores the profile information in a database

[0639] The server deserializes the received data packet and stores it in a database such as MySQL. For example, it executes the query "INSERT INTO users (name, age, gender, hobbies, interests) VALUES ('Tanaka', 30, 'Male', 'Watching Movies', 'Watching Sports');".

[0640] Input: User profile information contained in the data packet

[0641] Output: The user profile is saved in the database.

[0642] Step 4:

[0643] The user sends a conversation-initiating request

[0644] The user taps the "Start a conversation" button on the application's home screen.

[0645] Input: User taps

[0646] Output: A conversation-initiating request is generated

[0647] Step 5:

[0648] The device sends a conversation start request to the server.

[0649] The terminal generates a data packet for a dialogue initiation request and transmits it to the server.

[0650] Input: Dialogue-initiating request

[0651] Output: A conversation initiation request is sent to the server

[0652] Step 6:

[0653] The server does the matching

[0654] The server receives the request to start a conversation and searches the database for other online users who share the same hobbies and interests. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[0655] Input: Interaction start request, user profile information

[0656] Output: Matched users

[0657] Step 7:

[0658] The server passes the matched user's information to the emotion engine.

[0659] The server passes the profile information of the matched users to the emotion engine and begins analysis. The prompt text includes something like, "User A's profile is..., User B's profile is..., please suggest common topics."

[0660] Input: Profile information of the matched user

[0661] Output: A prompt is generated and sent to the emotion engine.

[0662] Step 8:

[0663] Emotion engine generates topics

[0664] The emotion engine receives the prompt, analyzes the user's emotions and profile information, and generates the most appropriate conversation topic, for example, selecting the topic "recent Marvel movies."

[0665] Input: prompt sentence, user's emotional information

[0666] Output: Generated topics

[0667] Step 9:

[0668] The server notifies the user of the generated topic

[0669] The server notifies both users of the generated topic. A message such as "The topic is 'Recent Marvel Movies'" is sent to both users A and B's devices.

[0670] Input: Generated topics, matching user information

[0671] Output: The topic is notified to the user's terminal.

[0672] Step 10:

[0673] Display topics received by the device

[0674] The device displays the received topics on the chat screen, and users can start a conversation based on this.

[0675] Input: Received topics

[0676] Output: Topics are displayed on the chat screen.

[0677] Step 11:

[0678] The user initiates the interaction

[0679] Users start a conversation based on the provided topic. For example, User A types and sends a message saying, "Have you seen the latest Marvel movie?"

[0680] Input: User message input

[0681] Output: Message is ready to be sent

[0682] Step 12:

[0683] The device sends a message to the server

[0684] The terminal converts the message entered by the user into a data packet and sends it to the server.

[0685] Input: User's message

[0686] Output: The message is sent to the server

[0687] Step 13:

[0688] The server receives and forwards the message

[0689] The server deserializes the received message and forwards it to the other user's device.

[0690] Input: User's message

[0691] Output: The message is forwarded to the other user's device.

[0692] Step 14:

[0693] A user requests a new topic

[0694] While a conversation is in progress, the user taps the "Request next topic" button.

[0695] Input: User taps

[0696] Output: A data packet is generated requesting the next topic.

[0697] Step 15:

[0698] The device sends a request for new topics to the server.

[0699] The device sends a request for a new topic to the server.

[0700] Input: New topic request

[0701] Output: Request data is sent to the server

[0702] Step 16:

[0703] The server creates a new topic

[0704] The server receives the request and again generates and sends a prompt to the emotion engine, which reanalyzes the current dialogue progress and emotional state and generates a new topic, for example, suggesting a topic about "recent sporting events."

[0705] Input: New topic requests, current conversation progress and sentiment information

[0706] Output: New topic

[0707] Step 17:

[0708] The server notifies the user of new topics

[0709] The server notifies both users of the newly created topic.

[0710] Input: New topic

[0711] Output: A new topic is notified to the user's device.

[0712] Step 18:

[0713] The device displays new topics

[0714] The terminal displays the newly received topic on the chat screen, allowing the users to continue the conversation on the new topic.

[0715] Input: Newly received topic

[0716] Output: A new topic appears on the chat screen.

[0717] Through the above steps, the dialogue support system of the present invention functions, allowing users to smoothly advance their dialogue with each other.

[0718] (Application example 2)

[0719] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0720] In conventional dialogue systems, dialogue between users often does not proceed smoothly, and there are psychological barriers, especially when communicating with people who meet for the first time. This makes it difficult for users to naturally find common topics and have enjoyable conversations. Furthermore, there is a problem that appropriate new topics cannot be offered during the dialogue, causing the conversation to stall.

[0721] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a dialogue start request from a user, means for searching for and matching other users with common hobbies and interests, means for analyzing the user's emotions with an emotion engine and adjusting the content of the dialogue, means for providing a topic of dialogue based on the emotion analysis results, means for starting a dialogue based on the provided topic of dialogue, reanalyzing the emotion engine as the dialogue progresses, and generating and providing a new topic, means for accepting an operation to request the next topic from the user, and means for reanalyzing the emotion engine based on the request, generating and providing a new topic. This enables users to naturally find common topics and enjoyably advance the dialogue.

[0722] A "user" is a person who uses the system to register profile information and initiate a dialogue.

[0723] "Profile information" is personal information related to a user, such as the user's name, age, gender, and hobbies.

[0724] The "emotion engine" is a function within the system that analyzes the user's emotions and adjusts the content of the dialogue based on the results.

[0725] A "dialogue start request" is a request that a user sends to the server in order to use the system to start a dialogue with someone they have met for the first time.

[0726] "Matching" is the process of connecting users with common hobbies and interests on the system.

[0727] A "topic of conversation" is a specific topic that the system provides to the user to facilitate the conversation.

[0728] "Reanalysis" is the process by which the emotion engine reevaluates the current emotional state as the conversation progresses and generates new topics as needed.

[0729] "New topics" are additional topics that the emotion engine generates and provides as the conversation progresses.

[0730] A "request" is an operation by the user to ask the system to provide the next topic.

[0731] The "server" is the core computer of the system that stores user profile information and processes dialogue initiation requests, matching, and sentiment analysis.

[0732] The embodiment of the present invention is a system mainly composed of three elements: a server, a terminal, and a user. A specific implementation method is shown below.

[0733] 1. User registration and profile settings

[0734] First, a user launches the app using their smartphone and enters profile information such as name, age, gender, hobbies, etc. on the registration screen. This profile information is sent by the device to the server, which then stores the received information in a database.

[0735] 2. Dialogue-initiating request

[0736] When a user taps the "Start a conversation" button, the device sends a conversation start request to the server, which receives the request, retrieves information about other online users with common hobbies and interests from its database, and performs matching.

[0737] 3. Analysis by Emotion Engine

[0738] If a match is made, the server analyzes the matched user's profile information using an emotion engine to evaluate the initial emotion at the start of the conversation. The emotion engine analyzes emotions using the EmotionEngine library and selects the most appropriate topic based on the results.

[0739] 4. Matching and providing topics

[0740] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics.

[0741] 5. Promoting dialogue and providing new topics

[0742] As the conversation progresses, if the user taps the "Request next topic" button, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the progress and emotional state of the current conversation using its emotion engine. As a result, it generates a new topic and provides it to the devices of both matched users.

[0743] Specific examples

[0744] The user enters their name, age, gender, and hobbies to register their profile information. The prompt to the generative AI model is "Please enter your name, age, gender, and hobbies." When the user taps the "Start conversation" button, a request to start a conversation is sent to the server. The emotion engine performs an analysis, selects the most appropriate topic, and sends it to the matched user's device. The prompt to the generative AI model is "Sending a request to start a conversation." When the "Request next topic" button is tapped while the conversation is in progress, the emotion engine reanalyzes, generates a new topic, and provides it. The prompt to the generative AI model is "Reanalyze the current conversation situation and emotional state, and provide a new topic."

[0745] This system utilizes smartphones and the EmotionEngine library to help users smoothly engage in conversations with people they meet for the first time.

[0746] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0747] Step 1:

[0748] A user starts the app on their smartphone and enters profile information such as name, age, gender, and hobbies on the registration screen. The entered information is sent to the server by the device. The server then stores the user's profile information in a database. The input is the user's profile information, and the output is the profile information stored in the database.

[0749] Step 2:

[0750] The user taps the "Start conversation" button. This sends a conversation start request from the device to the server. The server receives this request, retrieves information about other online users from a database, searches for users with common hobbies and interests, and performs matching. The input is the conversation start request and the user information in the database, and the output is the matching results.

[0751] Step 3:

[0752] Once a match is made, the server analyzes the profile information of the matched user using an emotion engine. The emotion engine uses the EmotionEngine library to analyze the user's emotions and evaluate their initial emotions. This allows the optimal topic to be selected at the start of the conversation. The input is the profile information of the matched user, and the output is the analysis results of the emotion engine and the selected topic.

[0753] Step 4:

[0754] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics. The input is the analysis results of the emotion engine and the selected topics, and the output is the topics displayed on the devices.

[0755] Step 5:

[0756] When a user taps the "Request next topic" button while a conversation is in progress, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the current conversation status and emotional state using its emotion engine. Based on this, a new topic is generated and sent to the devices of both matched users. The input is the request for a new topic and the current conversation status and emotional state, and the output is the reanalyzed new topic.

[0757] In this way, the system facilitates dialogue between users and supports the flow of the dialogue by providing appropriate topics through the emotion engine.

[0758] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0759] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0760] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0761] [Second embodiment]

[0762] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0763] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0764] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0765] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0766] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0767] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0768] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0769] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0770] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0771] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0772] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0773] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0774] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[0775] 1. User registration and profile settings

[0776] User

[0777] When a user launches the app for the first time, a registration screen will appear.

[0778] Users enter their name, age, gender, hobbies, and interests.

[0779] Terminal

[0780] Collects information entered by the user and sends it to the server.

[0781] server

[0782] The information received from the user is stored in a database.

[0783] 2. Dialogue-initiating request

[0784] User

[0785] Tap the "Start a conversation" button on the app's home screen.

[0786] Terminal

[0787] Send a conversation initiation request to the server.

[0788] server

[0789] A request is received to retrieve information about other online users from a database.

[0790] Search for and match with users who share common hobbies and interests.

[0791] 3. Matching and providing topics

[0792] server

[0793] If a match is made, matching information is sent to both users.

[0794] Generate topics based on common interests or the latest news articles.

[0795] The generated topics are sent to the devices of both matched users.

[0796] Terminal

[0797] The received topic is displayed on the chat screen.

[0798] 4. Dialogue Progress

[0799] User

[0800] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[0801] Terminal

[0802] Sends the message entered by the user to the server.

[0803] server

[0804] The received message is forwarded to the other user's terminal.

[0805] User

[0806] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[0807] Terminal

[0808] Sends a new topic request to the server.

[0809] server

[0810] A new topic is generated and sent to the terminals of both users who performed the match.

[0811] Specific examples

[0812] User registration and profile settings

[0813] User

[0814] Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[0815] Terminal

[0816] Send the registration information to the server.

[0817] server

[0818] The received information is stored in a database.

[0819] Interaction-initiating request

[0820] User

[0821] Tanaka taps the "Start conversation" button.

[0822] Terminal

[0823] Send a conversation initiation request to the server.

[0824] server

[0825] Receives a request and searches for other users who share the common hobby of "watching movies."

[0826] Match with Sato-san.

[0827] Send matching information to Tanaka and Sato.

[0828] Generate a topic related to watching movies (e.g., "recent Marvel movies") and send it to both devices.

[0829] Matching and topic provision

[0830] server

[0831] Generate topics related to watching movies.

[0832] The generated topics are sent to Tanaka and Sato's devices.

[0833] Terminal

[0834] The received topic is displayed on the chat screen.

[0835] Dialogue progress

[0836] User

[0837] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[0838] Sato replies, "Yes, I saw it last week! What about you?"

[0839] Terminal

[0840] Each message is sent to the server, which then forwards it to the other user's terminal.

[0841] User

[0842] Tanaka taps the "Request next topic" button.

[0843] Terminal

[0844] Send Tanaka's request to the server.

[0845] server

[0846] A new topic "Recent Sporting Events" is created and sent to Tanaka and Sato.

[0847] This system allows people meeting for the first time to naturally find common topics and start a conversation, and by offering new topics as the conversation progresses, it keeps the conversation flowing.

[0848] The processing flow will be explained below.

[0849] Step 1:

[0850] User

[0851] When a user launches the app for the first time, they are presented with a registration screen.

[0852] The user enters their name, age, gender, hobbies, and interests.

[0853] Step 2:

[0854] Terminal

[0855] The profile information entered by the user is sent to the server.

[0856] Step 3:

[0857] server

[0858] The received profile information is stored in a database.

[0859] Step 4:

[0860] User

[0861] The user taps the "Start a conversation" button on the app's home screen.

[0862] Step 5:

[0863] Terminal

[0864] Send a conversation initiation request to the server.

[0865] Step 6:

[0866] server

[0867] A request to start a conversation is received, and information on other online users is obtained from a database.

[0868] Search for and match with users who share common hobbies and interests.

[0869] Step 7:

[0870] server

[0871] If a match is made, matching information is sent to both users.

[0872] Generate conversation topics based on common interests or the latest news stories.

[0873] Step 8:

[0874] server

[0875] The generated topics are sent to the devices of both matched users.

[0876] Step 9:

[0877] Terminal

[0878] The received topic is displayed on the chat screen.

[0879] Step 10:

[0880] User

[0881] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[0882] Step 11:

[0883] Terminal

[0884] Sends messages sent by users to the server.

[0885] Step 12:

[0886] server

[0887] The received message is forwarded to the other user's terminal.

[0888] Step 13:

[0889] User

[0890] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[0891] Step 14:

[0892] Terminal

[0893] Sends a new topic request to the server.

[0894] Step 15:

[0895] server

[0896] A new topic is generated and sent to the devices of both matched users.

[0897] Example 1

[0898] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0899] In today's online communication environment, it is difficult for users who meet for the first time to naturally progress a conversation. In particular, if they cannot find a common topic, the conversation tends to stall. To solve this problem, a system is needed that matches users based on common hobbies and interests and provides appropriate topics. Furthermore, it is desirable to provide new topics in a timely manner while the conversation is in progress, ensuring uninterrupted communication.

[0900] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0901] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for generating conversation topics based on common hobbies and recent topics using a generative AI model, means for providing conversation topics to matched users, and means for transmitting the matching information and the generated conversation topics to a user terminal. This enables users to naturally find common topics and start a conversation, and to provide new topics as the conversation progresses.

[0902] "User" refers to an individual user of the system.

[0903] "Profile information" refers to personal information such as name, age, gender, hobbies, and interests that a user registers in the system.

[0904] "Database" refers to a storage device and its management system for storing user profile information and other data.

[0905] A "dialogue initiation request" refers to a request sent by a user to begin a dialogue.

[0906] "Matching" refers to the process of connecting users who share common hobbies or interests.

[0907] "Generative AI model" refers to a software model that uses artificial intelligence to generate conversation topics based on shared interests and current topics.

[0908] "Topics" refer to themes or topics related to common interests or the latest news that are generated by the server to encourage dialogue between users.

[0909] "Matching information" refers to data containing information about users who have been matched.

[0910] "User terminal" refers to an electronic device (e.g., smartphone, tablet, computer) used by a user to access the system.

[0911] "Means for receiving" refers to the functions and processes for receiving data from a user.

[0912] "Transmitting means" refers to the functions or processes for sending data to other devices or systems.

[0913] "Storage means" refers to the functions and processes for retaining data for long periods of time.

[0914] "New topics" refer to new themes or topics that are presented as the dialogue progresses.

[0915] The system for implementing this invention stores profile information registered by users, matches users with other users who share common hobbies and interests, and provides appropriate topics of conversation to facilitate smooth dialogue. In a specific implementation, the server, terminals, and users each have different roles and work together to form the system.

[0916] 1. User registration and profile settings

[0917] User

[0918] When a user launches the app, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[0919] Terminal

[0920] The terminal collects the profile information entered by the user, encrypts it, and transmits it to the server.

[0921] server

[0922] The server stores the received profile information in a database, such as MySQL.

[0923] Examples:

[0924] Tanaka uses the app to enter and submit her profile information.

[0925] 2. Dialogue-initiating request

[0926] User

[0927] The user taps the "Start a conversation" button on the app's home screen.

[0928] Terminal

[0929] The terminal sends a dialogue start request to the server in real time.

[0930] server

[0931] The server receives the request, retrieves information about other online users from a database, and matches users together based on common interests.

[0932] Examples:

[0933] Tanaka taps the "Start conversation" button, a request to start a conversation is sent to the server, and the server matches him with Sato.

[0934] 3. Matching and providing topics

[0935] server

[0936] The server uses a generative AI model to generate conversation topics based on common interests and the latest news, for example using the OpenAI GPT series.

[0937] The generated topics are sent to the devices of both matched users.

