System

Abstract

To provide a system for supporting smooth execution of business by providing quick and accurate explanation to a word which a new member does not know in daily business.SOLUTION: When a document including in-house information is uploaded, the specific processing unit 290 of the data processing system 12 in the system analyzes the uploaded document to extract terms and definitions, stores the extracted terms and definitions in the database, receives a query about terms from the user, searches the database based on the received keyword, generates an explanation using the generative AI model based on the retrieval result, and provides the generated explanation to the user.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

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

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

[0004] When new members join a department and encounter unfamiliar words in their daily work, there is a lack of a way to quickly and accurately understand their meaning. The traditional method of manually creating glossaries tends to delay the addition of new terms and the updating of existing terms, hindering the progress of work. Furthermore, individually searching for information scattered throughout internal documents takes time, placing a significant burden on new members. This situation makes it difficult to quickly understand work tasks and subsequently improve work efficiency. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, a means for uploading various documents, including internal company information, is provided. Next, a means for analyzing the uploaded documents, extracting terms and definitions, and storing them in a database is provided. Furthermore, a means for accepting queries about terms from users is provided, and a means for searching the database based on the accepted keywords is provided. A means for generating explanations using a generative AI model based on the search results is provided. Finally, a means for providing the generated explanations to the user is provided, creating an environment in which the user can quickly and accurately understand the meaning of terms.

[0006] In this way, the present invention constructs a system that provides quick and accurate explanations for words that new members do not understand in their daily work, thereby supporting the smooth execution of work.

[0007] "Internal information" refers to internal documents and data created within a company or organization and related to the performance of business.

[0008] "Document" refers to data in paper or electronic file format that contains specific information or data.

[0009] "Upload" refers to the act of a user transferring a file in a local environment to a server via a network.

[0010] "Parsing" refers to the process of extracting specific information from uploaded documents and converting that information into an understandable form.

[0011] "Terminology" refers to specialized words and expressions used in a particular field or business.

[0012] A "definition" is an explanation that elaborates and clarifies the meaning or content of a particular term or concept.

[0013] A "database" refers to a system for efficiently storing, retrieving, and updating information.

[0014] "User" refers to an individual or member of an organization who uses the System.

[0015] An "inquiry" refers to an action in which a user requests specific information or explanation from the system.

[0016] "Keywords" refer to terms or phrases that are central to a user's inquiry.

[0017] "Search" refers to the process of finding information that meets specific criteria from a database or other source of information.

[0018] A "generative AI model" refers to an algorithm or program that uses artificial intelligence techniques to generate text content.

[0019] "Explanation" refers to documents or information that provide detailed explanations of specific terms or concepts.

[0020] "Providing" refers to the act of presenting or distributing the generated information or commentary to users. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they do not understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries.

[0043] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0044] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify and manage information scattered across multiple documents.

[0045] When a user comes across a term they don't understand during work, they enter that term into the system's inquiry screen and submit it. The terminal sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[0046] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for users to understand. The generative AI model has previously studied internal company documents and is able to create appropriate explanations that fit the context.

[0047] The generated explanation is sent from the server to the terminal and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time.

[0048] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document," and provides it to the user.

[0049] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[0053] Step 2:

[0054] The terminal sends the selected document file to the server using an HTTP POST request.

[0055] Step 3:

[0056] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[0057] Step 4:

[0058] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[0059] Step 5:

[0060] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[0061] Step 6:

[0062] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[0063] Step 7:

[0064] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID and timestamp.

[0065] Step 8:

[0066] The server searches the database based on the received keywords and obtains related term information.

[0067] Step 9:

[0068] The server inputs the acquired term information into a generative AI model that generates appropriate explanations. This generative AI model has been trained in advance from internal company documents.

[0069] Step 10:

[0070] The server formats the generated commentary and sends it to the user's terminal as an HTTP response.

[0071] Step 11:

[0072] The terminal displays the received explanatory text on the user's inquiry screen, allowing the user to check the necessary information.

[0073] Example 1

[0074] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0075] New members joining the company have difficulty obtaining quick and accurate explanations for terms they don't understand while working, resulting in reduced work efficiency. Manually maintaining glossaries also requires a lot of man-hours, and the information tends to become outdated. To solve these issues, a system is needed that can efficiently provide explanations of terms and keep the information up to date.

[0076] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0077] In this invention, the server includes: a means for uploading documents containing internal company information; a means for analyzing the uploaded documents to extract terms and definitions; a means for storing the extracted terms and definitions in a database; a means for accepting user inquiries about terms; a means for searching the database based on the accepted terms; a means for using a generative AI model to generate explanations based on the search results; a means for providing the generated explanations to the user; a means for automatically extracting important terms and definitions from documents using an analysis engine; and a means for generating explanations by sending prompts to the generative AI model. This allows for quick resolution of questions raised by new members and improves work efficiency. It also reduces the labor required for manual glossary maintenance and creates an environment where the latest information is always provided.

[0078] "Documents" are electronic data such as text files or PDF files that contain internal company information.

[0079] A "server" is a computer system that accepts requests from users, processes documents, searches databases, and generates explanations using generative AI models.

[0080] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0081] A "user" is someone who uses the system to upload documents or request explanations of terms.

[0082] "Upload" is an operation in which a user sends a document to a server through a terminal.

[0083] An "analysis engine" is software that analyzes uploaded documents and automatically extracts terms and definitions.

[0084] "Terms" are words or phrases that are considered particularly important in a document.

[0085] A "definition" is the meaning or explanation of a term.

[0086] A "database" is a data storage system for storing extracted terms and definitions and making them searchable.

[0087] An "inquiry" is an operation in which a user requests the system to explain a term that they do not understand.

[0088] A "generative AI model" is an artificial intelligence software model that generates easy-to-understand explanations for users based on the information it receives.

[0089] A "prompt sentence" is an instruction sentence input to a generative AI model to generate an explanation.

[0090] "Explanation" is the meaning or explanation of a term generated by the generative AI model based on the prompt sentence.

[0091] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations of terms they do not understand during work. This system is built around a server and has multiple related functions.

[0092] Hardware and software used

[0093] Hardware

[0094] Server: A high-performance computer (e.g., Amazon EC2)

[0095] Device: The individual device used by the user (e.g., PC, tablet, smartphone)

[0096] software

[0097] Analysis engine: Natural language processing tools for analyzing internal documents (examples include Python's NLTK and SpaCy)

[0098] Database: A data storage system (e.g., MySQL, PostgreSQL)

[0099] Generative AI model: An artificial intelligence model that generates explanations (example: OpenAI's GPT-3)

[0100] Web application: Software for providing a user interface (e.g., React, Django)

[0101] Detailed System Description

[0102] In this system, users first upload internal documents (such as specifications and design documents) to a server using their terminals. The server receives and stores these documents. This storage process typically uses cloud storage such as Amazon S3.

[0103] The server passes the saved documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. The server then stores the extracted terms and definitions in a database, which uses an RDBMS such as MySQL or PostgreSQL.

[0104] When a user has a question about a particular term, they enter the term into the inquiry screen and submit it. The device then sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[0105] Next, the server sends a prompt to the generative AI model based on the acquired information to generate an explanation. For example, the prompt might read, "Please explain what an API is. Please provide an easy-to-understand explanation based on internal company documents." The generative AI model generates a detailed explanation based on this prompt.

[0106] The generated explanations are sent from the server to the terminal and displayed on the user's screen, allowing the user to quickly resolve their questions and improve work efficiency.

[0107] Specific examples

[0108] Consider a case where a user asks, "What is an API?" The user uses a device to enter the term "API" into the query screen and submits it. The device then sends this information to the server. The server searches the database, obtains the meaning of "API," and sends the following prompt to the generative AI model:

[0109] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[0110] The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. Our company's API for the XX project is described in Chapter 3 of the basic design document," and sends this information to the user's device. As a result, the user can quickly resolve their question.

[0111] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1:

[0114] Document upload

[0115] A user uses a terminal to upload an internal document (e.g., a specification or design document) to a server. In this process, the user selects the specified file and clicks the upload button. The uploaded document is sent from the terminal to the server as an HTTP POST request. The server saves the received document in a specific folder. The input is the document file selected by the user, and the output is the document file saved on the server.

[0116] Step 2:

[0117] Document Analysis

[0118] The server passes the stored documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. This analysis is performed using natural language processing tools such as Python's NLTK or SpaCy. The server passes the document files to the analysis engine as input, and receives a list of extracted terms and definitions as output.

[0119] Step 3:

[0120] Saving to a database

[0121] The server stores the extracted terms and definitions in a database, which is typically an RDBMS such as MySQL or PostgreSQL. The server takes the analysis results as input and stores them in the appropriate tables in the database. The output is a record of the newly stored terms and definitions in the database.

[0122] Step 4:

[0123] User-submitted term searches

[0124] When a user has a question about a particular term, they enter that term into a query screen and submit it. The device sends this input to the server as an HTTP POST request. The input is the term entered by the user, and the output is the search query sent from the device to the server.

[0125] Step 5:

[0126] Database search

[0127] The server searches the database based on the received terms to retrieve related definitions and information. The server receives the terms sent by the user as input and searches the database based on them. The output is the retrieved data of the terms and their definitions.

[0128] Step 6:

[0129] Explanation generation using generative AI models

[0130] The server sends a prompt to the generative AI model based on the acquired information and generates an explanation. Specifically, the server sends the following prompt to the generative AI model:

[0131] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[0132] A generative AI model (e.g., OpenAI's GPT-3) generates an explanation based on this prompt. The input is the prompt and the obtained term definition, and the output is the generated explanation.

[0133] Step 7:

[0134] Providing user explanations

[0135] The generated explanation is sent from the server to the terminal and displayed on the user's screen. The server receives the generated explanation as input and sends it to the terminal as an HTTP response. The output is an explanation displayed on the user's terminal. The user can check this explanation on the screen and quickly resolve their questions.

[0136] (Application example 1)

[0137] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0138] New factory members and operators often encounter unfamiliar terms and operating procedures during their work, which reduces work efficiency by forcing them to refer to manuals or ask questions of their seniors. A system that can quickly and efficiently solve these problems is needed.

[0139] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0140] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on search results, means for providing the generated explanations to users, and means for providing explanations to operators in real time using smart glasses or a robot. This allows new members and operators to quickly and accurately obtain information about unknown terms and operating procedures during work, improving work efficiency.

[0141] "Internal information" is a general term for documents and data generated within a company, and refers to information necessary for carrying out business.

[0142] "Documents" refers to documents such as materials, reports, and manuals created within a company.

[0143] "Upload" refers to the action of a user sending data from a local device to a server.

[0144] "Analysis" refers to the process of mechanically reading the contents of uploaded documents and extracting specific information or patterns.

[0145] "Terminology" refers to specialized language used in a particular field or industry.

[0146] A "definition" refers to text or information that explains the meaning, content, or nature of a term.

[0147] A "database" refers to a system that is constructed to enable efficient search and management of collected and organized information.

[0148] A "generative AI model" refers to an algorithm or system that uses machine learning or artificial intelligence techniques to automatically generate an appropriate response or commentary for a given input.

[0149] "Smart glasses" refers to a wearable device that integrates the real world with digital information by displaying information in front of the eyes.

[0150] A "robot" refers to a mechanical device that operates autonomously based on a program and performs specific tasks.

[0151] An "operator" refers to an employee in charge of operating and managing machinery in a factory or other facility.

[0152] "Real time" refers to a time state in which information processing and responses are immediate and without delay.

[0153] The present invention is a system that enables new factory members and operators to quickly and accurately obtain information on unfamiliar terms and operating procedures in real time while working in a factory. This system is installed in smart glasses or a robot and supports the operator's understanding. Detailed embodiments of this system are described below.

[0154] System Configuration

[0155] 1. Upload function:

[0156] Users use their own devices to upload internal documents (such as requirements definition documents and basic design documents) to the server, where they are stored.

[0157] 2. Data analysis and storage:

[0158] The server has a means of analyzing the uploaded documents. This analysis automatically extracts important terms and their definitions. The extracted terms and definitions are stored in a database, where the necessary information is organized and managed.

[0159] 3. Query acceptance and search:

[0160] When a user encounters a term they do not understand during work, they can input the term into the system through smart glasses or a robot. The input query is accepted by the server and a search is performed against the database.

[0161] 4. Description generation:

[0162] The server uses a generative AI model to automatically generate easy-to-understand explanations for users from search results. The generative AI model has previously studied internal documents and provides appropriate explanations tailored to the context.

[0163] 5. Information provision:

[0164] The generated explanations are sent from the server to smart glasses or a robot and displayed to the user in real time, allowing the user to quickly obtain the information they need while working.

[0165] Hardware and software used

[0166] Hardware:

[0167] Smart glasses (e.g. Google Glass)

[0168] Robots (e.g., autonomous mobile robots that respond to user questions)

[0169] server

[0170] End user's operating device (PC or smartphone)

[0171] software:

[0172] Analysis engine (for document analysis)

[0173] Database System

[0174] Generative AI models (e.g., GPT-2, Transformers library)

[0175] API server for query reception and search (e.g. Flask)

[0176] Specific examples

[0177] For example, if a new operator joins a factory and asks, "What is a PLC?", the server responds using the following procedure.

[0178] 1. The operator inputs "What is PLC" through the smart glasses.

[0179] 2. The server accepts this query and searches the database to get the definition of "PLC".

[0180] 3. Based on the definition, the generative AI model generates an explanation such as, "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[0181] 4. This commentary is displayed in real time on the smart glasses, allowing the operator to get the information instantly.

[0182] Example prompt sentence:

[0183] What is PLC?

[0184] It stands for programmable logic controller, a device used for factory automation.

[0185] Please explain in more detail.

[0186] This allows operators to instantly obtain the information they need without wasting time, improving work efficiency. It also aggregates the knowledge of engineers and promotes knowledge sharing across the entire company.

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] Users use their own devices to upload internal documents to the server. Specifically, they select documents such as requirements specifications and basic design documents and upload them via an interface for sending them to the server. This operation transfers the document data from the device's local storage to the server's storage.

