System

Abstract

A system is provided.SOLUTION: This system includes a means for acquiring the action history and contribution contents of a user, a means for storing the acquired action history and contribution contents in a data storage, a means for analyzing the stored data, and for extracting a frequently appearing keyword, a means for generating information based on the analyzed result, and a means for presenting the generated information to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, everyone has experienced the "tip of the tongue phenomenon," a memory lapse that leaves them thinking, "What was that again?" This phenomenon occurs particularly frequently among busy working adults and the elderly, who are exposed to a large amount of information on a daily basis. Furthermore, failure to recall a memory can lead to feelings of frustration, waste of time, and even stress. There is a need for a system that can solve these problems and efficiently support memory recall. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system including a means for acquiring a user's behavioral history and posted content, a means for storing the acquired behavioral history and posted content in a data storage, a means for analyzing the stored data and extracting frequently occurring keywords, a means for generating information based on the analysis results, and a means for presenting the generated information to the user. This system allows users to efficiently eliminate the "tip of the tongue phenomenon" and quickly recall necessary information. Furthermore, by performing analysis based on the behavioral history and posted content acquired, particularly from social networking services, it becomes possible to provide memory recall support that is closely related to the user's daily life.

[0006] "User" refers to an individual or specific user account that uses the system.

[0007] "Behavioral history" refers to a record of a series of actions or events that a user has taken in the past.

[0008] "Posted content" refers to information such as text, images, and videos posted by users on social networking services or other platforms.

[0009] "Data storage" refers to a storage device or database that stores collected data.

[0010] "Analysis" refers to the process of finding meaning and patterns in collected data.

[0011] "Frequent keywords" refer to words or phrases that appear frequently within a particular dataset as a result of analysis.

[0012] "Means of generation" refers to the techniques and methods for creating new text or information based on the analysis results.

[0013] "Presenting means" refers to a method or device for displaying or communicating the generated information to a user.

[0014] "Social networking service" refers to an online platform that enables users to communicate and share information with each other.

[0015] A "text generation algorithm" refers to a computational method or model for generating natural-sounding text based on input data. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] As a specific example of a form for implementing the present invention, a system will be described that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "what was that?", based on a user's daily activities and SNS posts.

[0038] Basic configuration

[0039] The system mainly consists of the following elements:

[0040] 1. Data Collection Module

[0041] 2. Database

[0042] 3. Data Analysis Module

[0043] 4. Generation AI

[0044] 5. User Interface

[0045] Data Collection Module

[0046] Device:

[0047] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on platforms such as Twitter and Facebook.

[0048] Database

[0049] server:

[0050] The server stores the collected data in a database, which is managed as an individual personal database for each user, with the collected behavioral history and posted content stored in chronological order.

[0051] Data Analysis Module

[0052] server:

[0053] The server analyzes the data in the database to extract frequently occurring keywords, using natural language processing techniques to calculate the frequency of occurrence of specific words and phrases.

[0054] Generation AI

[0055] server:

[0056] Based on the analysis results, the generative AI works to generate text and images related to the information the user wants to recall, using an advanced text generation algorithm such as GPT-3.

[0057] User Interface (UI)

[0058] Chatbots:

[0059] The generated information is presented to the user via the chatbot. When a user asks, "I can't remember the name of the movie I saw recently," the chatbot will provide a specific answer based on the analysis and generated results, such as, "You recently posted about a movie called ____. Is that what you're trying to remember?" This allows the user to quickly recall the desired information.

[0060] Specific examples

[0061] For example, consider a situation where a user says, "I can't remember the title of the song I recently listened to." In this case, the system operates as follows.

[0062] 1. The device retrieves related posts such as "music," "song title," and "listened to" from the user's SNS posts.

[0063] 2. The server stores these posts in a database and the analytics module analyzes them.

[0064] 3. Frequently used keywords such as "song," "recent," and "favorite" are extracted.

[0065] 4. The generative AI generates content such as, "You recently posted about the song 'XX'."

[0066] 5. The chatbot presents this generated information to the user to assist in memory recall.

[0067] In this way, the present invention can effectively eliminate the memory lapse phenomenon of users and improve the quality of daily life.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The user accesses the system and gives permission for data collection. The device connects to the user's social networking service (SNS) account and obtains the user's posts and behavioral history via API.

[0071] Step 2:

[0072] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[0073] Step 3:

[0074] The server stores the received data in the data storage. The database manages the individual personal data of each user and stores the data in chronological order.

[0075] Step 4:

[0076] The server retrieves user data from the data storage and analyzes it through a data analysis module. The server then uses natural language processing technology to extract frequently occurring keywords from the posts. For example, it calculates the frequency of occurrence of specific words or phrases such as "movies," "music," and "work."

[0077] Step 5:

[0078] The server uses generative AI to generate text based on the analysis results. The generative AI uses a text generation algorithm, such as GPT-3, to generate text and images related to the information the user wants to recall. For example, it creates text in the form of a specific question, such as, "Isn't the movie you saw recently ____?"

[0079] Step 6:

[0080] The chatbot presents the generated text and images to the user. When the user asks, "I can't remember the name of a movie I saw recently," the chatbot provides an answer based on the analysis results.

[0081] Step 7:

[0082] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, they can enter additional keywords or information and the system will analyze and generate it again.

[0083] In this way, a series of processes is completed that allows the system to identify and quickly resolve the user's memory lapse phenomenon (tip of the tongue phenomenon).

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] In users' daily lives, the "tip of the tongue phenomenon," where they are unable to remember specific information, frequently occurs, causing stress and reduced efficiency. The present invention aims to provide a system that quickly and effectively resolves this "tip of the tongue phenomenon" based on the user's past posts and activity history on social networking services (SNS). The present invention also aims to improve the user's quality of life by providing fast and accurate information.

[0087] 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.

[0088] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for analyzing the saved data and extracting frequently occurring keywords, means for generating information using a generation AI, and means for presenting the generated information to the user through a user interface, thereby enabling the user to quickly and accurately recall forgotten information.

[0089] "Behavioral history" is a record of specific actions and operations that a user performs in their daily life or online activities.

[0090] "Posted content" refers to text, images, videos, and other media content shared by users on platforms such as social networking services (SNS).

[0091] "Data storage" refers to a database or storage device for managing and storing acquired and saved behavioral history and posted content.

[0092] "Analysis" is the process of extracting and analyzing specific information and patterns from stored data.

[0093] "Frequent keywords" are words or phrases that appear repeatedly in the data analyzed, and are important indicators of user interests and behavior.

[0094] "Generative AI" refers to artificial intelligence techniques and algorithms that generate the information a user wants to recall based on analysis results.

[0095] A "text generation algorithm" is a computational procedure or model for generating natural language text based on given input data.

[0096] "User interface" refers to the interaction means by which generated information is presented to a user and by which the user interacts with the system.

[0097] The present invention provides a system that eliminates the "tip-of-the-tongue phenomenon" based on a user's daily activities and posts on social networking services (SNS). This system mainly consists of the following elements:

[0098] Data Collection Module

[0099] With the user's permission, the device retrieves the user's activity history and posts from social media platforms, including text, images, and videos shared on popular social media platforms such as Twitter and Facebook. The device retrieves the data using APIs and sends it for further processing.

[0100] Database

[0101] The server saves the data collected from the device in data storage. The data storage is a database that is managed as a personal database for each user. The database stores information such as user ID, posted content, and posting date and time in chronological order.

[0102] Data Analysis Module

[0103] The server analyzes the data in the database and extracts frequently occurring keywords. This analysis uses natural language processing (NLP) technology to calculate the frequency of occurrence of specific words and phrases and understand user interests and behavioral patterns.

[0104] Generation AI

[0105] The generative AI works based on the analysis results to generate text and images related to the information the user wants to recall. The generative AI uses an advanced text generation algorithm, such as GPT-3, to generate information related to the user's past actions and posts based on the analyzed frequently used keywords.

[0106] As an example, the prompt sentence to be input to the generative AI model is shown below.

[0107] "Guess what information a user wants to remember based on what they've recently posted."

[0108] or

[0109] "For a user who has forgotten the title of a song they recently listened to, please analyze their past social media posts and generate text to provide relevant information."

[0110] User Interface (UI)

[0111] The chatbot presents the generated information to the user. For example, if a user says, "I can't remember the title of the movie I saw recently," the chatbot will respond based on the analysis results and information generated by the generation AI, saying, "You recently posted about a movie called ____. Is that what you're trying to remember?" Through this interface, users can quickly obtain the desired information.

[0112] Specific examples

[0113] For example, if a user says, "I can't remember the title of the song I recently listened to," the system works as follows: First, the device retrieves related posts such as "music," "song name," and "listened to" from the social networking site. Next, the server stores these posts in a database, and the analysis module analyzes the data to extract frequently occurring keywords. Next, the generation AI generates content such as, "You recently posted about the song 'XX'." The chatbot then presents this generated information to the user, supporting memory recall.

[0114] As described above, the present invention can effectively resolve memory lapses based on a user's daily activities and SNS posts, thereby improving the quality of daily life.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1:

[0117] With the user's permission, the device obtains the user's behavioral history and posted content from the SNS. Specifically, the device uses the Twitter or Facebook API to collect data on posts, images, and videos that the user has made public. The data obtained at this time includes the post text, media link, and timestamp. (Input) User post data obtained from the SNS API. (Output) Obtained post content and behavioral history data.

[0118] Step 2:

[0119] The server stores data collected from the device in a database. First, the device sends the data it collected to the server. Next, the server records this data in a database managed individually for each user. The stored data includes the user ID, posted content, and posting date and time, and is used for subsequent analysis. (Input) Posted content and behavioral history data sent from the device. (Output) Record of behavioral history and posted content stored in the database.

[0120] Step 3:

[0121] The server analyzes the data in the database and extracts frequently occurring keywords. The server uses natural language processing (NLP) technology to tokenize the acquired text data and calculate the frequency of word occurrence. This allows important keywords that reflect the user's recent behavior and interests to be extracted. (Input) Text data stored in the database. (Output) A list of extracted frequently occurring keywords.

[0122] Step 4:

[0123] Based on the extracted frequent keywords, the generation AI generates text and images related to the information the user wants to recall. The generation AI uses a text generation algorithm such as GPT-3 to generate optimal information based on the prompt text. In this process, appropriate sentences and media links are output according to the instructions contained in the prompt text. (Input) Extracted frequent keywords and prompt text. (Output) Generated text and related media links.

[0124] Step 5:

[0125] The chatbot presents the generated information to the user. When a user inquires about specific information, the chatbot provides the user with text and media links generated by the generative AI. For example, if a user inquires, "I can't remember the name of the movie I saw recently," the chatbot will reply, "You recently posted about a movie called ____." (Input) The user's inquiry and generated text. (Output) The answer presented to the user.

[0126] Based on the above steps, the system can effectively resolve memory lapses based on users' daily activities and SNS posts, thereby improving the quality of daily life.

[0127] (Application example 1)

[0128] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0129] In factories, staff sometimes experience memory lapses while working. This can lead to an inability to remember specific work procedures or work content, which can reduce work efficiency and affect productivity and safety. Conventional methods require staff to manually go back through records, making it difficult to quickly obtain the necessary information. There is a need for a system that can solve this issue and support staff in performing their work effectively.

[0130] 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.

[0131] In this invention, the server includes a means for acquiring the user's work history and recorded content, a means for saving the acquired work history and recorded content in data storage, and a means for analyzing the saved data and extracting frequently occurring keywords, which allows staff to quickly recall necessary information in real time, improving work efficiency and safety.

[0132] "Users" refer to staff members who perform tasks within the factory.

[0133] "Work history" refers to records that include the work content and procedures that a user performed within a factory.

[0134] "Record contents" refers to data and notes related to the user's work, as well as information related thereto.

[0135] "Data storage" refers to a storage device or system for storing acquired business history and record content.

[0136] "Analysis" refers to the process of extracting and analyzing specific information from business history and record content stored in data storage.

[0137] "Frequent keywords" are important words or phrases that appear repeatedly in the analyzed business history and record contents.

[0138] "Generation" refers to the process of creating and providing new necessary information based on the analysis results.

[0139] A "robot assistant" is a mechanical device or system that provides users with the information they need and supports their work.

[0140] "Business system" is a general term for software and hardware used to support business management and work progress within a factory.

[0141] A "communication platform" is a system that allows users to exchange information and communicate about business matters.

[0142] A "text generation algorithm" is a computational method for automatically generating text based on input data.

[0143] MODE FOR CARRYING OUT THE INVENTION

[0144] As an embodiment of this invention, we will explain a system that uses a "robot assistant" to resolve the memory gaps of factory staff. This system acquires the user's work history and recorded content and provides necessary information in real time, thereby improving work efficiency.

[0145] Basic system configuration

[0146] 1. Data Collection Module

[0147] Means of obtaining user work history and record contents: Data is collected from daily work reports that record the work content and procedures performed by users in the factory, business systems, and communication platforms (e.g., Slack, Teams).

[0148] 2. Database

[0149] Data storage: The collected data is stored in a data storage such as an SQLite database. This data storage manages the collected work history and record contents in chronological order and holds data for each individual user.

[0150] 3. Data Analysis Module

[0151] Data analysis method: Analyzes stored data and extracts frequently occurring keywords. Natural language processing technology is used for the analysis to calculate the frequency of occurrence of specific words and phrases.

[0152] 4. Generation AI

[0153] A method of generating information using a text generation algorithm: Based on the analysis results, a generation AI operates to generate text related to the information the user wants to recall. This generation AI uses an advanced text generation algorithm, such as GPT-3.

[0154] 5. User Interface

[0155] A means of presenting information to users via a robot assistant: The generated information is provided to users through a robot assistant (a robot with a voice and a display), allowing users to quickly obtain the information they need during work and carry out their work smoothly.

[0156] Processing Details

[0157] The processing of this system will now be described in detail with reference to a specific example.

[0158] 1. Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms such as Slack. For example, it obtains records such as "I performed maintenance on Machine A."

[0159] 2. Data storage: The server stores the collected data in an SQLite database. This data is managed for each user and organized in chronological order.

[0160] 3. Data analysis: The server analyzes the stored data and extracts frequently occurring keywords, such as "maintenance," "machine A," and "parts replacement."

[0161] 4. Information generation: Based on the analysis results, the generation AI generates content such as, "Recently, you performed maintenance on Machine A. It also appears that you replaced parts."

[0162] 5. Information presentation: The generated information is presented to the user via a robot assistant. It can be presented visually via audio or a display, allowing the user to quickly obtain the information they need.

[0163] Specific examples

[0164] In a situation where the user cannot remember the details of the recent maintenance performed on Machine A, the system operates as follows:

[0165] 1. Data collection: The terminal acquires business records including "Machine A maintenance" and "parts replacement."

[0166] 2. Data storage: The server stores these data in an SQLite database.

[0167] 3. Data analysis: Extract frequently occurring keywords such as "maintenance," "machine A," and "parts replacement."

[0168] 4. Information generation: For example, the generation AI generates information based on the following prompt sentence:

[0169] Prompt: What work have you done recently? Hint: Maintenance on machine A.

[0170] 5. Information presentation: The robot assistant will provide the user with a voice message saying, "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts."

[0171] This allows users to quickly recall necessary information, improving work efficiency and safety.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] System program processing flow

[0174] Step 1:

[0175] Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms (e.g., Slack, Teams). Specifically, the device sends API requests to these data sources to obtain text data from daily reports and system log data.

[0176] Input: Daily work reports, business systems, Slack data (e.g., "2023-10-01: Maintenance performed on Machine A").

[0177] Output: A list of the retrieved data.

[0178] Step 2:

[0179] Data storage: The server stores the collected data in a data storage such as SQLite. Specifically, the server establishes a connection to the data storage and inserts the acquired data into the database in chronological order for each user.

[0180] Input: Collected work history and record contents.

[0181] Output: Data stored in data storage.

[0182] Step 3:

[0183] Data analysis: The server analyzes the stored data and extracts frequently occurring keywords. Specifically, the server uses natural language processing techniques (e.g., morphological analysis) to analyze the text data and calculate the frequency of occurrence of important keywords.

[0184] Input: Data stored in data storage.

[0185] Output: A list of frequently occurring keywords (e.g., "machine A," "maintenance," "parts replacement").

[0186] Step 4:

[0187] Information generation: The server generates information using a generation AI (e.g., GPT-3) based on frequently occurring keywords. Specifically, the server sends a prompt to the generation AI and receives the resulting text.

[0188] Input: Frequently used keywords, prompt sentence.

[0189] Output: Generated text (e.g., "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts.").

[0190] Step 5:

[0191] Information presentation: The server presents the generated information to the user via the robot assistant. Specifically, the robot assistant provides the generated information to the user using voice synthesis technology or a display.

[0192] Input: The generated text.

[0193] Output: The information presented to the user.

[0194] This configuration allows users to quickly recall necessary information, improving work efficiency and safety.

[0195] 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.

