System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a chat log of a social networking service from a user terminal; means for analyzing the received chat log through natural language processing; means for automatically generating a natural conversation corresponding to a past conversation style and content of the user based on the analyzed data; means for transmitting the generated conversation to the user terminal; means for analyzing chat logs of a plurality of users and detecting users having a common topic or similar conversation styles; and means for proposing a conversation with the detected congenial 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] In today's society, there is a strong demand for more efficient dating. However, social networkers, busy professionals, and people looking for new friends or partners face the difficulty and time constraints of finding a compatible partner. Other challenges include a lack of natural conversation and a lack of variety and real-time communication. It is necessary to solve these issues and provide an efficient and natural communication experience. [Means for solving the problem]

[0005] The present invention provides a system including: means for receiving chat logs from a social networking service from a user terminal; means for analyzing the received chat logs using natural language processing; means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data; means for transmitting the generated conversations to the user terminal; means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles; and means for suggesting conversations with the detected users who are compatible with the users. The present invention also includes a re-learning means for collecting feedback from users and continuously improving the accuracy of the generation means, thereby improving the accuracy of natural conversation generation and user satisfaction. Furthermore, by performing topic extraction, context understanding, and sentiment analysis when analyzing the chat logs, more precise and appropriate conversation generation can be achieved.

[0006] "User terminal" means an electronic device used by a user to send and receive chat logs on a social networking service.

[0007] "Chat logs" are data that record the history and content of conversations that users have on social networking services.

[0008] "Natural language processing" is a technology for analyzing text data and extracting and understanding information such as conversation topics, context, and emotions.

[0009] A "generative AI model" is an artificial intelligence model that automatically generates natural conversations that correspond to the user's past conversation style and content based on analyzed data.

[0010] "Matching method" is a function that analyzes the chat logs of multiple users and detects users who share common topics or similar conversation styles.

[0011] The "relearning method" is a function that continuously trains the generative AI model based on user feedback to improve the accuracy of conversation generation.

[0012] "Sentiment analysis" is a technique for analyzing emotions and emotional states within text data and classifying them into specific emotional categories.

[0013] "Topic extraction" is the process of identifying and extracting major themes or topics from the content of a conversation.

[0014] "Context understanding" is a method of analyzing the context and sequential relationships within chat data to understand its content and meaning. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0037] 1. Upload user chat logs

[0038] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[0039] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[0040] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[0041] 2. Chat log analysis

[0042] Server: The server decodes the received chat logs and extracts the textual conversation data, which includes the process of converting the chat data into text.

[0043] Natural Language Processing (NLP): The server uses natural language processing (NLP) libraries to analyze text data, specifically to understand the content of the conversation through conversation topic extraction (e.g., sports, music, daily life, etc.), contextual understanding, and sentiment analysis.

[0044] 3. Conversation Generation

[0045] Server: Based on the analyzed data, a generative AI model is used to generate natural conversations that match the user's past conversational style and content. For example, based on the analysis result that "User A often talks about sports," the generative AI model generates a conversation such as "It looks like X team won recently!"

[0046] 4. Automatic matching function

[0047] Server: The system analyzes chat logs of multiple users to find users who share common topics and similar conversation styles, allowing users to find compatible users.

[0048] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching sports-loving users A and B generates a conversation such as, "Have you seen the game of team X?"

[0049] 5. Providing generated conversations

[0050] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[0051] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[0052] 6. Continuous learning and improvement

[0053] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model. This improves the accuracy of conversation generation and user satisfaction.

[0054] Examples:

[0055] 1. User A's first use:

[0056] User A uploads the LINE chat log to the system from his / her own device.

[0057] The server receives the uploaded chat logs and analyzes them using NLP technology.

[0058] Based on the analysis results, the generative AI model generates conversations about topics such as "recent sports news" and provides them to User A.

[0059] User A uses the generated conversation to smoothly communicate with his friends.

[0060] 2. Matching User A and User B:

[0061] The server analyzes the chat logs of user A and user B and detects that they have a common interest (e.g., sports).

[0062] The system uses a generative AI model to generate conversations between users A and B that share common interests and suggests matches.

[0063] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This allows for efficient and natural communication and increases the probability of users meeting each other.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] User: Select the chat log files of social networking services on your device.

[0067] Step 2:

[0068] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[0069] Step 3:

[0070] Server: Receives chat log files sent from user devices.

[0071] Step 4:

[0072] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[0073] Step 5:

[0074] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[0075] Step 6:

[0076] Server: Based on the analyzed data, it uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversation style and content.

[0077] Step 7:

[0078] Server: Sends the generated conversation to the user's device.

[0079] Step 8:

[0080] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[0081] Step 9:

[0082] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0083] Step 10:

[0084] Server: Matches detected users with similar interests and uses generative AI models to suggest conversations based on common topics.

[0085] Step 11:

[0086] Server: Sends suggested conversations to matched users' devices.

[0087] Step 12:

[0088] Device: The user reviews the suggested conversation and uses it for actual communication.

[0089] Step 13:

[0090] Users: Provide feedback on the generated conversation.

[0091] Step 14:

[0092] Terminal: Sends user feedback information to the server.

[0093] Step 15:

[0094] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[0095] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners.

[0096] Example 1

[0097] 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."

[0098] Conventional chat log analysis systems for social networking services have had difficulty generating natural conversations based on a user's conversation style and interests, and automatically matching them with compatible partners. Furthermore, there has been a lack of feedback collection and continuous learning to improve the accuracy of generated conversations and matching, making it difficult to improve the user experience.

[0099] 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.

[0100] In this invention, the server includes means for receiving a data file from a user terminal, means for analyzing the received data file using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing data files of multiple users and detecting users with common topics or similar conversation styles, and means for suggesting conversations with the detected users who are compatible. This enables the generation of natural conversations based on the user's conversation style and interests and automatic matching with compatible partners, and further enables continuous learning and improvement based on feedback from the generated conversations, thereby improving the user experience.

[0101] A "user terminal" is a computing device from which a user selects and uploads data files.

[0102] A "data file" is a file that records user conversations, such as chat logs on social media.

[0103] "Natural language processing" refers to the technology of analyzing and processing natural language using a computer, and includes topic extraction, context understanding, sentiment analysis, etc.

[0104] "Generation means" refers to the function of automatically generating natural conversation based on the analyzed data.

[0105] The "transmission means" is a communication means for transmitting the generated conversation to the user terminal.

[0106] "Matching method" refers to the function that analyzes the data files of multiple users and detects users who share common topics or similar conversation styles.

[0107] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[0108] "Learning means" refers to a function that continuously improves the accuracy of the generation means based on feedback information.

[0109] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0110] Hardware and software used

[0111] User terminal: The user terminal provides an interface for users to select and upload chat log files to the system. Specifically, the user terminal can be a computer device such as a PC, smartphone, or tablet.

[0112] Server: The server is the central server responsible for analyzing received chat logs and performing conversation generation and matching functions. The following software libraries and services are installed on the server:

[0113] Natural Language Processing (NLP) libraries: NLTK, spaCy, etc.

[0114] Generative AI models: OpenAI (registered trademark) GPT series, etc.

[0115] Database system: MySQL (registered trademark), PostgreSQL, etc.

[0116] Specific data processing and calculation

[0117] 1. Upload user chat logs

[0118] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system.

[0119] Terminal: The terminal provides a file selection screen and an upload button, and sends the chat log file selected by the user to the server.

[0120] Server: The server receives the uploaded chat log files and temporarily stores them in a database.

[0121] 2. Chat log analysis

[0122] Server: The server decodes the received chat logs and extracts the text data. This includes converting chat data into text data.

[0123] Natural Language Processing (NLP): The server uses natural language processing libraries such as NLTK and spaCy to perform topic extraction, contextual understanding, and sentiment analysis of the text data.

[0124] 3. Conversation Generation

[0125] Server: Based on the analyzed data, a generative AI model (e.g., GPT-3 (registered trademark)) is used to generate natural conversations that match the user's past conversation style and content. As a specific example, a prompt message is generated: "User A's chat log analysis results: There are many sports topics. Please generate a conversation related to recent sports news."

[0126] 4. Automatic matching function

[0127] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0128] Matching method: For example, matching users who like sports with each other and generating conversations such as, "Have you seen a game by team X?"

[0129] 5. Providing generated conversations

[0130] Server: Sends the generated conversation to the user's device.

[0131] Terminal: The terminal displays the received conversations in a user interface, and the user can use the generated conversations to communicate with other users.

[0132] 6. Continuous learning and improvement

[0133] User: Users provide feedback on the generated conversations, including ratings and opinions.

[0134] Terminal: The terminal sends feedback to the server.

[0135] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[0136] Specific examples

[0137] 1. User A's first use:

[0138] User: User A uploads LINE chat logs to the system from his / her own device.

[0139] Server: The server receives the uploaded chat logs and analyzes them using NLP technology.

[0140] Server: Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and provides it to User A.

[0141] User: User A uses the generated conversation to smoothly communicate with his friends.

[0142] 2. Matching User A and User B:

[0143] Server: The server analyzes the chat logs of user A and user B and discovers that they have a common interest (e.g., sports).

[0144] Server: Using a generative AI model, it generates conversations between users A and B who share common interests and suggests matches.

[0145] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This enables efficient and natural communication, and is expected to increase opportunities for users to meet each other.

[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0147] Step 1: Upload user chat logs

[0148] User: A user can upload their SNS (e.g., LINE) chat logs to the system from their device. The user selects the chat log file using the device interface.

[0149] Terminal: The terminal provides a function to send the selected chat log file to the server using the HTTP POST method. The input is the chat log file selected by the user, and the output is a file send request to the server.

[0150] Server: The server receives the uploaded chat log file and temporarily stores it in a database. The input is the chat log file sent from the terminal, and the output is the reference information of the saved file.

[0151] Step 2: Analyzing the chat logs

[0152] Server: The server reads the saved chat log file, decodes it, and extracts the textual conversation data. The input is the saved chat log file, and the output is the extracted text data.

[0153] Natural Language Processing (NLP) Library: The server uses NLP libraries such as NLTK and spaCy to analyze text data. The specific analysis process includes topic extraction, context understanding, and sentiment analysis. The input is the extracted text data, and based on this, it outputs metadata such as topics and sentiment.

[0154] Step 3: Conversation generation

[0155] Server: The server creates an input prompt for the generative AI model (e.g., GPT-3) based on the analysis results. For example, it generates a prompt such as, "Results of analyzing user A's chat log: Many sports topics. Please generate conversations related to recent sports news." The input is the analysis results, and the output is the prompt.

[0156] Generative AI model: A generative AI model generates new conversational text based on a prompt. The input is the prompt, and the output is the generated conversational text.

[0157] Step 4: Auto-matching function

[0158] Server: The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is the analysis results of multiple users, and the output is a list of matching candidates.

[0159] Matching method: Generate a conversation between the detected match candidates. For example, match sports-loving user A and user B and generate a conversation such as "Have you seen the game of team X?" The input is a list of match candidates, and the output is the matched conversation text.

[0160] Step 5: Serving the generated conversation

[0161] Server: Sends the generated conversation text to the user terminal. The input is the generated conversation text, and the output is an HTTP response to the user terminal.

[0162] Terminal: The terminal displays the received conversation text in a user interface for the user to review. The input is the conversation text sent from the server, and the output is the conversation displayed in the interface.

[0163] Step 6: Continuous learning and improvement

[0164] User: The user provides feedback on the generated conversation. The feedback includes ratings and opinions, and its quality contributes to re-learning in the next step. The input is the generated conversation and the user's ratings, and the output is feedback information.

[0165] Terminal: The terminal sends the feedback input by the user to the server. The input is the feedback information input by the user, and the output is a feedback transmission request to the server.

[0166] Server: The server retrains the generative AI model based on the feedback information. This improves the accuracy of the model and enables more natural conversation generation. The input is the feedback information, and the output is the retrained generative AI model.

[0167] (Application example 1)

[0168] 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."

[0169] Conventional social networking and content distribution services lacked the means to provide appropriate content recommendations based on users' interests or natural communication between users. They also lacked automatic matching functions that take into account users' conversational styles and interests, making it difficult to improve the user experience.

[0170] 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.

[0171] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for recommending digital content tailored to each user based on the user's interests, and means for providing the recommended digital content to the user terminal, thereby enabling appropriate content recommendations and natural communication for the user and improving the user experience.

[0172] "User terminal" refers to a device such as a computer or smartphone used to access social networking services and content.

[0173] A "social networking service" is an online platform that allows users to communicate with each other and share information via the Internet.

[0174] A "chat log" is a text record of conversations between users on a social networking service.

[0175] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0176] The "generation means" is a mechanism that automatically generates natural conversations that match the user's past conversation style and content based on the analyzed data.

[0177] The "matching method" is a system that analyzes the chat logs of multiple users and identifies users who share common topics or similar conversation styles.

[0178] "Digital content" refers to information such as text, audio, and video that is provided electronically.

[0179] A "recommendation method" is a system that suggests the most suitable digital content to each individual user based on the user's interests.

[0180] The "relearning means" is a mechanism that collects user feedback on the generated conversations and recommended content, and uses this to continuously improve the accuracy of the system.

[0181] "Topic extraction" is a technique for identifying major topics or themes from text data.

[0182] "Contextual understanding" is the technology of understanding the meaning of words and phrases in text based on their context and usage.

[0183] "Sentiment analysis" is a technique for inferring a user's emotional state from text data.

[0184] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0185] 1. Upload user chat logs

[0186] Users upload their SNS chat logs from their own devices to the system. The devices provide an interface for users to send selected chat log files to the server. The server receives the chat log files sent from the user devices and temporarily stores them.

[0187] 2. Chat log analysis

[0188] The server decodes the received chat logs and extracts the text-formatted conversation data. This process includes converting the chat data into text. The server then analyzes the text data using a natural language processing (NLP) library. Specifically, it understands the content of the conversation through conversation topic extraction, context understanding, and sentiment analysis.

[0189] 3. Conversation Generation

[0190] Based on the analyzed data, the server uses a generative AI model to generate natural conversations that match the user's past conversation style and content. For example, based on the analysis result that "the user frequently talks about music," the generative AI model generates a conversation such as "Have you heard the latest hit songs?"

[0191] 4. Automatic matching function

[0192] The server analyzes chat logs of multiple users and detects users who share common topics and similar conversation styles. This allows users to discover users who are compatible with each other. The system then suggests conversations between users who are compatible with each other.

[0193] 5. Recommendation method

[0194] The server then recommends digital content based on the user's interests based on the analyzed data and the generated conversation, enabling the delivery of appropriate content to the user.

[0195] 6. Providing generated conversations and recommended content

[0196] The server sends the generated conversations and recommended content to the user's device, where the user can easily view and use the provided conversations and content on their device.

[0197] 7. Continuous learning and improvement

[0198] Users can provide feedback on the generated conversations and recommended content. The feedback information is sent to the server and used to continuously learn and improve the generative AI model and recommendation methods, thereby improving the accuracy of conversation generation and content recommendations.

[0199] Examples:

[0200] For example, if a user who likes sports uploads a chat log, the server will generate a conversation about "recent sports news" and provide it to the user. Based on this generated conversation, the server will recommend the latest sports news articles to the user and suggest communication with other users who have similar interests.

[0201] Example prompt sentence:

[0202] "Generate a conversation about the following topic:\nA log of people talking about recent soccer games"

[0203] Hardware and software used

[0204] Hardware: User device (smartphone or PC)

[0205] Software: Python (using scikit-learn as a natural language processing library and openai API for conversation generation)

[0206] As described above, this invention provides a system that improves the user experience by analyzing a user's SNS chat log, generating natural conversations, matching users with compatible users, and recommending digital content based on the user's interests.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] A user uploads a chat log from a social networking service to the system from their own device. The user selects a chat log file and clicks the upload button to send the chat log to the server. The input is the chat log file selected by the user, and the output is the transmission of the chat log file to the server.

[0210] Step 2:

[0211] The server receives the chat log file sent from the user's device and temporarily stores it. The server performs a decoding process to convert the received chat log into text format. The input is the received chat log file, and the output is the text-format chat log data.

[0212] Step 3:

[0213] The server analyzes the saved chat logs using a natural language processing (NLP) library. Specifically, it performs topic extraction, context understanding, and sentiment analysis from the chat logs to identify user interests and trends. The input is the chat log data in text format, and the output is the analyzed feature data.

[0214] Step 4:

[0215] Based on the analyzed data, the server uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversational style and content. Prompts are used for generation, generating conversational sentences that match the user's interests. The input is the analyzed feature data and prompts, and the output is the generated natural conversation.

[0216] Step 5:

[0217] The server sends the generated natural conversation to the user's device. The user can then view the generated conversation on their own device and communicate with their friends. The input is the generated natural conversation, and the output is the transmission of the conversation data to the user's device.

[0218] Step 6:

[0219] The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. This allows it to identify users who are compatible with each other. The input is the chat logs of multiple users, and the output is a list of users with common topics and similar conversation styles.

[0220] Step 7:

[0221] The server proposes conversations between users with good compatibility and recommends digital content based on the user's interests using a recommendation method. The input is a list of users with good compatibility and analyzed feature data, and the output is recommended digital content.

