system

Abstract

We provide a system that allows users to easily and quickly obtain the information they need, eliminating redundant work and waste within the company. [Solution] A system comprising: means for periodically collecting data from various internal data sources; means for converting the collected data into an appropriate format and storing it in an integrated database; means for users to input questions in chat format via a terminal; means for analyzing the received questions using natural language processing and generating search queries; means for obtaining relevant information from the integrated database based on the generated search queries; means for generating answers using generative artificial intelligence based on the obtained information; and means for sending and displaying the generated answers on the user's terminal.

Description

Technical Field

[0004] ,

[0006] , , ,

[0005] , , , ,

[0001] The technology of this disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Show the "Problems to be Solved by the Invention" and "Means for Solving the Problems" in the detailed description.

[0005] Various manuals within the company, legal review histories, work achievements, etc. exist in a scattered manner, making it difficult to quickly obtain the necessary information. Also, there are problems such as the easy occurrence of duplicate work and waste of information. Searching for and aggregating information takes a lot of time and often results in wasted labor. Therefore, there is an increasing need for an efficient system that allows users to easily obtain the necessary information and eliminates duplicate work.

Means for Solving the Problems

[0006] The present invention is a system that includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in a chat format via a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the obtained information, and means for sending and displaying the generated answers on the user terminal. With the present invention, users can easily and quickly obtain the information they need, and it is possible to eliminate redundant work and waste within the company.

[0007] A "data source" is the origin from which data is obtained from various systems and databases within a company.

[0008] "Data collection" is the process of periodically extracting necessary data from various data sources and incorporating it into the system.

[0009] "Data conversion" is the process of transforming collected data into a format that is appropriate for the system to use.

[0010] An "integrated database" is a database used to centrally store and manage data collected from multiple data sources.

[0011] A "user terminal" is an electronic device that a user uses to access a system and enter questions.

[0012] A "chat format" refers to an interface that allows users to send questions to the system in a conversational format, using natural language input.

[0013] "Natural language processing" is a technology that analyzes natural language questions entered by users, enabling computers to understand and process them.

[0014] A "search query" is a formal inquiry sentence generated by natural language processing to obtain information from a database.

[0015] A "generative artificial intelligence" is an artificial intelligence that can generate appropriate answers to human questions based on the acquired information and data.

[0016] "Answer generation" is a process in which a generative artificial intelligence creates an answer to a user's question based on the data it has acquired.

[0017] "Answer display" is a process of transmitting the generated answer to the user terminal and making it visible to the user.

Brief Description of the Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10]Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Further, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of the arithmetic unit include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the 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.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0032] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user inquiries using generative artificial intelligence. A specific embodiment of this system, including the program's processing, is described in detail below.

[0040] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[0041] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[0042] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[0043] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest legal review history," the NLP engine extracts keywords such as "latest," "legal," and "review history," and uses them to construct a search query.

[0044] Next, the server uses the generated search query to search the integrated database and retrieve relevant information. At this point, the server issues a query to the database and retrieves the corresponding records. The retrieved information is not used directly, but is instead input into the generative artificial intelligence.

[0045] The server inputs the acquired information into a generative artificial intelligence (AI) system, which generates answers to the user's questions in a natural way. The generative AI system creates the optimal answer based on the acquired data and generates it as a sentence in natural language. For example, it might generate a specific answer such as, "The latest legal review history is as follows..."

[0046] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. The user can instantly see the answer to the question they entered. This entire process allows the user to easily and quickly obtain the information they need.

[0047] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. This process allows users to obtain the necessary information without any effort, and significantly reduces redundant work and waste within the company.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The server collects the latest data from each data source. This is done by running automated scripts on a regular schedule. For example, it might send API requests to retrieve internal manuals, execute database queries to extract legal review history, and download performance data.

[0051] Step 2:

[0052] The server converts the collected data into an appropriate format and stores it in an integrated database. First, the collected data is converted to a format such as JSON, and metadata such as "source," "date," and "category" is added to the data. Then, the converted data is saved to the integrated database.

[0053] Step 3:

[0054] The user enters their question through the device's chat interface. The user enters their question in natural language, such as "Please tell me the latest legal review history" in the chat window.

[0055] Step 4:

[0056] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[0057] Step 5:

[0058] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[0059] Step 6:

[0060] The server generates a search query based on the extracted keywords. For example, a query like "latest AND legal AND verification history" is generated.

[0061] Step 7:

[0062] The server searches the integrated database using the generated search query. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[0063] Step 8:

[0064] The server inputs the acquired information into a generative artificial intelligence (AI) system to generate answers to the user's questions. The AI ​​system creates natural-sounding responses based on the acquired data. For example, it might generate an answer such as, "The latest legal review history is as follows..."

[0065] Step 9:

[0066] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal and displayed on the chat interface.

[0067] Step 10:

[0068] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific response to the question.

[0069] The above outlines the specific processing steps of the program. This allows users to quickly and easily obtain the necessary information through the system.

[0070] (Example 1)

[0071] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0072] Conventional data collection systems have struggled to centrally manage data from different formats and sources, making it difficult to quickly and accurately obtain necessary information. Furthermore, few systems could automatically generate appropriate answers to natural language questions, resulting in low user convenience.

[0073] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0074] In this invention, the server includes means for periodically executing automated scripts to collect data from various internal data sources, means for converting the collected data into JSON format or the like, adding metadata, and storing it in an integrated database, and means for analyzing received questions using natural language processing, extracting important keywords, and generating search queries. This makes it possible to generate and provide accurate and rapid answers using generative artificial intelligence to questions entered by users in natural language.

[0075] A "data source" refers to the system or database from which information is collected.

[0076] An "automatic script" refers to a program that is executed automatically at regular time intervals.

[0077] A "server" refers to a computer system that collects, transforms, and analyzes data.

[0078] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and refers to a text format for structuring and representing data.

[0079] "Metadata" refers to information related to data (such as source, date, category, etc.).

[0080] An "integrated database" refers to a database that centrally manages data collected from multiple data sources.

[0081] A "user" refers to anyone who wants to use the system to obtain information.

[0082] A "terminal" refers to a device (such as a PC or smartphone) that a user uses to access a system.

[0083] A "chat interface" refers to an interactive input method that allows users to enter questions using natural language.

[0084] "Natural language processing" refers to the technology of analyzing and understanding human language using computers.

[0085] A "search query" refers to a search command used to retrieve specific information from a database.

[0086] "Generative artificial intelligence" refers to artificial intelligence technology that generates natural-sounding sentences and responses based on data.

[0087] "Answer" refers to the response provided by a generative artificial intelligence system to a user's question.

[0088] This invention relates to a system that collects data from various data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. An embodiment of this system will be described in detail.

[0089] First, the server collects data using Python and SQL. It retrieves the necessary information from data sources using API requests (e.g., requests.get('https: / / internal-api.example.com / manuals')) and extracts information from databases by executing SQL queries (e.g., SELECT FROM legal_records WHERE update_date > CURDATE() - INTERVAL 1 DAY;). This allows data to be collected from systems such as the manual management system, the legal confirmation history database, and the system that manages the achievements of each department.

[0090] Next, the server converts the collected data into JSON format (using json.dumps) and adds metadata. This standardization of formatting makes subsequent searching and analysis easier. The converted data is then stored in the unified database using SQL (e.g., INSERT INTO unified_db (data, source, date) VALUES (...);).

[0091] If a user wants to obtain information, they enter their question through the chat interface on their device. The chat interface is provided via a web browser or a dedicated application. For example, the user might enter a question in text format, such as "Tell me about my recent legal review history." The device then sends the question to the server (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})).

[0092] The server analyzes the received question using natural language processing (NLP) techniques. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the question and extract important keywords. For example, from the question "Please tell me my recent legal review history," it extracts the keywords "recent," "legal," and "review history." Then, it generates a search query based on these keywords.

[0093] Using the generated search query, the server retrieves relevant information from the integrated database. In this process, the server issues SQL queries (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The retrieved information is then directly input into the generative artificial intelligence.

[0094] Next, the server uses generative artificial intelligence (e.g., GPT-3®) to generate answers to the user's questions based on the information it has acquired. The generative AI generates natural-sounding sentences based on the input data, creating specific answers such as, "The recent legal review history is as follows..."

[0095] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. This allows the user to instantly obtain the answer to the question they entered.

[0096] As an example of a prompt, the user might type, "Tell me about my recent legal review history." This prompts the server to search the legal review history data already collected during the data collection phase, and a generative artificial intelligence system generates a specific answer based on that data. The answer is then displayed on the user's terminal, providing the information instantly. This entire process allows the user to quickly obtain the necessary information without any hassle.

[0097] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0098] Step 1:

[0099] The server periodically runs automated scripts to collect data from various internal data sources. Specifically, it uses Python's requests library and SQL SELECT statements to retrieve data from API requests and extract information from the database. The server accesses API endpoints (e.g., requests.get('https: / / internal-api.example.com / manuals')) and temporarily stores the retrieved data. The input is API endpoints and database queries, and the output is the temporarily stored data.

[0100] Step 2:

[0101] The server converts the collected data into JSON format, adds metadata, and stores it in the unified database. Specifically, it uses the `json.dumps` method to convert the data into JSON format and then uses SQL to store it in the unified database. The input is the temporarily stored data, and the output is the JSON data stored in the unified database. The server executes SQL statements such as `INSERT INTO unified_db (data, source, date) VALUES (...);`.

[0102] Step 3:

[0103] The user enters their question through the terminal's chat interface. The terminal sends the text entered by the user (e.g., "Tell me about my recent legal review history") to the server. Specifically, the terminal sends the user's text input to the server as a POST request in JSON format (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})). The input is the user's question, and the output is the question data sent to the server.

[0104] Step 4:

[0105] The server analyzes received questions using natural language processing (NLP) techniques and generates search queries. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the questions and extract important keywords. For example, from the question "Please tell me about recent legal review history," it extracts the keywords "recent," "legal," and "review history." The input is the received question data, and the output is the search query.

[0106] Step 5:

[0107] The server uses the generated search query to search the unified database and retrieve relevant information. Specifically, it issues an SQL query (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The input is the search query, and the output is the retrieved database records.

[0108] Step 6:

[0109] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates answers to the user's questions in a natural-sounding format. Specifically, data is input into a generative AI model (e.g., GPT-3), and the AI ​​generates answers in natural language. For example, a specific answer such as "The latest legal review history is as follows..." might be generated. The input is the acquired database records, and the output is the generated answer.

[0110] Step 7:

[0111] The server sends the generated response to the user's terminal, and the terminal displays the response in the chat interface. Specifically, the server sends the generated response to the user's terminal as a POST request (e.g., requests.post('https: / / client-api.example.com / response', data={'response': 'The latest legal review history is as follows...'})), and the user's terminal displays the received response in the chat box. The input is the generated response, and the output is the response displayed in the chat interface.

[0112] (Application Example 1)

[0113] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0114] Conventional factory management systems suffer from a fragmented data collection system, lacking effective means to integrate necessary information. Furthermore, they lack automated response functions to allow workers to instantly obtain required information, necessitating manual responses even in situations requiring rapid action. This results in low factory efficiency and a tendency towards information duplication and waste.

[0115] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0116] In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format via a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the obtained information, means for forming detailed answers to the user's questions using a generative AI model, means for sending and displaying the generated answers on the user's terminal, and means for automatically collecting data from various sensors and systems within the factory and storing it in an integrated database. This enables workers to quickly and accurately obtain the latest information within the factory, significantly improving the operational efficiency of the factory.

[0117] "Various internal data sources" refers to data provided by multiple departments and business systems.

[0118] "Means of collecting data periodically" refers to a system that has the function of automatically collecting data at set time intervals.

[0119] "Means of converting to an appropriate format and storing in an integrated database" refers to the process of converting collected data into a unified format and saving it in an integrated database.

[0120] "A means for users to input questions in a chat format via their device" refers to an interface that allows users to input text from their device and interact with the system.

[0121] "A means of analyzing received questions using natural language processing and generating search queries" refers to a technology that analyzes input text and converts it into a query suitable for searching.

[0122] "A means of retrieving relevant information from an integrated database based on a generated search query" refers to the process of using a search query to search the database and extract the necessary information.

[0123] "A means of generating an answer using generative artificial intelligence based on acquired information" refers to a function that inputs data into an AI model and generates an answer in natural language.

[0124] "Means for forming detailed answers to user questions using a generative AI model" refers to the technology of creating detailed and specific answers using generative AI technology.

[0125] "Means of sending and displaying the generated answer on the user's terminal" refers to a mechanism for transferring the response generated by the AI ​​to the user's device and displaying it.

[0126] "Methods for automatically collecting data from various sensors and systems within a factory and storing it in an integrated database" refers to the process of automatically collecting and integrating data from sensors and systems within a factory and saving it to a database.

[0127] This invention specifically describes a factory management system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. The specific processes for implementing this invention are described below.

[0128] The server first runs automated scripts periodically to collect the latest data from various sensors and systems within the factory. These data sources include manufacturing line sensors, inventory management systems, and quality control systems. The server retrieves the necessary data using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database.

[0129] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format, making subsequent retrieval easier.

[0130] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[0131] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and uses them to construct a search query.

[0132] Next, the server searches the integrated database using the generated search query and retrieves relevant information. The retrieved information is not used directly, but is instead input into a generative artificial intelligence (AI). The server inputs the retrieved information into the generative AI, which generates answers to the user's questions in a natural way. The generative AI creates the optimal answer based on the retrieved data and generates it as a sentence in natural language. For example, a specific answer such as "The latest inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units" is generated.

[0133] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. Users can instantly see the answer to the question they entered. This entire process allows users to easily and quickly obtain the information they need, significantly improving operational efficiency within the factory.

[0134] As a concrete example, when a user enters the question, "Please tell me the latest inventory status," the server first searches for inventory data already acquired during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. Examples of such prompts include the following:

[0135] "Please tell me the latest stock status."

[0136] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0137] Step 1:

[0138] Data collection:

[0139] The server periodically executes automated scripts to collect the latest data from various sensors and systems within the factory. Specifically, it retrieves information from manufacturing line sensors, inventory management systems, quality control systems, etc., using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database. The input for this step is data from sensors and systems within the factory, and the output is a series of data containing various information.

[0140] Step 2:

[0141] Data transformation and integration:

[0142] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format. The input for this step is various types of data, and the output is the data in the integrated database.

[0143] Step 3:

[0144] User question input:

[0145] Users use a chat interface via their device to input questions in natural language. This interface is provided as a web browser or a dedicated application. The questions entered by users are intended to obtain specific information. For example, a user might enter, "Please tell me the latest stock status." The input in this step is the user's question, and the output is that the question is sent to the server.

[0146] Step 4:

[0147] Question analysis using natural language processing (NLP):

[0148] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. Specifically, the NLP engine performs morphological analysis on the question sentence and extracts important keywords and context. For example, in the case of "Please tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and constructs a search query based on these. The input for this step is the user's question, and the output is the generated search query.

[0149] Step 5:

[0150] Integrated database search:

[0151] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues an appropriate query to the database and retrieves the corresponding records. For example, a query might be issued to search for "latest inventory data". The input to this step is the generated search query, and the output is the retrieved relevant information.

[0152] Step 6:

[0153] Solution generation using generative AI models:

[0154] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates natural-sounding answers to the user's questions. The generative AI model creates the optimal response based on the acquired data and generates it as a natural language sentence. For example, it might generate a specific answer such as, "The current inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units." The input for this step is the acquired relevant information, and the output is the generated response sentence.

[0155] Step 7:

[0156] Submitting and displaying answers:

[0157] The server sends the generated answer to the user's terminal, which displays the answer on the chat interface. The user can immediately see the answer to the question they entered. In this step, the input is the generated answer text, and the output is the answer displayed on the user's terminal.

[0158] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0159] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence and an emotion engine. A specific embodiment of this system, including the program's processing, is described in detail below.

[0160] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[0161] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[0162] If a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided via a web browser or a dedicated application. Users enter their questions in natural language, such as "Please tell me the latest legal review history" in the chat window.

[0163] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[0164] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The server performs morphological analysis on the question text and extracts important keywords and context such as "latest," "legal," and "verification history." Next, the server generates a search query based on the extracted keywords, creating a query that is "latest AND legal AND verification history."

[0165] The server uses the generated search query to search the integrated database and retrieve relevant information. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[0166] The server analyzes the acquired information and inputs it into the emotion engine. The emotion engine analyzes the user's input questions and determines their emotional state (e.g., anger, joy, confusion, etc.). For example, it evaluates whether the user is in a hurry or dissatisfied based on the tone and specific wording of the question.

[0167] Next, the server inputs the acquired information and the analysis results from the emotion engine into the generative artificial intelligence to generate an appropriate answer. Based on the identified emotional state, the generative AI creates an answer with a more appropriate tone and content. For example, if the user is confused, a more polite and easy-to-understand answer will be generated.