[0196] As a specific example of a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[0197] Basic configuration

[0198] The system mainly consists of the following elements:

[0199] 1. Data Collection Module

[0200] 2. Database

[0201] 3. Data Analysis Module

[0202] 4. Generation AI

[0203] 5. User Interface

[0204] 6. Emotion Engine

[0205] Data Collection Module

[0206] Device:

[0207] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on the SNS platform.

[0208] Database

[0209] server:

[0210] The server stores the collected data in a database. This database manages the personal data of each user, and stores the collected behavioral history and posted content in chronological order.

[0211] Data Analysis Module

[0212] server:

[0213] The server analyzes the data in the database and uses an emotion engine to identify the user's emotional state. It also extracts frequently occurring keywords and analyzes them based on the user's emotional state and the trends of the content of posts.

[0214] Generation AI

[0215] server:

[0216] Based on the emotional state identified by the emotion engine, the generative AI generates relevant text and images. For example, if the user is feeling stressed, it can provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as GPT-3.

[0217] User Interface (UI)

[0218] Chatbots:

[0219] The generated information is presented to the user via a chatbot. When a user asks, "I can't remember the title of a song I heard recently," the chatbot will provide a response based on the analysis results, such as, "You recently posted about 'XX.' Is this the song you want to remember?"

[0220] Emotion Engine

[0221] server:

[0222] The emotion engine analyzes users' text and posts and identifies their emotional state using natural language processing technology. For example, if a post contains emotional expressions such as "fun," "happy," or "sad," the engine detects this and uses it for analysis. The emotion engine then integrates the user's emotional state into the analysis results, enabling the provision of more personalized information.

[0223] Specific examples

[0224] For example, consider a situation where a user cannot remember the title of a movie they recently watched. In this case, the system operates as follows.

[0225] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting."

[0226] 2. The server stores these posts in a database.

[0227] 3. The server retrieves the data from the database, and the emotion engine analyzes the user's emotional state. If the user posts comments such as "It was fun" or "I was moved," these will also be included in the analysis.

[0228] 4. The analysis module extracts the frequently occurring keywords "movie," "watched," and "interesting."

[0229] 5. The generative AI generates the question, "Isn't 'XX' the movie that moved you the most recently?"

[0230] 6. The chatbot presents this generated information to the user to assist in memory recall.

[0231] In this way, by providing information that takes into account the user's emotional state, the present invention can effectively resolve the memory lapses of the user and improve the quality of daily life.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] The user accesses the system and grants permission for data collection and analysis. The device connects the SNS account to the system and obtains the user's postings and behavioral history via API.

[0235] Step 2:

[0236] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[0237] Step 3:

[0238] The server stores the received data in the data storage. The database manages the individual personal data for each user and stores the acquired data in chronological order.

[0239] Step 4:

[0240] The server sends the stored data to a data analysis module, which uses natural language processing technology to analyze the posts, calculate the frequency of specific keywords and phrases, and extract highly relevant keywords.

[0241] Step 5:

[0242] Based on the analysis results, the server uses an emotion engine to analyze the user's emotional state. The emotion engine reads emotions from the text and identifies emotions such as "happy," "sad," and "excited."

[0243] Step 6:

[0244] The server combines the analyzed keywords with the emotional state and sends the combined results to the generation AI, which then uses a text generation algorithm such as GPT-3 to generate a specific answer. For example, it generates text such as, "You recently posted about the movie 'XX.' Was it moving?"

[0245] Step 7:

[0246] The chatbot presents the generated text to the user. When the user makes a query such as "I can't remember the title of the song I listened to recently," the chatbot will provide an appropriate answer based on the analysis and generation results.

[0247] Step 8:

[0248] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, the user can enter additional keywords or information, and the system will analyze and generate it again.

[0249] This allows the system to efficiently resolve memory lapses, reduce user stress, and quickly provide the information the user desires, while taking into account the user's emotional state.

[0250] Example 2

[0251] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0252] In today's information society, users consume a huge amount of information every day, which can make it difficult to recall important information. Effective methods are needed to resolve the "tip of the tongue phenomenon," a situation in which users want to recall specific information but are unable to. Furthermore, by taking the user's emotional state into consideration, more personalized support can be provided. To address this issue, a system is needed that analyzes a user's behavioral history and posted content, identifies their emotional state, and generates and provides appropriate information.

[0253] 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.

[0254] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in a data storage, means for analyzing the saved data and identifying the user's emotional state, means for extracting frequently occurring keywords, means for generating related information based on the analysis results and the extracted keywords, and means for presenting the generated information to the user. This eliminates the problem of memory lapses in the user's memory and enables the provision of personalized information that takes into account the user's emotional state.

[0255] "Behavioral history" is a record of specific actions or operations that a user has performed in the past, including web browsing, application usage, and location information.

[0256] "Posted content" refers to information such as text, images, and videos that users make public on social networking services, blogs, forums, etc.

[0257] "Data storage" means a physical or virtual repository for storing captured data, including databases and cloud storage.

[0258] An "emotional state" refers to the emotional or feeling state a user is experiencing at a particular moment, including emotions such as "happy," "sad," and "angry."

[0259] "Frequent keywords" are words or phrases that are frequently used within a certain period of time, as identified through data analysis.

[0260] "Related information" is information that is useful to users and is generated based on the analysis results and extracted keywords. This includes text, images, videos, etc.

[0261] A "text generation algorithm" is a computational method for automatically generating natural language text based on input prompts and data, including neural network-based models.

[0262] "User presentation" refers to the interface or device through which the generated information is presented to the user, including chatbots, notification systems, mobile apps, etc.

[0263] As a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[0264] Basic configuration

[0265] The system mainly consists of the following elements:

[0266] 1. Data Collection Module

[0267] 2. Data Storage

[0268] 3. Data Analysis Module

[0269] 4. Generation AI

[0270] 5. User Interface

[0271] 6. Emotion Engine

[0272] Data Collection Module

[0273] Terminal

[0274] With the user's permission, the device acquires the user's behavioral history and posted content from social networking services (SNS). For example, it collects text, images, and videos that the user has shared on the SNS platform. This data collection is done using the SNS API. Specifically, it acquires user posted data using the Twitter API or Facebook API.

[0275] Data Storage

[0276] server

[0277] The data collected by the server is stored in data storage. This data storage uses a relational database such as MySQL or PostgreSQL, and individual personal data for each user is stored in chronological order. The stored data includes fields such as "user ID," "post content," and "post date and time."

[0278] Data Analysis Module

[0279] server

[0280] The server retrieves data from the data storage and uses an emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing technology (e.g., BERT or GPT-3) to analyze the content of posts and extract frequently occurring keywords. It also analyzes the user's emotional state and trends in the content of posts.

[0281] Generation AI

[0282] server

[0283] The generative AI generates relevant text and images based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, it will provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as OpenAI's GPT-3.

[0284] User Interface (UI)

[0285] Chatbots

[0286] The generated information is presented to the user via a chatbot. For example, if a user asks, "I can't remember the title of the song I heard recently," the chatbot will provide an answer based on the analysis results, such as, "You recently posted about 'XX'. Is this the song you want to remember?" The chatbot uses Dialogflow, Microsoft Bot Framework, etc.

[0287] Emotion Engine

[0288] server

[0289] The emotion engine analyzes the user's text and post content and identifies their emotional state using natural language processing technology. For example, if the content contains emotional expressions such as "fun," "happy," or "sad," it detects these and uses them for analysis. The emotion engine uses Google's Natural Language API and IBM Watson's Tone Analyzer, among others.

[0290] Specific examples

[0291] For example, consider a situation where a user cannot remember the title of a movie they recently saw. In this case, the system would act as follows:

[0292] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting." For example, it uses the Twitter API to collect the user's past tweets.

[0293] 2. The server stores these posts in a MySQL database.

[0294] 3. The server retrieves the data from the database, and the emotion engine uses BERT to analyze the user's emotional state. If the user posts comments such as "I had fun" or "I was moved," these will also be included in the analysis.

[0295] 4. The analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" using a Python NLP library (e.g., spaCy).

[0296] 5. The generative AI uses GPT-3 to generate text such as, "Isn't 'XX' the movie you recently saw that moved you?"

[0297] 6. The chatbot uses Dialogflow to present this generated information to the user to assist in memory recall.

[0298] Example prompt sentence:

[0299] "I can't remember the title of the last movie I saw. What movie moved me?"

[0300] In this way, the system can effectively eliminate the memory lapse phenomenon of the user.

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Step 1: Data collection

[0303] Terminal

[0304] The user authorizes access to the social networking site. On this premise, the device uses the social networking site's API (for example, Twitter API or Facebook API) to obtain the user's behavioral history and posted content.

[0305] Input: Social media account credentials

[0306] Output: User posted data (text, images, videos)

[0307] Specific operation: The device calls the SNS API, sends a "Get recent posts" request, and retrieves the 100 most recent posts from the SNS.

[0308] Step 2: Save data

[0309] server

[0310] The acquired user's SNS data is received and saved in data storage (e.g. MySQL database). When saved, the post content, posting date and time, user ID, etc. are also recorded.

[0311] Input: User submitted data

[0312] Output: Post data saved in the database

[0313] Specific operation: The server executes the SQL statement "INSERT INTO user_data (user_id, post_content, post_date) VALUES (?, ?, ?)" to store the information in the database.

[0314] Step 3: Sentiment Analysis

[0315] server

[0316] User posted data is retrieved from the database and sentiment analysis is performed using natural language processing technology. Specifically, sentiment analysis is performed using a sentiment engine (e.g., BERT or Google Natural Language API).

[0317] Input: Post data stored in the database

[0318] Output: Parsed emotional state (e.g. positive, negative, neutral, etc.)

[0319] Specific operation: The server executes the SQL statement "SELECT post_content FROM user_data WHERE user_id = ?", passes the retrieved post text to the emotion engine, and receives the analysis results.

[0320] Step 4: Keyword extraction

[0321] server

[0322] Based on the sentiment analysis results, frequently occurring keywords are extracted using a natural language processing library. Specifically, an NLP library (e.g., spaCy) is used.

[0323] Input: Parsed emotional state and post data

[0324] Output: A list of extracted frequent keywords

[0325] Specific operation: Based on the results of the sentiment analysis, the server performs a process to extract frequently occurring words such as "movie" and "moving."

[0326] Step 5: Information Generation

[0327] Generation AI

[0328] Based on the results of sentiment analysis and keyword extraction, relevant information is generated using a generative AI model (e.g., GPT-3).

[0329] Input: Sentiment analysis results, frequently used keywords

[0330] Output: Generated text or image

[0331] Specific operation: The generative AI receives the prompt sentence "What movie did the user see recently that moved you?" as input and generates appropriate information.

[0332] Step 6: Information presentation

[0333] Chatbots

[0334] The generated information is presented to the user via a user interface (e.g., a chatbot), and responses to inquiries are generated using Dialogflow or the Microsoft Bot Framework.

[0335] Input: Generated information (text or image)

[0336] Output: Information presented to the user

[0337] Specific behavior: The chatbot sends the user a message saying, "Isn't 'XX' the movie that moved you the most recently?"

[0338] Through this specific processing flow, the system can effectively eliminate the user's "tip-of-the-tongue phenomenon" and improve the quality of daily life.

[0339] (Application example 2)

[0340] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0341] In recent years, there has been an increasing demand for systems that provide personalized information by analyzing users' behavioral history and posted content. However, current systems have difficulty providing information that takes into account the user's emotional state, resulting in a problem of a decline in the quality of the user experience. To solve this problem, more advanced personalized information generation that takes into account the user's emotional state is required.

[0342] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for identifying the user's emotional state, means for generating information using a generative AI model, and means for presenting the generated information to the user through a user interface. This makes it possible to recommend more appropriate content based on the user's emotional state.

[0343] "Behavioral history" refers to the history of various actions and activities that a user performs in their daily life, including social media posts, browsing history, GPS information, etc.

[0344] "Posted content" refers to content such as text, images, and videos that users make public on social networking services (SNS) and other platforms.

[0345] "Data storage" means systems or devices for storing collected data, including cloud storage, database servers, etc.

[0346] "Emotional state" refers to the emotion a user is feeling at a particular moment, which is extracted from text analysis using natural language processing techniques.

[0347] "Frequent keywords" refer to words and phrases that frequently appear in users' posts and behavioral history, and are important indicators of trends and interests.

[0348] A "generative AI model" is an artificial intelligence algorithm that generates natural language based on large amounts of data, generating personalized information based on a user's behavioral history and emotional state.

[0349] "User interface" refers to an interface that presents generated information to users in an easy-to-understand manner, including chatbots and application screen displays.

[0350] A specific embodiment for carrying out the present invention will be described below. First, the system mainly comprises the following elements:

[0351] 1. Data collection module: Obtains user behavior history and SNS postings from the device.

[0352] 2. Data storage: The acquired behavioral history and posted content are stored on a database server.

[0353] 3. Data analysis module: Analyzes the stored data and extracts frequently occurring keywords.

[0354] 4. Emotion Engine: Analyzes user posts to identify their emotional state.

[0355] 5. Generative AI model: Generates information based on emotional state and analysis results.

[0356] 6. User Interface: Presents the generated information to the user.

[0357] The detailed operation of each element will be explained below.

[0358] Data Collection Module

[0359] With the user's permission, the device will collect the user's behavioral history and posted content from social networking services (SNS), such as text, images, and videos shared by the user on the SNS platform. This data is collected in real time.

[0360] Data Storage

[0361] The server saves the collected data in data storage. This database manages the personal data of each user, and saves the collected behavioral history and posted content in chronological order. Examples of databases that can be used include MySQL and PostgreSQL.

[0362] Data Analysis Module

[0363] The server analyzes the data in the data storage and uses natural language processing libraries (e.g., spaCy or NLTK) to extract frequently occurring keywords and phrases. This analysis reveals frequently used words and trends among users.

[0364] Emotion Engine

[0365] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's posts and uses natural language processing technology to identify emotional states such as "joy," "happy," and "sad."

[0366] Generative AI Models

[0367] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate relevant information based on the emotional state identified by the emotion engine and the analysis results. If the user is feeling stressed, the generated information will be content that encourages relaxation.

[0368] User Interface

[0369] The generated information is presented to the user via a user interface. React Native or Flutter can be used for the interface, and information can be provided in the form of a chatbot. The user can receive suggested content in an interactive format.

[0370] Specific examples

[0371] For example, if a user posts, "I can't remember the name of the last movie I saw," then:

[0372] 1. The data collection module retrieves related posts such as "movies," "watched," and "interesting" from social media.

[0373] 2. The data analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" from the posted content.

[0374] 3. The emotion engine analyzes emotions such as "It was fun" or "I was moved" from the user's posts.

[0375] 4. The generative AI model generates the text, "Isn't 'XX' the movie you recently saw that moved you the most?"

[0376] 5. The user interface presents the text to the user in the form of a chatbot.

[0377] Prompt Sentence Examples

[0378] A user says they can't remember the title of a moving movie they recently saw. Please suggest movie titles based on the following keywords and their emotional state:

[0379] Keywords: movie, watched, interesting, fun, moving

[0380] Emotional state: Positive

[0381] As described above, this system provides highly personalized information based on the user's emotional state and behavioral history.

[0382] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0383] Step 1:

[0384] With the user's permission, the device obtains the user's behavioral history and posted content from a social networking service (SNS). The input is the posted content and behavioral history data using the SNS API, and the output is a collection of this data. The device obtains the user's text, images, videos, etc. from the SNS API and sends them to the next processing step.

[0385] Step 2:

[0386] The server stores the behavioral history and posted content sent from the device in data storage (for example, a MySQL or PostgreSQL database). The input is data obtained from the device, and the output is records stored in the database. The server connects to the database and stores the input data in individual records for each user.

[0387] Step 3:

[0388] The server analyzes the data in the data storage using a natural language processing library (e.g., spaCy or NLTK) and extracts frequently occurring keywords. The input is the data stored in the database, and the output is the extracted frequently occurring keywords. The server tokenizes the text data and analyzes the frequency of occurrence to extract keywords.

[0389] Step 4:

[0390] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to identify the emotional state from the user's posted content. The input is text data in the database, and the output is the identified emotional state. The server sends the posted text to the emotion engine, which identifies the emotional state, such as positive, negative, or neutral.

[0391] Step 5:

[0392] The server generates information using a generative AI model (e.g., OpenAI GPT-3) based on the emotional state and frequent keywords identified by the emotion engine. The input is the emotional state and frequent keywords, and the output is the generated text information. The server sends the input data to the generative AI model in the form of prompts to generate personalized content.

[0393] Step 6:

[0394] The server presents the generated information to the user through a user interface. The input is the output text from the generative AI model, and the output is the information displayed to the user through the user interface. The server uses React Native or Flutter to provide information to the user in the form of a chatbot, allowing the user to easily check the generated information.

[0395] In this way, highly personalized information provision based on the user's behavioral history and emotional state is realized.

[0396] 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.

[0397] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0398] 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.

