System

Abstract

To provide a system.SOLUTION: A system learns user characteristics and performs an information communication service, information search, and information arrangement instead of a user. The system includes: means for providing a virtual account, which is an avatar of the user, on an information communication application; means for cooperating with the generative AI, pre-learning a history of the information communication application, an internet search tool, and a purchase history, and realizing a virtual account "capable of having conversation" and of "push type," which has the same characteristics as the user; means for preprocessing learned data and extracting characteristics of the user; means for training a generative AI model using the extracted characteristics of the user; and means for collecting related information on the basis of an interest and concern of the user and performing push notification to the user through the virtual account.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] Currently, users must perform activities such as social media, web searches, and organizing information themselves, and there is a need for a system that can centrally perform these activities on their behalf. However, it is difficult to provide a system that reflects the user's characteristics, and it is particularly difficult to learn the user's characteristics and provide a "push-type" avatar account that can "converse" and reflects them. [Means for solving the problem]

[0005] This invention provides a system that learns user characteristics and performs social networking, web searches, information organization, etc. on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and in cooperation with generative AI, pre-learns the messenger app chat history and internet search tool shopping history. This realizes a "conversational" and "push-based" avatar account with the same characteristics as the user. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One embodiment of the present invention provides a system that learns user characteristics and performs social networking, web searches, information organization, and other functions on behalf of the user. Specifically, an avatar account that represents the user is provided on a messenger app. This avatar account pre-learns the user's messenger app chat history and internet search tool shopping history, and by linking with generative AI, it creates a "conversational" and "push-based" avatar account with the same characteristics as the user.

[0029] "Example 2"

[0030] As a specific example, User A provides his / her conversation history with Friend B on a messenger app and his / her purchase history on Amazon as pre-learning data. Based on this data, the system works with generative AI to learn User A's characteristics. After learning is complete, the system provides an avatar account on the messenger app that will represent User A. This avatar account will be a "push-type" avatar account with the same characteristics as User A, capable of "conversation," and will be able to post on social media, send messages, and perform web searches on User A's behalf.

[0031] "Example 3"

[0032] Another embodiment of the present invention provides a function for providing information and generating search results that reflect a user's preferences and tastes. Specifically, an avatar account is provided that automatically performs actions such as posting to social media, sending messages, and web searches. This avatar account can learn the user's characteristics and generate information and search results that reflect those characteristics.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user provides the system with their conversation history with friends on the messenger app and their purchase history on Amazon.

[0036] Step 2: Based on the data provided, the system works with generative AI to learn the user's characteristics.

[0037] Step 3: After learning is complete, the system will provide the user with an avatar account on the Messenger app.

[0038] Step 4: This avatar account will be a "conversational" and "push-type" avatar account with the same characteristics as the user, and will be able to post on social media, send messages, search the web, and more on behalf of the user.

[0039] "Example 2"

[0040] Step 1: The user provides the system with behavioral data such as social media posts, messaging, and web searches.

[0041] Step 2: The system learns the user's characteristics based on the data provided.

[0042] Step 3: After the learning is complete, the system will provide the user with an avatar account.

[0043] Step 4: This avatar account can generate information and search results that reflect the user's characteristics.

[0044] Example 1

[0045] Next, a description will be given of Example 1 of Form 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."

[0046] In today's information society, users need to efficiently collect and organize vast amounts of information. However, doing this manually takes time and effort, and is inefficient. In addition, while there is a demand for information to be provided based on the user's characteristics and preferences, it is difficult to fully realize this with conventional systems. Furthermore, when users use multiple information and communication services and search tools, there is a lack of a way to centrally manage and utilize the history and characteristics of each. A system that can solve these issues is needed.

[0047] 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.

[0048] In this invention, the server includes: means for learning user characteristics and providing information and communication services, information search, information organization, etc. on behalf of the user; means for providing a virtual account that serves as the user's avatar on the information and communication application; means for cooperating with a generative AI and pre-learning the information and communication application history, internet search tools, and purchase history to realize a "conversational" and "push-type" virtual account with the same characteristics as the user; means for pre-processing collected data and extracting user characteristics; means for training a generative AI model using the extracted characteristics; and means for collecting related information based on the user's interests and preferences and sending push notifications through the virtual account. This enables the provision of information and the generation of search results based on the user's characteristics and preferences, significantly improving the efficiency of users' information collection and organization.

[0049] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and interests.

[0050] "Information and communication services" refers to communication methods such as messaging, social networking services, and email provided via the Internet.

[0051] "Information search" refers to the act of finding specific information on the Internet.

[0052] "Information organization" refers to the act of classifying and organizing collected information to make it easier to use.

[0053] "Information and communication applications" refers to software that allows users to send and receive messages and share information.

[0054] A "virtual account" refers to a digital alter ego that acts on a user's behalf on an information and communication application.

[0055] "Generative AI" refers to artificial intelligence technology that learns the characteristics of a user and generates responses and behaviors similar to that user's.

[0056] "Pre-learning" refers to the process of pre-training a generative AI model using collected data.

[0057] "Conversational" refers to the virtual account's ability to engage in natural dialogue with the user.

[0058] "Push" refers to the function of automatically notifying users of relevant information based on their interests and concerns.

[0059] "Preprocessing" refers to the process of preparing collected data in a form that is easy to analyze.

[0060] "Feature extraction" refers to the act of extracting features such as user interests and preferences from preprocessed data.

[0061] "Training" refers to the process of training a generative AI model using extracted characteristics.

[0062] "Push notification" refers to the function of sending information to users in real time.

[0063] This invention is a system that learns user characteristics and performs information communication services, information search, information organization, etc. on behalf of the user. Specific embodiments of this system are described below.

[0064] 1. System Overview

[0065] The server learns user characteristics and provides a system for providing information and communication services, information search, information organization, etc. on behalf of the user. This system provides a virtual account that serves as the user's avatar on the information and communication application, and works in conjunction with generative AI.

[0066] 2. Hardware and Software Used

[0067] The server uses the following hardware and software:

[0068] Hardware: High-performance server machine, database server

[0069] Software: Information and communication applications, generative AI models, data analysis tools, push notification systems

[0070] 3. Data collection and pre-training

[0071] The server collects the user's information and communication application history, internet search tool history, and purchase history. This data serves as the basis for learning user characteristics. The collected data is preprocessed to remove unnecessary data and normalize the data.

[0072] Next, user characteristics are extracted from the preprocessed data. Natural language processing techniques are used to analyze the text data and identify the user's interests. The extracted characteristics are used to train a generative AI model. This pre-training allows the generative AI model to understand the user's characteristics and generate responses that resemble the user's.

[0073] 4. Creating and Configuring Virtual Accounts

[0074] The server uses a pre-trained generative AI model to generate a virtual account that reflects the user's characteristics. This virtual account can then converse on behalf of the user on information and communication applications. The virtual account also has the ability to push notifications of relevant information based on the user's interests.

[0075] 5. Specific Examples

[0076] Example 1: Travel planning

[0077] When a user is planning a trip with friends using an information and communication application, the server will provide information on suitable travel destinations and accommodations based on past travel history and search history. For example, it may suggest places that the user has visited in the past that the friend might be interested in.

[0078] Example 2: Providing shopping information

[0079] If a user is interested in a particular brand, the server collects information about new products from that brand and sends push notifications through the virtual account. For example, the server can instantly notify users when new products from a brand they have previously purchased are released.

[0080] 6. Examples of prompts

[0081] "Based on the user's information and communication application history and internet search history, please generate a virtual account that provides information about travel destinations that the user is interested in. Also, please implement a function to send push notifications with the latest information about those travel destinations."

[0082] In this way, a system is realized that learns the characteristics of the user and provides information and communication services, searches for information, and organizes information on behalf of the user.

[0083] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0084] Step 1: Data collection

[0085] The server collects the user's information and communication application history, internet search tool history, and purchase history.

[0086] Input: User's information and communication application history, internet search history, purchase history

[0087] Data processing: Collected data is stored in a database for centralized management.

[0088] Output: User behavior history data stored in a database

[0089] Specific operation: The server obtains data from information and communication applications and Internet search tools via API and stores it in a database.

[0090] Step 2: Preprocessing the data

[0091] The server pre-processes the collected data.

[0092] Input: User behavior history data stored in a database

[0093] Data processing: Removal of unnecessary data, data normalization, tokenization of text data

[0094] Output: A preprocessed, clean dataset

[0095] Specific operation: The server uses a data cleansing tool to remove noise data and prepare the text data in a form that is easy to analyze.

[0096] Step 3: Feature extraction

[0097] The server extracts user characteristics from the preprocessed data.

[0098] Input: Preprocessed clean dataset

[0099] Data processing: Analyze text data using natural language processing techniques to identify user interests and concerns

[0100] Output: A feature vector that describes the user's characteristics

[0101] Specific operation: The server uses a natural language processing library to analyze the text data and extract the user's interests and concerns.

[0102] Step 4: Training the generative AI model

[0103] The server uses the extracted features to train a generative AI model.

[0104] Input: A feature vector that describes the user's characteristics

[0105] Data processing: Input feature vectors into the generative AI model and train the model

[0106] Output: A generative AI model that learns user characteristics

[0107] How it works: The server uses a machine learning framework to train a generative AI model to learn the user's characteristics.

[0108] Step 5: Generate Virtual Accounts

[0109] The server uses a pre-trained generative AI model to generate a virtual account that reflects the user's characteristics.

[0110] Input: A generative AI model that learns user characteristics

[0111] Data processing: Using generative AI models to create virtual accounts and register them in information and communication applications

[0112] Output: Virtual account on information and communication application

[0113] Specific operation: The server generates a virtual account using the generative AI model and registers it in the information and communication application through the API.

[0114] Step 6: Implementing Push Notifications

[0115] The server collects relevant information based on the user's interests and pushes it to the user through the virtual account.

[0116] Input: User interest data, external sources

[0117] Data processing: Collecting relevant information and formatting it in a way that is appropriate for the user

[0118] Output: Push notification message

[0119] Specific operation: The server collects relevant information from external information sources and sends push notifications to users through virtual accounts.

[0120] In this way, a system is realized that learns the characteristics of the user and provides information and communication services, searches for information, and organizes information on behalf of the user.

[0121] (Application example 1)

[0122] Next, a description will be given of Application Example 1 of Embodiment 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."

[0123] It is difficult for modern consumers to find the best product for them from the vast amount of information available, and it takes time and effort. In addition, there is a lack of personalized product suggestions based on the user's characteristics and preferences, making it difficult for consumers to find products that suit them. Furthermore, there is no system that can search social media or the web or organize information on behalf of the user, so users have to collect information themselves, which is an issue.

[0124] 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.

[0125] In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account that represents the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for learning the user's purchase history and search history and automatically suggesting products that match the user's preferences; and means for suggesting products based on the user's history using a generative AI model. This allows users to easily find the products that are best suited to them and reduces the effort required for information gathering.

[0126] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and purchasing history.

[0127] "SNS" is an abbreviation for social networking service, an online platform where users can share information and communicate with other users.

[0128] "Web search" refers to the act of finding information on the Internet using a search engine.

[0129] "Information organization" refers to the act of classifying collected information and organizing it into an easy-to-understand format.

[0130] A "messenger app" is application software that allows users to send and receive text messages, images, audio, etc.

[0131] An "avatar account" is a virtual account that functions as a user's alter ego and communicates and collects information on behalf of the user.

[0132] "Generative AI" refers to artificial intelligence technology that generates new information and suggestions based on user input and historical data.

[0133] "Pre-learning" refers to the process in which the system learns the user's past behavioral history and data in advance.

[0134] "Push" refers to a method in which the system automatically provides information or suggestions before the user requests them.

[0135] "Purchase history" refers to a record of products a user has purchased in the past.

[0136] "Search history" refers to a record of keywords or phrases a user has previously searched for on a search engine.

[0137] A "generative AI model" refers to an artificial intelligence algorithm that generates new information and suggestions based on a user's historical data.

[0138] As an embodiment of this invention, we provide a system that learns user characteristics and performs SNS, web searches, information organization, etc. on behalf of the user. Specifically, we provide an avatar account that represents the user on a messenger app, and in cooperation with generative AI, pre-learn the user's messenger app chat history and internet search tool shopping history. This avatar account is a "conversational" and "push-type" avatar account with the same characteristics as the user.

[0139] The server learns the user's purchase and search history and automatically suggests products that match the user's preferences. Using a generative AI model, it suggests products based on the user's history. This system allows users to easily find the products that best suit them, eliminating the need to gather information.

[0140] Hardware and software used

[0141] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[0142] Software: Messenger apps, generative AI models (e.g., OpenAI (registered trademark) GPT-3 (registered trademark))

[0143] Data processing and calculation

[0144] The server collects the user's chat history from messenger apps, internet search tools, and shopping purchase history, and pre-trains this data. A generative AI model is used to analyze the user's history data and learn their characteristics and preferences. This allows it to automatically suggest products that match the user's preferences.

[0145] Specific examples

[0146] If a user has previously purchased a smartphone or wireless earphones and is searching for the latest smartphone or high-quality earphones, the generative AI model will suggest products related to the latest smartphones or high-quality earphones.

[0147] Prompt Sentence Examples

[0148] User purchase history: ["smartphone", "wireless earphones"]

[0149] User search history: ["latest smartphone", "high quality earphones"]

[0150] Suggest a product that you would recommend to this user.

[0151] In this way, a personal shopping assistant can be realized that automatically suggests products that match the user's preferences.

[0152] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0153] Step 1:

[0154] The server collects users' chat history, internet search results, and shopping history. This data is used as input to learn about users' characteristics and preferences. Specifically, the server obtains data from each platform via API and stores it in a database.

[0155] Input: Messenger app chat history, internet search tools, shopping purchase history

[0156] Output: User history data stored in a database

[0157] Step 2:

[0158] The server pre-trains the collected user history data. During this pre-training process, a generative AI model is used to analyze the data and learn the user's characteristics and preferences. Specifically, the historical data is input into the AI ​​model to extract the user's behavioral patterns and preferences.

[0159] Input: User history data stored in a database

[0160] Output: A model that reflects the user's characteristics and preferences

[0161] Step 3:

[0162] The server uses a generative AI model to suggest products based on the user's history. In this process, a prompt sentence is generated to suggest the most suitable product based on the user's purchase history and search history, and input into the AI ​​model. The AI ​​model then generates product suggestions based on the prompt sentence.

[0163] Input: A model that reflects the user's characteristics and preferences, prompts

[0164] Output: Product proposal

[0165] Step 4:

[0166] The server sends the generated product suggestions to the user's device, where the user can check the suggested products through a messenger app or a dedicated app. Specifically, the product suggestions are sent to the user's device via API and displayed on the user interface.

[0167] Input: Product proposal

[0168] Output: Product suggestions displayed on the user's device

[0169] Step 5:

[0170] The user reviews the suggested products and purchases them if necessary. In this process, the user receives the product suggestions, selects the products they are interested in, and then completes the purchase process by selecting the products through the user interface and clicking the purchase button.

[0171] Input: Product suggestions displayed on the user's device

[0172] Output: User purchase behavior

[0173] In this way, we have created a system that automatically makes product suggestions based on the user's characteristics and preferences, allowing users to easily find the products that are best suited to them.

[0174] Example 2

[0175] Next, a description will be given of Example 2 of Form 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."

[0176] Conventional information processing systems have had difficulty providing automated information and communication that fully reflects the user's characteristics. It has also been difficult to create an avatar account that posts to social media, sends messages, searches the web, and so on, on behalf of the user. This has increased the burden on the user and hindered efficient information processing.

[0177] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for learning user characteristics and processing information on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for linking with a generative AI model and pre-learning the conversation history of the messenger app and the purchase history of online shopping to realize a "conversational" and "push-type" avatar account with the same characteristics as the user; means for pre-processing data stored in a database, cleaning and tokenizing text data; and means for inputting prompt sentences into the generative AI model and sending generated messages. This enables automated information provision and communication that reflects the user's characteristics.

[0178] "User characteristics" refers to individual characteristics such as a user's behavioral patterns, preferences, and tastes.

[0179] "Information processing" refers to a series of operations such as collecting, analyzing, storing, retrieving, and generating data.

[0180] An "avatar account" refers to a virtual account that acts online on behalf of a user.

[0181] A "generative AI model" refers to an artificial intelligence model that generates new information or content based on given data.

[0182] "Pre-training" refers to the process of training a model using data in advance for a specific task.

[0183] "Conversational" refers to the ability to engage in natural dialogue on behalf of the user.

[0184] "Push" refers to a format in which information is provided automatically without waiting for a user request.

[0185] A "database" refers to a system for efficiently storing, managing, and retrieving data.

[0186] "Preprocessing" refers to the initial processing of data to convert it into a form suitable for analysis and learning.

[0187] "Cleaning" refers to the process of removing unnecessary information or noise from data.

[0188] "Tokenization" refers to the process of breaking down text data into words and phrases.

[0189] A "prompt sentence" refers to an input sentence that causes a generative AI model to generate a specific output.

[0190] The present invention is a system that learns user characteristics and processes information on behalf of the user. Specific embodiments of this system will be described below.

[0191] The server receives the conversation history of the messenger app and the purchase history of online shopping provided by the user. This data is used as pre-learning data to learn the characteristics of the user. The server stores this data in a database. The database uses a relational database such as MySQL (registered trademark) or PostgreSQL.

[0192] The server then preprocesses the stored data, which includes cleaning the text data (removing unnecessary characters and noise) and tokenizing it (dividing it into words and phrases), using the Python NLTK and spaCy libraries.

[0193] After preprocessing, the data is input into a generative AI model (e.g., OpenAI's GPT-4 (registered trademark)). The server uses this generative AI model to learn the user's characteristics. During this learning process, the model reflects the user's conversation patterns and purchasing tendencies. Once learning is complete, the server generates a model that incorporates the user's characteristics.

[0194] The server then generates an avatar account with the user's characteristics based on the trained model. This avatar account can then converse on the user's behalf on the messenger app. Specifically, the avatar account inputs prompts into the generative AI model and sends the generated messages to friends.

[0195] As a concrete example, consider a situation where a user provides a conversation history with a friend, for example, by providing the following prompt sentence to a generative AI model:

[0196] Prompt: "Generate a message for a user to send to a friend. The user recently purchased a new smartphone and wants to tell their friend about their experience with it."

[0197] The generative AI model generates messages like this:

[0198] Generated message: "Hi, friend! I recently bought a new smartphone and it's so easy to use. The camera in particular is amazing and it takes great photos. If your friend is also thinking about buying a new smartphone, I highly recommend it!"

[0199] In this way, avatar accounts can send messages to friends that reflect the user's characteristics. Avatar accounts can also post on social media and perform web searches. This reduces the burden on users and enables more efficient information processing.

[0200] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0201] Step 1: Data collection

[0202] The server receives the user's conversation history from the messenger app and the user's online shopping purchase history. This data is used as pre-learning data to learn the user's characteristics. The input is the conversation history and purchase history provided by the user, and the output is the raw data stored in the database. Specifically, the server receives the data uploaded by the user and stores it in the database.

[0203] Step 2: Data Preprocessing

[0204] The server preprocesses the stored data. This preprocessing includes cleaning the text data (removing unnecessary characters and noise) and tokenizing it (dividing it into words and phrases). The input is the raw data stored in the database, and the output is the preprocessed, clean data. Specifically, the server uses Python's NLTK and spaCy libraries to clean and tokenize the text data.

[0205] Step 3: Trait learning

[0206] The server inputs the preprocessed data into a generative AI model to learn the user's characteristics. The input is preprocessed, clean data, and the output is a trained model that reflects the user's characteristics. Specifically, the server uses a generative AI model (for example, OpenAI's GPT-4) to learn the user's conversation patterns and purchasing tendencies.

[0207] Step 4: Create an avatar account

[0208] The server generates an avatar account with the user's characteristics based on the trained model. The input is the trained model, and the output is the avatar account. Specifically, the server creates an avatar account that can converse on behalf of the user on the messenger app based on the output of the generative AI model.

[0209] Step 5: Avatar Account in Action

[0210] The avatar account inputs a prompt into the generative AI model and sends the generated message to a friend. The input is the prompt, and the output is the generated message. Specifically, the avatar account inputs the following prompt into the generative AI model:

[0211] Prompt: "Generate a message for a user to send to a friend. The user recently purchased a new smartphone and wants to tell their friend about their experience with it."

[0212] The generative AI model generates messages like this:

[0213] Generated message: "Hi, friend! I recently bought a new smartphone and it's so easy to use. The camera in particular is amazing and it takes great photos. If your friend is also thinking about buying a new smartphone, I highly recommend it!"

[0214] The avatar account will then send this message to friends, enabling automated information provision and communication that reflects the user's characteristics.

[0215] (Application example 2)

[0216] Next, a description will be given of Application Example 2 of Form 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."

[0217] Conventional social networking sites and messaging apps require users to collect information and post or send messages themselves, which takes time and effort. Furthermore, there is a lack of effective ways to deliver advertisements that reflect the characteristics and preferences of users. This creates a need to improve user convenience while maximizing the effectiveness of advertisements.

[0218] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping and purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; and means for the avatar that has learned the user's characteristics to post advertisements on SNS and messenger apps on behalf of the user. This enables automatic information collection and posting on behalf of the user, improving user convenience and enabling effective advertisement delivery that reflects the user's characteristics and preferences.

[0219] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and tastes.

[0220] "SNS" is an abbreviation for social networking service, which refers to an online platform where users can share information and communicate with other users.

[0221] "Web search" refers to the act of finding information on the Internet using a search engine.

[0222] "Information organization" refers to the act of classifying and organizing collected information.

[0223] A "messenger app" refers to an application that allows users to send and receive text messages, images, videos, etc.

[0224] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[0225] "Generative AI" refers to artificial intelligence that generates new information and content based on given data.

[0226] "Pre-training" refers to the process of pre-training a model with relevant data before it performs a specific task.

[0227] "Conversational" refers to the ability to have a natural dialogue with the user.

[0228] "Push" refers to a method in which information is provided automatically before the user requests it.

[0229] "Posting an advertisement" refers to the act of publishing information about a specific product or service on social media or a messaging app.

