System

Abstract

A system is provided.SOLUTION: Learning the profile information of the user using a generative AI model; and transmitting the inputted profile information of the user to a server; A system comprising: a learning unit configured to analyze a user's interest; a collection unit configured to collect latest news articles from the Internet and filter news related to the user's interest; a generation unit configured to extract a common topic between users and generate a message that triggers a conversation; a presentation unit configured to present the generated message to the user and allow the user to check the message; a reception unit configured to support transmission of the message by the user; an analysis unit configured to collect a log of the message and analyze a progress status of the conversation; and a suggestion unit configured to suggest a trigger for a new conversation based on an analysis result.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] Conventional matching apps and communication tools have the problem of making it difficult to start a conversation with someone you meet for the first time, which can lead to awkwardness. Furthermore, the impact of COVID-19 has led to a decrease in face-to-face interactions, making it difficult to meet people and build relationships in a natural way. The objective of this invention is to solve these problems and promote smooth communication and support the building of romantic relationships by providing natural conversation starters with people you meet for the first time. [Means for solving the problem]

[0005] The present invention provides the following means: to solve these problems, by providing a system including an input means for a user to input profile information, a transmission means for transmitting the input user profile information to a server, a learning means for learning the user profile information using a generative AI model and analyzing the user's interests, a collection means for collecting the latest news articles from the Internet and filtering out news related to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to the user and allowing the user to check the messages, a reception means for supporting the user in sending messages, an analysis means for collecting a message log and analyzing the progress of the conversation, and a suggestion means for suggesting new conversation starters based on the analysis results.

[0006] "Input means" refers to an interface through which a user inputs profile information into the system.

[0007] "Transmission means" refers to a function that transfers the entered user profile information to the server.

[0008] "Learning Method" refers to the process of using a generative AI model to learn user profile information and analyze user interests.

[0009] "Aggregation means" refers to the function of periodically retrieving the latest news articles from the Internet and filtering news relevant to the user's interests.

[0010] "Generation means" refers to the process of extracting common topics between users and creating messages that will spark conversation.

[0011] The "presentation means" refers to an interface that displays the generated message to the user and allows the user to confirm it.

[0012] "Receiving means" refers to a function that supports users in sending messages.

[0013] "Analysis tools" refers to the process of collecting logs of messages sent and received and evaluating the progress of the conversation.

[0014] "Suggestion means" refers to a function that suggests new conversation starters to users based on the analysis results. [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] The present invention relates to a system for providing an opportunity for smooth conversation between users, and specific embodiments thereof will be described below.

[0037] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet and filtering them according to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a proposal means for proposing new conversation starters based on the analysis results.

[0038] Overview of program processing

[0039] 1. Enter user information

[0040] User: Open the profile settings screen and enter your hobbies, interests, and location information.

[0041] Terminal: Formats the information entered and sends it to the server.

[0042] 2. Training the generative AI model

[0043] Server: Receives the submitted user profile information and provides it to the generative AI model for learning.

[0044] Server: Deeply analyzes user interests and personalities and stores this information.

[0045] 3. Collecting online news

[0046] Server: Uses RSS feeds and news APIs to gather the latest news articles from the internet.

[0047] Server: Organizes collected news into categories and filters news relevant to the user's interests.

[0048] 4. Extracting common topics and generating messages

[0049] Server: Uses a generative AI model to match user profile content with collected news articles.

[0050] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[0051] 5. Talk suggestions

[0052] Server: Sends the generated message to the user's terminal.

[0053] Terminal: Presents the generated message to the user in a preview format.

[0054] User: Checks the message presented and decides whether to send it to the recipient.

[0055] 6. Conversation analysis and feedback

[0056] Server: Collects the history of messages sent and received between users and monitors the progress of the conversation.

[0057] Server: Analyzes the content of the conversation using a generative AI model and evaluates the user's reaction and the level of conversation activity.

[0058] Server: Generates new topics and messages as needed and suggests them to users.

[0059] Specific examples

[0060] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest relevant online news.

[0061] The server extracts reviews of new movies as a common interest of users A and B. Next, the server generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to user A. User A checks this message and sends it to user B, creating a natural conversation starter.

[0062] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[0063] The processing flow will be explained below.

[0064] Step 1: Enter your information

[0065] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[0066] Terminal: Formats the information entered and sends it to the server.

[0067] Step 2: Training the generative AI model

[0068] Server: Receives profile information sent by users.

[0069] Server: Provides the generative AI model with user profile information, which allows the model to learn about the user's interests and personality.

[0070] Server: Stores the learning results of the generative AI model in a database.

[0071] Step 3: Collecting online news

[0072] Server: Periodically gathers the latest news articles from the internet, using RSS feeds and news APIs.

[0073] Server: Organizes news articles into categories and records metadata for each news article.

[0074] Step 4: Extracting common topics and generating messages

[0075] Server: Uses a generative AI model to match user profile information with collected news articles.

[0076] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[0077] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[0078] Step 5: Propose a talk

[0079] Server: Sends the generated conversation message to the user's terminal.

[0080] Terminal: Presents the generated message to the user in a preview format, allowing the user to review the message and decide whether to send it or not.

[0081] User: Edits the suggested message as needed and sends it to whomever they deem appropriate.

[0082] Step 6: Analysis and feedback of the conversation

[0083] Server: Collects the history of messages sent and received between users and stores it in a database.

[0084] Server: Using a generative AI model, the server analyzes the collected messages and evaluates the progress of the conversation based on factors such as user responses and message frequency.

[0085] Server: If the conversation dies or progress is not being made, the server generates new topics and messages and presents them to the user. For example, it generates new messages based on news articles related to a different topic of interest.

[0086] This makes it easier for users to maintain a natural conversation flow and helps ensure smooth communication with people they meet for the first time.

[0087] Example 1

[0088] 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."

[0089] In modern society, facilitating communication between users is an important issue. In particular, it is difficult to find an opportunity to naturally start a conversation between users with different hobbies and interests. Furthermore, insufficient topic suggestions based on users' interests have led to problems with conversations not continuing. A means to solve these problems is needed.

[0090] 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.

[0091] In this invention, the server includes an input means for inputting user data, a transmission means for transmitting the input user data to the server, a learning means for learning the user data using a generative AI model and analyzing the user's interests, a collection means for collecting the latest information from the network and filtering information related to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to the users and allowing the users to confirm the messages, a communication means for supporting the users in sending messages, an analysis means for collecting message logs and analyzing the progress of the conversation, and a suggestion means for suggesting new conversation starters based on the analysis results. This allows for smooth conversation starters to be provided between users, facilitating communication.

[0092] "User data" refers to personal information entered by the user, such as interests, hobbies, and location information.

[0093] "Input means" refers to an interface or device through which a user inputs data, specifically the settings screen of a mobile app or web application.

[0094] "Transmission means" refers to the function or protocol for transmitting input data to a server. For example, it includes secure communication methods such as HTTPS.

[0095] A "generative AI model" is an artificial intelligence algorithm that learns from user data and analyzes their interests and concerns, specifically a model that uses natural language processing technology.

[0096] A "learning method" is a method or process for using a generative AI model to analyze user data and identify user interests and concerns.

[0097] "Gathering methods" are methods and tools that obtain the latest information from the network and filter it according to the user's interests. Examples include RSS feed readers and news APIs.

[0098] The "generation means" refers to a method or function for extracting common topics between users and generating messages that will spark natural conversation.

[0099] "Presentation means" refers to the method or interface for displaying the generated message to the user and allowing them to check it. Examples include push notifications and in-app notification functions.

[0100] "Communication means" refers to the method or technology used by a user to send messages to others. Specifically, this applies to chat apps and messaging services.

[0101] "Analysis tools" are methods and algorithms for collecting logs of messages sent and received between users and assessing the progress of the conversation.

[0102] The "suggestion means" is a method or system for generating a message that can serve as a starting point for a new conversation based on the analysis results and presenting it to the user.

[0103] The present invention relates to a system for providing a smooth conversation starter between users, and a specific embodiment thereof will be described below. This system is realized using the following hardware and software.

[0104] Hardware and Software

[0105] 1. User device: smartphone, tablet, or PC

[0106] 2. Server: Cloud server, on-premise server, etc.

[0107] 3. Internet connection: A stable network connection (Wi-Fi, 4G / 5G, etc.)

[0108] 4. Generative AI models: AI models that apply natural language processing technology (e.g., GPT-3)

[0109] Overview of program processing

[0110] 1. Enter user information

[0111] User: A user opens a profile in a mobile or web application and enters their interests, hobbies, and location information. Examples include "movies," "music," and "travel."

[0112] Terminal: The entered information is formatted in JSON format and sent to the server via a secure protocol (e.g., HTTPS).

[0113] 2. Training the generative AI model

[0114] Server: The server receives the JSON data and extracts the user's profile information. The extracted information is fed into a generative AI model (e.g., GPT-3) to learn the user's interests and personality patterns. The learning results are stored in a database along with the user ID.

[0115] 3. Collecting online news

[0116] Server: The server uses an RSS feed reader or a news API (e.g., NewsAPI.org) to collect the latest news articles from the network, organize them into categories, and filter only those relevant to the user's interests.

[0117] 4. Extracting common topics and generating messages

[0118] Server: A generative AI model is used to match the user's profile information with filtered news articles. Common topics are extracted and a conversation-starting message in natural language is generated. For example, a message might be generated that asks, "Have you seen the recently talked-about movie 'Tenet'?"

[0119] 5. Talk suggestions

[0120] Server: The generated message is sent to the user's terminal.

[0121] Device: The device displays the message in a preview format to the user, who can then review the message and decide whether to send it to the other party.

[0122] 6. Conversation analysis and feedback

[0123] Server: The server collects message exchange history between users in real time and analyzes the content of the conversation using a generative AI model. It evaluates user reactions and the level of conversation activity, and generates and provides new topic suggestion messages as needed.

[0124] Specific examples

[0125] For example, consider the case where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters their interests in "movies" and "music" on their profile settings screen, and their device sends this information to the server. The server uses a generative AI model to learn about User A and collect and filter the latest related news articles from the internet. The server extracts reviews of new movies as a common topic between User A and User B, and generates a message asking, "Have you seen the recently talked-about movie 'Tenet'?" This message is sent to User A's device, where User A confirms it and sends it to User B, creating a natural conversation starter.

[0126] Prompt Sentence Examples

[0127] "Please talk about the movie 'Tenet'."

[0128] "Please extract topics that users A and B are both interested in from the latest music news."

[0129] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] Enter user information

[0133] User: Open the profile settings screen and enter your interests, hobbies, and location information.

[0134] Input: Movies, music, travel

[0135] Output: This information is entered into the form.

[0136] Terminal: Formats the input information into JSON format and sends it to the server.

[0137] Input: Movies, Music, Travel input fields

[0138] Output: JSON format data {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[0139] Step 2:

[0140] Training generative AI models

[0141] Server: Receives the JSON data and extracts the user's profile information.

[0142] Input: {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[0143] Output: User interest data

[0144] Server: Feeds data to a generative AI model (e.g., GPT-3) to learn patterns of user interests and personality.

[0145] Input: User interest data

[0146] Output: Learning results of user's interest and personality patterns

[0147] Server: The learning results are stored in a database, linked to the user ID.

[0148] Input: Learning results and user ID

[0149] Output: User profile stored in the database

[0150] Step 3:

[0151] Collecting online news

[0152] Server: Collects the latest news articles using the news API.

[0153] Input: News API request

[0154] Output: A list of the latest news articles

[0155] Server: Organizes news articles into categories and filters news relevant to the user's interests.

[0156] Input: A list of recent news articles

[0157] Output: News articles related to the user's interests

[0158] Step 4:

[0159] Extracting common topics and generating messages

[0160] Server: Uses a generative AI model to match user profile information with news articles.

[0161] Input: User interest / personality data, news articles

[0162] Output: Candidates for common topics

[0163] Server: Generates natural conversation starter messages.

[0164] Input: Candidates for common topics

[0165] Output: Generated message: "Have you seen the recent popular movie, Tenet?"

[0166] Step 5:

[0167] Talk suggestions

[0168] Server: Sends the generated message to the user's terminal.

[0169] Input: The generated message

[0170] Output: Sends a message to the user's terminal

[0171] Terminal: Presents the message to the user in a preview format.

[0172] Input: The generated message

[0173] Output: The message presented to the user

[0174] Step 6:

[0175] Conversation analysis and feedback

[0176] Server: Collects message exchange history between users in real time.

[0177] Input: User-to-user messages

[0178] Output: Collected message history

[0179] Server: Analyzes the content of the conversation using a generative AI model.

[0180] Input: Message history

[0181] Output: Analysis results (conversation activity, user responses, etc.)

[0182] Server: Generates new topic suggestion messages as needed and provides them to users.

[0183] Input: Analysis results

[0184] Output: New suggestion message: "Let's talk about recently released music albums."

[0185] This specific processing step promotes smooth conversation between users.

[0186] (Application example 1)

[0187] 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."

[0188] Communication between staff and customers in brick-and-mortar stores is challenging because it is difficult to accurately grasp customers' interests and provide appropriate conversation starters. There is also a need to instantly access the information needed to provide personalized customer service. However, current systems have difficulty meeting these demands.

[0189] 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.

[0190] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting the user in sending messages; an analysis means for collecting a message log and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; and a presentation means for presenting common topics between staff and customers in a physical store using smart glasses or a head-mounted display, thereby enabling smooth communication between staff and customers in a physical store.

[0191] "Input means" refers to a device or interface for inputting user profile information.

[0192] The "transmission means" is a communication means for transmitting the input user profile information to the server.

[0193] A "learning means" is a device or software that uses a generative AI model to learn a user's profile information and analyze the user's interests.

[0194] An "aggregator" is a device or software that gathers current news articles from the Internet and filters them for news relevant to the user's interests.

[0195] The "generation means" is a device or software for extracting common topics between users and generating messages that will serve as conversation starters.

[0196] The "presentation means" is a device or interface that presents the generated message to the user and allows the user to check the message.

[0197] A "receiving means" is a communication means that supports users in sending messages.

[0198] An "analysis means" is a device or software that collects a log of messages and analyzes the progress of a conversation.

[0199] The "suggestion means" is a device or software that suggests new conversation starters based on the analysis results.

[0200] "Smart glasses" are glasses-type devices that visually present information to a user.

[0201] A "head-mounted display" is a head-mounted display device for visually presenting information to a user.

[0202] A "common topic" is a concern or interest shared between users.

[0203] A "brick and mortar store" is a retail or service establishment that has a physical location.

[0204]

[0205] The present invention relates to a system for realizing smooth communication between staff and customers in a brick-and-mortar store. The system utilizes smart glasses or a head-mounted display to present staff with conversation starters based on the customer's interests.

[0206] First, when a user (customer) visits a store, they input their profile information, which includes their interests, concerns, and recent purchase history. This information is sent to the server through an input method. The server then uses a generative AI model to learn the user's profile information and analyze their interests. This learning method is important for gaining a deep understanding of the user's interests.

[0207] The server then collects the latest news articles from the internet using RSS feeds and news APIs, organizes them into categories, and filters news relevant to the user's interests.

[0208] The generative AI model compares user profile information with collected news articles to extract common topics between users. This generation method generates messages to spark conversation. The generated messages are presented to staff via smart glasses or a head-mounted display. This presentation method makes it easier for staff to identify topics that may interest customers.

[0209] The server also includes a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a suggestion means for suggesting new conversation starters based on the analysis results.

[0210] As a concrete example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news. The server extracts reviews of new movies as a common interest of Users A and B. The server then generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to User A. User A then sees this message, allowing the staff member to start a natural conversation with the customer.

[0211] Representative generative AI models include GPT-4 and BERT. News API and Google News API can be used to gather news. MySQL and PostgreSQL can be used as database management systems.

[0212] Examples of specific prompts include:

[0213] "User A's profile:

[0214] Hobbies: Movies, music

[0215] Interests: Latest technology, fashion

[0216] User B's profile:

[0217] Hobbies: Cooking, Traveling

[0218] Interests: Health, Sports

[0219] Please suggest some common topics for these users."

[0220] By providing such prompts, the generative AI model can identify common topics between users A and B and suggest appropriate conversation starters to the wait staff.

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] Enter user profile information

[0224] When a user visits a store, they input their profile information (interests, concerns, recent purchase history, etc.) using a smartphone or tablet device.

[0225] Input data: User interests, concerns, recent purchase history

[0226] Output data: JSON format of input data

[0227] Step 2:

[0228] Sending input data

[0229] The device formats the profile information entered by the user and sends it to the server over Wi-Fi or mobile data.

[0230] Input data: User profile information (JSON format)

[0231] Output data: Send data to the server

[0232] Step 3:

[0233] Training generative AI models

[0234] The server receives the user's profile information and provides it to the generative AI model for training. The training method uses a generative AI model (e.g., GPT-4, BERT).

[0235] Input data: User profile information

[0236] Output data: Analysis of user interests and personalities

[0237] Step 4:

[0238] News article collection and filtering

[0239] The server uses RSS feeds and news APIs to gather the latest news articles from the internet, organizes them into categories, and filters news relevant to the user's interests.

[0240] Input data: News articles collected from the news API

[0241] Output data: News articles related to the user's interests

[0242] Step 5:

[0243] Extracting common topics and generating messages

[0244] The server uses a generative AI model to match users' profile information with collected news articles, extract common topics between users, and generate messages that spark natural conversations.

[0245] Input data: user profile information, filtered news articles

[0246] Output data: Generated conversation starter message

[0247] Step 6:

[0248] Message presentation

[0249] The server then sends the generated message to the user's device and presents it to the staff via smart glasses or a head-mounted display, allowing the staff to visually confirm topics that may be of interest to the customer.

[0250] Input data: Generated conversation starter messages

[0251] Output data: Visual presentation of the message

[0252] Step 7:

[0253] Monitoring and analyzing conversation progress

[0254] The server collects messages sent and received between users and monitors the progress of the conversation. It uses a generative AI model to analyze the content of the conversation and evaluates the user's reactions and the level of conversation activity.

[0255] Input data: Message exchange history between users

[0256] Output data: Conversation analysis results and evaluation

[0257] Step 8:

[0258] Propose new conversation starters

[0259] The server proposes new conversation starters based on the analysis results, and the suggestion means generates new messages for the user, which are then presented again.

[0260] Input data: Conversation analysis results and evaluation

[0261] Output: New conversation starter message

[0262] 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.

[0263] The present invention relates to a system for providing natural conversation starters between users, and in particular, a specific embodiment will be described in which a combination of emotion engines is used to recognize user emotions and support more appropriate communication.

[0264] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning about user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet, a generation means for extracting common topics and generating conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, a suggestion means for proposing new conversation starters based on the analysis results, and an emotion engine for recognizing user emotions using an emotion engine and a function for generating appropriate conversation messages based on the recognition.

[0265] Overview of program processing

[0266] 1. Enter user information

[0267] User: Open the profile settings screen and enter your hobbies, interests, location, and self-introduction.

[0268] Terminal: Formats the information entered and sends it to the server.

[0269] 2. Training the generative AI model

[0270] Server: Receives the submitted profile information and provides it to the generative AI model for learning.