[0399] [Second embodiment]

[0400] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0412] As a specific example of a form for implementing the present invention, a system will be described that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "what was that?", based on a user's daily activities and SNS posts.

[0413] Basic configuration

[0414] The system mainly consists of the following elements:

[0415] 1. Data Collection Module

[0416] 2. Database

[0417] 3. Data Analysis Module

[0418] 4. Generation AI

[0419] 5. User Interface

[0420] Data Collection Module

[0421] Device:

[0422] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on platforms such as Twitter and Facebook.

[0423] Database

[0424] server:

[0425] The server stores the collected data in a database, which is managed as an individual personal database for each user, with the collected behavioral history and posted content stored in chronological order.

[0426] Data Analysis Module

[0427] server:

[0428] The server analyzes the data in the database to extract frequently occurring keywords, using natural language processing techniques to calculate the frequency of occurrence of specific words and phrases.

[0429] Generation AI

[0430] server:

[0431] Based on the analysis results, the generative AI works to generate text and images related to the information the user wants to recall, using an advanced text generation algorithm such as GPT-3.

[0432] User Interface (UI)

[0433] Chatbots:

[0434] The generated information is presented to the user via the chatbot. When a user asks, "I can't remember the name of the movie I saw recently," the chatbot will provide a specific answer based on the analysis and generated results, such as, "You recently posted about a movie called ____. Is that what you're trying to remember?" This allows the user to quickly recall the desired information.

[0435] Specific examples

[0436] For example, consider a situation where a user says, "I can't remember the title of the song I recently listened to." In this case, the system operates as follows.

[0437] 1. The device retrieves related posts such as "music," "song title," and "listened to" from the user's SNS posts.

[0438] 2. The server stores these posts in a database and the analytics module analyzes them.

[0439] 3. Frequently used keywords such as "song," "recent," and "favorite" are extracted.

[0440] 4. The generative AI generates content such as, "You recently posted about the song 'XX'."

[0441] 5. The chatbot presents this generated information to the user to assist in memory recall.

[0442] In this way, the present invention can effectively eliminate the memory lapse phenomenon of users and improve the quality of daily life.

[0443] The processing flow will be explained below.

[0444] Step 1:

[0445] The user accesses the system and gives permission for data collection. The device connects to the user's social networking service (SNS) account and obtains the user's posts and behavioral history via API.

[0446] Step 2:

[0447] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[0448] Step 3:

[0449] The server stores the received data in the data storage. The database manages the individual personal data of each user and stores the data in chronological order.

[0450] Step 4:

[0451] The server retrieves user data from the data storage and analyzes it through a data analysis module. The server then uses natural language processing technology to extract frequently occurring keywords from the posts. For example, it calculates the frequency of occurrence of specific words or phrases such as "movies," "music," and "work."

[0452] Step 5:

[0453] The server uses generative AI to generate text based on the analysis results. The generative AI uses a text generation algorithm, such as GPT-3, to generate text and images related to the information the user wants to recall. For example, it creates text in the form of a specific question, such as, "Isn't the movie you saw recently ____?"

[0454] Step 6:

[0455] The chatbot presents the generated text and images to the user. When the user asks, "I can't remember the name of a movie I saw recently," the chatbot provides an answer based on the analysis results.

[0456] Step 7:

[0457] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, they can enter additional keywords or information and the system will analyze and generate it again.

[0458] In this way, a series of processes is completed that allows the system to identify and quickly resolve the user's memory lapse phenomenon (tip of the tongue phenomenon).

[0459] Example 1

[0460] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0461] In users' daily lives, the "tip of the tongue phenomenon," where they are unable to remember specific information, frequently occurs, causing stress and reduced efficiency. The present invention aims to provide a system that quickly and effectively resolves this "tip of the tongue phenomenon" based on the user's past posts and activity history on social networking services (SNS). The present invention also aims to improve the user's quality of life by providing fast and accurate information.

[0462] 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.

[0463] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for analyzing the saved data and extracting frequently occurring keywords, means for generating information using a generation AI, and means for presenting the generated information to the user through a user interface, thereby enabling the user to quickly and accurately recall forgotten information.

[0464] "Behavioral history" is a record of specific actions and operations that a user performs in their daily life or online activities.

[0465] "Posted content" refers to text, images, videos, and other media content shared by users on platforms such as social networking services (SNS).

[0466] "Data storage" refers to a database or storage device for managing and storing acquired and saved behavioral history and posted content.

[0467] "Analysis" is the process of extracting and analyzing specific information and patterns from stored data.

[0468] "Frequent keywords" are words or phrases that appear repeatedly in the data analyzed, and are important indicators of user interests and behavior.

[0469] "Generative AI" refers to artificial intelligence techniques and algorithms that generate the information a user wants to recall based on analysis results.

[0470] A "text generation algorithm" is a computational procedure or model for generating natural language text based on given input data.

[0471] "User interface" refers to the interaction means by which generated information is presented to a user and by which the user interacts with the system.

[0472] The present invention provides a system that eliminates the "tip-of-the-tongue phenomenon" based on a user's daily activities and posts on social networking services (SNS). This system mainly consists of the following elements:

[0473] Data Collection Module

[0474] With the user's permission, the device retrieves the user's activity history and posts from social media platforms, including text, images, and videos shared on popular social media platforms such as Twitter and Facebook. The device retrieves the data using APIs and sends it for further processing.

[0475] Database

[0476] The server saves the data collected from the device in data storage. The data storage is a database that is managed as a personal database for each user. The database stores information such as user ID, posted content, and posting date and time in chronological order.

[0477] Data Analysis Module

[0478] The server analyzes the data in the database and extracts frequently occurring keywords. This analysis uses natural language processing (NLP) technology to calculate the frequency of occurrence of specific words and phrases and understand user interests and behavioral patterns.

[0479] Generation AI

[0480] The generative AI works based on the analysis results to generate text and images related to the information the user wants to recall. The generative AI uses an advanced text generation algorithm, such as GPT-3, to generate information related to the user's past actions and posts based on the analyzed frequently used keywords.

[0481] As an example, the prompt sentence to be input to the generative AI model is shown below.

[0482] "Guess what information a user wants to remember based on what they've recently posted."

[0483] or

[0484] "For a user who has forgotten the title of a song they recently listened to, please analyze their past social media posts and generate text to provide relevant information."

[0485] User Interface (UI)

[0486] The chatbot presents the generated information to the user. For example, if a user says, "I can't remember the title of the movie I saw recently," the chatbot will respond based on the analysis results and information generated by the generation AI, saying, "You recently posted about a movie called ____. Is that what you're trying to remember?" Through this interface, users can quickly obtain the desired information.

[0487] Specific examples

[0488] For example, if a user says, "I can't remember the title of the song I recently listened to," the system works as follows: First, the device retrieves related posts such as "music," "song name," and "listened to" from the social networking site. Next, the server stores these posts in a database, and the analysis module analyzes the data to extract frequently occurring keywords. Next, the generation AI generates content such as, "You recently posted about the song 'XX'." The chatbot then presents this generated information to the user, supporting memory recall.

[0489] As described above, the present invention can effectively resolve memory lapses based on a user's daily activities and SNS posts, thereby improving the quality of daily life.

[0490] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0491] Step 1:

[0492] With the user's permission, the device obtains the user's behavioral history and posted content from the SNS. Specifically, the device uses the Twitter or Facebook API to collect data on posts, images, and videos that the user has made public. The data obtained at this time includes the post text, media link, and timestamp. (Input) User post data obtained from the SNS API. (Output) Obtained post content and behavioral history data.

[0493] Step 2:

[0494] The server stores data collected from the device in a database. First, the device sends the data it collected to the server. Next, the server records this data in a database managed individually for each user. The stored data includes the user ID, posted content, and posting date and time, and is used for subsequent analysis. (Input) Posted content and behavioral history data sent from the device. (Output) Record of behavioral history and posted content stored in the database.

[0495] Step 3:

[0496] The server analyzes the data in the database and extracts frequently occurring keywords. The server uses natural language processing (NLP) technology to tokenize the acquired text data and calculate the frequency of word occurrence. This allows important keywords that reflect the user's recent behavior and interests to be extracted. (Input) Text data stored in the database. (Output) A list of extracted frequently occurring keywords.

[0497] Step 4:

[0498] Based on the extracted frequent keywords, the generation AI generates text and images related to the information the user wants to recall. The generation AI uses a text generation algorithm such as GPT-3 to generate optimal information based on the prompt text. In this process, appropriate sentences and media links are output according to the instructions contained in the prompt text. (Input) Extracted frequent keywords and prompt text. (Output) Generated text and related media links.

[0499] Step 5:

[0500] The chatbot presents the generated information to the user. When a user inquires about specific information, the chatbot provides the user with text and media links generated by the generative AI. For example, if a user inquires, "I can't remember the name of the movie I saw recently," the chatbot will reply, "You recently posted about a movie called ____." (Input) The user's inquiry and generated text. (Output) The answer presented to the user.

[0501] Based on the above steps, the system can effectively resolve memory lapses based on users' daily activities and SNS posts, thereby improving the quality of daily life.

[0502] (Application example 1)

[0503] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0504] In factories, staff sometimes experience memory lapses while working. This can lead to an inability to remember specific work procedures or work content, which can reduce work efficiency and affect productivity and safety. Conventional methods require staff to manually go back through records, making it difficult to quickly obtain the necessary information. There is a need for a system that can solve this issue and support staff in performing their work effectively.

[0505] 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.

[0506] In this invention, the server includes a means for acquiring the user's work history and recorded content, a means for saving the acquired work history and recorded content in data storage, and a means for analyzing the saved data and extracting frequently occurring keywords, which allows staff to quickly recall necessary information in real time, improving work efficiency and safety.

[0507] "Users" refer to staff members who perform tasks within the factory.

[0508] "Work history" refers to records that include the work content and procedures that a user performed within a factory.

[0509] "Record contents" refers to data and notes related to the user's work, as well as information related thereto.

[0510] "Data storage" refers to a storage device or system for storing acquired business history and record content.

[0511] "Analysis" refers to the process of extracting and analyzing specific information from business history and record content stored in data storage.

[0512] "Frequent keywords" are important words or phrases that appear repeatedly in the analyzed business history and record contents.

[0513] "Generation" refers to the process of creating and providing new necessary information based on the analysis results.

[0514] A "robot assistant" is a mechanical device or system that provides users with the information they need and supports their work.

[0515] "Business system" is a general term for software and hardware used to support business management and work progress within a factory.

[0516] A "communication platform" is a system that allows users to exchange information and communicate about business matters.

[0517] A "text generation algorithm" is a computational method for automatically generating text based on input data.

[0518] MODE FOR CARRYING OUT THE INVENTION

[0519] As an embodiment of this invention, we will explain a system that uses a "robot assistant" to resolve the memory gaps of factory staff. This system acquires the user's work history and recorded content and provides necessary information in real time, thereby improving work efficiency.

[0520] Basic system configuration

[0521] 1. Data Collection Module

[0522] Means of obtaining user work history and record contents: Data is collected from daily work reports that record the work content and procedures performed by users in the factory, business systems, and communication platforms (e.g., Slack, Teams).

[0523] 2. Database

[0524] Data storage: The collected data is stored in a data storage such as an SQLite database. This data storage manages the collected work history and record contents in chronological order and holds data for each individual user.

[0525] 3. Data Analysis Module

[0526] Data analysis method: Analyzes stored data and extracts frequently occurring keywords. Natural language processing technology is used for the analysis to calculate the frequency of occurrence of specific words and phrases.

[0527] 4. Generation AI

[0528] A method of generating information using a text generation algorithm: Based on the analysis results, a generation AI operates to generate text related to the information the user wants to recall. This generation AI uses an advanced text generation algorithm, such as GPT-3.

[0529] 5. User Interface

[0530] A means of presenting information to users via a robot assistant: The generated information is provided to users through a robot assistant (a robot with a voice and a display), allowing users to quickly obtain the information they need during work and carry out their work smoothly.

[0531] Processing Details

[0532] The processing of this system will now be described in detail with reference to a specific example.

[0533] 1. Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms such as Slack. For example, it obtains records such as "I performed maintenance on Machine A."

[0534] 2. Data storage: The server stores the collected data in an SQLite database. This data is managed for each user and organized in chronological order.

[0535] 3. Data analysis: The server analyzes the stored data and extracts frequently occurring keywords, such as "maintenance," "machine A," and "parts replacement."

[0536] 4. Information generation: Based on the analysis results, the generation AI generates content such as, "Recently, you performed maintenance on Machine A. It also appears that you replaced parts."

[0537] 5. Information presentation: The generated information is presented to the user via a robot assistant. It can be presented visually via audio or a display, allowing the user to quickly obtain the information they need.

[0538] Specific examples

[0539] In a situation where the user cannot remember the details of the recent maintenance performed on Machine A, the system operates as follows:

[0540] 1. Data collection: The terminal acquires business records including "Machine A maintenance" and "parts replacement."

[0541] 2. Data storage: The server stores these data in an SQLite database.

[0542] 3. Data analysis: Extract frequently occurring keywords such as "maintenance," "machine A," and "parts replacement."

[0543] 4. Information generation: For example, the generation AI generates information based on the following prompt sentence:

[0544] Prompt: What work have you done recently? Hint: Maintenance on machine A.

[0545] 5. Information presentation: The robot assistant will provide the user with a voice message saying, "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts."

[0546] This allows users to quickly recall necessary information, improving work efficiency and safety.

[0547] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0548] System program processing flow

[0549] Step 1:

[0550] Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms (e.g., Slack, Teams). Specifically, the device sends API requests to these data sources to obtain text data from daily reports and system log data.

[0551] Input: Daily work reports, business systems, Slack data (e.g., "2023-10-01: Maintenance performed on Machine A").

[0552] Output: A list of the retrieved data.

[0553] Step 2:

[0554] Data storage: The server stores the collected data in a data storage such as SQLite. Specifically, the server establishes a connection to the data storage and inserts the acquired data into the database in chronological order for each user.

[0555] Input: Collected work history and record contents.

[0556] Output: Data stored in data storage.

[0557] Step 3:

[0558] Data analysis: The server analyzes the stored data and extracts frequently occurring keywords. Specifically, the server uses natural language processing techniques (e.g., morphological analysis) to analyze the text data and calculate the frequency of occurrence of important keywords.

[0559] Input: Data stored in data storage.

[0560] Output: A list of frequently occurring keywords (e.g., "machine A," "maintenance," "parts replacement").

[0561] Step 4:

[0562] Information generation: The server generates information using a generation AI (e.g., GPT-3) based on frequently occurring keywords. Specifically, the server sends a prompt to the generation AI and receives the resulting text.

[0563] Input: Frequently used keywords, prompt sentence.

[0564] Output: Generated text (e.g., "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts.").

[0565] Step 5:

[0566] Information presentation: The server presents the generated information to the user via the robot assistant. Specifically, the robot assistant provides the generated information to the user using voice synthesis technology or a display.

[0567] Input: The generated text.

[0568] Output: The information presented to the user.

[0569] This configuration allows users to quickly recall necessary information, improving work efficiency and safety.

[0570] 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.

[0571] As a specific example of a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[0572] Basic configuration

[0573] The system mainly consists of the following elements:

[0574] 1. Data Collection Module

[0575] 2. Database

[0576] 3. Data Analysis Module

[0577] 4. Generation AI

[0578] 5. User Interface

[0579] 6. Emotion Engine

[0580] Data Collection Module

[0581] Device:

[0582] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on the SNS platform.

[0583] Database

[0584] server:

[0585] The server stores the collected data in a database. This database manages the personal data of each user, and stores the collected behavioral history and posted content in chronological order.

[0586] Data Analysis Module

[0587] server:

[0588] The server analyzes the data in the database and uses an emotion engine to identify the user's emotional state. It also extracts frequently occurring keywords and analyzes them based on the user's emotional state and the trends of the content of posts.

[0589] Generation AI

[0590] server:

[0591] Based on the emotional state identified by the emotion engine, the generative AI generates relevant text and images. For example, if the user is feeling stressed, it can provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as GPT-3.

[0592] User Interface (UI)

[0593] Chatbots:

[0594] The generated information is presented to the user via a chatbot. When a user asks, "I can't remember the title of a song I heard recently," the chatbot will provide a response based on the analysis results, such as, "You recently posted about 'XX.' Is this the song you want to remember?"

[0595] Emotion Engine

[0596] server:

[0597] The emotion engine analyzes users' text and posts and identifies their emotional state using natural language processing technology. For example, if a post contains emotional expressions such as "fun," "happy," or "sad," the engine detects this and uses it for analysis. The emotion engine then integrates the user's emotional state into the analysis results, enabling the provision of more personalized information.

[0598] Specific examples

[0599] For example, consider a situation where a user cannot remember the title of a movie they recently watched. In this case, the system operates as follows.

[0600] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting."

[0601] 2. The server stores these posts in a database.

[0602] 3. The server retrieves the data from the database, and the emotion engine analyzes the user's emotional state. If the user posts comments such as "It was fun" or "I was moved," these will also be included in the analysis.