[0230] The system for implementing this invention learns user characteristics and performs SNS, web searches, information organization, etc. on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and by working with generative AI to pre-learn the messenger app chat history and internet search tool shopping history, it realizes a "conversational" and "push-type" avatar account with the same characteristics as the user.

[0231] The server first obtains the user's conversation history and purchase history on the messenger app. This data is collected using the APIs of the messenger app and shopping site. The server then uses generative AI to learn the user's characteristics based on this data. Specifically, the conversation history and purchase history are input as prompts into the generative AI model, allowing it to learn the user's characteristics.

[0232] After the learning is complete, the server generates an avatar account with the user's characteristics, and this avatar posts advertisements on social media and messenger apps on the user's behalf. This makes it possible to automatically collect and post information on the user's behalf, improving user convenience and enabling effective advertisement delivery that reflects the user's characteristics and preferences.

[0233] The hardware used includes servers and user devices (smartphones, tablets, PCs, etc.), while the software used includes messenger apps, shopping site APIs, generative AI (e.g., OpenAI APIs), etc.

[0234] As a concrete example, consider the case where the user ID is "user123" and the ad content is "Check out this amazing product!" In this case, the server would do the following:

[0235] 1. The server obtains the conversation history and purchase history of user ID "user123".

[0236] 2. The server uses generative AI to learn the characteristics of "user123" based on the acquired data.

[0237] 3. The server uses the learned user model to post an ad on social media saying, "Check out this amazing product!"

[0238] Example prompts to input to a generative AI model:

[0239] Train a model based on the following data: [Conversation history and purchase history data]

[0240] This prompt is used to train a generative AI model to learn the user's characteristics.

[0241] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0242] Step 1:

[0243] The server obtains the user's conversation history and purchase history on the messenger app. Specifically, it uses the API of the messenger app or shopping site to collect the conversation history and purchase history related to the user ID. The input is the user ID, and the output is the conversation history and purchase history data.

[0244] Step 2:

[0245] The server uses generative AI to learn the user's characteristics based on the acquired conversation history and purchase history. Specifically, the conversation history and purchase history are input as prompts into the generative AI model, which then learns the user's characteristics. The input is conversation history and purchase history data, and the output is a model that reflects the user's characteristics.

[0246] Step 3:

[0247] The server generates an avatar account based on the learned user model. Specifically, it uses generative AI to create an avatar account with the user's characteristics and provides it to the messenger app. The input is the user model, and the output is the avatar account.

[0248] Step 4:

[0249] The server posts advertisements on social media and messenger apps using the avatar account. Specifically, it generates advertisement content that reflects the user's characteristics and posts it using the SNS or messenger app's API. The input is a user model and advertisement content, and the output is an advertisement posted on the SNS or messenger app.

[0250] Step 5:

[0251] The server monitors the effectiveness of the ads and updates the user model as necessary. Specifically, it collects data such as ad click-through rates and engagement rates, and uses generative AI to retrain the user model. The input is ad performance data, and the output is an updated user model.

[0252] Example 3

[0253] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0254] Conventional information provision systems and search engines have been unable to fully reflect users' preferences and tastes, making it difficult to provide users with the most appropriate information. In addition, users have to search for and organize information themselves, which makes it difficult to efficiently gather information.

[0255] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes: means for learning user characteristics and providing information and generating search results on behalf of the user; means for providing a virtual account on a messaging application that acts as a proxy for the user; means for working with a generative AI to pre-learn the messaging application chat history and internet search tool purchase history and realize an "interactive" and "push-type" virtual account with the same characteristics as the user; means for collecting user behavioral data and analyzing the data using natural language processing technology; means for generating a profile reflecting the user's preferences and tastes based on the analysis results; means for the virtual account to automatically provide information and perform searches based on the generated profile; and means for generating customized information and search results based on the behavioral results of the virtual account. This makes it possible to provide optimal information and generate search results that reflect the user's preferences and tastes.

[0256] "User characteristics" refers to individual characteristics such as a user's preferences, tastes, behavioral patterns, and interests.

[0257] "Information provision" refers to the act of providing useful information to users.

[0258] "Search Results" means the list of information returned in response to a search conducted by a user on the Internet.

[0259] "Messaging application" means software that enables users to send and receive text and multimedia messages.

[0260] "Virtual Account" refers to a digital account that acts on behalf of a user.

[0261] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[0262] "Pre-training" refers to the process by which the system learns using the user's past data.

[0263] "Interactive" refers to a system's ability to engage in natural dialogue with the user.

[0264] "Push" refers to a method in which the system automatically provides information without waiting for a user request.

[0265] "Behavioral Data" refers to data about user actions (e.g., social media posts, search history, message sending, etc.).

[0266] "Natural language processing technology" refers to technology for understanding, analyzing, and generating human language.

[0267] A "profile" refers to a collection of data generated based on a user's characteristics and behavioral patterns.

[0268] "Customized Information" refers to information that is individually tailored based on a user's characteristics and preferences.

[0269] MODE FOR CARRYING OUT THE INVENTION

[0270] The present invention is a system that learns user characteristics and provides information and generates search results on behalf of the user. A specific embodiment of this system is described below.

[0271] 1. Generating the system program

[0272] The server generates a program to provide information and generate search results that reflect the user's preferences and tastes. This program has the function of managing a virtual account that automatically performs actions such as posting to social media, sending messages, and web searches.

[0273] 2. Explanation of program processing

[0274] The server performs the following processing using the generated program.

[0275] 1. Data Collection:

[0276] The server collects data such as users' social media posts, message transmissions, and web search history. This data collection is obtained from each social media platform and search engine via API. Specifically, it uses the Twitter API and Google (registered trademark) Search API.

[0277] 2. Data Analysis:

[0278] The server uses natural language processing (NLP) techniques to analyze the collected data, specifically using software such as Google Cloud Natural Language API and IBM Watson® Natural Language Understanding.

[0279] 3. Create a user profile:

[0280] The server uses the analysis results to create a profile that reflects the user's preferences and tastes, including topics and keywords that interest the user.

[0281] 4. Virtual account behavior simulation:

[0282] The server then generates a virtual account that automatically posts on social media, sends messages, and performs web searches based on the generated user profile. This simulation uses a generative AI model (e.g., OpenAI's GPT-4).

[0283] 5. Information provision and search results generation:

[0284] The server generates customized information and search results for the user based on the behavior of the virtual account, and the information is presented in a form that best suits the user's preferences and tastes.

[0285] 3. Examples of concrete examples and prompts

[0286] Examples:

[0287] Let's say User A is interested in traveling. The server extracts keywords such as "travel," "tourist spots," and "hotels" from User A's social media posts and web search history. Based on this, a virtual account automatically posts travel-related information on social media and searches travel blogs. Finally, it provides User A with information on recommended tourist spots and hotels.

[0288] Example prompt sentence:

[0289] "To provide User A with travel-related information that interests him, please suggest recommended tourist spots and hotels based on his social media posts and web search history."

[0290] In this way, the server realizes a system for providing information and generating search results that reflect the user's preferences and tastes. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0291] Step 1: Data collection

[0292] The server collects data such as users' social media posts, message transmissions, and web search history. Specifically, it retrieves users' tweets using the Twitter API and collects users' search history using the Google Search API. The input is the user's account information, and the output is the collected behavioral data.

[0293] Step 2: Data analysis

[0294] The server uses natural language processing (NLP) technology to analyze the collected data. Specifically, it uses the Google Cloud Natural Language API to extract keywords from users' tweets and search history and perform sentiment analysis. The input is the collected behavioral data, and the output is the analyzed keywords and sentiment information.

[0295] Step 3: Generate a user profile

[0296] The server generates a profile that reflects the user's preferences and tastes based on the analysis results. Specifically, it creates a list of topics and keywords that interest the user based on the extracted keywords and the results of sentiment analysis. The input is the analyzed keywords and sentiment information, and the output is the generated user profile.

[0297] Step 4: Simulating virtual account behavior

[0298] The server automatically posts to social media, sends messages, and performs web searches using virtual accounts based on the generated user profile. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-4) to generate social media posts based on the user's interests and search related websites. The input is the user profile, and the output is the behavioral results of the virtual account.

[0299] Step 5: Providing information and generating search results

[0300] The server generates customized information and search results for users based on the behavioral results of the virtual accounts. Specifically, it organizes the information collected by the virtual accounts and provides users with information on recommended tourist spots and hotels. The input is the behavioral results of the virtual accounts, and the output is customized information and search results.

[0301] (Application example 3)

[0302] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0303] Conventional systems have had difficulty providing information and generating search results that accurately reflect a user's tastes and preferences. They also required users to post on social media, send messages, and search the web themselves, which was time-consuming and labor-intensive. Furthermore, the recommendation function for suggesting the most suitable products to users was insufficient, preventing users from increasing their purchasing motivation. To solve these issues, a system is needed that can automate user behavior, learn user characteristics, and provide optimal information and product suggestions.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0305] In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account on a messenger app that represents the user; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for analyzing the user's SNS posts, message sending, and web search history to learn the user's tastes and preferences; means for suggesting optimal products to the user; means for automatically posting product reviews and questions; and means for making recommendations based on purchase history. This makes it possible to automate user behavior, learn the user's characteristics, and provide optimal information and product suggestions.

[0306] "User characteristics" refers to individual characteristics such as a user's preferences, tastes, and behavioral patterns.

[0307] "SNS" is an abbreviation for social networking service, which refers to a platform where users can interact with other users online.

[0308] "Web search" refers to the act of finding information on the Internet using a search engine.

[0309] "Information organization" refers to the process of classifying and organizing collected data and information to make it easier to use.

[0310] A "messenger app" refers to application software for sending and receiving text messages, images, videos, etc.

[0311] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[0312] "Generative AI" refers to artificial intelligence technology that generates new information and content based on data.

[0313] "Pre-training" refers to the process of pre-training a model with relevant data before it performs a specific task.

[0314] "Push" refers to a method in which information is provided automatically before the user requests it.

[0315] "SNS posting" refers to the act of publishing content such as text, images, and videos on social networking services.

[0316] "Sending a message" refers to the act of sending text messages, images, videos, etc. to other users.

[0317] "Web search history" refers to a record of searches a user has conducted on the Internet in the past.

[0318] "Product suggestion" refers to the act of recommending appropriate products based on a user's preferences and tastes.

[0319] A "product review" refers to the act of writing an evaluation or opinion on a purchased product.

[0320] "Recommendation" refers to a system that recommends appropriate products and services based on a user's past behavior and preferences.

[0321] A system for implementing this invention learns user characteristics and performs social networking, web searches, information organization, etc. on behalf of the user. The system provides an avatar account that represents the user on a messenger app and works in conjunction with generative AI. Specific embodiments of the system are described below.

[0322] System configuration

[0323] The system consists of the following main components:

[0324] 1. User device: A device such as a smartphone or tablet with a messenger app installed.

[0325] 2. Server: Collects and analyzes user data and uses generative AI models to provide information and product suggestions.

[0326] 3. Generative AI model: An AI model that analyzes users' social media posts, messaging, and web search history to learn their preferences and tastes.

[0327] Program processing

[0328] The server implements the system using the following means:

[0329] 1. Learning user characteristics: The server collects users' social media posts, messages, and web search history, and uses a generative AI model to learn their characteristics. Specifically, it converts text data into TF-IDF vectors and analyzes their preferences and tastes.

[0330] 2. Providing avatar accounts: Create an avatar account on the messenger app that represents the user, and post to social media and send messages on the user's behalf.

[0331] 3. Information provision and product suggestions: The server provides optimal information and product suggestions based on the user's characteristics. Specifically, it makes recommendations based on the user's purchase history and search history.

[0332] 4. Auto-posting: Avatar accounts automatically post product reviews and questions on behalf of users.

[0333] Hardware and software used

[0334] Hardware: User devices (smartphones, tablets), servers

[0335] Software: Messenger app, generative AI models (e.g., sklearn's TfidfVectorizer, cosine_similarity)

[0336] Specific examples

[0337] For example, if a user posts on social media that they want a new smartphone, the system will collect this information and learn their preferences. Next, if the user frequently searches for "high-performance laptops" online, the system will use this information to suggest the best products. Additionally, avatar accounts will automatically post product reviews and questions, organizing information on the user's behalf.

[0338] Prompt Sentence Examples

[0339] Build an application that analyzes users' social media posts, messages, and web search history to learn their preferences and tastes and recommend the best products. Retrieve user data from an API and analyze the text data using TF-IDF vectors. Use cosine similarity to recommend products.

[0340] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0341] Step 1:

[0342] The user's device collects the user's social media posts, messages, and web search history. This data serves as input data for learning the user's preferences and tastes. Specifically, the system collects text posted on social media, text sent via messaging apps, URLs and search queries from the user's web search history.

[0343] Step 2:

[0344] The server inputs the collected user data into a generative AI model. The generative AI model uses this data to learn user characteristics. Specifically, it converts text data into TF-IDF vectors and analyzes user preferences and tastes. The input data is in text format, and the output is vector data representing the user's characteristics.

[0345] Step 3:

[0346] The server creates an avatar account on the messenger app that represents the user. This avatar account posts on social media and sends messages on behalf of the user. Specifically, the avatar account posts text generated based on the user's characteristics. The input data is the user's characteristic vector, and the output is the text to post on social media or send a message.

[0347] Step 4:

[0348] The server provides optimal information and product suggestions based on the user's characteristics. Specifically, it makes recommendations based on the user's purchase history and search history. The input data is the user's characteristic vector, purchase history, and search history, and the output is a list of recommended products.

[0349] Step 5:

[0350] The avatar account automatically posts product reviews and questions on behalf of the user. Specifically, it generates reviews and questions for recommended products and posts them from the avatar account. The input data is a list of recommended products, and the output is the text of the product reviews and questions.

[0351] Step 6:

[0352] The server continuously monitors user behavior, collects new data, and updates the generative AI model, keeping the user's characteristics up to date. The input data is the newly collected user data, and the output is the updated user's characteristic vector.

[0353] 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.

[0354] "Example 1"

[0355] One embodiment of the present invention is a system incorporating an emotion engine. This system recognizes a user's emotions and adjusts the behavior of an avatar account based on those emotions. Specifically, when a user feels happy, the avatar account posts a happy topic on social media that reflects that emotion. When a user feels sad, the avatar account sends comforting words to friends that reflect that emotion.

[0356] "Example 2"

[0357] In addition, systems that incorporate an emotion engine can recognize a user's emotions and tailor information and search results based on those emotions. For example, if a user is feeling stressed, the system can provide information about relaxation and meditation. If a user is feeling happy, the system can provide search results about fun events and news that reflect that emotion.

[0358] "Example 3"

[0359] Furthermore, a system that combines an emotion engine can recognize a user's emotions and automatically make the avatar account act based on those emotions. For example, when a user feels angry, the avatar account automatically posts on social media that reflects that emotion. Similarly, when a user feels surprised, the avatar account automatically reacts to a friend's post that reflects that emotion.

[0360] The processing flow of each embodiment will be described below.

[0361] "Example 1"

[0362] Step 1: The emotion engine recognizes the user's emotion.

[0363] Step 2: Adjust the avatar account's behavior based on the recognized emotion.

[0364] Step 3: For example, when a user feels happy, the avatar account posts happy topics on social media that reflect that emotion.

[0365] Step 4: Also, when a user is sad, the avatar account will send comforting words to their friends that reflect their emotions.

[0366] "Example 2"

[0367] Step 1: The emotion engine recognizes the user's emotion.

[0368] Step 2: Tailor your information and search results based on the perceived sentiment.

[0369] Step 3: For example, if the user is feeling stressed, the system will provide information on relaxation and meditation.

[0370] Step 4: Also, when a user is feeling joyful, the system will provide search results for fun events and news that reflect that emotion.

[0371] "Example 3"

[0372] Step 1: The emotion engine recognizes the user's emotion.

[0373] Step 2: Automatically perform actions on the avatar account based on the recognized emotion.

[0374] Step 3: For example, if a user feels angry, their avatar account will automatically post to social media reflecting that emotion.

[0375] Step 4: Also, when a user is feeling surprised, their avatar account will automatically react to their friends' posts to reflect that emotion.

[0376] Example 1

[0377] Next, a description will be given of Example 1 of Form 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."

[0378] Conventional information processing systems have difficulty in automating tasks that fully reflect the user's characteristics and emotions. When posting on social media, sending messages, or searching for information on behalf of the user, the systems are unable to accurately reflect the user's intentions and emotions. Furthermore, the systems are also inadequate in providing information and generating search results that reflect the user's preferences and tastes. This reduces user convenience and limits the usefulness of the system.

[0379] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for learning user characteristics and processing information on behalf of the user, a means for providing an avatar account that represents the user on a messenger app, a means for working with a generative AI to pre-learn the messenger app chat history, internet search history, and purchase history to realize a "conversational" and "push-type" avatar account with the same characteristics as the user, and a means for recognizing the user's emotions using an emotion engine and adjusting the behavior of the avatar account based on those emotions. This enables automation that accurately reflects the user's characteristics and emotions, thereby improving user convenience.

[0380] "User characteristics" refers to individual characteristics such as a user's behavioral patterns, preferences, tastes, and emotions.

[0381] "Information processing" refers to a series of operations such as collecting, analyzing, generating, and providing data.

[0382] A "messenger app" refers to software that enables users to send and receive text and multimedia messages.

[0383] "Avatar Account" refers to a virtual account that acts as a user's avatar and acts on the user's behalf.

[0384] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[0385] "Pre-learning" refers to the process of learning using data in advance for a specific task.

[0386] An "emotion engine" refers to software that analyzes a user's emotions and generates an appropriate response based on those emotions.

[0387] "Push" refers to a method of automatically providing information or notifications without waiting for a user request.

[0388] This invention is a system that learns user characteristics and processes information on behalf of the user. This system provides an avatar account that represents the user on a messenger app and learns the user's characteristics in cooperation with a generative AI. It also uses an emotion engine to recognize the user's emotions and adjusts the avatar account's behavior based on those emotions.

[0389] Hardware and software used

[0390] Hardware: Server, user device (smartphone, PC)

[0391] Software: Messenger apps, internet search tools, generative AI models (e.g., GPT-4), emotion engines

[0392] Data processing and calculation

[0393] Data collection: The server periodically collects the user's messenger app chat history, internet search history, and purchase history. Specifically, the server obtains chat history from the messenger app through APIs and search history from internet search tools. It also collects purchase history using the shopping site's API.

[0394] Data pre-training: The server uses the collected data to pre-train the generative AI model. During this process, it learns the user's characteristics and preferences. Specifically, the server pre-processes the collected data and tokenizes the text data. The data is then input into the generative AI model, which learns the user's characteristics and preferences.

[0395] Emotion recognition: The server uses an emotion engine to recognize the user's emotions in real time. Specifically, the server analyzes the latest messages received from the messenger app and inputs them into the emotion engine. The emotion engine analyzes the user's emotions from the content and tone of the message, identifying emotions such as "joy," "sadness," and "anger."

[0396] Action generation: The server combines the generative AI model and the emotion engine to generate an action based on the user's emotions. Specifically, the server inputs a prompt sentence into the generative AI model based on the emotion information obtained from the emotion engine. For example, the server inputs a prompt sentence such as "Please generate a fun topic to post on social media when the user is happy," and obtains the generated text.

[0397] Action execution: The server executes the generated action. Specifically, the server posts the generated text to a messenger app or social networking site. For example, if the user is happy, the server posts the generated happy story to the social networking site, and if the user is sad, the server sends the generated comforting words to a friend.

[0398] Specific examples

[0399] Example 1: When a user sends a message in a messenger app saying, "I'm so happy today!", the emotion engine recognizes the emotion as "joy." The generative AI model posts happy topics on social media based on the user's past chat history.

[0400] Example 2: If a user sends "I'm tired today," the emotion engine recognizes "fatigue" and "sadness." The generative AI model sends comforting words to the user's friends.

[0401] Prompt Sentence Examples

[0402] "Generate fun buzz for users to post on social media when they're happy."

[0403] "Generate words of comfort for users to send to friends when they're sad."

[0404] The above is an embodiment of the present invention.

[0405] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0406] Step 1: Data collection

[0407] The server periodically collects the user's chat history, internet search history, and purchase history from the messenger app. Specifically, the server obtains chat history from the messenger app through API, obtains search history from internet search tools, and collects purchase history using the API of the shopping site.

[0408] Input: Messenger app chat history, internet search history, purchase history

[0409] Output: Collected user data

[0410] Specific operation: The server calls the messenger app API at 2 AM every day to retrieve chat history, collects internet search history through a browser extension, and retrieves purchase history from a shopping site API once a week.

[0411] Step 2: Data pre-training

[0412] The server uses the collected data to pre-train the generative AI model, learning about the user's characteristics and preferences in the process.

[0413] Input: Collected user data

[0414] Output: A pre-trained generative AI model

[0415] How it works: The server saves the collected data in JSON format and stores it in a database. It then reads the data from the database and tokenizes the text data. It then inputs the data into a generative AI model, which learns the user's characteristics and preferences.

[0416] Step 3: Emotion Recognition

[0417] The server uses an emotion engine to recognize the user's emotions in real time. Specifically, the server analyzes the latest messages received from the messenger app and inputs them into the emotion engine.

[0418] Input: Latest Messenger app message

[0419] Output: User sentiment

[0420] How it works: The server retrieves the latest messages sent by the user in real time using the messenger app and inputs them into the emotion engine. The emotion engine analyzes the user's emotions from the content and tone of the message and identifies emotions such as "joy," "sadness," and "anger."

[0421] Step 4: Action Creation

[0422] The server combines the generative AI model and the emotion engine to generate actions based on the user's emotions. Specifically, the server inputs prompt sentences into the generative AI model based on the emotion information obtained from the emotion engine.

[0423] Input: User's emotional information

[0424] Output: Generated action text

[0425] Specific operation: Based on the emotional information obtained from the emotion engine, the server inputs the prompt sentence "Generate a fun topic to post on social media when the user is happy" into the generative AI model and obtains the generated text.

[0426] Step 5: Take Action

[0427] The server executes the generated action. Specifically, the server posts the generated text to a messenger app or social networking site.