[0271] Server: Analyzes the user's interests and personality and stores the learning results of the generative AI model.

[0272] 3. Collecting online news

[0273] Server: Periodically collects the latest news articles from the Internet and organizes them into categories.

[0274] Server: The news articles are then filtered to match the user's interests.

[0275] 4. Extracting common topics and generating messages

[0276] Server: Uses a generative AI model to match user profile information with collected news articles.

[0277] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[0278] Server: For example, create a message like, "Have you seen the recently talked about movie, Tenet?"

[0279] 5. Talk suggestions

[0280] Server: Sends the generated message to the user's terminal.

[0281] Terminal: Presents the message to the user in a preview format, allowing the user to review it and decide whether to send it.

[0282] User: Starts a conversation by sending a message.

[0283] 6. Conversation analysis and feedback

[0284] Server: Collects the history of messages sent and received between users and stores it in a database.

[0285] Server: Uses a generative AI model to analyze collected message content and evaluate user responses and conversation progress.

[0286] Server: If the conversation stalls or progress is not being made, it generates new topics and messages and suggests them to the user.

[0287] 7. Incorporating an Emotional Engine

[0288] Server: Uses an emotion engine to recognize emotions from messages and user behavior, for example, inferring a user's emotional state from the tone and frequency of their text messages.

[0289] Server: Adjusts conversation starters based on the recognized emotions. For example, if the user shows anger or sadness, it generates a calm message that takes that emotion into account.

[0290] Server: Suggested messages based on emotions are tailored to be emotionally appropriate using natural language generation technology.

[0291] Specific examples

[0292] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends this information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news.

[0293] Next, the server uses an emotion engine to recognize emotions from User A's messages and behavior. For example, if User A wrote "I've been very tired recently" in a past message, the emotion engine determines that User A is currently "tired." Based on this, the server generates a calm message related to a common interest.

[0294] The server generates a message in the form of "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and presents it to User A. User A checks this message and sends it to User B, creating a natural conversation starter. By taking into account the user's emotions, this system provides a more personalized experience.

[0295] This makes it easier for users to maintain a natural conversation flow that reflects their emotions, and allows for smooth communication with people they meet for the first time.

[0296] The processing flow will be explained below.

[0297] Step 1: Enter your information

[0298] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[0299] Terminal: Formats the information entered and sends it to the server.

[0300] Step 2: Training the generative AI model

[0301] Server: Receives the transmitted user profile information.

[0302] Server: Provides the generative AI model with user profile information, which allows the model to learn about interests and personality.

[0303] Server: Stores the learning results of the generative AI model in a database.

[0304] Step 3: Collecting online news

[0305] Server: Uses RSS feeds and news APIs to periodically gather the latest news articles from the internet.

[0306] Server: Organizes collected news articles by category and records metadata of news articles.

[0307] Step 4: Extracting common topics and generating messages

[0308] Server: Uses a generative AI model to match user profile information with collected news articles.

[0309] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[0310] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[0311] Step 5: Incorporating the Emotion Engine

[0312] Server: Using the emotion engine, analyzes the user's messages and behavioral data to recognize their current emotional state. For example, it determines whether the user is expressing emotions such as "tiredness" or "joy" based on the content and frequency of text messages.

[0313] Server: Adjusts the generated messages based on the user's perceived emotions. For example, if the user feels "tired," it suggests emotionally appropriate topics such as "relaxing movies."

[0314] Step 6: Propose a talk

[0315] Server: Sends the coordinated conversation message to the user's terminal.

[0316] Terminal: The generated message is presented to the user in a preview format, allowing the user to review it and decide whether it is appropriate.

[0317] User: Review the message and send it to whomever they deem appropriate.

[0318] Step 7: Collect conversation progress

[0319] Server: Collects the history of messages sent and received between users and stores it in a database.

[0320] Server: Analyzes collected message content using a generative AI model to evaluate user responses and conversation progress.

[0321] Step 8: Suggest new conversation starters

[0322] Server: Using the emotion engine, it reconfirms the user's current emotional state and generates new topics and messages as needed. For example, if the user has a positive emotion towards the conversation, it suggests further interesting topics.

[0323] Server: Maintains smooth communication by sending newly generated messages to the user's device.

[0324] This helps maintain a natural conversation flow between users and helps ensure smooth communication with people meeting for the first time.

[0325] Example 2

[0326] 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."

[0327] In today's world, it is difficult for users to naturally start a conversation, and it is often difficult for them to communicate their feelings, especially when they meet for the first time. Furthermore, conventional communication support systems have difficulty recognizing users' emotions and suggesting appropriate ways to start a conversation. This leads to unnatural communication between users, making it difficult to build relationships.

[0328] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0329] In this invention, the server includes an input means for inputting user profile information, a transmission means for transmitting the input user profile information to the server, and a learning means for learning the user profile information and analyzing the user's interests using a generative AI model, thereby enabling the server to recognize the user's emotions using an emotion engine and generate appropriate conversational messages.

[0330] "Input means" refers to an interface through which a user inputs their profile information.

[0331] "Transmission means" refers to the function of converting the entered profile information into an appropriate format and transmitting it to the server.

[0332] "Learning means" refers to the function that uses a generative AI model to analyze a user's profile information and learn about the user's interests and personality.

[0333] "Gathering means" refers to the function of collecting the latest news articles from the Internet, organizing them into categories, and filtering news related to the user's interests.

[0334] "Generation means" refers to a function that extracts common topics between users and generates messages that will serve as a starting point for natural conversation.

[0335] The "presentation means" refers to a function that presents the generated message to the user so that the user can confirm the message.

[0336] "Receiving means" refers to a function that supports users in sending messages.

[0337] "Analysis means" refers to the function of collecting message logs and analyzing the progress of the conversation and the user's reactions.

[0338] "Suggestion means" refers to a function that suggests new conversation starters to the user based on the analysis results.

[0339] "Emotion recognition means" refers to a function that uses an emotion engine to recognize a user's emotion and generates an appropriate conversational message based on that emotion.

[0340] The present invention is a system for providing natural conversation starters between users, and in particular, by combining an emotion engine, it recognizes user emotions and supports more appropriate communication. This system provides a terminal with an input means for users to input profile information, and includes a transmission means for transmitting the input information to a server. The server also has a learning means for learning the user's profile information using a generative AI model and analyzing the user's interests based on the results.

[0341] Next, the server has a collection means for collecting the latest news articles from the Internet and uses a specific algorithm to filter out news relevant to the user's interests.The server then extracts common topics based on this information and generates messages that serve as natural conversation starters.Natural language generation technology is used to generate these messages.The generated messages are displayed to the user via a presentation means provided on the terminal.The user can review these messages and send them as needed.

[0342] The server also has an analysis means for collecting messages sent and received between users and analyzing the progress of the conversation based on the collected messages. The server also includes a suggestion means for suggesting new conversation starters to users based on the results of this analysis. The server also has an emotion recognition means that uses an emotion engine to analyze the user's emotions and adjust conversation messages according to the emotions.

[0343] As a specific example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests on a profile setting screen, and the information is sent from the device to the server. The server uses a generative AI model to learn User A's profile information, while simultaneously collecting relevant and recent news articles and identifying articles related to User A's interests.

[0344] The server then uses the emotion engine to recognize User A's emotions. For example, if User A writes, "I've been feeling very tired lately," the emotion engine determines User A's current emotional state as "tired." Based on this, the server generates a calm message related to a common interest. The generated message might be, "Do you think you can enjoy the movie 'Tenet,' which is currently a hot topic, while relaxing?" and presents it to User A. User A can then review this message and send it to User B, sparking a natural conversation.

[0345] A specific example of a prompt sentence could be, "User A is interested in movies and music and has been feeling tired lately. Please generate a message that will provide a common topic." Based on this prompt sentence, the system can suggest appropriate conversation starters.

[0346] The hardware used includes the user's smartphone or PC (device) and a cloud server. The software includes a profile input UI, a transmission server, a generative AI model library (e.g., GPT-3), and a sentiment analysis engine (e.g., a natural language processing engine). This system enables users to start natural conversations and communicate in a way that takes emotions into consideration.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] Enter user information

[0350] User: The user opens the profile setting screen and enters their hobbies, interests, location information, and self-introduction. The entered data is stored in text format on the device.

[0351] Terminal: The terminal converts the profile information entered by the user into a specified format (e.g., JSON). The formatted data is sent to the server using the HTTPS protocol.

[0352] Input: Raw data entered by the user (hobbies, interests, location, bio).

[0353] Output: Formatted data (JSON format).

[0354] Step 2:

[0355] Training generative AI models

[0356] Server: The server takes the received profile information as an input dataset for the generative AI model. The dataset includes feature data such as the user's hobbies and interests.

[0357] Server: Extracts feature data and analyzes user interests. A generative AI model (e.g., GPT-3) is used to learn information related to the user's interests. Natural language processing (NLP) techniques are used in this process.

[0358] Server: The user model (profile of interests and personality) generated as a result of learning is stored in a database.

[0359] Input: Formatted profile data (JSON format).

[0360] Output: Learned user model (stored in database).

[0361] Step 3:

[0362] Collecting online news

[0363] Server: The server periodically collects the latest news articles from the Internet using RSS feeds and web scraping technology. The data collected includes information such as article titles, content, and categories.

[0364] Server: Organizes collected news articles by category and performs preprocessing (e.g., noise removal, text normalization).

[0365] Server: Using a filtering algorithm, extract only articles that are highly relevant to the user's interests.

[0366] Input: Raw news data collected from the internet.

[0367] Output: Organized news article data by category.

[0368] Step 4:

[0369] Extracting common topics and generating messages

[0370] Server: Uses a generative AI model to match user profile information with collected news articles, using a similarity calculation algorithm (e.g., cosine similarity) in the process.

[0371] Server: Combines highly similar news articles with user interests to extract common topics.

[0372] Server: Uses natural language generation technology to generate messages that spark conversations between users.

[0373] Input: Organized news article data, user profile information.

[0374] Output: The generated conversation starter message.

[0375] Step 5:

[0376] Talk suggestions

[0377] Server: Sends the generated message to the user's terminal.

[0378] Terminal: Updates the UI to present received messages to the user in a preview format.

[0379] User: Check the message presented and, if necessary, press the send button to send the message to the other user.

[0380] Input: The generated conversation message.

[0381] Output: Messages confirmed by users or sent.

[0382] Step 6:

[0383] Conversation analysis and feedback

[0384] Server: Collects logs of messages sent and received between users and stores them in a database.

[0385] Server: Analyzes the collected message content using a generative AI model to evaluate the progress of the conversation and user responses. This analysis uses text mining techniques.

[0386] Server: If the conversation is stagnating or if the user is not responding well, generate new topics and messages and suggest them to the user again.

[0387] Input: A log of messages sent and received.

[0388] Output: Analysis results, newly generated conversation starter messages.

[0389] Step 7:

[0390] Incorporating an emotion engine

[0391] Server: Uses an emotion engine (e.g., a natural language processing engine) to recognize emotions from users' messages and behaviors. Infers emotional states by analyzing the tone and frequency of text messages.

[0392] Server: Based on the recognized emotion data, the server fine-tunes the conversation starter message. For example, if the user is judged to be "tired," it generates a gentle message such as, "Do you think you can enjoy the popular movie "Tenet" while relaxing?"

[0393] Server: Emotionally tailored messages are made emotionally appropriate using natural language generation techniques.

[0394] Input: The user's message data.

[0395] Output: Tailored messages generated based on sentiment.

[0396] (Application example 2)

[0397] 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."

[0398] In recent years, communication with customers in brick-and-mortar stores has become increasingly important. However, it is difficult to smoothly advance natural conversations between store clerks and customers, and it is particularly challenging to provide appropriate topics of conversation for customers meeting for the first time. It is also difficult to instantly grasp the customer's emotional state and respond appropriately to the situation. Furthermore, there is a need to suggest new topics of conversation when the conversation stalls or when progress is not being made.

[0399] 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.

[0400] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting users in sending messages; an analysis means for collecting message logs and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; an emotion recognition means for recognizing the user's emotions using an emotion engine and generating conversation messages based on the recognized emotions; and a conversation support means for a store clerk wearing smart glasses in a physical store to support natural conversations with users. This enables smooth natural conversations with customers and enables responses according to the customer's emotional state.

[0401] "Input means" refers to a device or system for collecting user profile information.

[0402] The "transmission means" is a device or system that transmits the input user profile information to the server.

[0403] A "learning means" is a device or system that uses a generative AI model to learn user profile information and analyze user interests.

[0404] An "aggregator" is a device or system that collects the latest news articles from the Internet and filters them to those relevant to the user's interests.

[0405] The "generation means" is a device or system that extracts common topics between users and generates messages that serve as conversation starters.

[0406] The "presentation means" is a device or system that presents the generated message to the user and allows the user to check the message.

[0407] A "receiving means" is a device or system that supports users in sending messages.

[0408] The "analysis means" is a device or system that collects message logs and analyzes the progress of the conversation.

[0409] A "suggestion means" is a device or system that suggests new conversation starters based on the analysis results.

[0410] The "emotion recognition means" is a device or system that uses an emotion engine to recognize a user's emotion and generates a conversational message based on the recognized emotion.

[0411] A "conversation support means" is a device or system that supports natural conversation between a store clerk wearing smart glasses and a user in a physical store.

[0412] MODE FOR CARRYING OUT THE INVENTION

[0413] The present invention provides a system for supporting natural conversations with customers in a physical store. The system includes a series of means for inputting, transmitting, and learning user profile information. Specific embodiments of the system are described below.

[0414] System Overview

[0415] The system consists of an input means for inputting user profile information, a transmission means for sending the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting and filtering the latest news articles from the Internet, a generation means for extracting common topics between users and generating messages, a presentation means for presenting the generated messages, a reception means for supporting the sending and receiving of messages, an analysis means for analyzing the progress of the conversation, a suggestion means for proposing new topics based on the analysis results, and an emotion recognition means for recognizing user emotions using an emotion engine.It also includes a conversation support means in which store clerks wearing smart glasses support natural conversations with customers in physical stores.

[0416] What the program does

[0417] Enter and submit user information

[0418] Users enter their profile information through smart glasses worn by a store clerk in a brick-and-mortar store, such as their hobbies, interests, and current mood. This information is formatted and sent to a server via the smart glasses.

[0419] Learning and analysis with generative AI models

[0420] The server provides the received user profile information to the generative AI model for learning. The generative AI model analyzes the user's interests and personality and stores the results. This allows it to provide optimal conversation starters to customers.

[0421] News article collection and filtering

[0422] The server periodically collects the latest news articles from the Internet, organizes them into categories, and filters only those relevant to the user's interests, making it easier for customers to find topics of interest.

[0423] Conversation starter generation and presentation

[0424] The server uses a generative AI model to match the user's profile information with collected news articles to extract common topics. Based on the extracted topics, it generates messages that serve as natural conversation starters. The generated messages are displayed on the smart glasses to help store associates start conversations with customers.

[0425] Sending and receiving messages and analyzing progress

[0426] When a user sends a message, the history is stored on the server. The server analyzes the collected message logs and evaluates the progress of the conversation. Based on this evaluation, if the conversation has stalled or is not progressing, it will suggest a new topic.

[0427] Emotion recognition and conversation regulation

[0428] The server uses an emotion engine to recognize the user's emotions. It estimates the user's emotional state from the user's facial expressions and message tone, and adjusts the conversation message accordingly. For example, if the user is feeling "tired," a gentle message that takes that emotion into account is generated.

[0429] Specific examples

[0430] For example, if User A is interested in "movies" and "music" and is currently feeling "tired," the server will use a generative AI model based on User A's profile information to learn from it. The server will then collect the latest movie-related news articles from the Internet and extract topics suitable for User A, who is feeling "tired." The smart glasses will display a message saying, "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and the store clerk will use this message to help naturally start a conversation with User A.

[0431] Prompt Sentence Examples

[0432] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[0433] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0434] Step 1:

[0435] The user inputs profile information. The user inputs information such as hobbies, interests, and current mood through the interface of the smart glasses. The input information is formatted to be sent from the smart glasses to the server. The input data is the user's profile information, and the output data is the formatted profile information.

[0436] Step 2:

[0437] The server receives the transmitted profile information. The server receives the transmitted profile information from the smart glasses and stores it in a database. The input data is the formatted profile information, and the output data is the stored profile information.

[0438] Step 3:

[0439] The server uses the generative AI model to learn the user's profile information and analyze their interests and personality. The server trains the generative AI model based on the input profile information to identify the user's interests and personality. The input data is the profile information, and the output data is the analysis of the user's interests and personality.

[0440] Step 4:

[0441] The server collects the latest news articles from the Internet and organizes them by category. The server periodically scrapes the news articles, filters them by category, and stores them in a database. The input data are news articles from the Internet, and the output data are categorized news articles.

[0442] Step 5:

[0443] The collected news articles are filtered by relating them to the user's interests. The server selects relevant news articles based on the user's interests obtained from the generative AI model. The input data are categorized news articles and the user's interests, and the output data are filtered related news articles.

[0444] Step 6:

[0445] The server extracts common topics and generates messages that can spark conversation. The server matches the filtered news articles with the user's profile information to find common topics. It then uses a generative AI model to generate messages that can spark natural conversation. The input data are the filtered news articles and profile information, and the output data are the generated messages.

[0446] Step 7:

[0447] The server sends the generated message to the smart glasses and presents it to the user. The smart glasses display the received message for the user to review. The input data is the generated message, and the output data is the displayed message.

[0448] Step 8:

[0449] The user starts a conversation based on the message and sends and receives messages. The store clerk wearing smart glasses starts a conversation with the customer based on the displayed message. The message sent by the user is sent to the server and saved as a log. The input data is the sent message, and the output data is the saved message log.

[0450] Step 9:

[0451] The server collects message logs and analyzes the progress of the conversation. The server analyzes the collected message logs and identifies when the conversation has been interrupted or when progress is not being made. The input data is the message logs, and the output data is the progress analysis result.

[0452] Step 10:

[0453] The server proposes new topics based on the analysis results. The server then uses a generative AI model based on the results of the previous analysis to generate new conversation starters and sends them to the smart glasses. The input data is the analysis results, and the output data is the newly generated message.

[0454] Step 11:

[0455] The server recognizes the user's emotions using an emotion engine and adjusts the conversation message based on the recognized emotions. The server estimates the user's emotional state from the user's facial expression and message tone, generates an appropriate message, and displays it on the smart glasses. The input data is the user's facial expression and message tone, and the output data is the adjusted message.

[0456] Prompt Sentence Examples

[0457] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Second embodiment]

[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0473] 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."

[0474] The present invention relates to a system for providing an opportunity for smooth conversation between users, and specific embodiments thereof will be described below.

[0475] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet and filtering them according to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a proposal means for proposing new conversation starters based on the analysis results.

[0476] Overview of program processing

[0477] 1. Enter user information

[0478] User: Open the profile settings screen and enter your hobbies, interests, and location information.

[0479] Terminal: Formats the information entered and sends it to the server.

[0480] 2. Training the generative AI model

[0481] Server: Receives the submitted user profile information and provides it to the generative AI model for learning.

[0482] Server: Deeply analyzes user interests and personalities and stores this information.