[0190] Input: Internal documents (e.g., requirements definition documents and basic design documents)

[0191] Output: Document data stored in the server storage

[0192] Step 2:

[0193] The server analyzes the uploaded document. This analysis is the process of automatically extracting important terms and their definitions from the document. The analysis engine scans the document and uses specific algorithms to identify terms and their definitions. The server then stores this extracted data in a database.

[0194] Input: Document data stored on the server

[0195] Output: Terms and their definitions stored in the database

[0196] Step 3:

[0197] The user uses smart glasses or a robot to query the system about terms. Specifically, the user inputs terms that the system does not understand through the interface of the smart glasses or the robot. This input data is sent to the server.

[0198] Input: A term entered by the user (e.g., "What is a PLC?")

[0199] Output: Query data sent to the server

[0200] Step 4:

[0201] The server searches the database based on the received keywords. First, it receives the query data and searches the database for matching terms and related information. The search results include the definition of the term and related information.

[0202] Input: Query data sent to the server

[0203] Output: Definition of the term and related information retrieved from the database

[0204] Step 5:

[0205] The server uses a generative AI model to generate explanations based on the search results. Specifically, the definitions of the retrieved terms are input into the generative AI model as prompt sentences, and based on these, an explanation that is easy for the user to understand is automatically generated. The generative AI model has previously studied the contents of internal documents, and provides appropriate explanations according to the context.

[0206] Input: Term definition and related information retrieved from the database

[0207] Output: Generated description

[0208] Step 6:

[0209] The server then sends the generated commentary to the user's smart glasses or robot, which displays the commentary in real time on the smart glasses or robot's display, allowing the user to instantly check the information they need.

[0210] Input: Generated commentary

[0211] Output: Explanation displayed on smart glasses or robot

[0212] As a specific example of operation, if an operator asks "What is a PLC?", the system will operate as follows:

[0213] In step 1, the operator enters "What is PLC" through the smart glasses.

[0214] In step 3, the query is sent to the server, and in step 4, a database search is performed.

[0215] In step 5, the generative AI model generates an explanation: "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[0216] In step 6, the explanation will be displayed on the smart glasses.

[0217] Example prompt sentence:

[0218] What is PLC?

[0219] It stands for programmable logic controller, a device used for factory automation.

[0220] Please explain in more detail.

[0221] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0222] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they don't understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations it provides in a more appropriate manner.

[0223] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0224] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to manage information scattered across multiple documents in a unified manner.

[0225] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[0226] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[0227] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for the user to understand. This generative AI model has been trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[0228] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[0229] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the model will try to use more concise and easy-to-understand language.

[0230] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[0231] The processing flow will be explained below.

[0232] Step 1:

[0233] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[0234] Step 2:

[0235] The terminal sends the selected document file to the server using an HTTP POST request.

[0236] Step 3:

[0237] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[0238] Step 4:

[0239] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[0240] Step 5:

[0241] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[0242] Step 6:

[0243] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[0244] Step 7:

[0245] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID, timestamp, and emotional data based on keystrokes and clicks during input.

[0246] Step 8:

[0247] The server analyzes the received keywords and emotion data and retrieves related term information from a database.

[0248] Step 9:

[0249] The server inputs the acquired term information into a generative AI model to generate appropriate explanations. The generative AI model has previously trained on internal company documents. It also takes into account the user's emotional data and selects a tone and expression that matches the user's psychological state.

[0250] Step 10:

[0251] The server formats the generated description and sends it to the user's device as an HTTP response, which may also include additional information such as recommended next actions.

[0252] Step 11:

[0253] The device displays the received commentary on the inquiry screen, allowing the user to confirm the displayed commentary and deepen their understanding.

[0254] Example 2

[0255] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0256] It was difficult for new members of a department to quickly and accurately obtain explanations for unfamiliar terms and technical terms in their daily work. Conventional systems were unable to take into account the user's emotional state, resulting in inappropriate tone and content of explanations. This resulted in problems that reduced user satisfaction and work efficiency.

[0257] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0258] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for saving the extracted terms and definitions in a database, means for using an emotion engine to analyze user interactions and extract emotional states, means for accepting queries about terms from users, means for searching the database based on the accepted keywords and the user's emotional state, means for using a generative AI model to generate explanations based on the search results and the user's emotional state, and means for providing the generated explanations to users. This makes it possible to quickly resolve questions that new members have, improve work efficiency, and provide more appropriate and easy-to-understand explanations by taking the user's emotional state into consideration.

[0259] "Internal information" refers to various documents and data managed within a company.

[0260] "Document" refers to a record such as a text file, report, manual, or other document that describes specific information.

[0261] "Upload" refers to the operation of transferring data from a terminal to a server.

[0262] "Analysis" refers to the process of analyzing documents and data using specialized techniques to extract information.

[0263] "Extraction" refers to extracting specific information or features from data.

[0264] "Terminology" refers to specific words and expressions used in a particular business or field of expertise.

[0265] A "definition" refers to a clear explanation of the meaning or content of a particular term or concept.

[0266] "Database" refers to an information system that stores data in an organized manner and enables efficient access and management.

[0267] An "emotion engine" refers to a system that analyzes a user's interaction data to determine their emotional state at that time.

[0268] "User" refers to a person who uses the system.

[0269] "Interaction" refers to the actions and communications between a user and a system.

[0270] "Inquiry" refers to the act of a user requesting specific information or explanation from the system.

[0271] "Keywords" refer to the main words or phrases used in a search or inquiry.

[0272] "Generative AI models" refer to algorithms or systems that use artificial intelligence techniques to generate new text or information.

[0273] "Explanation" refers to text that provides detailed explanations of specific terms or concepts.

[0274] "Tone" refers to the expression of emotion or attitude in text or speech.

[0275] MODE FOR CARRYING OUT THE INVENTION

[0276] This invention provides a system that allows new members to quickly and accurately obtain explanations for terms they do not understand in their daily work. This system analyzes documents containing internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations in a more appropriate manner.

[0277] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0278] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine (e.g., an NLP engine) to extract important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify the management of information scattered across multiple documents.

[0279] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[0280] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[0281] Based on the acquired information, a generative AI model (e.g., GPT-3 or BERT model) is prepared. The server uses this generative AI model to generate term explanations in a format that is easy for the user to understand. This generative AI model is trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[0282] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[0283] Examples:

[0284] For example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the master design document." If the user is feeling stressed, the model strives to use more concise and easy-to-understand language. For example, the explanation might be, "API is the rules for communication between software programs. Detailed information about the XX project can be found in Chapter 3 of the master design document."

[0285] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[0286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0287] Step 1:

[0288] The user starts up the terminal and opens the system's upload screen. An upload button is displayed as an input. Using this button, the user selects an internal document such as a requirements specification document or a basic design document, and clicks the upload button.

[0289] Specifically, the terminal sends the selected document data to the server, and the server stores the received document in a specific directory. As an output, the document data is stored in the server.

[0290] Step 2:

[0291] The server detects new documents in a specified directory. It takes the stored document data as input. The server invokes an analysis engine (e.g., an NLP engine) to extract key terms and their definitions from the document.

[0292] As a specific operation, the extracted terms and definitions are stored in a database by the server. As an output, the data of the terms and definitions is stored in a database.

[0293] Step 3:

[0294] The device sends user interactions such as keystrokes and clicks to the emotion engine. The input is the user's operation data. The emotion engine analyzes the operation data and determines the user's emotional state (e.g., stress, excitement, calm, etc.).

[0295] In particular, the emotional information is sent from the terminal to the server and stored in the user profile. As an output, the user's emotional state data is stored in the server.

[0296] Step 4:

[0297] The user opens the system's inquiry screen, enters the term they do not understand, and clicks the send button. The input includes the query term. The device then sends the entered term and the user's emotional state to the server.

[0298] Specifically, the server searches the database based on the received terms and emotional state to obtain relevant definitions and information, and the output is the search results.

[0299] Step 5:

[0300] The server uses a generative AI model (e.g., GPT-3 or BERT model) to generate an explanation based on the search results and the user's emotional state. The inputs are search result data and emotional state data. The generative AI model generates an easy-to-understand explanation based on this data.

[0301] As a specific operation, the generated commentary is transmitted to the terminal by the server, and the generated commentary data is obtained as an output.

[0302] Step 6:

[0303] The terminal displays the explanation received from the server on the user's screen. The generated explanation data is used as input. The user checks the displayed explanation and obtains the necessary information.

[0304] Specifically, the user can check the explanation on the screen, and the user can obtain information as an output.

[0305] (Application example 2)

[0306] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0307] New members and operators joining factories need to be able to quickly and accurately understand unfamiliar terms and operating procedures. However, with conventional systems, searching for terms and procedures takes time, which reduces factory efficiency. Furthermore, information is not provided in accordance with the user's emotional state, which can cause stress and confusion.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0309] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on the search results, means for providing the generated explanations to users, means for combining with an emotion analysis engine that recognizes the emotional state of the user, and means for customizing the content of the explanations according to the emotional state. This enables new members and operators to quickly and accurately understand unfamiliar terms and operating procedures, and makes it possible to provide appropriate information according to their emotional state.

[0310] "Internal information" refers to data and documents generated or held within a company, including business instructions, manuals, reports, etc.

[0311] "Document upload means" refers to a function or device that allows a user to transfer and store digital documents in their possession in the system.

[0312] "Document Analysis Measures" means software or algorithms used to automatically extract key terms and their definitions from uploaded documents.

[0313] A "database" is a computer system or collection of structured data that systematically stores extracted terms, definitions, and related information and manages them in a searchable format.

[0314] "Terminology inquiry means" refers to an interface or function that allows a user to input questions about unknown terms or operating procedures and make inquiries to the system.

[0315] A "generative AI model" is an artificial intelligence algorithm or machine learning model that generates appropriate explanations or information based on input information.

[0316] An "emotion analysis engine" is software or algorithms that analyze and determine a user's emotional state (e.g., stress, excitement, calmness, etc.) at that time based on their input or actions.

[0317] The "explanation customization means" refers to a method or function for providing the generated explanation content in an optimal form according to the emotional state of the user.

[0318] To implement the present invention, the following elements and process steps are required.

[0319] Program Generation

[0320] First, as a means of uploading documents containing internal company information, users can transfer factory operation manuals and design documents to the system. The terminal receives the documents from the user and sends them to the server.

[0321] The server then analyzes the uploaded document, using a document analysis engine (e.g., OpenNLP or SpaCy) to automatically extract important terms and definitions from the document, and stores this extracted information in a database.

[0322] When a user encounters a term or operation procedure they do not understand during work, they can enter the term or question into the system's inquiry screen from their terminal and submit it. The terminal then sends this input to the server. At the same time, the user's emotional state (e.g., stressed, calm, excited, etc.) is also collected and analyzed by an emotion analysis engine (e.g., NLTK, TextBlob).

[0323] The server searches a database based on the received terms to retrieve relevant information. It then uses generative AI models (e.g., Hugging Face Transformers) to explain the information in a way that is easy for the user to understand. This explanation is customized to take into account the user's emotional state. For example, if the user is feeling stressed, the explanation will be more concise and easy to understand.

[0324] The generated explanations are sent from the server to the terminal and displayed on the user's screen in real time, allowing the user to quickly and accurately resolve any questions.

[0325] Specific examples of implementation

[0326] For example, if a new operator in a factory asks, "What is an API?", the server searches the database and extracts relevant information. The generative AI model then generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. In our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the system can use more concise and easy-to-understand language.

[0327] An example of a real prompt:

[0328] Analyze the following passage and save the key terms and their definitions: Sentence: "The operating manual provides detailed instructions for how to operate the robot..."

[0329]

[0330] Generate concise and easy-to-understand API descriptions to help users feel stressed. Terminology: "API"

[0331] In this way, the present invention can quickly resolve questions raised by new members and operators in the factory, thereby improving work efficiency.

[0332] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0333] Step 1:

[0334] Users use an operation panel or tablet device to upload documents containing internal information such as factory operation manuals and design documents to the system. The input is a digital document (PDF, DOCX, etc.), and the output is document data transferred to the server. This data is saved on the server by the document uploading means.

[0335] Step 2:

[0336] The server passes the uploaded document to an analysis engine (e.g., OpenNLP or SpaCy) to extract important terms and definitions. The input is the stored document data, and the output is the extracted terms and their definitions. This data is extracted and processed by the document analysis tool and stored in a database.

[0337] Step 3:

[0338] Users can enter questions about unfamiliar terms or operating procedures during work and send them from the inquiry screen on their terminal. The input is the keywords or questions entered by the user, and the output is the inquiry data sent to the server.

[0339] Step 4:

[0340] The device also collects the user's emotional state (e.g., stress, calm, excitement, etc.) and analyzes it using an emotion analysis engine (e.g., NLTK, TextBlob). The input is the user's keystrokes and clicks, and the output is the analyzed emotional state. This emotional data is also sent to the server.

[0341] Step 5:

[0342] The server searches the database based on the received query data to obtain related information. The input is keywords or questions, and the output is related information. The search process is performed by the database search means.

[0343] Step 6:

[0344] The server uses a generative AI model (e.g., Hugging Face Transformers) to generate a commentary based on the acquired information. The input is the relevant information and the user's emotional state, and the output is a customized commentary. The generative AI model generates text based on the prompts, providing a commentary with a tone and content that matches the user's emotions.

[0345] Step 7:

[0346] The server sends the generated explanation to the terminal and displays it on the user's screen. The input is the customized explanation, and the output is the explanation text displayed on the terminal, allowing the user to quickly resolve any questions.

[0347] This series of processes improves the work efficiency of new members and operators joining the factory, and enables the provision of information that takes into account the emotional state of the user.

[0348] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0349] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0350] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0351] [Second embodiment]

[0352] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0353] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0354] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0355] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0356] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0357] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0358] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0359] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0360] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0361] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0362] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0363] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0364] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they do not understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries.