[0222] Step 8:

[0223] The server provides the generated conversations and recommended digital content to the user's device. The user can check and use the provided conversations and content on their own device. The input is the recommended digital content and the generated conversation data, and the output is data transmission to the user's device.

[0224] Step 9:

[0225] Users provide feedback on the generated conversations and recommended content. The server collects the feedback information and performs retraining to continuously improve the accuracy of the generative AI model and recommendation method. The input is user feedback, and the output is an improved generative AI model and recommendation method.

[0226] Through the above process, the system analyzes users' SNS chat logs, generates natural conversations, matches users with compatible interests, and even recommends digital content based on the user's interests.

[0227] 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.

[0228] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[0229] 1. Upload user chat logs

[0230] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[0231] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[0232] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[0233] 2. Chat log analysis

[0234] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[0235] Natural Language Processing (NLP): The server uses Natural Language Processing (NLP) libraries to analyze the text data, including topic extraction (e.g., sports, music, daily life, etc.), context understanding, and sentiment analysis.

[0236] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[0237] 3. Conversation Generation

[0238] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model is used to generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[0239] 4. Automatic matching function

[0240] Server: The system analyzes chat logs of multiple users to find users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to further refine matching.

[0241] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching users A and B who are both sports fans and have recently shared positive feelings could generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[0242] 5. Providing generated conversations

[0243] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[0244] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[0245] 6. Continuous learning and improvement

[0246] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. This improves the accuracy of conversation generation and user satisfaction.

[0247] Examples:

[0248] 1. User A's first use:

[0249] User A uploads the LINE chat log to the system from his / her own device.

[0250] The server receives the uploaded chat logs and analyzes them using NLP techniques and an emotion engine.

[0251] Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and User A's positive emotions and provides it to User A.

[0252] User A uses the generated conversation to smoothly communicate with his friends.

[0253] 2. Matching User A and User B:

[0254] The server analyzes the chat logs and emotional states of User A and User B and detects that they have common interests (e.g., sports) and emotions.

[0255] The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[0256] As described above, this invention is a system that analyzes users' chat logs and emotional states to generate natural conversations and automatically match users with compatible partners, thereby realizing efficient and natural communication and increasing the probability of users meeting each other.

[0257] The processing flow will be explained below.

[0258] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[0259] Step 1:

[0260] User: Select the chat log files of social networking services on your device.

[0261] Step 2:

[0262] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[0263] Step 3:

[0264] Server: Receives chat log files sent from user devices.

[0265] Step 4:

[0266] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[0267] Step 5:

[0268] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[0269] Step 6:

[0270] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[0271] Step 7:

[0272] Server: Based on the analyzed data and the emotion analysis results of the emotion engine, the generative AI model is used to automatically generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[0273] Step 8:

[0274] Server: Sends the generated conversation to the user's device.

[0275] Step 9:

[0276] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[0277] Step 10:

[0278] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0279] Step 11:

[0280] Emotion Engine: Evaluates the user's real-time emotional state and uses this information to make more refined matches.

[0281] Step 12:

[0282] Server: Matches users who have been detected as having good chemistry with each other and suggests conversations based on common topics and emotions. For example, matching User A and User B, who are both sports fans and have recently shared positive emotions, generates a conversation such as, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[0283] Step 13:

[0284] Server: Sends suggested conversations to matched users' devices.

[0285] Step 14:

[0286] Device: The user reviews the suggested conversation and uses it for actual communication.

[0287] Step 15:

[0288] Users: Provide feedback on the generated conversation.

[0289] Step 16:

[0290] Terminal: Sends user feedback information to the server.

[0291] Step 17:

[0292] Server: Based on the feedback information, the generative AI model and emotion engine are retrained to improve the accuracy of conversation generation and user satisfaction.

[0293] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners. By incorporating an emotion engine, more appropriate and sophisticated communication that reflects the user's emotional state becomes possible.

[0294] Example 2

[0295] 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."

[0296] Conventional systems were unable to fully utilize user emotions and past chat logs, making it difficult to generate natural conversations and match users with compatible partners. Furthermore, the accuracy of the generated conversations was low, resulting in a lack of user satisfaction.

[0297] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a chat log of a communication service from a user terminal, means for analyzing the received chat log by natural language processing, means for automatically generating natural conversation corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversation to the user terminal, means for analyzing the chat logs of multiple users and detecting users who share common topics or similar conversation styles, means for analyzing user emotions and improving the generated conversation and matching accuracy, and means for suggesting conversations with compatible users. This makes it possible to generate natural conversations and achieve a compatible match between users.

[0298] A "user terminal" is a communication device used by a user, such as a smartphone or a personal computer.

[0299] "Communication service" refers to a platform for users to exchange messages and share information via the Internet.

[0300] "Chat log" refers to the history of conversations and messages a user has on a communication service.

[0301] "Natural Language Processing (NLP)" refers to the technology that enables computers to understand and analyze the natural language used by humans.

[0302] A "generative AI model" refers to an artificial intelligence framework that learns the user's conversation style and content based on the results of data analysis, and generates natural conversations.

[0303] "Sentiment analysis" refers to the technology of identifying and assessing a user's emotional state from text data.

[0304] "Matching method" refers to a function that detects and suggests users with common interests and conversation styles based on analyzed data.

[0305] "Retraining" refers to the process of gathering user feedback and continually improving the accuracy of the generative AI model.

[0306] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[0307] "Topic extraction" refers to the process of automatically identifying major themes or topics from text data.

[0308] "Contextual understanding" refers to the process of understanding the content and background of text data and interpreting its appropriate meaning.

[0309] "Sentiment analysis" refers to the technology of analyzing emotional keywords and tones in text data to evaluate user emotions.

[0310] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[0311] A user uploads their SNS (e.g., LINE) chat log from their device to the system. The device provides an interface for the user to send the chat log file selected by the user to the server. This includes a file selection screen and an upload button. The received chat log file is temporarily stored by the server.

[0312] The server decodes the received chat log file and extracts the textual conversation data. The server then uses a natural language processing (NLP) library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. Furthermore, the server uses an emotion engine (e.g., IBM Watson® Tone Analyzer) to analyze the sentiment of the user's chat log.

[0313] Once the analysis is complete, the server uses a generative AI model (e.g., GPT-3, GPT-4 (registered trademark)) to generate natural-sounding conversations that correspond to the user's past conversational style and content. Specifically, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that team X recently won!"

[0314] The system also analyzes chat logs from multiple users to detect users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to refine matching. Once a match is made, the system suggests conversations between users who are compatible. For example, it could match User A and User B, who both love sports and have recently shared positive emotions, and generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[0315] The generated conversation is sent from the server to the user's terminal, and the user can check the generated conversation on their own terminal and actually communicate with other users. The user terminal provides an interface that makes it easy to check and use the generated conversation.

[0316] Additionally, users can provide feedback on the generated conversations, which is sent to the server and used to continuously learn and improve the generative AI model and emotion engine, thereby improving the accuracy of conversation generation and user satisfaction.

[0317] Example prompt sentence:

[0318] "User A frequently talks about sports and has recently shown positive emotions. Generate a conversation appropriate for him / her."

[0319] "Based on User B's chat logs, generate natural conversations about topics that interest him / her."

[0320] By implementing the invention in this manner, efficient and natural communication is realized, increasing the probability of users meeting each other.

[0321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0322] Step 1: Upload user chat logs

[0323] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The input is the chat log file, and the output is the data sent to the server.

[0324] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server. This includes a file selection screen and an upload button. Specifically, the terminal reads the file according to the user's selection and sends it to the server.

[0325] Step 2: Receiving and saving chat logs

[0326] Server: The server receives the chat log file sent from the user's device and temporarily stores it. The input is the chat log file sent from the device, and the output is the saved chat log data. Specifically, the server decodes the received data and stores it in its internal storage.

[0327] Step 3: Analyzing the chat logs

[0328] Server: The server decodes the received chat log file and extracts the textual conversation data. The input is the saved chat log data, and the output is the textual conversation data. Specifically, the server uses a decoding algorithm to extract the textual data.

[0329] Natural Language Processing (NLP): The server uses an NLP library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. The input is the conversation data in text format, and the output is the analyzed data. Specifically, the NLP engine analyzes the text and extracts the required information.

[0330] Emotion Engine: Furthermore, the emotion engine is used to analyze emotions from the user's chat log. The input is text data, and the output is the emotion analysis result. Specifically, the emotion engine detects and evaluates the tone and emotional keywords in the text.

[0331] Step 4: Conversation generation

[0332] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model (e.g., GPT-3, GPT-4) is used to generate natural-sounding conversations that correspond to the user's past conversational style and content. The input is the analyzed data and the emotion analysis results, and the output is the generated conversation. Specifically, the generative AI model generates a conversation based on the specified prompt sentence.

[0333] Example: Based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that team X won recently!"

[0334] Step 5: Auto-matching function

[0335] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is chat log data of multiple users, and the output is a list of users with common topics and similar conversation styles. The emotion engine also evaluates the user's real-time emotional state. Specifically, the server uses a database to compare and analyze user characteristics.

[0336] Matching method: The system suggests conversations with users who are compatible with the system. The input is a list of compatible users, and the output is the suggested conversations. Specifically, the generative AI model generates conversations that reflect the interests and emotions of users.

[0337] Example: The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[0338] Step 6: Serving the generated conversation

[0339] Server: Sends the generated conversation to the user terminal. The input is the generated conversation, and the output is the data to be sent to the user terminal. In concrete terms, the server uses a communication protocol to send the generated conversation data to the user terminal.

[0340] Terminal: Users can view conversations generated on their own terminals and actually communicate with other users. The input is the conversation data sent from the server, and the output is the conversation content displayed on the user's screen. Specifically, the terminal analyzes the received data and displays it on the user interface.

[0341] Step 7: Continuous learning and improvement

[0342] Retraining means: Users can provide feedback on the generated conversation. This feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. The input is the user's feedback data, and the output is an improved generative model. Specifically, the server analyzes the collected feedback and incorporates it into the model's retraining process.

[0343] (Application example 2)

[0344] 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."

[0345] Conventional social networking services and chat log analysis systems are limited to generating natural conversations between users and matching users with similar interests, but do not adequately address personalized customer engagement or product recommendations in virtual stores. Therefore, a system that can increase user satisfaction and efficiently recommend products is needed. Furthermore, a system that can deeply understand users' emotions and interests and provide effective dialogue and services based on this understanding is also required.

[0346] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0347] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for suggesting conversations with the detected users who are compatible, means for providing customer engagement based on the user's history data so that the user can interact with a virtual agent in a virtual store, and means for suggesting products based on the results of the customer engagement, thereby enabling natural conversations and services that are highly satisfying for the user.

[0348] "User Device" means the electronic device used by a User to upload chat logs and view generated conversations.

[0349] A "social networking service" is an online platform that enables users to communicate with each other.

[0350] A "chat log" is a text-based conversation history that a user has on a social networking service.

[0351] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0352] The "generator" is a means for automatically generating natural conversations that correspond to the user's past conversation style and content.

[0353] A "matching method" is a method for analyzing chat logs of multiple users to detect users who share common topics or similar conversation styles.

[0354] A "virtual store" is a platform that provides store-like services and products online.

[0355] "Customer engagement" refers to the activity of a virtual agent interacting with a user to suggest products and provide services based on the user's interests and needs.

[0356] A "generative AI model" is an artificial intelligence model that analyzes a user's past conversation style and emotional state to generate natural conversations.

[0357] "History data" refers to data on a user's past chat logs and service usage history.

[0358] "Product suggestion means" refers to a means for suggesting appropriate products and services based on analyzed user data.

[0359] This invention is a system that receives chat logs from social networking services from user devices, analyzes them using natural language processing and an emotion engine, generates natural conversations using a generative AI model, and provides them to users. Furthermore, it is also possible to engage with customers and suggest products based on user history data in a virtual store.

[0360] System configuration

[0361] 1. User device: A device where users upload chat logs and view generated conversations and customer engagement results, such as a smartphone.

[0362] 2. Server: Receives chat logs, analyzes them, and generates conversations using a generative AI model. It also has the ability to analyze chat logs from multiple users and perform matching.

[0363] 3. Natural Language Processing (NLP): Use libraries such as Spacy to perform topic extraction, contextual understanding, and sentiment analysis of chat log text.

[0364] 4. Generative AI models: Use models such as GPT-2 to generate natural conversations and suggestions based on the analysis results.

[0365] 5. Database: A data storage device for storing user history data, chat logs, and sentiment analysis results, and accessing them as needed.

[0366] Program processing

[0367] 1. Receiving and saving chat logs: The server receives chat logs sent from the user devices and saves them in a database. This process uses a web framework such as Flask.

[0368] 2. Chat log analysis: The server analyzes the saved chat logs using an NLP library (Spacy) to extract topics, understand context, and analyze sentiment.

[0369] 3. Conversation generation: Based on the analysis results and the output of the emotion engine, a generative AI model (GPT-2) is used to generate natural conversations.

[0370] 4. Matching: The server analyzes chat logs of multiple users, detects and suggests users with common topics and similar conversation styles.

[0371] 5. Customer engagement: In virtual stores, personalized product recommendations are made through interactions between users and virtual agents based on historical user data.

[0372] Specific examples

[0373] 1. Example of User A's use:

[0374] User A uploads the chat log from his smartphone.

[0375] The server receives the data and performs topic extraction and sentiment analysis using Spacy.

[0376] The GPT-2 model generates and serves up the conversation, "What do you think about sports these days?"

[0377] 2. Matching User A and User B:

[0378] The server analyzes the chat logs of user A and user B.

[0379] "Sports" is detected as a common topic and a match is suggested.

[0380] Generates the conversation, "Did you watch the recent game?"

[0381] 3. Customer engagement in virtual stores:

[0382] User A accesses the virtual store.

[0383] The server performs customer engagement based on User A's historical data.

[0384] GPT-2 suggests, "How about this month's promotional item?"

[0385] Prompt Sentence Examples

[0386] "Analyze the conversation logs of the following users to identify topics of interest and sentiment. Generate conversation prompts based on the results. Log: [Paste user chat log here]"

[0387] As described above, the present invention analyzes a user's chat history and emotional data to generate natural conversations and provide personalized product recommendations in a virtual store, thereby providing a more fulfilling experience for the user.

[0388] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0389] Step 1:

[0390] A user uploads a chat log from a social networking service (SNS) to the system from their device. Specifically, they select the chat log file on the file selection screen on their device and press the upload button. The device then sends the selected chat log file to the server. The input of this step is the user's chat log file, and the output is the file sent to the server.

[0391] Step 2:

[0392] The server receives the chat log file sent from the terminal and stores it in the database. The received file is temporarily stored and used for subsequent processing. The input of this step is the user's chat log file, and the output is the file stored in the database.

[0393] Step 3:

[0394] The server retrieves the saved chat log files and analyzes them using a natural language processing (NLP) library (e.g., Spacy). Specifically, it converts the files into text format and performs topic extraction, context understanding, and sentiment analysis. The input of this step is the chat log text, and the output is the analyzed data.

[0395] Step 4:

[0396] Based on the analyzed data, a generative AI model (e.g., GPT-2) is used to generate natural-sounding conversations. The server uses the analysis results and the output of the emotion engine as inputs for the model and obtains the generated text. The inputs for this step are the analysis data and the results of the emotion engine, and the output is the generated conversation text.

[0397] Step 5:

[0398] The server sends the generated conversation text to the user terminal. The user checks the generated conversation on the terminal and communicates with other users as needed. The input of this step is the generated conversation text, and the output is the text sent to the user terminal.

[0399] Step 6:

[0400] The server analyzes chat logs of multiple users to find users with common topics and similar conversation styles. Specifically, it compares and analyzes multiple chat logs to identify users with high similarities. The input of this step is multiple chat log data, and the output is matched user pairs.

[0401] Step 7:

[0402] The server then proposes conversations between users with good compatibility. Based on the analyzed data, it uses a generative AI model to generate and propose relevant conversations. The inputs of this step are the matched user pairs and the analyzed data, and the output is the proposed conversation text.

[0403] Step 8:

[0404] In the virtual store, the server generates a dialogue for customer engagement based on the user's history data. Through the generated dialogue, it makes product and service suggestions. The input of this step is the user's history data, and the output is the generated engagement conversation text and suggestion content.

[0405] Step 9:

[0406] The user provides feedback on the generated conversations and suggestions. The server collects this feedback and uses it to retrain the generative AI model and emotion engine. The input of this step is the user's feedback, and the output is an improvement in the model's accuracy.

[0407] 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.

[0408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0409] 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.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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).

[0417] 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. 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] In the smart glasses 214, 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.

[0422] 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."

[0423] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0424] 1. Upload user chat logs

[0425] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[0426] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[0427] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[0428] 2. Chat log analysis

[0429] Server: The server decodes the received chat logs and extracts the textual conversation data, which includes the process of converting the chat data into text.