[0483] 3. Collecting online news

[0484] Server: Uses RSS feeds and news APIs to gather the latest news articles from the internet.

[0485] Server: Organizes collected news into categories and filters news relevant to the user's interests.

[0486] 4. Extracting common topics and generating messages

[0487] Server: Uses a generative AI model to match user profile content with collected news articles.

[0488] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[0489] 5. Talk suggestions

[0490] Server: Sends the generated message to the user's terminal.

[0491] Terminal: Presents the generated message to the user in a preview format.

[0492] User: Checks the message presented and decides whether to send it to the recipient.

[0493] 6. Conversation analysis and feedback

[0494] Server: Collects the history of messages sent and received between users and monitors the progress of the conversation.

[0495] Server: Analyzes the content of the conversation using a generative AI model and evaluates the user's reaction and the level of conversation activity.

[0496] Server: Generates new topics and messages as needed and suggests them to users.

[0497] Specific examples

[0498] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest relevant online news.

[0499] The server extracts reviews of new movies as a common interest of users A and B. Next, the server generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to user A. User A checks this message and sends it to user B, creating a natural conversation starter.

[0500] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[0501] The processing flow will be explained below.

[0502] Step 1: Enter your information

[0503] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[0504] Terminal: Formats the information entered and sends it to the server.

[0505] Step 2: Training the generative AI model

[0506] Server: Receives profile information sent by users.

[0507] Server: Provides the generative AI model with user profile information, which allows the model to learn about the user's interests and personality.

[0508] Server: Stores the learning results of the generative AI model in a database.

[0509] Step 3: Collecting online news

[0510] Server: Periodically gathers the latest news articles from the internet, using RSS feeds and news APIs.

[0511] Server: Organizes news articles into categories and records metadata for each news article.

[0512] Step 4: Extracting common topics and generating messages

[0513] Server: Uses a generative AI model to match user profile information with collected news articles.

[0514] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[0515] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[0516] Step 5: Propose a talk

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

[0518] Terminal: Presents the generated message to the user in a preview format, allowing the user to review the message and decide whether to send it or not.

[0519] User: Edits the suggested message as needed and sends it to whomever they deem appropriate.

[0520] Step 6: Analysis and feedback of the conversation

[0521] Server: Collects the history of messages sent and received between users and stores it in a database.

[0522] Server: Using a generative AI model, the server analyzes the collected messages and evaluates the progress of the conversation based on factors such as user responses and message frequency.

[0523] Server: If the conversation dies or progress is not being made, the server generates new topics and messages and presents them to the user. For example, it generates new messages based on news articles related to a different topic of interest.

[0524] This makes it easier for users to maintain a natural conversation flow and helps ensure smooth communication with people they meet for the first time.

[0525] Example 1

[0526] 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."

[0527] In modern society, facilitating communication between users is an important issue. In particular, it is difficult to find an opportunity to naturally start a conversation between users with different hobbies and interests. Furthermore, insufficient topic suggestions based on users' interests have led to problems with conversations not continuing. A means to solve these problems is needed.

[0528] 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.

[0529] In this invention, the server includes an input means for inputting user data, a transmission means for transmitting the input user data to the server, a learning means for learning the user data using a generative AI model and analyzing the user's interests, a collection means for collecting the latest information from the network and filtering information related to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to the users and allowing the users to confirm the messages, a communication means for supporting the users in sending messages, an analysis means for collecting message logs and analyzing the progress of the conversation, and a suggestion means for suggesting new conversation starters based on the analysis results. This allows for smooth conversation starters to be provided between users, facilitating communication.

[0530] "User data" refers to personal information entered by the user, such as interests, hobbies, and location information.

[0531] "Input means" refers to an interface or device through which a user inputs data, specifically the settings screen of a mobile app or web application.

[0532] "Transmission means" refers to the function or protocol for transmitting input data to a server. For example, it includes secure communication methods such as HTTPS.

[0533] A "generative AI model" is an artificial intelligence algorithm that learns from user data and analyzes their interests and concerns, specifically a model that uses natural language processing technology.

[0534] A "learning method" is a method or process for using a generative AI model to analyze user data and identify user interests and concerns.

[0535] "Gathering methods" are methods and tools that obtain the latest information from the network and filter it according to the user's interests. Examples include RSS feed readers and news APIs.

[0536] The "generation means" refers to a method or function for extracting common topics between users and generating messages that will spark natural conversation.

[0537] "Presentation means" refers to the method or interface for displaying the generated message to the user and allowing them to check it. Examples include push notifications and in-app notification functions.

[0538] "Communication means" refers to the method or technology used by a user to send messages to others. Specifically, this applies to chat apps and messaging services.

[0539] "Analysis tools" are methods and algorithms for collecting logs of messages sent and received between users and assessing the progress of the conversation.

[0540] The "suggestion means" is a method or system for generating a message that can serve as a starting point for a new conversation based on the analysis results and presenting it to the user.

[0541] The present invention relates to a system for providing a smooth conversation starter between users, and a specific embodiment thereof will be described below. This system is realized using the following hardware and software.

[0542] Hardware and Software

[0543] 1. User device: smartphone, tablet, or PC

[0544] 2. Server: Cloud server, on-premise server, etc.

[0545] 3. Internet connection: A stable network connection (Wi-Fi, 4G / 5G, etc.)

[0546] 4. Generative AI models: AI models that apply natural language processing technology (e.g., GPT-3)

[0547] Overview of program processing

[0548] 1. Enter user information

[0549] User: A user opens a profile in a mobile or web application and enters their interests, hobbies, and location information. Examples include "movies," "music," and "travel."

[0550] Terminal: The entered information is formatted in JSON format and sent to the server via a secure protocol (e.g., HTTPS).

[0551] 2. Training the generative AI model

[0552] Server: The server receives the JSON data and extracts the user's profile information. The extracted information is fed into a generative AI model (e.g., GPT-3) to learn the user's interests and personality patterns. The learning results are stored in a database along with the user ID.

[0553] 3. Collecting online news

[0554] Server: The server uses an RSS feed reader or a news API (e.g., NewsAPI.org) to collect the latest news articles from the network, organize them into categories, and filter only those relevant to the user's interests.

[0555] 4. Extracting common topics and generating messages

[0556] Server: A generative AI model is used to match the user's profile information with filtered news articles. Common topics are extracted and a conversation-starting message in natural language is generated. For example, a message might be generated that asks, "Have you seen the recently talked-about movie 'Tenet'?"

[0557] 5. Talk suggestions

[0558] Server: The generated message is sent to the user's terminal.

[0559] Device: The device displays the message in a preview format to the user, who can then review the message and decide whether to send it to the other party.

[0560] 6. Conversation analysis and feedback

[0561] Server: The server collects message exchange history between users in real time and analyzes the content of the conversation using a generative AI model. It evaluates user reactions and the level of conversation activity, and generates and provides new topic suggestion messages as needed.

[0562] Specific examples

[0563] For example, consider the case where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters their interests in "movies" and "music" on their profile settings screen, and their device sends this information to the server. The server uses a generative AI model to learn about User A and collect and filter the latest related news articles from the internet. The server extracts reviews of new movies as a common topic between User A and User B, and generates a message asking, "Have you seen the recently talked-about movie 'Tenet'?" This message is sent to User A's device, where User A confirms it and sends it to User B, creating a natural conversation starter.

[0564] Prompt Sentence Examples

[0565] "Please talk about the movie 'Tenet'."

[0566] "Please extract topics that users A and B are both interested in from the latest music news."

[0567] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[0568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0569] Step 1:

[0570] Enter user information

[0571] User: Open the profile settings screen and enter your interests, hobbies, and location information.

[0572] Input: Movies, music, travel

[0573] Output: This information is entered into the form.

[0574] Terminal: Formats the input information into JSON format and sends it to the server.

[0575] Input: Movies, Music, Travel input fields

[0576] Output: JSON format data {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[0577] Step 2:

[0578] Training generative AI models

[0579] Server: Receives the JSON data and extracts the user's profile information.

[0580] Input: {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[0581] Output: User interest data

[0582] Server: Feeds data to a generative AI model (e.g., GPT-3) to learn patterns of user interests and personality.

[0583] Input: User interest data

[0584] Output: Learning results of user's interest and personality patterns

[0585] Server: The learning results are stored in a database, linked to the user ID.

[0586] Input: Learning results and user ID

[0587] Output: User profile stored in the database

[0588] Step 3:

[0589] Collecting online news

[0590] Server: Collects the latest news articles using the news API.

[0591] Input: News API request

[0592] Output: A list of the latest news articles

[0593] Server: Organizes news articles into categories and filters news relevant to the user's interests.

[0594] Input: A list of recent news articles

[0595] Output: News articles related to the user's interests

[0596] Step 4:

[0597] Extracting common topics and generating messages

[0598] Server: Uses a generative AI model to match user profile information with news articles.

[0599] Input: User interest / personality data, news articles

[0600] Output: Candidates for common topics

[0601] Server: Generates natural conversation starter messages.

[0602] Input: Candidates for common topics

[0603] Output: Generated message: "Have you seen the recent popular movie, Tenet?"

[0604] Step 5:

[0605] Talk suggestions

[0606] Server: Sends the generated message to the user's terminal.

[0607] Input: The generated message

[0608] Output: Sends a message to the user's terminal

[0609] Terminal: Presents the message to the user in a preview format.

[0610] Input: The generated message

[0611] Output: The message presented to the user

[0612] Step 6:

[0613] Conversation analysis and feedback

[0614] Server: Collects message exchange history between users in real time.

[0615] Input: User-to-user messages

[0616] Output: Collected message history

[0617] Server: Analyzes the content of the conversation using a generative AI model.

[0618] Input: Message history

[0619] Output: Analysis results (conversation activity, user responses, etc.)

[0620] Server: Generates new topic suggestion messages as needed and provides them to users.

[0621] Input: Analysis results

[0622] Output: New suggestion message: "Let's talk about recently released music albums."

[0623] This specific processing step promotes smooth conversation between users.

[0624] (Application example 1)

[0625] 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."

[0626] Communication between staff and customers in brick-and-mortar stores is challenging because it is difficult to accurately grasp customers' interests and provide appropriate conversation starters. There is also a need to instantly access the information needed to provide personalized customer service. However, current systems have difficulty meeting these demands.

[0627] 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.

[0628] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting the user in sending messages; an analysis means for collecting a message log and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; and a presentation means for presenting common topics between staff and customers in a physical store using smart glasses or a head-mounted display, thereby enabling smooth communication between staff and customers in a physical store.

[0629] "Input means" refers to a device or interface for inputting user profile information.

[0630] The "transmission means" is a communication means for transmitting the input user profile information to the server.

[0631] A "learning means" is a device or software that uses a generative AI model to learn a user's profile information and analyze the user's interests.

[0632] An "aggregator" is a device or software that gathers current news articles from the Internet and filters them for news relevant to the user's interests.

[0633] The "generation means" is a device or software for extracting common topics between users and generating messages that will serve as conversation starters.

[0634] The "presentation means" is a device or interface that presents the generated message to the user and allows the user to check the message.

[0635] A "receiving means" is a communication means that supports users in sending messages.

[0636] An "analysis means" is a device or software that collects a log of messages and analyzes the progress of a conversation.

[0637] The "suggestion means" is a device or software that suggests new conversation starters based on the analysis results.

[0638] "Smart glasses" are glasses-type devices that visually present information to a user.

[0639] A "head-mounted display" is a head-mounted display device for visually presenting information to a user.

[0640] A "common topic" is a concern or interest shared between users.

[0641] A "brick and mortar store" is a retail or service establishment that has a physical location.

[0642]

[0643] The present invention relates to a system for realizing smooth communication between staff and customers in a brick-and-mortar store. The system utilizes smart glasses or a head-mounted display to present staff with conversation starters based on the customer's interests.

[0644] First, when a user (customer) visits a store, they input their profile information, which includes their interests, concerns, and recent purchase history. This information is sent to the server through an input method. The server then uses a generative AI model to learn the user's profile information and analyze their interests. This learning method is important for gaining a deep understanding of the user's interests.

[0645] The server then collects the latest news articles from the internet using RSS feeds and news APIs, organizes them into categories, and filters news relevant to the user's interests.

[0646] The generative AI model compares user profile information with collected news articles to extract common topics between users. This generation method generates messages to spark conversation. The generated messages are presented to staff via smart glasses or a head-mounted display. This presentation method makes it easier for staff to identify topics that may interest customers.

[0647] The server also includes a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a suggestion means for suggesting new conversation starters based on the analysis results.

[0648] As a concrete example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news. The server extracts reviews of new movies as a common interest of Users A and B. The server then generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to User A. User A then sees this message, allowing the staff member to start a natural conversation with the customer.

[0649] Representative generative AI models include GPT-4 and BERT. News API and Google News API can be used to gather news. MySQL and PostgreSQL can be used as database management systems.

[0650] Examples of specific prompts include:

[0651] "User A's profile:

[0652] Hobbies: Movies, music

[0653] Interests: Latest technology, fashion

[0654] User B's profile:

[0655] Hobbies: Cooking, Traveling

[0656] Interests: Health, Sports

[0657] Please suggest some common topics for these users."

[0658] By providing such prompts, the generative AI model can identify common topics between users A and B and suggest appropriate conversation starters to the wait staff.

[0659] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0660] Step 1:

[0661] Enter user profile information

[0662] When a user visits a store, they input their profile information (interests, concerns, recent purchase history, etc.) using a smartphone or tablet device.

[0663] Input data: User interests, concerns, recent purchase history

[0664] Output data: JSON format of input data

[0665] Step 2:

[0666] Sending input data

[0667] The device formats the profile information entered by the user and sends it to the server over Wi-Fi or mobile data.

[0668] Input data: User profile information (JSON format)

[0669] Output data: Send data to the server

[0670] Step 3:

[0671] Training generative AI models

[0672] The server receives the user's profile information and provides it to the generative AI model for training. The training method uses a generative AI model (e.g., GPT-4, BERT).

[0673] Input data: User profile information

[0674] Output data: Analysis of user interests and personalities

[0675] Step 4:

[0676] News article collection and filtering

[0677] The server uses RSS feeds and news APIs to gather the latest news articles from the internet, organizes them into categories, and filters news relevant to the user's interests.

[0678] Input data: News articles collected from the news API

[0679] Output data: News articles related to the user's interests

[0680] Step 5:

[0681] Extracting common topics and generating messages

[0682] The server uses a generative AI model to match users' profile information with collected news articles, extract common topics between users, and generate messages that spark natural conversations.

[0683] Input data: user profile information, filtered news articles

[0684] Output data: Generated conversation starter message

[0685] Step 6:

[0686] Message presentation

[0687] The server then sends the generated message to the user's device and presents it to the staff via smart glasses or a head-mounted display, allowing the staff to visually confirm topics that may be of interest to the customer.

[0688] Input data: Generated conversation starter messages

[0689] Output data: Visual presentation of the message

[0690] Step 7:

[0691] Monitoring and analyzing conversation progress

[0692] The server collects messages sent and received between users and monitors the progress of the conversation. It uses a generative AI model to analyze the content of the conversation and evaluates the user's reactions and the level of conversation activity.

[0693] Input data: Message exchange history between users

[0694] Output data: Conversation analysis results and evaluation

[0695] Step 8:

[0696] Propose new conversation starters

[0697] The server proposes new conversation starters based on the analysis results, and the suggestion means generates new messages for the user, which are then presented again.

[0698] Input data: Conversation analysis results and evaluation

[0699] Output: New conversation starter message

[0700] 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.

[0701] The present invention relates to a system for providing natural conversation starters between users, and in particular, a specific embodiment will be described in which a combination of emotion engines is used to recognize user emotions and support more appropriate communication.

[0702] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning about user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet, a generation means for extracting common topics and generating conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, a suggestion means for proposing new conversation starters based on the analysis results, and an emotion engine for recognizing user emotions using an emotion engine and a function for generating appropriate conversation messages based on the recognition.

[0703] Overview of program processing

[0704] 1. Enter user information

[0705] User: Open the profile settings screen and enter your hobbies, interests, location, and self-introduction.

[0706] Terminal: Formats the information entered and sends it to the server.

[0707] 2. Training the generative AI model

[0708] Server: Receives the submitted profile information and provides it to the generative AI model for learning.

[0709] Server: Analyzes the user's interests and personality and stores the learning results of the generative AI model.

[0710] 3. Collecting online news

[0711] Server: Periodically collects the latest news articles from the Internet and organizes them into categories.

[0712] Server: The news articles are then filtered to match the user's interests.

[0713] 4. Extracting common topics and generating messages

[0714] Server: Uses a generative AI model to match user profile information with collected news articles.

[0715] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[0716] Server: For example, create a message like, "Have you seen the recently talked about movie, Tenet?"

[0717] 5. Talk suggestions

[0718] Server: Sends the generated message to the user's terminal.

[0719] Terminal: Presents the message to the user in a preview format, allowing the user to review it and decide whether to send it.

[0720] User: Starts a conversation by sending a message.

[0721] 6. Conversation analysis and feedback

[0722] Server: Collects the history of messages sent and received between users and stores it in a database.

[0723] Server: Uses a generative AI model to analyze collected message content and evaluate user responses and conversation progress.

[0724] Server: If the conversation stalls or progress is not being made, it generates new topics and messages and suggests them to the user.

[0725] 7. Incorporating an Emotional Engine

[0726] Server: Uses an emotion engine to recognize emotions from messages and user behavior, for example, inferring a user's emotional state from the tone and frequency of their text messages.

[0727] Server: Adjusts conversation starters based on the recognized emotions. For example, if the user shows anger or sadness, it generates a calm message that takes that emotion into account.

[0728] Server: Suggested messages based on emotions are tailored to be emotionally appropriate using natural language generation technology.

[0729] Specific examples

[0730] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends this information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news.

[0731] Next, the server uses an emotion engine to recognize emotions from User A's messages and behavior. For example, if User A wrote "I've been very tired recently" in a past message, the emotion engine determines that User A is currently "tired." Based on this, the server generates a calm message related to a common interest.

[0732] The server generates a message in the form of "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and presents it to User A. User A checks this message and sends it to User B, creating a natural conversation starter. By taking into account the user's emotions, this system provides a more personalized experience.

[0733] This makes it easier for users to maintain a natural conversation flow that reflects their emotions, and allows for smooth communication with people they meet for the first time.

[0734] The processing flow will be explained below.

[0735] Step 1: Enter your information

[0736] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[0737] Terminal: Formats the information entered and sends it to the server.

[0738] Step 2: Training the generative AI model

[0739] Server: Receives the transmitted user profile information.

[0740] Server: Provides the generative AI model with user profile information, which allows the model to learn about interests and personality.

[0741] Server: Stores the learning results of the generative AI model in a database.

[0742] Step 3: Collecting online news

[0743] Server: Uses RSS feeds and news APIs to periodically gather the latest news articles from the internet.

[0744] Server: Organizes collected news articles by category and records metadata of news articles.

[0745] Step 4: Extracting common topics and generating messages

[0746] Server: Uses a generative AI model to match user profile information with collected news articles.

[0747] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[0748] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[0749] Step 5: Incorporating the Emotion Engine

[0750] Server: Using the emotion engine, analyzes the user's messages and behavioral data to recognize their current emotional state. For example, it determines whether the user is expressing emotions such as "tiredness" or "joy" based on the content and frequency of text messages.