[0428] Input: Generated action text

[0429] Output: The action taken (e.g., social media post, message sent, etc.)

[0430] Specific operation: The server posts the generated text to a messenger app or social networking site. For example, if the user is happy, the server posts the generated happy topic to the social networking site, and if the user is sad, the server sends the generated comforting words to a friend.

[0431] (Application example 1)

[0432] Next, a description will be given of Application Example 1 of Embodiment 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."

[0433] Conventional information processing systems have difficulty providing information and recommending products that fully reflect the user's characteristics and emotions, and have been unable to increase user satisfaction. Furthermore, users have had to spend time searching and organizing information themselves, making it difficult to efficiently obtain information. Furthermore, the inability to respond appropriately to the user's emotions has led to a decline in the quality of the user experience.

[0434] 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.

[0435] In this invention, the server includes: means for learning user characteristics and processing information on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for recognizing the user's emotions and adjusting the avatar account's behavior based on those emotions; and means for recommending products based on the user's emotions. This enables the provision of information and product recommendations that reflect the user's characteristics and emotions, thereby increasing user satisfaction. It also eliminates the need for users to search for and organize information themselves, enabling more efficient information acquisition. Furthermore, appropriate responses based on the user's emotions can be provided, improving the quality of the user experience.

[0436] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and emotions.

[0437] "Information processing" refers to a series of operations such as collecting, organizing, analyzing, and providing data.

[0438] A "messenger app" refers to a software application for sending and receiving text messages, images, audio, etc.

[0439] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[0440] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[0441] "Pre-training" refers to the process of training data in advance for a specific task.

[0442] "Emotion recognition" refers to technology that determines emotions from a user's text, voice, etc.

[0443] "Product recommendation" refers to the act of suggesting appropriate products based on the user's characteristics and emotions.

[0444] "Push" refers to a method of automatically providing information or notifications before the user requests them.

[0445] The system for implementing this invention learns user characteristics and processes information on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and works in conjunction with generative AI to pre-learn the user's chat history and internet search tool purchase history. This creates a "conversational" and "push-based" avatar account with the same characteristics as the user.

[0446] Hardware and software used

[0447] Hardware: Smartphone

[0448] Software: Python, Transformers library

[0449] Processing flow

[0450] 1. Emotion Recognition: The user's input text is fed into an emotion recognition model (Transformers' sentiment-analysis pipeline) to recognize the user's emotions. This allows us to identify what emotions the user is currently feeling.

[0451] 2. Product recommendation: Based on the recognized emotions, it recommends products based on the user's purchase history and search history. For example, if the user is happy, it will recommend special sale information, and if the user is sad, it will recommend relaxing products.

[0452] 3. Display recommended products: Display recommended products to users, so that users can easily find products that match their emotions.

[0453] Specific examples

[0454] If a user types, "I'm feeling really happy today!", the app will recommend "Sale Item 1" and "Sale Item 2."

[0455] If a user types, "I'm feeling sad today," the app will recommend "Relaxation Product 1" and "Relaxation Product 2."

[0456] Prompt Sentence Examples

[0457] Create a Python program that recognizes a user's emotions and recommends products based on those emotions. Input the user's input text into an emotion recognition model to recognize the user's emotions. Based on the recognized emotions, recommend products based on the user's purchase history and search history. For example, if the user is happy, recommend special sale information, and if the user is sad, recommend relaxing products.

[0458] In this way, it becomes possible to provide information and recommend products that reflect the user's characteristics and emotions, thereby increasing user satisfaction. It also saves the user the trouble of searching and organizing information themselves, allowing for more efficient information acquisition. Furthermore, it can respond appropriately to the user's emotions, improving the quality of the user experience.

[0459] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0460] Step 1:

[0461] A user types text into a messenger app.

[0462] Input: User's text message

[0463] Output: The text message entered

[0464] What happens: A user types text containing an emotion into a messenger app, such as "I'm feeling really happy today!"

[0465] Step 2:

[0466] The device sends the entered text message to the emotion recognition model.

[0467] Input: Typed text message

[0468] Output: Input data to the emotion recognition model

[0469] What it does: The device uses the sentiment-analysis pipeline in the Transformers library to send the input text message to an emotion recognition model.

[0470] Step 3:

[0471] The server recognizes the user's emotions using an emotion recognition model.

[0472] Input: Input data to the emotion recognition model

[0473] Output: Recognized emotion (e.g., happy, sad)

[0474] Specific operation: The server executes the emotion recognition model to determine the user's emotion from the input text message. For example, it recognizes the emotion "joy" from the text "I'm feeling very happy today!"

[0475] Step 4:

[0476] The server recommends products based on the recognized sentiment.

[0477] Input: Recognized emotions, user purchase history, search history

[0478] Output: Recommended products list

[0479] How it works: The server refers to the user's purchase and search history and selects appropriate products based on the recognized emotion. For example, for the emotion "joy," it recommends products with special sale information.

[0480] Step 5:

[0481] The server transmits a list of recommended products to the terminal.

[0482] Input: Recommended product list

[0483] Output: Product list data to the terminal

[0484] Specific operation: The server generates a list of recommended products and sends it to the terminal.

[0485] Step 6:

[0486] The terminal displays the recommended product list to the user.

[0487] Input: Product list data to the terminal

[0488] Output: The product list displayed to the user

[0489] Specific operation: The terminal displays the received product list to the user, allowing the user to check the products. For example, "Sale Product 1" and "Sale Product 2" are displayed.

[0490] Through the above steps, product recommendations based on the user's emotions can be realized, thereby increasing user satisfaction.

[0491] Example 2

[0492] Next, a description will be given of Example 2 of Form 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."

[0493] In today's information society, users need to process and manage a lot of information. However, this takes time and effort, placing a burden on users. In addition, there is a lack of information provided based on users' emotions and preferences, and users' needs cannot be fully met. Furthermore, there is no way to process information on behalf of users when they are absent or busy, which makes efficient information management difficult.

[0494] 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.

[0495] In this invention, the server includes means for learning user characteristics and processing information on behalf of the user, means for providing a virtual account that serves as the user's avatar on a communication application, means for working with a generative AI to pre-learn the communication application chat history and e-commerce tool purchase history to create a "conversational" and "push-type" virtual account with the same characteristics as the user, and means for analyzing the user's emotions using an emotion analysis engine and adjusting information provision and search results based on those emotions. This reduces the burden on the user, enables information provision based on the user's emotions and preferences, and realizes efficient information management.

[0496] "User characteristics" refers to individual characteristics such as a user's behavioral patterns, preferences, and emotions.

[0497] "Information processing" refers to a series of operations such as collecting, analyzing, organizing, and providing data.

[0498] "Communications application" refers to software that allows users to send and receive messages between users.

[0499] A "virtual account" refers to a digital proxy account created to process information on behalf of a user.

[0500] "Generative AI" refers to artificial intelligence that has the ability to generate new information and responses based on data.

[0501] "Pre-learning" refers to the process of pre-training a model with relevant data before it performs a specific task.

[0502] An "emotion analysis engine" refers to software that analyzes user emotions from data such as text and voice.

[0503] "Information provision" refers to the act of presenting necessary information to users.

[0504] "Search Results" refers to the list of information a user obtains using a search engine.

[0505] "Push" refers to a method in which information is provided automatically before the user requests it.

[0506] This invention is a system that learns user characteristics and processes information on behalf of the user. Specifically, it provides a virtual account that acts as the user's avatar on a communication application and learns the user's characteristics in cooperation with generative AI. It also uses an emotion analysis engine to analyze the user's emotions and adjusts the information provided and search results based on those emotions.

[0507] Hardware and software used

[0508] The server uses the following hardware and software:

[0509] Hardware: High-performance server machine

[0510] Software: Python, pandas, numpy, generative AI (e.g., GPT-4), sentiment analysis engine (e.g., IBM Watson's Tone Analyzer)

[0511] Data collection and preprocessing

[0512] The server retrieves conversation history using the API of the user's communication application and purchase history using the API of the e-commerce tool. This data is then stored in a secure database. Next, the data is preprocessed using Python's pandas library. Specifically, unnecessary information is removed and the data is normalized.

[0513] Feature extraction and model training

[0514] The server extracts features from the preprocessed data. For example, it uses natural language processing (NLP) techniques to extract the user's tone and frequently used phrases from their conversation history. It then analyzes the user's purchasing patterns and preferences from their purchase history. It then uses generative AI (GPT-4) to learn the user's characteristics. The preprocessed data and extracted features are input into a model to learn the user's conversation patterns and purchasing tendencies.

[0515] Generate Virtual Accounts

[0516] The server generates a virtual account with the user's characteristics on the communication application based on the learning results. Using the communication application's API, a new account is created and configured to have the user's characteristics. This virtual account can post information, send messages, and search for information on behalf of the user.

[0517] Sentiment analysis and information provision

[0518] The server uses an emotion analysis engine to analyze the user's emotions. When a user sends a message using a communication application, the server analyzes the tone of the message and provides relaxation information if the user is feeling stressed. If the user is feeling happy, the server provides search results of fun events and news that reflect that emotion.

[0519] Specific examples

[0520] User A provides conversation history with friend B on a communication application and purchase history on an e-commerce tool. The server collects this data and uses generative AI (GPT-4) to learn user A's characteristics. After learning is complete, the server generates a virtual account with user A's characteristics on the communication application. This virtual account can continue conversations with friend B on user A's behalf.

[0521] Prompt Sentence Examples

[0522] "Based on User A's conversation history in communication applications and purchase history in e-commerce tools, learn User A's characteristics and generate a virtual account that will converse and post information on User A's behalf."

[0523] In this way, the burden on the user is reduced, information can be provided based on the user's feelings and preferences, and efficient information management can be achieved.

[0524] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] The server retrieves the conversation history using the API of the user's communication application. It uses the user's authentication information and API endpoint as input and obtains the conversation history data as output. Specifically, the server sends an API request and receives the conversation history data in JSON format as a response.

[0527] Step 2:

[0528] The server obtains purchase history using the API of the e-commerce tool. It uses the user's authentication information and API endpoint as input and obtains purchase history data as output. Specifically, the server sends an API request and receives purchase history data in JSON format as a response.

[0529] Step 3:

[0530] The server preprocesses the acquired conversation history and purchase history. It uses the conversation history data and purchase history data as input and obtains the preprocessed data as output. Specifically, the server uses the Python pandas library to remove unnecessary information and normalize the data.

[0531] Step 4:

[0532] The server extracts features from the preprocessed data. It uses the preprocessed conversation history data and purchase history data as input and obtains extracted feature data as output. Specifically, the server uses natural language processing (NLP) techniques to extract conversational tones and frequently used phrases and analyze purchasing patterns.

[0533] Step 5:

[0534] The server uses generative AI (GPT-4) to learn user characteristics. It uses the extracted feature data as input and obtains a trained model as output. Specifically, the server inputs the feature data into the model and has it learn the user's conversation patterns and purchasing tendencies.

[0535] Step 6:

[0536] The server generates a virtual account with the user's characteristics on the communication application based on the learning results. It uses the trained model and the communication application's API endpoint as input and obtains the virtual account as output. Specifically, the server sends an API request to create a new account and configure it with the user's characteristics.

[0537] Step 7:

[0538] The server analyzes the user's emotions using an emotion analysis engine. It uses the user's message data as input and obtains the emotion analysis result as output. Specifically, the server inputs the message data into the emotion analysis engine and analyzes the emotional tone.

[0539] Step 8:

[0540] The server adjusts the information provided and search results based on the emotion analysis results. It uses the emotion analysis results and user characteristic data as input and obtains adjusted information provided and search results as output. Specifically, the server provides relaxation information and fun event information based on the emotion analysis results.

[0541] (Application example 2)

[0542] Next, a description will be given of Application Example 2 of Form 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."

[0543] Conventional systems have difficulty providing information and recommending content that fully reflects the user's characteristics and emotions, making it impossible to provide services that meet the user's needs. It has also been difficult to create an avatar account that posts on social media, sends messages, or searches the web on behalf of the user. This has led to problems such as reduced user convenience and satisfaction.

[0544] 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.

[0545] In this invention, the server includes: means for learning user characteristics and performing SNS, web searches, information organization, etc. on behalf of the user; means for providing an avatar account that represents the user on a messenger app; means for linking with a generative AI and pre-learning the messenger app chat history and internet search tool shopping purchase history to realize a "conversational" and "push-type" avatar account with the same characteristics as the user; means for analyzing the user's emotions and adjusting the information provision and search results based on those emotions; and means for recommending content based on the user's characteristics and emotions. This makes it possible to provide information and recommend content that reflects the user's characteristics and emotions, and to realize an avatar account that posts on SNS, sends messages, and performs web searches on behalf of the user.

[0546] "User characteristics" refers to the preferences, tastes, and behavioral patterns of individual users extracted from their behavioral history, purchasing history, conversation history, etc.

[0547] An "avatar account" is a virtual account that automatically performs actions such as posting on social media, sending messages, and searching the web on behalf of the user.

[0548] "Generative AI" refers to artificial intelligence technology that generates new information and content based on user data.

[0549] "Pre-learning" refers to the process in which generative AI learns a user's characteristics based on their past behavioral and purchasing history.

[0550] "Sentiment analysis" refers to the technology of analyzing a user's emotional state from their conversation history and behavioral data.

[0551] "Information provision" refers to the act of providing information appropriate to a user based on the user's characteristics and emotions.

[0552] "Content recommendation" refers to the act of recommending content suitable for a user based on the user's characteristics and emotions.

[0553] "Push" refers to a method of automatically providing information or content before the user requests it.

[0554] The system for implementing this invention has the ability to learn user characteristics and perform functions such as social media, web searches, and information organization on behalf of the user. The system provides an avatar account that represents the user on a messenger app, and works in conjunction with generative AI to pre-learn the user's messenger app chat history and internet search tool shopping history. This allows for the creation of a "conversational" and "push-based" avatar account with the same characteristics as the user.

[0555] The server has the ability to analyze user emotions and tailor information provision and search results based on those emotions, as well as recommend content based on user characteristics and emotions.

[0556] Hardware and software used

[0557] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[0558] Software: Messenger apps, generative AI models (e.g., OpenAI GPT-3), sentiment analysis libraries (e.g., NLTK, TextBlob), content recommendation engines (e.g., TENSORFLOW® Recommenders)

[0559] Data processing and calculation

[0560] 1. Data acquisition: The user's device sends the conversation history of the messenger app and the purchase history of the internet search tool to the server.

[0561] 2. Learning user characteristics: The server uses a generative AI model to learn user characteristics from the acquired data.

[0562] 3. Sentiment analysis: The server uses a sentiment analysis library to analyze emotions from the user's conversation history.

[0563] 4. Information provision and content recommendation: The server provides appropriate information and content to the user's device based on the user's characteristics and emotions.

[0564] Specific examples

[0565] For example, if a user says to a friend on a messenger app, "I've been busy at work lately and I'm feeling stressed," the server retrieves this conversation history and uses a sentiment analysis library to analyze that the user is feeling stressed. Furthermore, the server checks the user's purchasing history to see if they have purchased books related to relaxation, and uses a generative AI model to learn the user's characteristics.

[0566] Prompt Sentence Examples

[0567] User conversation history: Work has been busy and stressful lately.

[0568] User purchase history: Purchased books related to relaxation.

[0569] Learn the characteristics of this user.

[0570] By inputting this prompt into a generative AI model, it can learn the user's characteristics and recommend appropriate relaxation content.

[0571] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0572] Step 1:

[0573] The user terminal transmits the conversation history of the messenger app and the purchase history of the internet search tool to the server.

[0574] Input: User conversation history, purchase history

[0575] Output: User data sent to the server

[0576] Specific operation: The user device obtains conversation history using the API of the messenger app and purchase history using the API of the internet search tool, and sends this data to the server.

[0577] Step 2:

[0578] The server inputs the received user data into a generative AI model to learn the user's characteristics.

[0579] Input: User data sent to the server

[0580] Output: Learned user characteristics

[0581] Specific operation: The server generates prompts for a generative AI model (e.g., OpenAI GPT-3) and learns the user's characteristics based on the user's conversation history and purchase history. An example of a prompt is "User's conversation history: I've been busy at work recently and feeling stressed. User's purchase history: I bought a book related to relaxation. Please learn the characteristics of this user."

[0582] Step 3:

[0583] The server uses a sentiment analysis library to analyze emotions from the user's conversation history.

[0584] Input: User's conversation history

[0585] Output: Parsed user emotional state

[0586] What it does: The server uses a sentiment analysis library (e.g., NLTK, TextBlob) to analyze the user's conversation history and identify the emotions the user is feeling (e.g., stress, joy).

[0587] Step 4:

[0588] The server recommends appropriate information and content based on the user's characteristics and emotions.

[0589] Input: Learned user characteristics, analyzed user emotional state

[0590] Output: Recommended information or content

[0591] Specific operation: The server uses a content recommendation engine (e.g., TensorFlow Recommenders) to select appropriate information and content based on the user's characteristics and emotions and send it to the user's device.

[0592] Step 5:

[0593] The user terminal displays the recommended information and content received from the server.

[0594] Input: Recommended information or content

[0595] Output: Information or content displayed to the user

[0596] Specific operation: The user device displays the information and content received from the server on the messenger app or browser and provides it to the user.

[0597] Example 3

[0598] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0599] Conventional information provision systems and search engines have been unable to fully reflect the characteristics and preferences of users, making it difficult to provide optimal information for users. Furthermore, because information provision and behavioral automation do not take into account user emotions, it has been difficult to increase user satisfaction.

[0600] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes a means for providing an avatar account that represents the user, a means for working with a generative AI to pre-learn the user's behavioral history and create an avatar account with the same characteristics as the user, and a means for analyzing the user's emotions in real time using an emotion recognition engine and automatically performing actions on the avatar account based on the results. This makes it possible to provide information and generate search results that reflect the user's characteristics and preferences, and further realizes automation of actions that take the user's emotions into consideration.

[0601] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and interests.

[0602] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[0603] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[0604] "Pre-learning" refers to the process of learning user behavioral history and data in advance.

[0605] An "emotion recognition engine" refers to technology that analyzes emotions from a user's facial expressions, tone of voice, etc.

[0606] "Real-time" refers to data collection and processing occurring immediately.

[0607] "Information provision" refers to the act of presenting useful information to users.

[0608] "Search results" refers to the list of related information that is displayed when a user performs a search.

[0609] "Automated actions" refers to a system automatically performing a specific action on behalf of a user.

[0610] This invention is a system that learns user characteristics and provides information and generates search results on behalf of the user. The system provides an avatar account that represents the user and works with generative AI to pre-learn the user's behavioral history. It also uses an emotion recognition engine to analyze the user's emotions in real time and automatically controls the avatar account's behavior based on the results.

[0611] Hardware and software used

[0612] Hardware: Servers, terminals (PCs, smartphones)

[0613] Software: Generative AI models (e.g., GPT-4), emotion recognition engines (e.g., Affectiva), social media APIs (e.g., Twitter API, Facebook API)

[0614] Data processing and calculation

[0615] 1. Data Collection:

[0616] The server collects data such as users' social media posts, message transmissions, web search history, etc. Specifically, it uses the Twitter API and Facebook API to obtain users' posts and search history.

[0617] The device collects real-time emotional data from users using an emotion recognition engine, which uses the device's camera and microphone to analyze the user's facial expressions and tone of voice.

[0618] 2. Data Analysis:

[0619] The server inputs the collected data into a generative AI model to learn the user's characteristics and preferences. Specifically, it analyzes the user's posts and search history to identify topics of interest.

[0620] The generative AI model learns the user's characteristics based on the input data and generates a profile.

[0621] 3. Information provision and search results generation:

[0622] The server generates appropriate information and search results based on the learned user characteristics and preferences, specifically providing news articles and product information that may be of interest to the user.

[0623] The generative AI model generates relevant information based on the user's profile.

[0624] 4. Emotion Recognition and Avatar Account Behavior:

[0625] The device uses an emotion recognition engine to analyze the user's emotions in real time and transmits the results to the server.

[0626] Based on the results of the emotion recognition engine, the server instructs the avatar account to automatically take actions that reflect the user's emotions.

[0627] Specific examples

[0628] Example 1: If a user frequently posts about "travel" on social media

[0629] The server learns the user's travel preferences and prioritizes providing travel-related information and search results.

[0630] Example prompt for a generative AI model: "You frequently post about travel. Please provide travel-related information."

[0631] Example 2: When the user feels angry

[0632] The device uses an emotion recognition engine to detect when the user is feeling anger and sends the results to the server.

[0633] The server sends instructions to the avatar account saying, "The user is feeling angry. Please generate a social media post that reflects that anger."

[0634] The generative AI model generates "social media posts for angry users," which are then automatically posted by avatar accounts.

[0635] In this way, the system takes into consideration the characteristics and emotions of the user, and realizes optimal information provision and automation of actions. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0636] Step 1: Data collection

[0637] The server collects data such as users' social media posts, message transmissions, web search history, etc. Specifically, it uses the Twitter API and Facebook API to obtain users' posts and search history.

[0638] Input: User data obtained from SNS API (post content, search history, etc.)

[0639] Output: Collected user data

[0640] Specific operation: The server periodically calls the SNS API to obtain the user's latest post data.

[0641] Step 2: Collecting Emotional Data

[0642] The device collects real-time emotional data from users using an emotion recognition engine, which uses the device's camera and microphone to analyze the user's facial expressions and tone of voice.

[0643] Input: Real-time facial and voice data from the device's camera and microphone

[0644] Output: User emotion data analyzed by the emotion recognition engine

[0645] Specific operation: While the user is using the smartphone, the device collects facial expression data through the camera and sends it to the emotion recognition engine.

[0646] Step 3: Data analysis

[0647] The server inputs the collected data into a generative AI model to learn the user's characteristics and preferences. Specifically, it analyzes the user's posts and search history to identify topics of interest.

[0648] Input: Collected user data (posts, search history, etc.)

[0649] Output: A profile that reflects the user's characteristics and preferences

[0650] Specific operation: The server inputs the collected social media posting data into the generative AI model and analyzes it using the prompt, "What topics do users frequently post about?"