[0603] 4. The analysis module extracts the frequently occurring keywords "movie," "watched," and "interesting."

[0604] 5. The generative AI generates the question, "Isn't 'XX' the movie that moved you the most recently?"

[0605] 6. The chatbot presents this generated information to the user to assist in memory recall.

[0606] In this way, by providing information that takes into account the user's emotional state, the present invention can effectively resolve the memory lapses of the user and improve the quality of daily life.

[0607] The processing flow will be explained below.

[0608] Step 1:

[0609] The user accesses the system and grants permission for data collection and analysis. The device connects the SNS account to the system and obtains the user's postings and behavioral history via API.

[0610] Step 2:

[0611] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[0612] Step 3:

[0613] The server stores the received data in the data storage. The database manages the individual personal data for each user and stores the acquired data in chronological order.

[0614] Step 4:

[0615] The server sends the stored data to a data analysis module, which uses natural language processing technology to analyze the posts, calculate the frequency of specific keywords and phrases, and extract highly relevant keywords.

[0616] Step 5:

[0617] Based on the analysis results, the server uses an emotion engine to analyze the user's emotional state. The emotion engine reads emotions from the text and identifies emotions such as "happy," "sad," and "excited."

[0618] Step 6:

[0619] The server combines the analyzed keywords with the emotional state and sends the combined results to the generation AI, which then uses a text generation algorithm such as GPT-3 to generate a specific answer. For example, it generates text such as, "You recently posted about the movie 'XX.' Was it moving?"

[0620] Step 7:

[0621] The chatbot presents the generated text to the user. When the user makes a query such as "I can't remember the title of the song I listened to recently," the chatbot will provide an appropriate answer based on the analysis and generation results.

[0622] Step 8:

[0623] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, the user can enter additional keywords or information, and the system will analyze and generate it again.

[0624] This allows the system to efficiently resolve memory lapses, reduce user stress, and quickly provide the information the user desires, while taking into account the user's emotional state.

[0625] Example 2

[0626] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0627] In today's information society, users consume a huge amount of information every day, which can make it difficult to recall important information. Effective methods are needed to resolve the "tip of the tongue phenomenon," a situation in which users want to recall specific information but are unable to. Furthermore, by taking the user's emotional state into consideration, more personalized support can be provided. To address this issue, a system is needed that analyzes a user's behavioral history and posted content, identifies their emotional state, and generates and provides appropriate information.

[0628] 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.

[0629] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in a data storage, means for analyzing the saved data and identifying the user's emotional state, means for extracting frequently occurring keywords, means for generating related information based on the analysis results and the extracted keywords, and means for presenting the generated information to the user. This eliminates the problem of memory lapses in the user's memory and enables the provision of personalized information that takes into account the user's emotional state.

[0630] "Behavioral history" is a record of specific actions or operations that a user has performed in the past, including web browsing, application usage, and location information.

[0631] "Posted content" refers to information such as text, images, and videos that users make public on social networking services, blogs, forums, etc.

[0632] "Data storage" means a physical or virtual repository for storing captured data, including databases and cloud storage.

[0633] An "emotional state" refers to the emotional or feeling state a user is experiencing at a particular moment, including emotions such as "happy," "sad," and "angry."

[0634] "Frequent keywords" are words or phrases that are frequently used within a certain period of time, as identified through data analysis.

[0635] "Related information" is information that is useful to users and is generated based on the analysis results and extracted keywords. This includes text, images, videos, etc.

[0636] A "text generation algorithm" is a computational method for automatically generating natural language text based on input prompts and data, including neural network-based models.

[0637] "User presentation" refers to the interface or device through which the generated information is presented to the user, including chatbots, notification systems, mobile apps, etc.

[0638] As a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[0639] Basic configuration

[0640] The system mainly consists of the following elements:

[0641] 1. Data Collection Module

[0642] 2. Data Storage

[0643] 3. Data Analysis Module

[0644] 4. Generation AI

[0645] 5. User Interface

[0646] 6. Emotion Engine

[0647] Data Collection Module

[0648] Terminal

[0649] With the user's permission, the device acquires the user's behavioral history and posted content from social networking services (SNS). For example, it collects text, images, and videos that the user has shared on the SNS platform. This data collection is done using the SNS API. Specifically, it acquires user posted data using the Twitter API or Facebook API.

[0650] Data Storage

[0651] server

[0652] The data collected by the server is stored in data storage. This data storage uses a relational database such as MySQL or PostgreSQL, and individual personal data for each user is stored in chronological order. The stored data includes fields such as "user ID," "post content," and "post date and time."

[0653] Data Analysis Module

[0654] server

[0655] The server retrieves data from the data storage and uses an emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing technology (e.g., BERT or GPT-3) to analyze the content of posts and extract frequently occurring keywords. It also analyzes the user's emotional state and trends in the content of posts.

[0656] Generation AI

[0657] server

[0658] The generative AI generates relevant text and images based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, it will provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as OpenAI's GPT-3.

[0659] User Interface (UI)

[0660] Chatbots

[0661] The generated information is presented to the user via a chatbot. For example, if a user asks, "I can't remember the title of the song I heard recently," the chatbot will provide an answer based on the analysis results, such as, "You recently posted about 'XX'. Is this the song you want to remember?" The chatbot uses Dialogflow, Microsoft Bot Framework, etc.

[0662] Emotion Engine

[0663] server

[0664] The emotion engine analyzes the user's text and post content and identifies their emotional state using natural language processing technology. For example, if the content contains emotional expressions such as "fun," "happy," or "sad," it detects these and uses them for analysis. The emotion engine uses Google's Natural Language API and IBM Watson's Tone Analyzer, among others.

[0665] Specific examples

[0666] For example, consider a situation where a user cannot remember the title of a movie they recently saw. In this case, the system would act as follows:

[0667] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting." For example, it uses the Twitter API to collect the user's past tweets.

[0668] 2. The server stores these posts in a MySQL database.

[0669] 3. The server retrieves the data from the database, and the emotion engine uses BERT to analyze the user's emotional state. If the user posts comments such as "I had fun" or "I was moved," these will also be included in the analysis.

[0670] 4. The analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" using a Python NLP library (e.g., spaCy).

[0671] 5. The generative AI uses GPT-3 to generate text such as, "Isn't 'XX' the movie you recently saw that moved you?"

[0672] 6. The chatbot uses Dialogflow to present this generated information to the user to assist in memory recall.

[0673] Example prompt sentence:

[0674] "I can't remember the title of the last movie I saw. What movie moved me?"

[0675] In this way, the system can effectively eliminate the memory lapse phenomenon of the user.

[0676] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0677] Step 1: Data collection

[0678] Terminal

[0679] The user authorizes access to the social networking site. On this premise, the device uses the social networking site's API (for example, Twitter API or Facebook API) to obtain the user's behavioral history and posted content.

[0680] Input: Social media account credentials

[0681] Output: User posted data (text, images, videos)

[0682] Specific operation: The device calls the SNS API, sends a "Get recent posts" request, and retrieves the 100 most recent posts from the SNS.

[0683] Step 2: Save data

[0684] server

[0685] The acquired user's SNS data is received and saved in data storage (e.g. MySQL database). When saved, the post content, posting date and time, user ID, etc. are also recorded.

[0686] Input: User submitted data

[0687] Output: Post data saved in the database

[0688] Specific operation: The server executes the SQL statement "INSERT INTO user_data (user_id, post_content, post_date) VALUES (?, ?, ?)" to store the information in the database.

[0689] Step 3: Sentiment Analysis

[0690] server

[0691] User posted data is retrieved from the database and sentiment analysis is performed using natural language processing technology. Specifically, sentiment analysis is performed using a sentiment engine (e.g., BERT or Google Natural Language API).

[0692] Input: Post data stored in the database

[0693] Output: Parsed emotional state (e.g. positive, negative, neutral, etc.)

[0694] Specific operation: The server executes the SQL statement "SELECT post_content FROM user_data WHERE user_id = ?", passes the retrieved post text to the emotion engine, and receives the analysis results.

[0695] Step 4: Keyword extraction

[0696] server

[0697] Based on the sentiment analysis results, frequently occurring keywords are extracted using a natural language processing library. Specifically, an NLP library (e.g., spaCy) is used.

[0698] Input: Parsed emotional state and post data

[0699] Output: A list of extracted frequent keywords

[0700] Specific operation: Based on the results of the sentiment analysis, the server performs a process to extract frequently occurring words such as "movie" and "moving."

[0701] Step 5: Information Generation

[0702] Generation AI

[0703] Based on the results of sentiment analysis and keyword extraction, relevant information is generated using a generative AI model (e.g., GPT-3).

[0704] Input: Sentiment analysis results, frequently used keywords

[0705] Output: Generated text or image

[0706] Specific operation: The generative AI receives the prompt sentence "What movie did the user see recently that moved you?" as input and generates appropriate information.

[0707] Step 6: Information presentation

[0708] Chatbots

[0709] The generated information is presented to the user via a user interface (e.g., a chatbot), and responses to inquiries are generated using Dialogflow or the Microsoft Bot Framework.

[0710] Input: Generated information (text or image)

[0711] Output: Information presented to the user

[0712] Specific behavior: The chatbot sends the user a message saying, "Isn't 'XX' the movie that moved you the most recently?"

[0713] Through this specific processing flow, the system can effectively eliminate the user's "tip-of-the-tongue phenomenon" and improve the quality of daily life.

[0714] (Application example 2)

[0715] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0716] In recent years, there has been an increasing demand for systems that provide personalized information by analyzing users' behavioral history and posted content. However, current systems have difficulty providing information that takes into account the user's emotional state, resulting in a problem of a decline in the quality of the user experience. To solve this problem, more advanced personalized information generation that takes into account the user's emotional state is required.

[0717] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for identifying the user's emotional state, means for generating information using a generative AI model, and means for presenting the generated information to the user through a user interface. This makes it possible to recommend more appropriate content based on the user's emotional state.

[0718] "Behavioral history" refers to the history of various actions and activities that a user performs in their daily life, including social media posts, browsing history, GPS information, etc.

[0719] "Posted content" refers to content such as text, images, and videos that users make public on social networking services (SNS) and other platforms.

[0720] "Data storage" means systems or devices for storing collected data, including cloud storage, database servers, etc.

[0721] "Emotional state" refers to the emotion a user is feeling at a particular moment, which is extracted from text analysis using natural language processing techniques.

[0722] "Frequent keywords" refer to words and phrases that frequently appear in users' posts and behavioral history, and are important indicators of trends and interests.

[0723] A "generative AI model" is an artificial intelligence algorithm that generates natural language based on large amounts of data, generating personalized information based on a user's behavioral history and emotional state.

[0724] "User interface" refers to an interface that presents generated information to users in an easy-to-understand manner, including chatbots and application screen displays.

[0725] A specific embodiment for carrying out the present invention will be described below. First, the system mainly comprises the following elements:

[0726] 1. Data collection module: Obtains user behavior history and SNS postings from the device.

[0727] 2. Data storage: The acquired behavioral history and posted content are stored on a database server.

[0728] 3. Data analysis module: Analyzes the stored data and extracts frequently occurring keywords.

[0729] 4. Emotion Engine: Analyzes user posts to identify their emotional state.

[0730] 5. Generative AI model: Generates information based on emotional state and analysis results.

[0731] 6. User Interface: Presents the generated information to the user.

[0732] The detailed operation of each element will be explained below.

[0733] Data Collection Module

[0734] With the user's permission, the device will collect the user's behavioral history and posted content from social networking services (SNS), such as text, images, and videos shared by the user on the SNS platform. This data is collected in real time.

[0735] Data Storage

[0736] The server saves the collected data in data storage. This database manages the personal data of each user, and saves the collected behavioral history and posted content in chronological order. Examples of databases that can be used include MySQL and PostgreSQL.

[0737] Data Analysis Module

[0738] The server analyzes the data in the data storage and uses natural language processing libraries (e.g., spaCy or NLTK) to extract frequently occurring keywords and phrases. This analysis reveals frequently used words and trends among users.

[0739] Emotion Engine

[0740] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's posts and uses natural language processing technology to identify emotional states such as "joy," "happy," and "sad."

[0741] Generative AI Models

[0742] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate relevant information based on the emotional state identified by the emotion engine and the analysis results. If the user is feeling stressed, the generated information will be content that encourages relaxation.

[0743] User Interface

[0744] The generated information is presented to the user via a user interface. React Native or Flutter can be used for the interface, and information can be provided in the form of a chatbot. The user can receive suggested content in an interactive format.

[0745] Specific examples

[0746] For example, if a user posts, "I can't remember the name of the last movie I saw," then:

[0747] 1. The data collection module retrieves related posts such as "movies," "watched," and "interesting" from social media.

[0748] 2. The data analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" from the posted content.

[0749] 3. The emotion engine analyzes emotions such as "It was fun" or "I was moved" from the user's posts.

[0750] 4. The generative AI model generates the text, "Isn't 'XX' the movie you recently saw that moved you the most?"

[0751] 5. The user interface presents the text to the user in the form of a chatbot.

[0752] Prompt Sentence Examples

[0753] A user says they can't remember the title of a moving movie they recently saw. Please suggest movie titles based on the following keywords and their emotional state:

[0754] Keywords: movie, watched, interesting, fun, moving

[0755] Emotional state: Positive

[0756] As described above, this system provides highly personalized information based on the user's emotional state and behavioral history.

[0757] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0758] Step 1:

[0759] With the user's permission, the device obtains the user's behavioral history and posted content from a social networking service (SNS). The input is the posted content and behavioral history data using the SNS API, and the output is a collection of this data. The device obtains the user's text, images, videos, etc. from the SNS API and sends them to the next processing step.

[0760] Step 2:

[0761] The server stores the behavioral history and posted content sent from the device in data storage (for example, a MySQL or PostgreSQL database). The input is data obtained from the device, and the output is records stored in the database. The server connects to the database and stores the input data in individual records for each user.

[0762] Step 3:

[0763] The server analyzes the data in the data storage using a natural language processing library (e.g., spaCy or NLTK) and extracts frequently occurring keywords. The input is the data stored in the database, and the output is the extracted frequently occurring keywords. The server tokenizes the text data and analyzes the frequency of occurrence to extract keywords.

[0764] Step 4:

[0765] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to identify the emotional state from the user's posted content. The input is text data in the database, and the output is the identified emotional state. The server sends the posted text to the emotion engine, which identifies the emotional state, such as positive, negative, or neutral.

[0766] Step 5:

[0767] The server generates information using a generative AI model (e.g., OpenAI GPT-3) based on the emotional state and frequent keywords identified by the emotion engine. The input is the emotional state and frequent keywords, and the output is the generated text information. The server sends the input data to the generative AI model in the form of prompts to generate personalized content.

[0768] Step 6:

[0769] The server presents the generated information to the user through a user interface. The input is the output text from the generative AI model, and the output is the information displayed to the user through the user interface. The server uses React Native or Flutter to provide information to the user in the form of a chatbot, allowing the user to easily check the generated information.

[0770] In this way, highly personalized information provision based on the user's behavioral history and emotional state is realized.

[0771] 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.

[0772] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0773] 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.

[0774] [Third embodiment]

[0775] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0776] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0777] 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).

[0778] 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.

[0779] 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.

[0780] 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).

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0787] As a specific example of a form for implementing the present invention, a system will be described that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "what was that?", based on a user's daily activities and SNS posts.

[0788] Basic configuration

[0789] The system mainly consists of the following elements:

[0790] 1. Data Collection Module

[0791] 2. Database

[0792] 3. Data Analysis Module

[0793] 4. Generation AI

[0794] 5. User Interface

[0795] Data Collection Module

[0796] Device:

[0797] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on platforms such as Twitter and Facebook.

[0798] Database

[0799] server:

[0800] The server stores the collected data in a database, which is managed as an individual personal database for each user, with the collected behavioral history and posted content stored in chronological order.

[0801] Data Analysis Module

[0802] server:

[0803] The server analyzes the data in the database to extract frequently occurring keywords, using natural language processing techniques to calculate the frequency of occurrence of specific words and phrases.

[0804] Generation AI

[0805] server:

[0806] Based on the analysis results, the generative AI works to generate text and images related to the information the user wants to recall, using an advanced text generation algorithm such as GPT-3.

[0807] User Interface (UI)

[0808] Chatbots:

[0809] The generated information is presented to the user via the chatbot. When a user asks, "I can't remember the name of the movie I saw recently," the chatbot will provide a specific answer based on the analysis and generated results, such as, "You recently posted about a movie called ____. Is that what you're trying to remember?" This allows the user to quickly recall the desired information.

[0810] Specific examples

[0811] For example, consider a situation where a user says, "I can't remember the title of the song I recently listened to." In this case, the system operates as follows.

[0812] 1. The device retrieves related posts such as "music," "song title," and "listened to" from the user's SNS posts.

[0813] 2. The server stores these posts in a database and the analytics module analyzes them.

[0814] 3. Frequently used keywords such as "song," "recent," and "favorite" are extracted.