[0751] Server: Adjusts the generated messages based on the user's perceived emotions. For example, if the user feels "tired," it suggests emotionally appropriate topics such as "relaxing movies."

[0752] Step 6: Propose a talk

[0753] Server: Sends the coordinated conversation message to the user's terminal.

[0754] Terminal: The generated message is presented to the user in a preview format, allowing the user to review it and decide whether it is appropriate.

[0755] User: Review the message and send it to whomever they deem appropriate.

[0756] Step 7: Collect conversation progress

[0757] Server: Collects the history of messages sent and received between users and stores it in a database.

[0758] Server: Analyzes collected message content using a generative AI model to evaluate user responses and conversation progress.

[0759] Step 8: Suggest new conversation starters

[0760] Server: Using the emotion engine, it reconfirms the user's current emotional state and generates new topics and messages as needed. For example, if the user has a positive emotion towards the conversation, it suggests further interesting topics.

[0761] Server: Maintains smooth communication by sending newly generated messages to the user's device.

[0762] This helps maintain a natural conversation flow between users and helps ensure smooth communication with people meeting for the first time.

[0763] Example 2

[0764] 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."

[0765] In today's world, it is difficult for users to naturally start a conversation, and it is often difficult for them to communicate their feelings, especially when they meet for the first time. Furthermore, conventional communication support systems have difficulty recognizing users' emotions and suggesting appropriate ways to start a conversation. This leads to unnatural communication between users, making it difficult to build relationships.

[0766] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0767] In this invention, the server includes an input means for inputting user profile information, a transmission means for transmitting the input user profile information to the server, and a learning means for learning the user profile information and analyzing the user's interests using a generative AI model, thereby enabling the server to recognize the user's emotions using an emotion engine and generate appropriate conversational messages.

[0768] "Input means" refers to an interface through which a user inputs their profile information.

[0769] "Transmission means" refers to the function of converting the entered profile information into an appropriate format and transmitting it to the server.

[0770] "Learning means" refers to the function that uses a generative AI model to analyze a user's profile information and learn about the user's interests and personality.

[0771] "Gathering means" refers to the function of collecting the latest news articles from the Internet, organizing them into categories, and filtering news related to the user's interests.

[0772] "Generation means" refers to a function that extracts common topics between users and generates messages that will serve as a starting point for natural conversation.

[0773] The "presentation means" refers to a function that presents the generated message to the user so that the user can confirm the message.

[0774] "Receiving means" refers to a function that supports users in sending messages.

[0775] "Analysis means" refers to the function of collecting message logs and analyzing the progress of the conversation and the user's reactions.

[0776] "Suggestion means" refers to a function that suggests new conversation starters to the user based on the analysis results.

[0777] "Emotion recognition means" refers to a function that uses an emotion engine to recognize a user's emotion and generates an appropriate conversational message based on that emotion.

[0778] The present invention is a system for providing natural conversation starters between users, and in particular, by combining an emotion engine, it recognizes user emotions and supports more appropriate communication. This system provides a terminal with an input means for users to input profile information, and includes a transmission means for transmitting the input information to a server. The server also has a learning means for learning the user's profile information using a generative AI model and analyzing the user's interests based on the results.

[0779] Next, the server has a collection means for collecting the latest news articles from the Internet and uses a specific algorithm to filter out news relevant to the user's interests.The server then extracts common topics based on this information and generates messages that serve as natural conversation starters.Natural language generation technology is used to generate these messages.The generated messages are displayed to the user via a presentation means provided on the terminal.The user can review these messages and send them as needed.

[0780] The server also has an analysis means for collecting messages sent and received between users and analyzing the progress of the conversation based on the collected messages. The server also includes a suggestion means for suggesting new conversation starters to users based on the results of this analysis. The server also has an emotion recognition means that uses an emotion engine to analyze the user's emotions and adjust conversation messages according to the emotions.

[0781] As a specific example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests on a profile setting screen, and the information is sent from the device to the server. The server uses a generative AI model to learn User A's profile information, while simultaneously collecting relevant and recent news articles and identifying articles related to User A's interests.

[0782] The server then uses the emotion engine to recognize User A's emotions. For example, if User A writes, "I've been feeling very tired lately," the emotion engine determines User A's current emotional state as "tired." Based on this, the server generates a calm message related to a common interest. The generated message might be, "Do you think you can enjoy the movie 'Tenet,' which is currently a hot topic, while relaxing?" and presents it to User A. User A can then review this message and send it to User B, sparking a natural conversation.

[0783] A specific example of a prompt sentence could be, "User A is interested in movies and music and has been feeling tired lately. Please generate a message that will provide a common topic." Based on this prompt sentence, the system can suggest appropriate conversation starters.

[0784] The hardware used includes the user's smartphone or PC (device) and a cloud server. The software includes a profile input UI, a transmission server, a generative AI model library (e.g., GPT-3), and a sentiment analysis engine (e.g., a natural language processing engine). This system enables users to start natural conversations and communicate in a way that takes emotions into consideration.

[0785] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0786] Step 1:

[0787] Enter user information

[0788] User: The user opens the profile setting screen and enters their hobbies, interests, location information, and self-introduction. The entered data is stored in text format on the device.

[0789] Terminal: The terminal converts the profile information entered by the user into a specified format (e.g., JSON). The formatted data is sent to the server using the HTTPS protocol.

[0790] Input: Raw data entered by the user (hobbies, interests, location, bio).

[0791] Output: Formatted data (JSON format).

[0792] Step 2:

[0793] Training generative AI models

[0794] Server: The server takes the received profile information as an input dataset for the generative AI model. The dataset includes feature data such as the user's hobbies and interests.

[0795] Server: Extracts feature data and analyzes user interests. A generative AI model (e.g., GPT-3) is used to learn information related to the user's interests. Natural language processing (NLP) techniques are used in this process.

[0796] Server: The user model (profile of interests and personality) generated as a result of learning is stored in a database.

[0797] Input: Formatted profile data (JSON format).

[0798] Output: Learned user model (stored in database).

[0799] Step 3:

[0800] Collecting online news

[0801] Server: The server periodically collects the latest news articles from the Internet using RSS feeds and web scraping technology. The data collected includes information such as article titles, content, and categories.

[0802] Server: Organizes collected news articles by category and performs preprocessing (e.g., noise removal, text normalization).

[0803] Server: Using a filtering algorithm, extract only articles that are highly relevant to the user's interests.

[0804] Input: Raw news data collected from the internet.

[0805] Output: Organized news article data by category.

[0806] Step 4:

[0807] Extracting common topics and generating messages

[0808] Server: Uses a generative AI model to match user profile information with collected news articles, using a similarity calculation algorithm (e.g., cosine similarity) in the process.

[0809] Server: Combines highly similar news articles with user interests to extract common topics.

[0810] Server: Uses natural language generation technology to generate messages that spark conversations between users.

[0811] Input: Organized news article data, user profile information.

[0812] Output: The generated conversation starter message.

[0813] Step 5:

[0814] Talk suggestions

[0815] Server: Sends the generated message to the user's terminal.

[0816] Terminal: Updates the UI to present received messages to the user in a preview format.

[0817] User: Check the message presented and, if necessary, press the send button to send the message to the other user.

[0818] Input: The generated conversation message.

[0819] Output: Messages confirmed by users or sent.

[0820] Step 6:

[0821] Conversation analysis and feedback

[0822] Server: Collects logs of messages sent and received between users and stores them in a database.

[0823] Server: Analyzes the collected message content using a generative AI model to evaluate the progress of the conversation and user responses. This analysis uses text mining techniques.

[0824] Server: If the conversation is stagnating or if the user is not responding well, generate new topics and messages and suggest them to the user again.

[0825] Input: A log of messages sent and received.

[0826] Output: Analysis results, newly generated conversation starter messages.

[0827] Step 7:

[0828] Incorporating an emotion engine

[0829] Server: Uses an emotion engine (e.g., a natural language processing engine) to recognize emotions from users' messages and behaviors. Infers emotional states by analyzing the tone and frequency of text messages.

[0830] Server: Based on the recognized emotion data, the server fine-tunes the conversation starter message. For example, if the user is judged to be "tired," it generates a gentle message such as, "Do you think you can enjoy the popular movie "Tenet" while relaxing?"

[0831] Server: Emotionally tailored messages are made emotionally appropriate using natural language generation techniques.

[0832] Input: The user's message data.

[0833] Output: Tailored messages generated based on sentiment.

[0834] (Application example 2)

[0835] 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."

[0836] In recent years, communication with customers in brick-and-mortar stores has become increasingly important. However, it is difficult to smoothly advance natural conversations between store clerks and customers, and it is particularly challenging to provide appropriate topics of conversation for customers meeting for the first time. It is also difficult to instantly grasp the customer's emotional state and respond appropriately to the situation. Furthermore, there is a need to suggest new topics of conversation when the conversation stalls or when progress is not being made.

[0837] 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.

[0838] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting users in sending messages; an analysis means for collecting message logs and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; an emotion recognition means for recognizing the user's emotions using an emotion engine and generating conversation messages based on the recognized emotions; and a conversation support means for a store clerk wearing smart glasses in a physical store to support natural conversations with users. This enables smooth natural conversations with customers and enables responses according to the customer's emotional state.

[0839] "Input means" refers to a device or system for collecting user profile information.

[0840] The "transmission means" is a device or system that transmits the input user profile information to the server.

[0841] A "learning means" is a device or system that uses a generative AI model to learn user profile information and analyze user interests.

[0842] An "aggregator" is a device or system that collects the latest news articles from the Internet and filters them to those relevant to the user's interests.

[0843] The "generation means" is a device or system that extracts common topics between users and generates messages that serve as conversation starters.

[0844] The "presentation means" is a device or system that presents the generated message to the user and allows the user to check the message.

[0845] A "receiving means" is a device or system that supports users in sending messages.

[0846] The "analysis means" is a device or system that collects message logs and analyzes the progress of the conversation.

[0847] A "suggestion means" is a device or system that suggests new conversation starters based on the analysis results.

[0848] The "emotion recognition means" is a device or system that uses an emotion engine to recognize a user's emotion and generates a conversational message based on the recognized emotion.

[0849] A "conversation support means" is a device or system that supports natural conversation between a store clerk wearing smart glasses and a user in a physical store.

[0850] MODE FOR CARRYING OUT THE INVENTION

[0851] The present invention provides a system for supporting natural conversations with customers in a physical store. The system includes a series of means for inputting, transmitting, and learning user profile information. Specific embodiments of the system are described below.

[0852] System Overview

[0853] The system consists of an input means for inputting user profile information, a transmission means for sending the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting and filtering the latest news articles from the Internet, a generation means for extracting common topics between users and generating messages, a presentation means for presenting the generated messages, a reception means for supporting the sending and receiving of messages, an analysis means for analyzing the progress of the conversation, a suggestion means for proposing new topics based on the analysis results, and an emotion recognition means for recognizing user emotions using an emotion engine.It also includes a conversation support means in which store clerks wearing smart glasses support natural conversations with customers in physical stores.

[0854] What the program does

[0855] Enter and submit user information

[0856] Users enter their profile information through smart glasses worn by a store clerk in a brick-and-mortar store, such as their hobbies, interests, and current mood. This information is formatted and sent to a server via the smart glasses.

[0857] Learning and analysis with generative AI models

[0858] The server provides the received user profile information to the generative AI model for learning. The generative AI model analyzes the user's interests and personality and stores the results. This allows it to provide optimal conversation starters to customers.

[0859] News article collection and filtering

[0860] The server periodically collects the latest news articles from the Internet, organizes them into categories, and filters only those relevant to the user's interests, making it easier for customers to find topics of interest.

[0861] Conversation starter generation and presentation

[0862] The server uses a generative AI model to match the user's profile information with collected news articles to extract common topics. Based on the extracted topics, it generates messages that serve as natural conversation starters. The generated messages are displayed on the smart glasses to help store associates start conversations with customers.

[0863] Sending and receiving messages and analyzing progress

[0864] When a user sends a message, the history is stored on the server. The server analyzes the collected message logs and evaluates the progress of the conversation. Based on this evaluation, if the conversation has stalled or is not progressing, it will suggest a new topic.

[0865] Emotion recognition and conversation regulation

[0866] The server uses an emotion engine to recognize the user's emotions. It estimates the user's emotional state from the user's facial expressions and message tone, and adjusts the conversation message accordingly. For example, if the user is feeling "tired," a gentle message that takes that emotion into account is generated.

[0867] Specific examples

[0868] For example, if User A is interested in "movies" and "music" and is currently feeling "tired," the server will use a generative AI model based on User A's profile information to learn from it. The server will then collect the latest movie-related news articles from the Internet and extract topics suitable for User A, who is feeling "tired." The smart glasses will display a message saying, "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and the store clerk will use this message to help naturally start a conversation with User A.

[0869] Prompt Sentence Examples

[0870] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[0871] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0872] Step 1:

[0873] The user inputs profile information. The user inputs information such as hobbies, interests, and current mood through the interface of the smart glasses. The input information is formatted to be sent from the smart glasses to the server. The input data is the user's profile information, and the output data is the formatted profile information.

[0874] Step 2:

[0875] The server receives the transmitted profile information. The server receives the transmitted profile information from the smart glasses and stores it in a database. The input data is the formatted profile information, and the output data is the stored profile information.

[0876] Step 3:

[0877] The server uses the generative AI model to learn the user's profile information and analyze their interests and personality. The server trains the generative AI model based on the input profile information to identify the user's interests and personality. The input data is the profile information, and the output data is the analysis of the user's interests and personality.

[0878] Step 4:

[0879] The server collects the latest news articles from the Internet and organizes them by category. The server periodically scrapes the news articles, filters them by category, and stores them in a database. The input data are news articles from the Internet, and the output data are categorized news articles.

[0880] Step 5:

[0881] The collected news articles are filtered by relating them to the user's interests. The server selects relevant news articles based on the user's interests obtained from the generative AI model. The input data are categorized news articles and the user's interests, and the output data are filtered related news articles.

[0882] Step 6:

[0883] The server extracts common topics and generates messages that can spark conversation. The server matches the filtered news articles with the user's profile information to find common topics. It then uses a generative AI model to generate messages that can spark natural conversation. The input data are the filtered news articles and profile information, and the output data are the generated messages.

[0884] Step 7:

[0885] The server sends the generated message to the smart glasses and presents it to the user. The smart glasses display the received message for the user to review. The input data is the generated message, and the output data is the displayed message.

[0886] Step 8:

[0887] The user starts a conversation based on the message and sends and receives messages. The store clerk wearing smart glasses starts a conversation with the customer based on the displayed message. The message sent by the user is sent to the server and saved as a log. The input data is the sent message, and the output data is the saved message log.

[0888] Step 9:

[0889] The server collects message logs and analyzes the progress of the conversation. The server analyzes the collected message logs and identifies when the conversation has been interrupted or when progress is not being made. The input data is the message logs, and the output data is the progress analysis result.

[0890] Step 10:

[0891] The server proposes new topics based on the analysis results. The server then uses a generative AI model based on the results of the previous analysis to generate new conversation starters and sends them to the smart glasses. The input data is the analysis results, and the output data is the newly generated message.

[0892] Step 11:

[0893] The server recognizes the user's emotions using an emotion engine and adjusts the conversation message based on the recognized emotions. The server estimates the user's emotional state from the user's facial expression and message tone, generates an appropriate message, and displays it on the smart glasses. The input data is the user's facial expression and message tone, and the output data is the adjusted message.

[0894] Prompt Sentence Examples

[0895] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] [Third embodiment]

[0900] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0901] 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.

[0902] 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).

[0903] 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.

[0904] 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.

[0905] 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).

[0906] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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."

[0912] The present invention relates to a system for providing an opportunity for smooth conversation between users, and specific embodiments thereof will be described below.

[0913] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet and filtering them according to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a proposal means for proposing new conversation starters based on the analysis results.

[0914] Overview of program processing

[0915] 1. Enter user information

[0916] User: Open the profile settings screen and enter your hobbies, interests, and location information.

[0917] Terminal: Formats the information entered and sends it to the server.

[0918] 2. Training the generative AI model

[0919] Server: Receives the submitted user profile information and provides it to the generative AI model for learning.

[0920] Server: Deeply analyzes user interests and personalities and stores this information.

[0921] 3. Collecting online news

[0922] Server: Uses RSS feeds and news APIs to gather the latest news articles from the internet.

[0923] Server: Organizes collected news into categories and filters news relevant to the user's interests.

[0924] 4. Extracting common topics and generating messages

[0925] Server: Uses a generative AI model to match user profile content with collected news articles.

[0926] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[0927] 5. Talk suggestions

[0928] Server: Sends the generated message to the user's terminal.

[0929] Terminal: Presents the generated message to the user in a preview format.

[0930] User: Checks the message presented and decides whether to send it to the recipient.

[0931] 6. Conversation analysis and feedback

[0932] Server: Collects the history of messages sent and received between users and monitors the progress of the conversation.

[0933] Server: Analyzes the content of the conversation using a generative AI model and evaluates the user's reaction and the level of conversation activity.

[0934] Server: Generates new topics and messages as needed and suggests them to users.

[0935] Specific examples

[0936] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest relevant online news.

[0937] The server extracts reviews of new movies as a common interest of users A and B. Next, the server generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to user A. User A checks this message and sends it to user B, creating a natural conversation starter.

[0938] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[0939] The processing flow will be explained below.

[0940] Step 1: Enter your information

[0941] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[0942] Terminal: Formats the information entered and sends it to the server.

[0943] Step 2: Training the generative AI model

[0944] Server: Receives profile information sent by users.

[0945] Server: Provides the generative AI model with user profile information, which allows the model to learn about the user's interests and personality.

[0946] Server: Stores the learning results of the generative AI model in a database.

[0947] Step 3: Collecting online news

[0948] Server: Periodically gathers the latest news articles from the internet, using RSS feeds and news APIs.

[0949] Server: Organizes news articles into categories and records metadata for each news article.

[0950] Step 4: Extracting common topics and generating messages

[0951] Server: Uses a generative AI model to match user profile information with collected news articles.

[0952] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[0953] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[0954] Step 5: Propose a talk

[0955] Server: Sends the generated conversation message to the user's terminal.

[0956] Terminal: Presents the generated message to the user in a preview format, allowing the user to review the message and decide whether to send it or not.

[0957] User: Edits the suggested message as needed and sends it to whomever they deem appropriate.

[0958] Step 6: Analysis and feedback of the conversation

[0959] Server: Collects the history of messages sent and received between users and stores it in a database.

[0960] Server: Using a generative AI model, the server analyzes the collected messages and evaluates the progress of the conversation based on factors such as user responses and message frequency.

[0961] Server: If the conversation dies or progress is not being made, the server generates new topics and messages and presents them to the user. For example, it generates new messages based on news articles related to a different topic of interest.

[0962] This makes it easier for users to maintain a natural conversation flow and helps ensure smooth communication with people they meet for the first time.

[0963] Example 1

[0964] 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."

