system

Abstract

We provide the system. [Solution] Means for collecting technical information, Means of collecting technical information, A means for providing a generative model that learns based on the aforementioned collected technical information, A means for summarizing the information learned by the aforementioned generative model and generating it as related information, The means for processing the generated information based on user queries received through speech recognition, Means for presenting the processed information visually or audibly, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the advancement of technology, it has become difficult to inherit the knowledge and experience of experts, and accordingly, the responsiveness of engineers has decreased. In particular, when a disaster or failure occurs, a quick and accurate response is required, but there is a risk that the response may be delayed or an incorrect response may be made due to lack of knowledge. To solve this problem, it is important to quickly obtain the information required by engineers and provide it in an easy-to-understand format.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a means for collecting technical information and training a generative model based on the collected information. The generative model summarizes the learned information and automatically generates further related information, which is then provided to engineers via a terminal. In addition, it provides information through visual and auditory means by generating diagrams or flowcharts visually and video explanations aurally. With this system, engineers can understand and utilize the necessary information in a short time, thereby improving their responsiveness.

[0006] "Technical information" refers to information including documents, data, manuals, know-how, and past case studies that engineers need to perform their duties.

[0007] A "generative model" is an algorithm or program that learns from provided data and generates and summarizes information for a specific purpose.

[0008] A "summary" is information that has been extracted from a large amount of information and compiled into a concise format.

[0009] "Related information" refers to information that is directly or indirectly associated with a user's request or context in order to fulfill that request.

[0010] "Visual presentation methods" refer to the process of making information easier to understand by visualizing it in the form of diagrams, flowcharts, and other visual aids.

[0011] "Auditory presentation methods" refer to the process of providing information using audio and video, enabling users to obtain information through their ears. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system that consistently performs tasks from the collection of technical information to data processing using a generative model and the presentation of that information. The operation of this system is described below.

[0034] The server collects technical information. This technical information comes from databases, past cases, manuals, and industry standards. This collected information is cleansed into a specific format and managed centrally.

[0035] Next, the server trains a generative model based on this information. The generative model learns from a large amount of technical information and acquires the knowledge necessary to summarize technical documents and answer user queries. This learning process uses machine learning and natural language processing techniques.

[0036] Once information processing is complete, the terminal receives the user's query and contacts the server. The server uses a generative model to quickly summarize the information, extract relevant details, and organize them into structured data. This data is then presented visually or audibly in a format easily understood by engineers.

[0037] For example, if a user wants to know how to fix a base station communication failure, they enter a query into their terminal. In response, the server summarizes relevant past failure information and repair procedures and provides them to the terminal as a flowchart or video explanation. This allows users to quickly obtain accurate information based on past experience and respond to failures appropriately and quickly.

[0038] This system avoids delays caused by a lack of technical knowledge among engineers, significantly improving operational efficiency and responsiveness.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server periodically collects technical information from databases and external data sources. This includes technical documents, manuals, know-how, and records of past incident response. The collected information undergoes data cleansing to organize its content and format it correctly.

[0042] Step 2:

[0043] The server trains a generative model based on the cleansed information. This model improves its ability to summarize technical information and quickly extract relevant information in response to user queries.

[0044] Step 3:

[0045] Users input specific technical problems or questions through the terminal's interface. For example, they might enter a query about troubleshooting techniques for base stations.

[0046] Step 4:

[0047] The terminal sends queries from the user to the server and requests the provision of necessary information.

[0048] Step 5:

[0049] The server uses a pre-trained generative model to quickly extract relevant information from the database based on the received query. Furthermore, the extracted information is summarized by the generative model and organized into structured data.

[0050] Step 6:

[0051] The server uses computer vision technology to generate diagrams and flowcharts based on summarized information and related procedures. Furthermore, it creates video explanations to supplement the explanations using video generation technology.