[0365] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0366] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify and manage information scattered across multiple documents.

[0367] When a user comes across a term they don't understand during work, they enter that term into the system's inquiry screen and submit it. The terminal sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[0368] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for users to understand. The generative AI model has previously studied internal company documents and is able to create appropriate explanations that fit the context.

[0369] The generated explanation is sent from the server to the terminal and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time.

[0370] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document," and provides it to the user.

[0371] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[0372] The processing flow will be explained below.

[0373] Step 1:

[0374] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[0375] Step 2:

[0376] The terminal sends the selected document file to the server using an HTTP POST request.

[0377] Step 3:

[0378] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[0379] Step 4:

[0380] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[0381] Step 5:

[0382] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[0383] Step 6:

[0384] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[0385] Step 7:

[0386] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID and timestamp.

[0387] Step 8:

[0388] The server searches the database based on the received keywords and obtains related term information.

[0389] Step 9:

[0390] The server inputs the acquired term information into a generative AI model that generates appropriate explanations. This generative AI model has been trained in advance from internal company documents.

[0391] Step 10:

[0392] The server formats the generated commentary and sends it to the user's terminal as an HTTP response.

[0393] Step 11:

[0394] The terminal displays the received explanatory text on the user's inquiry screen, allowing the user to check the necessary information.

[0395] Example 1

[0396] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0397] New members joining the company have difficulty obtaining quick and accurate explanations for terms they don't understand while working, resulting in reduced work efficiency. Manually maintaining glossaries also requires a lot of man-hours, and the information tends to become outdated. To solve these issues, a system is needed that can efficiently provide explanations of terms and keep the information up to date.

[0398] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0399] In this invention, the server includes: a means for uploading documents containing internal company information; a means for analyzing the uploaded documents to extract terms and definitions; a means for storing the extracted terms and definitions in a database; a means for accepting user inquiries about terms; a means for searching the database based on the accepted terms; a means for using a generative AI model to generate explanations based on the search results; a means for providing the generated explanations to the user; a means for automatically extracting important terms and definitions from documents using an analysis engine; and a means for generating explanations by sending prompts to the generative AI model. This allows for quick resolution of questions raised by new members and improves work efficiency. It also reduces the labor required for manual glossary maintenance and creates an environment where the latest information is always provided.

[0400] "Documents" are electronic data such as text files or PDF files that contain internal company information.

[0401] A "server" is a computer system that accepts requests from users, processes documents, searches databases, and generates explanations using generative AI models.

[0402] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0403] A "user" is someone who uses the system to upload documents or request explanations of terms.

[0404] "Upload" is an operation in which a user sends a document to a server through a terminal.

[0405] An "analysis engine" is software that analyzes uploaded documents and automatically extracts terms and definitions.

[0406] "Terms" are words or phrases that are considered particularly important in a document.

[0407] A "definition" is the meaning or explanation of a term.

[0408] A "database" is a data storage system for storing extracted terms and definitions and making them searchable.

[0409] An "inquiry" is an operation in which a user requests the system to explain a term that they do not understand.

[0410] A "generative AI model" is an artificial intelligence software model that generates easy-to-understand explanations for users based on the information it receives.

[0411] A "prompt sentence" is an instruction sentence input to a generative AI model to generate an explanation.

[0412] "Explanation" is the meaning or explanation of a term generated by the generative AI model based on the prompt sentence.

[0413] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations of terms they do not understand during work. This system is built around a server and has multiple related functions.

[0414] Hardware and software used

[0415] Hardware

[0416] Server: A high-performance computer (e.g., Amazon EC2)

[0417] Device: The individual device used by the user (e.g., PC, tablet, smartphone)

[0418] software

[0419] Analysis engine: Natural language processing tools for analyzing internal documents (examples include Python's NLTK and SpaCy)

[0420] Database: A data storage system (e.g., MySQL, PostgreSQL)

[0421] Generative AI model: An artificial intelligence model that generates explanations (example: OpenAI's GPT-3)

[0422] Web application: Software for providing a user interface (e.g., React, Django)

[0423] Detailed System Description

[0424] In this system, users first upload internal documents (such as specifications and design documents) to a server using their terminals. The server receives and stores these documents. This storage process typically uses cloud storage such as Amazon S3.

[0425] The server passes the saved documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. The server then stores the extracted terms and definitions in a database, which uses an RDBMS such as MySQL or PostgreSQL.

[0426] When a user has a question about a particular term, they enter the term into the inquiry screen and submit it. The device then sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[0427] Next, the server sends a prompt to the generative AI model based on the acquired information to generate an explanation. For example, the prompt might read, "Please explain what an API is. Please provide an easy-to-understand explanation based on internal company documents." The generative AI model generates a detailed explanation based on this prompt.

[0428] The generated explanations are sent from the server to the terminal and displayed on the user's screen, allowing the user to quickly resolve their questions and improve work efficiency.

[0429] Specific examples

[0430] Consider a case where a user asks, "What is an API?" The user uses a device to enter the term "API" into the query screen and submits it. The device then sends this information to the server. The server searches the database, obtains the meaning of "API," and sends the following prompt to the generative AI model:

[0431] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[0432] The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. Our company's API for the XX project is described in Chapter 3 of the basic design document," and sends this information to the user's device. As a result, the user can quickly resolve their question.

[0433] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[0434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] Document upload

[0437] A user uses a terminal to upload an internal document (e.g., a specification or design document) to a server. In this process, the user selects the specified file and clicks the upload button. The uploaded document is sent from the terminal to the server as an HTTP POST request. The server saves the received document in a specific folder. The input is the document file selected by the user, and the output is the document file saved on the server.

[0438] Step 2:

[0439] Document Analysis

[0440] The server passes the stored documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. This analysis is performed using natural language processing tools such as Python's NLTK or SpaCy. The server passes the document files to the analysis engine as input, and receives a list of extracted terms and definitions as output.

[0441] Step 3:

[0442] Saving to a database

[0443] The server stores the extracted terms and definitions in a database, which is typically an RDBMS such as MySQL or PostgreSQL. The server takes the analysis results as input and stores them in the appropriate tables in the database. The output is a record of the newly stored terms and definitions in the database.

[0444] Step 4:

[0445] User-submitted term searches

[0446] When a user has a question about a particular term, they enter that term into a query screen and submit it. The device sends this input to the server as an HTTP POST request. The input is the term entered by the user, and the output is the search query sent from the device to the server.

[0447] Step 5:

[0448] Database search

[0449] The server searches the database based on the received terms to retrieve related definitions and information. The server receives the terms sent by the user as input and searches the database based on them. The output is the retrieved data of the terms and their definitions.

[0450] Step 6:

[0451] Explanation generation using generative AI models

[0452] The server sends a prompt to the generative AI model based on the acquired information and generates an explanation. Specifically, the server sends the following prompt to the generative AI model:

[0453] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[0454] A generative AI model (e.g., OpenAI's GPT-3) generates an explanation based on this prompt. The input is the prompt and the obtained term definition, and the output is the generated explanation.

[0455] Step 7:

[0456] Providing user explanations

[0457] The generated explanation is sent from the server to the terminal and displayed on the user's screen. The server receives the generated explanation as input and sends it to the terminal as an HTTP response. The output is an explanation displayed on the user's terminal. The user can check this explanation on the screen and quickly resolve their questions.

[0458] (Application example 1)

[0459] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0460] New factory members and operators often encounter unfamiliar terms and operating procedures during their work, which reduces work efficiency by forcing them to refer to manuals or ask questions of their seniors. A system that can quickly and efficiently solve these problems is needed.

[0461] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0462] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on search results, means for providing the generated explanations to users, and means for providing explanations to operators in real time using smart glasses or a robot. This allows new members and operators to quickly and accurately obtain information about unknown terms and operating procedures during work, improving work efficiency.

[0463] "Internal information" is a general term for documents and data generated within a company, and refers to information necessary for carrying out business.

[0464] "Documents" refers to documents such as materials, reports, and manuals created within a company.

[0465] "Upload" refers to the action of a user sending data from a local device to a server.

[0466] "Analysis" refers to the process of mechanically reading the contents of uploaded documents and extracting specific information or patterns.

[0467] "Terminology" refers to specialized language used in a particular field or industry.

[0468] A "definition" refers to text or information that explains the meaning, content, or nature of a term.

[0469] A "database" refers to a system that is constructed to enable efficient search and management of collected and organized information.

[0470] A "generative AI model" refers to an algorithm or system that uses machine learning or artificial intelligence techniques to automatically generate an appropriate response or commentary for a given input.

[0471] "Smart glasses" refers to a wearable device that integrates the real world with digital information by displaying information in front of the eyes.

[0472] A "robot" refers to a mechanical device that operates autonomously based on a program and performs specific tasks.

[0473] An "operator" refers to an employee in charge of operating and managing machinery in a factory or other facility.

[0474] "Real time" refers to a time state in which information processing and responses are immediate and without delay.

[0475] The present invention is a system that enables new factory members and operators to quickly and accurately obtain information on unfamiliar terms and operating procedures in real time while working in a factory. This system is installed in smart glasses or a robot and supports the operator's understanding. Detailed embodiments of this system are described below.

[0476] System Configuration

[0477] 1. Upload function:

[0478] Users use their own devices to upload internal documents (such as requirements definition documents and basic design documents) to the server, where they are stored.

[0479] 2. Data analysis and storage:

[0480] The server has a means of analyzing the uploaded documents. This analysis automatically extracts important terms and their definitions. The extracted terms and definitions are stored in a database, where the necessary information is organized and managed.

[0481] 3. Query acceptance and search:

[0482] When a user encounters a term they do not understand during work, they can input the term into the system through smart glasses or a robot. The input query is accepted by the server and a search is performed against the database.

[0483] 4. Description generation:

[0484] The server uses a generative AI model to automatically generate easy-to-understand explanations for users from search results. The generative AI model has previously studied internal documents and provides appropriate explanations tailored to the context.

[0485] 5. Information provision:

[0486] The generated explanations are sent from the server to smart glasses or a robot and displayed to the user in real time, allowing the user to quickly obtain the information they need while working.

[0487] Hardware and software used

[0488] Hardware:

[0489] Smart glasses (e.g. Google Glass)

[0490] Robots (e.g., autonomous mobile robots that respond to user questions)

[0491] server

[0492] End user's operating device (PC or smartphone)

[0493] software:

[0494] Analysis engine (for document analysis)

[0495] Database System

[0496] Generative AI models (e.g., GPT-2, Transformers library)

[0497] API server for query reception and search (e.g. Flask)

[0498] Specific examples

[0499] For example, if a new operator joins a factory and asks, "What is a PLC?", the server responds using the following procedure.

[0500] 1. The operator inputs "What is PLC" through the smart glasses.

[0501] 2. The server accepts this query and searches the database to get the definition of "PLC".

[0502] 3. Based on the definition, the generative AI model generates an explanation such as, "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[0503] 4. This commentary is displayed in real time on the smart glasses, allowing the operator to get the information instantly.

[0504] Example prompt sentence:

[0505] What is PLC?

[0506] It stands for programmable logic controller, a device used for factory automation.

[0507] Please explain in more detail.

[0508] This allows operators to instantly obtain the information they need without wasting time, improving work efficiency. It also aggregates the knowledge of engineers and promotes knowledge sharing across the entire company.

[0509] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0510] Step 1:

[0511] Users use their own devices to upload internal documents to the server. Specifically, they select documents such as requirements specifications and basic design documents and upload them via an interface for sending them to the server. This operation transfers the document data from the device's local storage to the server's storage.

[0512] Input: Internal documents (e.g., requirements definition documents and basic design documents)

[0513] Output: Document data stored in the server storage

[0514] Step 2:

[0515] The server analyzes the uploaded document. This analysis is the process of automatically extracting important terms and their definitions from the document. The analysis engine scans the document and uses specific algorithms to identify terms and their definitions. The server then stores this extracted data in a database.

[0516] Input: Document data stored on the server

[0517] Output: Terms and their definitions stored in the database

[0518] Step 3:

[0519] The user uses smart glasses or a robot to query the system about terms. Specifically, the user inputs terms that the system does not understand through the interface of the smart glasses or the robot. This input data is sent to the server.

[0520] Input: A term entered by the user (e.g., "What is a PLC?")

[0521] Output: Query data sent to the server

[0522] Step 4:

[0523] The server searches the database based on the received keywords. First, it receives the query data and searches the database for matching terms and related information. The search results include the definition of the term and related information.

[0524] Input: Query data sent to the server

[0525] Output: Definition of the term and related information retrieved from the database

[0526] Step 5:

[0527] The server uses a generative AI model to generate explanations based on the search results. Specifically, the definitions of the retrieved terms are input into the generative AI model as prompt sentences, and based on these, an explanation that is easy for the user to understand is automatically generated. The generative AI model has previously studied the contents of internal documents, and provides appropriate explanations according to the context.

[0528] Input: Term definition and related information retrieved from the database

[0529] Output: Generated description

[0530] Step 6:

[0531] The server then sends the generated commentary to the user's smart glasses or robot, which displays the commentary in real time on the smart glasses or robot's display, allowing the user to instantly check the information they need.

[0532] Input: Generated commentary

[0533] Output: Explanation displayed on smart glasses or robot

[0534] As a specific example of operation, if an operator asks "What is a PLC?", the system will operate as follows:

[0535] In step 1, the operator enters "What is PLC" through the smart glasses.

[0536] In step 3, the query is sent to the server, and in step 4, a database search is performed.

[0537] In step 5, the generative AI model generates an explanation: "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[0538] In step 6, the explanation will be displayed on the smart glasses.

[0539] Example prompt sentence:

[0540] What is PLC?

[0541] It stands for programmable logic controller, a device used for factory automation.

[0542] Please explain in more detail.

[0543] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0544] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they don't understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations it provides in a more appropriate manner.

[0545] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0546] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to manage information scattered across multiple documents in a unified manner.

[0547] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[0548] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[0549] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for the user to understand. This generative AI model has been trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[0550] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[0551] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the model will try to use more concise and easy-to-understand language.