[0938] Terminal

[0939] The device displays the received topics on the chat screen.

[0940] Examples:

[0941] The server generates a topic about "recent Marvel movies" and sends it to Tanaka and Sato's devices, which then display it on their chat screens.

[0942] 4. Dialogue Progress

[0943] User

[0944] The user enters a message based on the provided topic and starts a conversation.

[0945] Terminal

[0946] The terminal sends the message entered by the user to the server, which then forwards it to the other user's terminal.

[0947] server

[0948] As the conversation progresses, if the user taps the "Request next topic" button, a new topic will be generated and sent to the user's device again.

[0949] Examples:

[0950] Tanaka sends a message asking, "Have you seen the latest Marvel movie?", to which Sato replies, "Yes, I saw it last week! How about you?"

[0951] Tanaka taps the "Request next topic" button, and the server generates a new topic about "recent sporting events" and sends it to both devices.

[0952] Example prompt sentence:

[0953] "Start conversations with other users who share your interests, and if you match, offer topics based on those interests."

[0954] By implementing this invention, the system allows users to naturally find common topics and start a conversation, and new topics can be suggested as the conversation progresses. This system provides powerful support for smooth communication between people meeting for the first time.

[0955] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0956] Step 1: The user launches the app and is presented with a registration screen.

[0957] Input: The user launches the app for the first time.

[0958] Output: The registration screen is displayed.

[0959] Specific operation: When a user launches the app for the first time, the device checks the first-time launch flag built into the system. At first launch, the registration screen is displayed to the user.

[0960] Step 2: User enters required information

[0961] Input: The user enters their name, age, gender, hobbies, and interests on the registration screen.

[0962] Output: The information entered by the user.

[0963] Specific operation: The user enters their name, age, gender, hobbies, and interests in the fields displayed on the app's registration screen. For example, they might enter "Name: Tanaka, Age: 30, Gender: Male, Hobbies: Watching movies and sports."

[0964] Step 3: The device sends the entered information to the server

[0965] Input: Profile information entered by the user.

[0966] Output: Encrypted user information sent from the device to the server.

[0967] How it works: The device collects and encrypts the information entered by the user in real time, then sends the encrypted data to the server.

[0968] Step 4: The server receives the information and stores it in a database

[0969] Input: Encrypted user information sent from the device.

[0970] Output: User profile information stored in a database.

[0971] What happens: The server receives the encrypted data, decrypts it, verifies the information received, checks its integrity, and then stores it in a secure database (e.g., MySQL).

[0972] Step 5: User taps the "Start conversation" button

[0973] Input: A request from the user to initiate a conversation.

[0974] Output: A conversation initiation request.

[0975] What happens: The user finds the "Start a conversation" button on the app's home screen and taps it, which generates a conversation start request.

[0976] Step 6: The device sends a conversation start request to the server

[0977] Input: A request from the user to initiate a conversation.

[0978] Output: The conversation initiation request sent to the server.

[0979] Specific operation: The device sends a request to start a conversation tapped by the user to the server in real time.

[0980] Step 7: The server receives the request and retrieves other user information

[0981] Input: A conversation initiation request sent from the device.

[0982] Output: Information about other users with common hobbies and interests.

[0983] Specific operation: When the server receives a request to start a conversation, it retrieves information about other online users from the database, and then searches for matches based on common hobbies and interests.

[0984] Step 8: The server matches users based on common interests.

[0985] Input: Other user information obtained.

[0986] Output: The combination of users who matched.

[0987] Specific operation: The server analyzes the acquired information of other users and matches users with common hobbies and interests. For example, Tanaka and Sato, who share the hobby of "watching movies," are matched.

[0988] Step 9: The server generates a conversation topic using the generative AI model.

[0989] Input: Common interests and latest news information of matched users.

[0990] Output: The generated conversation topics.

[0991] How it works: The server uses a generative AI model (such as the OpenAI GPT series) to generate conversation topics based on shared interests and the latest news. For example, the topic "Recent Marvel Movies" might be generated.

[0992] Step 10: The server sends the conversation topic to the matching user's device.

[0993] Input: The topic of the generated conversation.

[0994] Output: Topics sent to the matched users' devices.

[0995] Specific operation: The server sends the generated conversation topic to the matched users' devices. For example, the topic of "recent Marvel movies" is sent to Tanaka and Sato's devices.

[0996] Step 11: Display the topic received by the device on the chat screen

[0997] Input: The conversation topic sent by the server.

[0998] Output: Topics displayed on the chat screen.

[0999] Specific operation: The device will display the received topic on the chat screen. For example, "Recent Marvel movies" will be displayed on the chat screen.

[1000] Step 12: The user types a message based on the provided topic and starts the conversation.

[1001] Input: Topics displayed on the chat screen.

[1002] Output: The message entered by the user.

[1003] Specific operation: The user starts a conversation by typing a message based on the topic displayed on the chat screen. For example, Tanaka types and sends a message saying, "Have you seen the latest Marvel movie?"

[1004] Step 13: The device sends a message to the server, which forwards it to the other user's device.

[1005] Input: The message entered by the user.

[1006] Output: The message forwarded to the other user's device.

[1007] Specific operation: The device sends the message entered by the user to the server, and the server forwards the message to the other user's device. For example, Tanaka's message "Have you seen the latest Marvel movie?" is forwarded to Sato's device.

[1008] Step 14: User taps the "Request next topic" button

[1009] Input: A user's request for a new topic.

[1010] Output: Next topic request.

[1011] What it does: When a user taps the "Request next topic" button, a request is made for a new topic. For example, Tanaka taps this button to rekindle the conversation.

[1012] Step 15: The device sends a new topic request to the server

[1013] Input: A new topic request from a user.

[1014] Output: New topic request sent to the server.

[1015] Specific operation: The terminal sends requests for new topics from the user to the server in real time.

[1016] Step 16: The server generates a new topic and sends it to the matching user's device.

[1017] Input: New topic request.

[1018] Output: The new topics generated.

[1019] Specific operation: The server generates a new topic and sends it to the devices of the matched users. For example, the server generates a topic about "recent sporting events" and sends it to the devices of Tanaka and Sato.

[1020] In this way, the system receives specific input at each step, processes and calculates the data, and links the output to the next step, allowing users to smoothly advance their dialogue.

[1021] (Application example 1)

[1022] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1023] Conventional conversation support systems lacked an appropriate mechanism for promoting conversations between visitors and staff in physical stores. They also had difficulty providing specific topics related to store-specific menus and services. This resulted in problems such as first-time customers feeling uncomfortable in the store, which did not contribute to improving the store experience.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1025] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for providing conversation topics to matched users, means for identifying users in a physical store and supporting conversations between store staff and customers, means for generating topics related to menus and services offered by the store, means for generating and providing new topics according to the content of the conversation, and means for using prompt sentences to prompt the generative AI model to promote the conversation.This makes it easier for customers who meet for the first time in a physical store, or between customers and staff, to find common topics, enabling natural conversations to be started and continued.

[1026] The "means for receiving profile information registered by a user" refers to the means by which the system receives information such as name, age, gender, hobbies, and interests that a user inputs through an application.

[1027] The "means for saving user profile information in a database" refers to a means for storing received user profile information in a database so that it can be referenced later.

[1028] The "means for receiving a dialogue start request from a user" refers to the means by which the system receives a request when a user wishes to start a dialogue.

[1029] "Means for searching for and matching with other users who share common hobbies and interests" refers to a means for searching for other users who share common hobbies and interests based on the received user profile information, and selecting those users as conversation partners.

[1030] The "means for providing conversation topics to matched users" refers to a means for generating and providing topics based on common hobbies and interests in order to promote conversation between matched users.

[1031] "Means for identifying users in a physical store and supporting interactions between store staff and customers" refers to means for identifying users who visit a physical store and supporting smooth interactions between store staff and users.

[1032] The "means for generating topics related to the menus and services offered by the store" refers to a means for generating conversation topics based on information about the menus and services offered in the store.

[1033] The "means for generating and providing new topics according to the content of the dialogue" refers to a means for generating new appropriate topics according to the content of the ongoing dialogue and providing them to the user.

[1034] "Means for using prompt sentences to encourage dialogue in a generative AI model" refers to means for using prompt sentences to enable a generative AI model to generate appropriate responses or questions to encourage dialogue.

[1035] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[1036] 1. User registration and profile settings

[1037] User

[1038] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[1039] Terminal

[1040] Collects information entered by the user and sends it to the server.

[1041] server

[1042] The information received from the user is stored in a database.

[1043] 2. Dialogue-initiating request

[1044] User

[1045] Tap the "Start a conversation" button on the application's home screen.

[1046] Terminal

[1047] Send a conversation initiation request to the server.

[1048] server

[1049] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[1050] 3. Matching and providing topics

[1051] server

[1052] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[1053] Terminal

[1054] The received topic is displayed on the chat screen.

[1055] 4. Dialogue Progress

[1056] User

[1057] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[1058] Terminal

[1059] Sends the message entered by the user to the server.

[1060] server

[1061] The received message is forwarded to the other user's terminal.

[1062] User

[1063] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[1064] Terminal

[1065] Sends a new topic request to the server.

[1066] server

[1067] A new topic is generated and sent to the terminals of both users who performed the match.

[1068] Hardware and software used

[1069] Hardware

[1070] Server (e.g. AWS or GCP)

[1071] User's smartphone

[1072] software

[1073] Flask (Python framework)

[1074] Python

[1075] Database (e.g. PostgreSQL or MySQL)

[1076] Specific examples

[1077] User registration and profile settings

[1078] User

[1079] A visitor comes to the cafe, launches the application, and registers his name "A," age "30," gender "male," and hobby "reading."

[1080] Terminal

[1081] Send the registration information to the server.

[1082] server

[1083] The received information is stored in a database.

[1084] Interaction-initiating request

[1085] User

[1086] The user taps the "Start conversation" button.

[1087] Terminal

[1088] Send a conversation initiation request to the server.

[1089] server

[1090] Receive requests and search for other users who share the common hobby of reading.

[1091] A match is made and the matching information is sent to both users.

[1092] Generate a reading topic (e.g., "recent bestselling books") and send it to both devices.

[1093] Matching and topic provision

[1094] server

[1095] Matching and generating common topics.

[1096] The generated topic is sent to the user's terminal.

[1097] Terminal

[1098] The received topic is displayed on the chat screen.

[1099] Dialogue progress

[1100] User

[1101] Send a message saying, "Want to talk about the latest bestselling book?"

[1102] The other person replies, "Yes, please!"

[1103] Terminal

[1104] The message is sent to the server, which then forwards it to the other user's device.

[1105] User

[1106] Tap the "Request next topic" button.

[1107] Terminal

[1108] Send the request to the server.

[1109] server

[1110] Generate new topics such as "Recent Limited Drinks" and send them to both devices.

[1111] Prompt Sentence Examples

[1112] "Have you seen the latest Marvel movie?"

[1113] This system makes it easier for customers meeting for the first time in a physical store, or between customers and staff, to find common topics of conversation, allowing them to start and continue natural conversations.

[1114] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1115] Step 1:

[1116] User registration and profile settings

[1117] User

[1118] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[1119] Input: Name, age, gender, hobbies, interests

[1120] Output: Entered profile information

[1121] Terminal

[1122] Collects information entered by the user and sends it to the server.

[1123] Input: User profile information

[1124] Data processing: Convert to JSON format

[1125] Output: Data sent to the server

[1126] server

[1127] The information received from the user is stored in a database.

[1128] Input: User profile information received from the device

[1129] Data processing: Save to database

[1130] Output: Information stored in the database

[1131] Step 2:

[1132] Interaction-initiating request

[1133] User

[1134] Tap the "Start a conversation" button on the application's home screen.

[1135] Input: Dialogue-initiating request

[1136] Output: Request signal

[1137] Terminal

[1138] Send a conversation initiation request to the server.

[1139] Input: Dialogue-initiating request

[1140] Data processing: Convert to JSON format

[1141] Output: Request sent to the server

[1142] server

[1143] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[1144] Input: Dialogue-initiating request

[1145] Data operations: database lookup, search for users with common hobbies and interests, and matching

[1146] Output: Matching information

[1147] Step 3:

[1148] Matching and topic provision

[1149] server

[1150] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[1151] Input: Matching information, common hobbies, store service information

[1152] Data Computing: Creating Common Sense

[1153] Output: Generated topics

[1154] Terminal

[1155] The received topic is displayed on the chat screen.

[1156] Input: Topics received from the server

[1157] Data processing: Converting to a format that can be displayed on the chat screen

[1158] Output: Topics displayed

[1159] Step 4:

[1160] Dialogue progress

[1161] User

[1162] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[1163] Input: Provided topic

[1164] Output: The message to be sent

[1165] Terminal

[1166] Sends the message entered by the user to the server.

[1167] Input: The message entered by the user

[1168] Data processing: Convert to JSON format

[1169] Output: Message sent to the server

[1170] server

[1171] The received message is forwarded to the other user's terminal.

[1172] Input: The message sent by the user

[1173] Data processing: Identifying the destination user, forwarding messages

[1174] Output: Forwarded message

[1175] User

[1176] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[1177] Input: Next topic request

[1178] Output: Request signal

[1179] Terminal

[1180] Sends a new topic request to the server.

[1181] Input: Next topic request

[1182] Data processing: Convert to JSON format

[1183] Output: Request sent to the server

[1184] server

[1185] A new topic is generated and sent to the terminals of both users who performed the match.

[1186] Input: Next topic request

[1187] Data calculation: Generate new topics and send them to the terminal

[1188] Output: The new topics generated

[1189] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1190] An embodiment of this invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system not only provides specific topics for the user to smoothly advance a dialogue with someone they meet for the first time, but also has the function of the emotion engine analyzing the user's emotions and adjusting the content of the dialogue accordingly.

[1191] 1. User registration and profile settings

[1192] User

[1193] When a user launches the app for the first time, a registration screen appears where they can enter their name, age, gender, hobbies, and interests.

[1194] Terminal

[1195] The profile information entered by the user is sent to the server.

[1196] server

[1197] The received profile information is stored in a database.

[1198] 2. Dialogue-initiating request

[1199] User

[1200] Tap the "Start a conversation" button on the app's home screen.

[1201] Terminal

[1202] Send a conversation initiation request to the server.

[1203] server

[1204] A request to start a conversation is received, and information on other online users is obtained from a database.

[1205] Search for and match with users who share common hobbies and interests.

[1206] 3. Analysis by Emotion Engine

[1207] server

[1208] The emotion engine analyzes the profile information of the matched user and the user's initial emotions at the start of the conversation.

[1209] The emotion engine analyzes the user's emotions and selects the most appropriate topic at the start of the conversation.

[1210] 4. Matching and providing topics

[1211] server

[1212] If a match is made, matching information is sent to both users.

[1213] Based on the analysis results of the emotion engine, a topic of conversation appropriate to the user's emotions is generated.

[1214] The generated topics are sent to the devices of both matched users.

[1215] Terminal

[1216] The received topic is displayed on the chat screen.

[1217] 5. Dialogue Progress

[1218] User

[1219] Start a conversation based on the topic provided. For example, if a user likes movies, send them a message saying, "Have you seen the latest Marvel movie?"

[1220] Terminal

[1221] Sends messages sent by users to the server.

[1222] server

[1223] The received message is forwarded to the other user's terminal.

[1224] 6. Providing new topics

[1225] User

[1226] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[1227] Terminal

[1228] Sends a new topic request to the server.

[1229] server

[1230] The request is received and the emotion engine reanalyzes the current dialogue progress and emotional state.

[1231] A new topic is generated and sent to the devices of both matched users.

[1232] Specific examples

[1233] User registration and profile settings

[1234] User

[1235] Mr. Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[1236] Terminal

[1237] Send the registration information to the server.

[1238] server

[1239] The received information is stored in a database.

[1240] Interaction-initiating request

[1241] User

[1242] Tanaka taps the "Start conversation" button.

[1243] Terminal

[1244] Send a conversation initiation request to the server.

[1245] server

[1246] The request is received, other users who share the common hobby of "watching movies" are searched for, and a match is made with Sato.

[1247] Send matching information to Tanaka and Sato.

[1248] Emotion engine analysis

[1249] server

[1250] The profile information of Tanaka and Sato is analyzed using an emotion engine to evaluate their initial emotions.

[1251] Generate optimal movie-watching topics like "Recent Marvel Movies" and adjust them according to each user's emotional state.

[1252] Matching and topic provision

[1253] server

[1254] Generates topics related to movie viewing and reflects the analysis results of the emotion engine.

[1255] The generated topics are sent to Tanaka and Sato's devices.

[1256] Terminal

[1257] The received topic is displayed on the chat screen.

[1258] Dialogue progress

[1259] User

[1260] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[1261] Sato replies, "Yes, I saw it last week! What about you?"

[1262] Terminal

[1263] Messages from Tanaka and Sato are sent to their respective devices, and the contents of the conversation are updated on the server.