[0168] The server sends the generated answer to the user's terminal, which then displays the answer in the chat window. The user can instantly see a specific and appropriate answer to the question they entered.

[0169] For example, if a user enters a question such as "Tell me about my recent legal review history," and the sentiment engine detects that the user is in a hurry, it will generate a quick and easy-to-understand answer tailored to the user's needs. This answer will then be displayed in the chat window. This process allows users to easily and quickly obtain the information they need, significantly reducing internal duplication and waste.

[0170] As a result, the system of the present invention can recognize the user's emotions and generate more appropriate responses, thereby improving user satisfaction and work efficiency.

[0171] The following describes the processing flow.

[0172] Step 1:

[0173] The server collects the latest data from each data source. This is done by running automated scripts according to a regular schedule. Specifically, it sends API requests to retrieve internal manuals, executes database queries to extract legal review history, and downloads performance data.

[0174] Step 2:

[0175] The server converts the collected data into an appropriate format and stores it in an integrated database for user convenience. This conversion involves changing the data to a standardized format such as JSON, and adding metadata such as "source," "date," and "category." The converted data is then stored in the integrated database.

[0176] Step 3:

[0177] Users enter questions through the chat interface on their device. Specifically, they use a web browser or a dedicated application to enter questions in the format of, "Please tell me the latest legal review history."

[0178] Step 4:

[0179] The terminal sends the entered question to the server in real time. The chat interface receives user input and immediately sends that data to the server.

[0180] Step 5:

[0181] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[0182] Step 6:

[0183] The server generates a search query based on the extracted keywords. For example, it might create a query like "latest AND legal AND verification history".

[0184] Step 7:

[0185] The server searches the integrated database using the generated search query. It issues the query to the database, searches for relevant records, and retrieves the corresponding data.

[0186] Step 8:

[0187] The server analyzes the acquired information and inputs it into the emotion engine. Specifically, it passes the user's entered question text to the emotion engine and analyzes their emotional state (e.g., anger, joy, confusion, etc.).

[0188] Step 9:

[0189] The server inputs the acquired information and the analysis results from the emotion engine into a generative artificial intelligence (AI) system to generate the optimal answer. The generative AI takes the identified emotion into consideration to create a more appropriate tone and content for the response. For example, if the user is confused, it will generate a more polite and easy-to-understand response.

[0190] Step 10:

[0191] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal in real time and displayed in the chat window.

[0192] Step 11:

[0193] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific and appropriate response to the question they entered.

[0194] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase. If the emotion engine determines that the user is in a hurry, the generative artificial intelligence generates a quick and easy-to-understand answer. This answer is displayed in the chat window, allowing the user to instantly obtain the necessary information. This process makes it possible for users to easily and quickly obtain the information they need, significantly reducing redundant work and waste within the company.

[0195] (Example 2)

[0196] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0197] Conventional information gathering systems have suffered from inefficiency due to the cumbersome process of collecting and integrating data from various internal data sources. Furthermore, the process of users inputting questions and obtaining information has not taken into account the emotional state of the user, resulting in unsatisfactory responses and a diminished user experience. This invention aims to improve convenience and satisfaction by recognizing the user's emotions and generating appropriate responses.

[0198] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the acquired information and the user's emotional state, and means for transmitting and displaying the generated answers on the user terminal. This makes it possible to provide quick, emotionally sensitive, and appropriate answers to user questions.

[0199] "Data source" refers to the systems and databases where various types of internal company data are stored.

[0200] An "integrated database" refers to a database system that centrally manages and stores collected data.

[0201] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[0202] A "search query" refers to the search conditions generated to retrieve specific information from a database.

[0203] "Generative artificial intelligence" refers to an AI system that generates responses in natural language, similar to human language, based on received data and analysis results.

[0204] An "emotion engine" refers to a technology that analyzes and identifies a user's emotional state based on the questions they enter.

[0205] A "user terminal" refers to a device (such as a personal computer or smartphone) that a user uses to access and operate a system.

[0206] "Metadata" refers to data that provides information about other data, and is supplementary information that facilitates the organization and retrieval of data.

[0207] This invention relates to a system that periodically collects data from multiple internal data sources, stores it in an integrated database, and provides answers based on user input using generative artificial intelligence and an emotion engine. Specific embodiments of the invention are described below.

[0208] Data collection and integration

[0209] The server periodically runs automated scripts to collect the latest data from various internal data sources. These data sources include a manual management system, a legal review history database, and a system for managing the achievements of each department. The server retrieves data by sending API requests to these data sources and executing database queries. The collected data is then converted into a unified format such as JSON, and metadata (e.g., acquisition date and time, data source, category) is added before it is stored in an integrated database. This allows the collected data to be efficiently used in subsequent search processes.

[0210] User inquiries

[0211] When a user wants to obtain information, they enter their question in natural language through the terminal's chat interface. This terminal is provided as a web browser or a dedicated application. For example, if a user types "Tell me the latest legal review history," the terminal sends the question to the server in real time.

[0212] Question analysis and query generation

[0213] The server analyzes the received question using natural language processing (NLP) techniques to extract necessary keywords and context. Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history," and a search query is generated. For example, a search query like "latest AND legal AND verification history" is generated.

[0214] Database search and information retrieval

[0215] Using the generated search query, the server searches the integrated database and retrieves relevant information. This information serves as the foundational data for constructing answers to the user's questions.

[0216] Emotional analysis and response generation

[0217] Based on the acquired information, the server uses an emotion engine to determine the user's emotional state (e.g., anger, joy, confusion) from the question entered by the user. Next, the results of the emotion engine's analysis and the acquired information are passed to a generative artificial intelligence system to generate an answer with a tone and content appropriate to the user's emotional state. If the user is in a hurry, a quick and concise answer will be generated.

[0218] Providing the answer

[0219] The generated answers are sent from the server to the user's terminal and displayed in the terminal's chat window. Users can instantly receive specific and appropriate answers to the questions they enter.

[0220] Examples of prompt statements

[0221] "Please tell me about your recent legal review history."

[0222] "Please tell me which parts of the latest manual have been updated."

[0223] "Please tell me about the sales department's achievements."

[0224] This system enables the provision of prompt, emotionally sensitive, and appropriate answers to user questions, improving user satisfaction and work efficiency.

[0225] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0226] Step 1: Data Collection

[0227] server:

[0228] The system runs automated scripts periodically to collect the latest data from internal data sources.

[0229] For example, it can send API requests to retrieve the latest manual information from the manual management system. It can also execute database queries to retrieve legal review history.

[0230] Input: API endpoint URL, database connection information

[0231] Data processing: Retrieve API responses and database response data.

[0232] Output: Collected raw data

[0233] Step 2: Data Integration and Format Conversion

[0234] server:

[0235] The collected raw data is converted into a standardized format (e.g., JSON format).

[0236] Metadata is added to the collected data. For example, the date and time the data was acquired, the data source, and the category are added.

[0237] Input: Collected raw data

[0238] Data processing: Format conversion of raw data, addition of metadata.

[0239] Output: Data converted to JSON format

[0240] Step 3: Storing data in an integrated database

[0241] server:

[0242] A database write operation is performed to store the converted data in the integrated database.

[0243] For example, the converted data is saved to the database using an INSERT statement.

[0244] Input: Data converted to JSON format

[0245] Data processing: Writing operations to the database

[0246] Output: Data stored in the database

[0247] Step 4: User inquiries

[0248] User:

[0249] To obtain information, enter your question in natural language through the device's chat interface.

[0250] For example, you could type, "Please provide the latest legal review history."

[0251] Input: Question (natural language text)

[0252] Data processing: None

[0253] Output: The question displayed on the terminal.

[0254] Terminal:

[0255] The questions entered by the user are sent to the server in real time.

[0256] Input: User's question

[0257] Data processing: Sending the question

[0258] Output: Question text sent to the server

[0259] Step 5: Analyze the question and generate search queries

[0260] server:

[0261] The received questions are analyzed using natural language processing (NLP) techniques to extract important keywords and context.

[0262] Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history."

[0263] A search query is generated based on the extracted keywords.

[0264] Input: User's question

[0265] Data processing: Natural language processing, keyword extraction, search query generation.

[0266] Output: Search query

[0267] Step 6: Search the integrated database

[0268] server:

[0269] The generated search query is used to search the integrated database and retrieve relevant information.

[0270] Execute a SELECT statement against the database and retrieve the corresponding records.

[0271] Input: Search query

[0272] Data processing: Executing queries and retrieving results

[0273] Output: Acquired information

[0274] Step 7: Emotional Analysis and Solution Generation

[0275] server:

[0276] Based on the acquired information, an emotion engine is used to determine the user's emotional state from the question text they entered.

[0277] The analysis results from the emotion engine and the acquired information are passed to a generative artificial intelligence system to generate an appropriate answer.

[0278] For example, if it is determined that the user is in a hurry, generate a quick and concise answer.

[0279] Input: Obtained information, user's question sentence

[0280] Data processing: Sentiment analysis, answer generation

[0281] Output: Generated answer

[0282] Step 8: Providing an answer

[0283] Server:

[0284] Send the generated answer to the user terminal.

[0285] Input: Generated answer

[0286] Data processing: Sending the answer

[0287] Output: Answer sent to the user terminal

[0288] Terminal:

[0289] Display the received answer on the chat window. [[ID=A]]

[0290] For example, it is displayed as "The latest legal confirmation history is as follows".

[0291] Input: Answer sent from the server

[0292] Data processing: Displaying the answer

[0293] Output: Answer displayed on the chat window

[0294] (Application Example 2)

[0295] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0296] Conventional database management systems have made it difficult for users to quickly and accurately retrieve necessary information from vast amounts of internal company data. Furthermore, because they do not take into account the user's emotions or circumstances, their effectiveness in improving user satisfaction and convenience is limited. This invention aims to solve these problems and improve user satisfaction by enabling users to quickly and appropriately retrieve information and providing personalized responses that correspond to their emotional state.

[0297] The specific processing performed by the specific 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 periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for analyzing the emotional state of the question entered by the user using an emotion engine, means for generating answers using generative artificial intelligence based on the acquired information and the analysis results from the emotion engine, and means for sending and displaying the generated answers on the user terminal. This makes it possible to provide quick and appropriate answers that take into account the user's emotional state when a user asks a question in chat format through a terminal.

[0298] "Various internal data sources" refers to the sources of various data managed within a company, including, for example, manual management systems, legal verification history databases, and departmental performance management systems.

[0299] "Means of collecting data periodically" refers to a mechanism for automatically collecting data at regular time intervals, and in practice, this often involves using API requests or database queries.

[0300] "Means of converting data into an appropriate format and storing it in an integrated database" refers to a mechanism that converts collected data into a unified format (e.g., JSON format), adds metadata (source, date, category, etc.), and then stores it in an integrated database.

[0301] "A means for users to input questions in a chat format via a device" refers to an interface that allows users to input questions in natural language using any device (e.g., smartphone, PC).

[0302] "A means of analyzing received questions using natural language processing and generating search queries" refers to a mechanism that analyzes user-inputted questions using natural language processing techniques such as morphological analysis, extracts important keywords and context, and generates search queries.

[0303] "Means of obtaining relevant information from an integrated database" refers to a mechanism that searches for and retrieves the relevant data from an integrated database based on the generated search query.

[0304] An "emotion engine" refers to a system that analyzes the user's inputted questions and determines their emotional state (e.g., anger, joy, confusion, etc.).

[0305] "Generative artificial intelligence" refers to artificial intelligence technology that generates the most optimal answer for the user based on acquired information and analysis results from an emotion engine.

[0306] "Means of sending and displaying answers on the user's terminal" refers to a mechanism that sends the generated answers to the user's terminal and displays them on an interface such as a chat window.

[0307] This invention relates to a system that generates personalized answers, including sentiment analysis, to questions entered by users through a terminal. This system collects data from internal data sources, stores it in an integrated database, analyzes user questions using natural language processing and sentiment analysis, and provides answers using generative artificial intelligence.

[0308] Overall System Structure

[0309] This system consists of the following main components:

[0310] 1. Server:

[0311] Regularly collect data from various internal data sources, convert it into an appropriate format, and store it in an integrated database.

[0312] Receive questions from users, analyze them using natural language processing (NLP) technology, and generate search queries.

[0313] Retrieve relevant information from the integrated database and analyze the user's emotional state with an emotion engine.

[0314] Use generative artificial intelligence to generate answers based on the retrieved information and the results of the emotion analysis, and send them to the user terminal.

[0315] 2. User Terminal:

[0316] Provide an interface for users to enter questions in a chat format. This operates on devices such as smartphones, PCs, and head-mounted displays (HMDs).

[0317] Display the received answers on the chat window.

[0318] Hardware and Software Used

[0319] 1. Server:

[0320] Data Collection: Data is collected periodically from various internal data sources (e.g., manual management system, legal review history) using automated scripts. The software used includes API request libraries (e.g., Python's requests) and database query libraries (e.g., SQLAlchemy).

[0321] Data conversion and storage: Convert data into a unified format such as JSON, add metadata, and store it in an integrated database (e.g., MySQL®, PostgreSQL).

[0322] Natural Language Processing (NLP): Analyzes user questions and generates search queries. The software used is an NLP library (e.g., spaCy, NLTK).

[0323] Sentiment Analysis: Analyzes the emotional state of the question using an emotion engine. This utilizes an emotion analysis API (e.g., IBM Watson®, AWS® Comprehend).

[0324] Generative artificial intelligence: Generates answers based on acquired information and sentiment analysis results. The software used is a generative artificial intelligence library (e.g., OpenAI® GPT-3).

[0325] 2. User terminal:

[0326] This includes smartphones, PCs, and head-mounted displays (HMDs). Users input natural language questions through these devices and receive answers from the server in real time.

[0327] Specific example

[0328] The user puts on an HMD (Head-Mounted Display) and accesses a virtual store. They input a question to the virtual assistant via voice or text, such as "Please tell me about the warranty for this product." After receiving the question, the server analyzes it using NLP (Neuro-Linguistic Programming) technology and retrieves relevant information from an integrated database. Next, an emotion engine analyzes the user's emotional state, and generative artificial intelligence (AI) generates an appropriate response. The tone and content of the response change according to the emotional state, and the result is sent to the user's terminal and displayed on the terminal.

[0329] Example of a prompt

[0330] As a concrete example of its use, here is an example of a prompt in response to a question asked by the user:

[0331] User's question: "Please tell me about the warranty for this product."

[0332] Sentiment analysis result: "In a hurry"

[0333] Generate the answer:

[0334] The warranty details are as follows:

[0335] Thus, the present invention aims to improve the user experience by taking into account the user's emotional state and providing quick and appropriate answers.

[0336] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0337] Step 1:

[0338] The server periodically collects data from various internal data sources. Specifically, it uses automated scripts to execute API requests and database queries to retrieve the latest data. The input is data from the data sources, and the output is the collected raw data.

[0339] Step 2:

[0340] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (source, date, category, etc.). The input is the collected raw data, and the output is data in a unified format.

[0341] Step 3:

[0342] Users enter questions in a chat format via their devices. Specifically, users input questions using natural language via smartphones or PCs. The input is the user's question text, and the output is the transmission of the question from the device to the server.

[0343] Step 4:

[0344] The terminal sends the received question to the server. The question is sent to the server in real time and is ready for analysis. The input is the user's question, and the output is the question sent to the server.

[0345] Step 5:

[0346] The server analyzes the received question using natural language processing (NLP) and generates a search query. Specifically, it performs morphological analysis to extract important keywords and context. The input is the user's question, and the output is the generated search query.

[0347] Step 6:

[0348] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues a query to the database and searches for the corresponding record. The input is the search query, and the output is the retrieved information.

[0349] Step 7:

[0350] The server inputs the acquired information into the emotion engine and analyzes the emotional state of the user's question. Specifically, it evaluates the emotion based on the tone and specific wording of the question. The input is the user's question and acquired information, and the output is the emotion analysis result.

[0351] Step 8:

[0352] The server generates answers using generative artificial intelligence based on the acquired information and the results of the emotion engine's analysis. Specifically, it uses a generative AI library to create answers with a tone and content appropriate to the emotional state. The input is the acquired information and the emotion analysis results, and the output is the generated answer.

[0353] Step 9:

[0354] The server sends the generated answer to the user's terminal, which then displays it in the chat window. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[0355] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0356] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0357] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0358] [Second Embodiment]

[0359] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0360] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0361] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0362] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0363] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0364] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0365] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0366] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0367] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0368] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0369] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0370] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0371] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user inquiries using generative artificial intelligence. A specific embodiment of this system, including the program's processing, is described in detail below.

[0372] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[0373] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[0374] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[0375] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest legal review history," the NLP engine extracts keywords such as "latest," "legal," and "review history," and uses them to construct a search query.