[0552] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[0556] Step 2:

[0557] The terminal sends the selected document file to the server using an HTTP POST request.

[0558] Step 3:

[0559] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[0560] Step 4:

[0561] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[0562] Step 5:

[0563] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[0564] Step 6:

[0565] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[0566] Step 7:

[0567] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID, timestamp, and emotional data based on keystrokes and clicks during input.

[0568] Step 8:

[0569] The server analyzes the received keywords and emotion data and retrieves related term information from a database.

[0570] Step 9:

[0571] The server inputs the acquired term information into a generative AI model to generate appropriate explanations. The generative AI model has previously trained on internal company documents. It also takes into account the user's emotional data and selects a tone and expression that matches the user's psychological state.

[0572] Step 10:

[0573] The server formats the generated description and sends it to the user's device as an HTTP response, which may also include additional information such as recommended next actions.

[0574] Step 11:

[0575] The device displays the received commentary on the inquiry screen, allowing the user to confirm the displayed commentary and deepen their understanding.

[0576] Example 2

[0577] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0578] It was difficult for new members of a department to quickly and accurately obtain explanations for unfamiliar terms and technical terms in their daily work. Conventional systems were unable to take into account the user's emotional state, resulting in inappropriate tone and content of explanations. This resulted in problems that reduced user satisfaction and work efficiency.

[0579] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0580] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for saving the extracted terms and definitions in a database, means for using an emotion engine to analyze user interactions and extract emotional states, means for accepting queries about terms from users, means for searching the database based on the accepted keywords and the user's emotional state, means for using a generative AI model to generate explanations based on the search results and the user's emotional state, and means for providing the generated explanations to users. This makes it possible to quickly resolve questions that new members have, improve work efficiency, and provide more appropriate and easy-to-understand explanations by taking the user's emotional state into consideration.

[0581] "Internal information" refers to various documents and data managed within a company.

[0582] "Document" refers to a record such as a text file, report, manual, or other document that describes specific information.

[0583] "Upload" refers to the operation of transferring data from a terminal to a server.

[0584] "Analysis" refers to the process of analyzing documents and data using specialized techniques to extract information.

[0585] "Extraction" refers to extracting specific information or features from data.

[0586] "Terminology" refers to specific words and expressions used in a particular business or field of expertise.

[0587] A "definition" refers to a clear explanation of the meaning or content of a particular term or concept.

[0588] "Database" refers to an information system that stores data in an organized manner and enables efficient access and management.

[0589] An "emotion engine" refers to a system that analyzes a user's interaction data to determine their emotional state at that time.

[0590] "User" refers to a person who uses the system.

[0591] "Interaction" refers to the actions and communications between a user and a system.

[0592] "Inquiry" refers to the act of a user requesting specific information or explanation from the system.

[0593] "Keywords" refer to the main words or phrases used in a search or inquiry.

[0594] "Generative AI models" refer to algorithms or systems that use artificial intelligence techniques to generate new text or information.

[0595] "Explanation" refers to text that provides detailed explanations of specific terms or concepts.

[0596] "Tone" refers to the expression of emotion or attitude in text or speech.

[0597] MODE FOR CARRYING OUT THE INVENTION

[0598] This invention provides a system that allows new members to quickly and accurately obtain explanations for terms they do not understand in their daily work. This system analyzes documents containing internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations in a more appropriate manner.

[0599] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0600] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine (e.g., an NLP engine) to extract important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify the management of information scattered across multiple documents.

[0601] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[0602] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[0603] Based on the acquired information, a generative AI model (e.g., GPT-3 or BERT model) is prepared. The server uses this generative AI model to generate term explanations in a format that is easy for the user to understand. This generative AI model is trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[0604] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[0605] Examples:

[0606] For example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the master design document." If the user is feeling stressed, the model strives to use more concise and easy-to-understand language. For example, the explanation might be, "API is the rules for communication between software programs. Detailed information about the XX project can be found in Chapter 3 of the master design document."

[0607] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[0608] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0609] Step 1:

[0610] The user starts up the terminal and opens the system's upload screen. An upload button is displayed as an input. Using this button, the user selects an internal document such as a requirements specification document or a basic design document, and clicks the upload button.

[0611] Specifically, the terminal sends the selected document data to the server, and the server stores the received document in a specific directory. As an output, the document data is stored in the server.

[0612] Step 2:

[0613] The server detects new documents in a specified directory. It takes the stored document data as input. The server invokes an analysis engine (e.g., an NLP engine) to extract key terms and their definitions from the document.

[0614] As a specific operation, the extracted terms and definitions are stored in a database by the server. As an output, the data of the terms and definitions is stored in a database.

[0615] Step 3:

[0616] The device sends user interactions such as keystrokes and clicks to the emotion engine. The input is the user's operation data. The emotion engine analyzes the operation data and determines the user's emotional state (e.g., stress, excitement, calm, etc.).

[0617] In particular, the emotional information is sent from the terminal to the server and stored in the user profile. As an output, the user's emotional state data is stored in the server.

[0618] Step 4:

[0619] The user opens the system's inquiry screen, enters the term they do not understand, and clicks the send button. The input includes the query term. The device then sends the entered term and the user's emotional state to the server.

[0620] Specifically, the server searches the database based on the received terms and emotional state to obtain relevant definitions and information, and the output is the search results.

[0621] Step 5:

[0622] The server uses a generative AI model (e.g., GPT-3 or BERT model) to generate an explanation based on the search results and the user's emotional state. The inputs are search result data and emotional state data. The generative AI model generates an easy-to-understand explanation based on this data.

[0623] As a specific operation, the generated commentary is transmitted to the terminal by the server, and the generated commentary data is obtained as an output.

[0624] Step 6:

[0625] The terminal displays the explanation received from the server on the user's screen. The generated explanation data is used as input. The user checks the displayed explanation and obtains the necessary information.

[0626] Specifically, the user can check the explanation on the screen, and the user can obtain information as an output.

[0627] (Application example 2)

[0628] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0629] New members and operators joining factories need to be able to quickly and accurately understand unfamiliar terms and operating procedures. However, with conventional systems, searching for terms and procedures takes time, which reduces factory efficiency. Furthermore, information is not provided in accordance with the user's emotional state, which can cause stress and confusion.

[0630] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0631] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on the search results, means for providing the generated explanations to users, means for combining with an emotion analysis engine that recognizes the emotional state of the user, and means for customizing the content of the explanations according to the emotional state. This enables new members and operators to quickly and accurately understand unfamiliar terms and operating procedures, and makes it possible to provide appropriate information according to their emotional state.

[0632] "Internal information" refers to data and documents generated or held within a company, including business instructions, manuals, reports, etc.

[0633] "Document upload means" refers to a function or device that allows a user to transfer and store digital documents in their possession in the system.

[0634] "Document Analysis Measures" means software or algorithms used to automatically extract key terms and their definitions from uploaded documents.

[0635] A "database" is a computer system or collection of structured data that systematically stores extracted terms, definitions, and related information and manages them in a searchable format.

[0636] "Terminology inquiry means" refers to an interface or function that allows a user to input questions about unknown terms or operating procedures and make inquiries to the system.

[0637] A "generative AI model" is an artificial intelligence algorithm or machine learning model that generates appropriate explanations or information based on input information.

[0638] An "emotion analysis engine" is software or algorithms that analyze and determine a user's emotional state (e.g., stress, excitement, calmness, etc.) at that time based on their input or actions.

[0639] The "explanation customization means" refers to a method or function for providing the generated explanation content in an optimal form according to the emotional state of the user.

[0640] To implement the present invention, the following elements and process steps are required.

[0641] Program Generation

[0642] First, as a means of uploading documents containing internal company information, users can transfer factory operation manuals and design documents to the system. The terminal receives the documents from the user and sends them to the server.

[0643] The server then analyzes the uploaded document, using a document analysis engine (e.g., OpenNLP or SpaCy) to automatically extract important terms and definitions from the document, and stores this extracted information in a database.

[0644] When a user encounters a term or operation procedure they do not understand during work, they can enter the term or question into the system's inquiry screen from their terminal and submit it. The terminal then sends this input to the server. At the same time, the user's emotional state (e.g., stressed, calm, excited, etc.) is also collected and analyzed by an emotion analysis engine (e.g., NLTK, TextBlob).

[0645] The server searches a database based on the received terms to retrieve relevant information. It then uses generative AI models (e.g., Hugging Face Transformers) to explain the information in a way that is easy for the user to understand. This explanation is customized to take into account the user's emotional state. For example, if the user is feeling stressed, the explanation will be more concise and easy to understand.

[0646] The generated explanations are sent from the server to the terminal and displayed on the user's screen in real time, allowing the user to quickly and accurately resolve any questions.

[0647] Specific examples of implementation

[0648] For example, if a new operator in a factory asks, "What is an API?", the server searches the database and extracts relevant information. The generative AI model then generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. In our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the system can use more concise and easy-to-understand language.

[0649] An example of a real prompt:

[0650] Analyze the following passage and save the key terms and their definitions: Sentence: "The operating manual provides detailed instructions for how to operate the robot..."

[0651]

[0652] Generate concise and easy-to-understand API descriptions to help users feel stressed. Terminology: "API"

[0653] In this way, the present invention can quickly resolve questions raised by new members and operators in the factory, thereby improving work efficiency.

[0654] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0655] Step 1:

[0656] Users use an operation panel or tablet device to upload documents containing internal information such as factory operation manuals and design documents to the system. The input is a digital document (PDF, DOCX, etc.), and the output is document data transferred to the server. This data is saved on the server by the document uploading means.

[0657] Step 2:

[0658] The server passes the uploaded document to an analysis engine (e.g., OpenNLP or SpaCy) to extract important terms and definitions. The input is the stored document data, and the output is the extracted terms and their definitions. This data is extracted and processed by the document analysis tool and stored in a database.

[0659] Step 3:

[0660] Users can enter questions about unfamiliar terms or operating procedures during work and send them from the inquiry screen on their terminal. The input is the keywords or questions entered by the user, and the output is the inquiry data sent to the server.

[0661] Step 4:

[0662] The device also collects the user's emotional state (e.g., stress, calm, excitement, etc.) and analyzes it using an emotion analysis engine (e.g., NLTK, TextBlob). The input is the user's keystrokes and clicks, and the output is the analyzed emotional state. This emotional data is also sent to the server.

[0663] Step 5:

[0664] The server searches the database based on the received query data to obtain related information. The input is keywords or questions, and the output is related information. The search process is performed by the database search means.

[0665] Step 6:

[0666] The server uses a generative AI model (e.g., Hugging Face Transformers) to generate a commentary based on the acquired information. The input is the relevant information and the user's emotional state, and the output is a customized commentary. The generative AI model generates text based on the prompts, providing a commentary with a tone and content that matches the user's emotions.

[0667] Step 7:

[0668] The server sends the generated explanation to the terminal and displays it on the user's screen. The input is the customized explanation, and the output is the explanation text displayed on the terminal, allowing the user to quickly resolve any questions.

[0669] This series of processes improves the work efficiency of new members and operators joining the factory, and enables the provision of information that takes into account the emotional state of the user.

[0670] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0671] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0672] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0673] [Third embodiment]

[0674] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0675] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0676] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0677] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0678] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0679] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0680] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0681] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0682] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0683] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0684] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0685] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0686] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they do not understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries.

[0687] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0688] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify and manage information scattered across multiple documents.

[0689] When a user comes across a term they don't understand during work, they enter that term into the system's inquiry screen and submit it. The terminal sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[0690] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for users to understand. The generative AI model has previously studied internal company documents and is able to create appropriate explanations that fit the context.

[0691] The generated explanation is sent from the server to the terminal and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time.

[0692] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document," and provides it to the user.

[0693] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[0694] The processing flow will be explained below.

[0695] Step 1:

[0696] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[0697] Step 2:

[0698] The terminal sends the selected document file to the server using an HTTP POST request.

[0699] Step 3:

[0700] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[0701] Step 4:

[0702] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[0703] Step 5:

[0704] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[0705] Step 6:

[0706] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[0707] Step 7:

[0708] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID and timestamp.

[0709] Step 8:

[0710] The server searches the database based on the received keywords and obtains related term information.

[0711] Step 9:

[0712] The server inputs the acquired term information into a generative AI model that generates appropriate explanations. This generative AI model has been trained in advance from internal company documents.

[0713] Step 10:

[0714] The server formats the generated commentary and sends it to the user's terminal as an HTTP response.

[0715] Step 11:

[0716] The terminal displays the received explanatory text on the user's inquiry screen, allowing the user to check the necessary information.

[0717] Example 1

[0718] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0719] New members joining the company have difficulty obtaining quick and accurate explanations for terms they don't understand while working, resulting in reduced work efficiency. Manually maintaining glossaries also requires a lot of man-hours, and the information tends to become outdated. To solve these issues, a system is needed that can efficiently provide explanations of terms and keep the information up to date.

[0720] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0721] In this invention, the server includes: a means for uploading documents containing internal company information; a means for analyzing the uploaded documents to extract terms and definitions; a means for storing the extracted terms and definitions in a database; a means for accepting user inquiries about terms; a means for searching the database based on the accepted terms; a means for using a generative AI model to generate explanations based on the search results; a means for providing the generated explanations to the user; a means for automatically extracting important terms and definitions from documents using an analysis engine; and a means for generating explanations by sending prompts to the generative AI model. This allows for quick resolution of questions raised by new members and improves work efficiency. It also reduces the labor required for manual glossary maintenance and creates an environment where the latest information is always provided.

[0722] "Documents" are electronic data such as text files or PDF files that contain internal company information.

[0723] A "server" is a computer system that accepts requests from users, processes documents, searches databases, and generates explanations using generative AI models.

[0724] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0725] A "user" is someone who uses the system to upload documents or request explanations of terms.

[0726] "Upload" is an operation in which a user sends a document to a server through a terminal.

[0727] An "analysis engine" is software that analyzes uploaded documents and automatically extracts terms and definitions.