[0052] Step 7:

[0053] The terminal presents the user with summary information, diagrams, flowcharts, and videos provided by the server. This allows the user to instantly understand the information necessary for problem-solving through both visual and auditory means.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] Modern engineers are required to make quick and accurate decisions, but efficiently extracting and understanding the necessary information from a vast amount of technical data is not easy. Furthermore, to cope with the rapid increase in technical information, detailed analysis and knowledge summarization are required, going beyond mere information retrieval. This invention aims to solve the problems of information processing delays and inaccuracies faced by such engineers.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for automatically extracting technical information from various sources and organizing and managing it in a unified format; means for training a generative model using machine learning techniques based on the organized technical information; and means for summarizing information based on received queries and generating it as structured data using the trained generative model. This enables engineers to obtain the necessary information more quickly and accurately than with conventional information processing, thereby improving the efficiency of their work.

[0059] "Technical information" refers to data and knowledge related to a technical field, and can be obtained from a variety of sources, such as databases, case studies, manuals, and standards.

[0060] "Information sources" refer to the sources from which technical information is obtained, and include databases, documented case studies, industry manuals, and standards.

[0061] A "format" is a framework for arranging information into a specific form and is used to maintain data consistency.

[0062] "Machine learning technology" refers to algorithms and methods that process large amounts of data and automatically learn patterns and rules from it.

[0063] A "generative model" is a mathematical model used to generate new information or data based on knowledge learned through machine learning.

[0064] "Structured data" refers to information that is organized according to certain rules and stored in a format that allows for efficient access and analysis.

[0065] "Inquiry" refers to a question or request that a user makes to a system in order to obtain specific information.

[0066] The following describes the "modes for carrying out the invention."

[0067] This invention describes a method for constructing a system that efficiently manages technical information and responds quickly to user inquiries.

[0068] The server collects technical information from a variety of sources. These sources include databases, historical cases, industry manuals, and standards. This information is organized into a unified format through data cleansing processes, enabling efficient management.

[0069] Next, the server uses the collected technical information to train a generative AI model. This process utilizes machine learning and natural language processing techniques. Specifically, deep learning frameworks such as TENSORFLOW® and PyTorch are used to learn useful patterns and knowledge from large amounts of data.

[0070] After processing the information, the terminal receives inquiries from the user. The user can enter specific queries into the terminal, such as how to repair communication failures at the base station. Examples of prompt messages include: "Please tell me the repair procedure when a communication failure occurs at the base station," and "Please summarize the risks and countermeasures for introducing new technologies."

[0071] The server uses a generated AI model based on the received query to quickly search for and summarize relevant technical information. As a result, the technical information is organized as structured data and provided to the user via the terminal. By presenting the information visually as diagrams and flowcharts, and aurally as video explanations, engineers can easily understand the information and utilize it in their work.

[0072] Therefore, this system allows engineers to efficiently acquire necessary information and achieve faster and more accurate work.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server collects technical information from diverse sources. Inputs include database connection information and access rights to documented technical data. Specifically, the server queries the database via an API to retrieve relevant information. The output is an initial dataset of the retrieved technical information.

[0076] Step 2:

[0077] The server organizes the collected technical information through a data cleansing process. The input is the raw technical information collected earlier. At this stage, natural language processing techniques are used to remove duplicate text and standardize the format. The output is a cleansed dataset organized in a standardized format.

[0078] Step 3:

[0079] The server trains a generative AI model using organized technical information. The input is a cleansed technical information dataset. Specifically, the server applies deep learning algorithms using TensorFlow or PyTorch to learn patterns and features. The output is an optimized generative model.

[0080] Step 4:

[0081] The terminal receives inquiries from the user. Input consists of prompts and query text entered by the user into the terminal. Specifically, the terminal receives queries through the user interface and sends them to the server. Output is the user query information sent to the server.

[0082] Step 5:

[0083] The server uses a generative model based on the received user query to retrieve and summarize relevant information. The input consists of the user query information and the trained generative model. At this stage, the model extracts and summarizes the technical information corresponding to the query. The output is the summarized technical information and related data.