[0376] Next, the server uses the generated search query to search the integrated database and retrieve relevant information. At this point, the server issues a query to the database and retrieves the corresponding records. The retrieved information is not used directly, but is instead input into the generative artificial intelligence.

[0377] The server inputs the acquired information into a generative artificial intelligence (AI) system, which generates answers to the user's questions in a natural way. The generative AI system creates the optimal answer based on the acquired data and generates it as a sentence in natural language. For example, it might generate a specific answer such as, "The latest legal review history is as follows..."

[0378] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. The user can instantly see the answer to the question they entered. This entire process allows the user to easily and quickly obtain the information they need.

[0379] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. This process allows users to obtain the necessary information without any effort, and significantly reduces redundant work and waste within the company.

[0380] The following describes the processing flow.

[0381] Step 1:

[0382] The server collects the latest data from each data source. This is done by running automated scripts on a regular schedule. For example, it might send API requests to retrieve internal manuals, execute database queries to extract legal review history, and download performance data.

[0383] Step 2:

[0384] The server converts the collected data into an appropriate format and stores it in an integrated database. First, the collected data is converted to a format such as JSON, and metadata such as "source," "date," and "category" is added to the data. Then, the converted data is saved to the integrated database.

[0385] Step 3:

[0386] The user enters their question through the device's chat interface. The user enters their question in natural language, such as "Please tell me the latest legal review history" in the chat window.

[0387] Step 4:

[0388] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[0389] Step 5:

[0390] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[0391] Step 6:

[0392] The server generates a search query based on the extracted keywords. For example, a query like "latest AND legal AND verification history" is generated.

[0393] Step 7:

[0394] The server searches the integrated database using the generated search query. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[0395] Step 8:

[0396] The server inputs the acquired information into a generative artificial intelligence (AI) system to generate answers to the user's questions. The AI ​​system creates natural-sounding responses based on the acquired data. For example, it might generate an answer such as, "The latest legal review history is as follows..."

[0397] Step 9:

[0398] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal and displayed on the chat interface.

[0399] Step 10:

[0400] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific response to the question.

[0401] The above outlines the specific processing steps of the program. This allows users to quickly and easily obtain the necessary information through the system.

[0402] (Example 1)

[0403] Next, we will describe Example 1. 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".

[0404] Conventional data collection systems have struggled to centrally manage data from different formats and sources, making it difficult to quickly and accurately obtain necessary information. Furthermore, few systems could automatically generate appropriate answers to natural language questions, resulting in low user convenience.

[0405] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0406] In this invention, the server includes means for periodically executing automated scripts to collect data from various internal data sources, means for converting the collected data into JSON format or the like, adding metadata, and storing it in an integrated database, and means for analyzing received questions using natural language processing, extracting important keywords, and generating search queries. This makes it possible to generate and provide accurate and rapid answers using generative artificial intelligence to questions entered by users in natural language.

[0407] A "data source" refers to the system or database from which information is collected.

[0408] An "automatic script" refers to a program that is executed automatically at regular time intervals.

[0409] A "server" refers to a computer system that collects, transforms, and analyzes data.

[0410] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a text format for structuring and representing data.

[0411] "Metadata" refers to information related to data (such as source, date, category, etc.).

[0412] An "integrated database" refers to a database that centrally manages data collected from multiple data sources.

[0413] A "user" refers to anyone who wants to use the system to obtain information.

[0414] A "terminal" refers to a device (such as a PC or smartphone) that a user uses to access a system.

[0415] A "chat interface" refers to an interactive input method that allows users to enter questions using natural language.

[0416] "Natural language processing" refers to the technology of analyzing and understanding human language using computers.

[0417] A "search query" refers to a search command used to retrieve specific information from a database.

[0418] "Generative artificial intelligence" refers to artificial intelligence technology that generates natural-sounding sentences and responses based on data.

[0419] "Answer" refers to the response provided by a generative artificial intelligence system to a user's question.

[0420] This invention relates to a system that collects data from various data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. An embodiment of this system will be described in detail.

[0421] First, the server collects data using Python and SQL. It retrieves the necessary information from data sources using API requests (e.g., requests.get('https: / / internal-api.example.com / manuals')) and extracts information from databases by executing SQL queries (e.g., SELECT FROM legal_records WHERE update_date > CURDATE() - INTERVAL 1 DAY;). This allows data to be collected from systems such as the manual management system, the legal confirmation history database, and the system that manages the achievements of each department.

[0422] Next, the server converts the collected data into JSON format (using json.dumps) and adds metadata. This standardization of formatting makes subsequent searching and analysis easier. The converted data is then stored in the unified database using SQL (e.g., INSERT INTO unified_db (data, source, date) VALUES (...);).

[0423] If a user wants to obtain information, they enter their question through the chat interface on their device. The chat interface is provided via a web browser or a dedicated application. For example, the user might enter a question in text format, such as "Tell me about my recent legal review history." The device then sends the question to the server (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})).

[0424] The server analyzes the received question using natural language processing (NLP) techniques. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the question and extract important keywords. For example, from the question "Please tell me my recent legal review history," it extracts the keywords "recent," "legal," and "review history." Then, it generates a search query based on these keywords.

[0425] Using the generated search query, the server retrieves relevant information from the integrated database. In this process, the server issues SQL queries (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The retrieved information is then directly input into the generative artificial intelligence.

[0426] Next, the server uses generative artificial intelligence (e.g., GPT-3) to generate answers to the user's questions based on the information it has acquired. The generative AI generates natural-sounding sentences based on the input data, creating specific answers such as, "The recent legal review history is as follows..."

[0427] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. This allows the user to instantly obtain the answer to the question they entered.

[0428] As an example of a prompt, the user might type, "Tell me about my recent legal review history." This prompts the server to search the legal review history data already collected during the data collection phase, and a generative artificial intelligence system generates a specific answer based on that data. The answer is then displayed on the user's terminal, providing the information instantly. This entire process allows the user to quickly obtain the necessary information without any hassle.

[0429] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0430] Step 1:

[0431] The server periodically runs automated scripts to collect data from various internal data sources. Specifically, it uses Python's requests library and SQL SELECT statements to retrieve data from API requests and extract information from the database. The server accesses API endpoints (e.g., requests.get('https: / / internal-api.example.com / manuals')) and temporarily stores the retrieved data. The input is API endpoints and database queries, and the output is the temporarily stored data.

[0432] Step 2:

[0433] The server converts the collected data into JSON format, adds metadata, and stores it in the unified database. Specifically, it uses the `json.dumps` method to convert the data into JSON format and then uses SQL to store it in the unified database. The input is the temporarily stored data, and the output is the JSON data stored in the unified database. The server executes SQL statements such as `INSERT INTO unified_db (data, source, date) VALUES (...);`.

[0434] Step 3:

[0435] The user enters their question through the terminal's chat interface. The terminal sends the text entered by the user (e.g., "Tell me about my recent legal review history") to the server. Specifically, the terminal sends the user's text input to the server as a POST request in JSON format (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})). The input is the user's question, and the output is the question data sent to the server.

[0436] Step 4:

[0437] The server analyzes received questions using natural language processing (NLP) techniques and generates search queries. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the questions and extract important keywords. For example, from the question "Please tell me about recent legal review history," it extracts the keywords "recent," "legal," and "review history." The input is the received question data, and the output is the search query.

[0438] Step 5:

[0439] The server uses the generated search query to search the unified database and retrieve relevant information. Specifically, it issues an SQL query (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The input is the search query, and the output is the retrieved database records.

[0440] Step 6:

[0441] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates answers to the user's questions in a natural-sounding format. Specifically, data is input into a generative AI model (e.g., GPT-3), and the AI ​​generates answers in natural language. For example, a specific answer such as "The latest legal review history is as follows..." might be generated. The input is the acquired database records, and the output is the generated answer.

[0442] Step 7:

[0443] The server sends the generated response to the user's terminal, and the terminal displays the response in the chat interface. Specifically, the server sends the generated response to the user's terminal as a POST request (e.g., requests.post('https: / / client-api.example.com / response', data={'response': 'The latest legal review history is as follows...'})), and the user's terminal displays the received response in the chat box. The input is the generated response, and the output is the response displayed in the chat interface.

[0444] (Application Example 1)

[0445] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0446] Conventional factory management systems suffer from a fragmented data collection system, lacking effective means to integrate necessary information. Furthermore, they lack automated response functions to allow workers to instantly obtain required information, necessitating manual responses even in situations requiring rapid action. This results in low factory efficiency and a tendency towards information duplication and waste.

[0447] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0448] In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format via a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the obtained information, means for forming detailed answers to the user's questions using a generative AI model, means for sending and displaying the generated answers on the user's terminal, and means for automatically collecting data from various sensors and systems within the factory and storing it in an integrated database. This enables workers to quickly and accurately obtain the latest information within the factory, significantly improving the operational efficiency of the factory.

[0449] "Various internal data sources" refers to data provided by multiple departments and business systems.

[0450] "Means of collecting data periodically" refers to a system that has the function of automatically collecting data at set time intervals.

[0451] "Means of converting to an appropriate format and storing in an integrated database" refers to the process of converting collected data into a unified format and saving it in an integrated database.

[0452] "A means for users to input questions in a chat format via their device" refers to an interface that allows users to input text from their device and interact with the system.

[0453] "A means of analyzing received questions using natural language processing and generating search queries" refers to a technology that analyzes input text and converts it into a query suitable for searching.

[0454] "A means of retrieving relevant information from an integrated database based on a generated search query" refers to the process of using a search query to search the database and extract the necessary information.

[0455] "A means of generating an answer using generative artificial intelligence based on acquired information" refers to a function that inputs data into an AI model and generates an answer in natural language.

[0456] "Means for forming detailed answers to user questions using a generative AI model" refers to the technology of creating detailed and specific answers using generative AI technology.

[0457] "Means of sending and displaying the generated answer on the user's terminal" refers to a mechanism for transferring the response generated by the AI ​​to the user's device and displaying it.

[0458] "Methods for automatically collecting data from various sensors and systems within a factory and storing it in an integrated database" refers to the process of automatically collecting and integrating data from sensors and systems within a factory and saving it to a database.

[0459] This invention specifically describes a factory management system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. The specific processes for implementing this invention are described below.

[0460] The server first runs automated scripts periodically to collect the latest data from various sensors and systems within the factory. These data sources include manufacturing line sensors, inventory management systems, and quality control systems. The server retrieves the necessary data using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database.

[0461] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format, making subsequent retrieval easier.

[0462] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[0463] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and uses them to construct a search query.

[0464] Next, the server searches the integrated database using the generated search query and retrieves relevant information. The retrieved information is not used directly, but is instead input into a generative artificial intelligence (AI). The server inputs the retrieved information into the generative AI, which generates answers to the user's questions in a natural way. The generative AI creates the optimal answer based on the retrieved data and generates it as a sentence in natural language. For example, a specific answer such as "The latest inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units" is generated.

[0465] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. Users can instantly see the answer to the question they entered. This entire process allows users to easily and quickly obtain the information they need, significantly improving operational efficiency within the factory.

[0466] As a concrete example, when a user enters the question, "Please tell me the latest inventory status," the server first searches for inventory data already acquired during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. Examples of such prompts include the following:

[0467] "Please tell me the latest stock status."

[0468] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0469] Step 1:

[0470] Data collection:

[0471] The server periodically executes automated scripts to collect the latest data from various sensors and systems within the factory. Specifically, it retrieves information from manufacturing line sensors, inventory management systems, quality control systems, etc., using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database. The input for this step is data from sensors and systems within the factory, and the output is a series of data containing various information.

[0472] Step 2:

[0473] Data transformation and integration:

[0474] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format. The input for this step is various types of data, and the output is the data in the integrated database.

[0475] Step 3:

[0476] User question input:

[0477] Users use a chat interface via their device to input questions in natural language. This interface is provided as a web browser or a dedicated application. The questions entered by users are intended to obtain specific information. For example, a user might enter, "Please tell me the latest stock status." The input in this step is the user's question, and the output is that the question is sent to the server.

[0478] Step 4:

[0479] Question analysis using natural language processing (NLP):

[0480] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. Specifically, the NLP engine performs morphological analysis on the question sentence and extracts important keywords and context. For example, in the case of "Please tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and constructs a search query based on these. The input for this step is the user's question, and the output is the generated search query.

[0481] Step 5:

[0482] Integrated database search:

[0483] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues an appropriate query to the database and retrieves the corresponding records. For example, a query might be issued to search for "latest inventory data". The input to this step is the generated search query, and the output is the retrieved relevant information.

[0484] Step 6:

[0485] Solution generation using generative AI models:

[0486] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates natural-sounding answers to the user's questions. The generative AI model creates the optimal response based on the acquired data and generates it as a natural language sentence. For example, it might generate a specific answer such as, "The current inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units." The input for this step is the acquired relevant information, and the output is the generated response sentence.

[0487] Step 7:

[0488] Submitting and displaying answers:

[0489] The server sends the generated answer to the user's terminal, which displays the answer on the chat interface. The user can immediately see the answer to the question they entered. In this step, the input is the generated answer text, and the output is the answer displayed on the user's terminal.

[0490] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0491] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence and an emotion engine. A specific embodiment of this system, including the program's processing, is described in detail below.

[0492] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[0493] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[0494] If a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided via a web browser or a dedicated application. Users enter their questions in natural language, such as "Please tell me the latest legal review history" in the chat window.

[0495] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[0496] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The server performs morphological analysis on the question text and extracts important keywords and context such as "latest," "legal," and "verification history." Next, the server generates a search query based on the extracted keywords, creating a query that is "latest AND legal AND verification history."

[0497] The server uses the generated search query to search the integrated database and retrieve relevant information. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[0498] The server analyzes the acquired information and inputs it into the emotion engine. The emotion engine analyzes the user's input questions and determines their emotional state (e.g., anger, joy, confusion, etc.). For example, it evaluates whether the user is in a hurry or dissatisfied based on the tone and specific wording of the question.

[0499] Next, the server inputs the acquired information and the analysis results from the emotion engine into the generative artificial intelligence to generate an appropriate answer. Based on the identified emotional state, the generative AI creates an answer with a more appropriate tone and content. For example, if the user is confused, a more polite and easy-to-understand answer will be generated.

[0500] The server sends the generated answer to the user's terminal, which then displays the answer in the chat window. The user can instantly see a specific and appropriate answer to the question they entered.

[0501] For example, if a user enters a question such as "Tell me about my recent legal review history," and the sentiment engine detects that the user is in a hurry, it will generate a quick and easy-to-understand answer tailored to the user's needs. This answer will then be displayed in the chat window. This process allows users to easily and quickly obtain the information they need, significantly reducing internal duplication and waste.

[0502] As a result, the system of the present invention can recognize the user's emotions and generate more appropriate responses, thereby improving user satisfaction and work efficiency.

[0503] The following describes the processing flow.

[0504] Step 1:

[0505] The server collects the latest data from each data source. This is done by running automated scripts according to a regular schedule. Specifically, it sends API requests to retrieve internal manuals, executes database queries to extract legal review history, and downloads performance data.

[0506] Step 2:

[0507] The server converts the collected data into an appropriate format and stores it in an integrated database for user convenience. This conversion involves changing the data to a standardized format such as JSON, and adding metadata such as "source," "date," and "category." The converted data is then stored in the integrated database.

[0508] Step 3:

[0509] Users enter questions through the chat interface on their device. Specifically, they use a web browser or a dedicated application to enter questions in the format of, "Please tell me the latest legal review history."

[0510] Step 4:

[0511] The terminal sends the entered question to the server in real time. The chat interface receives user input and immediately sends that data to the server.

[0512] Step 5:

[0513] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[0514] Step 6:

[0515] The server generates a search query based on the extracted keywords. For example, it might create a query like "latest AND legal AND verification history".

[0516] Step 7:

[0517] The server searches the integrated database using the generated search query. It issues the query to the database, searches for relevant records, and retrieves the corresponding data.

[0518] Step 8:

[0519] The server analyzes the acquired information and inputs it into the emotion engine. Specifically, it passes the user's entered question text to the emotion engine and analyzes their emotional state (e.g., anger, joy, confusion, etc.).

[0520] Step 9:

[0521] The server inputs the acquired information and the analysis results from the emotion engine into a generative artificial intelligence (AI) system to generate the optimal answer. The generative AI takes the identified emotion into consideration to create a more appropriate tone and content for the response. For example, if the user is confused, it will generate a more polite and easy-to-understand response.

[0522] Step 10:

[0523] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal in real time and displayed in the chat window.

[0524] Step 11:

[0525] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific and appropriate response to the question they entered.

[0526] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase. If the emotion engine determines that the user is in a hurry, the generative artificial intelligence generates a quick and easy-to-understand answer. This answer is displayed in the chat window, allowing the user to instantly obtain the necessary information. This process makes it possible for users to easily and quickly obtain the information they need, significantly reducing redundant work and waste within the company.