[0651] Step 4: Providing information and generating search results

[0652] The server generates appropriate information and search results based on the learned user characteristics and preferences, specifically providing news articles and product information that may be of interest to the user.

[0653] Input: A profile that reflects the user's characteristics and preferences

[0654] Output: Information or search results provided to the user

[0655] Specific operation: Based on the profile that "the user is interested in travel," the server searches for travel-related news articles and provides them to the user.

[0656] Step 5: Emotion Recognition and Avatar Account Behavior

[0657] The device uses an emotion recognition engine to analyze the user's emotions in real time and transmits the results to the server.

[0658] Based on the results of the emotion recognition engine, the server instructs the avatar account to automatically take actions that reflect the user's emotions.

[0659] Input: User emotion data analyzed by the emotion recognition engine

[0660] Output: Automatic actions performed by the avatar account (e.g., posting to social media, sending messages)

[0661] Specific operation: The device uses an emotion recognition engine to detect that the user is feeling angry and sends the result to the server. The server then sends an instruction to the avatar account saying, "The user is feeling angry. Please generate a social media post that reflects that anger." The generative AI model then generates a "social media post for the user who is feeling angry," and the avatar account automatically posts it.

[0662] (Application example 3)

[0663] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0664] Conventional avatar account systems were unable to provide information or generate search results that reflected the user's preferences and tastes, and were unable to automatically act based on the user's emotions. Furthermore, they lacked the functionality to recommend optimal content based on the user's emotions and tastes, making it difficult to improve the user experience.

[0665] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes: means for learning user characteristics and performing SNS / web searches / information organization on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for linking with a generative AI and pre-learning the messenger app chat history and internet search tool shopping history to realize a "conversational" and "push-type" avatar account with the same characteristics as the user; means for recognizing the user's emotions in real time using an emotion engine and automatically controlling the avatar account's behavior based on those emotions; and means for automatically recommending optimal content based on the user's emotions and preferences. This makes it possible to provide information, generate search results, and recommend optimal content based on the user's emotions and preferences.

[0666] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, tastes, and emotions.

[0667] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[0668] "Generative AI" refers to artificial intelligence that learns user behavior and characteristics and generates information based on that.

[0669] "Messenger app chat history" refers to a user's conversation history within the Messenger app.

[0670] "Internet search tool shopping purchase history" refers to the shopping history of a user using an Internet search tool.

[0671] "Pre-learning" refers to the process in which generative AI learns in advance using the user's past behavioral data.

[0672] An "emotion engine" refers to a system that recognizes a user's emotions in real time and determines actions based on those emotions.

[0673] "Content" refers to information and entertainment such as videos, articles, and music.

[0674] "Recommendation" refers to the act of selecting and presenting the most appropriate content based on the user's characteristics and emotions.

[0675] The system for implementing this invention has the ability to learn user characteristics and perform social media, web searches, information organization, etc. on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and works in conjunction with generative AI to pre-learn the messenger app chat history and internet search tool shopping history. This pre-learning allows for the creation of a "conversational" and "push-type" avatar account with the same characteristics as the user.

[0676] Furthermore, the system uses an emotion engine to recognize users' emotions in real time and automatically adjusts the avatar account's behavior based on those emotions. It also includes a function to automatically recommend the most suitable content based on the user's emotions and preferences.

[0677] Program processing explanation

[0678] The server runs programs for emotion recognition and content recommendation using Python. For emotion recognition, TextBlob is used to analyze the user's text data. To learn the user's preferences, the text data is vectorized using scikit-learn's TfidfVectorizer, and the optimal content is recommended by calculating the cosine similarity.

[0679] Hardware and software used

[0680] Hardware: Smartphone

[0681] Software: Python, TextBlob, scikit-learn

[0682] Specific examples

[0683] For example, if a user posts, "I'm so tired today," sentiment analysis will detect negative emotions and the system will recommend relaxing music and videos.

[0684] Prompt Sentence Examples

[0685] User post: "I'm so tired today"

[0686] User preferences: ["I like movies", "I like music", "I like traveling"]

[0687] Recommended content: ["Relaxing music", "Exciting movies", "Travel blogs"]

[0688] By inputting this prompt into a generative AI model, it is possible to recommend optimal content based on the user's emotions and preferences.

[0689] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0690] Step 1:

[0691] The server collects the user's chat history on messenger apps and their shopping history on internet search tools. This data is entered as the user's behavioral history. The server saves this data in text format for later processing.

[0692] Step 2:

[0693] The server uses the collected data to learn user characteristics. Specifically, it uses Python's scikit-learn library to vectorize text data using TfidfVectorizer. This vectorized data is output as features representing the user's preferences.

[0694] Step 3:

[0695] The server uses TextBlob to recognize user emotions in real time. It receives text data posted by users to the messenger app as input and performs sentiment analysis using TextBlob. The result of the sentiment analysis is an emotional score: positive, negative, or neutral.

[0696] Step 4:

[0697] The server uses an emotion engine to determine the behavior of the avatar account based on the user's emotions. It receives the emotion score as input and configures it to recommend relaxing content for negative emotions and exciting content for positive emotions. This configuration is output as the avatar account's behavioral guidelines.

[0698] Step 5:

[0699] The server recommends optimal content based on the user's preferences and emotions. Specifically, it receives features representing the user's preferences and emotion scores as input, and selects the most suitable content using scikit-learn's cosine similarity calculation. This recommended content is then output as information provided to the user.

[0700] Step 6:

[0701] The device presents the content recommended by the server to the user. The user can check the recommended content on the smartphone screen and use it as needed. In this step, the recommended content is displayed on the user's device.

[0702] Step 7:

[0703] The user uses the recommended content and sends their feedback to the server, which then receives this feedback and stores it in a database to be used for future recommendations. This feedback is then used to further learn about the user's characteristics.

[0704] 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.

[0705] The data generation model 58 is a so-called generative AI (Artificial Intelligence).

[0706] An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generative AIs. Data generation models 58

[0707] The data generation model 58 receives a prompt containing an instruction, and also receives inference data such as voice data representing a voice, text data representing a text, and image data representing an image.

[0708] The data generation model 58 performs inference on the input inference data according to the instructions given by the prompts, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0709] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0710] 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.

[0711] [Second embodiment]

[0712] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0713] 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.

[0714] 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).

[0715] 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.

[0716] 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.

[0717] 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).

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0724] "Example 1"

[0725] One embodiment of the present invention provides a system that learns user characteristics and performs social networking, web searches, information organization, and other functions on behalf of the user. Specifically, an avatar account that represents the user is provided on a messenger app. This avatar account pre-learns the user's messenger app chat history and internet search tool shopping history, and by linking with generative AI, it creates a "conversational" and "push-based" avatar account with the same characteristics as the user.

[0726] "Example 2"

[0727] As a specific example, User A provides his / her conversation history with Friend B on a messenger app and his / her purchase history on Amazon as pre-learning data. Based on this data, the system works with generative AI to learn User A's characteristics. After learning is complete, the system provides an avatar account on the messenger app that will represent User A. This avatar account will be a "push-type" avatar account with the same characteristics as User A, capable of "conversation," and will be able to post on social media, send messages, and perform web searches on User A's behalf.

[0728] "Example 3"

[0729] Another embodiment of the present invention provides a function for providing information and generating search results that reflect a user's preferences and tastes. Specifically, an avatar account is provided that automatically performs actions such as posting to social media, sending messages, and web searches. This avatar account can learn the user's characteristics and generate information and search results that reflect those characteristics.

[0730] The processing flow of each embodiment will be described below.

[0731] "Example 1"

[0732] Step 1: The user provides the system with their conversation history with friends on the messenger app and their purchase history on Amazon.

[0733] Step 2: Based on the data provided, the system works with generative AI to learn the user's characteristics.

[0734] Step 3: After learning is complete, the system will provide the user with an avatar account on the Messenger app.

[0735] Step 4: This avatar account will be a "conversational" and "push-type" avatar account with the same characteristics as the user, and will be able to post on social media, send messages, search the web, and more on behalf of the user.

[0736] "Example 2"

[0737] Step 1: The user provides the system with behavioral data such as social media posts, messaging, and web searches.

[0738] Step 2: The system learns the user's characteristics based on the data provided.

[0739] Step 3: After the learning is complete, the system will provide the user with an avatar account.

[0740] Step 4: This avatar account can generate information and search results that reflect the user's characteristics.

[0741] Example 1

[0742] Next, a description will be given of Example 1 of Form 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."

[0743] In today's information society, users need to efficiently collect and organize vast amounts of information. However, doing this manually takes time and effort, and is inefficient. In addition, while there is a demand for information to be provided based on the user's characteristics and preferences, it is difficult to fully realize this with conventional systems. Furthermore, when users use multiple information and communication services and search tools, there is a lack of a way to centrally manage and utilize the history and characteristics of each. A system that can solve these issues is needed.

[0744] 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.

[0745] In this invention, the server includes: means for learning user characteristics and providing information and communication services, information search, information organization, etc. on behalf of the user; means for providing a virtual account that serves as the user's avatar on the information and communication application; means for cooperating with a generative AI and pre-learning the information and communication application history, internet search tools, and purchase history to realize a "conversational" and "push-type" virtual account with the same characteristics as the user; means for pre-processing collected data and extracting user characteristics; means for training a generative AI model using the extracted characteristics; and means for collecting related information based on the user's interests and preferences and sending push notifications through the virtual account. This enables the provision of information and the generation of search results based on the user's characteristics and preferences, significantly improving the efficiency of users' information collection and organization.

[0746] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and interests.

[0747] "Information and communication services" refers to communication methods such as messaging, social networking services, and email provided via the Internet.

[0748] "Information search" refers to the act of finding specific information on the Internet.

[0749] "Information organization" refers to the act of classifying and organizing collected information to make it easier to use.

[0750] "Information and communication applications" refers to software that allows users to send and receive messages and share information.

[0751] A "virtual account" refers to a digital alter ego that acts on a user's behalf on an information and communication application.

[0752] "Generative AI" refers to artificial intelligence technology that learns the characteristics of a user and generates responses and behaviors similar to that user's.

[0753] "Pre-learning" refers to the process of pre-training a generative AI model using collected data.

[0754] "Conversational" refers to the virtual account's ability to engage in natural dialogue with the user.

[0755] "Push" refers to the function of automatically notifying users of relevant information based on their interests and concerns.

[0756] "Preprocessing" refers to the process of preparing collected data in a form that is easy to analyze.

[0757] "Feature extraction" refers to the act of extracting features such as user interests and preferences from preprocessed data.

[0758] "Training" refers to the process of training a generative AI model using extracted characteristics.

[0759] "Push notification" refers to the function of sending information to users in real time.

[0760] This invention is a system that learns user characteristics and performs information communication services, information search, information organization, etc. on behalf of the user. Specific embodiments of this system are described below.

[0761] 1. System Overview

[0762] The server learns user characteristics and provides a system for providing information and communication services, information search, information organization, etc. on behalf of the user. This system provides a virtual account that serves as the user's avatar on the information and communication application, and works in conjunction with generative AI.

[0763] 2. Hardware and Software Used

[0764] The server uses the following hardware and software:

[0765] Hardware: High-performance server machine, database server

[0766] Software: Information and communication applications, generative AI models, data analysis tools, push notification systems

[0767] 3. Data collection and pre-training

[0768] The server collects the user's information and communication application history, internet search tool history, and purchase history. This data serves as the basis for learning user characteristics. The collected data is preprocessed to remove unnecessary data and normalize the data.

[0769] Next, user characteristics are extracted from the preprocessed data. Natural language processing techniques are used to analyze the text data and identify the user's interests. The extracted characteristics are used to train a generative AI model. This pre-training allows the generative AI model to understand the user's characteristics and generate responses that resemble the user's.

[0770] 4. Creating and Configuring Virtual Accounts

[0771] The server uses a pre-trained generative AI model to generate a virtual account that reflects the user's characteristics. This virtual account can then converse on behalf of the user on information and communication applications. The virtual account also has the ability to push notifications of relevant information based on the user's interests.

[0772] 5. Specific Examples

[0773] Example 1: Travel planning

[0774] When a user is planning a trip with friends using an information and communication application, the server will provide information on suitable travel destinations and accommodations based on past travel history and search history. For example, it may suggest places that the user has visited in the past that the friend might be interested in.

[0775] Example 2: Providing shopping information

[0776] If a user is interested in a particular brand, the server collects information about new products from that brand and sends push notifications through the virtual account. For example, the server can instantly notify users when new products from a brand they have previously purchased are released.

[0777] 6. Examples of prompts

[0778] "Based on the user's information and communication application history and internet search history, please generate a virtual account that provides information about travel destinations that the user is interested in. Also, please implement a function to send push notifications with the latest information about those travel destinations."

[0779] In this way, a system is realized that learns the characteristics of the user and provides information and communication services, searches for information, and organizes information on behalf of the user.

[0780] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0781] Step 1: Data collection

[0782] The server collects the user's information and communication application history, internet search tool history, and purchase history.

[0783] Input: User's information and communication application history, internet search history, purchase history

[0784] Data processing: Collected data is stored in a database for centralized management.

[0785] Output: User behavior history data stored in a database

[0786] Specific operation: The server obtains data from information and communication applications and Internet search tools via API and stores it in a database.

[0787] Step 2: Preprocessing the data

[0788] The server pre-processes the collected data.

[0789] Input: User behavior history data stored in a database

[0790] Data processing: Removal of unnecessary data, data normalization, tokenization of text data

[0791] Output: A preprocessed, clean dataset

[0792] Specific operation: The server uses a data cleansing tool to remove noise data and prepare the text data in a form that is easy to analyze.

[0793] Step 3: Feature extraction

[0794] The server extracts user characteristics from the preprocessed data.

[0795] Input: Preprocessed clean dataset

[0796] Data processing: Analyze text data using natural language processing techniques to identify user interests and concerns

[0797] Output: A feature vector that describes the user's characteristics

[0798] Specific operation: The server uses a natural language processing library to analyze the text data and extract the user's interests and concerns.

[0799] Step 4: Training the generative AI model

[0800] The server uses the extracted features to train a generative AI model.

[0801] Input: A feature vector that describes the user's characteristics

[0802] Data processing: Input feature vectors into the generative AI model and train the model

[0803] Output: A generative AI model that learns user characteristics

[0804] How it works: The server uses a machine learning framework to train a generative AI model to learn the user's characteristics.

[0805] Step 5: Generate Virtual Accounts

[0806] The server uses a pre-trained generative AI model to generate a virtual account that reflects the user's characteristics.

[0807] Input: A generative AI model that learns user characteristics

[0808] Data processing: Using generative AI models to create virtual accounts and register them in information and communication applications

[0809] Output: Virtual account on information and communication application

[0810] Specific operation: The server generates a virtual account using the generative AI model and registers it in the information and communication application through the API.

[0811] Step 6: Implementing Push Notifications

[0812] The server collects relevant information based on the user's interests and pushes it to the user through the virtual account.

[0813] Input: User interest data, external sources

[0814] Data processing: Collecting relevant information and formatting it in a way that is appropriate for the user

[0815] Output: Push notification message

[0816] Specific operation: The server collects relevant information from external information sources and sends push notifications to users through virtual accounts.

[0817] In this way, a system is realized that learns the characteristics of the user and provides information and communication services, searches for information, and organizes information on behalf of the user.

[0818] (Application example 1)

[0819] Next, a description will be given of Application Example 1 of Form 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."

[0820] It is difficult for modern consumers to find the best product for them from the vast amount of information available, and it takes time and effort. In addition, there is a lack of personalized product suggestions based on the user's characteristics and preferences, making it difficult for consumers to find products that suit them. Furthermore, there is no system that can search social media or the web or organize information on behalf of the user, so users have to collect information themselves, which is an issue.

[0821] 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.

[0822] In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account that represents the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for learning the user's purchase history and search history and automatically suggesting products that match the user's preferences; and means for suggesting products based on the user's history using a generative AI model. This allows users to easily find the products that are best suited to them and reduces the effort required for information gathering.

[0823] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and purchasing history.

[0824] "SNS" is an abbreviation for social networking service, an online platform where users can share information and communicate with other users.

[0825] "Web search" refers to the act of finding information on the Internet using a search engine.

[0826] "Information organization" refers to the act of classifying collected information and organizing it into an easy-to-understand format.

[0827] A "messenger app" is application software that allows users to send and receive text messages, images, audio, etc.

[0828] An "avatar account" is a virtual account that functions as a user's alter ego and communicates and collects information on behalf of the user.

[0829] "Generative AI" refers to artificial intelligence technology that generates new information and suggestions based on user input and historical data.

[0830] "Pre-learning" refers to the process in which the system learns the user's past behavioral history and data in advance.

[0831] "Push" refers to a method in which the system automatically provides information or suggestions before the user requests them.

[0832] "Purchase history" refers to a record of products a user has purchased in the past.

[0833] "Search history" refers to a record of keywords or phrases a user has previously searched for on a search engine.

[0834] A "generative AI model" refers to an artificial intelligence algorithm that generates new information and suggestions based on a user's historical data.

[0835] As an embodiment of this invention, we provide a system that learns user characteristics and performs SNS, web searches, information organization, etc. on behalf of the user. Specifically, we provide an avatar account that represents the user on a messenger app, and in cooperation with generative AI, pre-learn the user's messenger app chat history and internet search tool shopping history. This avatar account is a "conversational" and "push-type" avatar account with the same characteristics as the user.

[0836] The server learns the user's purchase and search history and automatically suggests products that match the user's preferences. Using a generative AI model, it suggests products based on the user's history. This system allows users to easily find the products that best suit them, eliminating the need to gather information.

[0837] Hardware and software used

[0838] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[0839] Software: Messenger apps, generative AI models (e.g., OpenAI GPT-3)

[0840] Data processing and calculation

[0841] The server collects the user's chat history from messenger apps, internet search tools, and shopping purchase history, and pre-trains this data. A generative AI model is used to analyze the user's history data and learn their characteristics and preferences. This allows it to automatically suggest products that match the user's preferences.

[0842] Specific examples

[0843] If a user has previously purchased a smartphone or wireless earphones and is searching for the latest smartphone or high-quality earphones, the generative AI model will suggest products related to the latest smartphones or high-quality earphones.

[0844] Prompt Sentence Examples

[0845] User purchase history: ["smartphone", "wireless earphones"]

[0846] User search history: ["latest smartphone", "high quality earphones"]

[0847] Suggest a product that you would recommend to this user.

[0848] In this way, a personal shopping assistant can be realized that automatically suggests products that match the user's preferences.

[0849] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0850] Step 1:

[0851] The server collects users' chat history, internet search results, and shopping history. This data is used as input to learn about users' characteristics and preferences. Specifically, the server obtains data from each platform via API and stores it in a database.

[0852] Input: Messenger app chat history, internet search tools, shopping purchase history

[0853] Output: User history data stored in a database

[0854] Step 2:

[0855] The server pre-trains the collected user history data. During this pre-training process, a generative AI model is used to analyze the data and learn the user's characteristics and preferences. Specifically, the historical data is input into the AI ​​model to extract the user's behavioral patterns and preferences.

[0856] Input: User history data stored in a database

[0857] Output: A model that reflects the user's characteristics and preferences

[0858] Step 3:

[0859] The server uses a generative AI model to suggest products based on the user's history. In this process, a prompt sentence is generated to suggest the most suitable product based on the user's purchase history and search history, and input into the AI ​​model. The AI ​​model then generates product suggestions based on the prompt sentence.

[0860] Input: A model that reflects the user's characteristics and preferences, prompts

[0861] Output: Product proposal

[0862] Step 4:

[0863] The server sends the generated product suggestions to the user's device, where the user can check the suggested products through a messenger app or a dedicated app. Specifically, the product suggestions are sent to the user's device via API and displayed on the user interface.

[0864] Input: Product proposal

[0865] Output: Product suggestions displayed on the user's device

[0866] Step 5:

[0867] The user reviews the suggested products and purchases them if necessary. In this process, the user receives the product suggestions, selects the products they are interested in, and then completes the purchase process by selecting the products through the user interface and clicking the purchase button.

[0868] Input: Product suggestions displayed on the user's device

[0869] Output: User purchase behavior

[0870] In this way, we have created a system that automatically makes product suggestions based on the user's characteristics and preferences, allowing users to easily find the products that are best suited to them.

[0871] Example 2

[0872] Next, a description will be given of Example 2 of Form 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."

[0873] Conventional information processing systems have had difficulty providing automated information and communication that fully reflects the user's characteristics. It has also been difficult to create an avatar account that posts to social media, sends messages, searches the web, and so on, on behalf of the user. This has increased the burden on the user and hindered efficient information processing.

[0874] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for learning user characteristics and processing information on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for linking with a generative AI model and pre-learning the conversation history of the messenger app and the purchase history of online shopping to realize a "conversational" and "push-type" avatar account with the same characteristics as the user; means for pre-processing data stored in a database, cleaning and tokenizing text data; and means for inputting prompt sentences into the generative AI model and sending generated messages. This enables automated information provision and communication that reflects the user's characteristics.

[0875] "User characteristics" refers to individual characteristics such as a user's behavioral patterns, preferences, and tastes.

[0876] "Information processing" refers to a series of operations such as collecting, analyzing, storing, retrieving, and generating data.

[0877] An "avatar account" refers to a virtual account that acts online on behalf of a user.

[0878] A "generative AI model" refers to an artificial intelligence model that generates new information or content based on given data.

[0879] "Pre-training" refers to the process of training a model using data in advance for a specific task.

[0880] "Conversational" refers to the ability to engage in natural dialogue on behalf of the user.

[0881] "Push" refers to a format in which information is provided automatically without waiting for a user request.

[0882] A "database" refers to a system for efficiently storing, managing, and retrieving data.

[0883] "Preprocessing" refers to the initial processing of data to convert it into a form suitable for analysis and learning.

[0884] "Cleaning" refers to the process of removing unnecessary information or noise from data.

[0885] "Tokenization" refers to the process of breaking down text data into words and phrases.

[0886] A "prompt sentence" refers to an input sentence that causes a generative AI model to generate a specific output.