[0815] 4. The generative AI generates content such as, "You recently posted about the song 'XX'."

[0816] 5. The chatbot presents this generated information to the user to assist in memory recall.

[0817] In this way, the present invention can effectively eliminate the memory lapse phenomenon of users and improve the quality of daily life.

[0818] The processing flow will be explained below.

[0819] Step 1:

[0820] The user accesses the system and gives permission for data collection. The device connects to the user's social networking service (SNS) account and obtains the user's posts and behavioral history via API.

[0821] Step 2:

[0822] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[0823] Step 3:

[0824] The server stores the received data in the data storage. The database manages the individual personal data of each user and stores the data in chronological order.

[0825] Step 4:

[0826] The server retrieves user data from the data storage and analyzes it through a data analysis module. The server then uses natural language processing technology to extract frequently occurring keywords from the posts. For example, it calculates the frequency of occurrence of specific words or phrases such as "movies," "music," and "work."

[0827] Step 5:

[0828] The server uses generative AI to generate text based on the analysis results. The generative AI uses a text generation algorithm, such as GPT-3, to generate text and images related to the information the user wants to recall. For example, it creates text in the form of a specific question, such as, "Isn't the movie you saw recently ____?"

[0829] Step 6:

[0830] The chatbot presents the generated text and images to the user. When the user asks, "I can't remember the name of a movie I saw recently," the chatbot provides an answer based on the analysis results.

[0831] Step 7:

[0832] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, they can enter additional keywords or information and the system will analyze and generate it again.

[0833] In this way, a series of processes is completed that allows the system to identify and quickly resolve the user's memory lapse phenomenon (tip of the tongue phenomenon).

[0834] Example 1

[0835] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0836] In users' daily lives, the "tip of the tongue phenomenon," where they are unable to remember specific information, frequently occurs, causing stress and reduced efficiency. The present invention aims to provide a system that quickly and effectively resolves this "tip of the tongue phenomenon" based on the user's past posts and activity history on social networking services (SNS). The present invention also aims to improve the user's quality of life by providing fast and accurate information.

[0837] 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.

[0838] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for analyzing the saved data and extracting frequently occurring keywords, means for generating information using a generation AI, and means for presenting the generated information to the user through a user interface, thereby enabling the user to quickly and accurately recall forgotten information.

[0839] "Behavioral history" is a record of specific actions and operations that a user performs in their daily life or online activities.

[0840] "Posted content" refers to text, images, videos, and other media content shared by users on platforms such as social networking services (SNS).

[0841] "Data storage" refers to a database or storage device for managing and storing acquired and saved behavioral history and posted content.

[0842] "Analysis" is the process of extracting and analyzing specific information and patterns from stored data.

[0843] "Frequent keywords" are words or phrases that appear repeatedly in the data analyzed, and are important indicators of user interests and behavior.

[0844] "Generative AI" refers to artificial intelligence techniques and algorithms that generate the information a user wants to recall based on analysis results.

[0845] A "text generation algorithm" is a computational procedure or model for generating natural language text based on given input data.

[0846] "User interface" refers to the interaction means by which generated information is presented to a user and by which the user interacts with the system.

[0847] The present invention provides a system that eliminates the "tip-of-the-tongue phenomenon" based on a user's daily activities and posts on social networking services (SNS). This system mainly consists of the following elements:

[0848] Data Collection Module

[0849] With the user's permission, the device retrieves the user's activity history and posts from social media platforms, including text, images, and videos shared on popular social media platforms such as Twitter and Facebook. The device retrieves the data using APIs and sends it for further processing.

[0850] Database

[0851] The server saves the data collected from the device in data storage. The data storage is a database that is managed as a personal database for each user. The database stores information such as user ID, posted content, and posting date and time in chronological order.

[0852] Data Analysis Module

[0853] The server analyzes the data in the database and extracts frequently occurring keywords. This analysis uses natural language processing (NLP) technology to calculate the frequency of occurrence of specific words and phrases and understand user interests and behavioral patterns.

[0854] Generation AI

[0855] The generative AI works based on the analysis results to generate text and images related to the information the user wants to recall. The generative AI uses an advanced text generation algorithm, such as GPT-3, to generate information related to the user's past actions and posts based on the analyzed frequently used keywords.

[0856] As an example, the prompt sentence to be input to the generative AI model is shown below.

[0857] "Guess what information a user wants to remember based on what they've recently posted."

[0858] or

[0859] "For a user who has forgotten the title of a song they recently listened to, please analyze their past social media posts and generate text to provide relevant information."

[0860] User Interface (UI)

[0861] The chatbot presents the generated information to the user. For example, if a user says, "I can't remember the title of the movie I saw recently," the chatbot will respond based on the analysis results and information generated by the generation AI, saying, "You recently posted about a movie called ____. Is that what you're trying to remember?" Through this interface, users can quickly obtain the desired information.

[0862] Specific examples

[0863] For example, if a user says, "I can't remember the title of the song I recently listened to," the system works as follows: First, the device retrieves related posts such as "music," "song name," and "listened to" from the social networking site. Next, the server stores these posts in a database, and the analysis module analyzes the data to extract frequently occurring keywords. Next, the generation AI generates content such as, "You recently posted about the song 'XX'." The chatbot then presents this generated information to the user, supporting memory recall.

[0864] As described above, the present invention can effectively resolve memory lapses based on a user's daily activities and SNS posts, thereby improving the quality of daily life.

[0865] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0866] Step 1:

[0867] With the user's permission, the device obtains the user's behavioral history and posted content from the SNS. Specifically, the device uses the Twitter or Facebook API to collect data on posts, images, and videos that the user has made public. The data obtained at this time includes the post text, media link, and timestamp. (Input) User post data obtained from the SNS API. (Output) Obtained post content and behavioral history data.

[0868] Step 2:

[0869] The server stores data collected from the device in a database. First, the device sends the data it collected to the server. Next, the server records this data in a database managed individually for each user. The stored data includes the user ID, posted content, and posting date and time, and is used for subsequent analysis. (Input) Posted content and behavioral history data sent from the device. (Output) Record of behavioral history and posted content stored in the database.

[0870] Step 3:

[0871] The server analyzes the data in the database and extracts frequently occurring keywords. The server uses natural language processing (NLP) technology to tokenize the acquired text data and calculate the frequency of word occurrence. This allows important keywords that reflect the user's recent behavior and interests to be extracted. (Input) Text data stored in the database. (Output) A list of extracted frequently occurring keywords.

[0872] Step 4:

[0873] Based on the extracted frequent keywords, the generation AI generates text and images related to the information the user wants to recall. The generation AI uses a text generation algorithm such as GPT-3 to generate optimal information based on the prompt text. In this process, appropriate sentences and media links are output according to the instructions contained in the prompt text. (Input) Extracted frequent keywords and prompt text. (Output) Generated text and related media links.

[0874] Step 5:

[0875] The chatbot presents the generated information to the user. When a user inquires about specific information, the chatbot provides the user with text and media links generated by the generative AI. For example, if a user inquires, "I can't remember the name of the movie I saw recently," the chatbot will reply, "You recently posted about a movie called ____." (Input) The user's inquiry and generated text. (Output) The answer presented to the user.

[0876] Based on the above steps, the system can effectively resolve memory lapses based on users' daily activities and SNS posts, thereby improving the quality of daily life.

[0877] (Application example 1)

[0878] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0879] In factories, staff sometimes experience memory lapses while working. This can lead to an inability to remember specific work procedures or work content, which can reduce work efficiency and affect productivity and safety. Conventional methods require staff to manually go back through records, making it difficult to quickly obtain the necessary information. There is a need for a system that can solve this issue and support staff in performing their work effectively.

[0880] 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.

[0881] In this invention, the server includes a means for acquiring the user's work history and recorded content, a means for saving the acquired work history and recorded content in data storage, and a means for analyzing the saved data and extracting frequently occurring keywords, which allows staff to quickly recall necessary information in real time, improving work efficiency and safety.

[0882] "Users" refer to staff members who perform tasks within the factory.

[0883] "Work history" refers to records that include the work content and procedures that a user performed within a factory.

[0884] "Record contents" refers to data and notes related to the user's work, as well as information related thereto.

[0885] "Data storage" refers to a storage device or system for storing acquired business history and record content.

[0886] "Analysis" refers to the process of extracting and analyzing specific information from business history and record content stored in data storage.

[0887] "Frequent keywords" are important words or phrases that appear repeatedly in the analyzed business history and record contents.

[0888] "Generation" refers to the process of creating and providing new necessary information based on the analysis results.

[0889] A "robot assistant" is a mechanical device or system that provides users with the information they need and supports their work.

[0890] "Business system" is a general term for software and hardware used to support business management and work progress within a factory.

[0891] A "communication platform" is a system that allows users to exchange information and communicate about business matters.

[0892] A "text generation algorithm" is a computational method for automatically generating text based on input data.

[0893] MODE FOR CARRYING OUT THE INVENTION

[0894] As an embodiment of this invention, we will explain a system that uses a "robot assistant" to resolve the memory gaps of factory staff. This system acquires the user's work history and recorded content and provides necessary information in real time, thereby improving work efficiency.

[0895] Basic system configuration

[0896] 1. Data Collection Module

[0897] Means of obtaining user work history and record contents: Data is collected from daily work reports that record the work content and procedures performed by users in the factory, business systems, and communication platforms (e.g., Slack, Teams).

[0898] 2. Database

[0899] Data storage: The collected data is stored in a data storage such as an SQLite database. This data storage manages the collected work history and record contents in chronological order and holds data for each individual user.

[0900] 3. Data Analysis Module

[0901] Data analysis method: Analyzes stored data and extracts frequently occurring keywords. Natural language processing technology is used for the analysis to calculate the frequency of occurrence of specific words and phrases.

[0902] 4. Generation AI

[0903] A method of generating information using a text generation algorithm: Based on the analysis results, a generation AI operates to generate text related to the information the user wants to recall. This generation AI uses an advanced text generation algorithm, such as GPT-3.

[0904] 5. User Interface

[0905] A means of presenting information to users via a robot assistant: The generated information is provided to users through a robot assistant (a robot with a voice and a display), allowing users to quickly obtain the information they need during work and carry out their work smoothly.

[0906] Processing Details

[0907] The processing of this system will now be described in detail with reference to a specific example.

[0908] 1. Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms such as Slack. For example, it obtains records such as "I performed maintenance on Machine A."

[0909] 2. Data storage: The server stores the collected data in an SQLite database. This data is managed for each user and organized in chronological order.

[0910] 3. Data analysis: The server analyzes the stored data and extracts frequently occurring keywords, such as "maintenance," "machine A," and "parts replacement."

[0911] 4. Information generation: Based on the analysis results, the generation AI generates content such as, "Recently, you performed maintenance on Machine A. It also appears that you replaced parts."

[0912] 5. Information presentation: The generated information is presented to the user via a robot assistant. It can be presented visually via audio or a display, allowing the user to quickly obtain the information they need.

[0913] Specific examples

[0914] In a situation where the user cannot remember the details of the recent maintenance performed on Machine A, the system operates as follows:

[0915] 1. Data collection: The terminal acquires business records including "Machine A maintenance" and "parts replacement."

[0916] 2. Data storage: The server stores these data in an SQLite database.

[0917] 3. Data analysis: Extract frequently occurring keywords such as "maintenance," "machine A," and "parts replacement."

[0918] 4. Information generation: For example, the generation AI generates information based on the following prompt sentence:

[0919] Prompt: What work have you done recently? Hint: Maintenance on machine A.

[0920] 5. Information presentation: The robot assistant will provide the user with a voice message saying, "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts."

[0921] This allows users to quickly recall necessary information, improving work efficiency and safety.

[0922] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0923] System program processing flow

[0924] Step 1:

[0925] Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms (e.g., Slack, Teams). Specifically, the device sends API requests to these data sources to obtain text data from daily reports and system log data.

[0926] Input: Daily work reports, business systems, Slack data (e.g., "2023-10-01: Maintenance performed on Machine A").

[0927] Output: A list of the retrieved data.

[0928] Step 2:

[0929] Data storage: The server stores the collected data in a data storage such as SQLite. Specifically, the server establishes a connection to the data storage and inserts the acquired data into the database in chronological order for each user.

[0930] Input: Collected work history and record contents.

[0931] Output: Data stored in data storage.

[0932] Step 3:

[0933] Data analysis: The server analyzes the stored data and extracts frequently occurring keywords. Specifically, the server uses natural language processing techniques (e.g., morphological analysis) to analyze the text data and calculate the frequency of occurrence of important keywords.

[0934] Input: Data stored in data storage.

[0935] Output: A list of frequently occurring keywords (e.g., "machine A," "maintenance," "parts replacement").

[0936] Step 4:

[0937] Information generation: The server generates information using a generation AI (e.g., GPT-3) based on frequently occurring keywords. Specifically, the server sends a prompt to the generation AI and receives the resulting text.

[0938] Input: Frequently used keywords, prompt sentence.

[0939] Output: Generated text (e.g., "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts.").

[0940] Step 5:

[0941] Information presentation: The server presents the generated information to the user via the robot assistant. Specifically, the robot assistant provides the generated information to the user using voice synthesis technology or a display.

[0942] Input: The generated text.

[0943] Output: The information presented to the user.

[0944] This configuration allows users to quickly recall necessary information, improving work efficiency and safety.

[0945] 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.

[0946] As a specific example of a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[0947] Basic configuration

[0948] The system mainly consists of the following elements:

[0949] 1. Data Collection Module

[0950] 2. Database

[0951] 3. Data Analysis Module

[0952] 4. Generation AI

[0953] 5. User Interface

[0954] 6. Emotion Engine

[0955] Data Collection Module

[0956] Device:

[0957] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on the SNS platform.

[0958] Database

[0959] server:

[0960] The server stores the collected data in a database. This database manages the personal data of each user, and stores the collected behavioral history and posted content in chronological order.

[0961] Data Analysis Module

[0962] server:

[0963] The server analyzes the data in the database and uses an emotion engine to identify the user's emotional state. It also extracts frequently occurring keywords and analyzes them based on the user's emotional state and the trends of the content of posts.

[0964] Generation AI

[0965] server:

[0966] Based on the emotional state identified by the emotion engine, the generative AI generates relevant text and images. For example, if the user is feeling stressed, it can provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as GPT-3.

[0967] User Interface (UI)

[0968] Chatbots:

[0969] The generated information is presented to the user via a chatbot. When a user asks, "I can't remember the title of a song I heard recently," the chatbot will provide a response based on the analysis results, such as, "You recently posted about 'XX.' Is this the song you want to remember?"

[0970] Emotion Engine

[0971] server:

[0972] The emotion engine analyzes users' text and posts and identifies their emotional state using natural language processing technology. For example, if a post contains emotional expressions such as "fun," "happy," or "sad," the engine detects this and uses it for analysis. The emotion engine then integrates the user's emotional state into the analysis results, enabling the provision of more personalized information.

[0973] Specific examples

[0974] For example, consider a situation where a user cannot remember the title of a movie they recently watched. In this case, the system operates as follows.

[0975] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting."

[0976] 2. The server stores these posts in a database.

[0977] 3. The server retrieves the data from the database, and the emotion engine analyzes the user's emotional state. If the user posts comments such as "It was fun" or "I was moved," these will also be included in the analysis.

[0978] 4. The analysis module extracts the frequently occurring keywords "movie," "watched," and "interesting."

[0979] 5. The generative AI generates the question, "Isn't 'XX' the movie that moved you the most recently?"

[0980] 6. The chatbot presents this generated information to the user to assist in memory recall.

[0981] In this way, by providing information that takes into account the user's emotional state, the present invention can effectively resolve the memory lapses of the user and improve the quality of daily life.

[0982] The processing flow will be explained below.

[0983] Step 1:

[0984] The user accesses the system and grants permission for data collection and analysis. The device connects the SNS account to the system and obtains the user's postings and behavioral history via API.

[0985] Step 2:

[0986] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[0987] Step 3:

[0988] The server stores the received data in the data storage. The database manages the individual personal data for each user and stores the acquired data in chronological order.

[0989] Step 4:

[0990] The server sends the stored data to a data analysis module, which uses natural language processing technology to analyze the posts, calculate the frequency of specific keywords and phrases, and extract highly relevant keywords.

[0991] Step 5:

[0992] Based on the analysis results, the server uses an emotion engine to analyze the user's emotional state. The emotion engine reads emotions from the text and identifies emotions such as "happy," "sad," and "excited."

[0993] Step 6:

[0994] The server combines the analyzed keywords with the emotional state and sends the combined results to the generation AI, which then uses a text generation algorithm such as GPT-3 to generate a specific answer. For example, it generates text such as, "You recently posted about the movie 'XX.' Was it moving?"

[0995] Step 7:

[0996] The chatbot presents the generated text to the user. When the user makes a query such as "I can't remember the title of the song I listened to recently," the chatbot will provide an appropriate answer based on the analysis and generation results.