[0527] (Example 2)

[0528] Next, we will describe Example 2. 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".

[0529] Conventional information gathering systems have suffered from inefficiency due to the cumbersome process of collecting and integrating data from various internal data sources. Furthermore, the process of users inputting questions and obtaining information has not taken into account the emotional state of the user, resulting in unsatisfactory responses and a diminished user experience. This invention aims to improve convenience and satisfaction by recognizing the user's emotions and generating appropriate responses.

[0530] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the acquired information and the user's emotional state, and means for transmitting and displaying the generated answers on the user terminal. This makes it possible to provide quick, emotionally sensitive, and appropriate answers to user questions.

[0531] "Data source" refers to the systems and databases where various types of internal company data are stored.

[0532] An "integrated database" refers to a database system that centrally manages and stores collected data.

[0533] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[0534] A "search query" refers to the search conditions generated to retrieve specific information from a database.

[0535] "Generative artificial intelligence" refers to an AI system that generates responses in natural language, similar to human language, based on received data and analysis results.

[0536] An "emotion engine" refers to a technology that analyzes and identifies a user's emotional state based on the questions they enter.

[0537] A "user terminal" refers to a device (such as a personal computer or smartphone) that a user uses to access and operate a system.

[0538] "Metadata" refers to data that provides information about other data, and is supplementary information that facilitates the organization and retrieval of data.

[0539] This invention relates to a system that periodically collects data from multiple internal data sources, stores it in an integrated database, and provides answers based on user input using generative artificial intelligence and an emotion engine. Specific embodiments of the invention are described below.

[0540] Data collection and integration

[0541] The server periodically runs automated scripts to collect the latest data from various internal data sources. These data sources include a manual management system, a legal review history database, and a system for managing the achievements of each department. The server retrieves data by sending API requests to these data sources and executing database queries. The collected data is then converted into a unified format such as JSON, and metadata (e.g., acquisition date and time, data source, category) is added before it is stored in an integrated database. This allows the collected data to be efficiently used in subsequent search processes.

[0542] User inquiries

[0543] When a user wants to obtain information, they enter their question in natural language through the terminal's chat interface. This terminal is provided as a web browser or a dedicated application. For example, if a user types "Tell me the latest legal review history," the terminal sends the question to the server in real time.

[0544] Question analysis and query generation

[0545] The server analyzes the received question using natural language processing (NLP) techniques to extract necessary keywords and context. Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history," and a search query is generated. For example, a search query like "latest AND legal AND verification history" is generated.

[0546] Database search and information retrieval

[0547] Using the generated search query, the server searches the integrated database and retrieves relevant information. This information serves as the foundational data for constructing answers to the user's questions.

[0548] Emotional analysis and response generation

[0549] Based on the acquired information, the server uses an emotion engine to determine the user's emotional state (e.g., anger, joy, confusion) from the question entered by the user. Next, the results of the emotion engine's analysis and the acquired information are passed to a generative artificial intelligence system to generate an answer with a tone and content appropriate to the user's emotional state. If the user is in a hurry, a quick and concise answer will be generated.

[0550] Providing the answer

[0551] The generated answers are sent from the server to the user's terminal and displayed in the terminal's chat window. Users can instantly receive specific and appropriate answers to the questions they enter.

[0552] Examples of prompt statements

[0553] "Please tell me about your recent legal review history."

[0554] "Please tell me which parts of the latest manual have been updated."

[0555] "Please tell me about the sales department's achievements."

[0556] This system enables the provision of prompt, emotionally sensitive, and appropriate answers to user questions, improving user satisfaction and work efficiency.

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1: Data Collection

[0559] server:

[0560] The system runs automated scripts periodically to collect the latest data from internal data sources.

[0561] For example, it can send API requests to retrieve the latest manual information from the manual management system. It can also execute database queries to retrieve legal review history.

[0562] Input: API endpoint URL, database connection information

[0563] Data processing: Retrieve API responses and database response data.

[0564] Output: Collected raw data

[0565] Step 2: Data Integration and Format Conversion

[0566] server:

[0567] The collected raw data is converted into a standardized format (e.g., JSON format).

[0568] Metadata is added to the collected data. For example, the date and time the data was acquired, the data source, and the category are added.

[0569] Input: Collected raw data

[0570] Data processing: Format conversion of raw data, addition of metadata.

[0571] Output: Data converted to JSON format

[0572] Step 3: Storing data in an integrated database

[0573] server:

[0574] A database write operation is performed to store the converted data in the integrated database.

[0575] For example, the converted data is saved to the database using an INSERT statement.

[0576] Input: Data converted to JSON format

[0577] Data processing: Writing operations to the database

[0578] Output: Data stored in the database

[0579] Step 4: User inquiries

[0580] User:

[0581] To obtain information, enter your question in natural language through the device's chat interface.

[0582] For example, you could type, "Please provide the latest legal review history."

[0583] Input: Question (natural language text)

[0584] Data processing: None

[0585] Output: The question displayed on the terminal.

[0586] Terminal:

[0587] The questions entered by the user are sent to the server in real time.

[0588] Input: User's question

[0589] Data processing: Sending the question

[0590] Output: Question text sent to the server

[0591] Step 5: Analyze the question and generate search queries

[0592] server:

[0593] The received questions are analyzed using natural language processing (NLP) techniques to extract important keywords and context.

[0594] Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history."

[0595] A search query is generated based on the extracted keywords.

[0596] Input: User's question

[0597] Data processing: Natural language processing, keyword extraction, search query generation.

[0598] Output: Search query

[0599] Step 6: Search the integrated database

[0600] server:

[0601] The generated search query is used to search the integrated database and retrieve relevant information.

[0602] Execute a SELECT statement against the database and retrieve the corresponding records.

[0603] Input: Search query

[0604] Data processing: Executing queries and retrieving results

[0605] Output: Acquired information

[0606] Step 7: Emotional Analysis and Solution Generation

[0607] server:

[0608] Based on the acquired information, an emotion engine is used to determine the user's emotional state from the question text they entered.

[0609] The analysis results from the emotion engine and the acquired information are passed to a generative artificial intelligence system to generate an appropriate answer.

[0610] For example, if it's determined that the user is in a hurry, it will generate a quick and concise response.

[0611] Input: Information obtained, user's question

[0612] Data processing: Sentiment analysis, answer generation

[0613] Output: Generated solution

[0614] Step 8: Providing the answer

[0615] server:

[0616] The generated answer is sent to the user's terminal.

[0617] Input: Generated answer

[0618] Data processing: Submitting the answer

[0619] Output: Answer sent to the user's terminal

[0620] Terminal:

[0621] The received answers will be displayed in the chat window.

[0622] For example, it might display, "The latest legal review history is as follows."

[0623] Input: Answer sent from the server

[0624] Data processing: Displaying the answer

[0625] Output: Answer displayed in the chat window

[0626] (Application Example 2)

[0627] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0628] Conventional database management systems have made it difficult for users to quickly and accurately retrieve necessary information from vast amounts of internal company data. Furthermore, because they do not take into account the user's emotions or circumstances, their effectiveness in improving user satisfaction and convenience is limited. This invention aims to solve these problems and improve user satisfaction by enabling users to quickly and appropriately retrieve information and providing personalized responses that correspond to their emotional state.

[0629] The specific processing performed by the specific 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 periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for analyzing the emotional state of the question entered by the user using an emotion engine, means for generating answers using generative artificial intelligence based on the acquired information and the analysis results from the emotion engine, and means for sending and displaying the generated answers on the user terminal. This makes it possible to provide quick and appropriate answers that take into account the user's emotional state when a user asks a question in chat format through a terminal.

[0630] "Various internal data sources" refers to the sources of various data managed within a company, including, for example, manual management systems, legal verification history databases, and departmental performance management systems.

[0631] "Means of collecting data periodically" refers to a mechanism for automatically collecting data at regular time intervals, and in practice, this often involves using API requests or database queries.

[0632] "Means of converting data into an appropriate format and storing it in an integrated database" refers to a mechanism that converts collected data into a unified format (e.g., JSON format), adds metadata (source, date, category, etc.), and then stores it in an integrated database.

[0633] "A means for users to input questions in a chat format via a device" refers to an interface that allows users to input questions in natural language using any device (e.g., smartphone, PC).

[0634] "A means of analyzing received questions using natural language processing and generating search queries" refers to a mechanism that analyzes user-inputted questions using natural language processing techniques such as morphological analysis, extracts important keywords and context, and generates search queries.

[0635] "Means of obtaining relevant information from an integrated database" refers to a mechanism that searches for and retrieves the relevant data from an integrated database based on the generated search query.

[0636] An "emotion engine" refers to a system that analyzes the user's inputted questions and determines their emotional state (e.g., anger, joy, confusion, etc.).

[0637] "Generative artificial intelligence" refers to artificial intelligence technology that generates the most optimal answer for the user based on acquired information and analysis results from an emotion engine.

[0638] "Means of sending and displaying answers on the user's terminal" refers to a mechanism that sends the generated answers to the user's terminal and displays them on an interface such as a chat window.

[0639] This invention relates to a system that generates personalized answers, including sentiment analysis, to questions entered by users through a terminal. This system collects data from internal data sources, stores it in an integrated database, analyzes user questions using natural language processing and sentiment analysis, and provides answers using generative artificial intelligence.

[0640] Overall system configuration

[0641] This system consists of the following main components:

[0642] 1. Server:

[0643] We regularly collect data from various internal data sources, convert it to an appropriate format, and store it in an integrated database.

[0644] The system receives questions from users, analyzes them using natural language processing (NLP) techniques, and generates search queries.

[0645] Relevant information is retrieved from the integrated database, and the emotion engine analyzes the user's emotional state.

[0646] Using generative artificial intelligence, the system generates an answer based on acquired information and sentiment analysis results, and sends it to the user's terminal.

[0647] 2. User terminal:

[0648] It provides an interface where users can input questions in a chat format. This works on smartphones, PCs, and head-mounted displays (HMDs).

[0649] The received answers will be displayed in the chat window.

[0650] Hardware and software to be used

[0651] 1. Server:

[0652] Data Collection: Data is collected periodically from various internal data sources (e.g., manual management system, legal review history) using automated scripts. The software used includes API request libraries (e.g., Python's requests) and database query libraries (e.g., SQLAlchemy).

[0653] Data conversion and storage: Convert data into a unified format such as JSON, add metadata, and store it in an integrated database (e.g., MySQL, PostgreSQL).

[0654] Natural Language Processing (NLP): Analyzes user questions and generates search queries. The software used is an NLP library (e.g., spaCy, NLTK).

[0655] Sentiment Analysis: Analyzes the emotional state of the question using an emotion engine. Sentiment analysis APIs (e.g., IBM Watson, AWS Comprehend) are used.

[0656] Generative artificial intelligence: Generates answers based on acquired information and sentiment analysis results. The software used is a generative artificial intelligence library (e.g., OpenAI GPT-3).

[0657] 2. User terminal:

[0658] This includes smartphones, PCs, and head-mounted displays (HMDs). Users input natural language questions through these devices and receive answers from the server in real time.

[0659] Specific example

[0660] The user puts on an HMD (Head-Mounted Display) and accesses a virtual store. They input a question to the virtual assistant via voice or text, such as "Please tell me about the warranty for this product." After receiving the question, the server analyzes it using NLP (Neuro-Linguistic Programming) technology and retrieves relevant information from an integrated database. Next, an emotion engine analyzes the user's emotional state, and generative artificial intelligence (AI) generates an appropriate response. The tone and content of the response change according to the emotional state, and the result is sent to the user's terminal and displayed on the terminal.

[0661] Example of a prompt

[0662] As a concrete example of its use, here is an example of a prompt in response to a question asked by the user:

[0663] User's question: "Please tell me about the warranty for this product."

[0664] Sentiment analysis result: "In a hurry"

[0665] Generate the answer:

[0666] The warranty details are as follows:

[0667] Thus, the present invention aims to improve the user experience by taking into account the user's emotional state and providing quick and appropriate answers.

[0668] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0669] Step 1:

[0670] The server periodically collects data from various internal data sources. Specifically, it uses automated scripts to execute API requests and database queries to retrieve the latest data. The input is data from the data sources, and the output is the collected raw data.

[0671] Step 2:

[0672] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (source, date, category, etc.). The input is the collected raw data, and the output is data in a unified format.

[0673] Step 3:

[0674] Users enter questions in a chat format via their devices. Specifically, users input questions using natural language via smartphones or PCs. The input is the user's question text, and the output is the transmission of the question from the device to the server.

[0675] Step 4:

[0676] The terminal sends the received question to the server. The question is sent to the server in real time and is ready for analysis. The input is the user's question, and the output is the question sent to the server.

[0677] Step 5:

[0678] The server analyzes the received question using natural language processing (NLP) and generates a search query. Specifically, it performs morphological analysis to extract important keywords and context. The input is the user's question, and the output is the generated search query.

[0679] Step 6:

[0680] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues a query to the database and searches for the corresponding record. The input is the search query, and the output is the retrieved information.

[0681] Step 7:

[0682] The server inputs the acquired information into the emotion engine and analyzes the emotional state of the user's question. Specifically, it evaluates the emotion based on the tone and specific wording of the question. The input is the user's question and acquired information, and the output is the emotion analysis result.

[0683] Step 8:

[0684] The server generates answers using generative artificial intelligence based on the acquired information and the results of the emotion engine's analysis. Specifically, it uses a generative AI library to create answers with a tone and content appropriate to the emotional state. The input is the acquired information and the emotion analysis results, and the output is the generated answer.

[0685] Step 9:

[0686] The server sends the generated answer to the user's terminal, which then displays it in the chat window. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[0687] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0688] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0689] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0690] [Third Embodiment]

[0691] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0692] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0693] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0694] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0695] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0696] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0697] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0698] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0699] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0700] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0701] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0702] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0703] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user inquiries using generative artificial intelligence. A specific embodiment of this system, including the program's processing, is described in detail below.

[0704] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[0705] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[0706] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[0707] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest legal review history," the NLP engine extracts keywords such as "latest," "legal," and "review history," and uses them to construct a search query.

[0708] Next, the server uses the generated search query to search the integrated database and retrieve relevant information. At this point, the server issues a query to the database and retrieves the corresponding records. The retrieved information is not used directly, but is instead input into the generative artificial intelligence.

[0709] The server inputs the acquired information into a generative artificial intelligence (AI) system, which generates answers to the user's questions in a natural way. The generative AI system creates the optimal answer based on the acquired data and generates it as a sentence in natural language. For example, it might generate a specific answer such as, "The latest legal review history is as follows..."

[0710] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. The user can instantly see the answer to the question they entered. This entire process allows the user to easily and quickly obtain the information they need.

[0711] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. This process allows users to obtain the necessary information without any effort, and significantly reduces redundant work and waste within the company.

[0712] The following describes the processing flow.

[0713] Step 1:

[0714] The server collects the latest data from each data source. This is done by running automated scripts on a regular schedule. For example, it might send API requests to retrieve internal manuals, execute database queries to extract legal review history, and download performance data.

[0715] Step 2:

[0716] The server converts the collected data into an appropriate format and stores it in an integrated database. First, the collected data is converted to a format such as JSON, and metadata such as "source," "date," and "category" is added to the data. Then, the converted data is saved to the integrated database.

[0717] Step 3:

[0718] The user enters their question through the device's chat interface. The user enters their question in natural language, such as "Please tell me the latest legal review history" in the chat window.

[0719] Step 4:

[0720] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[0721] Step 5:

[0722] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[0723] Step 6:

[0724] The server generates a search query based on the extracted keywords. For example, a query like "latest AND legal AND verification history" is generated.

[0725] Step 7:

[0726] The server searches the integrated database using the generated search query. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[0727] Step 8:

[0728] The server inputs the acquired information into a generative artificial intelligence (AI) system to generate answers to the user's questions. The AI ​​system creates natural-sounding responses based on the acquired data. For example, it might generate an answer such as, "The latest legal review history is as follows..."

[0729] Step 9:

[0730] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal and displayed on the chat interface.

[0731] Step 10:

[0732] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific response to the question.

[0733] The above outlines the specific processing steps of the program. This allows users to quickly and easily obtain the necessary information through the system.

[0734] (Example 1)

[0735] Next, we will describe Example 1. 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."

[0736] Conventional data collection systems have struggled to centrally manage data from different formats and sources, making it difficult to quickly and accurately obtain necessary information. Furthermore, few systems could automatically generate appropriate answers to natural language questions, resulting in low user convenience.

[0737] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0738] In this invention, the server includes means for periodically executing automated scripts to collect data from various internal data sources, means for converting the collected data into JSON format or the like, adding metadata, and storing it in an integrated database, and means for analyzing received questions using natural language processing, extracting important keywords, and generating search queries. This makes it possible to generate and provide accurate and rapid answers using generative artificial intelligence to questions entered by users in natural language.

[0739] A "data source" refers to the system or database from which information is collected.