[1264] Providing new topics

[1265] User

[1266] While the conversation is in progress, Tanaka taps the "Request next topic" button.

[1267] Terminal

[1268] Sends a new topic request to the server.

[1269] server

[1270] The emotion engine is used again to analyze Tanaka and Sato's current emotional states and the state of their conversation.

[1271] A new topic "Recent Sporting Events" is created and sent to both devices.

[1272] This system allows people meeting for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation flowing.

[1273] The processing flow will be explained below.

[1274] Step 1:

[1275] User

[1276] When a user launches the app for the first time, they are presented with a registration screen.

[1277] The user enters their name, age, gender, hobbies, and interests.

[1278] Step 2:

[1279] Terminal

[1280] The profile information entered by the user is sent to the server.

[1281] Step 3:

[1282] server

[1283] The received profile information is stored in a database.

[1284] Step 4:

[1285] User

[1286] The user taps the "Start a conversation" button on the app's home screen.

[1287] Step 5:

[1288] Terminal

[1289] Send a conversation initiation request to the server.

[1290] Step 6:

[1291] server

[1292] A request to start a conversation is received, and information on other online users is obtained from a database.

[1293] Search for and match with users who share common hobbies and interests.

[1294] Step 7:

[1295] server

[1296] Matching is performed, and the profile information of both users and their emotional data at the start of the interaction are sent to the emotion engine.

[1297] Step 8:

[1298] Emotion Engine

[1299] Profile information and initial sentiment data are analyzed to select conversation topics that are appropriate for both users.

[1300] Step 9:

[1301] server

[1302] Topics selected by the emotion engine are sent to both users.

[1303] Step 10:

[1304] Terminal

[1305] The received topic is displayed on the chat screen.

[1306] Step 11:

[1307] User

[1308] Start a conversation based on a topic provided and type a message (e.g., "Have you seen the latest Marvel movie?").

[1309] Step 12:

[1310] Terminal

[1311] Sends the message entered by the user to the server.

[1312] Step 13:

[1313] server

[1314] The received message is forwarded to the other user's terminal.

[1315] Step 14:

[1316] User

[1317] The other user receives the message and replies in the same way (e.g., "Yes, I saw it last week! How about you?").

[1318] Step 15:

[1319] Terminal

[1320] A reply message is sent to the server and forwarded to the other party's terminal.

[1321] Step 16:

[1322] User

[1323] If you need a new topic during an ongoing conversation, tap the "Request next topic" button.

[1324] Step 17:

[1325] Terminal

[1326] Sends a new topic request to the server.

[1327] Step 18:

[1328] server

[1329] After receiving the request, the emotion engine is again sent the current emotion data of both users to select a new topic.

[1330] Step 19:

[1331] Emotion Engine

[1332] Analyze the emotional state of both users and select appropriate new topics.

[1333] Step 20:

[1334] server

[1335] The newly generated topic is sent to the devices of both matched users.

[1336] Step 21:

[1337] Terminal

[1338] Display new topics on the chat screen.

[1339] In this way, the user, terminal, server, and emotion engine cooperate to advance the process at each step, ensuring smooth dialogue. Furthermore, the emotion engine analyzes the user's emotions, providing conversation topics more suited to each individual user.

[1340] Example 2

[1341] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1342] Conventional technologies have had difficulty initiating a smooth dialogue between users who have just met and providing appropriate topics to advance the dialogue. Higher accuracy is particularly required for providing topics that take the user's emotions into account. A system that can provide appropriate dialogue topics based on the user's emotions and allow the dialogue to progress naturally is needed.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1344] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a dialogue from a user, means for searching for and matching with other users who share common hobbies and interests, means for analyzing the user's emotions using a generative AI model and providing optimal conversation topics, means for providing conversation topics to matched users, means for starting a dialogue based on the provided conversation topic and generating and providing new topics as the dialogue progresses, means for receiving an operation from the user to request the next topic, and means for generating and providing new topics based on the request. This allows for the provision of appropriate topics that take the user's emotions into consideration, enabling the dialogue to proceed smoothly.

[1345] A "user" is an individual who uses the system, registers profile information, and is involved in initiating and progressing interactions.

[1346] "Profile information" is information about a user, including data such as name, age, gender, hobbies, and interests.

[1347] A "dialogue start request" is a request sent by a user to indicate their desire to start a dialogue.

[1348] A "generative AI model" is a technology that uses artificial intelligence algorithms to analyze a user's profile information and emotions and generate optimal conversation topics.

[1349] An "emotion engine" is a combination of software or hardware for analyzing user emotions and is a system that includes a generative AI model.

[1350] "Matching" is the process of searching for other users who share common hobbies and interests and pairing them with suitable users to interact with.

[1351] A "topic" is a specific topic or theme that is generated for users to use during a conversation.

[1352] "Dialogue progression" refers to the process in which users exchange messages based on provided topics and continue the conversation.

[1353] "New topics" are additional topics or themes that are provided during the course of a conversation and are generated based on the user's emotions and the context of the conversation.

[1354] A "request" is an operation performed by a user to find the next topic and the request.

[1355] This invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system provides specific topics to help the user smoothly advance a dialogue with someone they meet for the first time, and the emotion engine has the function of analyzing the user's emotions and adjusting the content of the dialogue.

[1356] First, the user installs and launches the application. When the user launches the app for the first time, a registration screen appears where the user enters profile information such as name, age, gender, hobbies, and interests. The device encodes the profile information entered by the user into a data packet and sends it to the server. The server deserializes the received profile information and stores it in a database such as MySQL.

[1357] Next, when the user taps the "Start conversation" button on the application's home screen, the device generates a data packet for a conversation start request and sends it to the server. When the server receives the request, it searches its database for other users who share common hobbies and interests and performs matching. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[1358] The server passes the profile information of the matched users to an emotion engine (for example, IBM Watson emotion analysis API) to begin analysis. The emotion engine generates a prompt, which includes a format such as "User A's profile is..., User B's profile is..., please suggest a common topic." The emotion engine analyzes the user's emotions and profile information and provides the most appropriate conversation topic.

[1359] The generated topics are notified to both users by the server. The devices display the received topics on the chat screen, and users can start a conversation based on the provided topics. For example, a user can send a message saying, "Have you seen the latest Marvel movie?" The device converts this message into a data packet and sends it to the server. The server receives the message and forwards it to the other user's device.

[1360] If a new topic is needed as the conversation progresses, the user taps the "Request next topic" button. The device sends a request for a new topic to the server, and the server again generates and sends a prompt to the emotion engine. The emotion engine reanalyzes the progress and emotional state of the current conversation and generates a new topic. For example, it suggests a topic about "recent sporting events," and the server notifies both users of the new topic.

[1361] This system allows people who meet for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation moving smoothly. As a concrete example, the following prompt sentence is used:

[1362] "Generate a new conversation topic. User A's emotion is 'excited', and User B's emotion is 'calm'. They both like watching movies."

[1363] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1364] Step 1:

[1365] User registers profile information

[1366] Users launch the application and enter their profile information, including name, age, gender, hobbies and interests.

[1367] Input: Profile information entered by the user (name, age, gender, hobbies, interests)

[1368] Output: The profile information you entered is encoded into a data packet and ready to be sent.

[1369] Step 2:

[1370] The device sends profile information to the server

[1371] The terminal encodes the profile information entered by the user into a data packet and transmits it to the server.

[1372] Input: Profile information entered by the user

[1373] Output: Information is encoded and sent as a data packet to the server

[1374] Step 3:

[1375] The server stores the profile information in a database

[1376] The server deserializes the received data packet and stores it in a database such as MySQL. For example, it executes the query "INSERT INTO users (name, age, gender, hobbies, interests) VALUES ('Tanaka', 30, 'Male', 'Watching Movies', 'Watching Sports');".

[1377] Input: User profile information contained in the data packet

[1378] Output: The user profile is saved in the database.

[1379] Step 4:

[1380] The user sends a conversation-initiating request

[1381] The user taps the "Start a conversation" button on the application's home screen.

[1382] Input: User taps

[1383] Output: A conversation-initiating request is generated

[1384] Step 5:

[1385] The device sends a conversation start request to the server.

[1386] The terminal generates a data packet for a dialogue initiation request and transmits it to the server.

[1387] Input: Dialogue-initiating request

[1388] Output: A conversation initiation request is sent to the server

[1389] Step 6:

[1390] The server does the matching

[1391] The server receives the request to start a conversation and searches the database for other online users who share the same hobbies and interests. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[1392] Input: Interaction start request, user profile information

[1393] Output: Matched users

[1394] Step 7:

[1395] The server passes the matched user's information to the emotion engine.

[1396] The server passes the profile information of the matched users to the emotion engine and begins analysis. The prompt text includes something like, "User A's profile is..., User B's profile is..., please suggest common topics."

[1397] Input: Profile information of the matched user

[1398] Output: A prompt is generated and sent to the emotion engine.

[1399] Step 8:

[1400] Emotion engine generates topics

[1401] The emotion engine receives the prompt, analyzes the user's emotions and profile information, and generates the most appropriate conversation topic, for example, selecting the topic "recent Marvel movies."

[1402] Input: prompt sentence, user's emotional information

[1403] Output: Generated topics

[1404] Step 9:

[1405] The server notifies the user of the generated topic

[1406] The server notifies both users of the generated topic. A message such as "The topic is 'Recent Marvel Movies'" is sent to both users A and B's devices.

[1407] Input: Generated topics, matching user information

[1408] Output: The topic is notified to the user's terminal.

[1409] Step 10:

[1410] Display topics received by the device

[1411] The device displays the received topics on the chat screen, and users can start a conversation based on this.

[1412] Input: Received topics

[1413] Output: Topics are displayed on the chat screen.

[1414] Step 11:

[1415] The user initiates the interaction

[1416] Users start a conversation based on the provided topic. For example, User A types and sends a message saying, "Have you seen the latest Marvel movie?"

[1417] Input: User message input

[1418] Output: Message is ready to be sent

[1419] Step 12:

[1420] The device sends a message to the server

[1421] The terminal converts the message entered by the user into a data packet and sends it to the server.

[1422] Input: User's message

[1423] Output: The message is sent to the server

[1424] Step 13:

[1425] The server receives and forwards the message

[1426] The server deserializes the received message and forwards it to the other user's device.

[1427] Input: User's message

[1428] Output: The message is forwarded to the other user's device.

[1429] Step 14:

[1430] A user requests a new topic

[1431] While a conversation is in progress, the user taps the "Request next topic" button.

[1432] Input: User taps

[1433] Output: A data packet is generated requesting the next topic.

[1434] Step 15:

[1435] The device sends a request for new topics to the server.

[1436] The device sends a request for a new topic to the server.

[1437] Input: New topic request

[1438] Output: Request data is sent to the server

[1439] Step 16:

[1440] The server creates a new topic

[1441] The server receives the request and again generates and sends a prompt to the emotion engine, which reanalyzes the current dialogue progress and emotional state and generates a new topic, for example, suggesting a topic about "recent sporting events."

[1442] Input: New topic requests, current conversation progress and sentiment information

[1443] Output: New topic

[1444] Step 17:

[1445] The server notifies the user of new topics

[1446] The server notifies both users of the newly created topic.

[1447] Input: New topic

[1448] Output: A new topic is notified to the user's device.

[1449] Step 18:

[1450] The device displays new topics

[1451] The terminal displays the newly received topic on the chat screen, allowing the users to continue the conversation on the new topic.

[1452] Input: Newly received topic

[1453] Output: A new topic appears on the chat screen.

[1454] Through the above steps, the dialogue support system of the present invention functions, allowing users to smoothly advance their dialogue with each other.

[1455] (Application example 2)

[1456] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1457] In conventional dialogue systems, dialogue between users often does not proceed smoothly, and there are psychological barriers, especially when communicating with people who meet for the first time. This makes it difficult for users to naturally find common topics and have enjoyable conversations. Furthermore, there is a problem that appropriate new topics cannot be offered during the dialogue, causing the conversation to stall.

[1458] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a dialogue start request from a user, means for searching for and matching other users with common hobbies and interests, means for analyzing the user's emotions with an emotion engine and adjusting the content of the dialogue, means for providing a topic of dialogue based on the emotion analysis results, means for starting a dialogue based on the provided topic of dialogue, reanalyzing the emotion engine as the dialogue progresses, and generating and providing a new topic, means for accepting an operation to request the next topic from the user, and means for reanalyzing the emotion engine based on the request, generating and providing a new topic. This enables users to naturally find common topics and enjoyably advance the dialogue.

[1459] A "user" is a person who uses the system to register profile information and initiate a dialogue.

[1460] "Profile information" is personal information related to a user, such as the user's name, age, gender, and hobbies.

[1461] The "emotion engine" is a function within the system that analyzes the user's emotions and adjusts the content of the dialogue based on the results.

[1462] A "dialogue start request" is a request that a user sends to the server in order to use the system to start a dialogue with someone they have met for the first time.

[1463] "Matching" is the process of connecting users with common hobbies and interests on the system.

[1464] A "topic of conversation" is a specific topic that the system provides to the user to facilitate the conversation.

[1465] "Reanalysis" is the process by which the emotion engine reevaluates the current emotional state as the conversation progresses and generates new topics as needed.

[1466] "New topics" are additional topics that the emotion engine generates and provides as the conversation progresses.

[1467] A "request" is an operation by the user to ask the system to provide the next topic.

[1468] The "server" is the core computer of the system that stores user profile information and processes dialogue initiation requests, matching, and sentiment analysis.

[1469] The embodiment of the present invention is a system mainly composed of three elements: a server, a terminal, and a user. A specific implementation method is shown below.

[1470] 1. User registration and profile settings

[1471] First, a user launches the app using their smartphone and enters profile information such as name, age, gender, hobbies, etc. on the registration screen. This profile information is sent by the device to the server, which then stores the received information in a database.

[1472] 2. Dialogue-initiating request

[1473] When a user taps the "Start a conversation" button, the device sends a conversation start request to the server, which receives the request, retrieves information about other online users with common hobbies and interests from its database, and performs matching.

[1474] 3. Analysis by Emotion Engine

[1475] If a match is made, the server analyzes the matched user's profile information using an emotion engine to evaluate the initial emotion at the start of the conversation. The emotion engine analyzes emotions using the EmotionEngine library and selects the most appropriate topic based on the results.

[1476] 4. Matching and providing topics

[1477] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics.

[1478] 5. Promoting dialogue and providing new topics

[1479] As the conversation progresses, if the user taps the "Request next topic" button, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the progress and emotional state of the current conversation using its emotion engine. As a result, it generates a new topic and provides it to the devices of both matched users.

[1480] Specific examples

[1481] The user enters their name, age, gender, and hobbies to register their profile information. The prompt to the generative AI model is "Please enter your name, age, gender, and hobbies." When the user taps the "Start conversation" button, a request to start a conversation is sent to the server. The emotion engine performs an analysis, selects the most appropriate topic, and sends it to the matched user's device. The prompt to the generative AI model is "Sending a request to start a conversation." When the "Request next topic" button is tapped while the conversation is in progress, the emotion engine reanalyzes, generates a new topic, and provides it. The prompt to the generative AI model is "Reanalyze the current conversation situation and emotional state, and provide a new topic."

[1482] This system utilizes smartphones and the EmotionEngine library to help users smoothly engage in conversations with people they meet for the first time.

[1483] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1484] Step 1:

[1485] A user starts the app on their smartphone and enters profile information such as name, age, gender, and hobbies on the registration screen. The entered information is sent to the server by the device. The server then stores the user's profile information in a database. The input is the user's profile information, and the output is the profile information stored in the database.

[1486] Step 2:

[1487] The user taps the "Start conversation" button. This sends a conversation start request from the device to the server. The server receives this request, retrieves information about other online users from a database, searches for users with common hobbies and interests, and performs matching. The input is the conversation start request and the user information in the database, and the output is the matching results.

[1488] Step 3:

[1489] Once a match is made, the server analyzes the profile information of the matched user using an emotion engine. The emotion engine uses the EmotionEngine library to analyze the user's emotions and evaluate their initial emotions. This allows the optimal topic to be selected at the start of the conversation. The input is the profile information of the matched user, and the output is the analysis results of the emotion engine and the selected topic.

[1490] Step 4:

[1491] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics. The input is the analysis results of the emotion engine and the selected topics, and the output is the topics displayed on the devices.

[1492] Step 5:

[1493] When a user taps the "Request next topic" button while a conversation is in progress, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the current conversation status and emotional state using its emotion engine. Based on this, a new topic is generated and sent to the devices of both matched users. The input is the request for a new topic and the current conversation status and emotional state, and the output is the reanalyzed new topic.

[1494] In this way, the system facilitates dialogue between users and supports the flow of the dialogue by providing appropriate topics through the emotion engine.

[1495] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1496] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1497] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1498] [Third embodiment]

[1499] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1500] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1501] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1502] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1503] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1504] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1505] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1506] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1507] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1508] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1509] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1510] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1511] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[1512] 1. User registration and profile settings

[1513] User

[1514] When a user launches the app for the first time, a registration screen will appear.