[0430] Natural Language Processing (NLP): The server uses natural language processing (NLP) libraries to analyze text data, specifically to understand the content of the conversation through conversation topic extraction (e.g., sports, music, daily life, etc.), contextual understanding, and sentiment analysis.

[0431] 3. Conversation Generation

[0432] Server: Based on the analyzed data, a generative AI model is used to generate natural conversations that match the user's past conversational style and content. For example, based on the analysis result that "User A often talks about sports," the generative AI model generates a conversation such as "It looks like X team won recently!"

[0433] 4. Automatic matching function

[0434] Server: The system analyzes chat logs of multiple users to find users who share common topics and similar conversation styles, allowing users to find compatible users.

[0435] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching sports-loving users A and B generates a conversation such as, "Have you seen the game of team X?"

[0436] 5. Providing generated conversations

[0437] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[0438] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[0439] 6. Continuous learning and improvement

[0440] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model. This improves the accuracy of conversation generation and user satisfaction.

[0441] Examples:

[0442] 1. User A's first use:

[0443] User A uploads the LINE chat log to the system from his / her own device.

[0444] The server receives the uploaded chat logs and analyzes them using NLP technology.

[0445] Based on the analysis results, the generative AI model generates conversations about topics such as "recent sports news" and provides them to User A.

[0446] User A uses the generated conversation to smoothly communicate with his friends.

[0447] 2. Matching User A and User B:

[0448] The server analyzes the chat logs of user A and user B and detects that they have a common interest (e.g., sports).

[0449] The system uses a generative AI model to generate conversations between users A and B that share common interests and suggests matches.

[0450] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This allows for efficient and natural communication and increases the probability of users meeting each other.

[0451] The processing flow will be explained below.

[0452] Step 1:

[0453] User: Select the chat log files of social networking services on your device.

[0454] Step 2:

[0455] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[0456] Step 3:

[0457] Server: Receives chat log files sent from user devices.

[0458] Step 4:

[0459] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[0460] Step 5:

[0461] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[0462] Step 6:

[0463] Server: Based on the analyzed data, it uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversation style and content.

[0464] Step 7:

[0465] Server: Sends the generated conversation to the user's device.

[0466] Step 8:

[0467] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[0468] Step 9:

[0469] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0470] Step 10:

[0471] Server: Matches detected users with similar interests and uses generative AI models to suggest conversations based on common topics.

[0472] Step 11:

[0473] Server: Sends suggested conversations to matched users' devices.

[0474] Step 12:

[0475] Device: The user reviews the suggested conversation and uses it for actual communication.

[0476] Step 13:

[0477] Users: Provide feedback on the generated conversation.

[0478] Step 14:

[0479] Terminal: Sends user feedback information to the server.

[0480] Step 15:

[0481] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[0482] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners.

[0483] Example 1

[0484] 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."

[0485] Conventional chat log analysis systems for social networking services have had difficulty generating natural conversations based on a user's conversation style and interests, and automatically matching them with compatible partners. Furthermore, there has been a lack of feedback collection and continuous learning to improve the accuracy of generated conversations and matching, making it difficult to improve the user experience.

[0486] 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.

[0487] In this invention, the server includes means for receiving a data file from a user terminal, means for analyzing the received data file using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing data files of multiple users and detecting users with common topics or similar conversation styles, and means for suggesting conversations with the detected users who are compatible. This enables the generation of natural conversations based on the user's conversation style and interests and automatic matching with compatible partners, and further enables continuous learning and improvement based on feedback from the generated conversations, thereby improving the user experience.

[0488] A "user terminal" is a computing device from which a user selects and uploads data files.

[0489] A "data file" is a file that records user conversations, such as chat logs on social media.

[0490] "Natural language processing" refers to the technology of analyzing and processing natural language using a computer, and includes topic extraction, context understanding, sentiment analysis, etc.

[0491] "Generation means" refers to the function of automatically generating natural conversation based on the analyzed data.

[0492] The "transmission means" is a communication means for transmitting the generated conversation to the user terminal.

[0493] "Matching method" refers to the function that analyzes the data files of multiple users and detects users who share common topics or similar conversation styles.

[0494] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[0495] "Learning means" refers to a function that continuously improves the accuracy of the generation means based on feedback information.

[0496] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0497] Hardware and software used

[0498] User terminal: The user terminal provides an interface for users to select and upload chat log files to the system. Specifically, the user terminal can be a computer device such as a PC, smartphone, or tablet.

[0499] Server: The server is the central server responsible for analyzing received chat logs and performing conversation generation and matching functions. The following software libraries and services are installed on the server:

[0500] Natural Language Processing (NLP) libraries: NLTK, spaCy, etc.

[0501] Generative AI models: OpenAI's GPT series, etc.

[0502] Database system: MySQL, PostgreSQL, etc.

[0503] Specific data processing and calculation

[0504] 1. Upload user chat logs

[0505] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system.

[0506] Terminal: The terminal provides a file selection screen and an upload button, and sends the chat log file selected by the user to the server.

[0507] Server: The server receives the uploaded chat log files and temporarily stores them in a database.

[0508] 2. Chat log analysis

[0509] Server: The server decodes the received chat logs and extracts the text data. This includes converting chat data into text data.

[0510] Natural Language Processing (NLP): The server uses natural language processing libraries such as NLTK and spaCy to perform topic extraction, contextual understanding, and sentiment analysis of the text data.

[0511] 3. Conversation Generation

[0512] Server: Based on the analyzed data, a generative AI model (e.g., GPT-3) is used to generate natural conversations that match the user's past conversation style and content. For example, it generates a prompt such as, "User A's chat log analysis results: Many sports topics. Please generate a conversation related to recent sports news."

[0513] 4. Automatic matching function

[0514] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0515] Matching method: For example, matching users who like sports with each other and generating conversations such as, "Have you seen a game by team X?"

[0516] 5. Providing generated conversations

[0517] Server: Sends the generated conversation to the user's device.

[0518] Terminal: The terminal displays the received conversations in a user interface, and the user can use the generated conversations to communicate with other users.

[0519] 6. Continuous learning and improvement

[0520] User: Users provide feedback on the generated conversations, including ratings and opinions.

[0521] Terminal: The terminal sends feedback to the server.

[0522] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[0523] Specific examples

[0524] 1. User A's first use:

[0525] User: User A uploads LINE chat logs to the system from his / her own device.

[0526] Server: The server receives the uploaded chat logs and analyzes them using NLP technology.

[0527] Server: Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and provides it to User A.

[0528] User: User A uses the generated conversation to smoothly communicate with his friends.

[0529] 2. Matching User A and User B:

[0530] Server: The server analyzes the chat logs of user A and user B and discovers that they have a common interest (e.g., sports).

[0531] Server: Using a generative AI model, it generates conversations between users A and B who share common interests and suggests matches.

[0532] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This enables efficient and natural communication, and is expected to increase opportunities for users to meet each other.

[0533] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0534] Step 1: Upload user chat logs

[0535] User: A user can upload their SNS (e.g., LINE) chat logs to the system from their device. The user selects the chat log file using the device interface.

[0536] Terminal: The terminal provides a function to send the selected chat log file to the server using the HTTP POST method. The input is the chat log file selected by the user, and the output is a file send request to the server.

[0537] Server: The server receives the uploaded chat log file and temporarily stores it in a database. The input is the chat log file sent from the terminal, and the output is the reference information of the saved file.

[0538] Step 2: Analyzing the chat logs

[0539] Server: The server reads the saved chat log file, decodes it, and extracts the textual conversation data. The input is the saved chat log file, and the output is the extracted text data.

[0540] Natural Language Processing (NLP) Library: The server uses NLP libraries such as NLTK and spaCy to analyze text data. The specific analysis process includes topic extraction, context understanding, and sentiment analysis. The input is the extracted text data, and based on this, it outputs metadata such as topics and sentiment.

[0541] Step 3: Conversation generation

[0542] Server: The server creates an input prompt for the generative AI model (e.g., GPT-3) based on the analysis results. For example, it generates a prompt such as, "Results of analyzing user A's chat log: Many sports topics. Please generate conversations related to recent sports news." The input is the analysis results, and the output is the prompt.

[0543] Generative AI model: A generative AI model generates new conversational text based on a prompt. The input is the prompt, and the output is the generated conversational text.

[0544] Step 4: Auto-matching function

[0545] Server: The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is the analysis results of multiple users, and the output is a list of matching candidates.

[0546] Matching method: Generate a conversation between the detected match candidates. For example, match sports-loving user A and user B and generate a conversation such as "Have you seen the game of team X?" The input is a list of match candidates, and the output is the matched conversation text.

[0547] Step 5: Serving the generated conversation

[0548] Server: Sends the generated conversation text to the user terminal. The input is the generated conversation text, and the output is an HTTP response to the user terminal.

[0549] Terminal: The terminal displays the received conversation text in a user interface for the user to review. The input is the conversation text sent from the server, and the output is the conversation displayed in the interface.

[0550] Step 6: Continuous learning and improvement

[0551] User: The user provides feedback on the generated conversation. The feedback includes ratings and opinions, and its quality contributes to re-learning in the next step. The input is the generated conversation and the user's ratings, and the output is feedback information.

[0552] Terminal: The terminal sends the feedback input by the user to the server. The input is the feedback information input by the user, and the output is a feedback transmission request to the server.

[0553] Server: The server retrains the generative AI model based on the feedback information. This improves the accuracy of the model and enables more natural conversation generation. The input is the feedback information, and the output is the retrained generative AI model.

[0554] (Application example 1)

[0555] 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."

[0556] Conventional social networking and content distribution services lacked the means to provide appropriate content recommendations based on users' interests or natural communication between users. They also lacked automatic matching functions that take into account users' conversational styles and interests, making it difficult to improve the user experience.

[0557] 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.

[0558] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for recommending digital content tailored to each user based on the user's interests, and means for providing the recommended digital content to the user terminal, thereby enabling appropriate content recommendations and natural communication for the user and improving the user experience.

[0559] "User terminal" refers to a device such as a computer or smartphone used to access social networking services and content.

[0560] A "social networking service" is an online platform that allows users to communicate with each other and share information via the Internet.

[0561] A "chat log" is a text record of conversations between users on a social networking service.

[0562] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0563] The "generation means" is a mechanism that automatically generates natural conversations that match the user's past conversation style and content based on the analyzed data.

[0564] The "matching method" is a system that analyzes the chat logs of multiple users and identifies users who share common topics or similar conversation styles.

[0565] "Digital content" refers to information such as text, audio, and video that is provided electronically.

[0566] A "recommendation method" is a system that suggests the most suitable digital content to each individual user based on the user's interests.

[0567] The "relearning means" is a mechanism that collects user feedback on the generated conversations and recommended content, and uses this to continuously improve the accuracy of the system.

[0568] "Topic extraction" is a technique for identifying major topics or themes from text data.

[0569] "Contextual understanding" is the technology of understanding the meaning of words and phrases in text based on their context and usage.

[0570] "Sentiment analysis" is a technique for inferring a user's emotional state from text data.

[0571] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0572] 1. Upload user chat logs

[0573] Users upload their SNS chat logs from their own devices to the system. The devices provide an interface for users to send selected chat log files to the server. The server receives the chat log files sent from the user devices and temporarily stores them.

[0574] 2. Chat log analysis

[0575] The server decodes the received chat logs and extracts the text-formatted conversation data. This process includes converting the chat data into text. The server then analyzes the text data using a natural language processing (NLP) library. Specifically, it understands the content of the conversation through conversation topic extraction, context understanding, and sentiment analysis.

[0576] 3. Conversation Generation

[0577] Based on the analyzed data, the server uses a generative AI model to generate natural conversations that match the user's past conversation style and content. For example, based on the analysis result that "the user frequently talks about music," the generative AI model generates a conversation such as "Have you heard the latest hit songs?"

[0578] 4. Automatic matching function

[0579] The server analyzes chat logs of multiple users and detects users who share common topics and similar conversation styles. This allows users to discover users who are compatible with each other. The system then suggests conversations between users who are compatible with each other.

[0580] 5. Recommendation method

[0581] The server then recommends digital content based on the user's interests based on the analyzed data and the generated conversation, enabling the delivery of appropriate content to the user.

[0582] 6. Providing generated conversations and recommended content

[0583] The server sends the generated conversations and recommended content to the user's device, where the user can easily view and use the provided conversations and content on their device.

[0584] 7. Continuous learning and improvement

[0585] Users can provide feedback on the generated conversations and recommended content. The feedback information is sent to the server and used to continuously learn and improve the generative AI model and recommendation methods, thereby improving the accuracy of conversation generation and content recommendations.

[0586] Examples:

[0587] For example, if a user who likes sports uploads a chat log, the server will generate a conversation about "recent sports news" and provide it to the user. Based on this generated conversation, the server will recommend the latest sports news articles to the user and suggest communication with other users who have similar interests.

[0588] Example prompt sentence:

[0589] "Generate a conversation about the following topic:\nA log of people talking about recent soccer games"

[0590] Hardware and software used

[0591] Hardware: User device (smartphone or PC)

[0592] Software: Python (using scikit-learn as a natural language processing library and openai API for conversation generation)

[0593] As described above, this invention provides a system that improves the user experience by analyzing a user's SNS chat log, generating natural conversations, matching users with compatible users, and recommending digital content based on the user's interests.

[0594] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0595] Step 1:

[0596] A user uploads a chat log from a social networking service to the system from their own device. The user selects a chat log file and clicks the upload button to send the chat log to the server. The input is the chat log file selected by the user, and the output is the transmission of the chat log file to the server.

[0597] Step 2:

[0598] The server receives the chat log file sent from the user's device and temporarily stores it. The server performs a decoding process to convert the received chat log into text format. The input is the received chat log file, and the output is the text-format chat log data.

[0599] Step 3:

[0600] The server analyzes the saved chat logs using a natural language processing (NLP) library. Specifically, it performs topic extraction, context understanding, and sentiment analysis from the chat logs to identify user interests and trends. The input is the chat log data in text format, and the output is the analyzed feature data.

[0601] Step 4:

[0602] Based on the analyzed data, the server uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversational style and content. Prompts are used for generation, generating conversational sentences that match the user's interests. The input is the analyzed feature data and prompts, and the output is the generated natural conversation.

[0603] Step 5:

[0604] The server sends the generated natural conversation to the user's device. The user can then view the generated conversation on their own device and communicate with their friends. The input is the generated natural conversation, and the output is the transmission of the conversation data to the user's device.

[0605] Step 6:

[0606] The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. This allows it to identify users who are compatible with each other. The input is the chat logs of multiple users, and the output is a list of users with common topics and similar conversation styles.

[0607] Step 7:

[0608] The server proposes conversations between users with good compatibility and recommends digital content based on the user's interests using a recommendation method. The input is a list of users with good compatibility and analyzed feature data, and the output is recommended digital content.

[0609] Step 8:

[0610] The server provides the generated conversations and recommended digital content to the user's device. The user can check and use the provided conversations and content on their own device. The input is the recommended digital content and the generated conversation data, and the output is data transmission to the user's device.

[0611] Step 9:

[0612] Users provide feedback on the generated conversations and recommended content. The server collects the feedback information and performs retraining to continuously improve the accuracy of the generative AI model and recommendation method. The input is user feedback, and the output is an improved generative AI model and recommendation method.

[0613] Through the above process, the system analyzes users' SNS chat logs, generates natural conversations, matches users with compatible interests, and even recommends digital content based on the user's interests.

[0614] 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.

[0615] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[0616] 1. Upload user chat logs

[0617] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[0618] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[0619] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[0620] 2. Chat log analysis

[0621] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[0622] Natural Language Processing (NLP): The server uses Natural Language Processing (NLP) libraries to analyze the text data, including topic extraction (e.g., sports, music, daily life, etc.), context understanding, and sentiment analysis.

[0623] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[0624] 3. Conversation Generation

[0625] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model is used to generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[0626] 4. Automatic matching function

[0627] Server: The system analyzes chat logs of multiple users to find users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to further refine matching.

[0628] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching users A and B who are both sports fans and have recently shared positive feelings could generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[0629] 5. Providing generated conversations

[0630] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[0631] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[0632] 6. Continuous learning and improvement

[0633] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. This improves the accuracy of conversation generation and user satisfaction.

[0634] Examples:

[0635] 1. User A's first use:

[0636] User A uploads the LINE chat log to the system from his / her own device.

[0637] The server receives the uploaded chat logs and analyzes them using NLP techniques and an emotion engine.

[0638] Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and User A's positive emotions and provides it to User A.

[0639] User A uses the generated conversation to smoothly communicate with his friends.

[0640] 2. Matching User A and User B:

[0641] The server analyzes the chat logs and emotional states of User A and User B and detects that they have common interests (e.g., sports) and emotions.

[0642] The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[0643] As described above, this invention is a system that analyzes users' chat logs and emotional states to generate natural conversations and automatically match users with compatible partners, thereby realizing efficient and natural communication and increasing the probability of users meeting each other.

[0644] The processing flow will be explained below.

[0645] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[0646] Step 1:

[0647] User: Select the chat log files of social networking services on your device.

[0648] Step 2:

[0649] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[0650] Step 3:

[0651] Server: Receives chat log files sent from user devices.