[0084] Step 6:

[0085] The terminal provides the user with summarized information received from the server. Input consists of summarized technical information and related data. Specifically, the terminal visually converts the information into a flowchart or presents it audibly as a video explanation. Output is an easily understandable information display.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] In manufacturing environments such as factories, it is crucial for technicians to obtain information that allows them to respond quickly and accurately to equipment failures and problems. However, traditional methods require manual referencing of past cases and manuals, which is time-consuming and cumbersome. To solve this problem, a system is needed that efficiently collects and processes technical information and presents solutions in real time.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for collecting technical information, means for providing a generative model that learns based on the collected technical information, and means for processing the information learned by the generative model based on user queries received through speech recognition. This enables the user to quickly obtain appropriate technical information in response to a query made via voice and to confirm the information by visual or auditory means.

[0091] "Technical information" refers to knowledge and data related to the operation, repair, and maintenance of equipment, and is collected from sources such as past cases, manuals, and industry standards.

[0092] A "generative model" is a machine learning algorithm that learns from a large amount of technical information and generates summaries of that information or answers to user queries.

[0093] A "user query" is a question or request that a technician sends to a server via voice or text in order to obtain technical information.

[0094] "Speech recognition" is a technology that converts user-inputted speech into text data, playing a role in making voice input into a format that the server can understand.

[0095] "Visual presentation" refers to a method of displaying technical information on a screen using diagrams and interactive media, which helps users easily understand the information.

[0096] "Auditory presentation" refers to a method of conveying technical information to users through audio and video, with the aim of providing information without relying on visual means.

[0097] The system for implementing this invention mainly consists of a server, terminals, and users. The server is responsible for collecting a wide range of technical information and training a generative AI model based on that information. The server stores technical information obtained from industry standards and past cases in a database, cleanses the data into a certain format, and manages it centrally. The generative AI model also uses this information to learn and acquire the knowledge necessary for summarizing and extracting relevant information. TensorFlow and PyTorch, which are Python-based machine learning libraries, are used for training the generative AI model, and Transformers (Hugging Face) is used for natural language processing.

[0098] The device uses speech recognition technology to receive voice queries from users. For speech recognition, the Google® Cloud Speech-to-Text API is used to efficiently convert speech into text data. The user queries, now in text format, are sent to the server and rapidly processed by a generative AI model.

[0099] When users need technical information, such as when encountering robot problems on a factory production line, they can instantly obtain the necessary information via their smart devices. The server summarizes past troubleshooting cases and solutions corresponding to user queries and presents them as interactive media or visual content. This allows users to quickly take the necessary actions.

[0100] As a concrete example, consider a situation where a transport robot on a manufacturing line unexpectedly stops. In this case, the technician uses smart glasses to voice-input a prompt: "The transport robot has stopped. Please tell me the cause and repair procedure." Once this query is processed by the server, an appropriate diagnosis and repair procedure based on past repair history are visually displayed on the terminal. This consistent flow enables the technician to respond quickly and accurately.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The server collects technical information. It gathers a wide range of technical information from databases, past cases, manuals, and industry standards, cleanses the data into a consistent format, and manages it centrally. The input for this step is raw technical information, and the output is cleansed technical data.

[0104] Step 2:

[0105] The server trains a generative AI model based on the collected, cleansed technical information. In this step, machine learning is performed using TensorFlow or PyTorch, and natural language processing techniques are applied using Transformers (Hugging Face). The input is cleansed technical data, and the output is a generative model with the knowledge to answer user queries.

[0106] Step 3:

[0107] The user enters a voice query into the terminal. Specifically, they voice the prompt, "The transport robot has stopped. Please tell me the cause and the repair procedure." This input is voice data, which is then converted into text data using the Google Cloud Speech-to-Text API.

[0108] Step 4:

[0109] The terminal sends the voice-recognized query as text data to the server. The input for this step is the text data of the voice query, and the server completes the reception as output.