[1515] Users enter their name, age, gender, hobbies, and interests.

[1516] Terminal

[1517] Collects information entered by the user and sends it to the server.

[1518] server

[1519] The information received from the user is stored in a database.

[1520] 2. Dialogue-initiating request

[1521] User

[1522] Tap the "Start a conversation" button on the app's home screen.

[1523] Terminal

[1524] Send a conversation initiation request to the server.

[1525] server

[1526] A request is received to retrieve information about other online users from a database.

[1527] Search for and match with users who share common hobbies and interests.

[1528] 3. Matching and providing topics

[1529] server

[1530] If a match is made, matching information is sent to both users.

[1531] Generate topics based on common interests or the latest news articles.

[1532] The generated topics are sent to the devices of both matched users.

[1533] Terminal

[1534] The received topic is displayed on the chat screen.

[1535] 4. Dialogue Progress

[1536] User

[1537] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[1538] Terminal

[1539] Sends the message entered by the user to the server.

[1540] server

[1541] The received message is forwarded to the other user's terminal.

[1542] User

[1543] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[1544] Terminal

[1545] Sends a new topic request to the server.

[1546] server

[1547] A new topic is generated and sent to the terminals of both users who performed the match.

[1548] Specific examples

[1549] User registration and profile settings

[1550] User

[1551] Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[1552] Terminal

[1553] Send the registration information to the server.

[1554] server

[1555] The received information is stored in a database.

[1556] Interaction-initiating request

[1557] User

[1558] Tanaka taps the "Start conversation" button.

[1559] Terminal

[1560] Send a conversation initiation request to the server.

[1561] server

[1562] Receives a request and searches for other users who share the common hobby of "watching movies."

[1563] Match with Sato-san.

[1564] Send matching information to Tanaka and Sato.

[1565] Generate a topic related to watching movies (e.g., "recent Marvel movies") and send it to both devices.

[1566] Matching and topic provision

[1567] server

[1568] Generate topics related to watching movies.

[1569] The generated topics are sent to Tanaka and Sato's devices.

[1570] Terminal

[1571] The received topic is displayed on the chat screen.

[1572] Dialogue progress

[1573] User

[1574] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[1575] Sato replies, "Yes, I saw it last week! What about you?"

[1576] Terminal

[1577] Each message is sent to the server, which then forwards it to the other user's terminal.

[1578] User

[1579] Tanaka taps the "Request next topic" button.

[1580] Terminal

[1581] Send Tanaka's request to the server.

[1582] server

[1583] A new topic "Recent Sporting Events" is created and sent to Tanaka and Sato.

[1584] This system allows people meeting for the first time to naturally find common topics and start a conversation, and by offering new topics as the conversation progresses, it keeps the conversation flowing.

[1585] The processing flow will be explained below.

[1586] Step 1:

[1587] User

[1588] When a user launches the app for the first time, they are presented with a registration screen.

[1589] The user enters their name, age, gender, hobbies, and interests.

[1590] Step 2:

[1591] Terminal

[1592] The profile information entered by the user is sent to the server.

[1593] Step 3:

[1594] server

[1595] The received profile information is stored in a database.

[1596] Step 4:

[1597] User

[1598] The user taps the "Start a conversation" button on the app's home screen.

[1599] Step 5:

[1600] Terminal

[1601] Send a conversation initiation request to the server.

[1602] Step 6:

[1603] server

[1604] A request to start a conversation is received, and information on other online users is obtained from a database.

[1605] Search for and match with users who share common hobbies and interests.

[1606] Step 7:

[1607] server

[1608] If a match is made, matching information is sent to both users.

[1609] Generate conversation topics based on common interests or the latest news stories.

[1610] Step 8:

[1611] server

[1612] The generated topics are sent to the devices of both matched users.

[1613] Step 9:

[1614] Terminal

[1615] The received topic is displayed on the chat screen.

[1616] Step 10:

[1617] User

[1618] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[1619] Step 11:

[1620] Terminal

[1621] Sends messages sent by users to the server.

[1622] Step 12:

[1623] server

[1624] The received message is forwarded to the other user's terminal.

[1625] Step 13:

[1626] User

[1627] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[1628] Step 14:

[1629] Terminal

[1630] Sends a new topic request to the server.

[1631] Step 15:

[1632] server

[1633] A new topic is generated and sent to the devices of both matched users.

[1634] Example 1

[1635] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1636] In today's online communication environment, it is difficult for users who meet for the first time to naturally progress a conversation. In particular, if they cannot find a common topic, the conversation tends to stall. To solve this problem, a system is needed that matches users based on common hobbies and interests and provides appropriate topics. Furthermore, it is desirable to provide new topics in a timely manner while the conversation is in progress, ensuring uninterrupted communication.

[1637] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1638] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for generating conversation topics based on common hobbies and recent topics using a generative AI model, means for providing conversation topics to matched users, and means for transmitting the matching information and the generated conversation topics to a user terminal. This enables users to naturally find common topics and start a conversation, and to provide new topics as the conversation progresses.

[1639] "User" refers to an individual user of the system.

[1640] "Profile information" refers to personal information such as name, age, gender, hobbies, and interests that a user registers in the system.

[1641] "Database" refers to a storage device and its management system for storing user profile information and other data.

[1642] A "dialogue initiation request" refers to a request sent by a user to begin a dialogue.

[1643] "Matching" refers to the process of connecting users who share common hobbies or interests.

[1644] "Generative AI model" refers to a software model that uses artificial intelligence to generate conversation topics based on shared interests and current topics.

[1645] "Topics" refer to themes or topics related to common interests or the latest news that are generated by the server to encourage dialogue between users.

[1646] "Matching information" refers to data containing information about users who have been matched.

[1647] "User terminal" refers to an electronic device (e.g., smartphone, tablet, computer) used by a user to access the system.

[1648] "Means for receiving" refers to the functions and processes for receiving data from a user.

[1649] "Transmitting means" refers to the functions or processes for sending data to other devices or systems.

[1650] "Storage means" refers to the functions and processes for retaining data for long periods of time.

[1651] "New topics" refer to new themes or topics that are presented as the dialogue progresses.

[1652] The system for implementing this invention stores profile information registered by users, matches users with other users who share common hobbies and interests, and provides appropriate topics of conversation to facilitate smooth dialogue. In a specific implementation, the server, terminals, and users each have different roles and work together to form the system.

[1653] 1. User registration and profile settings

[1654] User

[1655] When a user launches the app, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[1656] Terminal

[1657] The terminal collects the profile information entered by the user, encrypts it, and transmits it to the server.

[1658] server

[1659] The server stores the received profile information in a database, such as MySQL.

[1660] Examples:

[1661] Tanaka uses the app to enter and submit her profile information.

[1662] 2. Dialogue-initiating request

[1663] User

[1664] The user taps the "Start a conversation" button on the app's home screen.

[1665] Terminal

[1666] The terminal sends a dialogue start request to the server in real time.

[1667] server

[1668] The server receives the request, retrieves information about other online users from a database, and matches users together based on common interests.

[1669] Examples:

[1670] Tanaka taps the "Start conversation" button, a request to start a conversation is sent to the server, and the server matches him with Sato.

[1671] 3. Matching and providing topics

[1672] server

[1673] The server uses a generative AI model to generate conversation topics based on common interests and the latest news, for example using the OpenAI GPT series.

[1674] The generated topics are sent to the devices of both matched users.

[1675] Terminal

[1676] The device displays the received topics on the chat screen.

[1677] Examples:

[1678] The server generates a topic about "recent Marvel movies" and sends it to Tanaka and Sato's devices, which then display it on their chat screens.

[1679] 4. Dialogue Progress

[1680] User

[1681] The user enters a message based on the provided topic and starts a conversation.

[1682] Terminal

[1683] The terminal sends the message entered by the user to the server, which then forwards it to the other user's terminal.

[1684] server

[1685] As the conversation progresses, if the user taps the "Request next topic" button, a new topic will be generated and sent to the user's device again.

[1686] Examples:

[1687] Tanaka sends a message asking, "Have you seen the latest Marvel movie?", to which Sato replies, "Yes, I saw it last week! How about you?"

[1688] Tanaka taps the "Request next topic" button, and the server generates a new topic about "recent sporting events" and sends it to both devices.

[1689] Example prompt sentence:

[1690] "Start conversations with other users who share your interests, and if you match, offer topics based on those interests."

[1691] By implementing this invention, the system allows users to naturally find common topics and start a conversation, and new topics can be suggested as the conversation progresses. This system provides powerful support for smooth communication between people meeting for the first time.

[1692] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1693] Step 1: The user launches the app and is presented with a registration screen.

[1694] Input: The user launches the app for the first time.

[1695] Output: The registration screen is displayed.

[1696] Specific operation: When a user launches the app for the first time, the device checks the first-time launch flag built into the system. At first launch, the registration screen is displayed to the user.

[1697] Step 2: User enters required information

[1698] Input: The user enters their name, age, gender, hobbies, and interests on the registration screen.

[1699] Output: The information entered by the user.

[1700] Specific operation: The user enters their name, age, gender, hobbies, and interests in the fields displayed on the app's registration screen. For example, they might enter "Name: Tanaka, Age: 30, Gender: Male, Hobbies: Watching movies and sports."

[1701] Step 3: The device sends the entered information to the server

[1702] Input: Profile information entered by the user.

[1703] Output: Encrypted user information sent from the device to the server.

[1704] How it works: The device collects and encrypts the information entered by the user in real time, then sends the encrypted data to the server.

[1705] Step 4: The server receives the information and stores it in a database

[1706] Input: Encrypted user information sent from the device.

[1707] Output: User profile information stored in a database.

[1708] What happens: The server receives the encrypted data, decrypts it, verifies the information received, checks its integrity, and then stores it in a secure database (e.g., MySQL).

[1709] Step 5: User taps the "Start conversation" button

[1710] Input: A request from the user to initiate a conversation.

[1711] Output: A conversation initiation request.

[1712] What happens: The user finds the "Start a conversation" button on the app's home screen and taps it, which generates a conversation start request.

[1713] Step 6: The device sends a conversation start request to the server

[1714] Input: A request from the user to initiate a conversation.

[1715] Output: The conversation initiation request sent to the server.

[1716] Specific operation: The device sends a request to start a conversation tapped by the user to the server in real time.

[1717] Step 7: The server receives the request and retrieves other user information

[1718] Input: A conversation initiation request sent from the device.

[1719] Output: Information about other users with common hobbies and interests.

[1720] Specific operation: When the server receives a request to start a conversation, it retrieves information about other online users from the database, and then searches for matches based on common hobbies and interests.

[1721] Step 8: The server matches users based on common interests.

[1722] Input: Other user information obtained.

[1723] Output: The combination of users who matched.

[1724] Specific operation: The server analyzes the acquired information of other users and matches users with common hobbies and interests. For example, Tanaka and Sato, who share the hobby of "watching movies," are matched.

[1725] Step 9: The server generates a conversation topic using the generative AI model.

[1726] Input: Common interests and latest news information of matched users.

[1727] Output: The generated conversation topics.

[1728] How it works: The server uses a generative AI model (such as the OpenAI GPT series) to generate conversation topics based on shared interests and the latest news. For example, the topic "Recent Marvel Movies" might be generated.

[1729] Step 10: The server sends the conversation topic to the matching user's device.

[1730] Input: The topic of the generated conversation.

[1731] Output: Topics sent to the matched users' devices.

[1732] Specific operation: The server sends the generated conversation topic to the matched users' devices. For example, the topic of "recent Marvel movies" is sent to Tanaka and Sato's devices.

[1733] Step 11: Display the topic received by the device on the chat screen

[1734] Input: The conversation topic sent by the server.

[1735] Output: Topics displayed on the chat screen.

[1736] Specific operation: The device will display the received topic on the chat screen. For example, "Recent Marvel movies" will be displayed on the chat screen.

[1737] Step 12: The user types a message based on the provided topic and starts the conversation.

[1738] Input: Topics displayed on the chat screen.

[1739] Output: The message entered by the user.

[1740] Specific operation: The user starts a conversation by typing a message based on the topic displayed on the chat screen. For example, Tanaka types and sends a message saying, "Have you seen the latest Marvel movie?"

[1741] Step 13: The device sends a message to the server, which forwards it to the other user's device.

[1742] Input: The message entered by the user.

[1743] Output: The message forwarded to the other user's device.

[1744] Specific operation: The device sends the message entered by the user to the server, and the server forwards the message to the other user's device. For example, Tanaka's message "Have you seen the latest Marvel movie?" is forwarded to Sato's device.

[1745] Step 14: User taps the "Request next topic" button

[1746] Input: A user's request for a new topic.

[1747] Output: Next topic request.

[1748] What it does: When a user taps the "Request next topic" button, a request is made for a new topic. For example, Tanaka taps this button to rekindle the conversation.

[1749] Step 15: The device sends a new topic request to the server

[1750] Input: A new topic request from a user.

[1751] Output: New topic request sent to the server.

[1752] Specific operation: The terminal sends requests for new topics from the user to the server in real time.

[1753] Step 16: The server generates a new topic and sends it to the matching user's device.

[1754] Input: New topic request.

[1755] Output: The new topics generated.

[1756] Specific operation: The server generates a new topic and sends it to the devices of the matched users. For example, the server generates a topic about "recent sporting events" and sends it to the devices of Tanaka and Sato.

[1757] In this way, the system receives specific input at each step, processes and calculates the data, and links the output to the next step, allowing users to smoothly advance their dialogue.

[1758] (Application example 1)

[1759] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1760] Conventional conversation support systems lacked an appropriate mechanism for promoting conversations between visitors and staff in physical stores. They also had difficulty providing specific topics related to store-specific menus and services. This resulted in problems such as first-time customers feeling uncomfortable in the store, which did not contribute to improving the store experience.

[1761] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1762] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for providing conversation topics to matched users, means for identifying users in a physical store and supporting conversations between store staff and customers, means for generating topics related to menus and services offered by the store, means for generating and providing new topics according to the content of the conversation, and means for using prompt sentences to prompt the generative AI model to promote the conversation.This makes it easier for customers who meet for the first time in a physical store, or between customers and staff, to find common topics, enabling natural conversations to be started and continued.

[1763] The "means for receiving profile information registered by a user" refers to the means by which the system receives information such as name, age, gender, hobbies, and interests that a user inputs through an application.

[1764] The "means for saving user profile information in a database" refers to a means for storing received user profile information in a database so that it can be referenced later.

[1765] The "means for receiving a dialogue start request from a user" refers to the means by which the system receives a request when a user wishes to start a dialogue.

[1766] "Means for searching for and matching with other users who share common hobbies and interests" refers to a means for searching for other users who share common hobbies and interests based on the received user profile information, and selecting those users as conversation partners.

[1767] The "means for providing conversation topics to matched users" refers to a means for generating and providing topics based on common hobbies and interests in order to promote conversation between matched users.

[1768] "Means for identifying users in a physical store and supporting interactions between store staff and customers" refers to means for identifying users who visit a physical store and supporting smooth interactions between store staff and users.

[1769] The "means for generating topics related to the menus and services offered by the store" refers to a means for generating conversation topics based on information about the menus and services offered in the store.

[1770] The "means for generating and providing new topics according to the content of the dialogue" refers to a means for generating new appropriate topics according to the content of the ongoing dialogue and providing them to the user.

[1771] "Means for using prompt sentences to encourage dialogue in a generative AI model" refers to means for using prompt sentences to enable a generative AI model to generate appropriate responses or questions to encourage dialogue.

[1772] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[1773] 1. User registration and profile settings

[1774] User

[1775] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[1776] Terminal

[1777] Collects information entered by the user and sends it to the server.

[1778] server

[1779] The information received from the user is stored in a database.

[1780] 2. Dialogue-initiating request

[1781] User

[1782] Tap the "Start a conversation" button on the application's home screen.

[1783] Terminal

[1784] Send a conversation initiation request to the server.

[1785] server

[1786] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[1787] 3. Matching and providing topics

[1788] server

[1789] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[1790] Terminal

[1791] The received topic is displayed on the chat screen.

[1792] 4. Dialogue Progress

[1793] User

[1794] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[1795] Terminal

[1796] Sends the message entered by the user to the server.

[1797] server

[1798] The received message is forwarded to the other user's terminal.

[1799] User

[1800] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[1801] Terminal

[1802] Sends a new topic request to the server.

[1803] server

[1804] A new topic is generated and sent to the terminals of both users who performed the match.

[1805] Hardware and software used

[1806] Hardware

[1807] Server (e.g. AWS or GCP)

[1808] User's smartphone

[1809] software

[1810] Flask (Python framework)

[1811] Python

[1812] Database (e.g. PostgreSQL or MySQL)

[1813] Specific examples

[1814] User registration and profile settings

[1815] User

[1816] A visitor comes to the cafe, launches the application, and registers his name "A," age "30," gender "male," and hobby "reading."

[1817] Terminal

[1818] Send the registration information to the server.