[0997] Step 8:

[0998] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, the user can enter additional keywords or information, and the system will analyze and generate it again.

[0999] This allows the system to efficiently resolve memory lapses, reduce user stress, and quickly provide the information the user desires, while taking into account the user's emotional state.

[1000] Example 2

[1001] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1002] In today's information society, users consume a huge amount of information every day, which can make it difficult to recall important information. Effective methods are needed to resolve the "tip of the tongue phenomenon," a situation in which users want to recall specific information but are unable to. Furthermore, by taking the user's emotional state into consideration, more personalized support can be provided. To address this issue, a system is needed that analyzes a user's behavioral history and posted content, identifies their emotional state, and generates and provides appropriate information.

[1003] 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.

[1004] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in a data storage, means for analyzing the saved data and identifying the user's emotional state, means for extracting frequently occurring keywords, means for generating related information based on the analysis results and the extracted keywords, and means for presenting the generated information to the user. This eliminates the problem of memory lapses in the user's memory and enables the provision of personalized information that takes into account the user's emotional state.

[1005] "Behavioral history" is a record of specific actions or operations that a user has performed in the past, including web browsing, application usage, and location information.

[1006] "Posted content" refers to information such as text, images, and videos that users make public on social networking services, blogs, forums, etc.

[1007] "Data storage" means a physical or virtual repository for storing captured data, including databases and cloud storage.

[1008] An "emotional state" refers to the emotional or feeling state a user is experiencing at a particular moment, including emotions such as "happy," "sad," and "angry."

[1009] "Frequent keywords" are words or phrases that are frequently used within a certain period of time, as identified through data analysis.

[1010] "Related information" is information that is useful to users and is generated based on the analysis results and extracted keywords. This includes text, images, videos, etc.

[1011] A "text generation algorithm" is a computational method for automatically generating natural language text based on input prompts and data, including neural network-based models.

[1012] "User presentation" refers to the interface or device through which the generated information is presented to the user, including chatbots, notification systems, mobile apps, etc.

[1013] As a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[1014] Basic configuration

[1015] The system mainly consists of the following elements:

[1016] 1. Data Collection Module

[1017] 2. Data Storage

[1018] 3. Data Analysis Module

[1019] 4. Generation AI

[1020] 5. User Interface

[1021] 6. Emotion Engine

[1022] Data Collection Module

[1023] Terminal

[1024] With the user's permission, the device acquires the user's behavioral history and posted content from social networking services (SNS). For example, it collects text, images, and videos that the user has shared on the SNS platform. This data collection is done using the SNS API. Specifically, it acquires user posted data using the Twitter API or Facebook API.

[1025] Data Storage

[1026] server

[1027] The data collected by the server is stored in data storage. This data storage uses a relational database such as MySQL or PostgreSQL, and individual personal data for each user is stored in chronological order. The stored data includes fields such as "user ID," "post content," and "post date and time."

[1028] Data Analysis Module

[1029] server

[1030] The server retrieves data from the data storage and uses an emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing technology (e.g., BERT or GPT-3) to analyze the content of posts and extract frequently occurring keywords. It also analyzes the user's emotional state and trends in the content of posts.

[1031] Generation AI

[1032] server

[1033] The generative AI generates relevant text and images based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, it will provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as OpenAI's GPT-3.

[1034] User Interface (UI)

[1035] Chatbots

[1036] The generated information is presented to the user via a chatbot. For example, if a user asks, "I can't remember the title of the song I heard recently," the chatbot will provide an answer based on the analysis results, such as, "You recently posted about 'XX'. Is this the song you want to remember?" The chatbot uses Dialogflow, Microsoft Bot Framework, etc.

[1037] Emotion Engine

[1038] server

[1039] The emotion engine analyzes the user's text and post content and identifies their emotional state using natural language processing technology. For example, if the content contains emotional expressions such as "fun," "happy," or "sad," it detects these and uses them for analysis. The emotion engine uses Google's Natural Language API and IBM Watson's Tone Analyzer, among others.

[1040] Specific examples

[1041] For example, consider a situation where a user cannot remember the title of a movie they recently saw. In this case, the system would act as follows:

[1042] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting." For example, it uses the Twitter API to collect the user's past tweets.

[1043] 2. The server stores these posts in a MySQL database.

[1044] 3. The server retrieves the data from the database, and the emotion engine uses BERT to analyze the user's emotional state. If the user posts comments such as "I had fun" or "I was moved," these will also be included in the analysis.

[1045] 4. The analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" using a Python NLP library (e.g., spaCy).

[1046] 5. The generative AI uses GPT-3 to generate text such as, "Isn't 'XX' the movie you recently saw that moved you?"

[1047] 6. The chatbot uses Dialogflow to present this generated information to the user to assist in memory recall.

[1048] Example prompt sentence:

[1049] "I can't remember the title of the last movie I saw. What movie moved me?"

[1050] In this way, the system can effectively eliminate the memory lapse phenomenon of the user.

[1051] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1052] Step 1: Data collection

[1053] Terminal

[1054] The user authorizes access to the social networking site. On this premise, the device uses the social networking site's API (for example, Twitter API or Facebook API) to obtain the user's behavioral history and posted content.

[1055] Input: Social media account credentials

[1056] Output: User posted data (text, images, videos)

[1057] Specific operation: The device calls the SNS API, sends a "Get recent posts" request, and retrieves the 100 most recent posts from the SNS.

[1058] Step 2: Save data

[1059] server

[1060] The acquired user's SNS data is received and saved in data storage (e.g. MySQL database). When saved, the post content, posting date and time, user ID, etc. are also recorded.

[1061] Input: User submitted data

[1062] Output: Post data saved in the database

[1063] Specific operation: The server executes the SQL statement "INSERT INTO user_data (user_id, post_content, post_date) VALUES (?, ?, ?)" to store the information in the database.

[1064] Step 3: Sentiment Analysis

[1065] server

[1066] User posted data is retrieved from the database and sentiment analysis is performed using natural language processing technology. Specifically, sentiment analysis is performed using a sentiment engine (e.g., BERT or Google Natural Language API).

[1067] Input: Post data stored in the database

[1068] Output: Parsed emotional state (e.g. positive, negative, neutral, etc.)

[1069] Specific operation: The server executes the SQL statement "SELECT post_content FROM user_data WHERE user_id = ?", passes the retrieved post text to the emotion engine, and receives the analysis results.

[1070] Step 4: Keyword extraction

[1071] server

[1072] Based on the sentiment analysis results, frequently occurring keywords are extracted using a natural language processing library. Specifically, an NLP library (e.g., spaCy) is used.

[1073] Input: Parsed emotional state and post data

[1074] Output: A list of extracted frequent keywords

[1075] Specific operation: Based on the results of the sentiment analysis, the server performs a process to extract frequently occurring words such as "movie" and "moving."

[1076] Step 5: Information Generation

[1077] Generation AI

[1078] Based on the results of sentiment analysis and keyword extraction, relevant information is generated using a generative AI model (e.g., GPT-3).

[1079] Input: Sentiment analysis results, frequently used keywords

[1080] Output: Generated text or image

[1081] Specific operation: The generative AI receives the prompt sentence "What movie did the user see recently that moved you?" as input and generates appropriate information.

[1082] Step 6: Information presentation

[1083] Chatbots

[1084] The generated information is presented to the user via a user interface (e.g., a chatbot), and responses to inquiries are generated using Dialogflow or the Microsoft Bot Framework.

[1085] Input: Generated information (text or image)

[1086] Output: Information presented to the user

[1087] Specific behavior: The chatbot sends the user a message saying, "Isn't 'XX' the movie that moved you the most recently?"

[1088] Through this specific processing flow, the system can effectively eliminate the user's "tip-of-the-tongue phenomenon" and improve the quality of daily life.

[1089] (Application example 2)

[1090] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1091] In recent years, there has been an increasing demand for systems that provide personalized information by analyzing users' behavioral history and posted content. However, current systems have difficulty providing information that takes into account the user's emotional state, resulting in a problem of a decline in the quality of the user experience. To solve this problem, more advanced personalized information generation that takes into account the user's emotional state is required.

[1092] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for identifying the user's emotional state, means for generating information using a generative AI model, and means for presenting the generated information to the user through a user interface. This makes it possible to recommend more appropriate content based on the user's emotional state.

[1093] "Behavioral history" refers to the history of various actions and activities that a user performs in their daily life, including social media posts, browsing history, GPS information, etc.

[1094] "Posted content" refers to content such as text, images, and videos that users make public on social networking services (SNS) and other platforms.

[1095] "Data storage" means systems or devices for storing collected data, including cloud storage, database servers, etc.

[1096] "Emotional state" refers to the emotion a user is feeling at a particular moment, which is extracted from text analysis using natural language processing techniques.

[1097] "Frequent keywords" refer to words and phrases that frequently appear in users' posts and behavioral history, and are important indicators of trends and interests.

[1098] A "generative AI model" is an artificial intelligence algorithm that generates natural language based on large amounts of data, generating personalized information based on a user's behavioral history and emotional state.

[1099] "User interface" refers to an interface that presents generated information to users in an easy-to-understand manner, including chatbots and application screen displays.

[1100] A specific embodiment for carrying out the present invention will be described below. First, the system mainly comprises the following elements:

[1101] 1. Data collection module: Obtains user behavior history and SNS postings from the device.

[1102] 2. Data storage: The acquired behavioral history and posted content are stored on a database server.

[1103] 3. Data analysis module: Analyzes the stored data and extracts frequently occurring keywords.

[1104] 4. Emotion Engine: Analyzes user posts to identify their emotional state.

[1105] 5. Generative AI model: Generates information based on emotional state and analysis results.

[1106] 6. User Interface: Presents the generated information to the user.

[1107] The detailed operation of each element will be explained below.

[1108] Data Collection Module

[1109] With the user's permission, the device will collect the user's behavioral history and posted content from social networking services (SNS), such as text, images, and videos shared by the user on the SNS platform. This data is collected in real time.

[1110] Data Storage

[1111] The server saves the collected data in data storage. This database manages the personal data of each user, and saves the collected behavioral history and posted content in chronological order. Examples of databases that can be used include MySQL and PostgreSQL.

[1112] Data Analysis Module

[1113] The server analyzes the data in the data storage and uses natural language processing libraries (e.g., spaCy or NLTK) to extract frequently occurring keywords and phrases. This analysis reveals frequently used words and trends among users.

[1114] Emotion Engine

[1115] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's posts and uses natural language processing technology to identify emotional states such as "joy," "happy," and "sad."

[1116] Generative AI Models

[1117] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate relevant information based on the emotional state identified by the emotion engine and the analysis results. If the user is feeling stressed, the generated information will be content that encourages relaxation.

[1118] User Interface

[1119] The generated information is presented to the user via a user interface. React Native or Flutter can be used for the interface, and information can be provided in the form of a chatbot. The user can receive suggested content in an interactive format.

[1120] Specific examples

[1121] For example, if a user posts, "I can't remember the name of the last movie I saw," then:

[1122] 1. The data collection module retrieves related posts such as "movies," "watched," and "interesting" from social media.

[1123] 2. The data analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" from the posted content.

[1124] 3. The emotion engine analyzes emotions such as "It was fun" or "I was moved" from the user's posts.

[1125] 4. The generative AI model generates the text, "Isn't 'XX' the movie you recently saw that moved you the most?"

[1126] 5. The user interface presents the text to the user in the form of a chatbot.

[1127] Prompt Sentence Examples

[1128] A user says they can't remember the title of a moving movie they recently saw. Please suggest movie titles based on the following keywords and their emotional state:

[1129] Keywords: movie, watched, interesting, fun, moving

[1130] Emotional state: Positive

[1131] As described above, this system provides highly personalized information based on the user's emotional state and behavioral history.

[1132] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1133] Step 1:

[1134] With the user's permission, the device obtains the user's behavioral history and posted content from a social networking service (SNS). The input is the posted content and behavioral history data using the SNS API, and the output is a collection of this data. The device obtains the user's text, images, videos, etc. from the SNS API and sends them to the next processing step.

[1135] Step 2:

[1136] The server stores the behavioral history and posted content sent from the device in data storage (for example, a MySQL or PostgreSQL database). The input is data obtained from the device, and the output is records stored in the database. The server connects to the database and stores the input data in individual records for each user.

[1137] Step 3:

[1138] The server analyzes the data in the data storage using a natural language processing library (e.g., spaCy or NLTK) and extracts frequently occurring keywords. The input is the data stored in the database, and the output is the extracted frequently occurring keywords. The server tokenizes the text data and analyzes the frequency of occurrence to extract keywords.

[1139] Step 4:

[1140] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to identify the emotional state from the user's posted content. The input is text data in the database, and the output is the identified emotional state. The server sends the posted text to the emotion engine, which identifies the emotional state, such as positive, negative, or neutral.

[1141] Step 5:

[1142] The server generates information using a generative AI model (e.g., OpenAI GPT-3) based on the emotional state and frequent keywords identified by the emotion engine. The input is the emotional state and frequent keywords, and the output is the generated text information. The server sends the input data to the generative AI model in the form of prompts to generate personalized content.

[1143] Step 6:

[1144] The server presents the generated information to the user through a user interface. The input is the output text from the generative AI model, and the output is the information displayed to the user through the user interface. The server uses React Native or Flutter to provide information to the user in the form of a chatbot, allowing the user to easily check the generated information.

[1145] In this way, highly personalized information provision based on the user's behavioral history and emotional state is realized.

[1146] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1147] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1148] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1149] [Fourth embodiment]

[1150] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1151] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1152] 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).

[1153] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1154] 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.

[1155] 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).

[1156] 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.

[1157] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1158] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1159] 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.

[1160] 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.

[1161] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1162] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1163] As a specific example of a form for implementing the present invention, a system will be described that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "what was that?", based on a user's daily activities and SNS posts.

[1164] Basic configuration

[1165] The system mainly consists of the following elements:

[1166] 1. Data Collection Module

[1167] 2. Database

[1168] 3. Data Analysis Module

[1169] 4. Generation AI

[1170] 5. User Interface

[1171] Data Collection Module

[1172] Device:

[1173] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on platforms such as Twitter and Facebook.

[1174] Database

[1175] server:

[1176] The server stores the collected data in a database, which is managed as an individual personal database for each user, with the collected behavioral history and posted content stored in chronological order.

[1177] Data Analysis Module

[1178] server:

[1179] The server analyzes the data in the database to extract frequently occurring keywords, using natural language processing techniques to calculate the frequency of occurrence of specific words and phrases.

[1180] Generation AI

[1181] server:

[1182] Based on the analysis results, the generative AI works to generate text and images related to the information the user wants to recall, using an advanced text generation algorithm such as GPT-3.

[1183] User Interface (UI)

[1184] Chatbots:

[1185] The generated information is presented to the user via the chatbot. When a user asks, "I can't remember the name of the movie I saw recently," the chatbot will provide a specific answer based on the analysis and generated results, such as, "You recently posted about a movie called ____. Is that what you're trying to remember?" This allows the user to quickly recall the desired information.

[1186] Specific examples

[1187] For example, consider a situation where a user says, "I can't remember the title of the song I recently listened to." In this case, the system operates as follows.

[1188] 1. The device retrieves related posts such as "music," "song title," and "listened to" from the user's SNS posts.

[1189] 2. The server stores these posts in a database and the analytics module analyzes them.

[1190] 3. Frequently used keywords such as "song," "recent," and "favorite" are extracted.

[1191] 4. The generative AI generates content such as, "You recently posted about the song 'XX'."

[1192] 5. The chatbot presents this generated information to the user to assist in memory recall.

[1193] In this way, the present invention can effectively eliminate the memory lapse phenomenon of users and improve the quality of daily life.

[1194] The processing flow will be explained below.

[1195] Step 1:

[1196] The user accesses the system and gives permission for data collection. The device connects to the user's social networking service (SNS) account and obtains the user's posts and behavioral history via API.

[1197] Step 2:

[1198] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[1199] Step 3:

[1200] The server stores the received data in the data storage. The database manages the individual personal data of each user and stores the data in chronological order.

[1201] Step 4:

[1202] The server retrieves user data from the data storage and analyzes it through a data analysis module. The server then uses natural language processing technology to extract frequently occurring keywords from the posts. For example, it calculates the frequency of occurrence of specific words or phrases such as "movies," "music," and "work."

[1203] Step 5:

[1204] The server uses generative AI to generate text based on the analysis results. The generative AI uses a text generation algorithm, such as GPT-3, to generate text and images related to the information the user wants to recall. For example, it creates text in the form of a specific question, such as, "Isn't the movie you saw recently ____?"

[1205] Step 6:

[1206] The chatbot presents the generated text and images to the user. When the user asks, "I can't remember the name of a movie I saw recently," the chatbot provides an answer based on the analysis results.

[1207] Step 7:

[1208] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, they can enter additional keywords or information and the system will analyze and generate it again.

[1209] In this way, a series of processes is completed that allows the system to identify and quickly resolve the user's memory lapse phenomenon (tip of the tongue phenomenon).