[0740] An "automatic script" refers to a program that is executed automatically at regular time intervals.

[0741] A "server" refers to a computer system that collects, transforms, and analyzes data.

[0742] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a text format for structuring and representing data.

[0743] "Metadata" refers to information related to data (such as source, date, category, etc.).

[0744] An "integrated database" refers to a database that centrally manages data collected from multiple data sources.

[0745] A "user" refers to anyone who wants to use the system to obtain information.

[0746] A "terminal" refers to a device (such as a PC or smartphone) that a user uses to access a system.

[0747] A "chat interface" refers to an interactive input method that allows users to enter questions using natural language.

[0748] "Natural language processing" refers to the technology of analyzing and understanding human language using computers.

[0749] A "search query" refers to a search command used to retrieve specific information from a database.

[0750] "Generative artificial intelligence" refers to artificial intelligence technology that generates natural-sounding sentences and responses based on data.

[0751] "Answer" refers to the response provided by a generative artificial intelligence system to a user's question.

[0752] This invention relates to a system that collects data from various data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. An embodiment of this system will be described in detail.

[0753] First, the server collects data using Python and SQL. It retrieves the necessary information from data sources using API requests (e.g., requests.get('https: / / internal-api.example.com / manuals')) and extracts information from databases by executing SQL queries (e.g., SELECT FROM legal_records WHERE update_date > CURDATE() - INTERVAL 1 DAY;). This allows data to be collected from systems such as the manual management system, the legal confirmation history database, and the system that manages the achievements of each department.

[0754] Next, the server converts the collected data into JSON format (using json.dumps) and adds metadata. This standardization of formatting makes subsequent searching and analysis easier. The converted data is then stored in the unified database using SQL (e.g., INSERT INTO unified_db (data, source, date) VALUES (...);).

[0755] If a user wants to obtain information, they enter their question through the chat interface on their device. The chat interface is provided via a web browser or a dedicated application. For example, the user might enter a question in text format, such as "Tell me about my recent legal review history." The device then sends the question to the server (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})).

[0756] The server analyzes the received question using natural language processing (NLP) techniques. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the question and extract important keywords. For example, from the question "Please tell me my recent legal review history," it extracts the keywords "recent," "legal," and "review history." Then, it generates a search query based on these keywords.

[0757] Using the generated search query, the server retrieves relevant information from the integrated database. In this process, the server issues SQL queries (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The retrieved information is then directly input into the generative artificial intelligence.

[0758] Next, the server uses generative artificial intelligence (e.g., GPT-3) to generate answers to the user's questions based on the information it has acquired. The generative AI generates natural-sounding sentences based on the input data, creating specific answers such as, "The recent legal review history is as follows..."

[0759] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. This allows the user to instantly obtain the answer to the question they entered.

[0760] As an example of a prompt, the user might type, "Tell me about my recent legal review history." This prompts the server to search the legal review history data already collected during the data collection phase, and a generative artificial intelligence system generates a specific answer based on that data. The answer is then displayed on the user's terminal, providing the information instantly. This entire process allows the user to quickly obtain the necessary information without any hassle.

[0761] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0762] Step 1:

[0763] The server periodically runs automated scripts to collect data from various internal data sources. Specifically, it uses Python's requests library and SQL SELECT statements to retrieve data from API requests and extract information from the database. The server accesses API endpoints (e.g., requests.get('https: / / internal-api.example.com / manuals')) and temporarily stores the retrieved data. The input is API endpoints and database queries, and the output is the temporarily stored data.

[0764] Step 2:

[0765] The server converts the collected data into JSON format, adds metadata, and stores it in the unified database. Specifically, it uses the `json.dumps` method to convert the data into JSON format and then uses SQL to store it in the unified database. The input is the temporarily stored data, and the output is the JSON data stored in the unified database. The server executes SQL statements such as `INSERT INTO unified_db (data, source, date) VALUES (...);`.

[0766] Step 3:

[0767] The user enters their question through the terminal's chat interface. The terminal sends the text entered by the user (e.g., "Tell me about my recent legal review history") to the server. Specifically, the terminal sends the user's text input to the server as a POST request in JSON format (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})). The input is the user's question, and the output is the question data sent to the server.

[0768] Step 4:

[0769] The server analyzes received questions using natural language processing (NLP) techniques and generates search queries. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the questions and extract important keywords. For example, from the question "Please tell me about recent legal review history," it extracts the keywords "recent," "legal," and "review history." The input is the received question data, and the output is the search query.

[0770] Step 5:

[0771] The server uses the generated search query to search the unified database and retrieve relevant information. Specifically, it issues an SQL query (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The input is the search query, and the output is the retrieved database records.

[0772] Step 6:

[0773] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates answers to the user's questions in a natural-sounding format. Specifically, data is input into a generative AI model (e.g., GPT-3), and the AI ​​generates answers in natural language. For example, a specific answer such as "The latest legal review history is as follows..." might be generated. The input is the acquired database records, and the output is the generated answer.

[0774] Step 7:

[0775] The server sends the generated response to the user's terminal, and the terminal displays the response in the chat interface. Specifically, the server sends the generated response to the user's terminal as a POST request (e.g., requests.post('https: / / client-api.example.com / response', data={'response': 'The latest legal review history is as follows...'})), and the user's terminal displays the received response in the chat box. The input is the generated response, and the output is the response displayed in the chat interface.

[0776] (Application Example 1)

[0777] Next, we will explain Application Example 1. In the following explanation, 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."

[0778] Conventional factory management systems suffer from a fragmented data collection system, lacking effective means to integrate necessary information. Furthermore, they lack automated response functions to allow workers to instantly obtain required information, necessitating manual responses even in situations requiring rapid action. This results in low factory efficiency and a tendency towards information duplication and waste.

[0779] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0780] In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format via a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the obtained information, means for forming detailed answers to the user's questions using a generative AI model, means for sending and displaying the generated answers on the user's terminal, and means for automatically collecting data from various sensors and systems within the factory and storing it in an integrated database. This enables workers to quickly and accurately obtain the latest information within the factory, significantly improving the operational efficiency of the factory.

[0781] "Various internal data sources" refers to data provided by multiple departments and business systems.

[0782] "Means of collecting data periodically" refers to a system that has the function of automatically collecting data at set time intervals.

[0783] "Means of converting to an appropriate format and storing in an integrated database" refers to the process of converting collected data into a unified format and saving it in an integrated database.

[0784] "A means for users to input questions in a chat format via their device" refers to an interface that allows users to input text from their device and interact with the system.

[0785] "A means of analyzing received questions using natural language processing and generating search queries" refers to a technology that analyzes input text and converts it into a query suitable for searching.

[0786] "A means of retrieving relevant information from an integrated database based on a generated search query" refers to the process of using a search query to search the database and extract the necessary information.

[0787] "A means of generating an answer using generative artificial intelligence based on acquired information" refers to a function that inputs data into an AI model and generates an answer in natural language.

[0788] "Means for forming detailed answers to user questions using a generative AI model" refers to the technology of creating detailed and specific answers using generative AI technology.

[0789] "Means of sending and displaying the generated answer on the user's terminal" refers to a mechanism for transferring the response generated by the AI ​​to the user's device and displaying it.

[0790] "Methods for automatically collecting data from various sensors and systems within a factory and storing it in an integrated database" refers to the process of automatically collecting and integrating data from sensors and systems within a factory and saving it to a database.

[0791] This invention specifically describes a factory management system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. The specific processes for implementing this invention are described below.

[0792] The server first runs automated scripts periodically to collect the latest data from various sensors and systems within the factory. These data sources include manufacturing line sensors, inventory management systems, and quality control systems. The server retrieves the necessary data using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database.

[0793] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format, making subsequent retrieval easier.

[0794] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[0795] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and uses them to construct a search query.

[0796] Next, the server searches the integrated database using the generated search query and retrieves relevant information. The retrieved information is not used directly, but is instead input into a generative artificial intelligence (AI). The server inputs the retrieved information into the generative AI, which generates answers to the user's questions in a natural way. The generative AI creates the optimal answer based on the retrieved data and generates it as a sentence in natural language. For example, a specific answer such as "The latest inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units" is generated.

[0797] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. Users can instantly see the answer to the question they entered. This entire process allows users to easily and quickly obtain the information they need, significantly improving operational efficiency within the factory.

[0798] As a concrete example, when a user enters the question, "Please tell me the latest inventory status," the server first searches for inventory data already acquired during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. Examples of such prompts include the following:

[0799] "Please tell me the latest stock status."

[0800] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0801] Step 1:

[0802] Data collection:

[0803] The server periodically executes automated scripts to collect the latest data from various sensors and systems within the factory. Specifically, it retrieves information from manufacturing line sensors, inventory management systems, quality control systems, etc., using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database. The input for this step is data from sensors and systems within the factory, and the output is a series of data containing various information.

[0804] Step 2:

[0805] Data transformation and integration:

[0806] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format. The input for this step is various types of data, and the output is the data in the integrated database.

[0807] Step 3:

[0808] User question input:

[0809] Users use a chat interface via their device to input questions in natural language. This interface is provided as a web browser or a dedicated application. The questions entered by users are intended to obtain specific information. For example, a user might enter, "Please tell me the latest stock status." The input in this step is the user's question, and the output is that the question is sent to the server.

[0810] Step 4:

[0811] Question analysis using natural language processing (NLP):

[0812] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. Specifically, the NLP engine performs morphological analysis on the question sentence and extracts important keywords and context. For example, in the case of "Please tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and constructs a search query based on these. The input for this step is the user's question, and the output is the generated search query.

[0813] Step 5:

[0814] Integrated database search:

[0815] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues an appropriate query to the database and retrieves the corresponding records. For example, a query might be issued to search for "latest inventory data". The input to this step is the generated search query, and the output is the retrieved relevant information.

[0816] Step 6:

[0817] Solution generation using generative AI models:

[0818] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates natural-sounding answers to the user's questions. The generative AI model creates the optimal response based on the acquired data and generates it as a natural language sentence. For example, it might generate a specific answer such as, "The current inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units." The input for this step is the acquired relevant information, and the output is the generated response sentence.

[0819] Step 7:

[0820] Submitting and displaying answers:

[0821] The server sends the generated answer to the user's terminal, which displays the answer on the chat interface. The user can immediately see the answer to the question they entered. In this step, the input is the generated answer text, and the output is the answer displayed on the user's terminal.

[0822] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0823] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence and an emotion engine. A specific embodiment of this system, including the program's processing, is described in detail below.

[0824] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[0825] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[0826] If a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided via a web browser or a dedicated application. Users enter their questions in natural language, such as "Please tell me the latest legal review history" in the chat window.

[0827] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[0828] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The server performs morphological analysis on the question text and extracts important keywords and context such as "latest," "legal," and "verification history." Next, the server generates a search query based on the extracted keywords, creating a query that is "latest AND legal AND verification history."

[0829] The server uses the generated search query to search the integrated database and retrieve relevant information. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[0830] The server analyzes the acquired information and inputs it into the emotion engine. The emotion engine analyzes the user's input questions and determines their emotional state (e.g., anger, joy, confusion, etc.). For example, it evaluates whether the user is in a hurry or dissatisfied based on the tone and specific wording of the question.

[0831] Next, the server inputs the acquired information and the analysis results from the emotion engine into the generative artificial intelligence to generate an appropriate answer. Based on the identified emotional state, the generative AI creates an answer with a more appropriate tone and content. For example, if the user is confused, a more polite and easy-to-understand answer will be generated.

[0832] The server sends the generated answer to the user's terminal, which then displays the answer in the chat window. The user can instantly see a specific and appropriate answer to the question they entered.

[0833] For example, if a user enters a question such as "Tell me about my recent legal review history," and the sentiment engine detects that the user is in a hurry, it will generate a quick and easy-to-understand answer tailored to the user's needs. This answer will then be displayed in the chat window. This process allows users to easily and quickly obtain the information they need, significantly reducing internal duplication and waste.

[0834] As a result, the system of the present invention can recognize the user's emotions and generate more appropriate responses, thereby improving user satisfaction and work efficiency.

[0835] The following describes the processing flow.

[0836] Step 1:

[0837] The server collects the latest data from each data source. This is done by running automated scripts according to a regular schedule. Specifically, it sends API requests to retrieve internal manuals, executes database queries to extract legal review history, and downloads performance data.

[0838] Step 2:

[0839] The server converts the collected data into an appropriate format and stores it in an integrated database for user convenience. This conversion involves changing the data to a standardized format such as JSON, and adding metadata such as "source," "date," and "category." The converted data is then stored in the integrated database.

[0840] Step 3:

[0841] Users enter questions through the chat interface on their device. Specifically, they use a web browser or a dedicated application to enter questions in the format of, "Please tell me the latest legal review history."

[0842] Step 4:

[0843] The terminal sends the entered question to the server in real time. The chat interface receives user input and immediately sends that data to the server.

[0844] Step 5:

[0845] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[0846] Step 6:

[0847] The server generates a search query based on the extracted keywords. For example, it might create a query like "latest AND legal AND verification history".

[0848] Step 7:

[0849] The server searches the integrated database using the generated search query. It issues the query to the database, searches for relevant records, and retrieves the corresponding data.

[0850] Step 8:

[0851] The server analyzes the acquired information and inputs it into the emotion engine. Specifically, it passes the user's entered question text to the emotion engine and analyzes their emotional state (e.g., anger, joy, confusion, etc.).

[0852] Step 9:

[0853] The server inputs the acquired information and the analysis results from the emotion engine into a generative artificial intelligence (AI) system to generate the optimal answer. The generative AI takes the identified emotion into consideration to create a more appropriate tone and content for the response. For example, if the user is confused, it will generate a more polite and easy-to-understand response.

[0854] Step 10:

[0855] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal in real time and displayed in the chat window.

[0856] Step 11:

[0857] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific and appropriate response to the question they entered.

[0858] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase. If the emotion engine determines that the user is in a hurry, the generative artificial intelligence generates a quick and easy-to-understand answer. This answer is displayed in the chat window, allowing the user to instantly obtain the necessary information. This process makes it possible for users to easily and quickly obtain the information they need, significantly reducing redundant work and waste within the company.

[0859] (Example 2)

[0860] Next, we will describe Example 2. 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."

[0861] Conventional information gathering systems have suffered from inefficiency due to the cumbersome process of collecting and integrating data from various internal data sources. Furthermore, the process of users inputting questions and obtaining information has not taken into account the emotional state of the user, resulting in unsatisfactory responses and a diminished user experience. This invention aims to improve convenience and satisfaction by recognizing the user's emotions and generating appropriate responses.

[0862] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the acquired information and the user's emotional state, and means for transmitting and displaying the generated answers on the user terminal. This makes it possible to provide quick, emotionally sensitive, and appropriate answers to user questions.

[0863] "Data source" refers to the systems and databases where various types of internal company data are stored.

[0864] An "integrated database" refers to a database system that centrally manages and stores collected data.

[0865] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[0866] A "search query" refers to the search conditions generated to retrieve specific information from a database.

[0867] "Generative artificial intelligence" refers to an AI system that generates responses in natural language, similar to human language, based on received data and analysis results.

[0868] An "emotion engine" refers to a technology that analyzes and identifies a user's emotional state based on the questions they enter.

[0869] A "user terminal" refers to a device (such as a personal computer or smartphone) that a user uses to access and operate a system.

[0870] "Metadata" refers to data that provides information about other data, and is supplementary information that facilitates the organization and retrieval of data.

[0871] This invention relates to a system that periodically collects data from multiple internal data sources, stores it in an integrated database, and provides answers based on user input using generative artificial intelligence and an emotion engine. Specific embodiments of the invention are described below.

[0872] Data collection and integration

[0873] The server periodically runs automated scripts to collect the latest data from various internal data sources. These data sources include a manual management system, a legal review history database, and a system for managing the achievements of each department. The server retrieves data by sending API requests to these data sources and executing database queries. The collected data is then converted into a unified format such as JSON, and metadata (e.g., acquisition date and time, data source, category) is added before it is stored in an integrated database. This allows the collected data to be efficiently used in subsequent search processes.

[0874] User inquiries

[0875] When a user wants to obtain information, they enter their question in natural language through the terminal's chat interface. This terminal is provided as a web browser or a dedicated application. For example, if a user types "Tell me the latest legal review history," the terminal sends the question to the server in real time.

[0876] Question analysis and query generation

[0877] The server analyzes the received question using natural language processing (NLP) techniques to extract necessary keywords and context. Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history," and a search query is generated. For example, a search query like "latest AND legal AND verification history" is generated.

[0878] Database search and information retrieval

[0879] Using the generated search query, the server searches the integrated database and retrieves relevant information. This information serves as the foundational data for constructing answers to the user's questions.