[1819] server

[1820] The received information is stored in a database.

[1821] Interaction-initiating request

[1822] User

[1823] The user taps the "Start conversation" button.

[1824] Terminal

[1825] Send a conversation initiation request to the server.

[1826] server

[1827] Receive requests and search for other users who share the common hobby of reading.

[1828] A match is made and the matching information is sent to both users.

[1829] Generate a reading topic (e.g., "recent bestselling books") and send it to both devices.

[1830] Matching and topic provision

[1831] server

[1832] Matching and generating common topics.

[1833] The generated topic is sent to the user's terminal.

[1834] Terminal

[1835] The received topic is displayed on the chat screen.

[1836] Dialogue progress

[1837] User

[1838] Send a message saying, "Want to talk about the latest bestselling book?"

[1839] The other person replies, "Yes, please!"

[1840] Terminal

[1841] The message is sent to the server, which then forwards it to the other user's device.

[1842] User

[1843] Tap the "Request next topic" button.

[1844] Terminal

[1845] Send the request to the server.

[1846] server

[1847] Generate new topics such as "Recent Limited Drinks" and send them to both devices.

[1848] Prompt Sentence Examples

[1849] "Have you seen the latest Marvel movie?"

[1850] This system makes it easier for customers meeting for the first time in a physical store, or between customers and staff, to find common topics of conversation, allowing them to start and continue natural conversations.

[1851] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1852] Step 1:

[1853] User registration and profile settings

[1854] User

[1855] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[1856] Input: Name, age, gender, hobbies, interests

[1857] Output: Entered profile information

[1858] Terminal

[1859] Collects information entered by the user and sends it to the server.

[1860] Input: User profile information

[1861] Data processing: Convert to JSON format

[1862] Output: Data sent to the server

[1863] server

[1864] The information received from the user is stored in a database.

[1865] Input: User profile information received from the device

[1866] Data processing: Save to database

[1867] Output: Information stored in the database

[1868] Step 2:

[1869] Interaction-initiating request

[1870] User

[1871] Tap the "Start a conversation" button on the application's home screen.

[1872] Input: Dialogue-initiating request

[1873] Output: Request signal

[1874] Terminal

[1875] Send a conversation initiation request to the server.

[1876] Input: Dialogue-initiating request

[1877] Data processing: Convert to JSON format

[1878] Output: Request sent to the server

[1879] server

[1880] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[1881] Input: Dialogue-initiating request

[1882] Data operations: database lookup, search for users with common hobbies and interests, and matching

[1883] Output: Matching information

[1884] Step 3:

[1885] Matching and topic provision

[1886] server

[1887] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[1888] Input: Matching information, common hobbies, store service information

[1889] Data Computing: Creating Common Sense

[1890] Output: Generated topics

[1891] Terminal

[1892] The received topic is displayed on the chat screen.

[1893] Input: Topics received from the server

[1894] Data processing: Converting to a format that can be displayed on the chat screen

[1895] Output: Topics displayed

[1896] Step 4:

[1897] Dialogue progress

[1898] User

[1899] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[1900] Input: Provided topic

[1901] Output: The message to be sent

[1902] Terminal

[1903] Sends the message entered by the user to the server.

[1904] Input: The message entered by the user

[1905] Data processing: Convert to JSON format

[1906] Output: Message sent to the server

[1907] server

[1908] The received message is forwarded to the other user's terminal.

[1909] Input: The message sent by the user

[1910] Data processing: Identifying the destination user, forwarding messages

[1911] Output: Forwarded message

[1912] User

[1913] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[1914] Input: Next topic request

[1915] Output: Request signal

[1916] Terminal

[1917] Sends a new topic request to the server.

[1918] Input: Next topic request

[1919] Data processing: Convert to JSON format

[1920] Output: Request sent to the server

[1921] server

[1922] A new topic is generated and sent to the terminals of both users who performed the match.

[1923] Input: Next topic request

[1924] Data calculation: Generate new topics and send them to the terminal

[1925] Output: The new topics generated

[1926] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1927] An embodiment of this invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system not only provides specific topics for the user to smoothly advance a dialogue with someone they meet for the first time, but also has the function of the emotion engine analyzing the user's emotions and adjusting the content of the dialogue accordingly.

[1928] 1. User registration and profile settings

[1929] User

[1930] When a user launches the app for the first time, a registration screen appears where they can enter their name, age, gender, hobbies, and interests.

[1931] Terminal

[1932] The profile information entered by the user is sent to the server.

[1933] server

[1934] The received profile information is stored in a database.

[1935] 2. Dialogue-initiating request

[1936] User

[1937] Tap the "Start a conversation" button on the app's home screen.

[1938] Terminal

[1939] Send a conversation initiation request to the server.

[1940] server

[1941] A request to start a conversation is received, and information on other online users is obtained from a database.

[1942] Search for and match with users who share common hobbies and interests.

[1943] 3. Analysis by Emotion Engine

[1944] server

[1945] The emotion engine analyzes the profile information of the matched user and the user's initial emotions at the start of the conversation.

[1946] The emotion engine analyzes the user's emotions and selects the most appropriate topic at the start of the conversation.

[1947] 4. Matching and providing topics

[1948] server

[1949] If a match is made, matching information is sent to both users.

[1950] Based on the analysis results of the emotion engine, a topic of conversation appropriate to the user's emotions is generated.

[1951] The generated topics are sent to the devices of both matched users.

[1952] Terminal

[1953] The received topic is displayed on the chat screen.

[1954] 5. Dialogue Progress

[1955] User

[1956] Start a conversation based on the topic provided. For example, if a user likes movies, send them a message saying, "Have you seen the latest Marvel movie?"

[1957] Terminal

[1958] Sends messages sent by users to the server.

[1959] server

[1960] The received message is forwarded to the other user's terminal.

[1961] 6. Providing new topics

[1962] User

[1963] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[1964] Terminal

[1965] Sends a new topic request to the server.

[1966] server

[1967] The request is received and the emotion engine reanalyzes the current dialogue progress and emotional state.

[1968] A new topic is generated and sent to the devices of both matched users.

[1969] Specific examples

[1970] User registration and profile settings

[1971] User

[1972] Mr. Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[1973] Terminal

[1974] Send the registration information to the server.

[1975] server

[1976] The received information is stored in a database.

[1977] Interaction-initiating request

[1978] User

[1979] Tanaka taps the "Start conversation" button.

[1980] Terminal

[1981] Send a conversation initiation request to the server.

[1982] server

[1983] The request is received, other users who share the common hobby of "watching movies" are searched for, and a match is made with Sato.

[1984] Send matching information to Tanaka and Sato.

[1985] Emotion engine analysis

[1986] server

[1987] The profile information of Tanaka and Sato is analyzed using an emotion engine to evaluate their initial emotions.

[1988] Generate optimal movie-watching topics like "Recent Marvel Movies" and adjust them according to each user's emotional state.

[1989] Matching and topic provision

[1990] server

[1991] Generates topics related to movie viewing and reflects the analysis results of the emotion engine.

[1992] The generated topics are sent to Tanaka and Sato's devices.

[1993] Terminal

[1994] The received topic is displayed on the chat screen.

[1995] Dialogue progress

[1996] User

[1997] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[1998] Sato replies, "Yes, I saw it last week! What about you?"

[1999] Terminal

[2000] Messages from Tanaka and Sato are sent to their respective devices, and the contents of the conversation are updated on the server.

[2001] Providing new topics

[2002] User

[2003] While the conversation is in progress, Tanaka taps the "Request next topic" button.

[2004] Terminal

[2005] Sends a new topic request to the server.

[2006] server

[2007] The emotion engine is used again to analyze Tanaka and Sato's current emotional states and the state of their conversation.

[2008] A new topic "Recent Sporting Events" is created and sent to both devices.

[2009] This system allows people meeting for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation flowing.

[2010] The processing flow will be explained below.

[2011] Step 1:

[2012] User

[2013] When a user launches the app for the first time, they are presented with a registration screen.

[2014] The user enters their name, age, gender, hobbies, and interests.

[2015] Step 2:

[2016] Terminal

[2017] The profile information entered by the user is sent to the server.

[2018] Step 3:

[2019] server

[2020] The received profile information is stored in a database.

[2021] Step 4:

[2022] User

[2023] The user taps the "Start a conversation" button on the app's home screen.

[2024] Step 5:

[2025] Terminal

[2026] Send a conversation initiation request to the server.

[2027] Step 6:

[2028] server

[2029] A request to start a conversation is received, and information on other online users is obtained from a database.

[2030] Search for and match with users who share common hobbies and interests.

[2031] Step 7:

[2032] server

[2033] Matching is performed, and the profile information of both users and their emotional data at the start of the interaction are sent to the emotion engine.

[2034] Step 8:

[2035] Emotion Engine

[2036] Profile information and initial sentiment data are analyzed to select conversation topics that are appropriate for both users.

[2037] Step 9:

[2038] server

[2039] Topics selected by the emotion engine are sent to both users.

[2040] Step 10:

[2041] Terminal

[2042] The received topic is displayed on the chat screen.

[2043] Step 11:

[2044] User

[2045] Start a conversation based on a topic provided and type a message (e.g., "Have you seen the latest Marvel movie?").

[2046] Step 12:

[2047] Terminal

[2048] Sends the message entered by the user to the server.

[2049] Step 13:

[2050] server

[2051] The received message is forwarded to the other user's terminal.

[2052] Step 14:

[2053] User

[2054] The other user receives the message and replies in the same way (e.g., "Yes, I saw it last week! How about you?").

[2055] Step 15:

[2056] Terminal

[2057] A reply message is sent to the server and forwarded to the other party's terminal.

[2058] Step 16:

[2059] User

[2060] If you need a new topic during an ongoing conversation, tap the "Request next topic" button.

[2061] Step 17:

[2062] Terminal

[2063] Sends a new topic request to the server.

[2064] Step 18:

[2065] server

[2066] After receiving the request, the emotion engine is again sent the current emotion data of both users to select a new topic.

[2067] Step 19:

[2068] Emotion Engine

[2069] Analyze the emotional state of both users and select appropriate new topics.

[2070] Step 20:

[2071] server

[2072] The newly generated topic is sent to the devices of both matched users.

[2073] Step 21:

[2074] Terminal

[2075] Display new topics on the chat screen.

[2076] In this way, the user, terminal, server, and emotion engine cooperate to advance the process at each step, ensuring smooth dialogue. Furthermore, the emotion engine analyzes the user's emotions, providing conversation topics more suited to each individual user.

[2077] Example 2

[2078] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2079] Conventional technologies have had difficulty initiating a smooth dialogue between users who have just met and providing appropriate topics to advance the dialogue. Higher accuracy is particularly required for providing topics that take the user's emotions into account. A system that can provide appropriate dialogue topics based on the user's emotions and allow the dialogue to progress naturally is needed.

[2080] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2081] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a dialogue from a user, means for searching for and matching with other users who share common hobbies and interests, means for analyzing the user's emotions using a generative AI model and providing optimal conversation topics, means for providing conversation topics to matched users, means for starting a dialogue based on the provided conversation topic and generating and providing new topics as the dialogue progresses, means for receiving an operation from the user to request the next topic, and means for generating and providing new topics based on the request. This allows for the provision of appropriate topics that take the user's emotions into consideration, enabling the dialogue to proceed smoothly.

[2082] A "user" is an individual who uses the system, registers profile information, and is involved in initiating and progressing interactions.

[2083] "Profile information" is information about a user, including data such as name, age, gender, hobbies, and interests.

[2084] A "dialogue start request" is a request sent by a user to indicate their desire to start a dialogue.

[2085] A "generative AI model" is a technology that uses artificial intelligence algorithms to analyze a user's profile information and emotions and generate optimal conversation topics.

[2086] An "emotion engine" is a combination of software or hardware for analyzing user emotions and is a system that includes a generative AI model.

[2087] "Matching" is the process of searching for other users who share common hobbies and interests and pairing them with suitable users to interact with.

[2088] A "topic" is a specific topic or theme that is generated for users to use during a conversation.

[2089] "Dialogue progression" refers to the process in which users exchange messages based on provided topics and continue the conversation.

[2090] "New topics" are additional topics or themes that are provided during the course of a conversation and are generated based on the user's emotions and the context of the conversation.

[2091] A "request" is an operation performed by a user to find the next topic and the request.

[2092] This invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system provides specific topics to help the user smoothly advance a dialogue with someone they meet for the first time, and the emotion engine has the function of analyzing the user's emotions and adjusting the content of the dialogue.

[2093] First, the user installs and launches the application. When the user launches the app for the first time, a registration screen appears where the user enters profile information such as name, age, gender, hobbies, and interests. The device encodes the profile information entered by the user into a data packet and sends it to the server. The server deserializes the received profile information and stores it in a database such as MySQL.

[2094] Next, when the user taps the "Start conversation" button on the application's home screen, the device generates a data packet for a conversation start request and sends it to the server. When the server receives the request, it searches its database for other users who share common hobbies and interests and performs matching. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[2095] The server passes the profile information of the matched users to an emotion engine (for example, IBM Watson emotion analysis API) to begin analysis. The emotion engine generates a prompt, which includes a format such as "User A's profile is..., User B's profile is..., please suggest a common topic." The emotion engine analyzes the user's emotions and profile information and provides the most appropriate conversation topic.

[2096] The generated topics are notified to both users by the server. The devices display the received topics on the chat screen, and users can start a conversation based on the provided topics. For example, a user can send a message saying, "Have you seen the latest Marvel movie?" The device converts this message into a data packet and sends it to the server. The server receives the message and forwards it to the other user's device.

[2097] If a new topic is needed as the conversation progresses, the user taps the "Request next topic" button. The device sends a request for a new topic to the server, and the server again generates and sends a prompt to the emotion engine. The emotion engine reanalyzes the progress and emotional state of the current conversation and generates a new topic. For example, it suggests a topic about "recent sporting events," and the server notifies both users of the new topic.

[2098] This system allows people who meet for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation moving smoothly. As a concrete example, the following prompt sentence is used:

[2099] "Generate a new conversation topic. User A's emotion is 'excited', and User B's emotion is 'calm'. They both like watching movies."

[2100] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2101] Step 1:

[2102] User registers profile information

[2103] Users launch the application and enter their profile information, including name, age, gender, hobbies and interests.

[2104] Input: Profile information entered by the user (name, age, gender, hobbies, interests)

[2105] Output: The profile information you entered is encoded into a data packet and ready to be sent.

[2106] Step 2:

[2107] The device sends profile information to the server

[2108] The terminal encodes the profile information entered by the user into a data packet and transmits it to the server.

[2109] Input: Profile information entered by the user

[2110] Output: Information is encoded and sent as a data packet to the server

[2111] Step 3:

[2112] The server stores the profile information in a database

[2113] The server deserializes the received data packet and stores it in a database such as MySQL. For example, it executes the query "INSERT INTO users (name, age, gender, hobbies, interests) VALUES ('Tanaka', 30, 'Male', 'Watching Movies', 'Watching Sports');".

[2114] Input: User profile information contained in the data packet

[2115] Output: The user profile is saved in the database.

[2116] Step 4:

[2117] The user sends a conversation-initiating request

[2118] The user taps the "Start a conversation" button on the application's home screen.

[2119] Input: User taps

[2120] Output: A conversation-initiating request is generated

[2121] Step 5:

[2122] The device sends a conversation start request to the server.

[2123] The terminal generates a data packet for a dialogue initiation request and transmits it to the server.

[2124] Input: Dialogue-initiating request

[2125] Output: A conversation initiation request is sent to the server

[2126] Step 6:

[2127] The server does the matching

[2128] The server receives the request to start a conversation and searches the database for other online users who share the same hobbies and interests. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[2129] Input: Interaction start request, user profile information

[2130] Output: Matched users

[2131] Step 7:

[2132] The server passes the matched user's information to the emotion engine.

[2133] The server passes the profile information of the matched users to the emotion engine and begins analysis. The prompt text includes something like, "User A's profile is..., User B's profile is..., please suggest common topics."

[2134] Input: Profile information of the matched user

[2135] Output: A prompt is generated and sent to the emotion engine.

[2136] Step 8:

[2137] Emotion engine generates topics

[2138] The emotion engine receives the prompt, analyzes the user's emotions and profile information, and generates the most appropriate conversation topic, for example, selecting the topic "recent Marvel movies."

[2139] Input: prompt sentence, user's emotional information

[2140] Output: Generated topics

[2141] Step 9:

[2142] The server notifies the user of the generated topic

[2143] The server notifies both users of the generated topic. A message such as "The topic is 'Recent Marvel Movies'" is sent to both users A and B's devices.

[2144] Input: Generated topics, matching user information

[2145] Output: The topic is notified to the user's terminal.

[2146] Step 10:

[2147] Display topics received by the device

[2148] The device displays the received topics on the chat screen, and users can start a conversation based on this.

[2149] Input: Received topics

[2150] Output: Topics are displayed on the chat screen.