[0965] In modern society, facilitating communication between users is an important issue. In particular, it is difficult to find an opportunity to naturally start a conversation between users with different hobbies and interests. Furthermore, insufficient topic suggestions based on users' interests have led to problems with conversations not continuing. A means to solve these problems is needed.

[0966] 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.

[0967] In this invention, the server includes an input means for inputting user data, a transmission means for transmitting the input user data to the server, a learning means for learning the user data using a generative AI model and analyzing the user's interests, a collection means for collecting the latest information from the network and filtering information related to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to the users and allowing the users to confirm the messages, a communication means for supporting the users in sending messages, an analysis means for collecting message logs and analyzing the progress of the conversation, and a suggestion means for suggesting new conversation starters based on the analysis results. This allows for smooth conversation starters to be provided between users, facilitating communication.

[0968] "User data" refers to personal information entered by the user, such as interests, hobbies, and location information.

[0969] "Input means" refers to an interface or device through which a user inputs data, specifically the settings screen of a mobile app or web application.

[0970] "Transmission means" refers to the function or protocol for transmitting input data to a server. For example, it includes secure communication methods such as HTTPS.

[0971] A "generative AI model" is an artificial intelligence algorithm that learns from user data and analyzes their interests and concerns, specifically a model that uses natural language processing technology.

[0972] A "learning method" is a method or process for using a generative AI model to analyze user data and identify user interests and concerns.

[0973] "Gathering methods" are methods and tools that obtain the latest information from the network and filter it according to the user's interests. Examples include RSS feed readers and news APIs.

[0974] The "generation means" refers to a method or function for extracting common topics between users and generating messages that will spark natural conversation.

[0975] "Presentation means" refers to the method or interface for displaying the generated message to the user and allowing them to check it. Examples include push notifications and in-app notification functions.

[0976] "Communication means" refers to the method or technology used by a user to send messages to others. Specifically, this applies to chat apps and messaging services.

[0977] "Analysis tools" are methods and algorithms for collecting logs of messages sent and received between users and assessing the progress of the conversation.

[0978] The "suggestion means" is a method or system for generating a message that can serve as a starting point for a new conversation based on the analysis results and presenting it to the user.

[0979] The present invention relates to a system for providing a smooth conversation starter between users, and a specific embodiment thereof will be described below. This system is realized using the following hardware and software.

[0980] Hardware and Software

[0981] 1. User device: smartphone, tablet, or PC

[0982] 2. Server: Cloud server, on-premise server, etc.

[0983] 3. Internet connection: A stable network connection (Wi-Fi, 4G / 5G, etc.)

[0984] 4. Generative AI models: AI models that apply natural language processing technology (e.g., GPT-3)

[0985] Overview of program processing

[0986] 1. Enter user information

[0987] User: A user opens a profile in a mobile or web application and enters their interests, hobbies, and location information. Examples include "movies," "music," and "travel."

[0988] Terminal: The entered information is formatted in JSON format and sent to the server via a secure protocol (e.g., HTTPS).

[0989] 2. Training the generative AI model

[0990] Server: The server receives the JSON data and extracts the user's profile information. The extracted information is fed into a generative AI model (e.g., GPT-3) to learn the user's interests and personality patterns. The learning results are stored in a database along with the user ID.

[0991] 3. Collecting online news

[0992] Server: The server uses an RSS feed reader or a news API (e.g., NewsAPI.org) to collect the latest news articles from the network, organize them into categories, and filter only those relevant to the user's interests.

[0993] 4. Extracting common topics and generating messages

[0994] Server: A generative AI model is used to match the user's profile information with filtered news articles. Common topics are extracted and a conversation-starting message in natural language is generated. For example, a message might be generated that asks, "Have you seen the recently talked-about movie 'Tenet'?"

[0995] 5. Talk suggestions

[0996] Server: The generated message is sent to the user's terminal.

[0997] Device: The device displays the message in a preview format to the user, who can then review the message and decide whether to send it to the other party.

[0998] 6. Conversation analysis and feedback

[0999] Server: The server collects message exchange history between users in real time and analyzes the content of the conversation using a generative AI model. It evaluates user reactions and the level of conversation activity, and generates and provides new topic suggestion messages as needed.

[1000] Specific examples

[1001] For example, consider the case where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters their interests in "movies" and "music" on their profile settings screen, and their device sends this information to the server. The server uses a generative AI model to learn about User A and collect and filter the latest related news articles from the internet. The server extracts reviews of new movies as a common topic between User A and User B, and generates a message asking, "Have you seen the recently talked-about movie 'Tenet'?" This message is sent to User A's device, where User A confirms it and sends it to User B, creating a natural conversation starter.

[1002] Prompt Sentence Examples

[1003] "Please talk about the movie 'Tenet'."

[1004] "Please extract topics that users A and B are both interested in from the latest music news."

[1005] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[1006] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1007] Step 1:

[1008] Enter user information

[1009] User: Open the profile settings screen and enter your interests, hobbies, and location information.

[1010] Input: Movies, music, travel

[1011] Output: This information is entered into the form.

[1012] Terminal: Formats the input information into JSON format and sends it to the server.

[1013] Input: Movies, Music, Travel input fields

[1014] Output: JSON format data {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[1015] Step 2:

[1016] Training generative AI models

[1017] Server: Receives the JSON data and extracts the user's profile information.

[1018] Input: {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[1019] Output: User interest data

[1020] Server: Feeds data to a generative AI model (e.g., GPT-3) to learn patterns of user interests and personality.

[1021] Input: User interest data

[1022] Output: Learning results of user's interest and personality patterns

[1023] Server: The learning results are stored in a database, linked to the user ID.

[1024] Input: Learning results and user ID

[1025] Output: User profile stored in the database

[1026] Step 3:

[1027] Collecting online news

[1028] Server: Collects the latest news articles using the news API.

[1029] Input: News API request

[1030] Output: A list of the latest news articles

[1031] Server: Organizes news articles into categories and filters news relevant to the user's interests.

[1032] Input: A list of recent news articles

[1033] Output: News articles related to the user's interests

[1034] Step 4:

[1035] Extracting common topics and generating messages

[1036] Server: Uses a generative AI model to match user profile information with news articles.

[1037] Input: User interest / personality data, news articles

[1038] Output: Candidates for common topics

[1039] Server: Generates natural conversation starter messages.

[1040] Input: Candidates for common topics

[1041] Output: Generated message: "Have you seen the recent popular movie, Tenet?"

[1042] Step 5:

[1043] Talk suggestions

[1044] Server: Sends the generated message to the user's terminal.

[1045] Input: The generated message

[1046] Output: Sends a message to the user's terminal

[1047] Terminal: Presents the message to the user in a preview format.

[1048] Input: The generated message

[1049] Output: The message presented to the user

[1050] Step 6:

[1051] Conversation analysis and feedback

[1052] Server: Collects message exchange history between users in real time.

[1053] Input: User-to-user messages

[1054] Output: Collected message history

[1055] Server: Analyzes the content of the conversation using a generative AI model.

[1056] Input: Message history

[1057] Output: Analysis results (conversation activity, user responses, etc.)

[1058] Server: Generates new topic suggestion messages as needed and provides them to users.

[1059] Input: Analysis results

[1060] Output: New suggestion message: "Let's talk about recently released music albums."

[1061] This specific processing step promotes smooth conversation between users.

[1062] (Application example 1)

[1063] 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."

[1064] Communication between staff and customers in brick-and-mortar stores is challenging because it is difficult to accurately grasp customers' interests and provide appropriate conversation starters. There is also a need to instantly access the information needed to provide personalized customer service. However, current systems have difficulty meeting these demands.

[1065] 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.

[1066] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting the user in sending messages; an analysis means for collecting a message log and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; and a presentation means for presenting common topics between staff and customers in a physical store using smart glasses or a head-mounted display, thereby enabling smooth communication between staff and customers in a physical store.

[1067] "Input means" refers to a device or interface for inputting user profile information.

[1068] The "transmission means" is a communication means for transmitting the input user profile information to the server.

[1069] A "learning means" is a device or software that uses a generative AI model to learn a user's profile information and analyze the user's interests.

[1070] An "aggregator" is a device or software that gathers current news articles from the Internet and filters them for news relevant to the user's interests.

[1071] The "generation means" is a device or software for extracting common topics between users and generating messages that will serve as conversation starters.

[1072] The "presentation means" is a device or interface that presents the generated message to the user and allows the user to check the message.

[1073] A "receiving means" is a communication means that supports users in sending messages.

[1074] An "analysis means" is a device or software that collects a log of messages and analyzes the progress of a conversation.

[1075] The "suggestion means" is a device or software that suggests new conversation starters based on the analysis results.

[1076] "Smart glasses" are glasses-type devices that visually present information to a user.

[1077] A "head-mounted display" is a head-mounted display device for visually presenting information to a user.

[1078] A "common topic" is a concern or interest shared between users.

[1079] A "brick and mortar store" is a retail or service establishment that has a physical location.

[1080]

[1081] The present invention relates to a system for realizing smooth communication between staff and customers in a brick-and-mortar store. The system utilizes smart glasses or a head-mounted display to present staff with conversation starters based on the customer's interests.

[1082] First, when a user (customer) visits a store, they input their profile information, which includes their interests, concerns, and recent purchase history. This information is sent to the server through an input method. The server then uses a generative AI model to learn the user's profile information and analyze their interests. This learning method is important for gaining a deep understanding of the user's interests.

[1083] The server then collects the latest news articles from the internet using RSS feeds and news APIs, organizes them into categories, and filters news relevant to the user's interests.

[1084] The generative AI model compares user profile information with collected news articles to extract common topics between users. This generation method generates messages to spark conversation. The generated messages are presented to staff via smart glasses or a head-mounted display. This presentation method makes it easier for staff to identify topics that may interest customers.

[1085] The server also includes a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a suggestion means for suggesting new conversation starters based on the analysis results.

[1086] As a concrete example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news. The server extracts reviews of new movies as a common interest of Users A and B. The server then generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to User A. User A then sees this message, allowing the staff member to start a natural conversation with the customer.

[1087] Representative generative AI models include GPT-4 and BERT. News API and Google News API can be used to gather news. MySQL and PostgreSQL can be used as database management systems.

[1088] Examples of specific prompts include:

[1089] "User A's profile:

[1090] Hobbies: Movies, music

[1091] Interests: Latest technology, fashion

[1092] User B's profile:

[1093] Hobbies: Cooking, Traveling

[1094] Interests: Health, Sports

[1095] Please suggest some common topics for these users."

[1096] By providing such prompts, the generative AI model can identify common topics between users A and B and suggest appropriate conversation starters to the wait staff.

[1097] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1098] Step 1:

[1099] Enter user profile information

[1100] When a user visits a store, they input their profile information (interests, concerns, recent purchase history, etc.) using a smartphone or tablet device.

[1101] Input data: User interests, concerns, recent purchase history

[1102] Output data: JSON format of input data

[1103] Step 2:

[1104] Sending input data

[1105] The device formats the profile information entered by the user and sends it to the server over Wi-Fi or mobile data.

[1106] Input data: User profile information (JSON format)

[1107] Output data: Send data to the server

[1108] Step 3:

[1109] Training generative AI models

[1110] The server receives the user's profile information and provides it to the generative AI model for training. The training method uses a generative AI model (e.g., GPT-4, BERT).

[1111] Input data: User profile information

[1112] Output data: Analysis of user interests and personalities

[1113] Step 4:

[1114] News article collection and filtering

[1115] The server uses RSS feeds and news APIs to gather the latest news articles from the internet, organizes them into categories, and filters news relevant to the user's interests.

[1116] Input data: News articles collected from the news API

[1117] Output data: News articles related to the user's interests

[1118] Step 5:

[1119] Extracting common topics and generating messages

[1120] The server uses a generative AI model to match users' profile information with collected news articles, extract common topics between users, and generate messages that spark natural conversations.

[1121] Input data: user profile information, filtered news articles

[1122] Output data: Generated conversation starter message

[1123] Step 6:

[1124] Message presentation

[1125] The server then sends the generated message to the user's device and presents it to the staff via smart glasses or a head-mounted display, allowing the staff to visually confirm topics that may be of interest to the customer.

[1126] Input data: Generated conversation starter messages

[1127] Output data: Visual presentation of the message

[1128] Step 7:

[1129] Monitoring and analyzing conversation progress

[1130] The server collects messages sent and received between users and monitors the progress of the conversation. It uses a generative AI model to analyze the content of the conversation and evaluates the user's reactions and the level of conversation activity.

[1131] Input data: Message exchange history between users

[1132] Output data: Conversation analysis results and evaluation

[1133] Step 8:

[1134] Propose new conversation starters

[1135] The server proposes new conversation starters based on the analysis results, and the suggestion means generates new messages for the user, which are then presented again.

[1136] Input data: Conversation analysis results and evaluation

[1137] Output: New conversation starter message

[1138] 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.

[1139] The present invention relates to a system for providing natural conversation starters between users, and in particular, a specific embodiment will be described in which a combination of emotion engines is used to recognize user emotions and support more appropriate communication.

[1140] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning about user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet, a generation means for extracting common topics and generating conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, a suggestion means for proposing new conversation starters based on the analysis results, and an emotion engine for recognizing user emotions using an emotion engine and a function for generating appropriate conversation messages based on the recognition.

[1141] Overview of program processing

[1142] 1. Enter user information

[1143] User: Open the profile settings screen and enter your hobbies, interests, location, and self-introduction.

[1144] Terminal: Formats the information entered and sends it to the server.

[1145] 2. Training the generative AI model

[1146] Server: Receives the submitted profile information and provides it to the generative AI model for learning.

[1147] Server: Analyzes the user's interests and personality and stores the learning results of the generative AI model.

[1148] 3. Collecting online news

[1149] Server: Periodically collects the latest news articles from the Internet and organizes them into categories.

[1150] Server: The news articles are then filtered to match the user's interests.

[1151] 4. Extracting common topics and generating messages

[1152] Server: Uses a generative AI model to match user profile information with collected news articles.

[1153] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[1154] Server: For example, create a message like, "Have you seen the recently talked about movie, Tenet?"

[1155] 5. Talk suggestions

[1156] Server: Sends the generated message to the user's terminal.

[1157] Terminal: Presents the message to the user in a preview format, allowing the user to review it and decide whether to send it.

[1158] User: Starts a conversation by sending a message.

[1159] 6. Conversation analysis and feedback

[1160] Server: Collects the history of messages sent and received between users and stores it in a database.

[1161] Server: Uses a generative AI model to analyze collected message content and evaluate user responses and conversation progress.

[1162] Server: If the conversation stalls or progress is not being made, it generates new topics and messages and suggests them to the user.

[1163] 7. Incorporating an Emotional Engine

[1164] Server: Uses an emotion engine to recognize emotions from messages and user behavior, for example, inferring a user's emotional state from the tone and frequency of their text messages.

[1165] Server: Adjusts conversation starters based on the recognized emotions. For example, if the user shows anger or sadness, it generates a calm message that takes that emotion into account.

[1166] Server: Suggested messages based on emotions are tailored to be emotionally appropriate using natural language generation technology.

[1167] Specific examples

[1168] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends this information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news.

[1169] Next, the server uses an emotion engine to recognize emotions from User A's messages and behavior. For example, if User A wrote "I've been very tired recently" in a past message, the emotion engine determines that User A is currently "tired." Based on this, the server generates a calm message related to a common interest.

[1170] The server generates a message in the form of "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and presents it to User A. User A checks this message and sends it to User B, creating a natural conversation starter. By taking into account the user's emotions, this system provides a more personalized experience.

[1171] This makes it easier for users to maintain a natural conversation flow that reflects their emotions, and allows for smooth communication with people they meet for the first time.

[1172] The processing flow will be explained below.

[1173] Step 1: Enter your information

[1174] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[1175] Terminal: Formats the information entered and sends it to the server.

[1176] Step 2: Training the generative AI model

[1177] Server: Receives the transmitted user profile information.

[1178] Server: Provides the generative AI model with user profile information, which allows the model to learn about interests and personality.

[1179] Server: Stores the learning results of the generative AI model in a database.

[1180] Step 3: Collecting online news

[1181] Server: Uses RSS feeds and news APIs to periodically gather the latest news articles from the internet.

[1182] Server: Organizes collected news articles by category and records metadata of news articles.

[1183] Step 4: Extracting common topics and generating messages

[1184] Server: Uses a generative AI model to match user profile information with collected news articles.

[1185] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[1186] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[1187] Step 5: Incorporating the Emotion Engine

[1188] Server: Using the emotion engine, analyzes the user's messages and behavioral data to recognize their current emotional state. For example, it determines whether the user is expressing emotions such as "tiredness" or "joy" based on the content and frequency of text messages.

[1189] Server: Adjusts the generated messages based on the user's perceived emotions. For example, if the user feels "tired," it suggests emotionally appropriate topics such as "relaxing movies."

[1190] Step 6: Propose a talk

[1191] Server: Sends the coordinated conversation message to the user's terminal.

[1192] Terminal: The generated message is presented to the user in a preview format, allowing the user to review it and decide whether it is appropriate.

[1193] User: Review the message and send it to whomever they deem appropriate.

[1194] Step 7: Collect conversation progress

[1195] Server: Collects the history of messages sent and received between users and stores it in a database.

[1196] Server: Analyzes collected message content using a generative AI model to evaluate user responses and conversation progress.

[1197] Step 8: Suggest new conversation starters

[1198] Server: Using the emotion engine, it reconfirms the user's current emotional state and generates new topics and messages as needed. For example, if the user has a positive emotion towards the conversation, it suggests further interesting topics.

[1199] Server: Maintains smooth communication by sending newly generated messages to the user's device.

[1200] This helps maintain a natural conversation flow between users and helps ensure smooth communication with people meeting for the first time.

[1201] Example 2

[1202] 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."

[1203] In today's world, it is difficult for users to naturally start a conversation, and it is often difficult for them to communicate their feelings, especially when they meet for the first time. Furthermore, conventional communication support systems have difficulty recognizing users' emotions and suggesting appropriate ways to start a conversation. This leads to unnatural communication between users, making it difficult to build relationships.

[1204] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1205] In this invention, the server includes an input means for inputting user profile information, a transmission means for transmitting the input user profile information to the server, and a learning means for learning the user profile information and analyzing the user's interests using a generative AI model, thereby enabling the server to recognize the user's emotions using an emotion engine and generate appropriate conversational messages.

[1206] "Input means" refers to an interface through which a user inputs their profile information.

[1207] "Transmission means" refers to the function of converting the entered profile information into an appropriate format and transmitting it to the server.

[1208] "Learning means" refers to the function that uses a generative AI model to analyze a user's profile information and learn about the user's interests and personality.

[1209] "Gathering means" refers to the function of collecting the latest news articles from the Internet, organizing them into categories, and filtering news related to the user's interests.

[1210] "Generation means" refers to a function that extracts common topics between users and generates messages that will serve as a starting point for natural conversation.

[1211] The "presentation means" refers to a function that presents the generated message to the user so that the user can confirm the message.

[1212] "Receiving means" refers to a function that supports users in sending messages.

[1213] "Analysis means" refers to the function of collecting message logs and analyzing the progress of the conversation and the user's reactions.

[1214] "Suggestion means" refers to a function that suggests new conversation starters to the user based on the analysis results.