[0880] Emotional analysis and response generation

[0881] Based on the acquired information, the server uses an emotion engine to determine the user's emotional state (e.g., anger, joy, confusion) from the question entered by the user. Next, the results of the emotion engine's analysis and the acquired information are passed to a generative artificial intelligence system to generate an answer with a tone and content appropriate to the user's emotional state. If the user is in a hurry, a quick and concise answer will be generated.

[0882] Providing the answer

[0883] The generated answers are sent from the server to the user's terminal and displayed in the terminal's chat window. Users can instantly receive specific and appropriate answers to the questions they enter.

[0884] Examples of prompt statements

[0885] "Please tell me about your recent legal review history."

[0886] "Please tell me which parts of the latest manual have been updated."

[0887] "Please tell me about the sales department's achievements."

[0888] This system enables the provision of prompt, emotionally sensitive, and appropriate answers to user questions, improving user satisfaction and work efficiency.

[0889] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0890] Step 1: Data Collection

[0891] server:

[0892] The system runs automated scripts periodically to collect the latest data from internal data sources.

[0893] For example, it can send API requests to retrieve the latest manual information from the manual management system. It can also execute database queries to retrieve legal review history.

[0894] Input: API endpoint URL, database connection information

[0895] Data processing: Retrieve API responses and database response data.

[0896] Output: Collected raw data

[0897] Step 2: Data Integration and Format Conversion

[0898] server:

[0899] The collected raw data is converted into a standardized format (e.g., JSON format).

[0900] Metadata is added to the collected data. For example, the date and time the data was acquired, the data source, and the category are added.

[0901] Input: Collected raw data

[0902] Data processing: Format conversion of raw data, addition of metadata.

[0903] Output: Data converted to JSON format

[0904] Step 3: Storing data in an integrated database

[0905] server:

[0906] A database write operation is performed to store the converted data in the integrated database.

[0907] For example, the converted data is saved to the database using an INSERT statement.

[0908] Input: Data converted to JSON format

[0909] Data processing: Writing operations to the database

[0910] Output: Data stored in the database

[0911] Step 4: User inquiries

[0912] User:

[0913] To obtain information, enter your question in natural language through the device's chat interface.

[0914] For example, you could type, "Please provide the latest legal review history."

[0915] Input: Question (natural language text)

[0916] Data processing: None

[0917] Output: The question displayed on the terminal.

[0918] Terminal:

[0919] The questions entered by the user are sent to the server in real time.

[0920] Input: User's question

[0921] Data processing: Sending the question

[0922] Output: Question text sent to the server

[0923] Step 5: Analyze the question and generate search queries

[0924] server:

[0925] The received questions are analyzed using natural language processing (NLP) techniques to extract important keywords and context.

[0926] Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history."

[0927] A search query is generated based on the extracted keywords.

[0928] Input: User's question

[0929] Data processing: Natural language processing, keyword extraction, search query generation.

[0930] Output: Search query

[0931] Step 6: Search the integrated database

[0932] server:

[0933] The generated search query is used to search the integrated database and retrieve relevant information.

[0934] Execute a SELECT statement against the database and retrieve the corresponding records.

[0935] Input: Search query

[0936] Data processing: Executing queries and retrieving results

[0937] Output: Acquired information

[0938] Step 7: Emotional Analysis and Solution Generation

[0939] server:

[0940] Based on the acquired information, an emotion engine is used to determine the user's emotional state from the question text they entered.

[0941] The analysis results from the emotion engine and the acquired information are passed to a generative artificial intelligence system to generate an appropriate answer.

[0942] For example, if it's determined that the user is in a hurry, it will generate a quick and concise response.

[0943] Input: Information obtained, user's question

[0944] Data processing: Sentiment analysis, answer generation

[0945] Output: Generated solution

[0946] Step 8: Providing the answer

[0947] server:

[0948] The generated answer is sent to the user's terminal.

[0949] Input: Generated answer

[0950] Data processing: Submitting the answer

[0951] Output: Answer sent to the user's terminal

[0952] Terminal:

[0953] The received answers will be displayed in the chat window.

[0954] For example, it might display, "The latest legal review history is as follows."

[0955] Input: Answer sent from the server

[0956] Data processing: Displaying the answer

[0957] Output: Answer displayed in the chat window

[0958] (Application Example 2)

[0959] Next, we will explain application example 2. In the following explanation, 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."

[0960] Conventional database management systems have made it difficult for users to quickly and accurately retrieve necessary information from vast amounts of internal company data. Furthermore, because they do not take into account the user's emotions or circumstances, their effectiveness in improving user satisfaction and convenience is limited. This invention aims to solve these problems and improve user satisfaction by enabling users to quickly and appropriately retrieve information and providing personalized responses that correspond to their emotional state.

[0961] The specific processing performed by the specific 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 periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for analyzing the emotional state of the question entered by the user using an emotion engine, means for generating answers using generative artificial intelligence based on the acquired information and the analysis results from the emotion engine, and means for sending and displaying the generated answers on the user terminal. This makes it possible to provide quick and appropriate answers that take into account the user's emotional state when a user asks a question in chat format through a terminal.

[0962] "Various internal data sources" refers to the sources of various data managed within a company, including, for example, manual management systems, legal verification history databases, and departmental performance management systems.

[0963] "Means of collecting data periodically" refers to a mechanism for automatically collecting data at regular time intervals, and in practice, this often involves using API requests or database queries.

[0964] "Means of converting data into an appropriate format and storing it in an integrated database" refers to a mechanism that converts collected data into a unified format (e.g., JSON format), adds metadata (source, date, category, etc.), and then stores it in an integrated database.

[0965] "A means for users to input questions in a chat format via a device" refers to an interface that allows users to input questions in natural language using any device (e.g., smartphone, PC).

[0966] "A means of analyzing received questions using natural language processing and generating search queries" refers to a mechanism that analyzes user-inputted questions using natural language processing techniques such as morphological analysis, extracts important keywords and context, and generates search queries.

[0967] "Means of obtaining relevant information from an integrated database" refers to a mechanism that searches for and retrieves the relevant data from an integrated database based on the generated search query.

[0968] An "emotion engine" refers to a system that analyzes the user's inputted questions and determines their emotional state (e.g., anger, joy, confusion, etc.).

[0969] "Generative artificial intelligence" refers to artificial intelligence technology that generates the most optimal answer for the user based on acquired information and analysis results from an emotion engine.

[0970] "Means of sending and displaying answers on the user's terminal" refers to a mechanism that sends the generated answers to the user's terminal and displays them on an interface such as a chat window.

[0971] This invention relates to a system that generates personalized answers, including sentiment analysis, to questions entered by users through a terminal. This system collects data from internal data sources, stores it in an integrated database, analyzes user questions using natural language processing and sentiment analysis, and provides answers using generative artificial intelligence.

[0972] Overall system configuration

[0973] This system consists of the following main components:

[0974] 1. Server:

[0975] We regularly collect data from various internal data sources, convert it to an appropriate format, and store it in an integrated database.

[0976] The system receives questions from users, analyzes them using natural language processing (NLP) techniques, and generates search queries.

[0977] Relevant information is retrieved from the integrated database, and the emotion engine analyzes the user's emotional state.

[0978] Using generative artificial intelligence, the system generates an answer based on acquired information and sentiment analysis results, and sends it to the user's terminal.

[0979] 2. User terminal:

[0980] It provides an interface where users can input questions in a chat format. This works on smartphones, PCs, and head-mounted displays (HMDs).

[0981] The received answers will be displayed in the chat window.

[0982] Hardware and software to be used

[0983] 1. Server:

[0984] Data Collection: Data is collected periodically from various internal data sources (e.g., manual management system, legal review history) using automated scripts. The software used includes API request libraries (e.g., Python's requests) and database query libraries (e.g., SQLAlchemy).

[0985] Data conversion and storage: Convert data into a unified format such as JSON, add metadata, and store it in an integrated database (e.g., MySQL, PostgreSQL).

[0986] Natural Language Processing (NLP): Analyzes user questions and generates search queries. The software used is an NLP library (e.g., spaCy, NLTK).

[0987] Sentiment Analysis: Analyzes the emotional state of the question using an emotion engine. Sentiment analysis APIs (e.g., IBM Watson, AWS Comprehend) are used.

[0988] Generative artificial intelligence: Generates answers based on acquired information and sentiment analysis results. The software used is a generative artificial intelligence library (e.g., OpenAI GPT-3).

[0989] 2. User terminal:

[0990] This includes smartphones, PCs, and head-mounted displays (HMDs). Users input natural language questions through these devices and receive answers from the server in real time.

[0991] Specific example

[0992] The user puts on an HMD (Head-Mounted Display) and accesses a virtual store. They input a question to the virtual assistant via voice or text, such as "Please tell me about the warranty for this product." After receiving the question, the server analyzes it using NLP (Neuro-Linguistic Programming) technology and retrieves relevant information from an integrated database. Next, an emotion engine analyzes the user's emotional state, and generative artificial intelligence (AI) generates an appropriate response. The tone and content of the response change according to the emotional state, and the result is sent to the user's terminal and displayed on the terminal.

[0993] Example of a prompt

[0994] As a concrete example of its use, here is an example of a prompt in response to a question asked by the user:

[0995] User's question: "Please tell me about the warranty for this product."

[0996] Sentiment analysis result: "In a hurry"

[0997] Generate the answer:

[0998] The warranty details are as follows:

[0999] Thus, the present invention aims to improve the user experience by taking into account the user's emotional state and providing quick and appropriate answers.

[1000] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1001] Step 1:

[1002] The server periodically collects data from various internal data sources. Specifically, it uses automated scripts to execute API requests and database queries to retrieve the latest data. The input is data from the data sources, and the output is the collected raw data.

[1003] Step 2:

[1004] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (source, date, category, etc.). The input is the collected raw data, and the output is data in a unified format.

[1005] Step 3:

[1006] Users enter questions in a chat format via their devices. Specifically, users input questions using natural language via smartphones or PCs. The input is the user's question text, and the output is the transmission of the question from the device to the server.

[1007] Step 4:

[1008] The terminal sends the received question to the server. The question is sent to the server in real time and is ready for analysis. The input is the user's question, and the output is the question sent to the server.

[1009] Step 5:

[1010] The server analyzes the received question using natural language processing (NLP) and generates a search query. Specifically, it performs morphological analysis to extract important keywords and context. The input is the user's question, and the output is the generated search query.

[1011] Step 6:

[1012] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues a query to the database and searches for the corresponding record. The input is the search query, and the output is the retrieved information.

[1013] Step 7:

[1014] The server inputs the acquired information into the emotion engine and analyzes the emotional state of the user's question. Specifically, it evaluates the emotion based on the tone and specific wording of the question. The input is the user's question and acquired information, and the output is the emotion analysis result.

[1015] Step 8:

[1016] The server generates answers using generative artificial intelligence based on the acquired information and the results of the emotion engine's analysis. Specifically, it uses a generative AI library to create answers with a tone and content appropriate to the emotional state. The input is the acquired information and the emotion analysis results, and the output is the generated answer.

[1017] Step 9:

[1018] The server sends the generated answer to the user's terminal, which then displays it in the chat window. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[1019] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1020] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1021] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1022] [Fourth Embodiment]

[1023] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1024] As shown in Figure 7, the 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.

[1025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1026] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1027] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1028] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1030] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1031] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1032] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1034] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1036] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user inquiries using generative artificial intelligence. A specific embodiment of this system, including the program's processing, is described in detail below.

[1037] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[1038] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[1039] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[1040] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest legal review history," the NLP engine extracts keywords such as "latest," "legal," and "review history," and uses them to construct a search query.

[1041] Next, the server uses the generated search query to search the integrated database and retrieve relevant information. At this point, the server issues a query to the database and retrieves the corresponding records. The retrieved information is not used directly, but is instead input into the generative artificial intelligence.

[1042] The server inputs the acquired information into a generative artificial intelligence (AI) system, which generates answers to the user's questions in a natural way. The generative AI system creates the optimal answer based on the acquired data and generates it as a sentence in natural language. For example, it might generate a specific answer such as, "The latest legal review history is as follows..."

[1043] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. The user can instantly see the answer to the question they entered. This entire process allows the user to easily and quickly obtain the information they need.

[1044] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. This process allows users to obtain the necessary information without any effort, and significantly reduces redundant work and waste within the company.

[1045] The following describes the processing flow.

[1046] Step 1:

[1047] The server collects the latest data from each data source. This is done by running automated scripts on a regular schedule. For example, it might send API requests to retrieve internal manuals, execute database queries to extract legal review history, and download performance data.

[1048] Step 2:

[1049] The server converts the collected data into an appropriate format and stores it in an integrated database. First, the collected data is converted to a format such as JSON, and metadata such as "source," "date," and "category" is added to the data. Then, the converted data is saved to the integrated database.

[1050] Step 3:

[1051] The user enters their question through the device's chat interface. The user enters their question in natural language, such as "Please tell me the latest legal review history" in the chat window.

[1052] Step 4:

[1053] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[1054] Step 5:

[1055] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[1056] Step 6:

[1057] The server generates a search query based on the extracted keywords. For example, a query like "latest AND legal AND verification history" is generated.

[1058] Step 7:

[1059] The server searches the integrated database using the generated search query. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[1060] Step 8:

[1061] The server inputs the acquired information into a generative artificial intelligence (AI) system to generate answers to the user's questions. The AI ​​system creates natural-sounding responses based on the acquired data. For example, it might generate an answer such as, "The latest legal review history is as follows..."

[1062] Step 9:

[1063] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal and displayed on the chat interface.

[1064] Step 10:

[1065] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific response to the question.

[1066] The above outlines the specific processing steps of the program. This allows users to quickly and easily obtain the necessary information through the system.

[1067] (Example 1)

[1068] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1069] Conventional data collection systems have struggled to centrally manage data from different formats and sources, making it difficult to quickly and accurately obtain necessary information. Furthermore, few systems could automatically generate appropriate answers to natural language questions, resulting in low user convenience.

[1070] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1071] In this invention, the server includes means for periodically executing automated scripts to collect data from various internal data sources, means for converting the collected data into JSON format or the like, adding metadata, and storing it in an integrated database, and means for analyzing received questions using natural language processing, extracting important keywords, and generating search queries. This makes it possible to generate and provide accurate and rapid answers using generative artificial intelligence to questions entered by users in natural language.

[1072] A "data source" refers to the system or database from which information is collected.

[1073] An "automatic script" refers to a program that is executed automatically at regular time intervals.

[1074] A "server" refers to a computer system that collects, transforms, and analyzes data.

[1075] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a text format for structuring and representing data.

[1076] "Metadata" refers to information related to data (such as source, date, category, etc.).

[1077] An "integrated database" refers to a database that centrally manages data collected from multiple data sources.

[1078] A "user" refers to anyone who wants to use the system to obtain information.

[1079] A "terminal" refers to a device (such as a PC or smartphone) that a user uses to access a system.

[1080] A "chat interface" refers to an interactive input method that allows users to enter questions using natural language.

[1081] "Natural language processing" refers to the technology of analyzing and understanding human language using computers.

[1082] A "search query" refers to a search command used to retrieve specific information from a database.

[1083] "Generative artificial intelligence" refers to artificial intelligence technology that generates natural-sounding sentences and responses based on data.

[1084] "Answer" refers to the response provided by a generative artificial intelligence system to a user's question.

[1085] This invention relates to a system that collects data from various data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. An embodiment of this system will be described in detail.

[1086] First, the server collects data using Python and SQL. It retrieves the necessary information from data sources using API requests (e.g., requests.get('https: / / internal-api.example.com / manuals')) and extracts information from databases by executing SQL queries (e.g., SELECT FROM legal_records WHERE update_date > CURDATE() - INTERVAL 1 DAY;). This allows data to be collected from systems such as the manual management system, the legal confirmation history database, and the system that manages the achievements of each department.

[1087] Next, the server converts the collected data into JSON format (using json.dumps) and adds metadata. This standardization of formatting makes subsequent searching and analysis easier. The converted data is then stored in the unified database using SQL (e.g., INSERT INTO unified_db (data, source, date) VALUES (...);).

[1088] If a user wants to obtain information, they enter their question through the chat interface on their device. The chat interface is provided via a web browser or a dedicated application. For example, the user might enter a question in text format, such as "Tell me about my recent legal review history." The device then sends the question to the server (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})).

[1089] The server analyzes the received question using natural language processing (NLP) techniques. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the question and extract important keywords. For example, from the question "Please tell me my recent legal review history," it extracts the keywords "recent," "legal," and "review history." Then, it generates a search query based on these keywords.

[1090] Using the generated search query, the server retrieves relevant information from the integrated database. In this process, the server issues SQL queries (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The retrieved information is then directly input into the generative artificial intelligence.

[1091] Next, the server uses generative artificial intelligence (e.g., GPT-3) to generate answers to the user's questions based on the information it has acquired. The generative AI generates natural-sounding sentences based on the input data, creating specific answers such as, "The recent legal review history is as follows..."