[0728] "Terms" are words or phrases that are considered particularly important in a document.

[0729] A "definition" is the meaning or explanation of a term.

[0730] A "database" is a data storage system for storing extracted terms and definitions and making them searchable.

[0731] An "inquiry" is an operation in which a user requests the system to explain a term that they do not understand.

[0732] A "generative AI model" is an artificial intelligence software model that generates easy-to-understand explanations for users based on the information it receives.

[0733] A "prompt sentence" is an instruction sentence input to a generative AI model to generate an explanation.

[0734] "Explanation" is the meaning or explanation of a term generated by the generative AI model based on the prompt sentence.

[0735] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations of terms they do not understand during work. This system is built around a server and has multiple related functions.

[0736] Hardware and software used

[0737] Hardware

[0738] Server: A high-performance computer (e.g., Amazon EC2)

[0739] Device: The individual device used by the user (e.g., PC, tablet, smartphone)

[0740] software

[0741] Analysis engine: Natural language processing tools for analyzing internal documents (examples include Python's NLTK and SpaCy)

[0742] Database: A data storage system (e.g., MySQL, PostgreSQL)

[0743] Generative AI model: An artificial intelligence model that generates explanations (example: OpenAI's GPT-3)

[0744] Web application: Software for providing a user interface (e.g., React, Django)

[0745] Detailed System Description

[0746] In this system, users first upload internal documents (such as specifications and design documents) to a server using their terminals. The server receives and stores these documents. This storage process typically uses cloud storage such as Amazon S3.

[0747] The server passes the saved documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. The server then stores the extracted terms and definitions in a database, which uses an RDBMS such as MySQL or PostgreSQL.

[0748] When a user has a question about a particular term, they enter the term into the inquiry screen and submit it. The device then sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[0749] Next, the server sends a prompt to the generative AI model based on the acquired information to generate an explanation. For example, the prompt might read, "Please explain what an API is. Please provide an easy-to-understand explanation based on internal company documents." The generative AI model generates a detailed explanation based on this prompt.

[0750] The generated explanations are sent from the server to the terminal and displayed on the user's screen, allowing the user to quickly resolve their questions and improve work efficiency.

[0751] Specific examples

[0752] Consider a case where a user asks, "What is an API?" The user uses a device to enter the term "API" into the query screen and submits it. The device then sends this information to the server. The server searches the database, obtains the meaning of "API," and sends the following prompt to the generative AI model:

[0753] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[0754] The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. Our company's API for the XX project is described in Chapter 3 of the basic design document," and sends this information to the user's device. As a result, the user can quickly resolve their question.

[0755] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[0756] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0757] Step 1:

[0758] Document upload

[0759] A user uses a terminal to upload an internal document (e.g., a specification or design document) to a server. In this process, the user selects the specified file and clicks the upload button. The uploaded document is sent from the terminal to the server as an HTTP POST request. The server saves the received document in a specific folder. The input is the document file selected by the user, and the output is the document file saved on the server.

[0760] Step 2:

[0761] Document Analysis

[0762] The server passes the stored documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. This analysis is performed using natural language processing tools such as Python's NLTK or SpaCy. The server passes the document files to the analysis engine as input, and receives a list of extracted terms and definitions as output.

[0763] Step 3:

[0764] Saving to a database

[0765] The server stores the extracted terms and definitions in a database, which is typically an RDBMS such as MySQL or PostgreSQL. The server takes the analysis results as input and stores them in the appropriate tables in the database. The output is a record of the newly stored terms and definitions in the database.

[0766] Step 4:

[0767] User-submitted term searches

[0768] When a user has a question about a particular term, they enter that term into a query screen and submit it. The device sends this input to the server as an HTTP POST request. The input is the term entered by the user, and the output is the search query sent from the device to the server.

[0769] Step 5:

[0770] Database search

[0771] The server searches the database based on the received terms to retrieve related definitions and information. The server receives the terms sent by the user as input and searches the database based on them. The output is the retrieved data of the terms and their definitions.

[0772] Step 6:

[0773] Explanation generation using generative AI models

[0774] The server sends a prompt to the generative AI model based on the acquired information and generates an explanation. Specifically, the server sends the following prompt to the generative AI model:

[0775] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[0776] A generative AI model (e.g., OpenAI's GPT-3) generates an explanation based on this prompt. The input is the prompt and the obtained term definition, and the output is the generated explanation.

[0777] Step 7:

[0778] Providing user explanations

[0779] The generated explanation is sent from the server to the terminal and displayed on the user's screen. The server receives the generated explanation as input and sends it to the terminal as an HTTP response. The output is an explanation displayed on the user's terminal. The user can check this explanation on the screen and quickly resolve their questions.

[0780] (Application example 1)

[0781] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0782] New factory members and operators often encounter unfamiliar terms and operating procedures during their work, which reduces work efficiency by forcing them to refer to manuals or ask questions of their seniors. A system that can quickly and efficiently solve these problems is needed.

[0783] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0784] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on search results, means for providing the generated explanations to users, and means for providing explanations to operators in real time using smart glasses or a robot. This allows new members and operators to quickly and accurately obtain information about unknown terms and operating procedures during work, improving work efficiency.

[0785] "Internal information" is a general term for documents and data generated within a company, and refers to information necessary for carrying out business.

[0786] "Documents" refers to documents such as materials, reports, and manuals created within a company.

[0787] "Upload" refers to the action of a user sending data from a local device to a server.

[0788] "Analysis" refers to the process of mechanically reading the contents of uploaded documents and extracting specific information or patterns.

[0789] "Terminology" refers to specialized language used in a particular field or industry.

[0790] A "definition" refers to text or information that explains the meaning, content, or nature of a term.

[0791] A "database" refers to a system that is constructed to enable efficient search and management of collected and organized information.

[0792] A "generative AI model" refers to an algorithm or system that uses machine learning or artificial intelligence techniques to automatically generate an appropriate response or commentary for a given input.

[0793] "Smart glasses" refers to a wearable device that integrates the real world with digital information by displaying information in front of the eyes.

[0794] A "robot" refers to a mechanical device that operates autonomously based on a program and performs specific tasks.

[0795] An "operator" refers to an employee in charge of operating and managing machinery in a factory or other facility.

[0796] "Real time" refers to a time state in which information processing and responses are immediate and without delay.

[0797] The present invention is a system that enables new factory members and operators to quickly and accurately obtain information on unfamiliar terms and operating procedures in real time while working in a factory. This system is installed in smart glasses or a robot and supports the operator's understanding. Detailed embodiments of this system are described below.

[0798] System Configuration

[0799] 1. Upload function:

[0800] Users use their own devices to upload internal documents (such as requirements definition documents and basic design documents) to the server, where they are stored.

[0801] 2. Data analysis and storage:

[0802] The server has a means of analyzing the uploaded documents. This analysis automatically extracts important terms and their definitions. The extracted terms and definitions are stored in a database, where the necessary information is organized and managed.

[0803] 3. Query acceptance and search:

[0804] When a user encounters a term they do not understand during work, they can input the term into the system through smart glasses or a robot. The input query is accepted by the server and a search is performed against the database.

[0805] 4. Description generation:

[0806] The server uses a generative AI model to automatically generate easy-to-understand explanations for users from search results. The generative AI model has previously studied internal documents and provides appropriate explanations tailored to the context.

[0807] 5. Information provision:

[0808] The generated explanations are sent from the server to smart glasses or a robot and displayed to the user in real time, allowing the user to quickly obtain the information they need while working.

[0809] Hardware and software used

[0810] Hardware:

[0811] Smart glasses (e.g. Google Glass)

[0812] Robots (e.g., autonomous mobile robots that respond to user questions)

[0813] server

[0814] End user's operating device (PC or smartphone)

[0815] software:

[0816] Analysis engine (for document analysis)

[0817] Database System

[0818] Generative AI models (e.g., GPT-2, Transformers library)

[0819] API server for query reception and search (e.g. Flask)

[0820] Specific examples

[0821] For example, if a new operator joins a factory and asks, "What is a PLC?", the server responds using the following procedure.

[0822] 1. The operator inputs "What is PLC" through the smart glasses.

[0823] 2. The server accepts this query and searches the database to get the definition of "PLC".

[0824] 3. Based on the definition, the generative AI model generates an explanation such as, "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[0825] 4. This commentary is displayed in real time on the smart glasses, allowing the operator to get the information instantly.

[0826] Example prompt sentence:

[0827] What is PLC?

[0828] It stands for programmable logic controller, a device used for factory automation.

[0829] Please explain in more detail.

[0830] This allows operators to instantly obtain the information they need without wasting time, improving work efficiency. It also aggregates the knowledge of engineers and promotes knowledge sharing across the entire company.

[0831] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0832] Step 1:

[0833] Users use their own devices to upload internal documents to the server. Specifically, they select documents such as requirements specifications and basic design documents and upload them via an interface for sending them to the server. This operation transfers the document data from the device's local storage to the server's storage.

[0834] Input: Internal documents (e.g., requirements definition documents and basic design documents)

[0835] Output: Document data stored in the server storage

[0836] Step 2:

[0837] The server analyzes the uploaded document. This analysis is the process of automatically extracting important terms and their definitions from the document. The analysis engine scans the document and uses specific algorithms to identify terms and their definitions. The server then stores this extracted data in a database.

[0838] Input: Document data stored on the server

[0839] Output: Terms and their definitions stored in the database

[0840] Step 3:

[0841] The user uses smart glasses or a robot to query the system about terms. Specifically, the user inputs terms that the system does not understand through the interface of the smart glasses or the robot. This input data is sent to the server.

[0842] Input: A term entered by the user (e.g., "What is a PLC?")

[0843] Output: Query data sent to the server

[0844] Step 4:

[0845] The server searches the database based on the received keywords. First, it receives the query data and searches the database for matching terms and related information. The search results include the definition of the term and related information.

[0846] Input: Query data sent to the server

[0847] Output: Definition of the term and related information retrieved from the database

[0848] Step 5:

[0849] The server uses a generative AI model to generate explanations based on the search results. Specifically, the definitions of the retrieved terms are input into the generative AI model as prompt sentences, and based on these, an explanation that is easy for the user to understand is automatically generated. The generative AI model has previously studied the contents of internal documents, and provides appropriate explanations according to the context.

[0850] Input: Term definition and related information retrieved from the database

[0851] Output: Generated description

[0852] Step 6:

[0853] The server then sends the generated commentary to the user's smart glasses or robot, which displays the commentary in real time on the smart glasses or robot's display, allowing the user to instantly check the information they need.

[0854] Input: Generated commentary

[0855] Output: Explanation displayed on smart glasses or robot

[0856] As a specific example of operation, if an operator asks "What is a PLC?", the system will operate as follows:

[0857] In step 1, the operator enters "What is PLC" through the smart glasses.

[0858] In step 3, the query is sent to the server, and in step 4, a database search is performed.

[0859] In step 5, the generative AI model generates an explanation: "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[0860] In step 6, the explanation will be displayed on the smart glasses.

[0861] Example prompt sentence:

[0862] What is PLC?

[0863] It stands for programmable logic controller, a device used for factory automation.

[0864] Please explain in more detail.

[0865] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0866] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they don't understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations it provides in a more appropriate manner.

[0867] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0868] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to manage information scattered across multiple documents in a unified manner.

[0869] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[0870] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[0871] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for the user to understand. This generative AI model has been trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[0872] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[0873] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the model will try to use more concise and easy-to-understand language.

[0874] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[0875] The processing flow will be explained below.

[0876] Step 1:

[0877] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[0878] Step 2:

[0879] The terminal sends the selected document file to the server using an HTTP POST request.

[0880] Step 3:

[0881] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[0882] Step 4:

[0883] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[0884] Step 5:

[0885] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[0886] Step 6:

[0887] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[0888] Step 7:

[0889] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID, timestamp, and emotional data based on keystrokes and clicks during input.

[0890] Step 8:

[0891] The server analyzes the received keywords and emotion data and retrieves related term information from a database.

[0892] Step 9:

[0893] The server inputs the acquired term information into a generative AI model to generate appropriate explanations. The generative AI model has previously trained on internal company documents. It also takes into account the user's emotional data and selects a tone and expression that matches the user's psychological state.

[0894] Step 10:

[0895] The server formats the generated description and sends it to the user's device as an HTTP response, which may also include additional information such as recommended next actions.

[0896] Step 11:

[0897] The device displays the received commentary on the inquiry screen, allowing the user to confirm the displayed commentary and deepen their understanding.

[0898] Example 2

[0899] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0900] It was difficult for new members of a department to quickly and accurately obtain explanations for unfamiliar terms and technical terms in their daily work. Conventional systems were unable to take into account the user's emotional state, resulting in inappropriate tone and content of explanations. This resulted in problems that reduced user satisfaction and work efficiency.

[0901] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0902] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for saving the extracted terms and definitions in a database, means for using an emotion engine to analyze user interactions and extract emotional states, means for accepting queries about terms from users, means for searching the database based on the accepted keywords and the user's emotional state, means for using a generative AI model to generate explanations based on the search results and the user's emotional state, and means for providing the generated explanations to users. This makes it possible to quickly resolve questions that new members have, improve work efficiency, and provide more appropriate and easy-to-understand explanations by taking the user's emotional state into consideration.

[0903] "Internal information" refers to various documents and data managed within a company.

[0904] "Document" refers to a record such as a text file, report, manual, or other document that describes specific information.

[0905] "Upload" refers to the operation of transferring data from a terminal to a server.

[0906] "Analysis" refers to the process of analyzing documents and data using specialized techniques to extract information.

[0907] "Extraction" refers to extracting specific information or features from data.

[0908] "Terminology" refers to specific words and expressions used in a particular business or field of expertise.

[0909] A "definition" refers to a clear explanation of the meaning or content of a particular term or concept.

[0910] "Database" refers to an information system that stores data in an organized manner and enables efficient access and management.

[0911] An "emotion engine" refers to a system that analyzes a user's interaction data to determine their emotional state at that time.