[1215] "Emotion recognition means" refers to a function that uses an emotion engine to recognize a user's emotion and generates an appropriate conversational message based on that emotion.

[1216] The present invention is a system for providing natural conversation starters between users, and in particular, by combining an emotion engine, it recognizes user emotions and supports more appropriate communication. This system provides a terminal with an input means for users to input profile information, and includes a transmission means for transmitting the input information to a server. The server also has a learning means for learning the user's profile information using a generative AI model and analyzing the user's interests based on the results.

[1217] Next, the server has a collection means for collecting the latest news articles from the Internet and uses a specific algorithm to filter out news relevant to the user's interests.The server then extracts common topics based on this information and generates messages that serve as natural conversation starters.Natural language generation technology is used to generate these messages.The generated messages are displayed to the user via a presentation means provided on the terminal.The user can review these messages and send them as needed.

[1218] The server also has an analysis means for collecting messages sent and received between users and analyzing the progress of the conversation based on the collected messages. The server also includes a suggestion means for suggesting new conversation starters to users based on the results of this analysis. The server also has an emotion recognition means that uses an emotion engine to analyze the user's emotions and adjust conversation messages according to the emotions.

[1219] As a specific example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests on a profile setting screen, and the information is sent from the device to the server. The server uses a generative AI model to learn User A's profile information, while simultaneously collecting relevant and recent news articles and identifying articles related to User A's interests.

[1220] The server then uses the emotion engine to recognize User A's emotions. For example, if User A writes, "I've been feeling very tired lately," the emotion engine determines User A's current emotional state as "tired." Based on this, the server generates a calm message related to a common interest. The generated message might be, "Do you think you can enjoy the movie 'Tenet,' which is currently a hot topic, while relaxing?" and presents it to User A. User A can then review this message and send it to User B, sparking a natural conversation.

[1221] A specific example of a prompt sentence could be, "User A is interested in movies and music and has been feeling tired lately. Please generate a message that will provide a common topic." Based on this prompt sentence, the system can suggest appropriate conversation starters.

[1222] The hardware used includes the user's smartphone or PC (device) and a cloud server. The software includes a profile input UI, a transmission server, a generative AI model library (e.g., GPT-3), and a sentiment analysis engine (e.g., a natural language processing engine). This system enables users to start natural conversations and communicate in a way that takes emotions into consideration.

[1223] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1224] Step 1:

[1225] Enter user information

[1226] User: The user opens the profile setting screen and enters their hobbies, interests, location information, and self-introduction. The entered data is stored in text format on the device.

[1227] Terminal: The terminal converts the profile information entered by the user into a specified format (e.g., JSON). The formatted data is sent to the server using the HTTPS protocol.

[1228] Input: Raw data entered by the user (hobbies, interests, location, bio).

[1229] Output: Formatted data (JSON format).

[1230] Step 2:

[1231] Training generative AI models

[1232] Server: The server takes the received profile information as an input dataset for the generative AI model. The dataset includes feature data such as the user's hobbies and interests.

[1233] Server: Extracts feature data and analyzes user interests. A generative AI model (e.g., GPT-3) is used to learn information related to the user's interests. Natural language processing (NLP) techniques are used in this process.

[1234] Server: The user model (profile of interests and personality) generated as a result of learning is stored in a database.

[1235] Input: Formatted profile data (JSON format).

[1236] Output: Learned user model (stored in database).

[1237] Step 3:

[1238] Collecting online news

[1239] Server: The server periodically collects the latest news articles from the Internet using RSS feeds and web scraping technology. The data collected includes information such as article titles, content, and categories.

[1240] Server: Organizes collected news articles by category and performs preprocessing (e.g., noise removal, text normalization).

[1241] Server: Using a filtering algorithm, extract only articles that are highly relevant to the user's interests.

[1242] Input: Raw news data collected from the internet.

[1243] Output: Organized news article data by category.

[1244] Step 4:

[1245] Extracting common topics and generating messages

[1246] Server: Uses a generative AI model to match user profile information with collected news articles, using a similarity calculation algorithm (e.g., cosine similarity) in the process.

[1247] Server: Combines highly similar news articles with user interests to extract common topics.

[1248] Server: Uses natural language generation technology to generate messages that spark conversations between users.

[1249] Input: Organized news article data, user profile information.

[1250] Output: The generated conversation starter message.

[1251] Step 5:

[1252] Talk suggestions

[1253] Server: Sends the generated message to the user's terminal.

[1254] Terminal: Updates the UI to present received messages to the user in a preview format.

[1255] User: Check the message presented and, if necessary, press the send button to send the message to the other user.

[1256] Input: The generated conversation message.

[1257] Output: Messages confirmed by users or sent.

[1258] Step 6:

[1259] Conversation analysis and feedback

[1260] Server: Collects logs of messages sent and received between users and stores them in a database.

[1261] Server: Analyzes the collected message content using a generative AI model to evaluate the progress of the conversation and user responses. This analysis uses text mining techniques.

[1262] Server: If the conversation is stagnating or if the user is not responding well, generate new topics and messages and suggest them to the user again.

[1263] Input: A log of messages sent and received.

[1264] Output: Analysis results, newly generated conversation starter messages.

[1265] Step 7:

[1266] Incorporating an emotion engine

[1267] Server: Uses an emotion engine (e.g., a natural language processing engine) to recognize emotions from users' messages and behaviors. Infers emotional states by analyzing the tone and frequency of text messages.

[1268] Server: Based on the recognized emotion data, the server fine-tunes the conversation starter message. For example, if the user is judged to be "tired," it generates a gentle message such as, "Do you think you can enjoy the popular movie "Tenet" while relaxing?"

[1269] Server: Emotionally tailored messages are made emotionally appropriate using natural language generation techniques.

[1270] Input: The user's message data.

[1271] Output: Tailored messages generated based on sentiment.

[1272] (Application example 2)

[1273] 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."

[1274] In recent years, communication with customers in brick-and-mortar stores has become increasingly important. However, it is difficult to smoothly advance natural conversations between store clerks and customers, and it is particularly challenging to provide appropriate topics of conversation for customers meeting for the first time. It is also difficult to instantly grasp the customer's emotional state and respond appropriately to the situation. Furthermore, there is a need to suggest new topics of conversation when the conversation stalls or when progress is not being made.

[1275] 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.

[1276] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting users in sending messages; an analysis means for collecting message logs and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; an emotion recognition means for recognizing the user's emotions using an emotion engine and generating conversation messages based on the recognized emotions; and a conversation support means for a store clerk wearing smart glasses in a physical store to support natural conversations with users. This enables smooth natural conversations with customers and enables responses according to the customer's emotional state.

[1277] "Input means" refers to a device or system for collecting user profile information.

[1278] The "transmission means" is a device or system that transmits the input user profile information to the server.

[1279] A "learning means" is a device or system that uses a generative AI model to learn user profile information and analyze user interests.

[1280] An "aggregator" is a device or system that collects the latest news articles from the Internet and filters them to those relevant to the user's interests.

[1281] The "generation means" is a device or system that extracts common topics between users and generates messages that serve as conversation starters.

[1282] The "presentation means" is a device or system that presents the generated message to the user and allows the user to check the message.

[1283] A "receiving means" is a device or system that supports users in sending messages.

[1284] The "analysis means" is a device or system that collects message logs and analyzes the progress of the conversation.

[1285] A "suggestion means" is a device or system that suggests new conversation starters based on the analysis results.

[1286] The "emotion recognition means" is a device or system that uses an emotion engine to recognize a user's emotion and generates a conversational message based on the recognized emotion.

[1287] A "conversation support means" is a device or system that supports natural conversation between a store clerk wearing smart glasses and a user in a physical store.

[1288] MODE FOR CARRYING OUT THE INVENTION

[1289] The present invention provides a system for supporting natural conversations with customers in a physical store. The system includes a series of means for inputting, transmitting, and learning user profile information. Specific embodiments of the system are described below.

[1290] System Overview

[1291] The system consists of an input means for inputting user profile information, a transmission means for sending the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting and filtering the latest news articles from the Internet, a generation means for extracting common topics between users and generating messages, a presentation means for presenting the generated messages, a reception means for supporting the sending and receiving of messages, an analysis means for analyzing the progress of the conversation, a suggestion means for proposing new topics based on the analysis results, and an emotion recognition means for recognizing user emotions using an emotion engine.It also includes a conversation support means in which store clerks wearing smart glasses support natural conversations with customers in physical stores.

[1292] What the program does

[1293] Enter and submit user information

[1294] Users enter their profile information through smart glasses worn by a store clerk in a brick-and-mortar store, such as their hobbies, interests, and current mood. This information is formatted and sent to a server via the smart glasses.

[1295] Learning and analysis with generative AI models

[1296] The server provides the received user profile information to the generative AI model for learning. The generative AI model analyzes the user's interests and personality and stores the results. This allows it to provide optimal conversation starters to customers.

[1297] News article collection and filtering

[1298] The server periodically collects the latest news articles from the Internet, organizes them into categories, and filters only those relevant to the user's interests, making it easier for customers to find topics of interest.

[1299] Conversation starter generation and presentation

[1300] The server uses a generative AI model to match the user's profile information with collected news articles to extract common topics. Based on the extracted topics, it generates messages that serve as natural conversation starters. The generated messages are displayed on the smart glasses to help store associates start conversations with customers.

[1301] Sending and receiving messages and analyzing progress

[1302] When a user sends a message, the history is stored on the server. The server analyzes the collected message logs and evaluates the progress of the conversation. Based on this evaluation, if the conversation has stalled or is not progressing, it will suggest a new topic.

[1303] Emotion recognition and conversation regulation

[1304] The server uses an emotion engine to recognize the user's emotions. It estimates the user's emotional state from the user's facial expressions and message tone, and adjusts the conversation message accordingly. For example, if the user is feeling "tired," a gentle message that takes that emotion into account is generated.

[1305] Specific examples

[1306] For example, if User A is interested in "movies" and "music" and is currently feeling "tired," the server will use a generative AI model based on User A's profile information to learn from it. The server will then collect the latest movie-related news articles from the Internet and extract topics suitable for User A, who is feeling "tired." The smart glasses will display a message saying, "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and the store clerk will use this message to help naturally start a conversation with User A.

[1307] Prompt Sentence Examples

[1308] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[1309] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1310] Step 1:

[1311] The user inputs profile information. The user inputs information such as hobbies, interests, and current mood through the interface of the smart glasses. The input information is formatted to be sent from the smart glasses to the server. The input data is the user's profile information, and the output data is the formatted profile information.

[1312] Step 2:

[1313] The server receives the transmitted profile information. The server receives the transmitted profile information from the smart glasses and stores it in a database. The input data is the formatted profile information, and the output data is the stored profile information.

[1314] Step 3:

[1315] The server uses the generative AI model to learn the user's profile information and analyze their interests and personality. The server trains the generative AI model based on the input profile information to identify the user's interests and personality. The input data is the profile information, and the output data is the analysis of the user's interests and personality.

[1316] Step 4:

[1317] The server collects the latest news articles from the Internet and organizes them by category. The server periodically scrapes the news articles, filters them by category, and stores them in a database. The input data are news articles from the Internet, and the output data are categorized news articles.

[1318] Step 5:

[1319] The collected news articles are filtered by relating them to the user's interests. The server selects relevant news articles based on the user's interests obtained from the generative AI model. The input data are categorized news articles and the user's interests, and the output data are filtered related news articles.

[1320] Step 6:

[1321] The server extracts common topics and generates messages that can spark conversation. The server matches the filtered news articles with the user's profile information to find common topics. It then uses a generative AI model to generate messages that can spark natural conversation. The input data are the filtered news articles and profile information, and the output data are the generated messages.

[1322] Step 7:

[1323] The server sends the generated message to the smart glasses and presents it to the user. The smart glasses display the received message for the user to review. The input data is the generated message, and the output data is the displayed message.

[1324] Step 8:

[1325] The user starts a conversation based on the message and sends and receives messages. The store clerk wearing smart glasses starts a conversation with the customer based on the displayed message. The message sent by the user is sent to the server and saved as a log. The input data is the sent message, and the output data is the saved message log.

[1326] Step 9:

[1327] The server collects message logs and analyzes the progress of the conversation. The server analyzes the collected message logs and identifies when the conversation has been interrupted or when progress is not being made. The input data is the message logs, and the output data is the progress analysis result.

[1328] Step 10:

[1329] The server proposes new topics based on the analysis results. The server then uses a generative AI model based on the results of the previous analysis to generate new conversation starters and sends them to the smart glasses. The input data is the analysis results, and the output data is the newly generated message.

[1330] Step 11:

[1331] The server recognizes the user's emotions using an emotion engine and adjusts the conversation message based on the recognized emotions. The server estimates the user's emotional state from the user's facial expression and message tone, generates an appropriate message, and displays it on the smart glasses. The input data is the user's facial expression and message tone, and the output data is the adjusted message.

[1332] Prompt Sentence Examples

[1333] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] [Fourth embodiment]

[1338] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1339] 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.

[1340] 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).

[1341] 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.

[1342] 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.

[1343] 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).

[1344] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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."

[1351] The present invention relates to a system for providing an opportunity for smooth conversation between users, and specific embodiments thereof will be described below.

[1352] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet and filtering them according to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a proposal means for proposing new conversation starters based on the analysis results.

[1353] Overview of program processing

[1354] 1. Enter user information

[1355] User: Open the profile settings screen and enter your hobbies, interests, and location information.

[1356] Terminal: Formats the information entered and sends it to the server.

[1357] 2. Training the generative AI model

[1358] Server: Receives the submitted user profile information and provides it to the generative AI model for learning.

[1359] Server: Deeply analyzes user interests and personalities and stores this information.

[1360] 3. Collecting online news

[1361] Server: Uses RSS feeds and news APIs to gather the latest news articles from the internet.

[1362] Server: Organizes collected news into categories and filters news relevant to the user's interests.

[1363] 4. Extracting common topics and generating messages

[1364] Server: Uses a generative AI model to match user profile content with collected news articles.

[1365] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[1366] 5. Talk suggestions

[1367] Server: Sends the generated message to the user's terminal.

[1368] Terminal: Presents the generated message to the user in a preview format.

[1369] User: Checks the message presented and decides whether to send it to the recipient.

[1370] 6. Conversation analysis and feedback

[1371] Server: Collects the history of messages sent and received between users and monitors the progress of the conversation.

[1372] Server: Analyzes the content of the conversation using a generative AI model and evaluates the user's reaction and the level of conversation activity.

[1373] Server: Generates new topics and messages as needed and suggests them to users.

[1374] Specific examples

[1375] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest relevant online news.

[1376] The server extracts reviews of new movies as a common interest of users A and B. Next, the server generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to user A. User A checks this message and sends it to user B, creating a natural conversation starter.

[1377] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[1378] The processing flow will be explained below.

[1379] Step 1: Enter your information

[1380] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[1381] Terminal: Formats the information entered and sends it to the server.

[1382] Step 2: Training the generative AI model

[1383] Server: Receives profile information sent by users.

[1384] Server: Provides the generative AI model with user profile information, which allows the model to learn about the user's interests and personality.

[1385] Server: Stores the learning results of the generative AI model in a database.

[1386] Step 3: Collecting online news

[1387] Server: Periodically gathers the latest news articles from the internet, using RSS feeds and news APIs.

[1388] Server: Organizes news articles into categories and records metadata for each news article.

[1389] Step 4: Extracting common topics and generating messages

[1390] Server: Uses a generative AI model to match user profile information with collected news articles.

[1391] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[1392] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[1393] Step 5: Propose a talk

[1394] Server: Sends the generated conversation message to the user's terminal.

[1395] Terminal: Presents the generated message to the user in a preview format, allowing the user to review the message and decide whether to send it or not.

[1396] User: Edits the suggested message as needed and sends it to whomever they deem appropriate.

[1397] Step 6: Analysis and feedback of the conversation

[1398] Server: Collects the history of messages sent and received between users and stores it in a database.

[1399] Server: Using a generative AI model, the server analyzes the collected messages and evaluates the progress of the conversation based on factors such as user responses and message frequency.

[1400] Server: If the conversation dies or progress is not being made, the server generates new topics and messages and presents them to the user. For example, it generates new messages based on news articles related to a different topic of interest.

[1401] This makes it easier for users to maintain a natural conversation flow and helps ensure smooth communication with people they meet for the first time.

[1402] Example 1

[1403] 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."

[1404] In modern society, facilitating communication between users is an important issue. In particular, it is difficult to find an opportunity to naturally start a conversation between users with different hobbies and interests. Furthermore, insufficient topic suggestions based on users' interests have led to problems with conversations not continuing. A means to solve these problems is needed.

[1405] 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.

[1406] In this invention, the server includes an input means for inputting user data, a transmission means for transmitting the input user data to the server, a learning means for learning the user data using a generative AI model and analyzing the user's interests, a collection means for collecting the latest information from the network and filtering information related to the user's interests, a generation means for extracting common topics between users and generating messages that can serve as conversation starters, a presentation means for presenting the generated messages to the users and allowing the users to confirm the messages, a communication means for supporting the users in sending messages, an analysis means for collecting message logs and analyzing the progress of the conversation, and a suggestion means for suggesting new conversation starters based on the analysis results. This allows for smooth conversation starters to be provided between users, facilitating communication.

[1407] "User data" refers to personal information entered by the user, such as interests, hobbies, and location information.

[1408] "Input means" refers to an interface or device through which a user inputs data, specifically the settings screen of a mobile app or web application.

[1409] "Transmission means" refers to the function or protocol for transmitting input data to a server. For example, it includes secure communication methods such as HTTPS.

[1410] A "generative AI model" is an artificial intelligence algorithm that learns from user data and analyzes their interests and concerns, specifically a model that uses natural language processing technology.

[1411] A "learning method" is a method or process for using a generative AI model to analyze user data and identify user interests and concerns.

[1412] "Gathering methods" are methods and tools that obtain the latest information from the network and filter it according to the user's interests. Examples include RSS feed readers and news APIs.

[1413] The "generation means" refers to a method or function for extracting common topics between users and generating messages that will spark natural conversation.

[1414] "Presentation means" refers to the method or interface for displaying the generated message to the user and allowing them to check it. Examples include push notifications and in-app notification functions.

[1415] "Communication means" refers to the method or technology used by a user to send messages to others. Specifically, this applies to chat apps and messaging services.

[1416] "Analysis tools" are methods and algorithms for collecting logs of messages sent and received between users and assessing the progress of the conversation.

[1417] The "suggestion means" is a method or system for generating a message that can serve as a starting point for a new conversation based on the analysis results and presenting it to the user.

[1418] The present invention relates to a system for providing a smooth conversation starter between users, and a specific embodiment thereof will be described below. This system is realized using the following hardware and software.

[1419] Hardware and Software

[1420] 1. User device: smartphone, tablet, or PC

[1421] 2. Server: Cloud server, on-premise server, etc.

[1422] 3. Internet connection: A stable network connection (Wi-Fi, 4G / 5G, etc.)

[1423] 4. Generative AI models: AI models that apply natural language processing technology (e.g., GPT-3)

[1424] Overview of program processing

[1425] 1. Enter user information

[1426] User: A user opens a profile in a mobile or web application and enters their interests, hobbies, and location information. Examples include "movies," "music," and "travel."