[0652] Step 4:

[0653] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[0654] Step 5:

[0655] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[0656] Step 6:

[0657] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[0658] Step 7:

[0659] Server: Based on the analyzed data and the emotion analysis results of the emotion engine, the generative AI model is used to automatically generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[0660] Step 8:

[0661] Server: Sends the generated conversation to the user's device.

[0662] Step 9:

[0663] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[0664] Step 10:

[0665] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0666] Step 11:

[0667] Emotion Engine: Evaluates the user's real-time emotional state and uses this information to make more refined matches.

[0668] Step 12:

[0669] Server: Matches users who have been detected as having good chemistry with each other and suggests conversations based on common topics and emotions. For example, matching User A and User B, who are both sports fans and have recently shared positive emotions, generates a conversation such as, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[0670] Step 13:

[0671] Server: Sends suggested conversations to matched users' devices.

[0672] Step 14:

[0673] Device: The user reviews the suggested conversation and uses it for actual communication.

[0674] Step 15:

[0675] Users: Provide feedback on the generated conversation.

[0676] Step 16:

[0677] Terminal: Sends user feedback information to the server.

[0678] Step 17:

[0679] Server: Based on the feedback information, the generative AI model and emotion engine are retrained to improve the accuracy of conversation generation and user satisfaction.

[0680] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners. By incorporating an emotion engine, more appropriate and sophisticated communication that reflects the user's emotional state becomes possible.

[0681] Example 2

[0682] 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."

[0683] Conventional systems were unable to fully utilize user emotions and past chat logs, making it difficult to generate natural conversations and match users with compatible partners. Furthermore, the accuracy of the generated conversations was low, resulting in a lack of user satisfaction.

[0684] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a chat log of a communication service from a user terminal, means for analyzing the received chat log by natural language processing, means for automatically generating natural conversation corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversation to the user terminal, means for analyzing the chat logs of multiple users and detecting users who share common topics or similar conversation styles, means for analyzing user emotions and improving the generated conversation and matching accuracy, and means for suggesting conversations with compatible users. This makes it possible to generate natural conversations and achieve a compatible match between users.

[0685] A "user terminal" is a communication device used by a user, such as a smartphone or a personal computer.

[0686] "Communication service" refers to a platform for users to exchange messages and share information via the Internet.

[0687] "Chat log" refers to the history of conversations and messages a user has on a communication service.

[0688] "Natural Language Processing (NLP)" refers to the technology that enables computers to understand and analyze the natural language used by humans.

[0689] A "generative AI model" refers to an artificial intelligence framework that learns the user's conversation style and content based on the results of data analysis, and generates natural conversations.

[0690] "Sentiment analysis" refers to the technology of identifying and assessing a user's emotional state from text data.

[0691] "Matching method" refers to a function that detects and suggests users with common interests and conversation styles based on analyzed data.

[0692] "Retraining" refers to the process of gathering user feedback and continually improving the accuracy of the generative AI model.

[0693] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[0694] "Topic extraction" refers to the process of automatically identifying major themes or topics from text data.

[0695] "Contextual understanding" refers to the process of understanding the content and background of text data and interpreting its appropriate meaning.

[0696] "Sentiment analysis" refers to the technology of analyzing emotional keywords and tones in text data to evaluate user emotions.

[0697] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[0698] A user uploads their SNS (e.g., LINE) chat log from their device to the system. The device provides an interface for the user to send the chat log file selected by the user to the server. This includes a file selection screen and an upload button. The received chat log file is temporarily stored by the server.

[0699] The server decodes the received chat log file and extracts the textual conversation data. It then uses a natural language processing (NLP) library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. It then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the sentiment of the user's chat log.

[0700] Once the analysis is complete, the server uses a generative AI model (e.g., GPT-3 or GPT-4) to generate natural-sounding conversations that correspond to the user's past conversational style and content. Specifically, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[0701] The system also analyzes chat logs from multiple users to detect users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to refine matching. Once a match is made, the system suggests conversations between users who are compatible. For example, it could match User A and User B, who both love sports and have recently shared positive emotions, and generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[0702] The generated conversation is sent from the server to the user's terminal, and the user can check the generated conversation on their own terminal and actually communicate with other users. The user terminal provides an interface that makes it easy to check and use the generated conversation.

[0703] Additionally, users can provide feedback on the generated conversations, which is sent to the server and used to continuously learn and improve the generative AI model and emotion engine, thereby improving the accuracy of conversation generation and user satisfaction.

[0704] Example prompt sentence:

[0705] "User A frequently talks about sports and has recently shown positive emotions. Generate a conversation appropriate for him / her."

[0706] "Based on User B's chat logs, generate natural conversations about topics that interest him / her."

[0707] By implementing the invention in this manner, efficient and natural communication is realized, increasing the probability of users meeting each other.

[0708] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0709] Step 1: Upload user chat logs

[0710] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The input is the chat log file, and the output is the data sent to the server.

[0711] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server. This includes a file selection screen and an upload button. Specifically, the terminal reads the file according to the user's selection and sends it to the server.

[0712] Step 2: Receiving and saving chat logs

[0713] Server: The server receives the chat log file sent from the user's device and temporarily stores it. The input is the chat log file sent from the device, and the output is the saved chat log data. Specifically, the server decodes the received data and stores it in its internal storage.

[0714] Step 3: Analyzing the chat logs

[0715] Server: The server decodes the received chat log file and extracts the textual conversation data. The input is the saved chat log data, and the output is the textual conversation data. Specifically, the server uses a decoding algorithm to extract the textual data.

[0716] Natural Language Processing (NLP): The server uses an NLP library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. The input is the conversation data in text format, and the output is the analyzed data. Specifically, the NLP engine analyzes the text and extracts the required information.

[0717] Emotion Engine: Furthermore, the emotion engine is used to analyze emotions from the user's chat log. The input is text data, and the output is the emotion analysis result. Specifically, the emotion engine detects and evaluates the tone and emotional keywords in the text.

[0718] Step 4: Conversation generation

[0719] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model (e.g., GPT-3, GPT-4) is used to generate natural-sounding conversations that correspond to the user's past conversational style and content. The input is the analyzed data and the emotion analysis results, and the output is the generated conversation. Specifically, the generative AI model generates a conversation based on the specified prompt sentence.

[0720] Example: Based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that team X won recently!"

[0721] Step 5: Auto-matching function

[0722] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is chat log data of multiple users, and the output is a list of users with common topics and similar conversation styles. The emotion engine also evaluates the user's real-time emotional state. Specifically, the server uses a database to compare and analyze user characteristics.

[0723] Matching method: The system suggests conversations with users who are compatible with the system. The input is a list of compatible users, and the output is the suggested conversations. Specifically, the generative AI model generates conversations that reflect the interests and emotions of users.

[0724] Example: The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[0725] Step 6: Serving the generated conversation

[0726] Server: Sends the generated conversation to the user terminal. The input is the generated conversation, and the output is the data to be sent to the user terminal. In concrete terms, the server uses a communication protocol to send the generated conversation data to the user terminal.

[0727] Terminal: Users can view conversations generated on their own terminals and actually communicate with other users. The input is the conversation data sent from the server, and the output is the conversation content displayed on the user's screen. Specifically, the terminal analyzes the received data and displays it on the user interface.

[0728] Step 7: Continuous learning and improvement

[0729] Retraining means: Users can provide feedback on the generated conversation. This feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. The input is the user's feedback data, and the output is an improved generative model. Specifically, the server analyzes the collected feedback and incorporates it into the model's retraining process.

[0730] (Application example 2)

[0731] 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."

[0732] Conventional social networking services and chat log analysis systems are limited to generating natural conversations between users and matching users with similar interests, but do not adequately address personalized customer engagement or product recommendations in virtual stores. Therefore, a system that can increase user satisfaction and efficiently recommend products is needed. Furthermore, a system that can deeply understand users' emotions and interests and provide effective dialogue and services based on this understanding is also required.

[0733] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0734] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for suggesting conversations with the detected users who are compatible, means for providing customer engagement based on the user's history data so that the user can interact with a virtual agent in a virtual store, and means for suggesting products based on the results of the customer engagement, thereby enabling natural conversations and services that are highly satisfying for the user.

[0735] "User Device" means the electronic device used by a User to upload chat logs and view generated conversations.

[0736] A "social networking service" is an online platform that enables users to communicate with each other.

[0737] A "chat log" is a text-based conversation history that a user has on a social networking service.

[0738] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0739] The "generator" is a means for automatically generating natural conversations that correspond to the user's past conversation style and content.

[0740] A "matching method" is a method for analyzing chat logs of multiple users to detect users who share common topics or similar conversation styles.

[0741] A "virtual store" is a platform that provides store-like services and products online.

[0742] "Customer engagement" refers to the activity of a virtual agent interacting with a user to suggest products and provide services based on the user's interests and needs.

[0743] A "generative AI model" is an artificial intelligence model that analyzes a user's past conversation style and emotional state to generate natural conversations.

[0744] "History data" refers to data on a user's past chat logs and service usage history.

[0745] "Product suggestion means" refers to a means for suggesting appropriate products and services based on analyzed user data.

[0746] This invention is a system that receives chat logs from social networking services from user devices, analyzes them using natural language processing and an emotion engine, generates natural conversations using a generative AI model, and provides them to users. Furthermore, it is also possible to engage with customers and suggest products based on user history data in a virtual store.

[0747] System configuration

[0748] 1. User device: A device where users upload chat logs and view generated conversations and customer engagement results, such as a smartphone.

[0749] 2. Server: Receives chat logs, analyzes them, and generates conversations using a generative AI model. It also has the ability to analyze chat logs from multiple users and perform matching.

[0750] 3. Natural Language Processing (NLP): Use libraries such as Spacy to perform topic extraction, contextual understanding, and sentiment analysis of chat log text.

[0751] 4. Generative AI models: Use models such as GPT-2 to generate natural conversations and suggestions based on the analysis results.

[0752] 5. Database: A data storage device for storing user history data, chat logs, and sentiment analysis results, and accessing them as needed.

[0753] Program processing

[0754] 1. Receiving and saving chat logs: The server receives chat logs sent from the user devices and saves them in a database. This process uses a web framework such as Flask.

[0755] 2. Chat log analysis: The server analyzes the saved chat logs using an NLP library (Spacy) to extract topics, understand context, and analyze sentiment.

[0756] 3. Conversation generation: Based on the analysis results and the output of the emotion engine, a generative AI model (GPT-2) is used to generate natural conversations.

[0757] 4. Matching: The server analyzes chat logs of multiple users, detects and suggests users with common topics and similar conversation styles.

[0758] 5. Customer engagement: In virtual stores, personalized product recommendations are made through interactions between users and virtual agents based on historical user data.

[0759] Specific examples

[0760] 1. Example of User A's use:

[0761] User A uploads the chat log from his smartphone.

[0762] The server receives the data and performs topic extraction and sentiment analysis using Spacy.

[0763] The GPT-2 model generates and serves up the conversation, "What do you think about sports these days?"

[0764] 2. Matching User A and User B:

[0765] The server analyzes the chat logs of user A and user B.

[0766] "Sports" is detected as a common topic and a match is suggested.

[0767] Generates the conversation, "Did you watch the recent game?"

[0768] 3. Customer engagement in virtual stores:

[0769] User A accesses the virtual store.

[0770] The server performs customer engagement based on User A's historical data.

[0771] GPT-2 suggests, "How about this month's promotional item?"

[0772] Prompt Sentence Examples

[0773] "Analyze the conversation logs of the following users to identify topics of interest and sentiment. Generate conversation prompts based on the results. Log: [Paste user chat log here]"

[0774] As described above, the present invention analyzes a user's chat history and emotional data to generate natural conversations and provide personalized product recommendations in a virtual store, thereby providing a more fulfilling experience for the user.

[0775] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0776] Step 1:

[0777] A user uploads a chat log from a social networking service (SNS) to the system from their device. Specifically, they select the chat log file on the file selection screen on their device and press the upload button. The device then sends the selected chat log file to the server. The input of this step is the user's chat log file, and the output is the file sent to the server.

[0778] Step 2:

[0779] The server receives the chat log file sent from the terminal and stores it in the database. The received file is temporarily stored and used for subsequent processing. The input of this step is the user's chat log file, and the output is the file stored in the database.

[0780] Step 3:

[0781] The server retrieves the saved chat log files and analyzes them using a natural language processing (NLP) library (e.g., Spacy). Specifically, it converts the files into text format and performs topic extraction, context understanding, and sentiment analysis. The input of this step is the chat log text, and the output is the analyzed data.

[0782] Step 4:

[0783] Based on the analyzed data, a generative AI model (e.g., GPT-2) is used to generate natural-sounding conversations. The server uses the analysis results and the output of the emotion engine as inputs for the model and obtains the generated text. The inputs for this step are the analysis data and the results of the emotion engine, and the output is the generated conversation text.

[0784] Step 5:

[0785] The server sends the generated conversation text to the user terminal. The user checks the generated conversation on the terminal and communicates with other users as needed. The input of this step is the generated conversation text, and the output is the text sent to the user terminal.

[0786] Step 6:

[0787] The server analyzes chat logs of multiple users to find users with common topics and similar conversation styles. Specifically, it compares and analyzes multiple chat logs to identify users with high similarities. The input of this step is multiple chat log data, and the output is matched user pairs.

[0788] Step 7:

[0789] The server then proposes conversations between users with good compatibility. Based on the analyzed data, it uses a generative AI model to generate and propose relevant conversations. The inputs of this step are the matched user pairs and the analyzed data, and the output is the proposed conversation text.

[0790] Step 8:

[0791] In the virtual store, the server generates a dialogue for customer engagement based on the user's history data. Through the generated dialogue, it makes product and service suggestions. The input of this step is the user's history data, and the output is the generated engagement conversation text and suggestion content.

[0792] Step 9:

[0793] The user provides feedback on the generated conversations and suggestions. The server collects this feedback and uses it to retrain the generative AI model and emotion engine. The input of this step is the user's feedback, and the output is an improvement in the model's accuracy.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] [Third embodiment]

[0798] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0799] 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.

[0800] 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).

[0801] 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.

[0802] 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.

[0803] 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).

[0804] 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. 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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."

[0810] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0811] 1. Upload user chat logs

[0812] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[0813] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[0814] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[0815] 2. Chat log analysis

[0816] Server: The server decodes the received chat logs and extracts the textual conversation data, which includes the process of converting the chat data into text.

[0817] Natural Language Processing (NLP): The server uses natural language processing (NLP) libraries to analyze text data, specifically to understand the content of the conversation through conversation topic extraction (e.g., sports, music, daily life, etc.), contextual understanding, and sentiment analysis.

[0818] 3. Conversation Generation

[0819] Server: Based on the analyzed data, a generative AI model is used to generate natural conversations that match the user's past conversational style and content. For example, based on the analysis result that "User A often talks about sports," the generative AI model generates a conversation such as "It looks like X team won recently!"

[0820] 4. Automatic matching function

[0821] Server: The system analyzes chat logs of multiple users to find users who share common topics and similar conversation styles, allowing users to find compatible users.

[0822] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching sports-loving users A and B generates a conversation such as, "Have you seen the game of team X?"

[0823] 5. Providing generated conversations

[0824] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[0825] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[0826] 6. Continuous learning and improvement

[0827] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model. This improves the accuracy of conversation generation and user satisfaction.

[0828] Examples:

[0829] 1. User A's first use:

[0830] User A uploads the LINE chat log to the system from his / her own device.

[0831] The server receives the uploaded chat logs and analyzes them using NLP technology.

[0832] Based on the analysis results, the generative AI model generates conversations about topics such as "recent sports news" and provides them to User A.

[0833] User A uses the generated conversation to smoothly communicate with his friends.

[0834] 2. Matching User A and User B:

[0835] The server analyzes the chat logs of user A and user B and detects that they have a common interest (e.g., sports).

[0836] The system uses a generative AI model to generate conversations between users A and B that share common interests and suggests matches.

[0837] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This allows for efficient and natural communication and increases the probability of users meeting each other.

[0838] The processing flow will be explained below.

[0839] Step 1:

[0840] User: Select the chat log files of social networking services on your device.

[0841] Step 2:

[0842] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[0843] Step 3:

[0844] Server: Receives chat log files sent from user devices.

[0845] Step 4:

[0846] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[0847] Step 5:

[0848] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[0849] Step 6:

[0850] Server: Based on the analyzed data, it uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversation style and content.

[0851] Step 7:

[0852] Server: Sends the generated conversation to the user's device.

[0853] Step 8:

[0854] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[0855] Step 9:

[0856] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0857] Step 10:

[0858] Server: Matches detected users with similar interests and uses generative AI models to suggest conversations based on common topics.

[0859] Step 11:

[0860] Server: Sends suggested conversations to matched users' devices.

[0861] Step 12:

[0862] Device: The user reviews the suggested conversation and uses it for actual communication.

[0863] Step 13:

[0864] Users: Provide feedback on the generated conversation.

[0865] Step 14:

[0866] Terminal: Sends user feedback information to the server.

[0867] Step 15:

[0868] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[0869] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners.