[2151] Step 11:

[2152] The user initiates the interaction

[2153] Users start a conversation based on the provided topic. For example, User A types and sends a message saying, "Have you seen the latest Marvel movie?"

[2154] Input: User message input

[2155] Output: Message is ready to be sent

[2156] Step 12:

[2157] The device sends a message to the server

[2158] The terminal converts the message entered by the user into a data packet and sends it to the server.

[2159] Input: User's message

[2160] Output: The message is sent to the server

[2161] Step 13:

[2162] The server receives and forwards the message

[2163] The server deserializes the received message and forwards it to the other user's device.

[2164] Input: User's message

[2165] Output: The message is forwarded to the other user's device.

[2166] Step 14:

[2167] A user requests a new topic

[2168] While a conversation is in progress, the user taps the "Request next topic" button.

[2169] Input: User taps

[2170] Output: A data packet is generated requesting the next topic.

[2171] Step 15:

[2172] The device sends a request for new topics to the server.

[2173] The device sends a request for a new topic to the server.

[2174] Input: New topic request

[2175] Output: Request data is sent to the server

[2176] Step 16:

[2177] The server creates a new topic

[2178] The server receives the request and again generates and sends a prompt to the emotion engine, which reanalyzes the current dialogue progress and emotional state and generates a new topic, for example, suggesting a topic about "recent sporting events."

[2179] Input: New topic requests, current conversation progress and sentiment information

[2180] Output: New topic

[2181] Step 17:

[2182] The server notifies the user of new topics

[2183] The server notifies both users of the newly created topic.

[2184] Input: New topic

[2185] Output: A new topic is notified to the user's device.

[2186] Step 18:

[2187] The device displays new topics

[2188] The terminal displays the newly received topic on the chat screen, allowing the users to continue the conversation on the new topic.

[2189] Input: Newly received topic

[2190] Output: A new topic appears on the chat screen.

[2191] Through the above steps, the dialogue support system of the present invention functions, allowing users to smoothly advance their dialogue with each other.

[2192] (Application example 2)

[2193] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2194] In conventional dialogue systems, dialogue between users often does not proceed smoothly, and there are psychological barriers, especially when communicating with people who meet for the first time. This makes it difficult for users to naturally find common topics and have enjoyable conversations. Furthermore, there is a problem that appropriate new topics cannot be offered during the dialogue, causing the conversation to stall.

[2195] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a dialogue start request from a user, means for searching for and matching other users with common hobbies and interests, means for analyzing the user's emotions with an emotion engine and adjusting the content of the dialogue, means for providing a topic of dialogue based on the emotion analysis results, means for starting a dialogue based on the provided topic of dialogue, reanalyzing the emotion engine as the dialogue progresses, and generating and providing a new topic, means for accepting an operation to request the next topic from the user, and means for reanalyzing the emotion engine based on the request, generating and providing a new topic. This enables users to naturally find common topics and enjoyably advance the dialogue.

[2196] A "user" is a person who uses the system to register profile information and initiate a dialogue.

[2197] "Profile information" is personal information related to a user, such as the user's name, age, gender, and hobbies.

[2198] The "emotion engine" is a function within the system that analyzes the user's emotions and adjusts the content of the dialogue based on the results.

[2199] A "dialogue start request" is a request that a user sends to the server in order to use the system to start a dialogue with someone they have met for the first time.

[2200] "Matching" is the process of connecting users with common hobbies and interests on the system.

[2201] A "topic of conversation" is a specific topic that the system provides to the user to facilitate the conversation.

[2202] "Reanalysis" is the process by which the emotion engine reevaluates the current emotional state as the conversation progresses and generates new topics as needed.

[2203] "New topics" are additional topics that the emotion engine generates and provides as the conversation progresses.

[2204] A "request" is an operation by the user to ask the system to provide the next topic.

[2205] The "server" is the core computer of the system that stores user profile information and processes dialogue initiation requests, matching, and sentiment analysis.

[2206] The embodiment of the present invention is a system mainly composed of three elements: a server, a terminal, and a user. A specific implementation method is shown below.

[2207] 1. User registration and profile settings

[2208] First, a user launches the app using their smartphone and enters profile information such as name, age, gender, hobbies, etc. on the registration screen. This profile information is sent by the device to the server, which then stores the received information in a database.

[2209] 2. Dialogue-initiating request

[2210] When a user taps the "Start a conversation" button, the device sends a conversation start request to the server, which receives the request, retrieves information about other online users with common hobbies and interests from its database, and performs matching.

[2211] 3. Analysis by Emotion Engine

[2212] If a match is made, the server analyzes the matched user's profile information using an emotion engine to evaluate the initial emotion at the start of the conversation. The emotion engine analyzes emotions using the EmotionEngine library and selects the most appropriate topic based on the results.

[2213] 4. Matching and providing topics

[2214] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics.

[2215] 5. Promoting dialogue and providing new topics

[2216] As the conversation progresses, if the user taps the "Request next topic" button, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the progress and emotional state of the current conversation using its emotion engine. As a result, it generates a new topic and provides it to the devices of both matched users.

[2217] Specific examples

[2218] The user enters their name, age, gender, and hobbies to register their profile information. The prompt to the generative AI model is "Please enter your name, age, gender, and hobbies." When the user taps the "Start conversation" button, a request to start a conversation is sent to the server. The emotion engine performs an analysis, selects the most appropriate topic, and sends it to the matched user's device. The prompt to the generative AI model is "Sending a request to start a conversation." When the "Request next topic" button is tapped while the conversation is in progress, the emotion engine reanalyzes, generates a new topic, and provides it. The prompt to the generative AI model is "Reanalyze the current conversation situation and emotional state, and provide a new topic."

[2219] This system utilizes smartphones and the EmotionEngine library to help users smoothly engage in conversations with people they meet for the first time.

[2220] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2221] Step 1:

[2222] A user starts the app on their smartphone and enters profile information such as name, age, gender, and hobbies on the registration screen. The entered information is sent to the server by the device. The server then stores the user's profile information in a database. The input is the user's profile information, and the output is the profile information stored in the database.

[2223] Step 2:

[2224] The user taps the "Start conversation" button. This sends a conversation start request from the device to the server. The server receives this request, retrieves information about other online users from a database, searches for users with common hobbies and interests, and performs matching. The input is the conversation start request and the user information in the database, and the output is the matching results.

[2225] Step 3:

[2226] Once a match is made, the server analyzes the profile information of the matched user using an emotion engine. The emotion engine uses the EmotionEngine library to analyze the user's emotions and evaluate their initial emotions. This allows the optimal topic to be selected at the start of the conversation. The input is the profile information of the matched user, and the output is the analysis results of the emotion engine and the selected topic.

[2227] Step 4:

[2228] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics. The input is the analysis results of the emotion engine and the selected topics, and the output is the topics displayed on the devices.

[2229] Step 5:

[2230] When a user taps the "Request next topic" button while a conversation is in progress, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the current conversation status and emotional state using its emotion engine. Based on this, a new topic is generated and sent to the devices of both matched users. The input is the request for a new topic and the current conversation status and emotional state, and the output is the reanalyzed new topic.

[2231] In this way, the system facilitates dialogue between users and supports the flow of the dialogue by providing appropriate topics through the emotion engine.

[2232] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[2233] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2234] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[2235] [Fourth embodiment]

[2236] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2237] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[2238] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[2239] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[2240] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[2241] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[2242] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2243] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[2244] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[2245] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[2246] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[2247] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[2248] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2249] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[2250] 1. User registration and profile settings

[2251] User

[2252] When a user launches the app for the first time, a registration screen will appear.

[2253] Users enter their name, age, gender, hobbies, and interests.

[2254] Terminal

[2255] Collects information entered by the user and sends it to the server.

[2256] server

[2257] The information received from the user is stored in a database.

[2258] 2. Dialogue-initiating request

[2259] User

[2260] Tap the "Start a conversation" button on the app's home screen.

[2261] Terminal

[2262] Send a conversation initiation request to the server.

[2263] server

[2264] A request is received to retrieve information about other online users from a database.

[2265] Search for and match with users who share common hobbies and interests.

[2266] 3. Matching and providing topics

[2267] server

[2268] If a match is made, matching information is sent to both users.

[2269] Generate topics based on common interests or the latest news articles.

[2270] The generated topics are sent to the devices of both matched users.

[2271] Terminal

[2272] The received topic is displayed on the chat screen.

[2273] 4. Dialogue Progress

[2274] User

[2275] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[2276] Terminal

[2277] Sends the message entered by the user to the server.

[2278] server

[2279] The received message is forwarded to the other user's terminal.

[2280] User

[2281] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[2282] Terminal

[2283] Sends a new topic request to the server.

[2284] server

[2285] A new topic is generated and sent to the terminals of both users who performed the match.

[2286] Specific examples

[2287] User registration and profile settings

[2288] User

[2289] Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[2290] Terminal

[2291] Send the registration information to the server.

[2292] server

[2293] The received information is stored in a database.

[2294] Interaction-initiating request

[2295] User

[2296] Tanaka taps the "Start conversation" button.

[2297] Terminal

[2298] Send a conversation initiation request to the server.

[2299] server

[2300] Receives a request and searches for other users who share the common hobby of "watching movies."

[2301] Match with Sato-san.

[2302] Send matching information to Tanaka and Sato.

[2303] Generate a topic related to watching movies (e.g., "recent Marvel movies") and send it to both devices.

[2304] Matching and topic provision

[2305] server

[2306] Generate topics related to watching movies.

[2307] The generated topics are sent to Tanaka and Sato's devices.

[2308] Terminal

[2309] The received topic is displayed on the chat screen.

[2310] Dialogue progress

[2311] User

[2312] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[2313] Sato replies, "Yes, I saw it last week! What about you?"

[2314] Terminal

[2315] Each message is sent to the server, which then forwards it to the other user's terminal.

[2316] User

[2317] Tanaka taps the "Request next topic" button.

[2318] Terminal

[2319] Send Tanaka's request to the server.

[2320] server

[2321] A new topic "Recent Sporting Events" is created and sent to Tanaka and Sato.

[2322] This system allows people meeting for the first time to naturally find common topics and start a conversation, and by offering new topics as the conversation progresses, it keeps the conversation flowing.

[2323] The processing flow will be explained below.

[2324] Step 1:

[2325] User

[2326] When a user launches the app for the first time, they are presented with a registration screen.

[2327] The user enters their name, age, gender, hobbies, and interests.

[2328] Step 2:

[2329] Terminal

[2330] The profile information entered by the user is sent to the server.

[2331] Step 3:

[2332] server

[2333] The received profile information is stored in a database.

[2334] Step 4:

[2335] User

[2336] The user taps the "Start a conversation" button on the app's home screen.

[2337] Step 5:

[2338] Terminal

[2339] Send a conversation initiation request to the server.

[2340] Step 6:

[2341] server

[2342] A request to start a conversation is received, and information on other online users is obtained from a database.

[2343] Search for and match with users who share common hobbies and interests.

[2344] Step 7:

[2345] server

[2346] If a match is made, matching information is sent to both users.

[2347] Generate conversation topics based on common interests or the latest news stories.

[2348] Step 8:

[2349] server

[2350] The generated topics are sent to the devices of both matched users.

[2351] Step 9:

[2352] Terminal

[2353] The received topic is displayed on the chat screen.

[2354] Step 10:

[2355] User

[2356] Start a conversation based on a topic you provide, for example, sending a message saying, "Have you seen the latest Marvel movie?"

[2357] Step 11:

[2358] Terminal

[2359] Sends messages sent by users to the server.

[2360] Step 12:

[2361] server

[2362] The received message is forwarded to the other user's terminal.

[2363] Step 13:

[2364] User

[2365] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[2366] Step 14:

[2367] Terminal

[2368] Sends a new topic request to the server.

[2369] Step 15:

[2370] server

[2371] A new topic is generated and sent to the devices of both matched users.

[2372] Example 1

[2373] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2374] In today's online communication environment, it is difficult for users who meet for the first time to naturally progress a conversation. In particular, if they cannot find a common topic, the conversation tends to stall. To solve this problem, a system is needed that matches users based on common hobbies and interests and provides appropriate topics. Furthermore, it is desirable to provide new topics in a timely manner while the conversation is in progress, ensuring uninterrupted communication.

[2375] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2376] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for generating conversation topics based on common hobbies and recent topics using a generative AI model, means for providing conversation topics to matched users, and means for transmitting the matching information and the generated conversation topics to a user terminal. This enables users to naturally find common topics and start a conversation, and to provide new topics as the conversation progresses.

[2377] "User" refers to an individual user of the system.

[2378] "Profile information" refers to personal information such as name, age, gender, hobbies, and interests that a user registers in the system.

[2379] "Database" refers to a storage device and its management system for storing user profile information and other data.

[2380] A "dialogue initiation request" refers to a request sent by a user to begin a dialogue.

[2381] "Matching" refers to the process of connecting users who share common hobbies or interests.

[2382] "Generative AI model" refers to a software model that uses artificial intelligence to generate conversation topics based on shared interests and current topics.

[2383] "Topics" refer to themes or topics related to common interests or the latest news that are generated by the server to encourage dialogue between users.

[2384] "Matching information" refers to data containing information about users who have been matched.

[2385] "User terminal" refers to an electronic device (e.g., smartphone, tablet, computer) used by a user to access the system.

[2386] "Means for receiving" refers to the functions and processes for receiving data from a user.

[2387] "Transmitting means" refers to the functions or processes for sending data to other devices or systems.

[2388] "Storage means" refers to the functions and processes for retaining data for long periods of time.

[2389] "New topics" refer to new themes or topics that are presented as the dialogue progresses.

[2390] The system for implementing this invention stores profile information registered by users, matches users with other users who share common hobbies and interests, and provides appropriate topics of conversation to facilitate smooth dialogue. In a specific implementation, the server, terminals, and users each have different roles and work together to form the system.

[2391] 1. User registration and profile settings

[2392] User

[2393] When a user launches the app, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[2394] Terminal

[2395] The terminal collects the profile information entered by the user, encrypts it, and transmits it to the server.

[2396] server

[2397] The server stores the received profile information in a database, such as MySQL.

[2398] Examples:

[2399] Tanaka uses the app to enter and submit her profile information.

[2400] 2. Dialogue-initiating request

[2401] User

[2402] The user taps the "Start a conversation" button on the app's home screen.

[2403] Terminal

[2404] The terminal sends a dialogue start request to the server in real time.

[2405] server

[2406] The server receives the request, retrieves information about other online users from a database, and matches users together based on common interests.

[2407] Examples:

[2408] Tanaka taps the "Start conversation" button, a request to start a conversation is sent to the server, and the server matches him with Sato.

[2409] 3. Matching and providing topics

[2410] server

[2411] The server uses a generative AI model to generate conversation topics based on common interests and the latest news, for example using the OpenAI GPT series.

[2412] The generated topics are sent to the devices of both matched users.

[2413] Terminal

[2414] The device displays the received topics on the chat screen.

[2415] Examples:

[2416] The server generates a topic about "recent Marvel movies" and sends it to Tanaka and Sato's devices, which then display it on their chat screens.

[2417] 4. Dialogue Progress

[2418] User

[2419] The user enters a message based on the provided topic and starts a conversation.

[2420] Terminal

[2421] The terminal sends the message entered by the user to the server, which then forwards it to the other user's terminal.

[2422] server

[2423] As the conversation progresses, if the user taps the "Request next topic" button, a new topic will be generated and sent to the user's device again.

[2424] Examples:

[2425] Tanaka sends a message asking, "Have you seen the latest Marvel movie?", to which Sato replies, "Yes, I saw it last week! How about you?"

[2426] Tanaka taps the "Request next topic" button, and the server generates a new topic about "recent sporting events" and sends it to both devices.

[2427] Example prompt sentence:

[2428] "Start conversations with other users who share your interests, and if you match, offer topics based on those interests."

[2429] By implementing this invention, the system allows users to naturally find common topics and start a conversation, and new topics can be suggested as the conversation progresses. This system provides powerful support for smooth communication between people meeting for the first time.

[2430] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2431] Step 1: The user launches the app and is presented with a registration screen.

[2432] Input: The user launches the app for the first time.

[2433] Output: The registration screen is displayed.

[2434] Specific operation: When a user launches the app for the first time, the device checks the first-time launch flag built into the system. At first launch, the registration screen is displayed to the user.

[2435] Step 2: User enters required information

[2436] Input: The user enters their name, age, gender, hobbies, and interests on the registration screen.

[2437] Output: The information entered by the user.

[2438] Specific operation: The user enters their name, age, gender, hobbies, and interests in the fields displayed on the app's registration screen. For example, they might enter "Name: Tanaka, Age: 30, Gender: Male, Hobbies: Watching movies and sports."

[2439] Step 3: The device sends the entered information to the server

[2440] Input: Profile information entered by the user.

[2441] Output: Encrypted user information sent from the device to the server.

[2442] How it works: The device collects and encrypts the information entered by the user in real time, then sends the encrypted data to the server.