[1427] Terminal: The entered information is formatted in JSON format and sent to the server via a secure protocol (e.g., HTTPS).

[1428] 2. Training the generative AI model

[1429] Server: The server receives the JSON data and extracts the user's profile information. The extracted information is fed into a generative AI model (e.g., GPT-3) to learn the user's interests and personality patterns. The learning results are stored in a database along with the user ID.

[1430] 3. Collecting online news

[1431] Server: The server uses an RSS feed reader or a news API (e.g., NewsAPI.org) to collect the latest news articles from the network, organize them into categories, and filter only those relevant to the user's interests.

[1432] 4. Extracting common topics and generating messages

[1433] Server: A generative AI model is used to match the user's profile information with filtered news articles. Common topics are extracted and a conversation-starting message in natural language is generated. For example, a message might be generated that asks, "Have you seen the recently talked-about movie 'Tenet'?"

[1434] 5. Talk suggestions

[1435] Server: The generated message is sent to the user's terminal.

[1436] Device: The device displays the message in a preview format to the user, who can then review the message and decide whether to send it to the other party.

[1437] 6. Conversation analysis and feedback

[1438] Server: The server collects message exchange history between users in real time and analyzes the content of the conversation using a generative AI model. It evaluates user reactions and the level of conversation activity, and generates and provides new topic suggestion messages as needed.

[1439] Specific examples

[1440] For example, consider the case where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters their interests in "movies" and "music" on their profile settings screen, and their device sends this information to the server. The server uses a generative AI model to learn about User A and collect and filter the latest related news articles from the internet. The server extracts reviews of new movies as a common topic between User A and User B, and generates a message asking, "Have you seen the recently talked-about movie 'Tenet'?" This message is sent to User A's device, where User A confirms it and sends it to User B, creating a natural conversation starter.

[1441] Prompt Sentence Examples

[1442] "Please talk about the movie 'Tenet'."

[1443] "Please extract topics that users A and B are both interested in from the latest music news."

[1444] The use of this system promotes smooth communication between users and supports the development of romantic relationships.

[1445] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1446] Step 1:

[1447] Enter user information

[1448] User: Open the profile settings screen and enter your interests, hobbies, and location information.

[1449] Input: Movies, music, travel

[1450] Output: This information is entered into the form.

[1451] Terminal: Formats the input information into JSON format and sends it to the server.

[1452] Input: Movies, Music, Travel input fields

[1453] Output: JSON format data {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[1454] Step 2:

[1455] Training generative AI models

[1456] Server: Receives the JSON data and extracts the user's profile information.

[1457] Input: {"interest": ["movies", "music", "travel"], "location": "Tokyo"}

[1458] Output: User interest data

[1459] Server: Feeds data to a generative AI model (e.g., GPT-3) to learn patterns of user interests and personality.

[1460] Input: User interest data

[1461] Output: Learning results of user's interest and personality patterns

[1462] Server: The learning results are stored in a database, linked to the user ID.

[1463] Input: Learning results and user ID

[1464] Output: User profile stored in the database

[1465] Step 3:

[1466] Collecting online news

[1467] Server: Collects the latest news articles using the news API.

[1468] Input: News API request

[1469] Output: A list of the latest news articles

[1470] Server: Organizes news articles into categories and filters news relevant to the user's interests.

[1471] Input: A list of recent news articles

[1472] Output: News articles related to the user's interests

[1473] Step 4:

[1474] Extracting common topics and generating messages

[1475] Server: Uses a generative AI model to match user profile information with news articles.

[1476] Input: User interest / personality data, news articles

[1477] Output: Candidates for common topics

[1478] Server: Generates natural conversation starter messages.

[1479] Input: Candidates for common topics

[1480] Output: Generated message: "Have you seen the recent popular movie, Tenet?"

[1481] Step 5:

[1482] Talk suggestions

[1483] Server: Sends the generated message to the user's terminal.

[1484] Input: The generated message

[1485] Output: Sends a message to the user's terminal

[1486] Terminal: Presents the message to the user in a preview format.

[1487] Input: The generated message

[1488] Output: The message presented to the user

[1489] Step 6:

[1490] Conversation analysis and feedback

[1491] Server: Collects message exchange history between users in real time.

[1492] Input: User-to-user messages

[1493] Output: Collected message history

[1494] Server: Analyzes the content of the conversation using a generative AI model.

[1495] Input: Message history

[1496] Output: Analysis results (conversation activity, user responses, etc.)

[1497] Server: Generates new topic suggestion messages as needed and provides them to users.

[1498] Input: Analysis results

[1499] Output: New suggestion message: "Let's talk about recently released music albums."

[1500] This specific processing step promotes smooth conversation between users.

[1501] (Application example 1)

[1502] 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."

[1503] Communication between staff and customers in brick-and-mortar stores is challenging because it is difficult to accurately grasp customers' interests and provide appropriate conversation starters. There is also a need to instantly access the information needed to provide personalized customer service. However, current systems have difficulty meeting these demands.

[1504] 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.

[1505] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting the user in sending messages; an analysis means for collecting a message log and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; and a presentation means for presenting common topics between staff and customers in a physical store using smart glasses or a head-mounted display, thereby enabling smooth communication between staff and customers in a physical store.

[1506] "Input means" refers to a device or interface for inputting user profile information.

[1507] The "transmission means" is a communication means for transmitting the input user profile information to the server.

[1508] A "learning means" is a device or software that uses a generative AI model to learn a user's profile information and analyze the user's interests.

[1509] An "aggregator" is a device or software that gathers current news articles from the Internet and filters them for news relevant to the user's interests.

[1510] The "generation means" is a device or software for extracting common topics between users and generating messages that will serve as conversation starters.

[1511] The "presentation means" is a device or interface that presents the generated message to the user and allows the user to check the message.

[1512] A "receiving means" is a communication means that supports users in sending messages.

[1513] An "analysis means" is a device or software that collects a log of messages and analyzes the progress of a conversation.

[1514] The "suggestion means" is a device or software that suggests new conversation starters based on the analysis results.

[1515] "Smart glasses" are glasses-type devices that visually present information to a user.

[1516] A "head-mounted display" is a head-mounted display device for visually presenting information to a user.

[1517] A "common topic" is a concern or interest shared between users.

[1518] A "brick and mortar store" is a retail or service establishment that has a physical location.

[1519]

[1520] The present invention relates to a system for realizing smooth communication between staff and customers in a brick-and-mortar store. The system utilizes smart glasses or a head-mounted display to present staff with conversation starters based on the customer's interests.

[1521] First, when a user (customer) visits a store, they input their profile information, which includes their interests, concerns, and recent purchase history. This information is sent to the server through an input method. The server then uses a generative AI model to learn the user's profile information and analyze their interests. This learning method is important for gaining a deep understanding of the user's interests.

[1522] The server then collects the latest news articles from the internet using RSS feeds and news APIs, organizes them into categories, and filters news relevant to the user's interests.

[1523] The generative AI model compares user profile information with collected news articles to extract common topics between users. This generation method generates messages to spark conversation. The generated messages are presented to staff via smart glasses or a head-mounted display. This presentation method makes it easier for staff to identify topics that may interest customers.

[1524] The server also includes a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, and a suggestion means for suggesting new conversation starters based on the analysis results.

[1525] As a concrete example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests in their profile settings, and their device sends the information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news. The server extracts reviews of new movies as a common interest of Users A and B. The server then generates a message saying, "Have you seen the recently talked-about movie 'Tenet'?" and presents it to User A. User A then sees this message, allowing the staff member to start a natural conversation with the customer.

[1526] Representative generative AI models include GPT-4 and BERT. News API and Google News API can be used to gather news. MySQL and PostgreSQL can be used as database management systems.

[1527] Examples of specific prompts include:

[1528] "User A's profile:

[1529] Hobbies: Movies, music

[1530] Interests: Latest technology, fashion

[1531] User B's profile:

[1532] Hobbies: Cooking, Traveling

[1533] Interests: Health, Sports

[1534] Please suggest some common topics for these users."

[1535] By providing such prompts, the generative AI model can identify common topics between users A and B and suggest appropriate conversation starters to the wait staff.

[1536] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1537] Step 1:

[1538] Enter user profile information

[1539] When a user visits a store, they input their profile information (interests, concerns, recent purchase history, etc.) using a smartphone or tablet device.

[1540] Input data: User interests, concerns, recent purchase history

[1541] Output data: JSON format of input data

[1542] Step 2:

[1543] Sending input data

[1544] The device formats the profile information entered by the user and sends it to the server over Wi-Fi or mobile data.

[1545] Input data: User profile information (JSON format)

[1546] Output data: Send data to the server

[1547] Step 3:

[1548] Training generative AI models

[1549] The server receives the user's profile information and provides it to the generative AI model for training. The training method uses a generative AI model (e.g., GPT-4, BERT).

[1550] Input data: User profile information

[1551] Output data: Analysis of user interests and personalities

[1552] Step 4:

[1553] News article collection and filtering

[1554] The server uses RSS feeds and news APIs to gather the latest news articles from the internet, organizes them into categories, and filters news relevant to the user's interests.

[1555] Input data: News articles collected from the news API

[1556] Output data: News articles related to the user's interests

[1557] Step 5:

[1558] Extracting common topics and generating messages

[1559] The server uses a generative AI model to match users' profile information with collected news articles, extract common topics between users, and generate messages that spark natural conversations.

[1560] Input data: user profile information, filtered news articles

[1561] Output data: Generated conversation starter message

[1562] Step 6:

[1563] Message presentation

[1564] The server then sends the generated message to the user's device and presents it to the staff via smart glasses or a head-mounted display, allowing the staff to visually confirm topics that may be of interest to the customer.

[1565] Input data: Generated conversation starter messages

[1566] Output data: Visual presentation of the message

[1567] Step 7:

[1568] Monitoring and analyzing conversation progress

[1569] The server collects messages sent and received between users and monitors the progress of the conversation. It uses a generative AI model to analyze the content of the conversation and evaluates the user's reactions and the level of conversation activity.

[1570] Input data: Message exchange history between users

[1571] Output data: Conversation analysis results and evaluation

[1572] Step 8:

[1573] Propose new conversation starters

[1574] The server proposes new conversation starters based on the analysis results, and the suggestion means generates new messages for the user, which are then presented again.

[1575] Input data: Conversation analysis results and evaluation

[1576] Output: New conversation starter message

[1577] 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.

[1578] The present invention relates to a system for providing natural conversation starters between users, and in particular, a specific embodiment will be described in which a combination of emotion engines is used to recognize user emotions and support more appropriate communication.

[1579] This system includes an input means for inputting user profile information, a transmission means for transmitting the input information to a server, a learning means for learning about user interests using a generative AI model, a collection means for collecting the latest news articles from the Internet, a generation means for extracting common topics and generating conversation starters, a presentation means for presenting the generated messages to users, a receiving means for supporting users in sending messages, an analysis means for collecting message logs and analyzing the progress of conversations, a suggestion means for proposing new conversation starters based on the analysis results, and an emotion engine for recognizing user emotions using an emotion engine and a function for generating appropriate conversation messages based on the recognition.

[1580] Overview of program processing

[1581] 1. Enter user information

[1582] User: Open the profile settings screen and enter your hobbies, interests, location, and self-introduction.

[1583] Terminal: Formats the information entered and sends it to the server.

[1584] 2. Training the generative AI model

[1585] Server: Receives the submitted profile information and provides it to the generative AI model for learning.

[1586] Server: Analyzes the user's interests and personality and stores the learning results of the generative AI model.

[1587] 3. Collecting online news

[1588] Server: Periodically collects the latest news articles from the Internet and organizes them into categories.

[1589] Server: The news articles are then filtered to match the user's interests.

[1590] 4. Extracting common topics and generating messages

[1591] Server: Uses a generative AI model to match user profile information with collected news articles.

[1592] Server: Extracts common topics between users and generates messages that will spark natural conversation.

[1593] Server: For example, create a message like, "Have you seen the recently talked about movie, Tenet?"

[1594] 5. Talk suggestions

[1595] Server: Sends the generated message to the user's terminal.

[1596] Terminal: Presents the message to the user in a preview format, allowing the user to review it and decide whether to send it.

[1597] User: Starts a conversation by sending a message.

[1598] 6. Conversation analysis and feedback

[1599] Server: Collects the history of messages sent and received between users and stores it in a database.

[1600] Server: Uses a generative AI model to analyze collected message content and evaluate user responses and conversation progress.

[1601] Server: If the conversation stalls or progress is not being made, it generates new topics and messages and suggests them to the user.

[1602] 7. Incorporating an Emotional Engine

[1603] Server: Uses an emotion engine to recognize emotions from messages and user behavior, for example, inferring a user's emotional state from the tone and frequency of their text messages.

[1604] Server: Adjusts conversation starters based on the recognized emotions. For example, if the user shows anger or sadness, it generates a calm message that takes that emotion into account.

[1605] Server: Suggested messages based on emotions are tailored to be emotionally appropriate using natural language generation technology.

[1606] Specific examples

[1607] For example, consider a situation where User A is interested in "movies" and "music," and User B is interested in "cooking" and "travel." User A enters these interests in their profile settings, and their device sends this information to the server. The server uses a generative AI model to learn User A's information and collects the latest related online news.

[1608] Next, the server uses an emotion engine to recognize emotions from User A's messages and behavior. For example, if User A wrote "I've been very tired recently" in a past message, the emotion engine determines that User A is currently "tired." Based on this, the server generates a calm message related to a common interest.

[1609] The server generates a message in the form of "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and presents it to User A. User A checks this message and sends it to User B, creating a natural conversation starter. By taking into account the user's emotions, this system provides a more personalized experience.

[1610] This makes it easier for users to maintain a natural conversation flow that reflects their emotions, and allows for smooth communication with people they meet for the first time.

[1611] The processing flow will be explained below.

[1612] Step 1: Enter your information

[1613] User: Open the profile settings screen and enter profile information such as hobbies, interests, location, and self-introduction.

[1614] Terminal: Formats the information entered and sends it to the server.

[1615] Step 2: Training the generative AI model

[1616] Server: Receives the transmitted user profile information.

[1617] Server: Provides the generative AI model with user profile information, which allows the model to learn about interests and personality.

[1618] Server: Stores the learning results of the generative AI model in a database.

[1619] Step 3: Collecting online news

[1620] Server: Uses RSS feeds and news APIs to periodically gather the latest news articles from the internet.

[1621] Server: Organizes collected news articles by category and records metadata of news articles.

[1622] Step 4: Extracting common topics and generating messages

[1623] Server: Uses a generative AI model to match user profile information with collected news articles.

[1624] Server: Extracts common topics from news articles related to the user's interests. For example, if multiple users are interested in "movies," it selects the latest movie review articles.

[1625] Server: Using natural language generation technology, it generates messages that serve as conversation starters based on the extracted common topics. For example, it creates messages such as, "Have you seen the popular movie 'Tenet' recently?"

[1626] Step 5: Incorporating the Emotion Engine

[1627] Server: Using the emotion engine, analyzes the user's messages and behavioral data to recognize their current emotional state. For example, it determines whether the user is expressing emotions such as "tiredness" or "joy" based on the content and frequency of text messages.

[1628] Server: Adjusts the generated messages based on the user's perceived emotions. For example, if the user feels "tired," it suggests emotionally appropriate topics such as "relaxing movies."

[1629] Step 6: Propose a talk

[1630] Server: Sends the coordinated conversation message to the user's terminal.

[1631] Terminal: The generated message is presented to the user in a preview format, allowing the user to review it and decide whether it is appropriate.

[1632] User: Review the message and send it to whomever they deem appropriate.

[1633] Step 7: Collect conversation progress

[1634] Server: Collects the history of messages sent and received between users and stores it in a database.

[1635] Server: Analyzes collected message content using a generative AI model to evaluate user responses and conversation progress.

[1636] Step 8: Suggest new conversation starters

[1637] Server: Using the emotion engine, it reconfirms the user's current emotional state and generates new topics and messages as needed. For example, if the user has a positive emotion towards the conversation, it suggests further interesting topics.

[1638] Server: Maintains smooth communication by sending newly generated messages to the user's device.

[1639] This helps maintain a natural conversation flow between users and helps ensure smooth communication with people meeting for the first time.

[1640] Example 2

[1641] 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."

[1642] In today's world, it is difficult for users to naturally start a conversation, and it is often difficult for them to communicate their feelings, especially when they meet for the first time. Furthermore, conventional communication support systems have difficulty recognizing users' emotions and suggesting appropriate ways to start a conversation. This leads to unnatural communication between users, making it difficult to build relationships.

[1643] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1644] In this invention, the server includes an input means for inputting user profile information, a transmission means for transmitting the input user profile information to the server, and a learning means for learning the user profile information and analyzing the user's interests using a generative AI model, thereby enabling the server to recognize the user's emotions using an emotion engine and generate appropriate conversational messages.

[1645] "Input means" refers to an interface through which a user inputs their profile information.

[1646] "Transmission means" refers to the function of converting the entered profile information into an appropriate format and transmitting it to the server.

[1647] "Learning means" refers to the function that uses a generative AI model to analyze a user's profile information and learn about the user's interests and personality.

[1648] "Gathering means" refers to the function of collecting the latest news articles from the Internet, organizing them into categories, and filtering news related to the user's interests.

[1649] "Generation means" refers to a function that extracts common topics between users and generates messages that will serve as a starting point for natural conversation.

[1650] The "presentation means" refers to a function that presents the generated message to the user so that the user can confirm the message.

[1651] "Receiving means" refers to a function that supports users in sending messages.

[1652] "Analysis means" refers to the function of collecting message logs and analyzing the progress of the conversation and the user's reactions.

[1653] "Suggestion means" refers to a function that suggests new conversation starters to the user based on the analysis results.

[1654] "Emotion recognition means" refers to a function that uses an emotion engine to recognize a user's emotion and generates an appropriate conversational message based on that emotion.

[1655] The present invention is a system for providing natural conversation starters between users, and in particular, by combining an emotion engine, it recognizes user emotions and supports more appropriate communication. This system provides a terminal with an input means for users to input profile information, and includes a transmission means for transmitting the input information to a server. The server also has a learning means for learning the user's profile information using a generative AI model and analyzing the user's interests based on the results.

[1656] Next, the server has a collection means for collecting the latest news articles from the Internet and uses a specific algorithm to filter out news relevant to the user's interests.The server then extracts common topics based on this information and generates messages that serve as natural conversation starters.Natural language generation technology is used to generate these messages.The generated messages are displayed to the user via a presentation means provided on the terminal.The user can review these messages and send them as needed.

[1657] The server also has an analysis means for collecting messages sent and received between users and analyzing the progress of the conversation based on the collected messages. The server also includes a suggestion means for suggesting new conversation starters to users based on the results of this analysis. The server also has an emotion recognition means that uses an emotion engine to analyze the user's emotions and adjust conversation messages according to the emotions.

[1658] As a specific example, consider a situation where User A is interested in movies and music, and User B is interested in cooking and travel. User A enters these interests on a profile setting screen, and the information is sent from the device to the server. The server uses a generative AI model to learn User A's profile information, while simultaneously collecting relevant and recent news articles and identifying articles related to User A's interests.