[0887] The present invention is a system that learns user characteristics and processes information on behalf of the user. Specific embodiments of this system will be described below.

[0888] The server receives the conversation history of the messenger app and the purchase history of online shopping provided by the user. This data is used as pre-learning data to learn the characteristics of the user. The server stores this data in a database. The database uses a relational database such as MySQL or PostgreSQL.

[0889] The server then preprocesses the stored data, which includes cleaning the text data (removing unnecessary characters and noise) and tokenizing it (dividing it into words and phrases), using the Python NLTK and spaCy libraries.

[0890] After preprocessing, the data is input into a generative AI model (for example, OpenAI's GPT-4). The server uses this generative AI model to learn the user's characteristics. During this learning process, the model is updated to reflect the user's conversation patterns and purchasing tendencies. Once learning is complete, the server generates a model that incorporates the user's characteristics.

[0891] The server then generates an avatar account with the user's characteristics based on the trained model. This avatar account can then converse on the user's behalf on the messenger app. Specifically, the avatar account inputs prompts into the generative AI model and sends the generated messages to friends.

[0892] As a concrete example, consider a situation where a user provides a conversation history with a friend, for example, by providing the following prompt sentence to a generative AI model:

[0893] Prompt: "Generate a message for a user to send to a friend. The user recently purchased a new smartphone and wants to tell their friend about their experience with it."

[0894] The generative AI model generates messages like this:

[0895] Generated message: "Hi, friend! I recently bought a new smartphone and it's so easy to use. The camera in particular is amazing and it takes great photos. If your friend is also thinking about buying a new smartphone, I highly recommend it!"

[0896] In this way, avatar accounts can send messages to friends that reflect the user's characteristics. Avatar accounts can also post on social media and perform web searches. This reduces the burden on users and enables more efficient information processing.

[0897] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0898] Step 1: Data collection

[0899] The server receives the user's conversation history from the messenger app and the user's online shopping purchase history. This data is used as pre-learning data to learn the user's characteristics. The input is the conversation history and purchase history provided by the user, and the output is the raw data stored in the database. Specifically, the server receives the data uploaded by the user and stores it in the database.

[0900] Step 2: Data Preprocessing

[0901] The server preprocesses the stored data. This preprocessing includes cleaning the text data (removing unnecessary characters and noise) and tokenizing it (dividing it into words and phrases). The input is the raw data stored in the database, and the output is the preprocessed, clean data. Specifically, the server uses Python's NLTK and spaCy libraries to clean and tokenize the text data.

[0902] Step 3: Trait learning

[0903] The server inputs the preprocessed data into a generative AI model to learn the user's characteristics. The input is preprocessed, clean data, and the output is a trained model that reflects the user's characteristics. Specifically, the server uses a generative AI model (for example, OpenAI's GPT-4) to learn the user's conversation patterns and purchasing tendencies.

[0904] Step 4: Create an avatar account

[0905] The server generates an avatar account with the user's characteristics based on the trained model. The input is the trained model, and the output is the avatar account. Specifically, the server creates an avatar account that can converse on behalf of the user on the messenger app based on the output of the generative AI model.

[0906] Step 5: Avatar Account in Action

[0907] The avatar account inputs a prompt into the generative AI model and sends the generated message to a friend. The input is the prompt, and the output is the generated message. Specifically, the avatar account inputs the following prompt into the generative AI model:

[0908] Prompt: "Generate a message for a user to send to a friend. The user recently purchased a new smartphone and wants to tell their friend about their experience with it."

[0909] The generative AI model generates messages like this:

[0910] Generated message: "Hi, friend! I recently bought a new smartphone and it's so easy to use. The camera in particular is amazing and it takes great photos. If your friend is also thinking about buying a new smartphone, I highly recommend it!"

[0911] The avatar account will then send this message to friends, enabling automated information provision and communication that reflects the user's characteristics.

[0912] (Application example 2)

[0913] Next, a description will be given of Application Example 2 of Form 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."

[0914] Conventional social networking sites and messaging apps require users to collect information and post or send messages themselves, which takes time and effort. Furthermore, there is a lack of effective ways to deliver advertisements that reflect the characteristics and preferences of users. This creates a need to improve user convenience while maximizing the effectiveness of advertisements.

[0915] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping and purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; and means for the avatar that has learned the user's characteristics to post advertisements on SNS and messenger apps on behalf of the user. This enables automatic information collection and posting on behalf of the user, improving user convenience and enabling effective advertisement delivery that reflects the user's characteristics and preferences.

[0916] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and tastes.

[0917] "SNS" is an abbreviation for social networking service, which refers to an online platform where users can share information and communicate with other users.

[0918] "Web search" refers to the act of finding information on the Internet using a search engine.

[0919] "Information organization" refers to the act of classifying and organizing collected information.

[0920] A "messenger app" refers to an application that allows users to send and receive text messages, images, videos, etc.

[0921] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[0922] "Generative AI" refers to artificial intelligence that generates new information and content based on given data.

[0923] "Pre-training" refers to the process of pre-training a model with relevant data before it performs a specific task.

[0924] "Conversational" refers to the ability to have a natural dialogue with the user.

[0925] "Push" refers to a method in which information is provided automatically before the user requests it.

[0926] "Posting an advertisement" refers to the act of publishing information about a specific product or service on social media or a messaging app.

[0927] The system for implementing this invention learns user characteristics and performs SNS, web searches, information organization, etc. on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and by working with generative AI to pre-learn the messenger app chat history and internet search tool shopping history, it realizes a "conversational" and "push-type" avatar account with the same characteristics as the user.

[0928] The server first obtains the user's conversation history and purchase history on the messenger app. This data is collected using the APIs of the messenger app and shopping site. The server then uses generative AI to learn the user's characteristics based on this data. Specifically, the conversation history and purchase history are input as prompts into the generative AI model, allowing it to learn the user's characteristics.

[0929] After the learning is complete, the server generates an avatar account with the user's characteristics, and this avatar posts advertisements on social media and messenger apps on the user's behalf. This makes it possible to automatically collect and post information on the user's behalf, improving user convenience and enabling effective advertisement delivery that reflects the user's characteristics and preferences.

[0930] The hardware used includes servers and user devices (smartphones, tablets, PCs, etc.), while the software used includes messenger apps, shopping site APIs, generative AI (e.g., OpenAI APIs), etc.

[0931] As a concrete example, consider the case where the user ID is "user123" and the ad content is "Check out this amazing product!" In this case, the server would do the following:

[0932] 1. The server obtains the conversation history and purchase history of user ID "user123".

[0933] 2. The server uses generative AI to learn the characteristics of "user123" based on the acquired data.

[0934] 3. The server uses the learned user model to post an ad on social media saying, "Check out this amazing product!"

[0935] Example prompts to input to a generative AI model:

[0936] Train a model based on the following data: [Conversation history and purchase history data]

[0937] This prompt is used to train a generative AI model to learn the user's characteristics.

[0938] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0939] Step 1:

[0940] The server obtains the user's conversation history and purchase history on the messenger app. Specifically, it uses the API of the messenger app or shopping site to collect the conversation history and purchase history related to the user ID. The input is the user ID, and the output is the conversation history and purchase history data.

[0941] Step 2:

[0942] The server uses generative AI to learn the user's characteristics based on the acquired conversation history and purchase history. Specifically, the conversation history and purchase history are input as prompts into the generative AI model, which then learns the user's characteristics. The input is conversation history and purchase history data, and the output is a model that reflects the user's characteristics.

[0943] Step 3:

[0944] The server generates an avatar account based on the learned user model. Specifically, it uses generative AI to create an avatar account with the user's characteristics and provides it to the messenger app. The input is the user model, and the output is the avatar account.

[0945] Step 4:

[0946] The server posts advertisements on social media and messenger apps using the avatar account. Specifically, it generates advertisement content that reflects the user's characteristics and posts it using the SNS or messenger app's API. The input is a user model and advertisement content, and the output is an advertisement posted on the SNS or messenger app.

[0947] Step 5:

[0948] The server monitors the effectiveness of the ads and updates the user model as necessary. Specifically, it collects data such as ad click-through rates and engagement rates, and uses generative AI to retrain the user model. The input is ad performance data, and the output is an updated user model.

[0949] Example 3

[0950] Next, a description will be given of Example 3 of Form Example 3. 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."

[0951] Conventional information provision systems and search engines have been unable to fully reflect users' preferences and tastes, making it difficult to provide users with the most appropriate information. In addition, users have to search for and organize information themselves, which makes it difficult to efficiently gather information.

[0952] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes: means for learning user characteristics and providing information and generating search results on behalf of the user; means for providing a virtual account on a messaging application that acts as a proxy for the user; means for working with a generative AI to pre-learn the messaging application chat history and internet search tool purchase history and realize an "interactive" and "push-type" virtual account with the same characteristics as the user; means for collecting user behavioral data and analyzing the data using natural language processing technology; means for generating a profile reflecting the user's preferences and tastes based on the analysis results; means for the virtual account to automatically provide information and perform searches based on the generated profile; and means for generating customized information and search results based on the behavioral results of the virtual account. This makes it possible to provide optimal information and generate search results that reflect the user's preferences and tastes.

[0953] "User characteristics" refers to individual characteristics such as a user's preferences, tastes, behavioral patterns, and interests.

[0954] "Information provision" refers to the act of providing useful information to users.

[0955] "Search Results" means the list of information returned in response to a search conducted by a user on the Internet.

[0956] "Messaging application" means software that enables users to send and receive text and multimedia messages.

[0957] "Virtual Account" refers to a digital account that acts on behalf of a user.

[0958] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[0959] "Pre-training" refers to the process by which the system learns using the user's past data.

[0960] "Interactive" refers to a system's ability to engage in natural dialogue with the user.

[0961] "Push" refers to a method in which the system automatically provides information without waiting for a user request.

[0962] "Behavioral Data" refers to data about user actions (e.g., social media posts, search history, message sending, etc.).

[0963] "Natural language processing technology" refers to technology for understanding, analyzing, and generating human language.

[0964] A "profile" refers to a collection of data generated based on a user's characteristics and behavioral patterns.

[0965] "Customized Information" refers to information that is individually tailored based on a user's characteristics and preferences.

[0966] MODE FOR CARRYING OUT THE INVENTION

[0967] The present invention is a system that learns user characteristics and provides information and generates search results on behalf of the user. A specific embodiment of this system is described below.

[0968] 1. Generating the system program

[0969] The server generates a program to provide information and generate search results that reflect the user's preferences and tastes. This program has the function of managing a virtual account that automatically performs actions such as posting to social media, sending messages, and web searches.

[0970] 2. Explanation of program processing

[0971] The server performs the following processing using the generated program.

[0972] 1. Data Collection:

[0973] The server collects data such as users' social media posts, message transmissions, and web search history. This data collection is obtained from each social media platform and search engine via API. Specifically, it uses the Twitter API and Google Search API.

[0974] 2. Data Analysis:

[0975] The server uses natural language processing (NLP) techniques to analyze the collected data, specifically using software such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0976] 3. Create a user profile:

[0977] The server uses the analysis results to create a profile that reflects the user's preferences and tastes, including topics and keywords that interest the user.

[0978] 4. Virtual account behavior simulation:

[0979] The server then generates a virtual account that automatically posts on social media, sends messages, and performs web searches based on the generated user profile. This simulation uses a generative AI model (e.g., OpenAI's GPT-4).

[0980] 5. Information provision and search results generation:

[0981] The server generates customized information and search results for the user based on the behavior of the virtual account, and the information is presented in a form that best suits the user's preferences and tastes.

[0982] 3. Examples of concrete examples and prompts

[0983] Examples:

[0984] Let's say User A is interested in traveling. The server extracts keywords such as "travel," "tourist spots," and "hotels" from User A's social media posts and web search history. Based on this, a virtual account automatically posts travel-related information on social media and searches travel blogs. Finally, it provides User A with information on recommended tourist spots and hotels.

[0985] Example prompt sentence:

[0986] "To provide User A with travel-related information that interests him, please suggest recommended tourist spots and hotels based on his social media posts and web search history."

[0987] In this way, the server realizes a system for providing information and generating search results that reflect the user's preferences and tastes. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0988] Step 1: Data collection

[0989] The server collects data such as users' social media posts, message transmissions, and web search history. Specifically, it retrieves users' tweets using the Twitter API and collects users' search history using the Google Search API. The input is the user's account information, and the output is the collected behavioral data.

[0990] Step 2: Data analysis

[0991] The server uses natural language processing (NLP) technology to analyze the collected data. Specifically, it uses the Google Cloud Natural Language API to extract keywords from users' tweets and search history and perform sentiment analysis. The input is the collected behavioral data, and the output is the analyzed keywords and sentiment information.

[0992] Step 3: Generate a user profile

[0993] The server generates a profile that reflects the user's preferences and tastes based on the analysis results. Specifically, it creates a list of topics and keywords that interest the user based on the extracted keywords and the results of sentiment analysis. The input is the analyzed keywords and sentiment information, and the output is the generated user profile.

[0994] Step 4: Simulating virtual account behavior

[0995] The server automatically posts to social media, sends messages, and performs web searches using virtual accounts based on the generated user profile. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-4) to generate social media posts based on the user's interests and search related websites. The input is the user profile, and the output is the behavioral results of the virtual account.

[0996] Step 5: Providing information and generating search results

[0997] The server generates customized information and search results for users based on the behavioral results of the virtual accounts. Specifically, it organizes the information collected by the virtual accounts and provides users with information on recommended tourist spots and hotels. The input is the behavioral results of the virtual accounts, and the output is customized information and search results.

[0998] (Application example 3)

[0999] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1000] Conventional systems have had difficulty providing information and generating search results that accurately reflect a user's tastes and preferences. They also required users to post on social media, send messages, and search the web themselves, which was time-consuming and labor-intensive. Furthermore, the recommendation function for suggesting the most suitable products to users was insufficient, preventing users from increasing their purchasing motivation. To solve these issues, a system is needed that can automate user behavior, learn user characteristics, and provide optimal information and product suggestions.

[1001] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1002] In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account on a messenger app that represents the user; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for analyzing the user's SNS posts, message sending, and web search history to learn the user's tastes and preferences; means for suggesting optimal products to the user; means for automatically posting product reviews and questions; and means for making recommendations based on purchase history. This makes it possible to automate user behavior, learn the user's characteristics, and provide optimal information and product suggestions.

[1003] "User characteristics" refers to individual characteristics such as a user's preferences, tastes, and behavioral patterns.

[1004] "SNS" is an abbreviation for social networking service, which refers to a platform where users can interact with other users online.

[1005] "Web search" refers to the act of finding information on the Internet using a search engine.

[1006] "Information organization" refers to the process of classifying and organizing collected data and information to make it easier to use.

[1007] A "messenger app" refers to application software for sending and receiving text messages, images, videos, etc.

[1008] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[1009] "Generative AI" refers to artificial intelligence technology that generates new information and content based on data.

[1010] "Pre-training" refers to the process of pre-training a model with relevant data before it performs a specific task.

[1011] "Push" refers to a method in which information is provided automatically before the user requests it.

[1012] "SNS posting" refers to the act of publishing content such as text, images, and videos on social networking services.

[1013] "Sending a message" refers to the act of sending text messages, images, videos, etc. to other users.

[1014] "Web search history" refers to a record of searches a user has conducted on the Internet in the past.

[1015] "Product suggestion" refers to the act of recommending appropriate products based on a user's preferences and tastes.

[1016] A "product review" refers to the act of writing an evaluation or opinion on a purchased product.

[1017] "Recommendation" refers to a system that recommends appropriate products and services based on a user's past behavior and preferences.

[1018] A system for implementing this invention learns user characteristics and performs social networking, web searches, information organization, etc. on behalf of the user. The system provides an avatar account that represents the user on a messenger app and works in conjunction with generative AI. Specific embodiments of the system are described below.

[1019] System configuration

[1020] The system consists of the following main components:

[1021] 1. User device: A device such as a smartphone or tablet with a messenger app installed.

[1022] 2. Server: Collects and analyzes user data and uses generative AI models to provide information and product suggestions.

[1023] 3. Generative AI model: An AI model that analyzes users' social media posts, messaging, and web search history to learn their preferences and tastes.

[1024] Program processing

[1025] The server implements the system using the following means:

[1026] 1. Learning user characteristics: The server collects users' social media posts, messages, and web search history, and uses a generative AI model to learn their characteristics. Specifically, it converts text data into TF-IDF vectors and analyzes their preferences and tastes.

[1027] 2. Providing avatar accounts: Create an avatar account on the messenger app that represents the user, and post to social media and send messages on the user's behalf.

[1028] 3. Information provision and product suggestions: The server provides optimal information and product suggestions based on the user's characteristics. Specifically, it makes recommendations based on the user's purchase history and search history.

[1029] 4. Auto-posting: Avatar accounts automatically post product reviews and questions on behalf of users.

[1030] Hardware and software used

[1031] Hardware: User devices (smartphones, tablets), servers

[1032] Software: Messenger app, generative AI models (e.g., sklearn's TfidfVectorizer, cosine_similarity)

[1033] Specific examples

[1034] For example, if a user posts on social media that they want a new smartphone, the system will collect this information and learn their preferences. Next, if the user frequently searches for "high-performance laptops" online, the system will use this information to suggest the best products. Additionally, avatar accounts will automatically post product reviews and questions, organizing information on the user's behalf.

[1035] Prompt Sentence Examples

[1036] Build an application that analyzes users' social media posts, messages, and web search history to learn their preferences and tastes and recommend the best products. Retrieve user data from an API and analyze the text data using TF-IDF vectors. Use cosine similarity to recommend products.

[1037] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1038] Step 1:

[1039] The user's device collects the user's social media posts, messages, and web search history. This data serves as input data for learning the user's preferences and tastes. Specifically, the system collects text posted on social media, text sent via messaging apps, URLs and search queries from the user's web search history.

[1040] Step 2:

[1041] The server inputs the collected user data into a generative AI model. The generative AI model uses this data to learn user characteristics. Specifically, it converts text data into TF-IDF vectors and analyzes user preferences and tastes. The input data is in text format, and the output is vector data representing the user's characteristics.

[1042] Step 3:

[1043] The server creates an avatar account on the messenger app that represents the user. This avatar account posts on social media and sends messages on behalf of the user. Specifically, the avatar account posts text generated based on the user's characteristics. The input data is the user's characteristic vector, and the output is the text to post on social media or send a message.

[1044] Step 4:

[1045] The server provides optimal information and product suggestions based on the user's characteristics. Specifically, it makes recommendations based on the user's purchase history and search history. The input data is the user's characteristic vector, purchase history, and search history, and the output is a list of recommended products.

[1046] Step 5:

[1047] The avatar account automatically posts product reviews and questions on behalf of the user. Specifically, it generates reviews and questions for recommended products and posts them from the avatar account. The input data is a list of recommended products, and the output is the text of the product reviews and questions.

[1048] Step 6:

[1049] The server continuously monitors user behavior, collects new data, and updates the generative AI model, keeping the user's characteristics up to date. The input data is the newly collected user data, and the output is the updated user's characteristic vector.

[1050] 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.

[1051] "Example 1"

[1052] One embodiment of the present invention is a system incorporating an emotion engine. This system recognizes a user's emotions and adjusts the behavior of an avatar account based on those emotions. Specifically, when a user feels happy, the avatar account posts a happy topic on social media that reflects that emotion. When a user feels sad, the avatar account sends comforting words to friends that reflect that emotion.

[1053] "Example 2"

[1054] In addition, systems that incorporate an emotion engine can recognize a user's emotions and tailor information and search results based on those emotions. For example, if a user is feeling stressed, the system can provide information about relaxation and meditation. If a user is feeling happy, the system can provide search results about fun events and news that reflect that emotion.

[1055] "Example 3"

[1056] Furthermore, a system that combines an emotion engine can recognize a user's emotions and automatically make the avatar account act based on those emotions. For example, when a user feels angry, the avatar account automatically posts on social media that reflects that emotion. Similarly, when a user feels surprised, the avatar account automatically reacts to a friend's post that reflects that emotion.

[1057] The processing flow of each embodiment will be described below.

[1058] "Example 1"

[1059] Step 1: The emotion engine recognizes the user's emotion.

[1060] Step 2: Adjust the avatar account's behavior based on the recognized emotion.

[1061] Step 3: For example, when a user feels happy, the avatar account posts happy topics on social media that reflect that emotion.

[1062] Step 4: Also, when a user is sad, the avatar account will send comforting words to their friends that reflect their emotions.

[1063] "Example 2"

[1064] Step 1: The emotion engine recognizes the user's emotion.

[1065] Step 2: Tailor your information and search results based on the perceived sentiment.

[1066] Step 3: For example, if the user is feeling stressed, the system will provide information on relaxation and meditation.

[1067] Step 4: Also, when a user is feeling joyful, the system will provide search results for fun events and news that reflect that emotion.

[1068] "Example 3"

[1069] Step 1: The emotion engine recognizes the user's emotion.

[1070] Step 2: Automatically perform actions on the avatar account based on the recognized emotion.

[1071] Step 3: For example, if a user feels angry, their avatar account will automatically post to social media reflecting that emotion.

[1072] Step 4: Also, when a user is feeling surprised, their avatar account will automatically react to their friends' posts to reflect that emotion.

[1073] Example 1

[1074] Next, a description will be given of Example 1 of Form 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."

[1075] Conventional information processing systems have difficulty in automating tasks that fully reflect the user's characteristics and emotions. When posting on social media, sending messages, or searching for information on behalf of the user, the systems are unable to accurately reflect the user's intentions and emotions. Furthermore, the systems are also inadequate in providing information and generating search results that reflect the user's preferences and tastes. This reduces user convenience and limits the usefulness of the system.

[1076] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for learning user characteristics and processing information on behalf of the user, a means for providing an avatar account that represents the user on a messenger app, a means for working with a generative AI to pre-learn the messenger app chat history, internet search history, and purchase history to realize a "conversational" and "push-type" avatar account with the same characteristics as the user, and a means for recognizing the user's emotions using an emotion engine and adjusting the behavior of the avatar account based on those emotions. This enables automation that accurately reflects the user's characteristics and emotions, thereby improving user convenience.