[1092] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. This allows the user to instantly obtain the answer to the question they entered.

[1093] As an example of a prompt, the user might type, "Tell me about my recent legal review history." This prompts the server to search the legal review history data already collected during the data collection phase, and a generative artificial intelligence system generates a specific answer based on that data. The answer is then displayed on the user's terminal, providing the information instantly. This entire process allows the user to quickly obtain the necessary information without any hassle.

[1094] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1095] Step 1:

[1096] The server periodically runs automated scripts to collect data from various internal data sources. Specifically, it uses Python's requests library and SQL SELECT statements to retrieve data from API requests and extract information from the database. The server accesses API endpoints (e.g., requests.get('https: / / internal-api.example.com / manuals')) and temporarily stores the retrieved data. The input is API endpoints and database queries, and the output is the temporarily stored data.

[1097] Step 2:

[1098] The server converts the collected data into JSON format, adds metadata, and stores it in the unified database. Specifically, it uses the `json.dumps` method to convert the data into JSON format and then uses SQL to store it in the unified database. The input is the temporarily stored data, and the output is the JSON data stored in the unified database. The server executes SQL statements such as `INSERT INTO unified_db (data, source, date) VALUES (...);`.

[1099] Step 3:

[1100] The user enters their question through the terminal's chat interface. The terminal sends the text entered by the user (e.g., "Tell me about my recent legal review history") to the server. Specifically, the terminal sends the user's text input to the server as a POST request in JSON format (e.g., requests.post('https: / / server-api.example.com / query', data={'query': 'Tell me about my recent legal review history'})). The input is the user's question, and the output is the question data sent to the server.

[1101] Step 4:

[1102] The server analyzes received questions using natural language processing (NLP) techniques and generates search queries. Specifically, it uses an NLP library (e.g., SpaCy or NLTK) to perform morphological analysis on the questions and extract important keywords. For example, from the question "Please tell me about recent legal review history," it extracts the keywords "recent," "legal," and "review history." The input is the received question data, and the output is the search query.

[1103] Step 5:

[1104] The server uses the generated search query to search the unified database and retrieve relevant information. Specifically, it issues an SQL query (e.g., SELECT FROM unified_db WHERE category = 'legal' AND update_date > CURDATE() - INTERVAL 1 MONTH;) to retrieve the necessary records. The input is the search query, and the output is the retrieved database records.

[1105] Step 6:

[1106] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates answers to the user's questions in a natural-sounding format. Specifically, data is input into a generative AI model (e.g., GPT-3), and the AI ​​generates answers in natural language. For example, a specific answer such as "The latest legal review history is as follows..." might be generated. The input is the acquired database records, and the output is the generated answer.

[1107] Step 7:

[1108] The server sends the generated response to the user's terminal, and the terminal displays the response in the chat interface. Specifically, the server sends the generated response to the user's terminal as a POST request (e.g., requests.post('https: / / client-api.example.com / response', data={'response': 'The latest legal review history is as follows...'})), and the user's terminal displays the received response in the chat box. The input is the generated response, and the output is the response displayed in the chat interface.

[1109] (Application Example 1)

[1110] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1111] Conventional factory management systems suffer from a fragmented data collection system, lacking effective means to integrate necessary information. Furthermore, they lack automated response functions to allow workers to instantly obtain required information, necessitating manual responses even in situations requiring rapid action. This results in low factory efficiency and a tendency towards information duplication and waste.

[1112] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1113] In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format via a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the obtained information, means for forming detailed answers to the user's questions using a generative AI model, means for sending and displaying the generated answers on the user's terminal, and means for automatically collecting data from various sensors and systems within the factory and storing it in an integrated database. This enables workers to quickly and accurately obtain the latest information within the factory, significantly improving the operational efficiency of the factory.

[1114] "Various internal data sources" refers to data provided by multiple departments and business systems.

[1115] "Means of collecting data periodically" refers to a system that has the function of automatically collecting data at set time intervals.

[1116] "Means of converting to an appropriate format and storing in an integrated database" refers to the process of converting collected data into a unified format and saving it in an integrated database.

[1117] "A means for users to input questions in a chat format via their device" refers to an interface that allows users to input text from their device and interact with the system.

[1118] "A means of analyzing received questions using natural language processing and generating search queries" refers to a technology that analyzes input text and converts it into a query suitable for searching.

[1119] "A means of retrieving relevant information from an integrated database based on a generated search query" refers to the process of using a search query to search the database and extract the necessary information.

[1120] "A means of generating an answer using generative artificial intelligence based on acquired information" refers to a function that inputs data into an AI model and generates an answer in natural language.

[1121] "Means for forming detailed answers to user questions using a generative AI model" refers to the technology of creating detailed and specific answers using generative AI technology.

[1122] "Means of sending and displaying the generated answer on the user's terminal" refers to a mechanism for transferring the response generated by the AI ​​to the user's device and displaying it.

[1123] "Methods for automatically collecting data from various sensors and systems within a factory and storing it in an integrated database" refers to the process of automatically collecting and integrating data from sensors and systems within a factory and saving it to a database.

[1124] This invention specifically describes a factory management system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence. The specific processes for implementing this invention are described below.

[1125] The server first runs automated scripts periodically to collect the latest data from various sensors and systems within the factory. These data sources include manufacturing line sensors, inventory management systems, and quality control systems. The server retrieves the necessary data using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database.

[1126] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format, making subsequent retrieval easier.

[1127] When a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided as a web browser or a dedicated application. The user enters their question in natural language, and the device sends the question to the server in real time.

[1128] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The NLP engine performs morphological analysis on the question text and extracts important keywords and context. For example, if a user enters "Tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and uses them to construct a search query.

[1129] Next, the server searches the integrated database using the generated search query and retrieves relevant information. The retrieved information is not used directly, but is instead input into a generative artificial intelligence (AI). The server inputs the retrieved information into the generative AI, which generates answers to the user's questions in a natural way. The generative AI creates the optimal answer based on the retrieved data and generates it as a sentence in natural language. For example, a specific answer such as "The latest inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units" is generated.

[1130] Finally, the server sends the generated answer to the user's terminal, which then displays the answer on the chat interface. Users can instantly see the answer to the question they entered. This entire process allows users to easily and quickly obtain the information they need, significantly improving operational efficiency within the factory.

[1131] As a concrete example, when a user enters the question, "Please tell me the latest inventory status," the server first searches for inventory data already acquired during the data collection phase, and then a generative artificial intelligence generates a specific answer based on that data. The answer is then sent to the user's terminal and displayed in the chat window. Examples of such prompts include the following:

[1132] "Please tell me the latest stock status."

[1133] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1134] Step 1:

[1135] Data collection:

[1136] The server periodically executes automated scripts to collect the latest data from various sensors and systems within the factory. Specifically, it retrieves information from manufacturing line sensors, inventory management systems, quality control systems, etc., using API requests and database queries. For example, it uses HTTP requests to retrieve sensor information from API endpoints and SQL queries to retrieve inventory data from the database. The input for this step is data from sensors and systems within the factory, and the output is a series of data containing various information.

[1137] Step 2:

[1138] Data transformation and integration:

[1139] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.) to the data. This ensures that the collected data is stored in the integrated database in a unified format. The input for this step is various types of data, and the output is the data in the integrated database.

[1140] Step 3:

[1141] User question input:

[1142] Users use a chat interface via their device to input questions in natural language. This interface is provided as a web browser or a dedicated application. The questions entered by users are intended to obtain specific information. For example, a user might enter, "Please tell me the latest stock status." The input in this step is the user's question, and the output is that the question is sent to the server.

[1143] Step 4:

[1144] Question analysis using natural language processing (NLP):

[1145] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. Specifically, the NLP engine performs morphological analysis on the question sentence and extracts important keywords and context. For example, in the case of "Please tell me the latest stock status," the NLP engine extracts keywords such as "latest," "stock," and "status," and constructs a search query based on these. The input for this step is the user's question, and the output is the generated search query.

[1146] Step 5:

[1147] Integrated database search:

[1148] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues an appropriate query to the database and retrieves the corresponding records. For example, a query might be issued to search for "latest inventory data". The input to this step is the generated search query, and the output is the retrieved relevant information.

[1149] Step 6:

[1150] Solution generation using generative AI models:

[1151] The server inputs the acquired information into a generative artificial intelligence (AI) system, which then generates natural-sounding answers to the user's questions. The generative AI model creates the optimal response based on the acquired data and generates it as a natural language sentence. For example, it might generate a specific answer such as, "The current inventory status is as follows: Product A - 50 units, Product B - 30 units, Product C - 20 units." The input for this step is the acquired relevant information, and the output is the generated response sentence.

[1152] Step 7:

[1153] Submitting and displaying answers:

[1154] The server sends the generated answer to the user's terminal, which displays the answer on the chat interface. The user can immediately see the answer to the question they entered. In this step, the input is the generated answer text, and the output is the answer displayed on the user's terminal.

[1155] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1156] This invention relates to a system that collects data from various internal data sources, stores it in an integrated database, and provides answers to user questions using generative artificial intelligence and an emotion engine. A specific embodiment of this system, including the program's processing, is described in detail below.

[1157] First, the server periodically runs automated scripts to collect the latest data from internal data sources. These data sources include, for example, the company's manual management system, a database of legal review history, and a system for managing the achievements of each department. In this step, the server retrieves the necessary data using API requests and database queries.

[1158] Next, the server converts the collected data into an appropriate format and stores it in an integrated database. This process converts the data into a unified format such as JSON and adds metadata (e.g., source, date, category, etc.). Storing the collected data in an integrated database makes subsequent retrieval easier.

[1159] If a user wants to obtain information, they enter their question through the chat interface on their device. This interface is provided via a web browser or a dedicated application. Users enter their questions in natural language, such as "Please tell me the latest legal review history" in the chat window.

[1160] The terminal sends the entered question to the server in real time. The chat interface on the terminal receives the user input and immediately sends that data to the server.

[1161] The server analyzes the received question using natural language processing (NLP) techniques and generates a search query. The server performs morphological analysis on the question text and extracts important keywords and context such as "latest," "legal," and "verification history." Next, the server generates a search query based on the extracted keywords, creating a query that is "latest AND legal AND verification history."

[1162] The server uses the generated search query to search the integrated database and retrieve relevant information. The server issues a query to the database, searches for relevant records, and retrieves the corresponding data.

[1163] The server analyzes the acquired information and inputs it into the emotion engine. The emotion engine analyzes the user's input questions and determines their emotional state (e.g., anger, joy, confusion, etc.). For example, it evaluates whether the user is in a hurry or dissatisfied based on the tone and specific wording of the question.

[1164] Next, the server inputs the acquired information and the analysis results from the emotion engine into the generative artificial intelligence to generate an appropriate answer. Based on the identified emotional state, the generative AI creates an answer with a more appropriate tone and content. For example, if the user is confused, a more polite and easy-to-understand answer will be generated.

[1165] The server sends the generated answer to the user's terminal, which then displays the answer in the chat window. The user can instantly see a specific and appropriate answer to the question they entered.

[1166] For example, if a user enters a question such as "Tell me about my recent legal review history," and the sentiment engine detects that the user is in a hurry, it will generate a quick and easy-to-understand answer tailored to the user's needs. This answer will then be displayed in the chat window. This process allows users to easily and quickly obtain the information they need, significantly reducing internal duplication and waste.

[1167] As a result, the system of the present invention can recognize the user's emotions and generate more appropriate responses, thereby improving user satisfaction and work efficiency.

[1168] The following describes the processing flow.

[1169] Step 1:

[1170] The server collects the latest data from each data source. This is done by running automated scripts according to a regular schedule. Specifically, it sends API requests to retrieve internal manuals, executes database queries to extract legal review history, and downloads performance data.

[1171] Step 2:

[1172] The server converts the collected data into an appropriate format and stores it in an integrated database for user convenience. This conversion involves changing the data to a standardized format such as JSON, and adding metadata such as "source," "date," and "category." The converted data is then stored in the integrated database.

[1173] Step 3:

[1174] Users enter questions through the chat interface on their device. Specifically, they use a web browser or a dedicated application to enter questions in the format of, "Please tell me the latest legal review history."

[1175] Step 4:

[1176] The terminal sends the entered question to the server in real time. The chat interface receives user input and immediately sends that data to the server.

[1177] Step 5:

[1178] The server analyzes the received question using natural language processing (NLP) techniques. The server performs morphological analysis on the question text and extracts important keywords and context, such as "latest," "legal," and "verification history."

[1179] Step 6:

[1180] The server generates a search query based on the extracted keywords. For example, it might create a query like "latest AND legal AND verification history".

[1181] Step 7:

[1182] The server searches the integrated database using the generated search query. It issues the query to the database, searches for relevant records, and retrieves the corresponding data.

[1183] Step 8:

[1184] The server analyzes the acquired information and inputs it into the emotion engine. Specifically, it passes the user's entered question text to the emotion engine and analyzes their emotional state (e.g., anger, joy, confusion, etc.).

[1185] Step 9:

[1186] The server inputs the acquired information and the analysis results from the emotion engine into a generative artificial intelligence (AI) system to generate the optimal answer. The generative AI takes the identified emotion into consideration to create a more appropriate tone and content for the response. For example, if the user is confused, it will generate a more polite and easy-to-understand response.

[1187] Step 10:

[1188] The server sends the generated answer to the user's terminal. The generated answer is sent from the server to the user's terminal in real time and displayed in the chat window.

[1189] Step 11:

[1190] The device displays the received answer to the user. The chat window instantly displays the answer, allowing the user to see a specific and appropriate response to the question they entered.

[1191] For example, when a user enters the question, "Tell me about my recent legal review history," the server first searches the legal review history data already collected during the data collection phase. If the emotion engine determines that the user is in a hurry, the generative artificial intelligence generates a quick and easy-to-understand answer. This answer is displayed in the chat window, allowing the user to instantly obtain the necessary information. This process makes it possible for users to easily and quickly obtain the information they need, significantly reducing redundant work and waste within the company.

[1192] (Example 2)

[1193] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1194] Conventional information gathering systems have suffered from inefficiency due to the cumbersome process of collecting and integrating data from various internal data sources. Furthermore, the process of users inputting questions and obtaining information has not taken into account the emotional state of the user, resulting in unsatisfactory responses and a diminished user experience. This invention aims to improve convenience and satisfaction by recognizing the user's emotions and generating appropriate responses.

[1195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for generating answers using generative artificial intelligence based on the acquired information and the user's emotional state, and means for transmitting and displaying the generated answers on the user terminal. This makes it possible to provide quick, emotionally sensitive, and appropriate answers to user questions.

[1196] "Data source" refers to the systems and databases where various types of internal company data are stored.

[1197] An "integrated database" refers to a database system that centrally manages and stores collected data.

[1198] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[1199] A "search query" refers to the search conditions generated to retrieve specific information from a database.

[1200] "Generative artificial intelligence" refers to an AI system that generates responses in natural language, similar to human language, based on received data and analysis results.

[1201] An "emotion engine" refers to a technology that analyzes and identifies a user's emotional state based on the questions they enter.

[1202] A "user terminal" refers to a device (such as a personal computer or smartphone) that a user uses to access and operate a system.

[1203] "Metadata" refers to data that provides information about other data, and is supplementary information that facilitates the organization and retrieval of data.

[1204] This invention relates to a system that periodically collects data from multiple internal data sources, stores it in an integrated database, and provides answers based on user input using generative artificial intelligence and an emotion engine. Specific embodiments of the invention are described below.

[1205] Data collection and integration

[1206] The server periodically runs automated scripts to collect the latest data from various internal data sources. These data sources include a manual management system, a legal review history database, and a system for managing the achievements of each department. The server retrieves data by sending API requests to these data sources and executing database queries. The collected data is then converted into a unified format such as JSON, and metadata (e.g., acquisition date and time, data source, category) is added before it is stored in an integrated database. This allows the collected data to be efficiently used in subsequent search processes.

[1207] User inquiries

[1208] When a user wants to obtain information, they enter their question in natural language through the terminal's chat interface. This terminal is provided as a web browser or a dedicated application. For example, if a user types "Tell me the latest legal review history," the terminal sends the question to the server in real time.

[1209] Question analysis and query generation

[1210] The server analyzes the received question using natural language processing (NLP) techniques to extract necessary keywords and context. Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history," and a search query is generated. For example, a search query like "latest AND legal AND verification history" is generated.

[1211] Database search and information retrieval

[1212] Using the generated search query, the server searches the integrated database and retrieves relevant information. This information serves as the foundational data for constructing answers to the user's questions.

[1213] Emotional analysis and response generation

[1214] Based on the acquired information, the server uses an emotion engine to determine the user's emotional state (e.g., anger, joy, confusion) from the question entered by the user. Next, the results of the emotion engine's analysis and the acquired information are passed to a generative artificial intelligence system to generate an answer with a tone and content appropriate to the user's emotional state. If the user is in a hurry, a quick and concise answer will be generated.