[2443] Step 4: The server receives the information and stores it in a database

[2444] Input: Encrypted user information sent from the device.

[2445] Output: User profile information stored in a database.

[2446] What happens: The server receives the encrypted data, decrypts it, verifies the information received, checks its integrity, and then stores it in a secure database (e.g., MySQL).

[2447] Step 5: User taps the "Start conversation" button

[2448] Input: A request from the user to initiate a conversation.

[2449] Output: A conversation initiation request.

[2450] What happens: The user finds the "Start a conversation" button on the app's home screen and taps it, which generates a conversation start request.

[2451] Step 6: The device sends a conversation start request to the server

[2452] Input: A request from the user to initiate a conversation.

[2453] Output: The conversation initiation request sent to the server.

[2454] Specific operation: The device sends a request to start a conversation tapped by the user to the server in real time.

[2455] Step 7: The server receives the request and retrieves other user information

[2456] Input: A conversation initiation request sent from the device.

[2457] Output: Information about other users with common hobbies and interests.

[2458] Specific operation: When the server receives a request to start a conversation, it retrieves information about other online users from the database, and then searches for matches based on common hobbies and interests.

[2459] Step 8: The server matches users based on common interests.

[2460] Input: Other user information obtained.

[2461] Output: The combination of users who matched.

[2462] Specific operation: The server analyzes the acquired information of other users and matches users with common hobbies and interests. For example, Tanaka and Sato, who share the hobby of "watching movies," are matched.

[2463] Step 9: The server generates a conversation topic using the generative AI model.

[2464] Input: Common interests and latest news information of matched users.

[2465] Output: The generated conversation topics.

[2466] How it works: The server uses a generative AI model (such as the OpenAI GPT series) to generate conversation topics based on shared interests and the latest news. For example, the topic "Recent Marvel Movies" might be generated.

[2467] Step 10: The server sends the conversation topic to the matching user's device.

[2468] Input: The topic of the generated conversation.

[2469] Output: Topics sent to the matched users' devices.

[2470] Specific operation: The server sends the generated conversation topic to the matched users' devices. For example, the topic of "recent Marvel movies" is sent to Tanaka and Sato's devices.

[2471] Step 11: Display the topic received by the device on the chat screen

[2472] Input: The conversation topic sent by the server.

[2473] Output: Topics displayed on the chat screen.

[2474] Specific operation: The device will display the received topic on the chat screen. For example, "Recent Marvel movies" will be displayed on the chat screen.

[2475] Step 12: The user types a message based on the provided topic and starts the conversation.

[2476] Input: Topics displayed on the chat screen.

[2477] Output: The message entered by the user.

[2478] Specific operation: The user starts a conversation by typing a message based on the topic displayed on the chat screen. For example, Tanaka types and sends a message saying, "Have you seen the latest Marvel movie?"

[2479] Step 13: The device sends a message to the server, which forwards it to the other user's device.

[2480] Input: The message entered by the user.

[2481] Output: The message forwarded to the other user's device.

[2482] Specific operation: The device sends the message entered by the user to the server, and the server forwards the message to the other user's device. For example, Tanaka's message "Have you seen the latest Marvel movie?" is forwarded to Sato's device.

[2483] Step 14: User taps the "Request next topic" button

[2484] Input: A user's request for a new topic.

[2485] Output: Next topic request.

[2486] What it does: When a user taps the "Request next topic" button, a request is made for a new topic. For example, Tanaka taps this button to rekindle the conversation.

[2487] Step 15: The device sends a new topic request to the server

[2488] Input: A new topic request from a user.

[2489] Output: New topic request sent to the server.

[2490] Specific operation: The terminal sends requests for new topics from the user to the server in real time.

[2491] Step 16: The server generates a new topic and sends it to the matching user's device.

[2492] Input: New topic request.

[2493] Output: The new topics generated.

[2494] Specific operation: The server generates a new topic and sends it to the devices of the matched users. For example, the server generates a topic about "recent sporting events" and sends it to the devices of Tanaka and Sato.

[2495] In this way, the system receives specific input at each step, processes and calculates the data, and links the output to the next step, allowing users to smoothly advance their dialogue.

[2496] (Application example 1)

[2497] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2498] Conventional conversation support systems lacked an appropriate mechanism for promoting conversations between visitors and staff in physical stores. They also had difficulty providing specific topics related to store-specific menus and services. This resulted in problems such as first-time customers feeling uncomfortable in the store, which did not contribute to improving the store experience.

[2499] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2500] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a conversation from a user, means for searching for and matching with other users who share common hobbies and interests, means for providing conversation topics to matched users, means for identifying users in a physical store and supporting conversations between store staff and customers, means for generating topics related to menus and services offered by the store, means for generating and providing new topics according to the content of the conversation, and means for using prompt sentences to prompt the generative AI model to promote the conversation.This makes it easier for customers who meet for the first time in a physical store, or between customers and staff, to find common topics, enabling natural conversations to be started and continued.

[2501] The "means for receiving profile information registered by a user" refers to the means by which the system receives information such as name, age, gender, hobbies, and interests that a user inputs through an application.

[2502] The "means for saving user profile information in a database" refers to a means for storing received user profile information in a database so that it can be referenced later.

[2503] The "means for receiving a dialogue start request from a user" refers to the means by which the system receives a request when a user wishes to start a dialogue.

[2504] "Means for searching for and matching with other users who share common hobbies and interests" refers to a means for searching for other users who share common hobbies and interests based on the received user profile information, and selecting those users as conversation partners.

[2505] The "means for providing conversation topics to matched users" refers to a means for generating and providing topics based on common hobbies and interests in order to promote conversation between matched users.

[2506] "Means for identifying users in a physical store and supporting interactions between store staff and customers" refers to means for identifying users who visit a physical store and supporting smooth interactions between store staff and users.

[2507] The "means for generating topics related to the menus and services offered by the store" refers to a means for generating conversation topics based on information about the menus and services offered in the store.

[2508] The "means for generating and providing new topics according to the content of the dialogue" refers to a means for generating new appropriate topics according to the content of the ongoing dialogue and providing them to the user.

[2509] "Means for using prompt sentences to encourage dialogue in a generative AI model" refers to means for using prompt sentences to enable a generative AI model to generate appropriate responses or questions to encourage dialogue.

[2510] The system for implementing this invention is mainly responsible for user registration, processing of dialogue start requests, matching, providing topics, and progressing the dialogue. The overall processing flow of the program for this system is explained below.

[2511] 1. User registration and profile settings

[2512] User

[2513] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[2514] Terminal

[2515] Collects information entered by the user and sends it to the server.

[2516] server

[2517] The information received from the user is stored in a database.

[2518] 2. Dialogue-initiating request

[2519] User

[2520] Tap the "Start a conversation" button on the application's home screen.

[2521] Terminal

[2522] Send a conversation initiation request to the server.

[2523] server

[2524] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[2525] 3. Matching and providing topics

[2526] server

[2527] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[2528] Terminal

[2529] The received topic is displayed on the chat screen.

[2530] 4. Dialogue Progress

[2531] User

[2532] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[2533] Terminal

[2534] Sends the message entered by the user to the server.

[2535] server

[2536] The received message is forwarded to the other user's terminal.

[2537] User

[2538] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[2539] Terminal

[2540] Sends a new topic request to the server.

[2541] server

[2542] A new topic is generated and sent to the terminals of both users who performed the match.

[2543] Hardware and software used

[2544] Hardware

[2545] Server (e.g. AWS or GCP)

[2546] User's smartphone

[2547] software

[2548] Flask (Python framework)

[2549] Python

[2550] Database (e.g. PostgreSQL or MySQL)

[2551] Specific examples

[2552] User registration and profile settings

[2553] User

[2554] A visitor comes to the cafe, launches the application, and registers his name "A," age "30," gender "male," and hobby "reading."

[2555] Terminal

[2556] Send the registration information to the server.

[2557] server

[2558] The received information is stored in a database.

[2559] Interaction-initiating request

[2560] User

[2561] The user taps the "Start conversation" button.

[2562] Terminal

[2563] Send a conversation initiation request to the server.

[2564] server

[2565] Receive requests and search for other users who share the common hobby of reading.

[2566] A match is made and the matching information is sent to both users.

[2567] Generate a reading topic (e.g., "recent bestselling books") and send it to both devices.

[2568] Matching and topic provision

[2569] server

[2570] Matching and generating common topics.

[2571] The generated topic is sent to the user's terminal.

[2572] Terminal

[2573] The received topic is displayed on the chat screen.

[2574] Dialogue progress

[2575] User

[2576] Send a message saying, "Want to talk about the latest bestselling book?"

[2577] The other person replies, "Yes, please!"

[2578] Terminal

[2579] The message is sent to the server, which then forwards it to the other user's device.

[2580] User

[2581] Tap the "Request next topic" button.

[2582] Terminal

[2583] Send the request to the server.

[2584] server

[2585] Generate new topics such as "Recent Limited Drinks" and send them to both devices.

[2586] Prompt Sentence Examples

[2587] "Have you seen the latest Marvel movie?"

[2588] This system makes it easier for customers meeting for the first time in a physical store, or between customers and staff, to find common topics of conversation, allowing them to start and continue natural conversations.

[2589] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2590] Step 1:

[2591] User registration and profile settings

[2592] User

[2593] When a user launches the application for the first time, a registration screen appears, where the user enters their name, age, gender, hobbies, and interests.

[2594] Input: Name, age, gender, hobbies, interests

[2595] Output: Entered profile information

[2596] Terminal

[2597] Collects information entered by the user and sends it to the server.

[2598] Input: User profile information

[2599] Data processing: Convert to JSON format

[2600] Output: Data sent to the server

[2601] server

[2602] The information received from the user is stored in a database.

[2603] Input: User profile information received from the device

[2604] Data processing: Save to database

[2605] Output: Information stored in the database

[2606] Step 2:

[2607] Interaction-initiating request

[2608] User

[2609] Tap the "Start a conversation" button on the application's home screen.

[2610] Input: Dialogue-initiating request

[2611] Output: Request signal

[2612] Terminal

[2613] Send a conversation initiation request to the server.

[2614] Input: Dialogue-initiating request

[2615] Data processing: Convert to JSON format

[2616] Output: Request sent to the server

[2617] server

[2618] Receives requests and retrieves information about other online users from a database, searching for and matching with users who share common hobbies and interests.

[2619] Input: Dialogue-initiating request

[2620] Data operations: database lookup, search for users with common hobbies and interests, and matching

[2621] Output: Matching information

[2622] Step 3:

[2623] Matching and topic provision

[2624] server

[2625] If a match is made, the system sends matching information to both users. It generates topics based on common interests and the latest services at brick-and-mortar stores. It sends the generated topics to the devices of both matched users.

[2626] Input: Matching information, common hobbies, store service information

[2627] Data Computing: Creating Common Sense

[2628] Output: Generated topics

[2629] Terminal

[2630] The received topic is displayed on the chat screen.

[2631] Input: Topics received from the server

[2632] Data processing: Converting to a format that can be displayed on the chat screen

[2633] Output: Topics displayed

[2634] Step 4:

[2635] Dialogue progress

[2636] User

[2637] Start a conversation based on a topic you provide. For example, send a message saying, "Want to talk about our latest limited edition drink?"

[2638] Input: Provided topic

[2639] Output: The message to be sent

[2640] Terminal

[2641] Sends the message entered by the user to the server.

[2642] Input: The message entered by the user

[2643] Data processing: Convert to JSON format

[2644] Output: Message sent to the server

[2645] server

[2646] The received message is forwarded to the other user's terminal.

[2647] Input: The message sent by the user

[2648] Data processing: Identifying the destination user, forwarding messages

[2649] Output: Forwarded message

[2650] User

[2651] If you need to change the topic again as the conversation progresses, tap the "Request next topic" button.

[2652] Input: Next topic request

[2653] Output: Request signal

[2654] Terminal

[2655] Sends a new topic request to the server.

[2656] Input: Next topic request

[2657] Data processing: Convert to JSON format

[2658] Output: Request sent to the server

[2659] server

[2660] A new topic is generated and sent to the terminals of both users who performed the match.

[2661] Input: Next topic request

[2662] Data calculation: Generate new topics and send them to the terminal

[2663] Output: The new topics generated

[2664] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2665] An embodiment of this invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system not only provides specific topics for the user to smoothly advance a dialogue with someone they meet for the first time, but also has the function of the emotion engine analyzing the user's emotions and adjusting the content of the dialogue accordingly.

[2666] 1. User registration and profile settings

[2667] User

[2668] When a user launches the app for the first time, a registration screen appears where they can enter their name, age, gender, hobbies, and interests.

[2669] Terminal

[2670] The profile information entered by the user is sent to the server.

[2671] server

[2672] The received profile information is stored in a database.

[2673] 2. Dialogue-initiating request

[2674] User

[2675] Tap the "Start a conversation" button on the app's home screen.

[2676] Terminal

[2677] Send a conversation initiation request to the server.

[2678] server

[2679] A request to start a conversation is received, and information on other online users is obtained from a database.

[2680] Search for and match with users who share common hobbies and interests.

[2681] 3. Analysis by Emotion Engine

[2682] server

[2683] The emotion engine analyzes the profile information of the matched user and the user's initial emotions at the start of the conversation.

[2684] The emotion engine analyzes the user's emotions and selects the most appropriate topic at the start of the conversation.

[2685] 4. Matching and providing topics

[2686] server

[2687] If a match is made, matching information is sent to both users.

[2688] Based on the analysis results of the emotion engine, a topic of conversation appropriate to the user's emotions is generated.

[2689] The generated topics are sent to the devices of both matched users.

[2690] Terminal

[2691] The received topic is displayed on the chat screen.

[2692] 5. Dialogue Progress

[2693] User

[2694] Start a conversation based on the topic provided. For example, if a user likes movies, send them a message saying, "Have you seen the latest Marvel movie?"

[2695] Terminal

[2696] Sends messages sent by users to the server.

[2697] server

[2698] The received message is forwarded to the other user's terminal.

[2699] 6. Providing new topics

[2700] User

[2701] If you need a new topic as the conversation progresses, tap the "Request next topic" button.

[2702] Terminal

[2703] Sends a new topic request to the server.

[2704] server

[2705] The request is received and the emotion engine reanalyzes the current dialogue progress and emotional state.

[2706] A new topic is generated and sent to the devices of both matched users.

[2707] Specific examples

[2708] User registration and profile settings

[2709] User

[2710] Mr. Tanaka launches the app and registers his name "Tanaka," age "30," gender "male," and hobbies "watching movies" and "watching sports."

[2711] Terminal

[2712] Send the registration information to the server.

[2713] server

[2714] The received information is stored in a database.

[2715] Interaction-initiating request

[2716] User

[2717] Tanaka taps the "Start conversation" button.

[2718] Terminal

[2719] Send a conversation initiation request to the server.

[2720] server

[2721] The request is received, other users who share the common hobby of "watching movies" are searched for, and a match is made with Sato.

[2722] Send matching information to Tanaka and Sato.

[2723] Emotion engine analysis

[2724] server

[2725] The profile information of Tanaka and Sato is analyzed using an emotion engine to evaluate their initial emotions.

[2726] Generate optimal movie-watching topics like "Recent Marvel Movies" and adjust them according to each user's emotional state.

[2727] Matching and topic provision

[2728] server

[2729] Generates topics related to movie viewing and reflects the analysis results of the emotion engine.

[2730] The generated topics are sent to Tanaka and Sato's devices.

[2731] Terminal

[2732] The received topic is displayed on the chat screen.

[2733] Dialogue progress

[2734] User

[2735] Tanaka sends a message saying, "Have you seen the latest Marvel movie?"

[2736] Sato replies, "Yes, I saw it last week! What about you?"

[2737] Terminal

[2738] Messages from Tanaka and Sato are sent to their respective devices, and the contents of the conversation are updated on the server.

[2739] Providing new topics

[2740] User

[2741] While the conversation is in progress, Tanaka taps the "Request next topic" button.

[2742] Terminal

[2743] Sends a new topic request to the server.

[2744] server

[2745] The emotion engine is used again to analyze Tanaka and Sato's current emotional states and the state of their conversation.

[2746] A new topic "Recent Sporting Events" is created and sent to both devices.

[2747] This system allows people meeting for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation flowing.

[2748] The processing flow will be explained below.

[2749] Step 1:

[2750] User

[2751] When a user launches the app for the first time, they are presented with a registration screen.

[2752] The user enters their name, age, gender, hobbies, and interests.

[2753] Step 2:

[2754] Terminal

[2755] The profile information entered by the user is sent to the server.

[2756] Step 3:

[2757] server

[2758] The received profile information is stored in a database.

[2759] Step 4:

[2760] User

[2761] The user taps the "Start a conversation" button on the app's home screen.

[2762] Step 5:

[2763] Terminal

[2764] Send a conversation initiation request to the server.

[2765] Step 6:

[2766] server

[2767] A request to start a conversation is received, and information on other online users is obtained from a database.