[0870] Example 1

[0871] 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."

[0872] Conventional chat log analysis systems for social networking services have had difficulty generating natural conversations based on a user's conversation style and interests, and automatically matching them with compatible partners. Furthermore, there has been a lack of feedback collection and continuous learning to improve the accuracy of generated conversations and matching, making it difficult to improve the user experience.

[0873] 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.

[0874] In this invention, the server includes means for receiving a data file from a user terminal, means for analyzing the received data file using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing data files of multiple users and detecting users with common topics or similar conversation styles, and means for suggesting conversations with the detected users who are compatible. This enables the generation of natural conversations based on the user's conversation style and interests and automatic matching with compatible partners, and further enables continuous learning and improvement based on feedback from the generated conversations, thereby improving the user experience.

[0875] A "user terminal" is a computing device from which a user selects and uploads data files.

[0876] A "data file" is a file that records user conversations, such as chat logs on social media.

[0877] "Natural language processing" refers to the technology of analyzing and processing natural language using a computer, and includes topic extraction, context understanding, sentiment analysis, etc.

[0878] "Generation means" refers to the function of automatically generating natural conversation based on the analyzed data.

[0879] The "transmission means" is a communication means for transmitting the generated conversation to the user terminal.

[0880] "Matching method" refers to the function that analyzes the data files of multiple users and detects users who share common topics or similar conversation styles.

[0881] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[0882] "Learning means" refers to a function that continuously improves the accuracy of the generation means based on feedback information.

[0883] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0884] Hardware and software used

[0885] User terminal: The user terminal provides an interface for users to select and upload chat log files to the system. Specifically, the user terminal can be a computer device such as a PC, smartphone, or tablet.

[0886] Server: The server is the central server responsible for analyzing received chat logs and performing conversation generation and matching functions. The following software libraries and services are installed on the server:

[0887] Natural Language Processing (NLP) libraries: NLTK, spaCy, etc.

[0888] Generative AI models: OpenAI's GPT series, etc.

[0889] Database system: MySQL, PostgreSQL, etc.

[0890] Specific data processing and calculation

[0891] 1. Upload user chat logs

[0892] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system.

[0893] Terminal: The terminal provides a file selection screen and an upload button, and sends the chat log file selected by the user to the server.

[0894] Server: The server receives the uploaded chat log files and temporarily stores them in a database.

[0895] 2. Chat log analysis

[0896] Server: The server decodes the received chat logs and extracts the text data. This includes converting chat data into text data.

[0897] Natural Language Processing (NLP): The server uses natural language processing libraries such as NLTK and spaCy to perform topic extraction, contextual understanding, and sentiment analysis of the text data.

[0898] 3. Conversation Generation

[0899] Server: Based on the analyzed data, a generative AI model (e.g., GPT-3) is used to generate natural conversations that match the user's past conversation style and content. For example, it generates a prompt such as, "User A's chat log analysis results: Many sports topics. Please generate a conversation related to recent sports news."

[0900] 4. Automatic matching function

[0901] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[0902] Matching method: For example, matching users who like sports with each other and generating conversations such as, "Have you seen a game by team X?"

[0903] 5. Providing generated conversations

[0904] Server: Sends the generated conversation to the user's device.

[0905] Terminal: The terminal displays the received conversations in a user interface, and the user can use the generated conversations to communicate with other users.

[0906] 6. Continuous learning and improvement

[0907] User: Users provide feedback on the generated conversations, including ratings and opinions.

[0908] Terminal: The terminal sends feedback to the server.

[0909] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[0910] Specific examples

[0911] 1. User A's first use:

[0912] User: User A uploads LINE chat logs to the system from his / her own device.

[0913] Server: The server receives the uploaded chat logs and analyzes them using NLP technology.

[0914] Server: Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and provides it to User A.

[0915] User: User A uses the generated conversation to smoothly communicate with his friends.

[0916] 2. Matching User A and User B:

[0917] Server: The server analyzes the chat logs of user A and user B and discovers that they have a common interest (e.g., sports).

[0918] Server: Using a generative AI model, it generates conversations between users A and B who share common interests and suggests matches.

[0919] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This enables efficient and natural communication, and is expected to increase opportunities for users to meet each other.

[0920] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0921] Step 1: Upload user chat logs

[0922] User: A user can upload their SNS (e.g., LINE) chat logs to the system from their device. The user selects the chat log file using the device interface.

[0923] Terminal: The terminal provides a function to send the selected chat log file to the server using the HTTP POST method. The input is the chat log file selected by the user, and the output is a file send request to the server.

[0924] Server: The server receives the uploaded chat log file and temporarily stores it in a database. The input is the chat log file sent from the terminal, and the output is the reference information of the saved file.

[0925] Step 2: Analyzing the chat logs

[0926] Server: The server reads the saved chat log file, decodes it, and extracts the textual conversation data. The input is the saved chat log file, and the output is the extracted text data.

[0927] Natural Language Processing (NLP) Library: The server uses NLP libraries such as NLTK and spaCy to analyze text data. The specific analysis process includes topic extraction, context understanding, and sentiment analysis. The input is the extracted text data, and based on this, it outputs metadata such as topics and sentiment.

[0928] Step 3: Conversation generation

[0929] Server: The server creates an input prompt for the generative AI model (e.g., GPT-3) based on the analysis results. For example, it generates a prompt such as, "Results of analyzing user A's chat log: Many sports topics. Please generate conversations related to recent sports news." The input is the analysis results, and the output is the prompt.

[0930] Generative AI model: A generative AI model generates new conversational text based on a prompt. The input is the prompt, and the output is the generated conversational text.

[0931] Step 4: Auto-matching function

[0932] Server: The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is the analysis results of multiple users, and the output is a list of matching candidates.

[0933] Matching method: Generate a conversation between the detected match candidates. For example, match sports-loving user A and user B and generate a conversation such as "Have you seen the game of team X?" The input is a list of match candidates, and the output is the matched conversation text.

[0934] Step 5: Serving the generated conversation

[0935] Server: Sends the generated conversation text to the user terminal. The input is the generated conversation text, and the output is an HTTP response to the user terminal.

[0936] Terminal: The terminal displays the received conversation text in a user interface for the user to review. The input is the conversation text sent from the server, and the output is the conversation displayed in the interface.

[0937] Step 6: Continuous learning and improvement

[0938] User: The user provides feedback on the generated conversation. The feedback includes ratings and opinions, and its quality contributes to re-learning in the next step. The input is the generated conversation and the user's ratings, and the output is feedback information.

[0939] Terminal: The terminal sends the feedback input by the user to the server. The input is the feedback information input by the user, and the output is a feedback transmission request to the server.

[0940] Server: The server retrains the generative AI model based on the feedback information. This improves the accuracy of the model and enables more natural conversation generation. The input is the feedback information, and the output is the retrained generative AI model.

[0941] (Application example 1)

[0942] 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."

[0943] Conventional social networking and content distribution services lacked the means to provide appropriate content recommendations based on users' interests or natural communication between users. They also lacked automatic matching functions that take into account users' conversational styles and interests, making it difficult to improve the user experience.

[0944] 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.

[0945] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for recommending digital content tailored to each user based on the user's interests, and means for providing the recommended digital content to the user terminal, thereby enabling appropriate content recommendations and natural communication for the user and improving the user experience.

[0946] "User terminal" refers to a device such as a computer or smartphone used to access social networking services and content.

[0947] A "social networking service" is an online platform that allows users to communicate with each other and share information via the Internet.

[0948] A "chat log" is a text record of conversations between users on a social networking service.

[0949] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0950] The "generation means" is a mechanism that automatically generates natural conversations that match the user's past conversation style and content based on the analyzed data.

[0951] The "matching method" is a system that analyzes the chat logs of multiple users and identifies users who share common topics or similar conversation styles.

[0952] "Digital content" refers to information such as text, audio, and video that is provided electronically.

[0953] A "recommendation method" is a system that suggests the most suitable digital content to each individual user based on the user's interests.

[0954] The "relearning means" is a mechanism that collects user feedback on the generated conversations and recommended content, and uses this to continuously improve the accuracy of the system.

[0955] "Topic extraction" is a technique for identifying major topics or themes from text data.

[0956] "Contextual understanding" is the technology of understanding the meaning of words and phrases in text based on their context and usage.

[0957] "Sentiment analysis" is a technique for inferring a user's emotional state from text data.

[0958] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[0959] 1. Upload user chat logs

[0960] Users upload their SNS chat logs from their own devices to the system. The devices provide an interface for users to send selected chat log files to the server. The server receives the chat log files sent from the user devices and temporarily stores them.

[0961] 2. Chat log analysis

[0962] The server decodes the received chat logs and extracts the text-formatted conversation data. This process includes converting the chat data into text. The server then analyzes the text data using a natural language processing (NLP) library. Specifically, it understands the content of the conversation through conversation topic extraction, context understanding, and sentiment analysis.

[0963] 3. Conversation Generation

[0964] Based on the analyzed data, the server uses a generative AI model to generate natural conversations that match the user's past conversation style and content. For example, based on the analysis result that "the user frequently talks about music," the generative AI model generates a conversation such as "Have you heard the latest hit songs?"

[0965] 4. Automatic matching function

[0966] The server analyzes chat logs of multiple users and detects users who share common topics and similar conversation styles. This allows users to discover users who are compatible with each other. The system then suggests conversations between users who are compatible with each other.

[0967] 5. Recommendation method

[0968] The server then recommends digital content based on the user's interests based on the analyzed data and the generated conversation, enabling the delivery of appropriate content to the user.

[0969] 6. Providing generated conversations and recommended content

[0970] The server sends the generated conversations and recommended content to the user's device, where the user can easily view and use the provided conversations and content on their device.

[0971] 7. Continuous learning and improvement

[0972] Users can provide feedback on the generated conversations and recommended content. The feedback information is sent to the server and used to continuously learn and improve the generative AI model and recommendation methods, thereby improving the accuracy of conversation generation and content recommendations.

[0973] Examples:

[0974] For example, if a user who likes sports uploads a chat log, the server will generate a conversation about "recent sports news" and provide it to the user. Based on this generated conversation, the server will recommend the latest sports news articles to the user and suggest communication with other users who have similar interests.

[0975] Example prompt sentence:

[0976] "Generate a conversation about the following topic:\nA log of people talking about recent soccer games"

[0977] Hardware and software used

[0978] Hardware: User device (smartphone or PC)

[0979] Software: Python (using scikit-learn as a natural language processing library and openai API for conversation generation)

[0980] As described above, this invention provides a system that improves the user experience by analyzing a user's SNS chat log, generating natural conversations, matching users with compatible users, and recommending digital content based on the user's interests.

[0981] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0982] Step 1:

[0983] A user uploads a chat log from a social networking service to the system from their own device. The user selects a chat log file and clicks the upload button to send the chat log to the server. The input is the chat log file selected by the user, and the output is the transmission of the chat log file to the server.

[0984] Step 2:

[0985] The server receives the chat log file sent from the user's device and temporarily stores it. The server performs a decoding process to convert the received chat log into text format. The input is the received chat log file, and the output is the text-format chat log data.

[0986] Step 3:

[0987] The server analyzes the saved chat logs using a natural language processing (NLP) library. Specifically, it performs topic extraction, context understanding, and sentiment analysis from the chat logs to identify user interests and trends. The input is the chat log data in text format, and the output is the analyzed feature data.

[0988] Step 4:

[0989] Based on the analyzed data, the server uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversational style and content. Prompts are used for generation, generating conversational sentences that match the user's interests. The input is the analyzed feature data and prompts, and the output is the generated natural conversation.

[0990] Step 5:

[0991] The server sends the generated natural conversation to the user's device. The user can then view the generated conversation on their own device and communicate with their friends. The input is the generated natural conversation, and the output is the transmission of the conversation data to the user's device.

[0992] Step 6:

[0993] The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. This allows it to identify users who are compatible with each other. The input is the chat logs of multiple users, and the output is a list of users with common topics and similar conversation styles.

[0994] Step 7:

[0995] The server proposes conversations between users with good compatibility and recommends digital content based on the user's interests using a recommendation method. The input is a list of users with good compatibility and analyzed feature data, and the output is recommended digital content.

[0996] Step 8:

[0997] The server provides the generated conversations and recommended digital content to the user's device. The user can check and use the provided conversations and content on their own device. The input is the recommended digital content and the generated conversation data, and the output is data transmission to the user's device.

[0998] Step 9:

[0999] Users provide feedback on the generated conversations and recommended content. The server collects the feedback information and performs retraining to continuously improve the accuracy of the generative AI model and recommendation method. The input is user feedback, and the output is an improved generative AI model and recommendation method.

[1000] Through the above process, the system analyzes users' SNS chat logs, generates natural conversations, matches users with compatible interests, and even recommends digital content based on the user's interests.

[1001] 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.

[1002] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[1003] 1. Upload user chat logs

[1004] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[1005] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[1006] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[1007] 2. Chat log analysis

[1008] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[1009] Natural Language Processing (NLP): The server uses Natural Language Processing (NLP) libraries to analyze the text data, including topic extraction (e.g., sports, music, daily life, etc.), context understanding, and sentiment analysis.

[1010] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[1011] 3. Conversation Generation

[1012] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model is used to generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[1013] 4. Automatic matching function

[1014] Server: The system analyzes chat logs of multiple users to find users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to further refine matching.

[1015] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching users A and B who are both sports fans and have recently shared positive feelings could generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[1016] 5. Providing generated conversations

[1017] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[1018] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[1019] 6. Continuous learning and improvement

[1020] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. This improves the accuracy of conversation generation and user satisfaction.

[1021] Examples:

[1022] 1. User A's first use:

[1023] User A uploads the LINE chat log to the system from his / her own device.

[1024] The server receives the uploaded chat logs and analyzes them using NLP techniques and an emotion engine.

[1025] Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and User A's positive emotions and provides it to User A.

[1026] User A uses the generated conversation to smoothly communicate with his friends.

[1027] 2. Matching User A and User B:

[1028] The server analyzes the chat logs and emotional states of User A and User B and detects that they have common interests (e.g., sports) and emotions.

[1029] The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[1030] As described above, this invention is a system that analyzes users' chat logs and emotional states to generate natural conversations and automatically match users with compatible partners, thereby realizing efficient and natural communication and increasing the probability of users meeting each other.

[1031] The processing flow will be explained below.

[1032] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[1033] Step 1:

[1034] User: Select the chat log files of social networking services on your device.

[1035] Step 2:

[1036] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[1037] Step 3:

[1038] Server: Receives chat log files sent from user devices.

[1039] Step 4:

[1040] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[1041] Step 5:

[1042] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[1043] Step 6:

[1044] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[1045] Step 7:

[1046] Server: Based on the analyzed data and the emotion analysis results of the emotion engine, the generative AI model is used to automatically generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[1047] Step 8:

[1048] Server: Sends the generated conversation to the user's device.

[1049] Step 9:

[1050] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[1051] Step 10:

[1052] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[1053] Step 11:

[1054] Emotion Engine: Evaluates the user's real-time emotional state and uses this information to make more refined matches.

[1055] Step 12:

[1056] Server: Matches users who have been detected as having good chemistry with each other and suggests conversations based on common topics and emotions. For example, matching User A and User B, who are both sports fans and have recently shared positive emotions, generates a conversation such as, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[1057] Step 13:

[1058] Server: Sends suggested conversations to matched users' devices.

[1059] Step 14:

[1060] Device: The user reviews the suggested conversation and uses it for actual communication.

[1061] Step 15:

[1062] Users: Provide feedback on the generated conversation.

[1063] Step 16:

[1064] Terminal: Sends user feedback information to the server.

[1065] Step 17:

[1066] Server: Based on the feedback information, the generative AI model and emotion engine are retrained to improve the accuracy of conversation generation and user satisfaction.

[1067] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners. By incorporating an emotion engine, more appropriate and sophisticated communication that reflects the user's emotional state becomes possible.

[1068] Example 2

[1069] 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."

[1070] Conventional systems were unable to fully utilize user emotions and past chat logs, making it difficult to generate natural conversations and match users with compatible partners. Furthermore, the accuracy of the generated conversations was low, resulting in a lack of user satisfaction.

[1071] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a chat log of a communication service from a user terminal, means for analyzing the received chat log by natural language processing, means for automatically generating natural conversation corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversation to the user terminal, means for analyzing the chat logs of multiple users and detecting users who share common topics or similar conversation styles, means for analyzing user emotions and improving the generated conversation and matching accuracy, and means for suggesting conversations with compatible users. This makes it possible to generate natural conversations and achieve a compatible match between users.

[1072] A "user terminal" is a communication device used by a user, such as a smartphone or a personal computer.

[1073] "Communication service" refers to a platform for users to exchange messages and share information via the Internet.

[1074] "Chat log" refers to the history of conversations and messages a user has on a communication service.

[1075] "Natural Language Processing (NLP)" refers to the technology that enables computers to understand and analyze the natural language used by humans.

[1076] A "generative AI model" refers to an artificial intelligence framework that learns the user's conversation style and content based on the results of data analysis, and generates natural conversations.