[0912] "User" refers to a person who uses the system.

[0913] "Interaction" refers to the actions and communications between a user and a system.

[0914] "Inquiry" refers to the act of a user requesting specific information or explanation from the system.

[0915] "Keywords" refer to the main words or phrases used in a search or inquiry.

[0916] "Generative AI models" refer to algorithms or systems that use artificial intelligence techniques to generate new text or information.

[0917] "Explanation" refers to text that provides detailed explanations of specific terms or concepts.

[0918] "Tone" refers to the expression of emotion or attitude in text or speech.

[0919] MODE FOR CARRYING OUT THE INVENTION

[0920] This invention provides a system that allows new members to quickly and accurately obtain explanations for terms they do not understand in their daily work. This system analyzes documents containing internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations in a more appropriate manner.

[0921] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[0922] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine (e.g., an NLP engine) to extract important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify the management of information scattered across multiple documents.

[0923] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[0924] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[0925] Based on the acquired information, a generative AI model (e.g., GPT-3 or BERT model) is prepared. The server uses this generative AI model to generate term explanations in a format that is easy for the user to understand. This generative AI model is trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[0926] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[0927] Examples:

[0928] For example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the master design document." If the user is feeling stressed, the model strives to use more concise and easy-to-understand language. For example, the explanation might be, "API is the rules for communication between software programs. Detailed information about the XX project can be found in Chapter 3 of the master design document."

[0929] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[0930] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0931] Step 1:

[0932] The user starts up the terminal and opens the system's upload screen. An upload button is displayed as an input. Using this button, the user selects an internal document such as a requirements specification document or a basic design document, and clicks the upload button.

[0933] Specifically, the terminal sends the selected document data to the server, and the server stores the received document in a specific directory. As an output, the document data is stored in the server.

[0934] Step 2:

[0935] The server detects new documents in a specified directory. It takes the stored document data as input. The server invokes an analysis engine (e.g., an NLP engine) to extract key terms and their definitions from the document.

[0936] As a specific operation, the extracted terms and definitions are stored in a database by the server. As an output, the data of the terms and definitions is stored in a database.

[0937] Step 3:

[0938] The device sends user interactions such as keystrokes and clicks to the emotion engine. The input is the user's operation data. The emotion engine analyzes the operation data and determines the user's emotional state (e.g., stress, excitement, calm, etc.).

[0939] In particular, the emotional information is sent from the terminal to the server and stored in the user profile. As an output, the user's emotional state data is stored in the server.

[0940] Step 4:

[0941] The user opens the system's inquiry screen, enters the term they do not understand, and clicks the send button. The input includes the query term. The device then sends the entered term and the user's emotional state to the server.

[0942] Specifically, the server searches the database based on the received terms and emotional state to obtain relevant definitions and information, and the output is the search results.

[0943] Step 5:

[0944] The server uses a generative AI model (e.g., GPT-3 or BERT model) to generate an explanation based on the search results and the user's emotional state. The inputs are search result data and emotional state data. The generative AI model generates an easy-to-understand explanation based on this data.

[0945] As a specific operation, the generated commentary is transmitted to the terminal by the server, and the generated commentary data is obtained as an output.

[0946] Step 6:

[0947] The terminal displays the explanation received from the server on the user's screen. The generated explanation data is used as input. The user checks the displayed explanation and obtains the necessary information.

[0948] Specifically, the user can check the explanation on the screen, and the user can obtain information as an output.

[0949] (Application example 2)

[0950] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0951] New members and operators joining factories need to be able to quickly and accurately understand unfamiliar terms and operating procedures. However, with conventional systems, searching for terms and procedures takes time, which reduces factory efficiency. Furthermore, information is not provided in accordance with the user's emotional state, which can cause stress and confusion.

[0952] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0953] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on the search results, means for providing the generated explanations to users, means for combining with an emotion analysis engine that recognizes the emotional state of the user, and means for customizing the content of the explanations according to the emotional state. This enables new members and operators to quickly and accurately understand unfamiliar terms and operating procedures, and makes it possible to provide appropriate information according to their emotional state.

[0954] "Internal information" refers to data and documents generated or held within a company, including business instructions, manuals, reports, etc.

[0955] "Document upload means" refers to a function or device that allows a user to transfer and store digital documents in their possession in the system.

[0956] "Document Analysis Measures" means software or algorithms used to automatically extract key terms and their definitions from uploaded documents.

[0957] A "database" is a computer system or collection of structured data that systematically stores extracted terms, definitions, and related information and manages them in a searchable format.

[0958] "Terminology inquiry means" refers to an interface or function that allows a user to input questions about unknown terms or operating procedures and make inquiries to the system.

[0959] A "generative AI model" is an artificial intelligence algorithm or machine learning model that generates appropriate explanations or information based on input information.

[0960] An "emotion analysis engine" is software or algorithms that analyze and determine a user's emotional state (e.g., stress, excitement, calmness, etc.) at that time based on their input or actions.

[0961] The "explanation customization means" refers to a method or function for providing the generated explanation content in an optimal form according to the emotional state of the user.

[0962] To implement the present invention, the following elements and process steps are required.

[0963] Program Generation

[0964] First, as a means of uploading documents containing internal company information, users can transfer factory operation manuals and design documents to the system. The terminal receives the documents from the user and sends them to the server.

[0965] The server then analyzes the uploaded document, using a document analysis engine (e.g., OpenNLP or SpaCy) to automatically extract important terms and definitions from the document, and stores this extracted information in a database.

[0966] When a user encounters a term or operation procedure they do not understand during work, they can enter the term or question into the system's inquiry screen from their terminal and submit it. The terminal then sends this input to the server. At the same time, the user's emotional state (e.g., stressed, calm, excited, etc.) is also collected and analyzed by an emotion analysis engine (e.g., NLTK, TextBlob).

[0967] The server searches a database based on the received terms to retrieve relevant information. It then uses generative AI models (e.g., Hugging Face Transformers) to explain the information in a way that is easy for the user to understand. This explanation is customized to take into account the user's emotional state. For example, if the user is feeling stressed, the explanation will be more concise and easy to understand.

[0968] The generated explanations are sent from the server to the terminal and displayed on the user's screen in real time, allowing the user to quickly and accurately resolve any questions.

[0969] Specific examples of implementation

[0970] For example, if a new operator in a factory asks, "What is an API?", the server searches the database and extracts relevant information. The generative AI model then generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. In our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the system can use more concise and easy-to-understand language.

[0971] An example of a real prompt:

[0972] Analyze the following passage and save the key terms and their definitions: Sentence: "The operating manual provides detailed instructions for how to operate the robot..."

[0973]

[0974] Generate concise and easy-to-understand API descriptions to help users feel stressed. Terminology: "API"

[0975] In this way, the present invention can quickly resolve questions raised by new members and operators in the factory, thereby improving work efficiency.

[0976] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0977] Step 1:

[0978] Users use an operation panel or tablet device to upload documents containing internal information such as factory operation manuals and design documents to the system. The input is a digital document (PDF, DOCX, etc.), and the output is document data transferred to the server. This data is saved on the server by the document uploading means.

[0979] Step 2:

[0980] The server passes the uploaded document to an analysis engine (e.g., OpenNLP or SpaCy) to extract important terms and definitions. The input is the stored document data, and the output is the extracted terms and their definitions. This data is extracted and processed by the document analysis tool and stored in a database.

[0981] Step 3:

[0982] Users can enter questions about unfamiliar terms or operating procedures during work and send them from the inquiry screen on their terminal. The input is the keywords or questions entered by the user, and the output is the inquiry data sent to the server.

[0983] Step 4:

[0984] The device also collects the user's emotional state (e.g., stress, calm, excitement, etc.) and analyzes it using an emotion analysis engine (e.g., NLTK, TextBlob). The input is the user's keystrokes and clicks, and the output is the analyzed emotional state. This emotional data is also sent to the server.

[0985] Step 5:

[0986] The server searches the database based on the received query data to obtain related information. The input is keywords or questions, and the output is related information. The search process is performed by the database search means.

[0987] Step 6:

[0988] The server uses a generative AI model (e.g., Hugging Face Transformers) to generate a commentary based on the acquired information. The input is the relevant information and the user's emotional state, and the output is a customized commentary. The generative AI model generates text based on the prompts, providing a commentary with a tone and content that matches the user's emotions.

[0989] Step 7:

[0990] The server sends the generated explanation to the terminal and displays it on the user's screen. The input is the customized explanation, and the output is the explanation text displayed on the terminal, allowing the user to quickly resolve any questions.

[0991] This series of processes improves the work efficiency of new members and operators joining the factory, and enables the provision of information that takes into account the emotional state of the user.

[0992] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0993] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0994] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0995] [Fourth embodiment]

[0996] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0997] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0998] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0999] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1000] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1001] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1002] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1003] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1004] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1005] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1006] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1007] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1008] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1009] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they do not understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries.

[1010] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[1011] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify and manage information scattered across multiple documents.

[1012] When a user comes across a term they don't understand during work, they enter that term into the system's inquiry screen and submit it. The terminal sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[1013] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for users to understand. The generative AI model has previously studied internal company documents and is able to create appropriate explanations that fit the context.

[1014] The generated explanation is sent from the server to the terminal and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time.

[1015] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document," and provides it to the user.

[1016] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[1017] The processing flow will be explained below.

[1018] Step 1:

[1019] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[1020] Step 2:

[1021] The terminal sends the selected document file to the server using an HTTP POST request.

[1022] Step 3:

[1023] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[1024] Step 4:

[1025] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[1026] Step 5:

[1027] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[1028] Step 6:

[1029] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[1030] Step 7:

[1031] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID and timestamp.

[1032] Step 8:

[1033] The server searches the database based on the received keywords and obtains related term information.

[1034] Step 9:

[1035] The server inputs the acquired term information into a generative AI model that generates appropriate explanations. This generative AI model has been trained in advance from internal company documents.

[1036] Step 10:

[1037] The server formats the generated commentary and sends it to the user's terminal as an HTTP response.

[1038] Step 11:

[1039] The terminal displays the received explanatory text on the user's inquiry screen, allowing the user to check the necessary information.

[1040] Example 1

[1041] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1042] New members joining the company have difficulty obtaining quick and accurate explanations for terms they don't understand while working, resulting in reduced work efficiency. Manually maintaining glossaries also requires a lot of man-hours, and the information tends to become outdated. To solve these issues, a system is needed that can efficiently provide explanations of terms and keep the information up to date.

[1043] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1044] In this invention, the server includes: a means for uploading documents containing internal company information; a means for analyzing the uploaded documents to extract terms and definitions; a means for storing the extracted terms and definitions in a database; a means for accepting user inquiries about terms; a means for searching the database based on the accepted terms; a means for using a generative AI model to generate explanations based on the search results; a means for providing the generated explanations to the user; a means for automatically extracting important terms and definitions from documents using an analysis engine; and a means for generating explanations by sending prompts to the generative AI model. This allows for quick resolution of questions raised by new members and improves work efficiency. It also reduces the labor required for manual glossary maintenance and creates an environment where the latest information is always provided.

[1045] "Documents" are electronic data such as text files or PDF files that contain internal company information.

[1046] A "server" is a computer system that accepts requests from users, processes documents, searches databases, and generates explanations using generative AI models.

[1047] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[1048] A "user" is someone who uses the system to upload documents or request explanations of terms.

[1049] "Upload" is an operation in which a user sends a document to a server through a terminal.

[1050] An "analysis engine" is software that analyzes uploaded documents and automatically extracts terms and definitions.

[1051] "Terms" are words or phrases that are considered particularly important in a document.

[1052] A "definition" is the meaning or explanation of a term.

[1053] A "database" is a data storage system for storing extracted terms and definitions and making them searchable.

[1054] An "inquiry" is an operation in which a user requests the system to explain a term that they do not understand.

[1055] A "generative AI model" is an artificial intelligence software model that generates easy-to-understand explanations for users based on the information it receives.

[1056] A "prompt sentence" is an instruction sentence input to a generative AI model to generate an explanation.

[1057] "Explanation" is the meaning or explanation of a term generated by the generative AI model based on the prompt sentence.

[1058] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations of terms they do not understand during work. This system is built around a server and has multiple related functions.

[1059] Hardware and software used

[1060] Hardware

[1061] Server: A high-performance computer (e.g., Amazon EC2)

[1062] Device: The individual device used by the user (e.g., PC, tablet, smartphone)

[1063] software

[1064] Analysis engine: Natural language processing tools for analyzing internal documents (examples include Python's NLTK and SpaCy)

[1065] Database: A data storage system (e.g., MySQL, PostgreSQL)

[1066] Generative AI model: An artificial intelligence model that generates explanations (example: OpenAI's GPT-3)

[1067] Web application: Software for providing a user interface (e.g., React, Django)

[1068] Detailed System Description

[1069] In this system, users first upload internal documents (such as specifications and design documents) to a server using their terminals. The server receives and stores these documents. This storage process typically uses cloud storage such as Amazon S3.

[1070] The server passes the saved documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. The server then stores the extracted terms and definitions in a database, which uses an RDBMS such as MySQL or PostgreSQL.

[1071] When a user has a question about a particular term, they enter the term into the inquiry screen and submit it. The device then sends this input to the server, which then searches the database based on the received term to retrieve related definitions and information.

[1072] Next, the server sends a prompt to the generative AI model based on the acquired information to generate an explanation. For example, the prompt might read, "Please explain what an API is. Please provide an easy-to-understand explanation based on internal company documents." The generative AI model generates a detailed explanation based on this prompt.

[1073] The generated explanations are sent from the server to the terminal and displayed on the user's screen, allowing the user to quickly resolve their questions and improve work efficiency.

[1074] Specific examples

[1075] Consider a case where a user asks, "What is an API?" The user uses a device to enter the term "API" into the query screen and submits it. The device then sends this information to the server. The server searches the database, obtains the meaning of "API," and sends the following prompt to the generative AI model:

[1076] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[1077] The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. Our company's API for the XX project is described in Chapter 3 of the basic design document," and sends this information to the user's device. As a result, the user can quickly resolve their question.