[2768] Search for and match with users who share common hobbies and interests.

[2769] Step 7:

[2770] server

[2771] Matching is performed, and the profile information of both users and their emotional data at the start of the interaction are sent to the emotion engine.

[2772] Step 8:

[2773] Emotion Engine

[2774] Profile information and initial sentiment data are analyzed to select conversation topics that are appropriate for both users.

[2775] Step 9:

[2776] server

[2777] Topics selected by the emotion engine are sent to both users.

[2778] Step 10:

[2779] Terminal

[2780] The received topic is displayed on the chat screen.

[2781] Step 11:

[2782] User

[2783] Start a conversation based on a topic provided and type a message (e.g., "Have you seen the latest Marvel movie?").

[2784] Step 12:

[2785] Terminal

[2786] Sends the message entered by the user to the server.

[2787] Step 13:

[2788] server

[2789] The received message is forwarded to the other user's terminal.

[2790] Step 14:

[2791] User

[2792] The other user receives the message and replies in the same way (e.g., "Yes, I saw it last week! How about you?").

[2793] Step 15:

[2794] Terminal

[2795] A reply message is sent to the server and forwarded to the other party's terminal.

[2796] Step 16:

[2797] User

[2798] If you need a new topic during an ongoing conversation, tap the "Request next topic" button.

[2799] Step 17:

[2800] Terminal

[2801] Sends a new topic request to the server.

[2802] Step 18:

[2803] server

[2804] After receiving the request, the emotion engine is again sent the current emotion data of both users to select a new topic.

[2805] Step 19:

[2806] Emotion Engine

[2807] Analyze the emotional state of both users and select appropriate new topics.

[2808] Step 20:

[2809] server

[2810] The newly generated topic is sent to the devices of both matched users.

[2811] Step 21:

[2812] Terminal

[2813] Display new topics on the chat screen.

[2814] In this way, the user, terminal, server, and emotion engine cooperate to advance the process at each step, ensuring smooth dialogue. Furthermore, the emotion engine analyzes the user's emotions, providing conversation topics more suited to each individual user.

[2815] Example 2

[2816] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2817] Conventional technologies have had difficulty initiating a smooth dialogue between users who have just met and providing appropriate topics to advance the dialogue. Higher accuracy is particularly required for providing topics that take the user's emotions into account. A system that can provide appropriate dialogue topics based on the user's emotions and allow the dialogue to progress naturally is needed.

[2818] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2819] In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a request to start a dialogue from a user, means for searching for and matching with other users who share common hobbies and interests, means for analyzing the user's emotions using a generative AI model and providing optimal conversation topics, means for providing conversation topics to matched users, means for starting a dialogue based on the provided conversation topic and generating and providing new topics as the dialogue progresses, means for receiving an operation from the user to request the next topic, and means for generating and providing new topics based on the request. This allows for the provision of appropriate topics that take the user's emotions into consideration, enabling the dialogue to proceed smoothly.

[2820] A "user" is an individual who uses the system, registers profile information, and is involved in initiating and progressing interactions.

[2821] "Profile information" is information about a user, including data such as name, age, gender, hobbies, and interests.

[2822] A "dialogue start request" is a request sent by a user to indicate their desire to start a dialogue.

[2823] A "generative AI model" is a technology that uses artificial intelligence algorithms to analyze a user's profile information and emotions and generate optimal conversation topics.

[2824] An "emotion engine" is a combination of software or hardware for analyzing user emotions and is a system that includes a generative AI model.

[2825] "Matching" is the process of searching for other users who share common hobbies and interests and pairing them with suitable users to interact with.

[2826] A "topic" is a specific topic or theme that is generated for users to use during a conversation.

[2827] "Dialogue progression" refers to the process in which users exchange messages based on provided topics and continue the conversation.

[2828] "New topics" are additional topics or themes that are provided during the course of a conversation and are generated based on the user's emotions and the context of the conversation.

[2829] A "request" is an operation performed by a user to find the next topic and the request.

[2830] This invention is a dialogue support system incorporating an emotion engine that recognizes the user's emotions. This system provides specific topics to help the user smoothly advance a dialogue with someone they meet for the first time, and the emotion engine has the function of analyzing the user's emotions and adjusting the content of the dialogue.

[2831] First, the user installs and launches the application. When the user launches the app for the first time, a registration screen appears where the user enters profile information such as name, age, gender, hobbies, and interests. The device encodes the profile information entered by the user into a data packet and sends it to the server. The server deserializes the received profile information and stores it in a database such as MySQL.

[2832] Next, when the user taps the "Start conversation" button on the application's home screen, the device generates a data packet for a conversation start request and sends it to the server. When the server receives the request, it searches its database for other users who share common hobbies and interests and performs matching. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[2833] The server passes the profile information of the matched users to an emotion engine (for example, IBM Watson emotion analysis API) to begin analysis. The emotion engine generates a prompt, which includes a format such as "User A's profile is..., User B's profile is..., please suggest a common topic." The emotion engine analyzes the user's emotions and profile information and provides the most appropriate conversation topic.

[2834] The generated topics are notified to both users by the server. The devices display the received topics on the chat screen, and users can start a conversation based on the provided topics. For example, a user can send a message saying, "Have you seen the latest Marvel movie?" The device converts this message into a data packet and sends it to the server. The server receives the message and forwards it to the other user's device.

[2835] If a new topic is needed as the conversation progresses, the user taps the "Request next topic" button. The device sends a request for a new topic to the server, and the server again generates and sends a prompt to the emotion engine. The emotion engine reanalyzes the progress and emotional state of the current conversation and generates a new topic. For example, it suggests a topic about "recent sporting events," and the server notifies both users of the new topic.

[2836] This system allows people who meet for the first time to naturally find common topics and start a conversation, and as the conversation progresses, the emotion engine analyzes the user's emotions and suggests new topics, keeping the conversation moving smoothly. As a concrete example, the following prompt sentence is used:

[2837] "Generate a new conversation topic. User A's emotion is 'excited', and User B's emotion is 'calm'. They both like watching movies."

[2838] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2839] Step 1:

[2840] User registers profile information

[2841] Users launch the application and enter their profile information, including name, age, gender, hobbies and interests.

[2842] Input: Profile information entered by the user (name, age, gender, hobbies, interests)

[2843] Output: The profile information you entered is encoded into a data packet and ready to be sent.

[2844] Step 2:

[2845] The device sends profile information to the server

[2846] The terminal encodes the profile information entered by the user into a data packet and transmits it to the server.

[2847] Input: Profile information entered by the user

[2848] Output: Information is encoded and sent as a data packet to the server

[2849] Step 3:

[2850] The server stores the profile information in a database

[2851] The server deserializes the received data packet and stores it in a database such as MySQL. For example, it executes the query "INSERT INTO users (name, age, gender, hobbies, interests) VALUES ('Tanaka', 30, 'Male', 'Watching Movies', 'Watching Sports');".

[2852] Input: User profile information contained in the data packet

[2853] Output: The user profile is saved in the database.

[2854] Step 4:

[2855] The user sends a conversation-initiating request

[2856] The user taps the "Start a conversation" button on the application's home screen.

[2857] Input: User taps

[2858] Output: A conversation-initiating request is generated

[2859] Step 5:

[2860] The device sends a conversation start request to the server.

[2861] The terminal generates a data packet for a dialogue initiation request and transmits it to the server.

[2862] Input: Dialogue-initiating request

[2863] Output: A conversation initiation request is sent to the server

[2864] Step 6:

[2865] The server does the matching

[2866] The server receives the request to start a conversation and searches the database for other online users who share the same hobbies and interests. For example, it searches the database for other users who share the common hobby of "watching movies" and selects an appropriate pair.

[2867] Input: Interaction start request, user profile information

[2868] Output: Matched users

[2869] Step 7:

[2870] The server passes the matched user's information to the emotion engine.

[2871] The server passes the profile information of the matched users to the emotion engine and begins analysis. The prompt text includes something like, "User A's profile is..., User B's profile is..., please suggest common topics."

[2872] Input: Profile information of the matched user

[2873] Output: A prompt is generated and sent to the emotion engine.

[2874] Step 8:

[2875] Emotion engine generates topics

[2876] The emotion engine receives the prompt, analyzes the user's emotions and profile information, and generates the most appropriate conversation topic, for example, selecting the topic "recent Marvel movies."

[2877] Input: prompt sentence, user's emotional information

[2878] Output: Generated topics

[2879] Step 9:

[2880] The server notifies the user of the generated topic

[2881] The server notifies both users of the generated topic. A message such as "The topic is 'Recent Marvel Movies'" is sent to both users A and B's devices.

[2882] Input: Generated topics, matching user information

[2883] Output: The topic is notified to the user's terminal.

[2884] Step 10:

[2885] Display topics received by the device

[2886] The device displays the received topics on the chat screen, and users can start a conversation based on this.

[2887] Input: Received topics

[2888] Output: Topics are displayed on the chat screen.

[2889] Step 11:

[2890] The user initiates the interaction

[2891] Users start a conversation based on the provided topic. For example, User A types and sends a message saying, "Have you seen the latest Marvel movie?"

[2892] Input: User message input

[2893] Output: Message is ready to be sent

[2894] Step 12:

[2895] The device sends a message to the server

[2896] The terminal converts the message entered by the user into a data packet and sends it to the server.

[2897] Input: User's message

[2898] Output: The message is sent to the server

[2899] Step 13:

[2900] The server receives and forwards the message

[2901] The server deserializes the received message and forwards it to the other user's device.

[2902] Input: User's message

[2903] Output: The message is forwarded to the other user's device.

[2904] Step 14:

[2905] A user requests a new topic

[2906] While a conversation is in progress, the user taps the "Request next topic" button.

[2907] Input: User taps

[2908] Output: A data packet is generated requesting the next topic.

[2909] Step 15:

[2910] The device sends a request for new topics to the server.

[2911] The device sends a request for a new topic to the server.

[2912] Input: New topic request

[2913] Output: Request data is sent to the server

[2914] Step 16:

[2915] The server creates a new topic

[2916] The server receives the request and again generates and sends a prompt to the emotion engine, which reanalyzes the current dialogue progress and emotional state and generates a new topic, for example, suggesting a topic about "recent sporting events."

[2917] Input: New topic requests, current conversation progress and sentiment information

[2918] Output: New topic

[2919] Step 17:

[2920] The server notifies the user of new topics

[2921] The server notifies both users of the newly created topic.

[2922] Input: New topic

[2923] Output: A new topic is notified to the user's device.

[2924] Step 18:

[2925] The device displays new topics

[2926] The terminal displays the newly received topic on the chat screen, allowing the users to continue the conversation on the new topic.

[2927] Input: Newly received topic

[2928] Output: A new topic appears on the chat screen.

[2929] Through the above steps, the dialogue support system of the present invention functions, allowing users to smoothly advance their dialogue with each other.

[2930] (Application example 2)

[2931] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2932] In conventional dialogue systems, dialogue between users often does not proceed smoothly, and there are psychological barriers, especially when communicating with people who meet for the first time. This makes it difficult for users to naturally find common topics and have enjoyable conversations. Furthermore, there is a problem that appropriate new topics cannot be offered during the dialogue, causing the conversation to stall.

[2933] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving profile information registered by a user, means for saving the user's profile information in a database, means for receiving a dialogue start request from a user, means for searching for and matching other users with common hobbies and interests, means for analyzing the user's emotions with an emotion engine and adjusting the content of the dialogue, means for providing a topic of dialogue based on the emotion analysis results, means for starting a dialogue based on the provided topic of dialogue, reanalyzing the emotion engine as the dialogue progresses, and generating and providing a new topic, means for accepting an operation to request the next topic from the user, and means for reanalyzing the emotion engine based on the request, generating and providing a new topic. This enables users to naturally find common topics and enjoyably advance the dialogue.

[2934] A "user" is a person who uses the system to register profile information and initiate a dialogue.

[2935] "Profile information" is personal information related to a user, such as the user's name, age, gender, and hobbies.

[2936] The "emotion engine" is a function within the system that analyzes the user's emotions and adjusts the content of the dialogue based on the results.

[2937] A "dialogue start request" is a request that a user sends to the server in order to use the system to start a dialogue with someone they have met for the first time.

[2938] "Matching" is the process of connecting users with common hobbies and interests on the system.

[2939] A "topic of conversation" is a specific topic that the system provides to the user to facilitate the conversation.

[2940] "Reanalysis" is the process by which the emotion engine reevaluates the current emotional state as the conversation progresses and generates new topics as needed.

[2941] "New topics" are additional topics that the emotion engine generates and provides as the conversation progresses.

[2942] A "request" is an operation by the user to ask the system to provide the next topic.

[2943] The "server" is the core computer of the system that stores user profile information and processes dialogue initiation requests, matching, and sentiment analysis.

[2944] The embodiment of the present invention is a system mainly composed of three elements: a server, a terminal, and a user. A specific implementation method is shown below.

[2945] 1. User registration and profile settings

[2946] First, a user launches the app using their smartphone and enters profile information such as name, age, gender, hobbies, etc. on the registration screen. This profile information is sent by the device to the server, which then stores the received information in a database.

[2947] 2. Dialogue-initiating request

[2948] When a user taps the "Start a conversation" button, the device sends a conversation start request to the server, which receives the request, retrieves information about other online users with common hobbies and interests from its database, and performs matching.

[2949] 3. Analysis by Emotion Engine

[2950] If a match is made, the server analyzes the matched user's profile information using an emotion engine to evaluate the initial emotion at the start of the conversation. The emotion engine analyzes emotions using the EmotionEngine library and selects the most appropriate topic based on the results.

[2951] 4. Matching and providing topics

[2952] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics.

[2953] 5. Promoting dialogue and providing new topics

[2954] As the conversation progresses, if the user taps the "Request next topic" button, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the progress and emotional state of the current conversation using its emotion engine. As a result, it generates a new topic and provides it to the devices of both matched users.

[2955] Specific examples

[2956] The user enters their name, age, gender, and hobbies to register their profile information. The prompt to the generative AI model is "Please enter your name, age, gender, and hobbies." When the user taps the "Start conversation" button, a request to start a conversation is sent to the server. The emotion engine performs an analysis, selects the most appropriate topic, and sends it to the matched user's device. The prompt to the generative AI model is "Sending a request to start a conversation." When the "Request next topic" button is tapped while the conversation is in progress, the emotion engine reanalyzes, generates a new topic, and provides it. The prompt to the generative AI model is "Reanalyze the current conversation situation and emotional state, and provide a new topic."

[2957] This system utilizes smartphones and the EmotionEngine library to help users smoothly engage in conversations with people they meet for the first time.

[2958] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2959] Step 1:

[2960] A user starts the app on their smartphone and enters profile information such as name, age, gender, and hobbies on the registration screen. The entered information is sent to the server by the device. The server then stores the user's profile information in a database. The input is the user's profile information, and the output is the profile information stored in the database.

[2961] Step 2:

[2962] The user taps the "Start conversation" button. This sends a conversation start request from the device to the server. The server receives this request, retrieves information about other online users from a database, searches for users with common hobbies and interests, and performs matching. The input is the conversation start request and the user information in the database, and the output is the matching results.

[2963] Step 3:

[2964] Once a match is made, the server analyzes the profile information of the matched user using an emotion engine. The emotion engine uses the EmotionEngine library to analyze the user's emotions and evaluate their initial emotions. This allows the optimal topic to be selected at the start of the conversation. The input is the profile information of the matched user, and the output is the analysis results of the emotion engine and the selected topic.

[2965] Step 4:

[2966] The server generates topics based on the analysis results and sends them to the devices of both matched users. The devices display the received topics on the chat screen, allowing users to start a conversation based on the topics. The input is the analysis results of the emotion engine and the selected topics, and the output is the topics displayed on the devices.

[2967] Step 5:

[2968] When a user taps the "Request next topic" button while a conversation is in progress, the device sends a request for a new topic to the server. The server receives the request and reanalyzes the current conversation status and emotional state using its emotion engine. Based on this, a new topic is generated and sent to the devices of both matched users. The input is the request for a new topic and the current conversation status and emotional state, and the output is the reanalyzed new topic.

[2969] In this way, the system facilitates dialogue between users and supports the flow of the dialogue by providing appropriate topics through the emotion engine.

[2970] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2971] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2972] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2973] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2974] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2975] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2976] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2977] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2978] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2979] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2980] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2981] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2982] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2983] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2984] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2985] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2986] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2987] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources. ...

Claims

1. means for receiving profile information registered by a user; means for storing user profile information in a database; means for receiving a dialogue initiation request from a user; A way to find and match with other users who share common hobbies and interests; A system including a means for providing conversation topics to matched users.

2. 2. The system according to claim 1, further comprising means for starting a dialogue based on the provided dialogue topic, and for generating and providing a new topic as the dialogue progresses.

3. A means for receiving an operation from a user to request the next topic; 10. The system of claim 1, further comprising means for generating and providing new topics based on requests.

Images