[1210] Example 1

[1211] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1212] In users' daily lives, the "tip of the tongue phenomenon," where they are unable to remember specific information, frequently occurs, causing stress and reduced efficiency. The present invention aims to provide a system that quickly and effectively resolves this "tip of the tongue phenomenon" based on the user's past posts and activity history on social networking services (SNS). The present invention also aims to improve the user's quality of life by providing fast and accurate information.

[1213] 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.

[1214] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for analyzing the saved data and extracting frequently occurring keywords, means for generating information using a generation AI, and means for presenting the generated information to the user through a user interface, thereby enabling the user to quickly and accurately recall forgotten information.

[1215] "Behavioral history" is a record of specific actions and operations that a user performs in their daily life or online activities.

[1216] "Posted content" refers to text, images, videos, and other media content shared by users on platforms such as social networking services (SNS).

[1217] "Data storage" refers to a database or storage device for managing and storing acquired and saved behavioral history and posted content.

[1218] "Analysis" is the process of extracting and analyzing specific information and patterns from stored data.

[1219] "Frequent keywords" are words or phrases that appear repeatedly in the data analyzed, and are important indicators of user interests and behavior.

[1220] "Generative AI" refers to artificial intelligence techniques and algorithms that generate the information a user wants to recall based on analysis results.

[1221] A "text generation algorithm" is a computational procedure or model for generating natural language text based on given input data.

[1222] "User interface" refers to the interaction means by which generated information is presented to a user and by which the user interacts with the system.

[1223] The present invention provides a system that eliminates the "tip-of-the-tongue phenomenon" based on a user's daily activities and posts on social networking services (SNS). This system mainly consists of the following elements:

[1224] Data Collection Module

[1225] With the user's permission, the device retrieves the user's activity history and posts from social media platforms, including text, images, and videos shared on popular social media platforms such as Twitter and Facebook. The device retrieves the data using APIs and sends it for further processing.

[1226] Database

[1227] The server saves the data collected from the device in data storage. The data storage is a database that is managed as a personal database for each user. The database stores information such as user ID, posted content, and posting date and time in chronological order.

[1228] Data Analysis Module

[1229] The server analyzes the data in the database and extracts frequently occurring keywords. This analysis uses natural language processing (NLP) technology to calculate the frequency of occurrence of specific words and phrases and understand user interests and behavioral patterns.

[1230] Generation AI

[1231] The generative AI works based on the analysis results to generate text and images related to the information the user wants to recall. The generative AI uses an advanced text generation algorithm, such as GPT-3, to generate information related to the user's past actions and posts based on the analyzed frequently used keywords.

[1232] As an example, the prompt sentence to be input to the generative AI model is shown below.

[1233] "Guess what information a user wants to remember based on what they've recently posted."

[1234] or

[1235] "For a user who has forgotten the title of a song they recently listened to, please analyze their past social media posts and generate text to provide relevant information."

[1236] User Interface (UI)

[1237] The chatbot presents the generated information to the user. For example, if a user says, "I can't remember the title of the movie I saw recently," the chatbot will respond based on the analysis results and information generated by the generation AI, saying, "You recently posted about a movie called ____. Is that what you're trying to remember?" Through this interface, users can quickly obtain the desired information.

[1238] Specific examples

[1239] For example, if a user says, "I can't remember the title of the song I recently listened to," the system works as follows: First, the device retrieves related posts such as "music," "song name," and "listened to" from the social networking site. Next, the server stores these posts in a database, and the analysis module analyzes the data to extract frequently occurring keywords. Next, the generation AI generates content such as, "You recently posted about the song 'XX'." The chatbot then presents this generated information to the user, supporting memory recall.

[1240] As described above, the present invention can effectively resolve memory lapses based on a user's daily activities and SNS posts, thereby improving the quality of daily life.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] With the user's permission, the device obtains the user's behavioral history and posted content from the SNS. Specifically, the device uses the Twitter or Facebook API to collect data on posts, images, and videos that the user has made public. The data obtained at this time includes the post text, media link, and timestamp. (Input) User post data obtained from the SNS API. (Output) Obtained post content and behavioral history data.

[1244] Step 2:

[1245] The server stores data collected from the device in a database. First, the device sends the data it collected to the server. Next, the server records this data in a database managed individually for each user. The stored data includes the user ID, posted content, and posting date and time, and is used for subsequent analysis. (Input) Posted content and behavioral history data sent from the device. (Output) Record of behavioral history and posted content stored in the database.

[1246] Step 3:

[1247] The server analyzes the data in the database and extracts frequently occurring keywords. The server uses natural language processing (NLP) technology to tokenize the acquired text data and calculate the frequency of word occurrence. This allows important keywords that reflect the user's recent behavior and interests to be extracted. (Input) Text data stored in the database. (Output) A list of extracted frequently occurring keywords.

[1248] Step 4:

[1249] Based on the extracted frequent keywords, the generation AI generates text and images related to the information the user wants to recall. The generation AI uses a text generation algorithm such as GPT-3 to generate optimal information based on the prompt text. In this process, appropriate sentences and media links are output according to the instructions contained in the prompt text. (Input) Extracted frequent keywords and prompt text. (Output) Generated text and related media links.

[1250] Step 5:

[1251] The chatbot presents the generated information to the user. When a user inquires about specific information, the chatbot provides the user with text and media links generated by the generative AI. For example, if a user inquires, "I can't remember the name of the movie I saw recently," the chatbot will reply, "You recently posted about a movie called ____." (Input) The user's inquiry and generated text. (Output) The answer presented to the user.

[1252] Based on the above steps, the system can effectively resolve memory lapses based on users' daily activities and SNS posts, thereby improving the quality of daily life.

[1253] (Application example 1)

[1254] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1255] In factories, staff sometimes experience memory lapses while working. This can lead to an inability to remember specific work procedures or work content, which can reduce work efficiency and affect productivity and safety. Conventional methods require staff to manually go back through records, making it difficult to quickly obtain the necessary information. There is a need for a system that can solve this issue and support staff in performing their work effectively.

[1256] 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.

[1257] In this invention, the server includes a means for acquiring the user's work history and recorded content, a means for saving the acquired work history and recorded content in data storage, and a means for analyzing the saved data and extracting frequently occurring keywords, which allows staff to quickly recall necessary information in real time, improving work efficiency and safety.

[1258] "Users" refer to staff members who perform tasks within the factory.

[1259] "Work history" refers to records that include the work content and procedures that a user performed within a factory.

[1260] "Record contents" refers to data and notes related to the user's work, as well as information related thereto.

[1261] "Data storage" refers to a storage device or system for storing acquired business history and record content.

[1262] "Analysis" refers to the process of extracting and analyzing specific information from business history and record content stored in data storage.

[1263] "Frequent keywords" are important words or phrases that appear repeatedly in the analyzed business history and record contents.

[1264] "Generation" refers to the process of creating and providing new necessary information based on the analysis results.

[1265] A "robot assistant" is a mechanical device or system that provides users with the information they need and supports their work.

[1266] "Business system" is a general term for software and hardware used to support business management and work progress within a factory.

[1267] A "communication platform" is a system that allows users to exchange information and communicate about business matters.

[1268] A "text generation algorithm" is a computational method for automatically generating text based on input data.

[1269] MODE FOR CARRYING OUT THE INVENTION

[1270] As an embodiment of this invention, we will explain a system that uses a "robot assistant" to resolve the memory gaps of factory staff. This system acquires the user's work history and recorded content and provides necessary information in real time, thereby improving work efficiency.

[1271] Basic system configuration

[1272] 1. Data Collection Module

[1273] Means of obtaining user work history and record contents: Data is collected from daily work reports that record the work content and procedures performed by users in the factory, business systems, and communication platforms (e.g., Slack, Teams).

[1274] 2. Database

[1275] Data storage: The collected data is stored in a data storage such as an SQLite database. This data storage manages the collected work history and record contents in chronological order and holds data for each individual user.

[1276] 3. Data Analysis Module

[1277] Data analysis method: Analyzes stored data and extracts frequently occurring keywords. Natural language processing technology is used for the analysis to calculate the frequency of occurrence of specific words and phrases.

[1278] 4. Generation AI

[1279] A method of generating information using a text generation algorithm: Based on the analysis results, a generation AI operates to generate text related to the information the user wants to recall. This generation AI uses an advanced text generation algorithm, such as GPT-3.

[1280] 5. User Interface

[1281] A means of presenting information to users via a robot assistant: The generated information is provided to users through a robot assistant (a robot with a voice and a display), allowing users to quickly obtain the information they need during work and carry out their work smoothly.

[1282] Processing Details

[1283] The processing of this system will now be described in detail with reference to a specific example.

[1284] 1. Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms such as Slack. For example, it obtains records such as "I performed maintenance on Machine A."

[1285] 2. Data storage: The server stores the collected data in an SQLite database. This data is managed for each user and organized in chronological order.

[1286] 3. Data analysis: The server analyzes the stored data and extracts frequently occurring keywords, such as "maintenance," "machine A," and "parts replacement."

[1287] 4. Information generation: Based on the analysis results, the generation AI generates content such as, "Recently, you performed maintenance on Machine A. It also appears that you replaced parts."

[1288] 5. Information presentation: The generated information is presented to the user via a robot assistant. It can be presented visually via audio or a display, allowing the user to quickly obtain the information they need.

[1289] Specific examples

[1290] In a situation where the user cannot remember the details of the recent maintenance performed on Machine A, the system operates as follows:

[1291] 1. Data collection: The terminal acquires business records including "Machine A maintenance" and "parts replacement."

[1292] 2. Data storage: The server stores these data in an SQLite database.

[1293] 3. Data analysis: Extract frequently occurring keywords such as "maintenance," "machine A," and "parts replacement."

[1294] 4. Information generation: For example, the generation AI generates information based on the following prompt sentence:

[1295] Prompt: What work have you done recently? Hint: Maintenance on machine A.

[1296] 5. Information presentation: The robot assistant will provide the user with a voice message saying, "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts."

[1297] This allows users to quickly recall necessary information, improving work efficiency and safety.

[1298] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1299] System program processing flow

[1300] Step 1:

[1301] Data collection: The device collects work history and records from the user's daily work report, business systems, and communication platforms (e.g., Slack, Teams). Specifically, the device sends API requests to these data sources to obtain text data from daily reports and system log data.

[1302] Input: Daily work reports, business systems, Slack data (e.g., "2023-10-01: Maintenance performed on Machine A").

[1303] Output: A list of the retrieved data.

[1304] Step 2:

[1305] Data storage: The server stores the collected data in a data storage such as SQLite. Specifically, the server establishes a connection to the data storage and inserts the acquired data into the database in chronological order for each user.

[1306] Input: Collected work history and record contents.

[1307] Output: Data stored in data storage.

[1308] Step 3:

[1309] Data analysis: The server analyzes the stored data and extracts frequently occurring keywords. Specifically, the server uses natural language processing techniques (e.g., morphological analysis) to analyze the text data and calculate the frequency of occurrence of important keywords.

[1310] Input: Data stored in data storage.

[1311] Output: A list of frequently occurring keywords (e.g., "machine A," "maintenance," "parts replacement").

[1312] Step 4:

[1313] Information generation: The server generates information using a generation AI (e.g., GPT-3) based on frequently occurring keywords. Specifically, the server sends a prompt to the generation AI and receives the resulting text.

[1314] Input: Frequently used keywords, prompt sentence.

[1315] Output: Generated text (e.g., "Recently, you have performed maintenance on Machine A. It appears that you have also replaced some parts.").

[1316] Step 5:

[1317] Information presentation: The server presents the generated information to the user via the robot assistant. Specifically, the robot assistant provides the generated information to the user using voice synthesis technology or a display.

[1318] Input: The generated text.

[1319] Output: The information presented to the user.

[1320] This configuration allows users to quickly recall necessary information, improving work efficiency and safety.

[1321] 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.

[1322] As a specific example of a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[1323] Basic configuration

[1324] The system mainly consists of the following elements:

[1325] 1. Data Collection Module

[1326] 2. Database

[1327] 3. Data Analysis Module

[1328] 4. Generation AI

[1329] 5. User Interface

[1330] 6. Emotion Engine

[1331] Data Collection Module

[1332] Device:

[1333] With the user's permission, the device will collect the user's activity history and posted content from social networking services (SNS), for example, text, images, and videos shared by the user on the SNS platform.

[1334] Database

[1335] server:

[1336] The server stores the collected data in a database. This database manages the personal data of each user, and stores the collected behavioral history and posted content in chronological order.

[1337] Data Analysis Module

[1338] server:

[1339] The server analyzes the data in the database and uses an emotion engine to identify the user's emotional state. It also extracts frequently occurring keywords and analyzes them based on the user's emotional state and the trends of the content of posts.

[1340] Generation AI

[1341] server:

[1342] Based on the emotional state identified by the emotion engine, the generative AI generates relevant text and images. For example, if the user is feeling stressed, it can provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as GPT-3.

[1343] User Interface (UI)

[1344] Chatbots:

[1345] The generated information is presented to the user via a chatbot. When a user asks, "I can't remember the title of a song I heard recently," the chatbot will provide a response based on the analysis results, such as, "You recently posted about 'XX.' Is this the song you want to remember?"

[1346] Emotion Engine

[1347] server:

[1348] The emotion engine analyzes users' text and posts and identifies their emotional state using natural language processing technology. For example, if a post contains emotional expressions such as "fun," "happy," or "sad," the engine detects this and uses it for analysis. The emotion engine then integrates the user's emotional state into the analysis results, enabling the provision of more personalized information.

[1349] Specific examples

[1350] For example, consider a situation where a user cannot remember the title of a movie they recently watched. In this case, the system operates as follows.

[1351] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting."

[1352] 2. The server stores these posts in a database.

[1353] 3. The server retrieves the data from the database, and the emotion engine analyzes the user's emotional state. If the user posts comments such as "It was fun" or "I was moved," these will also be included in the analysis.

[1354] 4. The analysis module extracts the frequently occurring keywords "movie," "watched," and "interesting."

[1355] 5. The generative AI generates the question, "Isn't 'XX' the movie that moved you the most recently?"

[1356] 6. The chatbot presents this generated information to the user to assist in memory recall.

[1357] In this way, by providing information that takes into account the user's emotional state, the present invention can effectively resolve the memory lapses of the user and improve the quality of daily life.

[1358] The processing flow will be explained below.

[1359] Step 1:

[1360] The user accesses the system and grants permission for data collection and analysis. The device connects the SNS account to the system and obtains the user's postings and behavioral history via API.

[1361] Step 2:

[1362] The device sends the content of social media posts and activity history data it has acquired to a server. The sent data includes information such as text, images, and videos.

[1363] Step 3:

[1364] The server stores the received data in the data storage. The database manages the individual personal data for each user and stores the acquired data in chronological order.

[1365] Step 4:

[1366] The server sends the stored data to a data analysis module, which uses natural language processing technology to analyze the posts, calculate the frequency of specific keywords and phrases, and extract highly relevant keywords.

[1367] Step 5:

[1368] Based on the analysis results, the server uses an emotion engine to analyze the user's emotional state. The emotion engine reads emotions from the text and identifies emotions such as "happy," "sad," and "excited."

[1369] Step 6:

[1370] The server combines the analyzed keywords with the emotional state and sends the combined results to the generation AI, which then uses a text generation algorithm such as GPT-3 to generate a specific answer. For example, it generates text such as, "You recently posted about the movie 'XX.' Was it moving?"

[1371] Step 7:

[1372] The chatbot presents the generated text to the user. When the user makes a query such as "I can't remember the title of the song I listened to recently," the chatbot will provide an appropriate answer based on the analysis and generation results.

[1373] Step 8:

[1374] The user reviews the information presented and determines whether the information they want to recall is correct. If it is correct, the user can quickly obtain the information they need. If it is not, the user can enter additional keywords or information, and the system will analyze and generate it again.

[1375] This allows the system to efficiently resolve memory lapses, reduce user stress, and quickly provide the information the user desires, while taking into account the user's emotional state.

[1376] Example 2

[1377] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1378] In today's information society, users consume a huge amount of information every day, which can make it difficult to recall important information. Effective methods are needed to resolve the "tip of the tongue phenomenon," a situation in which users want to recall specific information but are unable to. Furthermore, by taking the user's emotional state into consideration, more personalized support can be provided. To address this issue, a system is needed that analyzes a user's behavioral history and posted content, identifies their emotional state, and generates and provides appropriate information.

[1379] 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.

[1380] In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in a data storage, means for analyzing the saved data and identifying the user's emotional state, means for extracting frequently occurring keywords, means for generating related information based on the analysis results and the extracted keywords, and means for presenting the generated information to the user. This eliminates the problem of memory lapses in the user's memory and enables the provision of personalized information that takes into account the user's emotional state.

[1381] "Behavioral history" is a record of specific actions or operations that a user has performed in the past, including web browsing, application usage, and location information.

[1382] "Posted content" refers to information such as text, images, and videos that users make public on social networking services, blogs, forums, etc.