[1078] In this way, this system can quickly resolve any questions that new members may have, improving work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always available.

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Step 1:

[1081] Document upload

[1082] A user uses a terminal to upload an internal document (e.g., a specification or design document) to a server. In this process, the user selects the specified file and clicks the upload button. The uploaded document is sent from the terminal to the server as an HTTP POST request. The server saves the received document in a specific folder. The input is the document file selected by the user, and the output is the document file saved on the server.

[1083] Step 2:

[1084] Document Analysis

[1085] The server passes the stored documents to an analysis engine, which analyzes the documents and extracts important terms and their definitions. This analysis is performed using natural language processing tools such as Python's NLTK or SpaCy. The server passes the document files to the analysis engine as input, and receives a list of extracted terms and definitions as output.

[1086] Step 3:

[1087] Saving to a database

[1088] The server stores the extracted terms and definitions in a database, which is typically an RDBMS such as MySQL or PostgreSQL. The server takes the analysis results as input and stores them in the appropriate tables in the database. The output is a record of the newly stored terms and definitions in the database.

[1089] Step 4:

[1090] User-submitted term searches

[1091] When a user has a question about a particular term, they enter that term into a query screen and submit it. The device sends this input to the server as an HTTP POST request. The input is the term entered by the user, and the output is the search query sent from the device to the server.

[1092] Step 5:

[1093] Database search

[1094] The server searches the database based on the received terms to retrieve related definitions and information. The server receives the terms sent by the user as input and searches the database based on them. The output is the retrieved data of the terms and their definitions.

[1095] Step 6:

[1096] Explanation generation using generative AI models

[1097] The server sends a prompt to the generative AI model based on the acquired information and generates an explanation. Specifically, the server sends the following prompt to the generative AI model:

[1098] "Please explain what an API is. Please provide a clear explanation based on our internal documentation."

[1099] A generative AI model (e.g., OpenAI's GPT-3) generates an explanation based on this prompt. The input is the prompt and the obtained term definition, and the output is the generated explanation.

[1100] Step 7:

[1101] Providing user explanations

[1102] The generated explanation is sent from the server to the terminal and displayed on the user's screen. The server receives the generated explanation as input and sends it to the terminal as an HTTP response. The output is an explanation displayed on the user's terminal. The user can check this explanation on the screen and quickly resolve their questions.

[1103] (Application example 1)

[1104] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1105] New factory members and operators often encounter unfamiliar terms and operating procedures during their work, which reduces work efficiency by forcing them to refer to manuals or ask questions of their seniors. A system that can quickly and efficiently solve these problems is needed.

[1106] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1107] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on search results, means for providing the generated explanations to users, and means for providing explanations to operators in real time using smart glasses or a robot. This allows new members and operators to quickly and accurately obtain information about unknown terms and operating procedures during work, improving work efficiency.

[1108] "Internal information" is a general term for documents and data generated within a company, and refers to information necessary for carrying out business.

[1109] "Documents" refers to documents such as materials, reports, and manuals created within a company.

[1110] "Upload" refers to the action of a user sending data from a local device to a server.

[1111] "Analysis" refers to the process of mechanically reading the contents of uploaded documents and extracting specific information or patterns.

[1112] "Terminology" refers to specialized language used in a particular field or industry.

[1113] A "definition" refers to text or information that explains the meaning, content, or nature of a term.

[1114] A "database" refers to a system that is constructed to enable efficient search and management of collected and organized information.

[1115] A "generative AI model" refers to an algorithm or system that uses machine learning or artificial intelligence techniques to automatically generate an appropriate response or commentary for a given input.

[1116] "Smart glasses" refers to a wearable device that integrates the real world with digital information by displaying information in front of the eyes.

[1117] A "robot" refers to a mechanical device that operates autonomously based on a program and performs specific tasks.

[1118] An "operator" refers to an employee in charge of operating and managing machinery in a factory or other facility.

[1119] "Real time" refers to a time state in which information processing and responses are immediate and without delay.

[1120] The present invention is a system that enables new factory members and operators to quickly and accurately obtain information on unfamiliar terms and operating procedures in real time while working in a factory. This system is installed in smart glasses or a robot and supports the operator's understanding. Detailed embodiments of this system are described below.

[1121] System Configuration

[1122] 1. Upload function:

[1123] Users use their own devices to upload internal documents (such as requirements definition documents and basic design documents) to the server, where they are stored.

[1124] 2. Data analysis and storage:

[1125] The server has a means of analyzing the uploaded documents. This analysis automatically extracts important terms and their definitions. The extracted terms and definitions are stored in a database, where the necessary information is organized and managed.

[1126] 3. Query acceptance and search:

[1127] When a user encounters a term they do not understand during work, they can input the term into the system through smart glasses or a robot. The input query is accepted by the server and a search is performed against the database.

[1128] 4. Description generation:

[1129] The server uses a generative AI model to automatically generate easy-to-understand explanations for users from search results. The generative AI model has previously studied internal documents and provides appropriate explanations tailored to the context.

[1130] 5. Information provision:

[1131] The generated explanations are sent from the server to smart glasses or a robot and displayed to the user in real time, allowing the user to quickly obtain the information they need while working.

[1132] Hardware and software used

[1133] Hardware:

[1134] Smart glasses (e.g. Google Glass)

[1135] Robots (e.g., autonomous mobile robots that respond to user questions)

[1136] server

[1137] End user's operating device (PC or smartphone)

[1138] software:

[1139] Analysis engine (for document analysis)

[1140] Database System

[1141] Generative AI models (e.g., GPT-2, Transformers library)

[1142] API server for query reception and search (e.g. Flask)

[1143] Specific examples

[1144] For example, if a new operator joins a factory and asks, "What is a PLC?", the server responds using the following procedure.

[1145] 1. The operator inputs "What is PLC" through the smart glasses.

[1146] 2. The server accepts this query and searches the database to get the definition of "PLC".

[1147] 3. Based on the definition, the generative AI model generates an explanation such as, "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[1148] 4. This commentary is displayed in real time on the smart glasses, allowing the operator to get the information instantly.

[1149] Example prompt sentence:

[1150] What is PLC?

[1151] It stands for programmable logic controller, a device used for factory automation.

[1152] Please explain in more detail.

[1153] This allows operators to instantly obtain the information they need without wasting time, improving work efficiency. It also aggregates the knowledge of engineers and promotes knowledge sharing across the entire company.

[1154] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1155] Step 1:

[1156] Users use their own devices to upload internal documents to the server. Specifically, they select documents such as requirements specifications and basic design documents and upload them via an interface for sending them to the server. This operation transfers the document data from the device's local storage to the server's storage.

[1157] Input: Internal documents (e.g., requirements definition documents and basic design documents)

[1158] Output: Document data stored in the server storage

[1159] Step 2:

[1160] The server analyzes the uploaded document. This analysis is the process of automatically extracting important terms and their definitions from the document. The analysis engine scans the document and uses specific algorithms to identify terms and their definitions. The server then stores this extracted data in a database.

[1161] Input: Document data stored on the server

[1162] Output: Terms and their definitions stored in the database

[1163] Step 3:

[1164] The user uses smart glasses or a robot to query the system about terms. Specifically, the user inputs terms that the system does not understand through the interface of the smart glasses or the robot. This input data is sent to the server.

[1165] Input: A term entered by the user (e.g., "What is a PLC?")

[1166] Output: Query data sent to the server

[1167] Step 4:

[1168] The server searches the database based on the received keywords. First, it receives the query data and searches the database for matching terms and related information. The search results include the definition of the term and related information.

[1169] Input: Query data sent to the server

[1170] Output: Definition of the term and related information retrieved from the database

[1171] Step 5:

[1172] The server uses a generative AI model to generate explanations based on the search results. Specifically, the definitions of the retrieved terms are input into the generative AI model as prompt sentences, and based on these, an explanation that is easy for the user to understand is automatically generated. The generative AI model has previously studied the contents of internal documents, and provides appropriate explanations according to the context.

[1173] Input: Term definition and related information retrieved from the database

[1174] Output: Generated description

[1175] Step 6:

[1176] The server then sends the generated commentary to the user's smart glasses or robot, which displays the commentary in real time on the smart glasses or robot's display, allowing the user to instantly check the information they need.

[1177] Input: Generated commentary

[1178] Output: Explanation displayed on smart glasses or robot

[1179] As a specific example of operation, if an operator asks "What is a PLC?", the system will operate as follows:

[1180] In step 1, the operator enters "What is PLC" through the smart glasses.

[1181] In step 3, the query is sent to the server, and in step 4, a database search is performed.

[1182] In step 5, the generative AI model generates an explanation: "PLC stands for Programmable Logic Controller, a device used for factory automation. Specifically, it is used to operate XXX."

[1183] In step 6, the explanation will be displayed on the smart glasses.

[1184] Example prompt sentence:

[1185] What is PLC?

[1186] It stands for programmable logic controller, a device used for factory automation.

[1187] Please explain in more detail.

[1188] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1189] This invention relates to a system that allows new members of a department to quickly and accurately obtain explanations for words they don't understand in their daily work. This system analyzes various documents, including internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations it provides in a more appropriate manner.

[1190] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[1191] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine, which extracts important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to manage information scattered across multiple documents in a unified manner.

[1192] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[1193] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[1194] A generative AI model is prepared based on the acquired information. The server uses this generative AI model to generate explanations of terms in a format that is easy for the user to understand. This generative AI model has been trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[1195] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[1196] As a concrete example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the model will try to use more concise and easy-to-understand language.

[1197] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The user accesses the in-house portal site from their own device, selects an in-house document such as a requirements specification document or a basic design document, and clicks the upload button.

[1201] Step 2:

[1202] The terminal sends the selected document file to the server using an HTTP POST request.

[1203] Step 3:

[1204] The server stores the received document file in a temporary storage directory and confirms that the storage is complete.

[1205] Step 4:

[1206] The server reads the document file from the storage directory and passes it to the text analysis engine, which analyzes all the text in the document and extracts terms and their definitions.

[1207] Step 5:

[1208] The server stores the terms and their definitions received from the text analysis engine in a database, assigning each term a unique ID and saving it along with related information.

[1209] Step 6:

[1210] When a user encounters a term they do not understand (e.g., "API") during work, they enter the term into the inquiry screen on their device and press the send button.

[1211] Step 7:

[1212] The device sends the keyword entered by the user to the server via an HTTP request, along with the user's ID, timestamp, and emotional data based on keystrokes and clicks during input.

[1213] Step 8:

[1214] The server analyzes the received keywords and emotion data and retrieves related term information from a database.

[1215] Step 9:

[1216] The server inputs the acquired term information into a generative AI model to generate appropriate explanations. The generative AI model has previously trained on internal company documents. It also takes into account the user's emotional data and selects a tone and expression that matches the user's psychological state.

[1217] Step 10:

[1218] The server formats the generated description and sends it to the user's device as an HTTP response, which may also include additional information such as recommended next actions.

[1219] Step 11:

[1220] The device displays the received commentary on the inquiry screen, allowing the user to confirm the displayed commentary and deepen their understanding.

[1221] Example 2

[1222] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1223] It was difficult for new members of a department to quickly and accurately obtain explanations for unfamiliar terms and technical terms in their daily work. Conventional systems were unable to take into account the user's emotional state, resulting in inappropriate tone and content of explanations. This resulted in problems that reduced user satisfaction and work efficiency.

[1224] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1225] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for saving the extracted terms and definitions in a database, means for using an emotion engine to analyze user interactions and extract emotional states, means for accepting queries about terms from users, means for searching the database based on the accepted keywords and the user's emotional state, means for using a generative AI model to generate explanations based on the search results and the user's emotional state, and means for providing the generated explanations to users. This makes it possible to quickly resolve questions that new members have, improve work efficiency, and provide more appropriate and easy-to-understand explanations by taking the user's emotional state into consideration.

[1226] "Internal information" refers to various documents and data managed within a company.

[1227] "Document" refers to a record such as a text file, report, manual, or other document that describes specific information.

[1228] "Upload" refers to the operation of transferring data from a terminal to a server.

[1229] "Analysis" refers to the process of analyzing documents and data using specialized techniques to extract information.

[1230] "Extraction" refers to extracting specific information or features from data.

[1231] "Terminology" refers to specific words and expressions used in a particular business or field of expertise.

[1232] A "definition" refers to a clear explanation of the meaning or content of a particular term or concept.

[1233] "Database" refers to an information system that stores data in an organized manner and enables efficient access and management.

[1234] An "emotion engine" refers to a system that analyzes a user's interaction data to determine their emotional state at that time.

[1235] "User" refers to a person who uses the system.

[1236] "Interaction" refers to the actions and communications between a user and a system.

[1237] "Inquiry" refers to the act of a user requesting specific information or explanation from the system.

[1238] "Keywords" refer to the main words or phrases used in a search or inquiry.

[1239] "Generative AI models" refer to algorithms or systems that use artificial intelligence techniques to generate new text or information.

[1240] "Explanation" refers to text that provides detailed explanations of specific terms or concepts.

[1241] "Tone" refers to the expression of emotion or attitude in text or speech.

[1242] MODE FOR CARRYING OUT THE INVENTION

[1243] This invention provides a system that allows new members to quickly and accurately obtain explanations for terms they do not understand in their daily work. This system analyzes documents containing internal company information, automatically extracts terms and definitions, stores them in a database, and provides explanations in response to user inquiries. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can customize the explanations in a more appropriate manner.

[1244] First, it provides a means for uploading internal documents. Users use their terminals to upload internal documents such as requirements specifications and basic design documents to the server. These uploaded documents are then stored by the server.

[1245] Next, there is a means to analyze the stored documents. The server passes the documents to an analysis engine (e.g., an NLP engine) to extract important terms and their definitions from the documents. The extracted terms and definitions are stored in a database. This makes it possible to unify the management of information scattered across multiple documents.