[1077] "Sentiment analysis" refers to the technology of identifying and assessing a user's emotional state from text data.

[1078] "Matching method" refers to a function that detects and suggests users with common interests and conversation styles based on analyzed data.

[1079] "Retraining" refers to the process of gathering user feedback and continually improving the accuracy of the generative AI model.

[1080] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[1081] "Topic extraction" refers to the process of automatically identifying major themes or topics from text data.

[1082] "Contextual understanding" refers to the process of understanding the content and background of text data and interpreting its appropriate meaning.

[1083] "Sentiment analysis" refers to the technology of analyzing emotional keywords and tones in text data to evaluate user emotions.

[1084] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[1085] A user uploads their SNS (e.g., LINE) chat log from their device to the system. The device provides an interface for the user to send the chat log file selected by the user to the server. This includes a file selection screen and an upload button. The received chat log file is temporarily stored by the server.

[1086] The server decodes the received chat log file and extracts the textual conversation data. It then uses a natural language processing (NLP) library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. It then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the sentiment of the user's chat log.

[1087] Once the analysis is complete, the server uses a generative AI model (e.g., GPT-3 or GPT-4) to generate natural-sounding conversations that correspond to the user's past conversational style and content. Specifically, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[1088] The system also analyzes chat logs from multiple users to detect users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to refine matching. Once a match is made, the system suggests conversations between users who are compatible. For example, it could match User A and User B, who both love sports and have recently shared positive emotions, and generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[1089] The generated conversation is sent from the server to the user's terminal, and the user can check the generated conversation on their own terminal and actually communicate with other users. The user terminal provides an interface that makes it easy to check and use the generated conversation.

[1090] Additionally, users can provide feedback on the generated conversations, which is sent to the server and used to continuously learn and improve the generative AI model and emotion engine, thereby improving the accuracy of conversation generation and user satisfaction.

[1091] Example prompt sentence:

[1092] "User A frequently talks about sports and has recently shown positive emotions. Generate a conversation appropriate for him / her."

[1093] "Based on User B's chat logs, generate natural conversations about topics that interest him / her."

[1094] By implementing the invention in this manner, efficient and natural communication is realized, increasing the probability of users meeting each other.

[1095] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1096] Step 1: Upload user chat logs

[1097] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The input is the chat log file, and the output is the data sent to the server.

[1098] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server. This includes a file selection screen and an upload button. Specifically, the terminal reads the file according to the user's selection and sends it to the server.

[1099] Step 2: Receiving and saving chat logs

[1100] Server: The server receives the chat log file sent from the user's device and temporarily stores it. The input is the chat log file sent from the device, and the output is the saved chat log data. Specifically, the server decodes the received data and stores it in its internal storage.

[1101] Step 3: Analyzing the chat logs

[1102] Server: The server decodes the received chat log file and extracts the textual conversation data. The input is the saved chat log data, and the output is the textual conversation data. Specifically, the server uses a decoding algorithm to extract the textual data.

[1103] Natural Language Processing (NLP): The server uses an NLP library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. The input is the conversation data in text format, and the output is the analyzed data. Specifically, the NLP engine analyzes the text and extracts the required information.

[1104] Emotion Engine: Furthermore, the emotion engine is used to analyze emotions from the user's chat log. The input is text data, and the output is the emotion analysis result. Specifically, the emotion engine detects and evaluates the tone and emotional keywords in the text.

[1105] Step 4: Conversation generation

[1106] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model (e.g., GPT-3, GPT-4) is used to generate natural-sounding conversations that correspond to the user's past conversational style and content. The input is the analyzed data and the emotion analysis results, and the output is the generated conversation. Specifically, the generative AI model generates a conversation based on the specified prompt sentence.

[1107] Example: Based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that team X won recently!"

[1108] Step 5: Auto-matching function

[1109] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is chat log data of multiple users, and the output is a list of users with common topics and similar conversation styles. The emotion engine also evaluates the user's real-time emotional state. Specifically, the server uses a database to compare and analyze user characteristics.

[1110] Matching method: The system suggests conversations with users who are compatible with the system. The input is a list of compatible users, and the output is the suggested conversations. Specifically, the generative AI model generates conversations that reflect the interests and emotions of users.

[1111] Example: The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[1112] Step 6: Serving the generated conversation

[1113] Server: Sends the generated conversation to the user terminal. The input is the generated conversation, and the output is the data to be sent to the user terminal. In concrete terms, the server uses a communication protocol to send the generated conversation data to the user terminal.

[1114] Terminal: Users can view conversations generated on their own terminals and actually communicate with other users. The input is the conversation data sent from the server, and the output is the conversation content displayed on the user's screen. Specifically, the terminal analyzes the received data and displays it on the user interface.

[1115] Step 7: Continuous learning and improvement

[1116] Retraining means: Users can provide feedback on the generated conversation. This feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. The input is the user's feedback data, and the output is an improved generative model. Specifically, the server analyzes the collected feedback and incorporates it into the model's retraining process.

[1117] (Application example 2)

[1118] 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."

[1119] Conventional social networking services and chat log analysis systems are limited to generating natural conversations between users and matching users with similar interests, but do not adequately address personalized customer engagement or product recommendations in virtual stores. Therefore, a system that can increase user satisfaction and efficiently recommend products is needed. Furthermore, a system that can deeply understand users' emotions and interests and provide effective dialogue and services based on this understanding is also required.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1121] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for suggesting conversations with the detected users who are compatible, means for providing customer engagement based on the user's history data so that the user can interact with a virtual agent in a virtual store, and means for suggesting products based on the results of the customer engagement, thereby enabling natural conversations and services that are highly satisfying for the user.

[1122] "User Device" means the electronic device used by a User to upload chat logs and view generated conversations.

[1123] A "social networking service" is an online platform that enables users to communicate with each other.

[1124] A "chat log" is a text-based conversation history that a user has on a social networking service.

[1125] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1126] The "generator" is a means for automatically generating natural conversations that correspond to the user's past conversation style and content.

[1127] A "matching method" is a method for analyzing chat logs of multiple users to detect users who share common topics or similar conversation styles.

[1128] A "virtual store" is a platform that provides store-like services and products online.

[1129] "Customer engagement" refers to the activity of a virtual agent interacting with a user to suggest products and provide services based on the user's interests and needs.

[1130] A "generative AI model" is an artificial intelligence model that analyzes a user's past conversation style and emotional state to generate natural conversations.

[1131] "History data" refers to data on a user's past chat logs and service usage history.

[1132] "Product suggestion means" refers to a means for suggesting appropriate products and services based on analyzed user data.

[1133] This invention is a system that receives chat logs from social networking services from user devices, analyzes them using natural language processing and an emotion engine, generates natural conversations using a generative AI model, and provides them to users. Furthermore, it is also possible to engage with customers and suggest products based on user history data in a virtual store.

[1134] System configuration

[1135] 1. User device: A device where users upload chat logs and view generated conversations and customer engagement results, such as a smartphone.

[1136] 2. Server: Receives chat logs, analyzes them, and generates conversations using a generative AI model. It also has the ability to analyze chat logs from multiple users and perform matching.

[1137] 3. Natural Language Processing (NLP): Use libraries such as Spacy to perform topic extraction, contextual understanding, and sentiment analysis of chat log text.

[1138] 4. Generative AI models: Use models such as GPT-2 to generate natural conversations and suggestions based on the analysis results.

[1139] 5. Database: A data storage device for storing user history data, chat logs, and sentiment analysis results, and accessing them as needed.

[1140] Program processing

[1141] 1. Receiving and saving chat logs: The server receives chat logs sent from the user devices and saves them in a database. This process uses a web framework such as Flask.

[1142] 2. Chat log analysis: The server analyzes the saved chat logs using an NLP library (Spacy) to extract topics, understand context, and analyze sentiment.

[1143] 3. Conversation generation: Based on the analysis results and the output of the emotion engine, a generative AI model (GPT-2) is used to generate natural conversations.

[1144] 4. Matching: The server analyzes chat logs of multiple users, detects and suggests users with common topics and similar conversation styles.

[1145] 5. Customer engagement: In virtual stores, personalized product recommendations are made through interactions between users and virtual agents based on historical user data.

[1146] Specific examples

[1147] 1. Example of User A's use:

[1148] User A uploads the chat log from his smartphone.

[1149] The server receives the data and performs topic extraction and sentiment analysis using Spacy.

[1150] The GPT-2 model generates and serves up the conversation, "What do you think about sports these days?"

[1151] 2. Matching User A and User B:

[1152] The server analyzes the chat logs of user A and user B.

[1153] "Sports" is detected as a common topic and a match is suggested.

[1154] Generates the conversation, "Did you watch the recent game?"

[1155] 3. Customer engagement in virtual stores:

[1156] User A accesses the virtual store.

[1157] The server performs customer engagement based on User A's historical data.

[1158] GPT-2 suggests, "How about this month's promotional item?"

[1159] Prompt Sentence Examples

[1160] "Analyze the conversation logs of the following users to identify topics of interest and sentiment. Generate conversation prompts based on the results. Log: [Paste user chat log here]"

[1161] As described above, the present invention analyzes a user's chat history and emotional data to generate natural conversations and provide personalized product recommendations in a virtual store, thereby providing a more fulfilling experience for the user.

[1162] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1163] Step 1:

[1164] A user uploads a chat log from a social networking service (SNS) to the system from their device. Specifically, they select the chat log file on the file selection screen on their device and press the upload button. The device then sends the selected chat log file to the server. The input of this step is the user's chat log file, and the output is the file sent to the server.

[1165] Step 2:

[1166] The server receives the chat log file sent from the terminal and stores it in the database. The received file is temporarily stored and used for subsequent processing. The input of this step is the user's chat log file, and the output is the file stored in the database.

[1167] Step 3:

[1168] The server retrieves the saved chat log files and analyzes them using a natural language processing (NLP) library (e.g., Spacy). Specifically, it converts the files into text format and performs topic extraction, context understanding, and sentiment analysis. The input of this step is the chat log text, and the output is the analyzed data.

[1169] Step 4:

[1170] Based on the analyzed data, a generative AI model (e.g., GPT-2) is used to generate natural-sounding conversations. The server uses the analysis results and the output of the emotion engine as inputs for the model and obtains the generated text. The inputs for this step are the analysis data and the results of the emotion engine, and the output is the generated conversation text.

[1171] Step 5:

[1172] The server sends the generated conversation text to the user terminal. The user checks the generated conversation on the terminal and communicates with other users as needed. The input of this step is the generated conversation text, and the output is the text sent to the user terminal.

[1173] Step 6:

[1174] The server analyzes chat logs of multiple users to find users with common topics and similar conversation styles. Specifically, it compares and analyzes multiple chat logs to identify users with high similarities. The input of this step is multiple chat log data, and the output is matched user pairs.

[1175] Step 7:

[1176] The server then proposes conversations between users with good compatibility. Based on the analyzed data, it uses a generative AI model to generate and propose relevant conversations. The inputs of this step are the matched user pairs and the analyzed data, and the output is the proposed conversation text.

[1177] Step 8:

[1178] In the virtual store, the server generates a dialogue for customer engagement based on the user's history data. Through the generated dialogue, it makes product and service suggestions. The input of this step is the user's history data, and the output is the generated engagement conversation text and suggestion content.

[1179] Step 9:

[1180] The user provides feedback on the generated conversations and suggestions. The server collects this feedback and uses it to retrain the generative AI model and emotion engine. The input of this step is the user's feedback, and the output is an improvement in the model's accuracy.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] [Fourth embodiment]

[1185] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1186] 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.

[1187] 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).

[1188] 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.

[1189] 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.

[1190] 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).

[1191] 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. 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.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] 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.

[1196] 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.

[1197] 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."

[1198] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[1199] 1. Upload user chat logs

[1200] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[1201] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[1202] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[1203] 2. Chat log analysis

[1204] Server: The server decodes the received chat logs and extracts the textual conversation data, which includes the process of converting the chat data into text.

[1205] Natural Language Processing (NLP): The server uses natural language processing (NLP) libraries to analyze text data, specifically to understand the content of the conversation through conversation topic extraction (e.g., sports, music, daily life, etc.), contextual understanding, and sentiment analysis.

[1206] 3. Conversation Generation

[1207] Server: Based on the analyzed data, a generative AI model is used to generate natural conversations that match the user's past conversational style and content. For example, based on the analysis result that "User A often talks about sports," the generative AI model generates a conversation such as "It looks like X team won recently!"

[1208] 4. Automatic matching function

[1209] Server: The system analyzes chat logs of multiple users to find users who share common topics and similar conversation styles, allowing users to find compatible users.

[1210] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching sports-loving users A and B generates a conversation such as, "Have you seen the game of team X?"

[1211] 5. Providing generated conversations

[1212] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[1213] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[1214] 6. Continuous learning and improvement

[1215] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model. This improves the accuracy of conversation generation and user satisfaction.

[1216] Examples:

[1217] 1. User A's first use:

[1218] User A uploads the LINE chat log to the system from his / her own device.

[1219] The server receives the uploaded chat logs and analyzes them using NLP technology.

[1220] Based on the analysis results, the generative AI model generates conversations about topics such as "recent sports news" and provides them to User A.

[1221] User A uses the generated conversation to smoothly communicate with his friends.

[1222] 2. Matching User A and User B:

[1223] The server analyzes the chat logs of user A and user B and detects that they have a common interest (e.g., sports).

[1224] The system uses a generative AI model to generate conversations between users A and B that share common interests and suggests matches.

[1225] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This allows for efficient and natural communication and increases the probability of users meeting each other.

[1226] The processing flow will be explained below.

[1227] Step 1:

[1228] User: Select the chat log files of social networking services on your device.

[1229] Step 2:

[1230] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[1231] Step 3:

[1232] Server: Receives chat log files sent from user devices.

[1233] Step 4:

[1234] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[1235] Step 5:

[1236] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[1237] Step 6:

[1238] Server: Based on the analyzed data, it uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversation style and content.

[1239] Step 7:

[1240] Server: Sends the generated conversation to the user's device.

[1241] Step 8:

[1242] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[1243] Step 9:

[1244] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[1245] Step 10:

[1246] Server: Matches detected users with similar interests and uses generative AI models to suggest conversations based on common topics.

[1247] Step 11:

[1248] Server: Sends suggested conversations to matched users' devices.

[1249] Step 12:

[1250] Device: The user reviews the suggested conversation and uses it for actual communication.

[1251] Step 13:

[1252] Users: Provide feedback on the generated conversation.

[1253] Step 14:

[1254] Terminal: Sends user feedback information to the server.

[1255] Step 15:

[1256] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[1257] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners.

[1258] Example 1

[1259] 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."

[1260] Conventional chat log analysis systems for social networking services have had difficulty generating natural conversations based on a user's conversation style and interests, and automatically matching them with compatible partners. Furthermore, there has been a lack of feedback collection and continuous learning to improve the accuracy of generated conversations and matching, making it difficult to improve the user experience.

[1261] 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.

[1262] In this invention, the server includes means for receiving a data file from a user terminal, means for analyzing the received data file using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing data files of multiple users and detecting users with common topics or similar conversation styles, and means for suggesting conversations with the detected users who are compatible. This enables the generation of natural conversations based on the user's conversation style and interests and automatic matching with compatible partners, and further enables continuous learning and improvement based on feedback from the generated conversations, thereby improving the user experience.

[1263] A "user terminal" is a computing device from which a user selects and uploads data files.

[1264] A "data file" is a file that records user conversations, such as chat logs on social media.

[1265] "Natural language processing" refers to the technology of analyzing and processing natural language using a computer, and includes topic extraction, context understanding, sentiment analysis, etc.

[1266] "Generation means" refers to the function of automatically generating natural conversation based on the analyzed data.

[1267] The "transmission means" is a communication means for transmitting the generated conversation to the user terminal.

[1268] "Matching method" refers to the function that analyzes the data files of multiple users and detects users who share common topics or similar conversation styles.

[1269] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[1270] "Learning means" refers to a function that continuously improves the accuracy of the generation means based on feedback information.

[1271] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[1272] Hardware and software used

[1273] User terminal: The user terminal provides an interface for users to select and upload chat log files to the system. Specifically, the user terminal can be a computer device such as a PC, smartphone, or tablet.

[1274] Server: The server is the central server responsible for analyzing received chat logs and performing conversation generation and matching functions. The following software libraries and services are installed on the server:

[1275] Natural Language Processing (NLP) libraries: NLTK, spaCy, etc.

[1276] Generative AI models: OpenAI's GPT series, etc.

[1277] Database system: MySQL, PostgreSQL, etc.

[1278] Specific data processing and calculation

[1279] 1. Upload user chat logs

[1280] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system.

[1281] Terminal: The terminal provides a file selection screen and an upload button, and sends the chat log file selected by the user to the server.

[1282] Server: The server receives the uploaded chat log files and temporarily stores them in a database.

[1283] 2. Chat log analysis

[1284] Server: The server decodes the received chat logs and extracts the text data. This includes converting chat data into text data.

[1285] Natural Language Processing (NLP): The server uses natural language processing libraries such as NLTK and spaCy to perform topic extraction, contextual understanding, and sentiment analysis of the text data.