[1077] "User characteristics" refers to individual characteristics such as a user's behavioral patterns, preferences, tastes, and emotions.

[1078] "Information processing" refers to a series of operations such as collecting, analyzing, generating, and providing data.

[1079] A "messenger app" refers to software that enables users to send and receive text and multimedia messages.

[1080] "Avatar Account" refers to a virtual account that acts as a user's avatar and acts on the user's behalf.

[1081] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[1082] "Pre-learning" refers to the process of learning using data in advance for a specific task.

[1083] An "emotion engine" refers to software that analyzes a user's emotions and generates an appropriate response based on those emotions.

[1084] "Push" refers to a method of automatically providing information or notifications without waiting for a user request.

[1085] This invention is a system that learns user characteristics and processes information on behalf of the user. This system provides an avatar account that represents the user on a messenger app and learns the user's characteristics in cooperation with a generative AI. It also uses an emotion engine to recognize the user's emotions and adjusts the avatar account's behavior based on those emotions.

[1086] Hardware and software used

[1087] Hardware: Server, user device (smartphone, PC)

[1088] Software: Messenger apps, internet search tools, generative AI models (e.g., GPT-4), emotion engines

[1089] Data processing and calculation

[1090] Data collection: The server periodically collects the user's messenger app chat history, internet search history, and purchase history. Specifically, the server obtains chat history from the messenger app through APIs and search history from internet search tools. It also collects purchase history using the shopping site's API.

[1091] Data pre-training: The server uses the collected data to pre-train the generative AI model. During this process, it learns the user's characteristics and preferences. Specifically, the server pre-processes the collected data and tokenizes the text data. The data is then input into the generative AI model, which learns the user's characteristics and preferences.

[1092] Emotion recognition: The server uses an emotion engine to recognize the user's emotions in real time. Specifically, the server analyzes the latest messages received from the messenger app and inputs them into the emotion engine. The emotion engine analyzes the user's emotions from the content and tone of the message, identifying emotions such as "joy," "sadness," and "anger."

[1093] Action generation: The server combines the generative AI model and the emotion engine to generate an action based on the user's emotions. Specifically, the server inputs a prompt sentence into the generative AI model based on the emotion information obtained from the emotion engine. For example, the server inputs a prompt sentence such as "Please generate a fun topic to post on social media when the user is happy," and obtains the generated text.

[1094] Action execution: The server executes the generated action. Specifically, the server posts the generated text to a messenger app or social networking site. For example, if the user is happy, the server posts the generated happy story to the social networking site, and if the user is sad, the server sends the generated comforting words to a friend.

[1095] Specific examples

[1096] Example 1: When a user sends a message in a messenger app saying, "I'm so happy today!", the emotion engine recognizes the emotion as "joy." The generative AI model posts happy topics on social media based on the user's past chat history.

[1097] Example 2: If a user sends "I'm tired today," the emotion engine recognizes "fatigue" and "sadness." The generative AI model sends comforting words to the user's friends.

[1098] Prompt Sentence Examples

[1099] "Generate fun buzz for users to post on social media when they're happy."

[1100] "Generate words of comfort for users to send to friends when they're sad."

[1101] The above is an embodiment of the present invention.

[1102] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1103] Step 1: Data collection

[1104] The server periodically collects the user's chat history, internet search history, and purchase history from the messenger app. Specifically, the server obtains chat history from the messenger app through API, obtains search history from internet search tools, and collects purchase history using the API of the shopping site.

[1105] Input: Messenger app chat history, internet search history, purchase history

[1106] Output: Collected user data

[1107] Specific operation: The server calls the messenger app API at 2 AM every day to retrieve chat history, collects internet search history through a browser extension, and retrieves purchase history from a shopping site API once a week.

[1108] Step 2: Data pre-training

[1109] The server uses the collected data to pre-train the generative AI model, learning about the user's characteristics and preferences in the process.

[1110] Input: Collected user data

[1111] Output: A pre-trained generative AI model

[1112] How it works: The server saves the collected data in JSON format and stores it in a database. It then reads the data from the database and tokenizes the text data. It then inputs the data into a generative AI model, which learns the user's characteristics and preferences.

[1113] Step 3: Emotion Recognition

[1114] The server uses an emotion engine to recognize the user's emotions in real time. Specifically, the server analyzes the latest messages received from the messenger app and inputs them into the emotion engine.

[1115] Input: Latest Messenger app message

[1116] Output: User sentiment

[1117] How it works: The server retrieves the latest messages sent by the user in real time using the messenger app and inputs them into the emotion engine. The emotion engine analyzes the user's emotions from the content and tone of the message and identifies emotions such as "joy," "sadness," and "anger."

[1118] Step 4: Action Creation

[1119] The server combines the generative AI model and the emotion engine to generate actions based on the user's emotions. Specifically, the server inputs prompt sentences into the generative AI model based on the emotion information obtained from the emotion engine.

[1120] Input: User's emotional information

[1121] Output: Generated action text

[1122] Specific operation: Based on the emotional information obtained from the emotion engine, the server inputs the prompt sentence "Generate a fun topic to post on social media when the user is happy" into the generative AI model and obtains the generated text.

[1123] Step 5: Take Action

[1124] The server executes the generated action. Specifically, the server posts the generated text to a messenger app or social networking site.

[1125] Input: Generated action text

[1126] Output: The action taken (e.g., social media post, message sent, etc.)

[1127] Specific operation: The server posts the generated text to a messenger app or social networking site. For example, if the user is happy, the server posts a generated happy topic to the social networking site, and if the user is sad, the server sends a generated message of comfort to a friend.

[1128] (Application example 1)

[1129] Next, a description will be given of Application Example 1 of Form 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."

[1130] Conventional information processing systems have difficulty providing information and recommending products that fully reflect the user's characteristics and emotions, and have been unable to increase user satisfaction. Furthermore, users have had to spend time searching and organizing information themselves, making it difficult to efficiently obtain information. Furthermore, the inability to respond appropriately to the user's emotions has led to a decline in the quality of the user experience.

[1131] 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.

[1132] In this invention, the server includes: means for learning user characteristics and processing information on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for recognizing the user's emotions and adjusting the avatar account's behavior based on those emotions; and means for recommending products based on the user's emotions. This enables the provision of information and product recommendations that reflect the user's characteristics and emotions, thereby increasing user satisfaction. It also eliminates the need for users to search for and organize information themselves, enabling more efficient information acquisition. Furthermore, appropriate responses based on the user's emotions can be provided, improving the quality of the user experience.

[1133] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and emotions.

[1134] "Information processing" refers to a series of operations such as collecting, organizing, analyzing, and providing data.

[1135] A "messenger app" refers to a software application for sending and receiving text messages, images, audio, etc.

[1136] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[1137] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[1138] "Pre-training" refers to the process of training data in advance for a specific task.

[1139] "Emotion recognition" refers to technology that determines emotions from a user's text, voice, etc.

[1140] "Product recommendation" refers to the act of suggesting appropriate products based on the user's characteristics and emotions.

[1141] "Push" refers to a method of automatically providing information or notifications before the user requests them.

[1142] The system for implementing this invention learns user characteristics and processes information on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and works with generative AI to pre-learn the user's chat history and internet search tool purchase history. This creates a "conversational" and "push-based" avatar account with the same characteristics as the user.

[1143] Hardware and software used

[1144] Hardware: Smartphone

[1145] Software: Python, Transformers library

[1146] Processing flow

[1147] 1. Emotion Recognition: The user's input text is fed into an emotion recognition model (Transformers' sentiment-analysis pipeline) to recognize the user's emotions. This allows us to identify what emotions the user is currently feeling.

[1148] 2. Product recommendation: Based on the recognized emotions, it recommends products based on the user's purchase history and search history. For example, if the user is happy, it will recommend special sale information, and if the user is sad, it will recommend relaxing products.

[1149] 3. Display recommended products: Display recommended products to users, so that users can easily find products that match their emotions.

[1150] Specific examples

[1151] If a user types, "I'm feeling really happy today!", the app will recommend "Sale Item 1" and "Sale Item 2."

[1152] If a user types, "I'm feeling sad today," the app will recommend "Relaxation Product 1" and "Relaxation Product 2."

[1153] Prompt Sentence Examples

[1154] Create a Python program that recognizes a user's emotions and recommends products based on those emotions. Input the user's input text into an emotion recognition model to recognize the user's emotions. Based on the recognized emotions, recommend products based on the user's purchase history and search history. For example, if the user is happy, recommend special sale information, and if the user is sad, recommend relaxing products.

[1155] In this way, it becomes possible to provide information and recommend products that reflect the user's characteristics and emotions, thereby increasing user satisfaction. It also saves the user the trouble of searching and organizing information themselves, allowing for more efficient information acquisition. Furthermore, it can respond appropriately to the user's emotions, improving the quality of the user experience.

[1156] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1157] Step 1:

[1158] A user types text into a messenger app.

[1159] Input: User's text message

[1160] Output: The text message entered

[1161] What happens: A user types text containing an emotion into a messenger app, such as "I'm feeling really happy today!"

[1162] Step 2:

[1163] The device sends the entered text message to the emotion recognition model.

[1164] Input: Typed text message

[1165] Output: Input data to the emotion recognition model

[1166] What it does: The device uses the sentiment-analysis pipeline in the Transformers library to send the input text message to an emotion recognition model.

[1167] Step 3:

[1168] The server recognizes the user's emotions using an emotion recognition model.

[1169] Input: Input data to the emotion recognition model

[1170] Output: Recognized emotion (e.g., happy, sad)

[1171] Specific operation: The server executes the emotion recognition model to determine the user's emotion from the input text message. For example, it recognizes the emotion "joy" from the text "I'm feeling very happy today!"

[1172] Step 4:

[1173] The server recommends products based on the recognized sentiment.

[1174] Input: Recognized emotions, user purchase history, search history

[1175] Output: Recommended products list

[1176] How it works: The server refers to the user's purchase and search history and selects appropriate products based on the recognized emotion. For example, for the emotion "joy," it recommends products with special sale information.

[1177] Step 5:

[1178] The server sends a list of recommended products to the terminal.

[1179] Input: Recommended product list

[1180] Output: Product list data to the terminal

[1181] Specific operation: The server generates a list of recommended products and sends it to the terminal.

[1182] Step 6:

[1183] The terminal displays the recommended product list to the user.

[1184] Input: Product list data to the terminal

[1185] Output: The product list displayed to the user

[1186] Specific operation: The terminal displays the received product list to the user, allowing the user to check the products. For example, "Sale Item 1" and "Sale Item 2" are displayed.

[1187] Through the above steps, product recommendations based on the user's emotions can be realized, thereby increasing user satisfaction.

[1188] Example 2

[1189] Next, a description will be given of Example 2 of Form 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."

[1190] In today's information society, users need to process and manage a lot of information. However, this takes time and effort, placing a burden on users. In addition, there is a lack of information provided based on users' emotions and preferences, and users' needs cannot be fully met. Furthermore, there is no way to process information on behalf of users when they are absent or busy, which makes efficient information management difficult.

[1191] 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.

[1192] In this invention, the server includes means for learning user characteristics and processing information on behalf of the user, means for providing a virtual account that serves as the user's avatar on a communication application, means for working with a generative AI to pre-learn the communication application chat history and e-commerce tool purchase history to create a "conversational" and "push-type" virtual account with the same characteristics as the user, and means for analyzing the user's emotions using an emotion analysis engine and adjusting information provision and search results based on those emotions. This reduces the burden on the user, enables information provision based on the user's emotions and preferences, and realizes efficient information management.

[1193] "User characteristics" refers to individual characteristics such as a user's behavioral patterns, preferences, and emotions.

[1194] "Information processing" refers to a series of operations such as collecting, analyzing, organizing, and providing data.

[1195] "Communications application" refers to software that allows users to send and receive messages between users.

[1196] A "virtual account" refers to a digital proxy account created to process information on behalf of a user.

[1197] "Generative AI" refers to artificial intelligence that has the ability to generate new information and responses based on data.

[1198] "Pre-learning" refers to the process of pre-training a model with relevant data before it performs a specific task.

[1199] An "emotion analysis engine" refers to software that analyzes user emotions from data such as text and voice.

[1200] "Information provision" refers to the act of presenting necessary information to users.

[1201] "Search Results" refers to the list of information a user obtains using a search engine.

[1202] "Push" refers to a method in which information is provided automatically before the user requests it.

[1203] This invention is a system that learns user characteristics and processes information on behalf of the user. Specifically, it provides a virtual account that acts as the user's avatar on a communication application and learns the user's characteristics in cooperation with generative AI. It also uses an emotion analysis engine to analyze the user's emotions and adjusts the information provided and search results based on those emotions.

[1204] Hardware and software used

[1205] The server uses the following hardware and software:

[1206] Hardware: High-performance server machine

[1207] Software: Python, pandas, numpy, generative AI (e.g., GPT-4), sentiment analysis engine (e.g., IBM Watson's Tone Analyzer)

[1208] Data collection and preprocessing

[1209] The server retrieves conversation history using the API of the user's communication application and purchase history using the API of the e-commerce tool. This data is then stored in a secure database. Next, the data is preprocessed using Python's pandas library. Specifically, unnecessary information is removed and the data is normalized.

[1210] Feature extraction and model training

[1211] The server extracts features from the preprocessed data. For example, it uses natural language processing (NLP) techniques to extract the user's tone and frequently used phrases from their conversation history. It then analyzes the user's purchasing patterns and preferences from their purchase history. It then uses generative AI (GPT-4) to learn the user's characteristics. The preprocessed data and extracted features are input into a model to learn the user's conversation patterns and purchasing tendencies.

[1212] Generate Virtual Accounts

[1213] The server generates a virtual account with the user's characteristics on the communication application based on the learning results. Using the communication application's API, a new account is created and configured to have the user's characteristics. This virtual account can post information, send messages, and search for information on behalf of the user.

[1214] Sentiment analysis and information provision

[1215] The server uses an emotion analysis engine to analyze the user's emotions. When a user sends a message using a communication application, the server analyzes the tone of the message and provides relaxation information if the user is feeling stressed. If the user is feeling happy, the server provides search results of fun events and news that reflect that emotion.

[1216] Specific examples

[1217] User A provides conversation history with friend B on a communication application and purchase history on an e-commerce tool. The server collects this data and uses generative AI (GPT-4) to learn user A's characteristics. After learning is complete, the server generates a virtual account with user A's characteristics on the communication application. This virtual account can continue conversations with friend B on user A's behalf.

[1218] Prompt Sentence Examples

[1219] "Based on User A's conversation history in communication applications and purchase history in e-commerce tools, learn User A's characteristics and generate a virtual account that will converse and post information on User A's behalf."

[1220] In this way, the burden on the user is reduced, information can be provided based on the user's feelings and preferences, and efficient information management can be achieved.

[1221] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1222] Step 1:

[1223] The server retrieves the conversation history using the API of the user's communication application. It uses the user's authentication information and API endpoint as input and obtains the conversation history data as output. Specifically, the server sends an API request and receives the conversation history data in JSON format as a response.

[1224] Step 2:

[1225] The server obtains purchase history using the API of the e-commerce tool. It uses the user's authentication information and API endpoint as input and obtains purchase history data as output. Specifically, the server sends an API request and receives purchase history data in JSON format as a response.

[1226] Step 3:

[1227] The server preprocesses the acquired conversation history and purchase history. It uses the conversation history data and purchase history data as input and obtains the preprocessed data as output. Specifically, the server uses the Python pandas library to remove unnecessary information and normalize the data.

[1228] Step 4:

[1229] The server extracts features from the preprocessed data. It uses the preprocessed conversation history data and purchase history data as input and obtains extracted feature data as output. Specifically, the server uses natural language processing (NLP) techniques to extract conversational tones and frequently used phrases and analyze purchasing patterns.

[1230] Step 5:

[1231] The server uses generative AI (GPT-4) to learn user characteristics. It uses the extracted feature data as input and obtains a trained model as output. Specifically, the server inputs the feature data into the model and has it learn the user's conversation patterns and purchasing tendencies.

[1232] Step 6:

[1233] The server generates a virtual account with the user's characteristics on the communication application based on the learning results. It uses the trained model and the communication application's API endpoint as input and obtains the virtual account as output. Specifically, the server sends an API request to create a new account and configure it with the user's characteristics.

[1234] Step 7:

[1235] The server analyzes the user's emotions using an emotion analysis engine. It uses the user's message data as input and obtains the emotion analysis result as output. Specifically, the server inputs the message data into the emotion analysis engine and analyzes the emotional tone.

[1236] Step 8:

[1237] The server adjusts the information provided and search results based on the emotion analysis results. It uses the emotion analysis results and user characteristic data as input and obtains adjusted information provided and search results as output. Specifically, the server provides relaxation information and fun event information based on the emotion analysis results.

[1238] (Application example 2)

[1239] Next, a description will be given of Application Example 2 of Form 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."

[1240] Conventional systems have difficulty providing information and recommending content that fully reflects the user's characteristics and emotions, making it impossible to provide services that meet the user's needs. It has also been difficult to create an avatar account that posts on social media, sends messages, or searches the web on behalf of the user. This has led to problems such as reduced user convenience and satisfaction.

[1241] 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.

[1242] In this invention, the server includes: means for learning user characteristics and performing SNS, web searches, information organization, etc. on behalf of the user; means for providing an avatar account that represents the user on a messenger app; means for linking with a generative AI and pre-learning the messenger app chat history and internet search tool shopping purchase history to realize a "conversational" and "push-type" avatar account with the same characteristics as the user; means for analyzing the user's emotions and adjusting the information provision and search results based on those emotions; and means for recommending content based on the user's characteristics and emotions. This makes it possible to provide information and recommend content that reflects the user's characteristics and emotions, and to realize an avatar account that posts on SNS, sends messages, and performs web searches on behalf of the user.

[1243] "User characteristics" refers to the preferences, tastes, and behavioral patterns of individual users extracted from their behavioral history, purchasing history, conversation history, etc.

[1244] An "avatar account" is a virtual account that automatically performs actions such as posting on social media, sending messages, and searching the web on behalf of the user.

[1245] "Generative AI" refers to artificial intelligence technology that generates new information and content based on user data.

[1246] "Pre-learning" refers to the process in which generative AI learns a user's characteristics based on their past behavioral and purchasing history.

[1247] "Sentiment analysis" refers to the technology of analyzing a user's emotional state from their conversation history and behavioral data.

[1248] "Information provision" refers to the act of providing information appropriate to a user based on the user's characteristics and emotions.

[1249] "Content recommendation" refers to the act of recommending content suitable for a user based on the user's characteristics and emotions.

[1250] "Push" refers to a method of automatically providing information or content before the user requests it.

[1251] The system for implementing this invention has the ability to learn user characteristics and perform functions such as social media, web searches, and information organization on behalf of the user. The system provides an avatar account that represents the user on a messenger app, and works in conjunction with generative AI to pre-learn the user's messenger app chat history and internet search tool shopping history. This allows for the creation of a "conversational" and "push-based" avatar account with the same characteristics as the user.

[1252] The server has the ability to analyze user emotions and tailor information provision and search results based on those emotions, as well as recommend content based on user characteristics and emotions.

[1253] Hardware and software used

[1254] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[1255] Software: Messenger apps, generative AI models (e.g., OpenAI GPT-3), sentiment analysis libraries (e.g., NLTK, TextBlob), content recommendation engines (e.g., TensorFlow Recommenders)

[1256] Data processing and calculation

[1257] 1. Data acquisition: The user's device sends the conversation history of the messenger app and the purchase history of the internet search tool to the server.

[1258] 2. Learning user characteristics: The server uses a generative AI model to learn user characteristics from the acquired data.

[1259] 3. Sentiment analysis: The server uses a sentiment analysis library to analyze emotions from the user's conversation history.

[1260] 4. Information provision and content recommendation: The server provides appropriate information and content to the user's device based on the user's characteristics and emotions.

[1261] Specific examples

[1262] For example, if a user says to a friend on a messenger app, "I've been busy at work lately and I'm feeling stressed," the server retrieves this conversation history and uses a sentiment analysis library to analyze that the user is feeling stressed. Furthermore, the server checks the user's purchasing history to see if they have purchased books related to relaxation, and uses a generative AI model to learn the user's characteristics.

[1263] Prompt Sentence Examples

[1264] User conversation history: Work has been busy and stressful lately.

[1265] User purchase history: Purchased books related to relaxation.

[1266] Learn the characteristics of this user.

[1267] By inputting this prompt into a generative AI model, it can learn the user's characteristics and recommend appropriate relaxation content.

[1268] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1269] Step 1:

[1270] The user terminal transmits the conversation history of the messenger app and the purchase history of the internet search tool to the server.

[1271] Input: User conversation history, purchase history

[1272] Output: User data sent to the server

[1273] Specific operation: The user device obtains conversation history using the API of the messenger app and purchase history using the API of the internet search tool, and sends this data to the server.

[1274] Step 2:

[1275] The server inputs the received user data into a generative AI model to learn the user's characteristics.

[1276] Input: User data sent to the server

[1277] Output: Learned user characteristics

[1278] Specific operation: The server generates prompts for a generative AI model (e.g., OpenAI GPT-3) and learns the user's characteristics based on the user's conversation history and purchase history. An example of a prompt is "User's conversation history: I've been busy at work recently and feeling stressed. User's purchase history: I bought a book related to relaxation. Please learn the characteristics of this user."

[1279] Step 3:

[1280] The server uses a sentiment analysis library to analyze emotions from the user's conversation history.

[1281] Input: User's conversation history

[1282] Output: Parsed user emotional state

[1283] What it does: The server uses a sentiment analysis library (e.g., NLTK, TextBlob) to analyze the user's conversation history and identify the emotions the user is feeling (e.g., stress, joy).

[1284] Step 4:

[1285] The server recommends appropriate information and content based on the user's characteristics and emotions.

[1286] Input: Learned user characteristics, analyzed user emotional state

[1287] Output: Recommended information or content

[1288] Specific operation: The server uses a content recommendation engine (e.g., TensorFlow Recommenders) to select appropriate information and content based on the user's characteristics and emotions and send it to the user's device.