[1246] Furthermore, an emotion engine is provided that recognizes the user's emotions. It analyzes the user's emotions from interactions such as specific keystrokes and clicks, and uses that information. This emotion recognition is applied when making inquiries or providing explanations.

[1247] When a user encounters a term they don't understand during work, they enter the term into the system's inquiry screen and submit it. The terminal sends this input to the server, along with the user's emotional state (e.g., stressed, excited, calm, etc.). The server searches a database based on the received term to retrieve related definitions and information.

[1248] Based on the acquired information, a generative AI model (e.g., GPT-3 or BERT model) is prepared. The server uses this generative AI model to generate term explanations in a format that is easy for the user to understand. This generative AI model is trained in advance from internal company documents. Furthermore, when generating explanations, the system takes the user's emotional state into consideration and provides explanations with an appropriate tone and content.

[1249] The generated commentary is sent from the server to the user's device and displayed on the user's screen, allowing the user to obtain the necessary information without wasting time, while taking into consideration the user's emotional state.

[1250] Examples:

[1251] For example, consider the case where a user asks, "What is an API?" In this case, the server searches the database to retrieve relevant information. The generative AI model generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. At our company, the API for the XX project is described in Chapter 3 of the master design document." If the user is feeling stressed, the model strives to use more concise and easy-to-understand language. For example, the explanation might be, "API is the rules for communication between software programs. Detailed information about the XX project can be found in Chapter 3 of the master design document."

[1252] In this way, this system can quickly resolve questions that new members may have and improve work efficiency. It also reduces the amount of work required to manually maintain the glossary, creating an environment where the latest information is always provided. Furthermore, the introduction of an emotion engine makes it possible to provide appropriate information according to the user's psychological state.

[1253] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1254] Step 1:

[1255] The user starts up the terminal and opens the system's upload screen. An upload button is displayed as an input. Using this button, the user selects an internal document such as a requirements specification document or a basic design document, and clicks the upload button.

[1256] Specifically, the terminal sends the selected document data to the server, and the server stores the received document in a specific directory. As an output, the document data is stored in the server.

[1257] Step 2:

[1258] The server detects new documents in a specified directory. It takes the stored document data as input. The server invokes an analysis engine (e.g., an NLP engine) to extract key terms and their definitions from the document.

[1259] As a specific operation, the extracted terms and definitions are stored in a database by the server. As an output, the data of the terms and definitions is stored in a database.

[1260] Step 3:

[1261] The device sends user interactions such as keystrokes and clicks to the emotion engine. The input is the user's operation data. The emotion engine analyzes the operation data and determines the user's emotional state (e.g., stress, excitement, calm, etc.).

[1262] In particular, the emotional information is sent from the terminal to the server and stored in the user profile. As an output, the user's emotional state data is stored in the server.

[1263] Step 4:

[1264] The user opens the system's inquiry screen, enters the term they do not understand, and clicks the send button. The input includes the query term. The device then sends the entered term and the user's emotional state to the server.

[1265] Specifically, the server searches the database based on the received terms and emotional state to obtain relevant definitions and information, and the output is the search results.

[1266] Step 5:

[1267] The server uses a generative AI model (e.g., GPT-3 or BERT model) to generate an explanation based on the search results and the user's emotional state. The inputs are search result data and emotional state data. The generative AI model generates an easy-to-understand explanation based on this data.

[1268] As a specific operation, the generated commentary is transmitted to the terminal by the server, and the generated commentary data is obtained as an output.

[1269] Step 6:

[1270] The terminal displays the explanation received from the server on the user's screen. The generated explanation data is used as input. The user checks the displayed explanation and obtains the necessary information.

[1271] Specifically, the user can check the explanation on the screen, and the user can obtain information as an output.

[1272] (Application example 2)

[1273] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1274] New members and operators joining factories need to be able to quickly and accurately understand unfamiliar terms and operating procedures. However, with conventional systems, searching for terms and procedures takes time, which reduces factory efficiency. Furthermore, information is not provided in accordance with the user's emotional state, which can cause stress and confusion.

[1275] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1276] In this invention, the server includes means for uploading documents containing internal company information, means for analyzing the uploaded documents to extract terms and definitions, means for storing the extracted terms and definitions in a database, means for accepting queries about terms from users, means for searching the database based on accepted keywords, means for using a generative AI model to generate explanations based on the search results, means for providing the generated explanations to users, means for combining with an emotion analysis engine that recognizes the emotional state of the user, and means for customizing the content of the explanations according to the emotional state. This enables new members and operators to quickly and accurately understand unfamiliar terms and operating procedures, and makes it possible to provide appropriate information according to their emotional state.

[1277] "Internal information" refers to data and documents generated or held within a company, including business instructions, manuals, reports, etc.

[1278] "Document upload means" refers to a function or device that allows a user to transfer and store digital documents in their possession in the system.

[1279] "Document Analysis Measures" means software or algorithms used to automatically extract key terms and their definitions from uploaded documents.

[1280] A "database" is a computer system or collection of structured data that systematically stores extracted terms, definitions, and related information and manages them in a searchable format.

[1281] "Terminology inquiry means" refers to an interface or function that allows a user to input questions about unknown terms or operating procedures and make inquiries to the system.

[1282] A "generative AI model" is an artificial intelligence algorithm or machine learning model that generates appropriate explanations or information based on input information.

[1283] An "emotion analysis engine" is software or algorithms that analyze and determine a user's emotional state (e.g., stress, excitement, calmness, etc.) at that time based on their input or actions.

[1284] The "explanation customization means" refers to a method or function for providing the generated explanation content in an optimal form according to the emotional state of the user.

[1285] To implement the present invention, the following elements and process steps are required.

[1286] Program Generation

[1287] First, as a means of uploading documents containing internal company information, users can transfer factory operation manuals and design documents to the system. The terminal receives the documents from the user and sends them to the server.

[1288] The server then analyzes the uploaded document, using a document analysis engine (e.g., OpenNLP or SpaCy) to automatically extract important terms and definitions from the document, and stores this extracted information in a database.

[1289] When a user encounters a term or operation procedure they do not understand during work, they can enter the term or question into the system's inquiry screen from their terminal and submit it. The terminal then sends this input to the server. At the same time, the user's emotional state (e.g., stressed, calm, excited, etc.) is also collected and analyzed by an emotion analysis engine (e.g., NLTK, TextBlob).

[1290] The server searches a database based on the received terms to retrieve relevant information. It then uses generative AI models (e.g., Hugging Face Transformers) to explain the information in a way that is easy for the user to understand. This explanation is customized to take into account the user's emotional state. For example, if the user is feeling stressed, the explanation will be more concise and easy to understand.

[1291] The generated explanations are sent from the server to the terminal and displayed on the user's screen in real time, allowing the user to quickly and accurately resolve any questions.

[1292] Specific examples of implementation

[1293] For example, if a new operator in a factory asks, "What is an API?", the server searches the database and extracts relevant information. The generative AI model then generates an explanation such as, "API stands for Application Programming Interface, and is an interface between software. In our company, the API for the XX project is described in Chapter 3 of the basic design document." If the user is feeling stressed, the system can use more concise and easy-to-understand language.

[1294] An example of a real prompt:

[1295] Analyze the following passage and save the key terms and their definitions: Sentence: "The operating manual provides detailed instructions for how to operate the robot..."

[1296]

[1297] Generate concise and easy-to-understand API descriptions to help users feel stressed. Terminology: "API"

[1298] In this way, the present invention can quickly resolve questions raised by new members and operators in the factory, thereby improving work efficiency.

[1299] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1300] Step 1:

[1301] Users use an operation panel or tablet device to upload documents containing internal information such as factory operation manuals and design documents to the system. The input is a digital document (PDF, DOCX, etc.), and the output is document data transferred to the server. This data is saved on the server by the document uploading means.

[1302] Step 2:

[1303] The server passes the uploaded document to an analysis engine (e.g., OpenNLP or SpaCy) to extract important terms and definitions. The input is the stored document data, and the output is the extracted terms and their definitions. This data is extracted and processed by the document analysis tool and stored in a database.

[1304] Step 3:

[1305] Users can enter questions about unfamiliar terms or operating procedures during work and send them from the inquiry screen on their terminal. The input is the keywords or questions entered by the user, and the output is the inquiry data sent to the server.

[1306] Step 4:

[1307] The device also collects the user's emotional state (e.g., stress, calm, excitement, etc.) and analyzes it using an emotion analysis engine (e.g., NLTK, TextBlob). The input is the user's keystrokes and clicks, and the output is the analyzed emotional state. This emotional data is also sent to the server.

[1308] Step 5:

[1309] The server searches the database based on the received query data to obtain related information. The input is keywords or questions, and the output is related information. The search process is performed by the database search means.

[1310] Step 6:

[1311] The server uses a generative AI model (e.g., Hugging Face Transformers) to generate a commentary based on the acquired information. The input is the relevant information and the user's emotional state, and the output is a customized commentary. The generative AI model generates text based on the prompts, providing a commentary with a tone and content that matches the user's emotions.

[1312] Step 7:

[1313] The server sends the generated explanation to the terminal and displays it on the user's screen. The input is the customized explanation, and the output is the explanation text displayed on the terminal, allowing the user to quickly resolve any questions.

[1314] This series of processes improves the work efficiency of new members and operators joining the factory, and enables the provision of information that takes into account the emotional state of the user.

[1315] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1316] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1317] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1318] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1319] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1320] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1321] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1322] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1323] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1324] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1325] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1326] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1327] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1328] 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.

[1329] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1330] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1331] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1332] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1333] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1334] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1335] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1336] The following is further disclosed regarding the above embodiment.

[1337] (Claim 1)

[1338] A means to upload documents containing company information;

[1339] A means of analyzing uploaded documents to extract terms and definitions;

[1340] a means for storing the extracted terms and definitions in a database;

[1341] means for accepting queries from users regarding terms;

[1342] a means for searching the database based on the received keywords;

[1343] Using a generative AI model to generate commentary based on search results;

[1344] means for providing the generated commentary to a user;

[1345] A system including:

[1346] (Claim 2)

[1347] 2. The system according to claim 1, wherein the uploaded document is a requirements specification document or a basic design document.

[1348] (Claim 3)

[1349] 2. The system of claim 1, wherein the generated commentary is specialized for company information.

[1350] "Example 1"

[1351] (Claim 1)

[1352] A means to upload documents containing company information;

[1353] A means of analyzing uploaded documents to extract terms and definitions;

[1354] a means for storing the extracted terms and definitions in a database;

[1355] means for accepting queries from users regarding terms;

[1356] a means for searching the database based on accepted terms;

[1357] Using a generative AI model to generate commentary based on search results;

[1358] means for providing the generated commentary to a user;

[1359] A means of automatically extracting important terms and definitions within a document using an analysis engine;

[1360] a means for sending a prompt to a generative AI model to generate an explanation;

[1361] A system including:

[1362] (Claim 2)

[1363] 2. The system according to claim 1, wherein the uploaded document is a specification or design document.

[1364] (Claim 3)

[1365] 2. The system of claim 1, wherein the generated commentary is specialized for inside information.

[1366] "Application Example 1"

[1367] (Claim 1)

[1368] A means to upload documents containing company information;

[1369] A means of analyzing uploaded documents to extract terms and definitions;

[1370] a means for storing the extracted terms and definitions in a database;

[1371] means for accepting queries from users regarding terms;

[1372] a means for searching the database based on the received keywords;

[1373] Using a generative AI model to generate commentary based on search results;

[1374] means for providing the generated commentary to a user;

[1375] A means of providing real-time commentary to operators using smart glasses or robots;

[1376] A system including:

[1377] (Claim 2)

[1378] 2. The system according to claim 1, wherein the uploaded document is a requirements specification document or a basic design document.

[1379] (Claim 3)

[1380] The system of claim 1, wherein the generated commentary is specific to internal company information and is provided through smart glasses or a robot.

[1381] "Example 2: Combining Emotion Engines"

[1382] (Claim 1)

[1383] A means to upload documents containing company information;

[1384] A means of analyzing uploaded documents to extract terms and definitions;

[1385] a means for storing the extracted terms and definitions in a database;

[1386] a means for using an emotion engine to analyze a user's interactions and extract an emotional state;

[1387] means for accepting queries from users regarding terms;

[1388] means for searching a database based on the received keywords and the user's emotional state;

[1389] a generative AI model that generates commentary based on search results and the user's emotional state;

[1390] means for providing the generated commentary to a user;

[1391] A system including:

[1392] (Claim 2)

[1393] 2. The system according to claim 1, wherein the uploaded document is technical information related to the business.

[1394] (Claim 3)

[1395] 10. The system of claim 1, wherein the generated commentary is customized according to the user's emotional state.

[1396] "Application example 2 when combining emotion engines"

[1397] (Claim 1)

[1398] A means to upload documents containing company information;

[1399] A means of analyzing uploaded documents to extract terms and definitions;

[1400] a means for storing the extracted terms and definitions in a database;

[1401] means for accepting queries from users regarding terms;

[1402] a means for searching the database based on the received keywords;

[1403] Using a generative AI model to generate commentary based on search results;

[1404] means for providing the generated commentary to a user;

[1405] a means for combining an emotion analysis engine that recognizes the emotional state of a user;

[1406] A means to customize commentary content depending on emotional state;

[1407] A system including:

[1408] (Claim 2)

[1409] 2. The system according to claim 1, wherein the uploaded document is a requirements specification document or a basic design document.

[1410] (Claim 3)

[1411] 2. The system of claim 1, wherein the generated commentary is specialized for company information. [Explanation of symbols]

[1412] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to upload documents containing company information; A means of analyzing uploaded documents to extract terms and definitions; a means for storing the extracted terms and definitions in a database; means for accepting queries from users regarding terms; a means for searching the database based on the received keywords; Using a generative AI model to generate commentary based on search results; means for providing the generated commentary to a user; A system including:

2. 2. The system according to claim 1, wherein the uploaded document is a requirements definition document or a basic design document.

3. The system of claim 1 , wherein the generated commentary is specialized for company information.

Images