[1286] 3. Conversation Generation

[1287] Server: Based on the analyzed data, a generative AI model (e.g., GPT-3) is used to generate natural conversations that match the user's past conversation style and content. For example, it generates a prompt such as, "User A's chat log analysis results: Many sports topics. Please generate a conversation related to recent sports news."

[1288] 4. Automatic matching function

[1289] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[1290] Matching method: For example, matching users who like sports with each other and generating conversations such as, "Have you seen a game by team X?"

[1291] 5. Providing generated conversations

[1292] Server: Sends the generated conversation to the user's device.

[1293] Terminal: The terminal displays the received conversations in a user interface, and the user can use the generated conversations to communicate with other users.

[1294] 6. Continuous learning and improvement

[1295] User: Users provide feedback on the generated conversations, including ratings and opinions.

[1296] Terminal: The terminal sends feedback to the server.

[1297] Server: Retrains the generative AI model based on feedback information to improve the accuracy of conversation generation and user satisfaction.

[1298] Specific examples

[1299] 1. User A's first use:

[1300] User: User A uploads LINE chat logs to the system from his / her own device.

[1301] Server: The server receives the uploaded chat logs and analyzes them using NLP technology.

[1302] Server: Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and provides it to User A.

[1303] User: User A uses the generated conversation to smoothly communicate with his friends.

[1304] 2. Matching User A and User B:

[1305] Server: The server analyzes the chat logs of user A and user B and discovers that they have a common interest (e.g., sports).

[1306] Server: Using a generative AI model, it generates conversations between users A and B who share common interests and suggests matches.

[1307] As described above, this invention is a system that analyzes users' chat logs, generates natural conversations, and automatically matches users with compatible partners. This enables efficient and natural communication, and is expected to increase opportunities for users to meet each other.

[1308] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1309] Step 1: Upload user chat logs

[1310] User: A user can upload their SNS (e.g., LINE) chat logs to the system from their device. The user selects the chat log file using the device interface.

[1311] Terminal: The terminal provides a function to send the selected chat log file to the server using the HTTP POST method. The input is the chat log file selected by the user, and the output is a file send request to the server.

[1312] Server: The server receives the uploaded chat log file and temporarily stores it in a database. The input is the chat log file sent from the terminal, and the output is the reference information of the saved file.

[1313] Step 2: Analyzing the chat logs

[1314] Server: The server reads the saved chat log file, decodes it, and extracts the textual conversation data. The input is the saved chat log file, and the output is the extracted text data.

[1315] Natural Language Processing (NLP) Library: The server uses NLP libraries such as NLTK and spaCy to analyze text data. The specific analysis process includes topic extraction, context understanding, and sentiment analysis. The input is the extracted text data, and based on this, it outputs metadata such as topics and sentiment.

[1316] Step 3: Conversation generation

[1317] Server: The server creates an input prompt for the generative AI model (e.g., GPT-3) based on the analysis results. For example, it generates a prompt such as, "Results of analyzing user A's chat log: Many sports topics. Please generate conversations related to recent sports news." The input is the analysis results, and the output is the prompt.

[1318] Generative AI model: A generative AI model generates new conversational text based on a prompt. The input is the prompt, and the output is the generated conversational text.

[1319] Step 4: Auto-matching function

[1320] Server: The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is the analysis results of multiple users, and the output is a list of matching candidates.

[1321] Matching method: Generate a conversation between the detected match candidates. For example, match sports-loving user A and user B and generate a conversation such as "Have you seen the game of team X?" The input is a list of match candidates, and the output is the matched conversation text.

[1322] Step 5: Serving the generated conversation

[1323] Server: Sends the generated conversation text to the user terminal. The input is the generated conversation text, and the output is an HTTP response to the user terminal.

[1324] Terminal: The terminal displays the received conversation text in a user interface for the user to review. The input is the conversation text sent from the server, and the output is the conversation displayed in the interface.

[1325] Step 6: Continuous learning and improvement

[1326] User: The user provides feedback on the generated conversation. The feedback includes ratings and opinions, and its quality contributes to re-learning in the next step. The input is the generated conversation and the user's ratings, and the output is feedback information.

[1327] Terminal: The terminal sends the feedback input by the user to the server. The input is the feedback information input by the user, and the output is a feedback transmission request to the server.

[1328] Server: The server retrains the generative AI model based on the feedback information. This improves the accuracy of the model and enables more natural conversation generation. The input is the feedback information, and the output is the retrained generative AI model.

[1329] (Application example 1)

[1330] 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."

[1331] Conventional social networking and content distribution services lacked the means to provide appropriate content recommendations based on users' interests or natural communication between users. They also lacked automatic matching functions that take into account users' conversational styles and interests, making it difficult to improve the user experience.

[1332] 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.

[1333] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for recommending digital content tailored to each user based on the user's interests, and means for providing the recommended digital content to the user terminal, thereby enabling appropriate content recommendations and natural communication for the user and improving the user experience.

[1334] "User terminal" refers to a device such as a computer or smartphone used to access social networking services and content.

[1335] A "social networking service" is an online platform that allows users to communicate with each other and share information via the Internet.

[1336] A "chat log" is a text record of conversations between users on a social networking service.

[1337] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1338] The "generation means" is a mechanism that automatically generates natural conversations that match the user's past conversation style and content based on the analyzed data.

[1339] The "matching method" is a system that analyzes the chat logs of multiple users and identifies users who share common topics or similar conversation styles.

[1340] "Digital content" refers to information such as text, audio, and video that is provided electronically.

[1341] A "recommendation method" is a system that suggests the most suitable digital content to each individual user based on the user's interests.

[1342] The "relearning means" is a mechanism that collects user feedback on the generated conversations and recommended content, and uses this to continuously improve the accuracy of the system.

[1343] "Topic extraction" is a technique for identifying major topics or themes from text data.

[1344] "Contextual understanding" is the technology of understanding the meaning of words and phrases in text based on their context and usage.

[1345] "Sentiment analysis" is a technique for inferring a user's emotional state from text data.

[1346] This invention is a system that analyzes chat logs from users' social networking services (SNS) to generate natural conversations and automatically match users with compatible partners. The system includes a user terminal, a server, and a communication network for linking them.

[1347] 1. Upload user chat logs

[1348] Users upload their SNS chat logs from their own devices to the system. The devices provide an interface for users to send selected chat log files to the server. The server receives the chat log files sent from the user devices and temporarily stores them.

[1349] 2. Chat log analysis

[1350] The server decodes the received chat logs and extracts the text-formatted conversation data. This process includes converting the chat data into text. The server then analyzes the text data using a natural language processing (NLP) library. Specifically, it understands the content of the conversation through conversation topic extraction, context understanding, and sentiment analysis.

[1351] 3. Conversation Generation

[1352] Based on the analyzed data, the server uses a generative AI model to generate natural conversations that match the user's past conversation style and content. For example, based on the analysis result that "the user frequently talks about music," the generative AI model generates a conversation such as "Have you heard the latest hit songs?"

[1353] 4. Automatic matching function

[1354] The server analyzes chat logs of multiple users and detects users who share common topics and similar conversation styles. This allows users to discover users who are compatible with each other. The system then suggests conversations between users who are compatible with each other.

[1355] 5. Recommendation method

[1356] The server then recommends digital content based on the user's interests based on the analyzed data and the generated conversation, enabling the delivery of appropriate content to the user.

[1357] 6. Providing generated conversations and recommended content

[1358] The server sends the generated conversations and recommended content to the user's device, where the user can easily view and use the provided conversations and content on their device.

[1359] 7. Continuous learning and improvement

[1360] Users can provide feedback on the generated conversations and recommended content. The feedback information is sent to the server and used to continuously learn and improve the generative AI model and recommendation methods, thereby improving the accuracy of conversation generation and content recommendations.

[1361] Examples:

[1362] For example, if a user who likes sports uploads a chat log, the server will generate a conversation about "recent sports news" and provide it to the user. Based on this generated conversation, the server will recommend the latest sports news articles to the user and suggest communication with other users who have similar interests.

[1363] Example prompt sentence:

[1364] "Generate a conversation about the following topic:\nA log of people talking about recent soccer games"

[1365] Hardware and software used

[1366] Hardware: User device (smartphone or PC)

[1367] Software: Python (using scikit-learn as a natural language processing library and openai API for conversation generation)

[1368] As described above, this invention provides a system that improves the user experience by analyzing a user's SNS chat log, generating natural conversations, matching users with compatible users, and recommending digital content based on the user's interests.

[1369] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1370] Step 1:

[1371] A user uploads a chat log from a social networking service to the system from their own device. The user selects a chat log file and clicks the upload button to send the chat log to the server. The input is the chat log file selected by the user, and the output is the transmission of the chat log file to the server.

[1372] Step 2:

[1373] The server receives the chat log file sent from the user's device and temporarily stores it. The server performs a decoding process to convert the received chat log into text format. The input is the received chat log file, and the output is the text-format chat log data.

[1374] Step 3:

[1375] The server analyzes the saved chat logs using a natural language processing (NLP) library. Specifically, it performs topic extraction, context understanding, and sentiment analysis from the chat logs to identify user interests and trends. The input is the chat log data in text format, and the output is the analyzed feature data.

[1376] Step 4:

[1377] Based on the analyzed data, the server uses a generative AI model to automatically generate natural conversations that correspond to the user's past conversational style and content. Prompts are used for generation, generating conversational sentences that match the user's interests. The input is the analyzed feature data and prompts, and the output is the generated natural conversation.

[1378] Step 5:

[1379] The server sends the generated natural conversation to the user's device. The user can then view the generated conversation on their own device and communicate with their friends. The input is the generated natural conversation, and the output is the transmission of the conversation data to the user's device.

[1380] Step 6:

[1381] The server analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. This allows it to identify users who are compatible with each other. The input is the chat logs of multiple users, and the output is a list of users with common topics and similar conversation styles.

[1382] Step 7:

[1383] The server proposes conversations between users with good compatibility and recommends digital content based on the user's interests using a recommendation method. The input is a list of users with good compatibility and analyzed feature data, and the output is recommended digital content.

[1384] Step 8:

[1385] The server provides the generated conversations and recommended digital content to the user's device. The user can check and use the provided conversations and content on their own device. The input is the recommended digital content and the generated conversation data, and the output is data transmission to the user's device.

[1386] Step 9:

[1387] Users provide feedback on the generated conversations and recommended content. The server collects the feedback information and performs retraining to continuously improve the accuracy of the generative AI model and recommendation method. The input is user feedback, and the output is an improved generative AI model and recommendation method.

[1388] Through the above process, the system analyzes users' SNS chat logs, generates natural conversations, matches users with compatible interests, and even recommends digital content based on the user's interests.

[1389] 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.

[1390] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[1391] 1. Upload user chat logs

[1392] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The chat log is usually saved as text data and sent to the system.

[1393] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server, including a file selection screen and an upload button.

[1394] Server: The server receives the chat log file sent from the user terminal and temporarily stores it.

[1395] 2. Chat log analysis

[1396] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[1397] Natural Language Processing (NLP): The server uses Natural Language Processing (NLP) libraries to analyze the text data, including topic extraction (e.g., sports, music, daily life, etc.), context understanding, and sentiment analysis.

[1398] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[1399] 3. Conversation Generation

[1400] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model is used to generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[1401] 4. Automatic matching function

[1402] Server: The system analyzes chat logs of multiple users to find users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to further refine matching.

[1403] Matching method: Suggest conversations between users who have good chemistry with the detected users. For example, matching users A and B who are both sports fans and have recently shared positive feelings could generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[1404] 5. Providing generated conversations

[1405] Server: Sends the generated conversation to the user's device. The user can then view the generated conversation on their own device and actually communicate with other users.

[1406] Terminal: The terminal provides an interface that allows users to easily view and use the generated conversations.

[1407] 6. Continuous learning and improvement

[1408] Retraining: Users can provide feedback on the generated conversations. The feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. This improves the accuracy of conversation generation and user satisfaction.

[1409] Examples:

[1410] 1. User A's first use:

[1411] User A uploads the LINE chat log to the system from his / her own device.

[1412] The server receives the uploaded chat logs and analyzes them using NLP techniques and an emotion engine.

[1413] Based on the analysis results, the generative AI model generates a conversation about "recent sports news" and User A's positive emotions and provides it to User A.

[1414] User A uses the generated conversation to smoothly communicate with his friends.

[1415] 2. Matching User A and User B:

[1416] The server analyzes the chat logs and emotional states of User A and User B and detects that they have common interests (e.g., sports) and emotions.

[1417] The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[1418] As described above, this invention is a system that analyzes users' chat logs and emotional states to generate natural conversations and automatically match users with compatible partners, thereby realizing efficient and natural communication and increasing the probability of users meeting each other.

[1419] The processing flow will be explained below.

[1420] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system also incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[1421] Step 1:

[1422] User: Select the chat log files of social networking services on your device.

[1423] Step 2:

[1424] Terminal: Provides an interface (e.g., a file selection screen and an upload button) for sending the selected chat log file to the server.

[1425] Step 3:

[1426] Server: Receives chat log files sent from user devices.

[1427] Step 4:

[1428] Server: Decodes the received chat log file and extracts the text-formatted conversation data.

[1429] Step 5:

[1430] Server: Uses natural language processing (NLP) libraries to analyze text data, including topic extraction, context understanding, and sentiment analysis.

[1431] Step 6:

[1432] Emotion Engine: Additionally, the emotion engine is used to analyze emotions from users' chat logs, including extracting the language tone and emotional keywords used in the chat content.

[1433] Step 7:

[1434] Server: Based on the analyzed data and the emotion analysis results of the emotion engine, the generative AI model is used to automatically generate natural conversations that correspond to the user's past conversation style and content. For example, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[1435] Step 8:

[1436] Server: Sends the generated conversation to the user's device.

[1437] Step 9:

[1438] Terminal: Provides an interface that receives generated conversations and displays them to the user.

[1439] Step 10:

[1440] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles.

[1441] Step 11:

[1442] Emotion Engine: Evaluates the user's real-time emotional state and uses this information to make more refined matches.

[1443] Step 12:

[1444] Server: Matches users who have been detected as having good chemistry with each other and suggests conversations based on common topics and emotions. For example, matching User A and User B, who are both sports fans and have recently shared positive emotions, generates a conversation such as, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[1445] Step 13:

[1446] Server: Sends suggested conversations to matched users' devices.

[1447] Step 14:

[1448] Device: The user reviews the suggested conversation and uses it for actual communication.

[1449] Step 15:

[1450] Users: Provide feedback on the generated conversation.

[1451] Step 16:

[1452] Terminal: Sends user feedback information to the server.

[1453] Step 17:

[1454] Server: Based on the feedback information, the generative AI model and emotion engine are retrained to improve the accuracy of conversation generation and user satisfaction.

[1455] Through the above processing steps, the system efficiently generates natural conversations based on the user's chat log and matches users with compatible partners. By incorporating an emotion engine, more appropriate and sophisticated communication that reflects the user's emotional state becomes possible.

[1456] Example 2

[1457] 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."

[1458] Conventional systems were unable to fully utilize user emotions and past chat logs, making it difficult to generate natural conversations and match users with compatible partners. Furthermore, the accuracy of the generated conversations was low, resulting in a lack of user satisfaction.

[1459] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a chat log of a communication service from a user terminal, means for analyzing the received chat log by natural language processing, means for automatically generating natural conversation corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversation to the user terminal, means for analyzing the chat logs of multiple users and detecting users who share common topics or similar conversation styles, means for analyzing user emotions and improving the generated conversation and matching accuracy, and means for suggesting conversations with compatible users. This makes it possible to generate natural conversations and achieve a compatible match between users.

[1460] A "user terminal" is a communication device used by a user, such as a smartphone or a personal computer.

[1461] "Communication service" refers to a platform for users to exchange messages and share information via the Internet.

[1462] "Chat log" refers to the history of conversations and messages a user has on a communication service.

[1463] "Natural Language Processing (NLP)" refers to the technology that enables computers to understand and analyze the natural language used by humans.

[1464] A "generative AI model" refers to an artificial intelligence framework that learns the user's conversation style and content based on the results of data analysis, and generates natural conversations.

[1465] "Sentiment analysis" refers to the technology of identifying and assessing a user's emotional state from text data.

[1466] "Matching method" refers to a function that detects and suggests users with common interests and conversation styles based on analyzed data.

[1467] "Retraining" refers to the process of gathering user feedback and continually improving the accuracy of the generative AI model.

[1468] "Feedback" refers to the ratings and opinions users provide on generated conversations.

[1469] "Topic extraction" refers to the process of automatically identifying major themes or topics from text data.

[1470] "Contextual understanding" refers to the process of understanding the content and background of text data and interpreting its appropriate meaning.

[1471] "Sentiment analysis" refers to the technology of analyzing emotional keywords and tones in text data to evaluate user emotions.

[1472] This invention is a system that analyzes a user's chat log on a social networking service (SNS) to generate natural conversations and automatically match users with compatible partners. The system incorporates an emotion engine that recognizes the user's emotions, improving the content of the conversations generated and the accuracy of matching based on the user's emotional state.