[1289] Step 5:

[1290] The user terminal displays the recommended information and content received from the server.

[1291] Input: Recommended information or content

[1292] Output: Information or content displayed to the user

[1293] Specific operation: The user device displays the information and content received from the server on the messenger app or browser and provides it to the user.

[1294] Example 3

[1295] Next, a description will be given of Example 3 of Form Example 3. 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."

[1296] Conventional information provision systems and search engines have been unable to fully reflect the characteristics and preferences of users, making it difficult to provide optimal information for users. Furthermore, because information provision and behavioral automation do not take into account user emotions, it has been difficult to increase user satisfaction.

[1297] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes a means for providing an avatar account that represents the user, a means for working with a generative AI to pre-learn the user's behavioral history and create an avatar account with the same characteristics as the user, and a means for analyzing the user's emotions in real time using an emotion recognition engine and automatically performing actions on the avatar account based on the results. This makes it possible to provide information and generate search results that reflect the user's characteristics and preferences, and further realizes automation of actions that take the user's emotions into consideration.

[1298] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and interests.

[1299] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[1300] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[1301] "Pre-learning" refers to the process of learning user behavioral history and data in advance.

[1302] An "emotion recognition engine" refers to technology that analyzes emotions from a user's facial expressions, tone of voice, etc.

[1303] "Real-time" refers to data collection and processing occurring immediately.

[1304] "Information provision" refers to the act of presenting useful information to users.

[1305] "Search results" refers to the list of related information that is displayed when a user performs a search.

[1306] "Automated actions" refers to a system automatically performing a specific action on behalf of a user.

[1307] This invention is a system that learns user characteristics and provides information and generates search results on behalf of the user. The system provides an avatar account that represents the user and works with generative AI to pre-learn the user's behavioral history. It also uses an emotion recognition engine to analyze the user's emotions in real time and automatically controls the avatar account's behavior based on the results.

[1308] Hardware and software used

[1309] Hardware: Servers, terminals (PCs, smartphones)

[1310] Software: Generative AI models (e.g., GPT-4), emotion recognition engines (e.g., Affectiva), social media APIs (e.g., Twitter API, Facebook API)

[1311] Data processing and calculation

[1312] 1. Data Collection:

[1313] The server collects data such as users' social media posts, message transmissions, web search history, etc. Specifically, it uses the Twitter API and Facebook API to obtain users' posts and search history.

[1314] The device collects real-time emotional data from users using an emotion recognition engine, which uses the device's camera and microphone to analyze the user's facial expressions and tone of voice.

[1315] 2. Data Analysis:

[1316] The server inputs the collected data into a generative AI model to learn the user's characteristics and preferences. Specifically, it analyzes the user's posts and search history to identify topics of interest.

[1317] The generative AI model learns the user's characteristics based on the input data and generates a profile.

[1318] 3. Information provision and search results generation:

[1319] The server generates appropriate information and search results based on the learned user characteristics and preferences, specifically providing news articles and product information that may be of interest to the user.

[1320] The generative AI model generates relevant information based on the user's profile.

[1321] 4. Emotion Recognition and Avatar Account Behavior:

[1322] The device uses an emotion recognition engine to analyze the user's emotions in real time and transmits the results to the server.

[1323] Based on the results of the emotion recognition engine, the server instructs the avatar account to automatically take actions that reflect the user's emotions.

[1324] Specific examples

[1325] Example 1: If a user frequently posts about "travel" on social media

[1326] The server learns the user's travel preferences and prioritizes providing travel-related information and search results.

[1327] Example prompt for a generative AI model: "You frequently post about travel. Please provide travel-related information."

[1328] Example 2: When the user feels angry

[1329] The device uses an emotion recognition engine to detect when the user is feeling anger and sends the results to the server.

[1330] The server sends instructions to the avatar account saying, "The user is feeling angry. Please generate a social media post that reflects that anger."

[1331] The generative AI model generates "social media posts for angry users," which are then automatically posted by avatar accounts.

[1332] In this way, the system takes into consideration the characteristics and emotions of the user, and realizes optimal information provision and automation of actions. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1333] Step 1: Data collection

[1334] The server collects data such as users' social media posts, message transmissions, web search history, etc. Specifically, it uses the Twitter API and Facebook API to obtain users' posts and search history.

[1335] Input: User data obtained from SNS API (post content, search history, etc.)

[1336] Output: Collected user data

[1337] Specific operation: The server periodically calls the SNS API to obtain the user's latest post data.

[1338] Step 2: Collecting Emotional Data

[1339] The device collects real-time emotional data from users using an emotion recognition engine, which uses the device's camera and microphone to analyze the user's facial expressions and tone of voice.

[1340] Input: Real-time facial and voice data from the device's camera and microphone

[1341] Output: User emotion data analyzed by the emotion recognition engine

[1342] Specific operation: While the user is using the smartphone, the device collects facial expression data through the camera and sends it to the emotion recognition engine.

[1343] Step 3: Data analysis

[1344] The server inputs the collected data into a generative AI model to learn the user's characteristics and preferences. Specifically, it analyzes the user's posts and search history to identify topics of interest.

[1345] Input: Collected user data (posts, search history, etc.)

[1346] Output: A profile that reflects the user's characteristics and preferences

[1347] Specific operation: The server inputs the collected social media posting data into the generative AI model and analyzes it using the prompt, "What topics do users frequently post about?"

[1348] Step 4: Providing information and generating search results

[1349] The server generates appropriate information and search results based on the learned user characteristics and preferences, specifically providing news articles and product information that may be of interest to the user.

[1350] Input: A profile that reflects the user's characteristics and preferences

[1351] Output: Information or search results provided to the user

[1352] Specific operation: Based on the profile that "the user is interested in travel," the server searches for travel-related news articles and provides them to the user.

[1353] Step 5: Emotion Recognition and Avatar Account Behavior

[1354] The device uses an emotion recognition engine to analyze the user's emotions in real time and transmits the results to the server.

[1355] Based on the results of the emotion recognition engine, the server instructs the avatar account to automatically take actions that reflect the user's emotions.

[1356] Input: User emotion data analyzed by the emotion recognition engine

[1357] Output: Automatic actions performed by the avatar account (e.g., posting to social media, sending messages)

[1358] Specific operation: The device uses an emotion recognition engine to detect that the user is feeling angry and sends the result to the server. The server then sends an instruction to the avatar account saying, "The user is feeling angry. Please generate a social media post that reflects that anger." The generative AI model then generates a "social media post for the user who is feeling angry," and the avatar account automatically posts it.

[1359] (Application example 3)

[1360] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1361] Conventional avatar account systems were unable to provide information or generate search results that reflected the user's preferences and tastes, and were unable to automatically act based on the user's emotions. Furthermore, they lacked the functionality to recommend optimal content based on the user's emotions and tastes, making it difficult to improve the user experience.

[1362] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes: means for learning user characteristics and performing SNS / web searches / information organization on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for linking with a generative AI and pre-learning the messenger app chat history and internet search tool shopping history to realize a "conversational" and "push-type" avatar account with the same characteristics as the user; means for recognizing the user's emotions in real time using an emotion engine and automatically controlling the avatar account's behavior based on those emotions; and means for automatically recommending optimal content based on the user's emotions and preferences. This makes it possible to provide information, generate search results, and recommend optimal content based on the user's emotions and preferences.

[1363] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, tastes, and emotions.

[1364] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[1365] "Generative AI" refers to artificial intelligence that learns user behavior and characteristics and generates information based on that.

[1366] "Messenger app chat history" refers to a user's conversation history within the Messenger app.

[1367] "Internet search tool shopping purchase history" refers to the shopping history of a user using an Internet search tool.

[1368] "Pre-learning" refers to the process in which generative AI learns in advance using the user's past behavioral data.

[1369] An "emotion engine" refers to a system that recognizes a user's emotions in real time and determines actions based on those emotions.

[1370] "Content" refers to information and entertainment such as videos, articles, and music.

[1371] "Recommendation" refers to the act of selecting and presenting the most appropriate content based on the user's characteristics and emotions.

[1372] The system for implementing this invention has the ability to learn user characteristics and perform social media, web searches, information organization, etc. on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and works in conjunction with generative AI to pre-learn the messenger app chat history and internet search tool shopping history. This pre-learning allows for the creation of a "conversational" and "push-type" avatar account with the same characteristics as the user.

[1373] Furthermore, the system uses an emotion engine to recognize users' emotions in real time and automatically adjusts the avatar account's behavior based on those emotions. It also includes a function to automatically recommend the most suitable content based on the user's emotions and preferences.

[1374] Program processing explanation

[1375] The server runs programs for emotion recognition and content recommendation using Python. For emotion recognition, TextBlob is used to analyze the user's text data. To learn the user's preferences, the text data is vectorized using scikit-learn's TfidfVectorizer, and the optimal content is recommended by calculating the cosine similarity.

[1376] Hardware and software used

[1377] Hardware: Smartphone

[1378] Software: Python, TextBlob, scikit-learn

[1379] Specific examples

[1380] For example, if a user posts, "I'm so tired today," sentiment analysis will detect negative emotions and the system will recommend relaxing music and videos.

[1381] Prompt Sentence Examples

[1382] User post: "I'm so tired today"

[1383] User preferences: ["I like movies", "I like music", "I like traveling"]

[1384] Recommended content: ["Relaxing music", "Exciting movies", "Travel blogs"]

[1385] By inputting this prompt into a generative AI model, it is possible to recommend optimal content based on the user's emotions and preferences.

[1386] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1387] Step 1:

[1388] The server collects the user's chat history on messenger apps and their shopping history on internet search tools. This data is entered as the user's behavioral history. The server saves this data in text format for later processing.

[1389] Step 2:

[1390] The server uses the collected data to learn user characteristics. Specifically, it uses Python's scikit-learn library to vectorize text data using TfidfVectorizer. This vectorized data is output as features representing the user's preferences.

[1391] Step 3:

[1392] The server uses TextBlob to recognize user emotions in real time. It receives text data posted by users to the messenger app as input and performs sentiment analysis using TextBlob. The result of the sentiment analysis is an emotional score: positive, negative, or neutral.

[1393] Step 4:

[1394] The server uses an emotion engine to determine the behavior of the avatar account based on the user's emotions. It receives the emotion score as input and configures it to recommend relaxing content for negative emotions and exciting content for positive emotions. This configuration is output as the avatar account's behavioral guidelines.

[1395] Step 5:

[1396] The server recommends optimal content based on the user's preferences and emotions. Specifically, it receives features representing the user's preferences and emotion scores as input, and selects the most suitable content using scikit-learn's cosine similarity calculation. This recommended content is then output as information provided to the user.

[1397] Step 6:

[1398] The device presents the content recommended by the server to the user. The user can check the recommended content on the smartphone screen and use it as needed. In this step, the recommended content is displayed on the user's device.

[1399] Step 7:

[1400] The user uses the recommended content and sends their feedback to the server, which then receives this feedback and stores it in a database to be used for future recommendations. This feedback is then used to further learn about the user's characteristics.

[1401] 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.

[1402] 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> ) 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.

[1403] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1404] 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.

[1405] [Third embodiment]

[1406] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1407] 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.

[1408] 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).

[1409] 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.

[1410] 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.

[1411] 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).

[1412] 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.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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.

[1417] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1418] "Example 1"

[1419] One embodiment of the present invention provides a system that learns user characteristics and performs social networking, web searches, information organization, and other functions on behalf of the user. Specifically, an avatar account that represents the user is provided on a messenger app. This avatar account pre-learns the user's messenger app chat history and internet search tool shopping history, and by linking with generative AI, it creates a "conversational" and "push-based" avatar account with the same characteristics as the user.

[1420] "Example 2"

[1421] As a specific example, User A provides his / her conversation history with Friend B on a messenger app and his / her purchase history on Amazon as pre-learning data. Based on this data, the system works with generative AI to learn User A's characteristics. After learning is complete, the system provides an avatar account on the messenger app that will represent User A. This avatar account will be a "push-type" avatar account with the same characteristics as User A, capable of "conversation," and will be able to post on social media, send messages, and perform web searches on User A's behalf.

[1422] "Example 3"

[1423] Another embodiment of the present invention provides a function for providing information and generating search results that reflect a user's preferences and tastes. Specifically, an avatar account is provided that automatically performs actions such as posting to social media, sending messages, and web searches. This avatar account can learn the user's characteristics and generate information and search results that reflect those characteristics.

[1424] The processing flow of each embodiment will be described below.

[1425] "Example 1"

[1426] Step 1: The user provides the system with their conversation history with friends on the messenger app and their purchase history on Amazon.

[1427] Step 2: Based on the data provided, the system works with generative AI to learn the user's characteristics.

[1428] Step 3: After learning is complete, the system will provide the user with an avatar account on the Messenger app.

[1429] Step 4: This avatar account will be a "conversational" and "push-type" avatar account with the same characteristics as the user, and will be able to post on social media, send messages, search the web, and more on behalf of the user.

[1430] "Example 2"

[1431] Step 1: The user provides the system with behavioral data such as social media posts, messaging, and web searches.

[1432] Step 2: The system learns the user's characteristics based on the data provided.

[1433] Step 3: After the learning is complete, the system will provide the user with an avatar account.

[1434] Step 4: This avatar account can generate information and search results that reflect the user's characteristics.

[1435] Example 1

[1436] Next, a description will be given of Example 1 of Form 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."

[1437] In today's information society, users need to efficiently collect and organize vast amounts of information. However, doing this manually takes time and effort, and is inefficient. In addition, while there is a demand for information to be provided based on the user's characteristics and preferences, it is difficult to fully realize this with conventional systems. Furthermore, when users use multiple information and communication services and search tools, there is a lack of a way to centrally manage and utilize the history and characteristics of each. A system that can solve these issues is needed.

[1438] 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.

[1439] In this invention, the server includes: means for learning user characteristics and providing information and communication services, information search, information organization, etc. on behalf of the user; means for providing a virtual account that serves as the user's avatar on the information and communication application; means for cooperating with a generative AI and pre-learning the information and communication application history, internet search tools, and purchase history to realize a "conversational" and "push-type" virtual account with the same characteristics as the user; means for pre-processing collected data and extracting user characteristics; means for training a generative AI model using the extracted characteristics; and means for collecting related information based on the user's interests and preferences and sending push notifications through the virtual account. This enables the provision of information and the generation of search results based on the user's characteristics and preferences, significantly improving the efficiency of users' information collection and organization.

[1440] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and interests.

[1441] "Information and communication services" refers to communication methods such as messaging, social networking services, and email provided via the Internet.

[1442] "Information search" refers to the act of finding specific information on the Internet.

[1443] "Information organization" refers to the act of classifying and organizing collected information to make it easier to use.

[1444] "Information and communication applications" refers to software that allows users to send and receive messages and share information.

[1445] A "virtual account" refers to a digital alter ego that acts on a user's behalf on an information and communication application.

[1446] "Generative AI" refers to artificial intelligence technology that learns the characteristics of a user and generates responses and behaviors similar to that user's.

[1447] "Pre-learning" refers to the process of pre-training a generative AI model using collected data.

[1448] "Conversational" refers to the virtual account's ability to engage in natural dialogue with the user.

[1449] "Push" refers to the function of automatically notifying users of relevant information based on their interests and concerns.

[1450] "Preprocessing" refers to the process of preparing collected data in a form that is easy to analyze.

[1451] "Feature extraction" refers to the act of extracting features such as user interests and preferences from preprocessed data.

[1452] "Training" refers to the process of training a generative AI model using extracted characteristics.

[1453] "Push notification" refers to the function of sending information to users in real time.

[1454] This invention is a system that learns user characteristics and performs information communication services, information search, information organization, etc. on behalf of the user. Specific embodiments of this system are described below.

[1455] 1. System Overview

[1456] The server learns user characteristics and provides a system for providing information and communication services, information search, information organization, etc. on behalf of the user. This system provides a virtual account that serves as the user's avatar on the information and communication application, and works in conjunction with generative AI.

[1457] 2. Hardware and Software Used

[1458] The server uses the following hardware and software:

[1459] Hardware: High-performance server machine, database server

[1460] Software: Information and communication applications, generative AI models, data analysis tools, push notification systems

[1461] 3. Data collection and pre-training

[1462] The server collects the user's information and communication application history, internet search tool history, and purchase history. This data serves as the basis for learning user characteristics. The collected data is preprocessed to remove unnecessary data and normalize the data.

[1463] Next, user characteristics are extracted from the preprocessed data. Natural language processing techniques are used to analyze the text data and identify the user's interests. The extracted characteristics are used to train a generative AI model. This pre-training allows the generative AI model to understand the user's characteristics and generate responses that resemble the user's.

[1464] 4. Creating and Configuring Virtual Accounts

[1465] The server uses a pre-trained generative AI model to generate a virtual account that reflects the user's characteristics. This virtual account can then converse on behalf of the user on information and communication applications. The virtual account also has the ability to push notifications of relevant information based on the user's interests.

[1466] 5. Specific Examples

[1467] Example 1: Travel planning

[1468] When a user is planning a trip with friends using an information and communication application, the server will provide information on suitable travel destinations and accommodations based on past travel history and search history. For example, it may suggest places that the user has visited in the past that the friend might be interested in.

[1469] Example 2: Providing shopping information

[1470] If a user is interested in a particular brand, the server collects information about new products from that brand and sends push notifications through the virtual account. For example, the server can instantly notify users when new products from a brand they have previously purchased are released.

[1471] 6. Examples of prompts

[1472] "Based on the user's information and communication application history and internet search history, please generate a virtual account that provides information about travel destinations that the user is interested in. Also, please implement a function to send push notifications with the latest information about those travel destinations."

[1473] In this way, a system is realized that learns the characteristics of the user and provides information and communication services, searches for information, and organizes information on behalf of the user.

[1474] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1475] Step 1: Data collection

[1476] The server collects the user's information and communication application history, internet search tool history, and purchase history.

[1477] Input: User's information and communication application history, internet search history, purchase history

[1478] Data processing: Collected data is stored in a database for centralized management.

[1479] Output: User behavior history data stored in a database

[1480] Specific operation: The server obtains data from information and communication applications and Internet search tools via API and stores it in a database.

[1481] Step 2: Preprocessing the data

[1482] The server pre-processes the collected data.

[1483] Input: User behavior history data stored in a database

[1484] Data processing: Removal of unnecessary data, data normalization, tokenization of text data

[1485] Output: A preprocessed, clean dataset

[1486] Specific operation: The server uses a data cleansing tool to remove noise data and prepare the text data in a form that is easy to analyze.

[1487] Step 3: Feature extraction

[1488] The server extracts user characteristics from the preprocessed data.

[1489] Input: Preprocessed clean dataset

[1490] Data processing: Analyze text data using natural language processing techniques to identify user interests and concerns

[1491] Output: A feature vector that describes the user's characteristics

[1492] Specific operation: The server uses a natural language processing library to analyze the text data and extract the user's interests and concerns.

[1493] Step 4: Training the generative AI model

[1494] The server uses the extracted features to train a generative AI model.

[1495] Input: A feature vector that describes the user's characteristics

[1496] Data processing: Input feature vectors into the generative AI model and train the model

[1497] Output: A generative AI model that learns user characteristics

[1498] How it works: The server uses a machine learning framework to train a generative AI model to learn the user's characteristics.

[1499] Step 5: Generate Virtual Accounts

[1500] The server uses a pre-trained generative AI model to generate a virtual account that reflects the user's characteristics.

[1501] Input: A generative AI model that learns user characteristics

[1502] Data processing: Using generative AI models to create virtual accounts and register them in information and communication applications

[1503] Output: Virtual account on information and communication application

[1504] Specific operation: The server generates a virtual account using the generative AI model and registers it in the information and communication application through the API.

[1505] Step 6: Implementing Push Notifications

[1506] The server collects relevant information based on the user's interests and pushes it to the user through the virtual account.

[1507] Input: User interest data, external sources

[1508] Data processing: Collecting relevant information and formatting it in a way that is appropriate for the user

[1509] Output: Push notification message

[1510] Specific operation: The server collects relevant information from external information sources and sends push notifications to users through virtual accounts.

[1511] In this way, a system is realized that learns the characteristics of the user and provides information and communication services, searches for information, and organizes information on behalf of the user.

[1512] (Application example 1)

[1513] Next, a description will be given of Application Example 1 of Form 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."

[1514] It is difficult for modern consumers to find the best product for them from the vast amount of information available, and it takes time and effort. In addition, there is a lack of personalized product suggestions based on the user's characteristics and preferences, making it difficult for consumers to find products that suit them. Furthermore, there is no system that can search social media or the web or organize information on behalf of the user, so users have to collect information themselves, which is an issue.

[1515] 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.

[1516] In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account that represents the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for learning the user's purchase history and search history and automatically suggesting products that match the user's preferences; and means for suggesting products based on the user's history using a generative AI model. This allows users to easily find the products that are best suited to them and reduces the effort required for information gathering.

[1517] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and purchasing history.

[1518] "SNS" is an abbreviation for social networking service, an online platform where users can share information and communicate with other users.

[1519] "Web search" refers to the act of finding information on the Internet using a search engine.

[1520] "Information organization" refers to the act of classifying collected information and organizing it into an easy-to-understand format.

[1521] A "messenger app" is application software that allows users to send and receive text messages, images, audio, etc.

[1522] An "avatar account" is a virtual account that functions as a user's alter ego and communicates and collects information on behalf of the user.

[1523] "Generative AI" refers to artificial intelligence technology that generates new information and suggestions based on user input and historical data.

[1524] "Pre-learning" refers to the process in which the system learns the user's past behavioral history and data in advance.

[1525] "Push" refers to a method in which the system automatically provides information or suggestions before the user requests them.

[1526] "Purchase history" refers to a record of products a user has purchased in the past.

[1527] "Search history" refers to a record of keywords or phrases a user has previously searched for on a search engine.

[1528] A "generative AI model" refers to an artificial intelligence algorithm that generates new information and suggestions based on a user's historical data.

[1529] As an embodiment of this invention, we provide a system that learns user characteristics and performs SNS, web searches, information organization, etc. on behalf of the user. Specifically, we provide an avatar account that represents the user on a messenger app, and in cooperation with generative AI, pre-learn the user's messenger app chat history and internet search tool shopping history. This avatar account is a "conversational" and "push-type" avatar account with the same characteristics as the user.