[1383] "Data storage" means a physical or virtual repository for storing captured data, including databases and cloud storage.

[1384] An "emotional state" refers to the emotional or feeling state a user is experiencing at a particular moment, including emotions such as "happy," "sad," and "angry."

[1385] "Frequent keywords" are words or phrases that are frequently used within a certain period of time, as identified through data analysis.

[1386] "Related information" is information that is useful to users and is generated based on the analysis results and extracted keywords. This includes text, images, videos, etc.

[1387] A "text generation algorithm" is a computational method for automatically generating natural language text based on input prompts and data, including neural network-based models.

[1388] "User presentation" refers to the interface or device through which the generated information is presented to the user, including chatbots, notification systems, mobile apps, etc.

[1389] As a form for implementing the present invention, we will explain a system that combines a system that eliminates the "tip of the tongue phenomenon," i.e., the memory lapse phenomenon of "What was that again?", based on the user's daily behavior and SNS posts, with an emotion engine that recognizes the user's emotions.

[1390] Basic configuration

[1391] The system mainly consists of the following elements:

[1392] 1. Data Collection Module

[1393] 2. Data Storage

[1394] 3. Data Analysis Module

[1395] 4. Generation AI

[1396] 5. User Interface

[1397] 6. Emotion Engine

[1398] Data Collection Module

[1399] Terminal

[1400] With the user's permission, the device acquires the user's behavioral history and posted content from social networking services (SNS). For example, it collects text, images, and videos that the user has shared on the SNS platform. This data collection is done using the SNS API. Specifically, it acquires user posted data using the Twitter API or Facebook API.

[1401] Data Storage

[1402] server

[1403] The data collected by the server is stored in data storage. This data storage uses a relational database such as MySQL or PostgreSQL, and individual personal data for each user is stored in chronological order. The stored data includes fields such as "user ID," "post content," and "post date and time."

[1404] Data Analysis Module

[1405] server

[1406] The server retrieves data from the data storage and uses an emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing technology (e.g., BERT or GPT-3) to analyze the content of posts and extract frequently occurring keywords. It also analyzes the user's emotional state and trends in the content of posts.

[1407] Generation AI

[1408] server

[1409] The generative AI generates relevant text and images based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, it will provide information to encourage relaxation. The generative AI uses advanced text generation algorithms such as OpenAI's GPT-3.

[1410] User Interface (UI)

[1411] Chatbots

[1412] The generated information is presented to the user via a chatbot. For example, if a user asks, "I can't remember the title of the song I heard recently," the chatbot will provide an answer based on the analysis results, such as, "You recently posted about 'XX'. Is this the song you want to remember?" The chatbot uses Dialogflow, Microsoft Bot Framework, etc.

[1413] Emotion Engine

[1414] server

[1415] The emotion engine analyzes the user's text and post content and identifies their emotional state using natural language processing technology. For example, if the content contains emotional expressions such as "fun," "happy," or "sad," it detects these and uses them for analysis. The emotion engine uses Google's Natural Language API and IBM Watson's Tone Analyzer, among others.

[1416] Specific examples

[1417] For example, consider a situation where a user cannot remember the title of a movie they recently saw. In this case, the system would act as follows:

[1418] 1. The device retrieves related posts from the user's social media posts, such as "movies," "watched," and "interesting." For example, it uses the Twitter API to collect the user's past tweets.

[1419] 2. The server stores these posts in a MySQL database.

[1420] 3. The server retrieves the data from the database, and the emotion engine uses BERT to analyze the user's emotional state. If the user posts comments such as "I had fun" or "I was moved," these will also be included in the analysis.

[1421] 4. The analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" using a Python NLP library (e.g., spaCy).

[1422] 5. The generative AI uses GPT-3 to generate text such as, "Isn't 'XX' the movie you recently saw that moved you?"

[1423] 6. The chatbot uses Dialogflow to present this generated information to the user to assist in memory recall.

[1424] Example prompt sentence:

[1425] "I can't remember the title of the last movie I saw. What movie moved me?"

[1426] In this way, the system can effectively eliminate the memory lapse phenomenon of the user.

[1427] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1428] Step 1: Data collection

[1429] Terminal

[1430] The user authorizes access to the social networking site. On this premise, the device uses the social networking site's API (for example, Twitter API or Facebook API) to obtain the user's behavioral history and posted content.

[1431] Input: Social media account credentials

[1432] Output: User posted data (text, images, videos)

[1433] Specific operation: The device calls the SNS API, sends a "Get recent posts" request, and retrieves the 100 most recent posts from the SNS.

[1434] Step 2: Save data

[1435] server

[1436] The acquired user's SNS data is received and saved in data storage (e.g. MySQL database). When saved, the post content, posting date and time, user ID, etc. are also recorded.

[1437] Input: User submitted data

[1438] Output: Post data saved in the database

[1439] Specific operation: The server executes the SQL statement "INSERT INTO user_data (user_id, post_content, post_date) VALUES (?, ?, ?)" to store the information in the database.

[1440] Step 3: Sentiment Analysis

[1441] server

[1442] User posted data is retrieved from the database and sentiment analysis is performed using natural language processing technology. Specifically, sentiment analysis is performed using a sentiment engine (e.g., BERT or Google Natural Language API).

[1443] Input: Post data stored in the database

[1444] Output: Parsed emotional state (e.g. positive, negative, neutral, etc.)

[1445] Specific operation: The server executes the SQL statement "SELECT post_content FROM user_data WHERE user_id = ?", passes the retrieved post text to the emotion engine, and receives the analysis results.

[1446] Step 4: Keyword extraction

[1447] server

[1448] Based on the sentiment analysis results, frequently occurring keywords are extracted using a natural language processing library. Specifically, an NLP library (e.g., spaCy) is used.

[1449] Input: Parsed emotional state and post data

[1450] Output: A list of extracted frequent keywords

[1451] Specific operation: Based on the results of the sentiment analysis, the server performs a process to extract frequently occurring words such as "movie" and "moving."

[1452] Step 5: Information Generation

[1453] Generation AI

[1454] Based on the results of sentiment analysis and keyword extraction, relevant information is generated using a generative AI model (e.g., GPT-3).

[1455] Input: Sentiment analysis results, frequently used keywords

[1456] Output: Generated text or image

[1457] Specific operation: The generative AI receives the prompt sentence "What movie did the user see recently that moved you?" as input and generates appropriate information.

[1458] Step 6: Information presentation

[1459] Chatbots

[1460] The generated information is presented to the user via a user interface (e.g., a chatbot), and responses to inquiries are generated using Dialogflow or the Microsoft Bot Framework.

[1461] Input: Generated information (text or image)

[1462] Output: Information presented to the user

[1463] Specific behavior: The chatbot sends the user a message saying, "Isn't 'XX' the movie that moved you the most recently?"

[1464] Through this specific processing flow, the system can effectively eliminate the user's "tip-of-the-tongue phenomenon" and improve the quality of daily life.

[1465] (Application example 2)

[1466] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1467] In recent years, there has been an increasing demand for systems that provide personalized information by analyzing users' behavioral history and posted content. However, current systems have difficulty providing information that takes into account the user's emotional state, resulting in a problem of a decline in the quality of the user experience. To solve this problem, more advanced personalized information generation that takes into account the user's emotional state is required.

[1468] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a user's behavioral history and posted content, means for saving the acquired behavioral history and posted content in data storage, means for identifying the user's emotional state, means for generating information using a generative AI model, and means for presenting the generated information to the user through a user interface. This makes it possible to recommend more appropriate content based on the user's emotional state.

[1469] "Behavioral history" refers to the history of various actions and activities that a user performs in their daily life, including social media posts, browsing history, GPS information, etc.

[1470] "Posted content" refers to content such as text, images, and videos that users make public on social networking services (SNS) and other platforms.

[1471] "Data storage" means systems or devices for storing collected data, including cloud storage, database servers, etc.

[1472] "Emotional state" refers to the emotion a user is feeling at a particular moment, which is extracted from text analysis using natural language processing techniques.

[1473] "Frequent keywords" refer to words and phrases that frequently appear in users' posts and behavioral history, and are important indicators of trends and interests.

[1474] A "generative AI model" is an artificial intelligence algorithm that generates natural language based on large amounts of data, generating personalized information based on a user's behavioral history and emotional state.

[1475] "User interface" refers to an interface that presents generated information to users in an easy-to-understand manner, including chatbots and application screen displays.

[1476] A specific embodiment for carrying out the present invention will be described below. First, the system mainly comprises the following elements:

[1477] 1. Data collection module: Obtains user behavior history and SNS postings from the device.

[1478] 2. Data storage: The acquired behavioral history and posted content are stored on a database server.

[1479] 3. Data analysis module: Analyzes the stored data and extracts frequently occurring keywords.

[1480] 4. Emotion Engine: Analyzes user posts to identify their emotional state.

[1481] 5. Generative AI model: Generates information based on emotional state and analysis results.

[1482] 6. User Interface: Presents the generated information to the user.

[1483] The detailed operation of each element will be explained below.

[1484] Data Collection Module

[1485] With the user's permission, the device will collect the user's behavioral history and posted content from social networking services (SNS), such as text, images, and videos shared by the user on the SNS platform. This data is collected in real time.

[1486] Data Storage

[1487] The server saves the collected data in data storage. This database manages the personal data of each user, and saves the collected behavioral history and posted content in chronological order. Examples of databases that can be used include MySQL and PostgreSQL.

[1488] Data Analysis Module

[1489] The server analyzes the data in the data storage and uses natural language processing libraries (e.g., spaCy or NLTK) to extract frequently occurring keywords and phrases. This analysis reveals frequently used words and trends among users.

[1490] Emotion Engine

[1491] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the user's posts and uses natural language processing technology to identify emotional states such as "joy," "happy," and "sad."

[1492] Generative AI Models

[1493] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate relevant information based on the emotional state identified by the emotion engine and the analysis results. If the user is feeling stressed, the generated information will be content that encourages relaxation.

[1494] User Interface

[1495] The generated information is presented to the user via a user interface. React Native or Flutter can be used for the interface, and information can be provided in the form of a chatbot. The user can receive suggested content in an interactive format.

[1496] Specific examples

[1497] For example, if a user posts, "I can't remember the name of the last movie I saw," then:

[1498] 1. The data collection module retrieves related posts such as "movies," "watched," and "interesting" from social media.

[1499] 2. The data analysis module extracts frequently occurring keywords such as "movie," "watched," and "interesting" from the posted content.

[1500] 3. The emotion engine analyzes emotions such as "It was fun" or "I was moved" from the user's posts.

[1501] 4. The generative AI model generates the text, "Isn't 'XX' the movie you recently saw that moved you the most?"

[1502] 5. The user interface presents the text to the user in the form of a chatbot.

[1503] Prompt Sentence Examples

[1504] A user says they can't remember the title of a moving movie they recently saw. Please suggest movie titles based on the following keywords and their emotional state:

[1505] Keywords: movie, watched, interesting, fun, moving

[1506] Emotional state: Positive

[1507] As described above, this system provides highly personalized information based on the user's emotional state and behavioral history.

[1508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1509] Step 1:

[1510] With the user's permission, the device obtains the user's behavioral history and posted content from a social networking service (SNS). The input is the posted content and behavioral history data using the SNS API, and the output is a collection of this data. The device obtains the user's text, images, videos, etc. from the SNS API and sends them to the next processing step.

[1511] Step 2:

[1512] The server stores the behavioral history and posted content sent from the device in data storage (for example, a MySQL or PostgreSQL database). The input is data obtained from the device, and the output is records stored in the database. The server connects to the database and stores the input data in individual records for each user.

[1513] Step 3:

[1514] The server analyzes the data in the data storage using a natural language processing library (e.g., spaCy or NLTK) and extracts frequently occurring keywords. The input is the data stored in the database, and the output is the extracted frequently occurring keywords. The server tokenizes the text data and analyzes the frequency of occurrence to extract keywords.

[1515] Step 4:

[1516] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to identify the emotional state from the user's posted content. The input is text data in the database, and the output is the identified emotional state. The server sends the posted text to the emotion engine, which identifies the emotional state, such as positive, negative, or neutral.

[1517] Step 5:

[1518] The server generates information using a generative AI model (e.g., OpenAI GPT-3) based on the emotional state and frequent keywords identified by the emotion engine. The input is the emotional state and frequent keywords, and the output is the generated text information. The server sends the input data to the generative AI model in the form of prompts to generate personalized content.

[1519] Step 6:

[1520] The server presents the generated information to the user through a user interface. The input is the output text from the generative AI model, and the output is the information displayed to the user through the user interface. The server uses React Native or Flutter to provide information to the user in the form of a chatbot, allowing the user to easily check the generated information.

[1521] In this way, highly personalized information provision based on the user's behavioral history and emotional state is realized.

[1522] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1523] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1524] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1525] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1526] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1527] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1528] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1529] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1530] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1531] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1532] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1533] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1534] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1535] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1536] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1537] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1538] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1539] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1540] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1541] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1542] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1543] The following is further disclosed regarding the above embodiment.

[1544] (Claim 1)

[1545] A means for acquiring a user's behavior history and posted content;

[1546] A means for storing the acquired behavioral history and posted content in data storage;

[1547] A means for analyzing the stored data and extracting frequently occurring keywords;

[1548] generating means based on the analysis results;

[1549] means for presenting the generated information to a user;

[1550] A system including:

[1551] (Claim 2)

[1552] 2. The system according to claim 1, further comprising means for acquiring a user's behavior history and posted content from a social networking service.

[1553] (Claim 3)

[1554] 10. The system of claim 1, further comprising means for generating information using a text generation algorithm based on the extracted frequent keywords.

[1555] "Example 1"

[1556] (Claim 1)

[1557] A means for acquiring a user's behavior history and posted content;

[1558] A means for storing the acquired behavioral history and posted content in data storage;

[1559] A means for analyzing the stored data and extracting frequently occurring keywords;

[1560] A means using a generation AI to generate information based on the analysis results;

[1561] a user interface means for presenting the generated information to a user;

[1562] A system including:

[1563] (Claim 2)

[1564] 2. The system according to claim 1, further comprising means for acquiring a user's behavior history and posted content from a social networking service.

[1565] (Claim 3)

[1566] 10. The system of claim 1, further comprising means for generating information using a text generation algorithm based on the extracted frequent keywords.

[1567] "Application Example 1"

[1568] (Claim 1)

[1569] A means for acquiring the user's work history and record contents;

[1570] A means for storing the acquired business history and record contents in data storage;

[1571] A means for analyzing the stored data and extracting frequently occurring keywords;

[1572] generating means based on the analysis results;

[1573] means for presenting the generated information to a user via a robot assistant;

[1574] A system including:

[1575] (Claim 2)

[1576] 2. The system according to claim 1, further comprising means for acquiring a user's business history and recorded contents from the business system and the communication platform.

[1577] (Claim 3)

[1578] 10. The system of claim 1, further comprising means for generating information using a text generation algorithm based on the extracted frequent keywords.

[1579] "Example 2: Combining Emotion Engines"

[1580] (Claim 1)

[1581] A means for acquiring a user's behavior history and posted content;

[1582] A means for storing the acquired behavioral history and posted content in data storage;

[1583] means for analyzing the stored data to identify an emotional state;

[1584] A means of extracting frequently occurring keywords,

[1585] means for generating related information based on the analysis results and the extracted keywords;

[1586] means for presenting the generated information to a user;

[1587] A system including:

[1588] (Claim 2)

[1589] 2. The system according to claim 1, further comprising means for acquiring a user's behavior history and posted content from a social networking service.

[1590] (Claim 3)

[1591] 10. The system of claim 1, further comprising means for generating relevant information based on the emotional state and the extracted frequent keywords using a text generation algorithm.

[1592] "Application example 2 when combining emotion engines"

[1593] (Claim 1)

[1594] A means for acquiring a user's behavior history and posted content;

[1595] A means for storing the acquired behavioral history and posted content in data storage;

[1596] A means for analyzing the stored data and extracting frequently occurring keywords;

[1597] means for identifying an emotional state of a user;

[1598] a means for generating information using a generative AI model based on the analysis results and the emotional state;

[1599] means including a user interface for presenting the generated information to a user;

[1600] A system including:

[1601] (Claim 2)

[1602] 2. The system according to claim 1, further comprising means for acquiring a user's behavior history and posted content from a social networking service.

[1603] (Claim 3)

[1604] 10. The system of claim 1, further comprising: means for generating information using a generative AI model based on the extracted frequent keywords and emotional states. [Explanation of symbols]

[1605] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring a user's behavior history and posted content; A means for storing the acquired behavioral history and posted content in data storage; A means for analyzing the stored data and extracting frequently occurring keywords; generating means based on the analysis results; means for presenting the generated information to a user; A system including:

2. The system according to claim 1, further comprising means for acquiring a user's behavior history and posted content from a social networking service.

3. 2. The system according to claim 1, further comprising means for generating information using a text generation algorithm based on the extracted frequently occurring keywords.

Images