[1473] A user uploads their SNS (e.g., LINE) chat log from their device to the system. The device provides an interface for the user to send the chat log file selected by the user to the server. This includes a file selection screen and an upload button. The received chat log file is temporarily stored by the server.

[1474] The server decodes the received chat log file and extracts the textual conversation data. It then uses a natural language processing (NLP) library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. It then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the sentiment of the user's chat log.

[1475] Once the analysis is complete, the server uses a generative AI model (e.g., GPT-3 or GPT-4) to generate natural-sounding conversations that correspond to the user's past conversational style and content. Specifically, based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that X team won recently!"

[1476] The system also analyzes chat logs from multiple users to detect users with common topics and similar conversation styles. An emotion engine also evaluates users' real-time emotional states, and this information is used to refine matching. Once a match is made, the system suggests conversations between users who are compatible. For example, it could match User A and User B, who both love sports and have recently shared positive emotions, and generate a conversation like, "Have you seen Team X's game? You were happy they won the recent game, weren't you?"

[1477] The generated conversation is sent from the server to the user's terminal, and the user can check the generated conversation on their own terminal and actually communicate with other users. The user terminal provides an interface that makes it easy to check and use the generated conversation.

[1478] Additionally, users can provide feedback on the generated conversations, which is sent to the server and used to continuously learn and improve the generative AI model and emotion engine, thereby improving the accuracy of conversation generation and user satisfaction.

[1479] Example prompt sentence:

[1480] "User A frequently talks about sports and has recently shown positive emotions. Generate a conversation appropriate for him / her."

[1481] "Based on User B's chat logs, generate natural conversations about topics that interest him / her."

[1482] By implementing the invention in this manner, efficient and natural communication is realized, increasing the probability of users meeting each other.

[1483] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1484] Step 1: Upload user chat logs

[1485] User: The user uploads their SNS (e.g., LINE) chat log from their device to the system. The input is the chat log file, and the output is the data sent to the server.

[1486] Terminal: The terminal provides an interface for sending the chat log file selected by the user to the server. This includes a file selection screen and an upload button. Specifically, the terminal reads the file according to the user's selection and sends it to the server.

[1487] Step 2: Receiving and saving chat logs

[1488] Server: The server receives the chat log file sent from the user's device and temporarily stores it. The input is the chat log file sent from the device, and the output is the saved chat log data. Specifically, the server decodes the received data and stores it in its internal storage.

[1489] Step 3: Analyzing the chat logs

[1490] Server: The server decodes the received chat log file and extracts the textual conversation data. The input is the saved chat log data, and the output is the textual conversation data. Specifically, the server uses a decoding algorithm to extract the textual data.

[1491] Natural Language Processing (NLP): The server uses an NLP library (e.g., spaCy, NLTK) to analyze the text data. This analysis includes topic extraction, context understanding, and sentiment analysis. The input is the conversation data in text format, and the output is the analyzed data. Specifically, the NLP engine analyzes the text and extracts the required information.

[1492] Emotion Engine: Furthermore, the emotion engine is used to analyze emotions from the user's chat log. The input is text data, and the output is the emotion analysis result. Specifically, the emotion engine detects and evaluates the tone and emotional keywords in the text.

[1493] Step 4: Conversation generation

[1494] Server: Based on the analyzed data and the emotion analysis results from the emotion engine, a generative AI model (e.g., GPT-3, GPT-4) is used to generate natural-sounding conversations that correspond to the user's past conversational style and content. The input is the analyzed data and the emotion analysis results, and the output is the generated conversation. Specifically, the generative AI model generates a conversation based on the specified prompt sentence.

[1495] Example: Based on the result that "User A often talks about sports and has recently shown positive emotions," the generative AI model generates a conversation such as "I'm so happy that team X won recently!"

[1496] Step 5: Auto-matching function

[1497] Server: Analyzes chat logs of multiple users and detects users with common topics and similar conversation styles. The input is chat log data of multiple users, and the output is a list of users with common topics and similar conversation styles. The emotion engine also evaluates the user's real-time emotional state. Specifically, the server uses a database to compare and analyze user characteristics.

[1498] Matching method: The system suggests conversations with users who are compatible with the system. The input is a list of compatible users, and the output is the suggested conversations. Specifically, the generative AI model generates conversations that reflect the interests and emotions of users.

[1499] Example: The system uses a generative AI model to generate conversations between users A and B where they share interests and emotions, and suggests matches.

[1500] Step 6: Serving the generated conversation

[1501] Server: Sends the generated conversation to the user terminal. The input is the generated conversation, and the output is the data to be sent to the user terminal. In concrete terms, the server uses a communication protocol to send the generated conversation data to the user terminal.

[1502] Terminal: Users can view conversations generated on their own terminals and actually communicate with other users. The input is the conversation data sent from the server, and the output is the conversation content displayed on the user's screen. Specifically, the terminal analyzes the received data and displays it on the user interface.

[1503] Step 7: Continuous learning and improvement

[1504] Retraining means: Users can provide feedback on the generated conversation. This feedback information is sent to the server and used to continuously train and improve the generative AI model and emotion engine. The input is the user's feedback data, and the output is an improved generative model. Specifically, the server analyzes the collected feedback and incorporates it into the model's retraining process.

[1505] (Application example 2)

[1506] 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."

[1507] Conventional social networking services and chat log analysis systems are limited to generating natural conversations between users and matching users with similar interests, but do not adequately address personalized customer engagement or product recommendations in virtual stores. Therefore, a system that can increase user satisfaction and efficiently recommend products is needed. Furthermore, a system that can deeply understand users' emotions and interests and provide effective dialogue and services based on this understanding is also required.

[1508] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1509] In this invention, the server includes means for receiving chat logs of a social networking service from a user terminal, means for analyzing the received chat logs using natural language processing, means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data, means for transmitting the generated conversations to the user terminal, means for analyzing the chat logs of multiple users and detecting users with common topics or similar conversation styles, means for suggesting conversations with the detected users who are compatible, means for providing customer engagement based on the user's history data so that the user can interact with a virtual agent in a virtual store, and means for suggesting products based on the results of the customer engagement, thereby enabling natural conversations and services that are highly satisfying for the user.

[1510] "User Device" means the electronic device used by a User to upload chat logs and view generated conversations.

[1511] A "social networking service" is an online platform that enables users to communicate with each other.

[1512] A "chat log" is a text-based conversation history that a user has on a social networking service.

[1513] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1514] The "generator" is a means for automatically generating natural conversations that correspond to the user's past conversation style and content.

[1515] A "matching method" is a method for analyzing chat logs of multiple users to detect users who share common topics or similar conversation styles.

[1516] A "virtual store" is a platform that provides store-like services and products online.

[1517] "Customer engagement" refers to the activity of a virtual agent interacting with a user to suggest products and provide services based on the user's interests and needs.

[1518] A "generative AI model" is an artificial intelligence model that analyzes a user's past conversation style and emotional state to generate natural conversations.

[1519] "History data" refers to data on a user's past chat logs and service usage history.

[1520] "Product suggestion means" refers to a means for suggesting appropriate products and services based on analyzed user data.

[1521] This invention is a system that receives chat logs from social networking services from user devices, analyzes them using natural language processing and an emotion engine, generates natural conversations using a generative AI model, and provides them to users. Furthermore, it is also possible to engage with customers and suggest products based on user history data in a virtual store.

[1522] System configuration

[1523] 1. User device: A device where users upload chat logs and view generated conversations and customer engagement results, such as a smartphone.

[1524] 2. Server: Receives chat logs, analyzes them, and generates conversations using a generative AI model. It also has the ability to analyze chat logs from multiple users and perform matching.

[1525] 3. Natural Language Processing (NLP): Use libraries such as Spacy to perform topic extraction, contextual understanding, and sentiment analysis of chat log text.

[1526] 4. Generative AI models: Use models such as GPT-2 to generate natural conversations and suggestions based on the analysis results.

[1527] 5. Database: A data storage device for storing user history data, chat logs, and sentiment analysis results, and accessing them as needed.

[1528] Program processing

[1529] 1. Receiving and saving chat logs: The server receives chat logs sent from the user devices and saves them in a database. This process uses a web framework such as Flask.

[1530] 2. Chat log analysis: The server analyzes the saved chat logs using an NLP library (Spacy) to extract topics, understand context, and analyze sentiment.

[1531] 3. Conversation generation: Based on the analysis results and the output of the emotion engine, a generative AI model (GPT-2) is used to generate natural conversations.

[1532] 4. Matching: The server analyzes chat logs of multiple users, detects and suggests users with common topics and similar conversation styles.

[1533] 5. Customer engagement: In virtual stores, personalized product recommendations are made through interactions between users and virtual agents based on historical user data.

[1534] Specific examples

[1535] 1. Example of User A's use:

[1536] User A uploads the chat log from his smartphone.

[1537] The server receives the data and performs topic extraction and sentiment analysis using Spacy.

[1538] The GPT-2 model generates and serves up the conversation, "What do you think about sports these days?"

[1539] 2. Matching User A and User B:

[1540] The server analyzes the chat logs of user A and user B.

[1541] "Sports" is detected as a common topic and a match is suggested.

[1542] Generates the conversation, "Did you watch the recent game?"

[1543] 3. Customer engagement in virtual stores:

[1544] User A accesses the virtual store.

[1545] The server performs customer engagement based on User A's historical data.

[1546] GPT-2 suggests, "How about this month's promotional item?"

[1547] Prompt Sentence Examples

[1548] "Analyze the conversation logs of the following users to identify topics of interest and sentiment. Generate conversation prompts based on the results. Log: [Paste user chat log here]"

[1549] As described above, the present invention analyzes a user's chat history and emotional data to generate natural conversations and provide personalized product recommendations in a virtual store, thereby providing a more fulfilling experience for the user.

[1550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1551] Step 1:

[1552] A user uploads a chat log from a social networking service (SNS) to the system from their device. Specifically, they select the chat log file on the file selection screen on their device and press the upload button. The device then sends the selected chat log file to the server. The input of this step is the user's chat log file, and the output is the file sent to the server.

[1553] Step 2:

[1554] The server receives the chat log file sent from the terminal and stores it in the database. The received file is temporarily stored and used for subsequent processing. The input of this step is the user's chat log file, and the output is the file stored in the database.

[1555] Step 3:

[1556] The server retrieves the saved chat log files and analyzes them using a natural language processing (NLP) library (e.g., Spacy). Specifically, it converts the files into text format and performs topic extraction, context understanding, and sentiment analysis. The input of this step is the chat log text, and the output is the analyzed data.

[1557] Step 4:

[1558] Based on the analyzed data, a generative AI model (e.g., GPT-2) is used to generate natural-sounding conversations. The server uses the analysis results and the output of the emotion engine as inputs for the model and obtains the generated text. The inputs for this step are the analysis data and the results of the emotion engine, and the output is the generated conversation text.

[1559] Step 5:

[1560] The server sends the generated conversation text to the user terminal. The user checks the generated conversation on the terminal and communicates with other users as needed. The input of this step is the generated conversation text, and the output is the text sent to the user terminal.

[1561] Step 6:

[1562] The server analyzes chat logs of multiple users to find users with common topics and similar conversation styles. Specifically, it compares and analyzes multiple chat logs to identify users with high similarities. The input of this step is multiple chat log data, and the output is matched user pairs.

[1563] Step 7:

[1564] The server then proposes conversations between users with good compatibility. Based on the analyzed data, it uses a generative AI model to generate and propose relevant conversations. The inputs of this step are the matched user pairs and the analyzed data, and the output is the proposed conversation text.

[1565] Step 8:

[1566] In the virtual store, the server generates a dialogue for customer engagement based on the user's history data. Through the generated dialogue, it makes product and service suggestions. The input of this step is the user's history data, and the output is the generated engagement conversation text and suggestion content.

[1567] Step 9:

[1568] The user provides feedback on the generated conversations and suggestions. The server collects this feedback and uses it to retrain the generative AI model and emotion engine. The input of this step is the user's feedback, and the output is an improvement in the model's accuracy.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] FIG. 9 is a diagram illustrating 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 actions 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.

[1574] 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.

[1575] 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).

[1576] 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.

[1577] 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."

[1578] 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.

[1579] 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).

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1588] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1589] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1590] The following is further disclosed regarding the above embodiment.

[1591] (Claim 1)

[1592] A means for receiving a chat log of a social networking service from a user terminal;

[1593] means for analyzing the received chat log by natural language processing;

[1594] a generating means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data;

[1595] means for transmitting the generated conversation to a user terminal;

[1596] A matching method that analyzes chat logs of multiple users and detects users with common topics and similar conversation styles;

[1597] The system includes a means for suggesting a conversation with the detected user who has good compatibility.

[1598] (Claim 2)

[1599] 10. The system of claim 1, further comprising a retraining means for collecting user feedback and continuously improving the accuracy of said generating means.

[1600] (Claim 3)

[1601] The system according to claim 1, characterized in that topic extraction, context understanding, and sentiment analysis are performed when analyzing the chat log.

[1602] "Example 1"

[1603] (Claim 1)

[1604] means for receiving a data file from a user terminal;

[1605] means for analyzing the received data file by natural language processing;

[1606] a generating means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data;

[1607] means for transmitting the generated conversation to a user terminal;

[1608] A matching method that analyzes data files of multiple users to find users who share common topics or similar conversation styles;

[1609] The system includes a means for suggesting a conversation with the detected user who has good compatibility.

[1610] (Claim 2)

[1611] 10. The system of claim 1, further comprising a learning means for collecting user feedback and continuously improving the accuracy of said generating means.

[1612] (Claim 3)

[1613] The system of claim 1, wherein topic extraction, context understanding, and sentiment analysis are performed when analyzing the data file.

[1614] "Application Example 1"

[1615] (Claim 1)

[1616] A means for receiving a chat log of a social networking service from a user terminal;

[1617] means for analyzing the received chat log by natural language processing;

[1618] a generating means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data;

[1619] means for transmitting the generated conversation to a user terminal;

[1620] A matching method that analyzes chat logs of multiple users and detects users with common topics and similar conversation styles;

[1621] means for suggesting a conversation with the detected user with good compatibility;

[1622] means for recommending digital content adapted to an individual user based on the user's interests;

[1623] means for providing the recommended digital content to a user terminal;

[1624] A system including:

[1625] (Claim 2)

[1626] 10. The system of claim 1, further comprising a re-learning means for collecting feedback from users and continuously improving the accuracy of the generating means and the recommending means.

[1627] (Claim 3)

[1628] The system according to claim 1, characterized in that topic extraction, context understanding, and sentiment analysis are performed when analyzing the chat log.

[1629] "Example 2: Combining Emotion Engines"

[1630] (Claim 1)

[1631] A means for receiving a chat log of the communication service from the user terminal;

[1632] means for analyzing the received chat log by natural language processing;

[1633] a generating means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data;

[1634] means for transmitting the generated conversation to a user terminal;

[1635] A method for analyzing chat logs of multiple users to detect users with common topics or similar conversation styles;

[1636] A means to analyze user emotions and improve the accuracy of generated conversations and matching,

[1637] The system includes a means for suggesting a conversation with the detected user who has good compatibility.

[1638] (Claim 2)

[1639] 10. The system of claim 1, further comprising a retraining means for collecting user feedback and continuously improving the accuracy of said generating means.

[1640] (Claim 3)

[1641] The system according to claim 1, characterized in that topic extraction, context understanding, and sentiment analysis are performed when analyzing the chat log.

[1642] "Application example 2 when combining emotion engines"

[1643] (Claim 1)

[1644] A means for receiving a chat log of a social networking service from a user terminal;

[1645] means for analyzing the received chat log by natural language processing;

[1646] a generating means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data;

[1647] means for transmitting the generated conversation to a user terminal;

[1648] A matching method that analyzes chat logs of multiple users and detects users with common topics and similar conversation styles;

[1649] means for suggesting a conversation with the detected user with good compatibility;

[1650] A means for providing customer engagement based on historical data of a user for a conversation between the user and a virtual agent in a virtual store;

[1651] means for making product recommendations based on the results of said customer engagement;

[1652] A system including:

[1653] (Claim 2)

[1654] 10. The system of claim 1, further comprising a retraining means for collecting user feedback and continuously improving the accuracy of said generating means.

[1655] (Claim 3)

[1656] The system according to claim 1, characterized in that, when analyzing the chat log, topic extraction, context understanding, sentiment analysis, and personalized product suggestions based on the user's history data are performed. [Explanation of symbols]

[1657] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving a chat log of a social networking service from a user terminal; means for analyzing the received chat log by natural language processing; a generating means for automatically generating natural conversations corresponding to the user's past conversation style and content based on the analyzed data; means for transmitting the generated conversation to a user terminal; A matching method that analyzes chat logs of multiple users and detects users with common topics and similar conversation styles; The system includes a means for suggesting a conversation with the detected user who has good compatibility.

2. 10. The system of claim 1, further comprising a retraining means for collecting user feedback and continually improving the accuracy of said generating means.

3. The system according to claim 1, wherein topic extraction, context understanding, and sentiment analysis are performed when analyzing the chat log.

Images