[1530] The server learns the user's purchase and search history and automatically suggests products that match the user's preferences. Using a generative AI model, it suggests products based on the user's history. This system allows users to easily find the products that best suit them, eliminating the need to gather information.

[1531] Hardware and software used

[1532] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[1533] Software: Messenger apps, generative AI models (e.g., OpenAI GPT-3)

[1534] Data processing and calculation

[1535] The server collects the user's chat history from messenger apps, internet search tools, and shopping purchase history, and pre-trains this data. A generative AI model is used to analyze the user's history data and learn their characteristics and preferences. This allows it to automatically suggest products that match the user's preferences.

[1536] Specific examples

[1537] If a user has previously purchased a smartphone or wireless earphones and is searching for the latest smartphone or high-quality earphones, the generative AI model will suggest products related to the latest smartphones or high-quality earphones.

[1538] Prompt Sentence Examples

[1539] User purchase history: ["smartphone", "wireless earphones"]

[1540] User search history: ["latest smartphone", "high quality earphones"]

[1541] Suggest a product that you would recommend to this user.

[1542] In this way, a personal shopping assistant can be realized that automatically suggests products that match the user's preferences.

[1543] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1544] Step 1:

[1545] The server collects users' chat history, internet search results, and shopping history. This data is used as input to learn about users' characteristics and preferences. Specifically, the server obtains data from each platform via API and stores it in a database.

[1546] Input: Messenger app chat history, internet search tools, shopping purchase history

[1547] Output: User history data stored in a database

[1548] Step 2:

[1549] The server pre-trains the collected user history data. During this pre-training process, a generative AI model is used to analyze the data and learn the user's characteristics and preferences. Specifically, the historical data is input into the AI ​​model to extract the user's behavioral patterns and preferences.

[1550] Input: User history data stored in a database

[1551] Output: A model that reflects the user's characteristics and preferences

[1552] Step 3:

[1553] The server uses a generative AI model to suggest products based on the user's history. In this process, a prompt sentence is generated to suggest the most suitable product based on the user's purchase history and search history, and input into the AI ​​model. The AI ​​model then generates product suggestions based on the prompt sentence.

[1554] Input: A model that reflects the user's characteristics and preferences, prompts

[1555] Output: Product proposal

[1556] Step 4:

[1557] The server sends the generated product suggestions to the user's device, where the user can check the suggested products through a messenger app or a dedicated app. Specifically, the product suggestions are sent to the user's device via API and displayed on the user interface.

[1558] Input: Product proposal

[1559] Output: Product suggestions displayed on the user's device

[1560] Step 5:

[1561] The user reviews the suggested products and purchases them if necessary. In this process, the user receives the product suggestions, selects the products they are interested in, and then completes the purchase process by selecting the products through the user interface and clicking the purchase button.

[1562] Input: Product suggestions displayed on the user's device

[1563] Output: User purchase behavior

[1564] In this way, we have created a system that automatically makes product suggestions based on the user's characteristics and preferences, allowing users to easily find the products that are best suited to them.

[1565] Example 2

[1566] Next, a description will be given of Example 2 of Form 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."

[1567] Conventional information processing systems have had difficulty providing automated information and communication that fully reflects the user's characteristics. It has also been difficult to create an avatar account that posts to social media, sends messages, searches the web, and so on, on behalf of the user. This has increased the burden on the user and hindered efficient information processing.

[1568] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for learning user characteristics and processing information on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for linking with a generative AI model and pre-learning the conversation history of the messenger app and the purchase history of online shopping to realize a "conversational" and "push-type" avatar account with the same characteristics as the user; means for pre-processing data stored in a database, cleaning and tokenizing text data; and means for inputting prompt sentences into the generative AI model and sending generated messages. This enables automated information provision and communication that reflects the user's characteristics.

[1569] "User characteristics" refers to individual characteristics such as a user's behavioral patterns, preferences, and tastes.

[1570] "Information processing" refers to a series of operations such as collecting, analyzing, storing, retrieving, and generating data.

[1571] An "avatar account" refers to a virtual account that acts online on behalf of a user.

[1572] A "generative AI model" refers to an artificial intelligence model that generates new information or content based on given data.

[1573] "Pre-training" refers to the process of training a model using data in advance for a specific task.

[1574] "Conversational" refers to the ability to engage in natural dialogue on behalf of the user.

[1575] "Push" refers to a format in which information is provided automatically without waiting for a user request.

[1576] A "database" refers to a system for efficiently storing, managing, and retrieving data.

[1577] "Preprocessing" refers to the initial processing of data to convert it into a form suitable for analysis and learning.

[1578] "Cleaning" refers to the process of removing unnecessary information or noise from data.

[1579] "Tokenization" refers to the process of breaking down text data into words and phrases.

[1580] A "prompt sentence" refers to an input sentence that causes a generative AI model to generate a specific output.

[1581] The present invention is a system that learns user characteristics and processes information on behalf of the user. Specific embodiments of this system will be described below.

[1582] The server receives the conversation history of the messenger app and the purchase history of online shopping provided by the user. This data is used as pre-learning data to learn the characteristics of the user. The server stores this data in a database. The database uses a relational database such as MySQL or PostgreSQL.

[1583] The server then preprocesses the stored data, which includes cleaning the text data (removing unnecessary characters and noise) and tokenizing it (dividing it into words and phrases), using the Python NLTK and spaCy libraries.

[1584] After preprocessing, the data is input into a generative AI model (for example, OpenAI's GPT-4). The server uses this generative AI model to learn the user's characteristics. During this learning process, the model is updated to reflect the user's conversation patterns and purchasing tendencies. Once learning is complete, the server generates a model that incorporates the user's characteristics.

[1585] The server then generates an avatar account with the user's characteristics based on the trained model. This avatar account can then converse on the user's behalf on the messenger app. Specifically, the avatar account inputs prompts into the generative AI model and sends the generated messages to friends.

[1586] As a concrete example, consider a situation where a user provides a conversation history with a friend, for example, by providing the following prompt sentence to a generative AI model:

[1587] Prompt: "Generate a message for a user to send to a friend. The user recently purchased a new smartphone and wants to tell their friend about their experience with it."

[1588] The generative AI model generates messages like this:

[1589] Generated message: "Hi, friend! I recently bought a new smartphone and it's so easy to use. The camera in particular is amazing and it takes great photos. If your friend is also thinking about buying a new smartphone, I highly recommend it!"

[1590] In this way, avatar accounts can send messages to friends that reflect the user's characteristics. Avatar accounts can also post on social media and perform web searches. This reduces the burden on users and enables more efficient information processing.

[1591] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1592] Step 1: Data collection

[1593] The server receives the user's conversation history from the messenger app and the user's online shopping purchase history. This data is used as pre-learning data to learn the user's characteristics. The input is the conversation history and purchase history provided by the user, and the output is the raw data stored in the database. Specifically, the server receives the data uploaded by the user and stores it in the database.

[1594] Step 2: Data Preprocessing

[1595] The server preprocesses the stored data. This preprocessing includes cleaning the text data (removing unnecessary characters and noise) and tokenizing it (dividing it into words and phrases). The input is the raw data stored in the database, and the output is the preprocessed, clean data. Specifically, the server uses Python's NLTK and spaCy libraries to clean and tokenize the text data.

[1596] Step 3: Trait learning

[1597] The server inputs the preprocessed data into a generative AI model to learn the user's characteristics. The input is preprocessed, clean data, and the output is a trained model that reflects the user's characteristics. Specifically, the server uses a generative AI model (for example, OpenAI's GPT-4) to learn the user's conversation patterns and purchasing tendencies.

[1598] Step 4: Create an avatar account

[1599] The server generates an avatar account with the user's characteristics based on the trained model. The input is the trained model, and the output is the avatar account. Specifically, the server creates an avatar account that can converse on behalf of the user on the messenger app based on the output of the generative AI model.

[1600] Step 5: Avatar Account in Action

[1601] The avatar account inputs a prompt into the generative AI model and sends the generated message to a friend. The input is the prompt, and the output is the generated message. Specifically, the avatar account inputs the following prompt into the generative AI model:

[1602] Prompt: "Generate a message for a user to send to a friend. The user recently purchased a new smartphone and wants to tell their friend about their experience with it."

[1603] The generative AI model generates messages like this:

[1604] Generated message: "Hi, friend! I recently bought a new smartphone and it's so easy to use. The camera in particular is amazing and it takes great photos. If your friend is also thinking about buying a new smartphone, I highly recommend it!"

[1605] The avatar account will then send this message to friends, enabling automated information provision and communication that reflects the user's characteristics.

[1606] (Application example 2)

[1607] Next, a description will be given of Application Example 2 of Form 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."

[1608] Conventional social networking sites and messaging apps require users to collect information and post or send messages themselves, which takes time and effort. Furthermore, there is a lack of effective ways to deliver advertisements that reflect the characteristics and preferences of users. This creates a need to improve user convenience while maximizing the effectiveness of advertisements.

[1609] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account representing the user on a messenger app; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping and purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; and means for the avatar that has learned the user's characteristics to post advertisements on SNS and messenger apps on behalf of the user. This enables automatic information collection and posting on behalf of the user, improving user convenience and enabling effective advertisement delivery that reflects the user's characteristics and preferences.

[1610] "User characteristics" refers to individual characteristics such as a user's behavioral history, preferences, and tastes.

[1611] "SNS" is an abbreviation for social networking service, which refers to an online platform where users can share information and communicate with other users.

[1612] "Web search" refers to the act of finding information on the Internet using a search engine.

[1613] "Information organization" refers to the act of classifying and organizing collected information.

[1614] A "messenger app" refers to an application that allows users to send and receive text messages, images, videos, etc.

[1615] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[1616] "Generative AI" refers to artificial intelligence that generates new information and content based on given data.

[1617] "Pre-training" refers to the process of pre-training a model with relevant data before it performs a specific task.

[1618] "Conversational" refers to the ability to have a natural dialogue with the user.

[1619] "Push" refers to a method in which information is provided automatically before the user requests it.

[1620] "Posting an advertisement" refers to the act of publishing information about a specific product or service on social media or a messaging app.

[1621] The system for implementing this invention learns user characteristics and performs SNS, web searches, information organization, etc. on behalf of the user. Specifically, it provides an avatar account that represents the user on a messenger app, and by working with generative AI to pre-learn the messenger app chat history and internet search tool shopping history, it realizes a "conversational" and "push-type" avatar account with the same characteristics as the user.

[1622] The server first obtains the user's conversation history and purchase history on the messenger app. This data is collected using the APIs of the messenger app and shopping site. The server then uses generative AI to learn the user's characteristics based on this data. Specifically, the conversation history and purchase history are input as prompts into the generative AI model, allowing it to learn the user's characteristics.

[1623] After the learning is complete, the server generates an avatar account with the user's characteristics, and this avatar posts advertisements on social media and messenger apps on the user's behalf. This makes it possible to automatically collect and post information on the user's behalf, improving user convenience and enabling effective advertisement delivery that reflects the user's characteristics and preferences.

[1624] The hardware used includes servers and user devices (smartphones, tablets, PCs, etc.), while the software used includes messenger apps, shopping site APIs, generative AI (e.g., OpenAI APIs), etc.

[1625] As a concrete example, consider the case where the user ID is "user123" and the ad content is "Check out this amazing product!" In this case, the server would do the following:

[1626] 1. The server obtains the conversation history and purchase history of user ID "user123".

[1627] 2. The server uses generative AI to learn the characteristics of "user123" based on the acquired data.

[1628] 3. The server uses the learned user model to post an ad on social media saying, "Check out this amazing product!"

[1629] Example prompts to input to a generative AI model:

[1630] Train a model based on the following data: [Conversation history and purchase history data]

[1631] This prompt is used to train a generative AI model to learn the user's characteristics.

[1632] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1633] Step 1:

[1634] The server obtains the user's conversation history and purchase history on the messenger app. Specifically, it uses the API of the messenger app or shopping site to collect the conversation history and purchase history related to the user ID. The input is the user ID, and the output is the conversation history and purchase history data.

[1635] Step 2:

[1636] The server uses generative AI to learn the user's characteristics based on the acquired conversation history and purchase history. Specifically, the conversation history and purchase history are input as prompts into the generative AI model, which then learns the user's characteristics. The input is conversation history and purchase history data, and the output is a model that reflects the user's characteristics.

[1637] Step 3:

[1638] The server generates an avatar account based on the learned user model. Specifically, it uses generative AI to create an avatar account with the user's characteristics and provides it to the messenger app. The input is the user model, and the output is the avatar account.

[1639] Step 4:

[1640] The server posts advertisements on social media and messenger apps using the avatar account. Specifically, it generates advertisement content that reflects the user's characteristics and posts it using the SNS or messenger app's API. The input is a user model and advertisement content, and the output is an advertisement posted on the SNS or messenger app.

[1641] Step 5:

[1642] The server monitors the effectiveness of the ads and updates the user model as necessary. Specifically, it collects data such as ad click-through rates and engagement rates, and uses generative AI to retrain the user model. The input is ad performance data, and the output is an updated user model.

[1643] Example 3

[1644] Next, a third embodiment of the third embodiment will be described. 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."

[1645] Conventional information provision systems and search engines have been unable to fully reflect users' preferences and tastes, making it difficult to provide users with the most appropriate information. In addition, users have to search for and organize information themselves, which makes it difficult to efficiently gather information.

[1646] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes: means for learning user characteristics and providing information and generating search results on behalf of the user; means for providing a virtual account on a messaging application that acts as a proxy for the user; means for working with a generative AI to pre-learn the messaging application chat history and internet search tool purchase history and realize an "interactive" and "push-type" virtual account with the same characteristics as the user; means for collecting user behavioral data and analyzing the data using natural language processing technology; means for generating a profile reflecting the user's preferences and tastes based on the analysis results; means for the virtual account to automatically provide information and perform searches based on the generated profile; and means for generating customized information and search results based on the behavioral results of the virtual account. This makes it possible to provide optimal information and generate search results that reflect the user's preferences and tastes.

[1647] "User characteristics" refers to individual characteristics such as a user's preferences, tastes, behavioral patterns, and interests.

[1648] "Information provision" refers to the act of providing useful information to users.

[1649] "Search Results" means the list of information returned in response to a search conducted by a user on the Internet.

[1650] "Messaging application" means software that enables users to send and receive text and multimedia messages.

[1651] "Virtual Account" refers to a digital account that acts on behalf of a user.

[1652] "Generative AI" refers to artificial intelligence that has the ability to generate new information and content based on data.

[1653] "Pre-training" refers to the process by which the system learns using the user's past data.

[1654] "Interactive" refers to a system's ability to engage in natural dialogue with the user.

[1655] "Push" refers to a method in which the system automatically provides information without waiting for a user request.

[1656] "Behavioral Data" refers to data about user actions (e.g., social media posts, search history, message sending, etc.).

[1657] "Natural language processing technology" refers to technology for understanding, analyzing, and generating human language.

[1658] A "profile" refers to a collection of data generated based on a user's characteristics and behavioral patterns.

[1659] "Customized Information" refers to information that is individually tailored based on a user's characteristics and preferences.

[1660] MODE FOR CARRYING OUT THE INVENTION

[1661] The present invention is a system that learns user characteristics and provides information and generates search results on behalf of the user. A specific embodiment of this system is described below.

[1662] 1. Generating the system program

[1663] The server generates a program to provide information and generate search results that reflect the user's preferences and tastes. This program has the function of managing a virtual account that automatically performs actions such as posting to social media, sending messages, and web searches.

[1664] 2. Explanation of program processing

[1665] The server performs the following processing using the generated program.

[1666] 1. Data Collection:

[1667] The server collects data such as users' social media posts, message transmissions, and web search history. This data collection is obtained from each social media platform and search engine via API. Specifically, it uses the Twitter API and Google Search API.

[1668] 2. Data Analysis:

[1669] The server uses natural language processing (NLP) techniques to analyze the collected data, specifically using software such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1670] 3. Create a user profile:

[1671] The server uses the analysis results to create a profile that reflects the user's preferences and tastes, including topics and keywords that interest the user.

[1672] 4. Virtual account behavior simulation:

[1673] The server then generates a virtual account that automatically posts on social media, sends messages, and performs web searches based on the generated user profile. This simulation uses a generative AI model (e.g., OpenAI's GPT-4).

[1674] 5. Information provision and search results generation:

[1675] The server generates customized information and search results for the user based on the behavior of the virtual account, and the information is presented in a form that best suits the user's preferences and tastes.

[1676] 3. Examples of concrete examples and prompts

[1677] Examples:

[1678] Let's say User A is interested in traveling. The server extracts keywords such as "travel," "tourist spots," and "hotels" from User A's social media posts and web search history. Based on this, a virtual account automatically posts travel-related information on social media and searches travel blogs. Finally, it provides User A with information on recommended tourist spots and hotels.

[1679] Example prompt sentence:

[1680] "To provide User A with travel-related information that interests him, please suggest recommended tourist spots and hotels based on his social media posts and web search history."

[1681] In this way, the server realizes a system for providing information and generating search results that reflect the user's preferences and tastes. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1682] Step 1: Data collection

[1683] The server collects data such as users' social media posts, message transmissions, and web search history. Specifically, it retrieves users' tweets using the Twitter API and collects users' search history using the Google Search API. The input is the user's account information, and the output is the collected behavioral data.

[1684] Step 2: Data analysis

[1685] The server uses natural language processing (NLP) technology to analyze the collected data. Specifically, it uses the Google Cloud Natural Language API to extract keywords from users' tweets and search history and perform sentiment analysis. The input is the collected behavioral data, and the output is the analyzed keywords and sentiment information.

[1686] Step 3: Generate a user profile

[1687] The server generates a profile that reflects the user's preferences and tastes based on the analysis results. Specifically, it creates a list of topics and keywords that interest the user based on the extracted keywords and the results of sentiment analysis. The input is the analyzed keywords and sentiment information, and the output is the generated user profile.

[1688] Step 4: Simulating virtual account behavior

[1689] The server automatically posts to social media, sends messages, and performs web searches using virtual accounts based on the generated user profile. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-4) to generate social media posts based on the user's interests and search related websites. The input is the user profile, and the output is the behavioral results of the virtual account.

[1690] Step 5: Providing information and generating search results

[1691] The server generates customized information and search results for users based on the behavioral results of the virtual accounts. Specifically, it organizes the information collected by the virtual accounts and provides users with information on recommended tourist spots and hotels. The input is the behavioral results of the virtual accounts, and the output is customized information and search results.

[1692] (Application example 3)

[1693] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1694] Conventional systems have had difficulty providing information and generating search results that accurately reflect a user's tastes and preferences. They also required users to post on social media, send messages, and search the web themselves, which was time-consuming and labor-intensive. Furthermore, the recommendation function for suggesting the most suitable products to users was insufficient, preventing users from increasing their purchasing motivation. To solve these issues, a system is needed that can automate user behavior, learn user characteristics, and provide optimal information and product suggestions.

[1695] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1696] In this invention, the server includes: means for learning user characteristics and performing SNS and web searches and information organization on behalf of the user; means for providing an avatar account on a messenger app that represents the user; means for working with a generative AI to pre-learn the messenger app chat history and internet search tool shopping purchase history to create a "conversational" and "push-type" avatar account with the same characteristics as the user; means for analyzing the user's SNS posts, message sending, and web search history to learn the user's tastes and preferences; means for suggesting optimal products to the user; means for automatically posting product reviews and questions; and means for making recommendations based on purchase history. This makes it possible to automate user behavior, learn the user's characteristics, and provide optimal information and product suggestions.

[1697] "User characteristics" refers to individual characteristics such as a user's preferences, tastes, and behavioral patterns.

[1698] "SNS" is an abbreviation for social networking service, which refers to a platform where users can interact with other users online.

[1699] "Web search" refers to the act of finding information on the Internet using a search engine.

[1700] "Information organization" refers to the process of classifying and organizing collected data and information to make it easier to use.

[1701] A "messenger app" refers to application software for sending and receiving text messages, images, videos, etc.

[1702] An "avatar account" refers to a virtual account that acts as a user's alter ego online.

[1703] "Generative AI" refers to artificial intelligence technology that generates new information and content based on data.

[1704] "Pre-training" refers to the process of pre-training a model with relevant data before it performs a specific task.

[1705] "Push" refers to a method in which information is provided automatically before the user requests it.

[1706] "SNS posting" refers to the act of publishing content such as text, images, and videos on social networking services.

[1707] "Sending a message" refers to the act of sending text messages, images, videos, etc. to other users.

[1708] "Web search history" refers to a record of searches a user has conducted on the Internet in the past.

[1709] "Product suggestion" refers to the act of recommending appropriate products based on a user's preferences and tastes.

[1710] A "product review" refers to the act of writing an evaluation or opinion on a purchased product.

[1711] "Recommendation" refers to a system that recommends appropriate products and services based on a user's past behavior and preferences.

[1712] A system for implementing this invention learns user characteristics and performs social networking, web searches, information organization, etc. on behalf of the user. The system provides an avatar account that represents the user on a messenger app and works in conjunction with generative AI. Specific embodiments of the system are described below.

[1713] System configuration

[1714] The system consists of the following main components:

[1715] 1. User device: A device such as a smartphone or...

Claims

1. A system that learns user characteristics and performs information and communication services, information searches, and information organization on behalf of the user, A means for providing a virtual account representing the user on an information and communication application; A means for linking with generative AI, pre-learning the history of the information and communication application, internet search tools, and purchase history, and realizing a "push-type" virtual account that has the same characteristics as the user and can "converse" with the user; A means for pre-processing the learned data and extracting characteristics of the user; A means for training a generative AI model using the extracted user characteristics; A means for collecting relevant information based on the user's interests and concerns and sending a push notification to the user through a virtual account; A system including:

2. The system according to claim 1 , wherein the pre-learning enables provision of information and generation of search results that reflect the user's preferences and tastes.

3. The system according to claim 1 , wherein the virtual account is capable of automatically performing actions such as posting, sending messages, and searching for information on the user's information and communication services.

Images