[1215] Providing the answer

[1216] The generated answers are sent from the server to the user's terminal and displayed in the terminal's chat window. Users can instantly receive specific and appropriate answers to the questions they enter.

[1217] Examples of prompt statements

[1218] "Please tell me about your recent legal review history."

[1219] "Please tell me which parts of the latest manual have been updated."

[1220] "Please tell me about the sales department's achievements."

[1221] This system enables the provision of prompt, emotionally sensitive, and appropriate answers to user questions, improving user satisfaction and work efficiency.

[1222] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1223] Step 1: Data Collection

[1224] server:

[1225] The system runs automated scripts periodically to collect the latest data from internal data sources.

[1226] For example, it can send API requests to retrieve the latest manual information from the manual management system. It can also execute database queries to retrieve legal review history.

[1227] Input: API endpoint URL, database connection information

[1228] Data processing: Retrieve API responses and database response data.

[1229] Output: Collected raw data

[1230] Step 2: Data Integration and Format Conversion

[1231] server:

[1232] The collected raw data is converted into a standardized format (e.g., JSON format).

[1233] Metadata is added to the collected data. For example, the date and time the data was acquired, the data source, and the category are added.

[1234] Input: Collected raw data

[1235] Data processing: Format conversion of raw data, addition of metadata.

[1236] Output: Data converted to JSON format

[1237] Step 3: Storing data in an integrated database

[1238] server:

[1239] A database write operation is performed to store the converted data in the integrated database.

[1240] For example, the converted data is saved to the database using an INSERT statement.

[1241] Input: Data converted to JSON format

[1242] Data processing: Writing operations to the database

[1243] Output: Data stored in the database

[1244] Step 4: User inquiries

[1245] User:

[1246] To obtain information, enter your question in natural language through the device's chat interface.

[1247] For example, you could type, "Please provide the latest legal review history."

[1248] Input: Question (natural language text)

[1249] Data processing: None

[1250] Output: The question displayed on the terminal.

[1251] Terminal:

[1252] The questions entered by the user are sent to the server in real time.

[1253] Input: User's question

[1254] Data processing: Sending the question

[1255] Output: Question text sent to the server

[1256] Step 5: Analyze the question and generate search queries

[1257] server:

[1258] The received questions are analyzed using natural language processing (NLP) techniques to extract important keywords and context.

[1259] Morphological analysis is performed to extract keywords such as "latest," "legal," and "verification history."

[1260] A search query is generated based on the extracted keywords.

[1261] Input: User's question

[1262] Data processing: Natural language processing, keyword extraction, search query generation.

[1263] Output: Search query

[1264] Step 6: Search the integrated database

[1265] server:

[1266] The generated search query is used to search the integrated database and retrieve relevant information.

[1267] Execute a SELECT statement against the database and retrieve the corresponding records.

[1268] Input: Search query

[1269] Data processing: Executing queries and retrieving results

[1270] Output: Acquired information

[1271] Step 7: Emotional Analysis and Solution Generation

[1272] server:

[1273] Based on the acquired information, an emotion engine is used to determine the user's emotional state from the question text they entered.

[1274] The analysis results from the emotion engine and the acquired information are passed to a generative artificial intelligence system to generate an appropriate answer.

[1275] For example, if it's determined that the user is in a hurry, it will generate a quick and concise response.

[1276] Input: Information obtained, user's question

[1277] Data processing: Sentiment analysis, answer generation

[1278] Output: Generated solution

[1279] Step 8: Providing the answer

[1280] server:

[1281] The generated answer is sent to the user's terminal.

[1282] Input: Generated answer

[1283] Data processing: Submitting the answer

[1284] Output: Answer sent to the user's terminal

[1285] Terminal:

[1286] The received answers will be displayed in the chat window.

[1287] For example, it might display, "The latest legal review history is as follows."

[1288] Input: Answer sent from the server

[1289] Data processing: Displaying the answer

[1290] Output: Answer displayed in the chat window

[1291] (Application Example 2)

[1292] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1293] Conventional database management systems have made it difficult for users to quickly and accurately retrieve necessary information from vast amounts of internal company data. Furthermore, because they do not take into account the user's emotions or circumstances, their effectiveness in improving user satisfaction and convenience is limited. This invention aims to solve these problems and improve user satisfaction by enabling users to quickly and appropriately retrieve information and providing personalized responses that correspond to their emotional state.

[1294] The specific processing performed by the specific 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 periodically collecting data from various internal data sources, means for converting the collected data into an appropriate format and storing it in an integrated database, means for users to input questions in chat format through a terminal, means for analyzing the received questions using natural language processing and generating search queries, means for obtaining relevant information from the integrated database based on the generated search queries, means for analyzing the emotional state of the question entered by the user using an emotion engine, means for generating answers using generative artificial intelligence based on the acquired information and the analysis results from the emotion engine, and means for sending and displaying the generated answers on the user terminal. This makes it possible to provide quick and appropriate answers that take into account the user's emotional state when a user asks a question in chat format through a terminal.

[1295] "Various internal data sources" refers to the sources of various data managed within a company, including, for example, manual management systems, legal verification history databases, and departmental performance management systems.

[1296] "Means of collecting data periodically" refers to a mechanism for automatically collecting data at regular time intervals, and in practice, this often involves using API requests or database queries.

[1297] "Means of converting data into an appropriate format and storing it in an integrated database" refers to a mechanism that converts collected data into a unified format (e.g., JSON format), adds metadata (source, date, category, etc.), and then stores it in an integrated database.

[1298] "A means for users to input questions in a chat format via a device" refers to an interface that allows users to input questions in natural language using any device (e.g., smartphone, PC).

[1299] "A means of analyzing received questions using natural language processing and generating search queries" refers to a mechanism that analyzes user-inputted questions using natural language processing techniques such as morphological analysis, extracts important keywords and context, and generates search queries.

[1300] "Means of obtaining relevant information from an integrated database" refers to a mechanism that searches for and retrieves the relevant data from an integrated database based on the generated search query.

[1301] An "emotion engine" refers to a system that analyzes the user's inputted questions and determines their emotional state (e.g., anger, joy, confusion, etc.).

[1302] "Generative artificial intelligence" refers to artificial intelligence technology that generates the most optimal answer for the user based on acquired information and analysis results from an emotion engine.

[1303] "Means of sending and displaying answers on the user's terminal" refers to a mechanism that sends the generated answers to the user's terminal and displays them on an interface such as a chat window.

[1304] This invention relates to a system that generates personalized answers, including sentiment analysis, to questions entered by users through a terminal. This system collects data from internal data sources, stores it in an integrated database, analyzes user questions using natural language processing and sentiment analysis, and provides answers using generative artificial intelligence.

[1305] Overall system configuration

[1306] This system consists of the following main components:

[1307] 1. Server:

[1308] We regularly collect data from various internal data sources, convert it to an appropriate format, and store it in an integrated database.

[1309] The system receives questions from users, analyzes them using natural language processing (NLP) techniques, and generates search queries.

[1310] Relevant information is retrieved from the integrated database, and the emotion engine analyzes the user's emotional state.

[1311] Using generative artificial intelligence, the system generates an answer based on acquired information and sentiment analysis results, and sends it to the user's terminal.

[1312] 2. User terminal:

[1313] It provides an interface where users can input questions in a chat format. This works on smartphones, PCs, and head-mounted displays (HMDs).

[1314] The received answers will be displayed in the chat window.

[1315] Hardware and software to be used

[1316] 1. Server:

[1317] Data Collection: Data is collected periodically from various internal data sources (e.g., manual management system, legal review history) using automated scripts. The software used includes API request libraries (e.g., Python's requests) and database query libraries (e.g., SQLAlchemy).

[1318] Data conversion and storage: Convert data into a unified format such as JSON, add metadata, and store it in an integrated database (e.g., MySQL, PostgreSQL).

[1319] Natural Language Processing (NLP): Analyzes user questions and generates search queries. The software used is an NLP library (e.g., spaCy, NLTK).

[1320] Sentiment Analysis: Analyzes the emotional state of the question using an emotion engine. Sentiment analysis APIs (e.g., IBM Watson, AWS Comprehend) are used.

[1321] Generative artificial intelligence: Generates answers based on acquired information and sentiment analysis results. The software used is a generative artificial intelligence library (e.g., OpenAI GPT-3).

[1322] 2. User terminal:

[1323] This includes smartphones, PCs, and head-mounted displays (HMDs). Users input natural language questions through these devices and receive answers from the server in real time.

[1324] Specific example

[1325] The user puts on an HMD (Head-Mounted Display) and accesses a virtual store. They input a question to the virtual assistant via voice or text, such as "Please tell me about the warranty for this product." After receiving the question, the server analyzes it using NLP (Neuro-Linguistic Programming) technology and retrieves relevant information from an integrated database. Next, an emotion engine analyzes the user's emotional state, and generative artificial intelligence (AI) generates an appropriate response. The tone and content of the response change according to the emotional state, and the result is sent to the user's terminal and displayed on the terminal.

[1326] Example of a prompt

[1327] As a concrete example of its use, here is an example of a prompt in response to a question asked by the user:

[1328] User's question: "Please tell me about the warranty for this product."

[1329] Sentiment analysis result: "In a hurry"

[1330] Generate the answer:

[1331] The warranty details are as follows:

[1332] Thus, the present invention aims to improve the user experience by taking into account the user's emotional state and providing quick and appropriate answers.

[1333] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1334] Step 1:

[1335] The server periodically collects data from various internal data sources. Specifically, it uses automated scripts to execute API requests and database queries to retrieve the latest data. The input is data from the data sources, and the output is the collected raw data.

[1336] Step 2:

[1337] The server converts the collected data into an appropriate format and stores it in an integrated database. Specifically, it converts the data into a unified format such as JSON and adds metadata (source, date, category, etc.). The input is the collected raw data, and the output is data in a unified format.

[1338] Step 3:

[1339] Users enter questions in a chat format via their devices. Specifically, users input questions using natural language via smartphones or PCs. The input is the user's question text, and the output is the transmission of the question from the device to the server.

[1340] Step 4:

[1341] The terminal sends the received question to the server. The question is sent to the server in real time and is ready for analysis. The input is the user's question, and the output is the question sent to the server.

[1342] Step 5:

[1343] The server analyzes the received question using natural language processing (NLP) and generates a search query. Specifically, it performs morphological analysis to extract important keywords and context. The input is the user's question, and the output is the generated search query.

[1344] Step 6:

[1345] The server uses the generated search query to search the integrated database and retrieve relevant information. Specifically, it issues a query to the database and searches for the corresponding record. The input is the search query, and the output is the retrieved information.

[1346] Step 7:

[1347] The server inputs the acquired information into the emotion engine and analyzes the emotional state of the user's question. Specifically, it evaluates the emotion based on the tone and specific wording of the question. The input is the user's question and acquired information, and the output is the emotion analysis result.

[1348] Step 8:

[1349] The server generates answers using generative artificial intelligence based on the acquired information and the results of the emotion engine's analysis. Specifically, it uses a generative AI library to create answers with a tone and content appropriate to the emotional state. The input is the acquired information and the emotion analysis results, and the output is the generated answer.

[1350] Step 9:

[1351] The server sends the generated answer to the user's terminal, which then displays it in the chat window. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[1352] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1353] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1354] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1355] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1356] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1357] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1358] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1359] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1360] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1361] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1362] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1363] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1364] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1365] 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.

[1366] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1367] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1368] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1369] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1370] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1371] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1372] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1373] The following is further disclosed regarding the embodiments described above.

[1374] (Claim 1)

[1375] A means of regularly collecting data from various internal data sources,

[1376] A means of converting the collected data into an appropriate format and storing it in an integrated database,

[1377] A means for users to input questions in a chat format via their device,

[1378] A means for analyzing received questions using natural language processing and generating search queries,

[1379] A means of retrieving relevant information from an integrated database based on the generated search query,

[1380] A means of generating an answer using generative artificial intelligence based on acquired information,

[1381] A means of sending the generated answer to the user's terminal and displaying it,

[1382] A system that includes this.

[1383] (Claim 2)

[1384] The system according to claim 1, comprising a means for generating an answer to an input question using a generative artificial intelligence.

[1385] (Claim 3)

[1386] The system according to claim 1, comprising means for analyzing a user's question using natural language processing.

[1387] The above is the draft of the proposed patent claims.

[1388] "Example 1"

[1389] (Claim 1)

[1390] A method by which the server periodically executes automated scripts to collect data from various internal data sources,

[1391] A method for converting data collected by a server into JSON format or similar, adding metadata, and storing it in an integrated database,

[1392] A means by which a user enters a question via a chat interface through a device, and the device sends that question to a server,

[1393] A means by which a server analyzes received questions using natural language processing, extracts important keywords, and generates search queries,

[1394] Based on that search query, the server has a means of retrieving relevant information from the integrated database,

[1395] A means of inputting information acquired by a server into a generative artificial intelligence and generating an answer in natural language format,

[1396] A means for sending the generated answer to the user's terminal and for the terminal to display the answer on the chat interface,

[1397] A system that includes this.

[1398] (Claim 2)

[1399] The system according to claim 1, wherein the generative artificial intelligence is equipped with means for generating an optimal answer based on acquired information.

[1400] (Claim 3)

[1401] The system according to claim 1, comprising means for analyzing a user's question using natural language processing and extracting important keywords and context.

[1402] "Application Example 1"

[1403] (Claim 1)

[1404] A means of regularly collecting data from various internal data sources,

[1405] A means of converting the collected data into an appropriate format and storing it in an integrated database,

[1406] A means for users to input questions in a chat format via their device,

[1407] A means for analyzing received questions using natural language processing and generating search queries,

[1408] A means of retrieving relevant information from an integrated database based on the generated search query,

[1409] A means of generating an answer using generative artificial intelligence based on acquired information,

[1410] A means for generating detailed answers to user questions using an AI model,

[1411] A means of sending the generated answer to the user's terminal and displaying it,

[1412] A means of automatically collecting data from various sensors and systems within the factory and storing it in an integrated database,

[1413] A system that includes this.

[1414] (Claim 2)

[1415] The system according to claim 1, comprising a means for generating an answer to an input question using a generative artificial intelligence.

[1416] (Claim 3)

[1417] The system according to claim 1, comprising means for analyzing a user's question using natural language processing.

[1418] "Example 2 of combining an emotion engine"

[1419] (Claim 1)

[1420] A means of regularly collecting data from various internal data sources,

[1421] A means of converting the collected data into an appropriate format and storing it in an integrated database,

[1422] A means for users to input questions in a chat format via their device,

[1423] A means for analyzing received questions using natural language processing and generating search queries,

[1424] A means of retrieving relevant information from an integrated database based on the generated search query,

[1425] A means for generating an answer using generative artificial intelligence based on acquired information and the user's emotional state,

[1426] A means of sending the generated answer to the user's terminal and displaying it,

[1427] A system that includes this.

[1428] (Claim 2)

[1429] The system according to claim 1, comprising means for analyzing a question entered by a user and determining their emotional state.

[1430] (Claim 3)

[1431] The system according to claim 1, comprising a generative artificial intelligence system that provides means for generating answers with appropriate tone and content according to the user's emotional state.

[1432] "Application example 2 when combining with an emotional engine"

[1433] (Claim 1)

[1434] A means of regularly collecting data from various internal data sources,

[1435] A means of converting the collected data into an appropriate format and storing it in an integrated database,

[1436] A means for users to input questions in a chat format via their device,

[1437] A means for analyzing received questions using natural language processing and generating search queries,

[1438] A means of retrieving relevant information from an integrated database based on the generated search query,

[1439] A means of analyzing the emotional state of a user-inputted question using an emotion engine,

[1440] A means of generating an answer using generative artificial intelligence based on acquired information and analysis results from an emotion engine,

[1441] A means of sending the generated answer to the user's terminal and displaying it,

[1442] A system that includes this.

[1443] (Claim 2)

[1444] The system according to claim 1, comprising a means for a generative artificial intelligence to generate an answer based on an input question and the result of sentiment analysis.

[1445] (Claim 3)

[1446] The system according to claim 1, comprising means for analyzing a user's question using natural language processing and means for determining an emotional state using an emotion engine. [Explanation of Symbols]

[1447] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of regularly collecting data from various internal data sources, A means of converting the collected data into an appropriate format and storing it in an integrated database, A means for users to input questions in a chat format via their device, A means for analyzing received questions using natural language processing and generating search queries, A means of retrieving relevant information from an integrated database based on the generated search query, A means of generating an answer using generative artificial intelligence based on acquired information, A means of sending the generated answer to the user's terminal and displaying it, A system that includes this.

2. The system according to claim 1, comprising a means for generating an answer to an input question using a generative artificial intelligence.

3. The system according to claim 1, comprising means for analyzing a user's question using natural language processing. The above is the draft of the proposed patent claims.

Images