[1659] The server then uses the emotion engine to recognize User A's emotions. For example, if User A writes, "I've been feeling very tired lately," the emotion engine determines User A's current emotional state as "tired." Based on this, the server generates a calm message related to a common interest. The generated message might be, "Do you think you can enjoy the movie 'Tenet,' which is currently a hot topic, while relaxing?" and presents it to User A. User A can then review this message and send it to User B, sparking a natural conversation.

[1660] A specific example of a prompt sentence could be, "User A is interested in movies and music and has been feeling tired lately. Please generate a message that will provide a common topic." Based on this prompt sentence, the system can suggest appropriate conversation starters.

[1661] The hardware used includes the user's smartphone or PC (device) and a cloud server. The software includes a profile input UI, a transmission server, a generative AI model library (e.g., GPT-3), and a sentiment analysis engine (e.g., a natural language processing engine). This system enables users to start natural conversations and communicate in a way that takes emotions into consideration.

[1662] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1663] Step 1:

[1664] Enter user information

[1665] User: The user opens the profile setting screen and enters their hobbies, interests, location information, and self-introduction. The entered data is stored in text format on the device.

[1666] Terminal: The terminal converts the profile information entered by the user into a specified format (e.g., JSON). The formatted data is sent to the server using the HTTPS protocol.

[1667] Input: Raw data entered by the user (hobbies, interests, location, bio).

[1668] Output: Formatted data (JSON format).

[1669] Step 2:

[1670] Training generative AI models

[1671] Server: The server takes the received profile information as an input dataset for the generative AI model. The dataset includes feature data such as the user's hobbies and interests.

[1672] Server: Extracts feature data and analyzes user interests. A generative AI model (e.g., GPT-3) is used to learn information related to the user's interests. Natural language processing (NLP) techniques are used in this process.

[1673] Server: The user model (profile of interests and personality) generated as a result of learning is stored in a database.

[1674] Input: Formatted profile data (JSON format).

[1675] Output: Learned user model (stored in database).

[1676] Step 3:

[1677] Collecting online news

[1678] Server: The server periodically collects the latest news articles from the Internet using RSS feeds and web scraping technology. The data collected includes information such as article titles, content, and categories.

[1679] Server: Organizes collected news articles by category and performs preprocessing (e.g., noise removal, text normalization).

[1680] Server: Using a filtering algorithm, extract only articles that are highly relevant to the user's interests.

[1681] Input: Raw news data collected from the internet.

[1682] Output: Organized news article data by category.

[1683] Step 4:

[1684] Extracting common topics and generating messages

[1685] Server: Uses a generative AI model to match user profile information with collected news articles, using a similarity calculation algorithm (e.g., cosine similarity) in the process.

[1686] Server: Combines highly similar news articles with user interests to extract common topics.

[1687] Server: Uses natural language generation technology to generate messages that spark conversations between users.

[1688] Input: Organized news article data, user profile information.

[1689] Output: The generated conversation starter message.

[1690] Step 5:

[1691] Talk suggestions

[1692] Server: Sends the generated message to the user's terminal.

[1693] Terminal: Updates the UI to present received messages to the user in a preview format.

[1694] User: Check the message presented and, if necessary, press the send button to send the message to the other user.

[1695] Input: The generated conversation message.

[1696] Output: Messages confirmed by users or sent.

[1697] Step 6:

[1698] Conversation analysis and feedback

[1699] Server: Collects logs of messages sent and received between users and stores them in a database.

[1700] Server: Analyzes the collected message content using a generative AI model to evaluate the progress of the conversation and user responses. This analysis uses text mining techniques.

[1701] Server: If the conversation is stagnating or if the user is not responding well, generate new topics and messages and suggest them to the user again.

[1702] Input: A log of messages sent and received.

[1703] Output: Analysis results, newly generated conversation starter messages.

[1704] Step 7:

[1705] Incorporating an emotion engine

[1706] Server: Uses an emotion engine (e.g., a natural language processing engine) to recognize emotions from users' messages and behaviors. Infers emotional states by analyzing the tone and frequency of text messages.

[1707] Server: Based on the recognized emotion data, the server fine-tunes the conversation starter message. For example, if the user is judged to be "tired," it generates a gentle message such as, "Do you think you can enjoy the popular movie "Tenet" while relaxing?"

[1708] Server: Emotionally tailored messages are made emotionally appropriate using natural language generation techniques.

[1709] Input: The user's message data.

[1710] Output: Tailored messages generated based on sentiment.

[1711] (Application example 2)

[1712] 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."

[1713] In recent years, communication with customers in brick-and-mortar stores has become increasingly important. However, it is difficult to smoothly advance natural conversations between store clerks and customers, and it is particularly challenging to provide appropriate topics of conversation for customers meeting for the first time. It is also difficult to instantly grasp the customer's emotional state and respond appropriately to the situation. Furthermore, there is a need to suggest new topics of conversation when the conversation stalls or when progress is not being made.

[1714] 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.

[1715] In this invention, the server includes: an input means for inputting user profile information; a transmission means for transmitting the input user profile information to the server; a learning means for learning the user profile information using a generative AI model and analyzing the user's interests; a collection means for collecting the latest news articles from the Internet and filtering news related to the user's interests; a generation means for extracting common topics between users and generating messages to start a conversation; a presentation means for presenting the generated messages to the user and allowing the user to confirm the messages; a reception means for supporting users in sending messages; an analysis means for collecting message logs and analyzing the progress of the conversation; a suggestion means for suggesting new conversation starters based on the analysis results; an emotion recognition means for recognizing the user's emotions using an emotion engine and generating conversation messages based on the recognized emotions; and a conversation support means for a store clerk wearing smart glasses in a physical store to support natural conversations with users. This enables smooth natural conversations with customers and enables responses according to the customer's emotional state.

[1716] "Input means" refers to a device or system for collecting user profile information.

[1717] The "transmission means" is a device or system that transmits the input user profile information to the server.

[1718] A "learning means" is a device or system that uses a generative AI model to learn user profile information and analyze user interests.

[1719] An "aggregator" is a device or system that collects the latest news articles from the Internet and filters them to those relevant to the user's interests.

[1720] The "generation means" is a device or system that extracts common topics between users and generates messages that serve as conversation starters.

[1721] The "presentation means" is a device or system that presents the generated message to the user and allows the user to check the message.

[1722] A "receiving means" is a device or system that supports users in sending messages.

[1723] The "analysis means" is a device or system that collects message logs and analyzes the progress of the conversation.

[1724] A "suggestion means" is a device or system that suggests new conversation starters based on the analysis results.

[1725] The "emotion recognition means" is a device or system that uses an emotion engine to recognize a user's emotion and generates a conversational message based on the recognized emotion.

[1726] A "conversation support means" is a device or system that supports natural conversation between a store clerk wearing smart glasses and a user in a physical store.

[1727] MODE FOR CARRYING OUT THE INVENTION

[1728] The present invention provides a system for supporting natural conversations with customers in a physical store. The system includes a series of means for inputting, transmitting, and learning user profile information. Specific embodiments of the system are described below.

[1729] System Overview

[1730] The system consists of an input means for inputting user profile information, a transmission means for sending the input information to a server, a learning means for learning and analyzing user interests using a generative AI model, a collection means for collecting and filtering the latest news articles from the Internet, a generation means for extracting common topics between users and generating messages, a presentation means for presenting the generated messages, a reception means for supporting the sending and receiving of messages, an analysis means for analyzing the progress of the conversation, a suggestion means for proposing new topics based on the analysis results, and an emotion recognition means for recognizing user emotions using an emotion engine.It also includes a conversation support means in which store clerks wearing smart glasses support natural conversations with customers in physical stores.

[1731] What the program does

[1732] Enter and submit user information

[1733] Users enter their profile information through smart glasses worn by a store clerk in a brick-and-mortar store, such as their hobbies, interests, and current mood. This information is formatted and sent to a server via the smart glasses.

[1734] Learning and analysis with generative AI models

[1735] The server provides the received user profile information to the generative AI model for learning. The generative AI model analyzes the user's interests and personality and stores the results. This allows it to provide optimal conversation starters to customers.

[1736] News article collection and filtering

[1737] The server periodically collects the latest news articles from the Internet, organizes them into categories, and filters only those relevant to the user's interests, making it easier for customers to find topics of interest.

[1738] Conversation starter generation and presentation

[1739] The server uses a generative AI model to match the user's profile information with collected news articles to extract common topics. Based on the extracted topics, it generates messages that serve as natural conversation starters. The generated messages are displayed on the smart glasses to help store associates start conversations with customers.

[1740] Sending and receiving messages and analyzing progress

[1741] When a user sends a message, the history is stored on the server. The server analyzes the collected message logs and evaluates the progress of the conversation. Based on this evaluation, if the conversation has stalled or is not progressing, it will suggest a new topic.

[1742] Emotion recognition and conversation regulation

[1743] The server uses an emotion engine to recognize the user's emotions. It estimates the user's emotional state from the user's facial expressions and message tone, and adjusts the conversation message accordingly. For example, if the user is feeling "tired," a gentle message that takes that emotion into account is generated.

[1744] Specific examples

[1745] For example, if User A is interested in "movies" and "music" and is currently feeling "tired," the server will use a generative AI model based on User A's profile information to learn from it. The server will then collect the latest movie-related news articles from the Internet and extract topics suitable for User A, who is feeling "tired." The smart glasses will display a message saying, "Do you think you can enjoy the recently popular movie 'Tenet' while relaxing?" and the store clerk will use this message to help naturally start a conversation with User A.

[1746] Prompt Sentence Examples

[1747] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[1748] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1749] Step 1:

[1750] The user inputs profile information. The user inputs information such as hobbies, interests, and current mood through the interface of the smart glasses. The input information is formatted to be sent from the smart glasses to the server. The input data is the user's profile information, and the output data is the formatted profile information.

[1751] Step 2:

[1752] The server receives the transmitted profile information. The server receives the transmitted profile information from the smart glasses and stores it in a database. The input data is the formatted profile information, and the output data is the stored profile information.

[1753] Step 3:

[1754] The server uses the generative AI model to learn the user's profile information and analyze their interests and personality. The server trains the generative AI model based on the input profile information to identify the user's interests and personality. The input data is the profile information, and the output data is the analysis of the user's interests and personality.

[1755] Step 4:

[1756] The server collects the latest news articles from the Internet and organizes them by category. The server periodically scrapes the news articles, filters them by category, and stores them in a database. The input data are news articles from the Internet, and the output data are categorized news articles.

[1757] Step 5:

[1758] The collected news articles are filtered by relating them to the user's interests. The server selects relevant news articles based on the user's interests obtained from the generative AI model. The input data are categorized news articles and the user's interests, and the output data are filtered related news articles.

[1759] Step 6:

[1760] The server extracts common topics and generates messages that can spark conversation. The server matches the filtered news articles with the user's profile information to find common topics. It then uses a generative AI model to generate messages that can spark natural conversation. The input data are the filtered news articles and profile information, and the output data are the generated messages.

[1761] Step 7:

[1762] The server sends the generated message to the smart glasses and presents it to the user. The smart glasses display the received message for the user to review. The input data is the generated message, and the output data is the displayed message.

[1763] Step 8:

[1764] The user starts a conversation based on the message and sends and receives messages. The store clerk wearing smart glasses starts a conversation with the customer based on the displayed message. The message sent by the user is sent to the server and saved as a log. The input data is the sent message, and the output data is the saved message log.

[1765] Step 9:

[1766] The server collects message logs and analyzes the progress of the conversation. The server analyzes the collected message logs and identifies when the conversation has been interrupted or when progress is not being made. The input data is the message logs, and the output data is the progress analysis result.

[1767] Step 10:

[1768] The server proposes new topics based on the analysis results. The server then uses a generative AI model based on the results of the previous analysis to generate new conversation starters and sends them to the smart glasses. The input data is the analysis results, and the output data is the newly generated message.

[1769] Step 11:

[1770] The server recognizes the user's emotions using an emotion engine and adjusts the conversation message based on the recognized emotions. The server estimates the user's emotional state from the user's facial expression and message tone, generates an appropriate message, and displays it on the smart glasses. The input data is the user's facial expression and message tone, and the output data is the adjusted message.

[1771] Prompt Sentence Examples

[1772] Consider a system that provides conversation starters when User A and User B meet for the first time in a physical store. User A's profile information states that he is interested in "movies" and "music" and that he is currently feeling "tired." User B is interested in "travel" and "cooking." Based on this situation, use smart glasses and combine an emotion engine to provide appropriate conversation starters.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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).

[1780] 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.

[1781] 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."

[1782] 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.

[1783] 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).

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] The following is further disclosed regarding the above embodiment.

[1795] (Claim 1)

[1796] input means for inputting user profile information;

[1797] a transmitting means for transmitting the input user profile information to a server;

[1798] a learning means for using a generative AI model to learn user profile information and analyze user interests;

[1799] aggregating means for collecting the latest news articles from the internet and filtering the news relevant to the user's interests;

[1800] A generating means for extracting common topics between users and generating messages that will serve as conversation starters;

[1801] a presentation means for presenting the generated message to a user and allowing the user to confirm the message;

[1802] receiving means for supporting users to send messages;

[1803] an analytical means for collecting message logs and analyzing the progress of conversations;

[1804] A suggestion tool that suggests new conversation starters based on the analysis results;

[1805] A system including:

[1806] (Claim 2)

[1807] 2. The system according to claim 1, further comprising an evaluation means for storing a history of messages sent and received between users and evaluating the progress of the conversation based on the stored history.

[1808] (Claim 3)

[1809] 10. The system of claim 1, wherein the generative AI model uses natural language generation techniques to generate natural conversational messages relevant to the user's interests.

[1810] "Example 1"

[1811] (Claim 1)

[1812] input means for inputting user data;

[1813] a transmitting means for transmitting the input user data to a server;

[1814] a learning means that uses a generative AI model to learn user data and analyze user interests;

[1815] a collection means for collecting up-to-date information from the network and filtering the information relevant to the user's interests;

[1816] A generating means for extracting common topics between users and generating messages that will serve as conversation starters;

[1817] a presentation means for presenting the generated message to a user and allowing the user to confirm the message;

[1818] a communication means for supporting users to send messages;

[1819] an analytical means for collecting message logs and analyzing the progress of conversations;

[1820] A suggestion tool that suggests new conversation starters based on the analysis results;

[1821] A system including:

[1822] (Claim 2)

[1823] 2. The system according to claim 1, further comprising an evaluation means for storing a history of messages sent and received between users and evaluating the progress of the conversation based on the stored history.

[1824] (Claim 3)

[1825] 10. The system of claim 1, wherein the generative AI model uses natural language generation techniques to generate natural conversational messages relevant to the user's interests.

[1826] "Application Example 1"

[1827] (Claim 1)

[1828] input means for inputting user profile information;

[1829] a transmitting means for transmitting the input user profile information to a server;

[1830] a learning means for using a generative AI model to learn user profile information and analyze user interests;

[1831] aggregating means for collecting the latest news articles from the internet and filtering the news relevant to the user's interests;

[1832] A generating means for extracting common topics between users and generating messages that will serve as conversation starters;

[1833] a presentation means for presenting the generated message to a user and allowing the user to confirm the message;

[1834] receiving means for supporting users to send messages;

[1835] an analytical means for collecting message logs and analyzing the progress of conversations;

[1836] A suggestion tool that suggests new conversation starters based on the analysis results;

[1837] A presentation means for presenting common topics between staff and customers in a physical store using smart glasses or a head-mounted display;

[1838] A system including:

[1839] (Claim 2)

[1840] 2. The system according to claim 1, further comprising an evaluation means for storing a history of messages sent and received between users and evaluating the progress of the conversation based on the stored history.

[1841] (Claim 3)

[1842] 10. The system of claim 1, wherein the generative AI model uses natural language generation techniques to generate natural conversational messages relevant to the user's interests.

[1843] "Example 2: Combining Emotion Engines"

[1844] (Claim 1)

[1845] input means for inputting user profile information;

[1846] a transmitting means for transmitting the input user profile information to a server;

[1847] a learning means for using a generative AI model to learn user profile information and analyze user interests;

[1848] aggregating means for collecting the latest news articles from the internet and filtering the news relevant to the user's interests;

[1849] A generating means for extracting common topics between users and generating messages that will serve as conversation starters;

[1850] a presentation means for presenting the generated message to a user and allowing the user to confirm the message;

[1851] receiving means for supporting users to send messages;

[1852] an analytical means for collecting message logs and analyzing the progress of conversations;

[1853] A suggestion tool that suggests new conversation starters based on the analysis results;

[1854] an emotion recognition means for recognizing an emotion of a user using an emotion engine and generating an appropriate conversational message;

[1855] A system including:

[1856] (Claim 2)

[1857] 2. The system according to claim 1, further comprising an evaluation means for storing a history of messages sent and received between users and evaluating the progress of the conversation based on the stored history.

[1858] (Claim 3)

[1859] 10. The system of claim 1, wherein the generative AI model uses natural language generation techniques to generate natural conversational messages relevant to the user's interests.

[1860] "Application example 2 when combining emotion engines"

[1861] (Claim 1)

[1862] input means for inputting user profile information;

[1863] a transmitting means for transmitting the input user profile information to a server;

[1864] a learning means for using a generative AI model to learn user profile information and analyze user interests;

[1865] aggregating means for collecting the latest news articles from the internet and filtering the news relevant to the user's interests;

[1866] A generating means for extracting common topics between users and generating messages that will serve as conversation starters;

[1867] a presentation means for presenting the generated message to a user and allowing the user to confirm the message;

[1868] receiving means for supporting users to send messages;

[1869] an analytical means for collecting message logs and analyzing the progress of conversations;

[1870] A suggestion tool that suggests new conversation starters based on the analysis results;

[1871] an emotion recognition means for recognizing an emotion of a user using an emotion engine and generating a conversational message based on the recognized emotion;

[1872] A conversation support means for a store clerk wearing smart glasses in a physical store to support natural conversations with a user;

[1873] A system including:

[1874] (Claim 2)

[1875] 2. The system according to claim 1, further comprising an evaluation means for storing a history of messages sent and received between users and evaluating the progress of the conversation based on the stored history.

[1876] (Claim 3)

[1877] 10. The system of claim 1, wherein the generative AI model uses natural language generation techniques to generate natural conversational messages relevant to the user's interests. [Explanation of symbols]

[1878] 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. input means for inputting user profile information; a transmitting means for transmitting the input user profile information to a server; a learning means for using a generative AI model to learn user profile information and analyze user interests; aggregating means for collecting the latest news articles from the internet and filtering the news relevant to the user's interests; A generating means for extracting common topics between users and generating messages that will serve as conversation starters; a presentation means for presenting the generated message to a user and allowing the user to confirm the message; receiving means for supporting users to send messages; an analytical means for collecting message logs and analyzing the progress of conversations; A suggestion tool that suggests new conversation starters based on the analysis results; A system including:

2. 2. The system according to claim 1, further comprising evaluation means for storing a history of messages sent and received between users and evaluating the progress of the conversation based on the stored history.

3. 10. The system of claim 1, wherein the generative AI model uses natural language generation techniques to generate natural conversational messages relevant to the user's interests.

Images