[0110] Step 5:

[0111] The server processes the text data of the received user query using a generative AI model to generate relevant technical information and summaries. Based on the query, the server searches a database to extract relevant past cases and repair procedures. The input consists of the user query text data and the generative model, and the output is a summary of the generated technical information.

[0112] Step 6:

[0113] The terminal presents generated information sent from the server to the user visually or audibly. The terminal displays interactive media and text on a smart device, providing information in a format easily understood by the user. The input is a summary of the generated information, and the output is a visual or audible presentation.

[0114] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0115] This invention is a system that combines an emotion engine with the provision of technical information, enabling more effective information transmission by adjusting the method of information presentation based on the user's emotions. This system integrates everything from the collection of technical information to learning by a generative model, and further to the provision of information based on the recognition of the user's emotions.

[0116] First, the server collects a wide range of technical information and stores it in a database. This information is then trained by a generative model, which efficiently performs summarization and extracts relevant information.

[0117] When a user enters a technical query into the terminal, the terminal uses an emotion engine to analyze the user's current emotional state. The emotion engine monitors the user's facial expressions, tone of voice, biometric data, etc., in real time to identify emotions such as joy, frustration, and confusion.

[0118] The server adjusts how it presents information extracted by the generative model based on the emotional data sent from the emotion engine. For example, if the user is irritated, it provides information in a more concise and direct format, while if the user is calm, it presents detailed and comprehensive information.

[0119] The device provides users with adjusted information in the form of diagrams, flowcharts, or video explanations. This allows users to receive information tailored to their emotional state and effectively solve problems.

[0120] For example, if a user requests help with a complex setup process, and the emotion engine recognizes the user's frustration, the server will provide step-by-step instructions and charts, offering information in a visually easy-to-understand format. Conversely, if the user shows confidence, the system may provide more detailed information and alternative procedures. This ensures that the system always provides a user-friendly experience.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The server collects technical information, including manuals, technical documents, and past troubleshooting examples from the database. The collected data is formatted and stored in the database.

[0124] Step 2:

[0125] The server trains a generative model based on this technical information. This model uses natural language processing techniques to enable information summarization and efficient extraction of relevant information.

[0126] Step 3:

[0127] The user enters a query through the terminal interface. This query includes details about a specific technical problem or the information they are seeking.

[0128] Step 4:

[0129] The device activates an emotion engine simultaneously with query input, collecting the user's facial expressions, voice tone, and other biometric data through sensors to analyze the user's emotions.

[0130] Step 5:

[0131] The server receives queries and sentiment data from the terminal, extracts relevant information using a generative model, and creates a summary tailored to the user's sentiment. It adjusts the focus and level of detail of the information according to the sentiment.

[0132] Step 6:

[0133] The server constructs the processed information as diagrams, flowcharts, or video explanations using computer vision and multimedia technologies.

[0134] Step 7:

[0135] The device presents the constructed information to the user. This allows the user to receive information optimized to their emotional state and use it to solve problems. For example, if the emotion engine detects the user's confusion, the system will directly visualize and present detailed steps in diagrams.

[0136] (Example 2)

[0137] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0138] Conventional systems that provide technical information present information uniformly and lack the flexibility to respond to the user's emotional state. As a result, users may find it difficult to understand the information. This invention aims to solve this problem and realize information provision optimized for the user's emotional state.

[0139] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0140] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for analyzing the user's emotional state. This makes it possible to adjust the information presentation method according to the user's emotional state and achieve optimal information provision.

[0141] "Technical information" is a general term for data and insights related to specialized knowledge and technology, and is part of the information sources provided by the system.

[0142] A "generative model" refers to an algorithm or system that processes and learns information based on collected data, and has the ability to summarize and extract relevant information.

[0143] "Means for analyzing a user's emotional state" refers to processes and technologies for identifying what emotions a user is currently experiencing, using the user's facial expressions, voice, and biometric data to identify emotions.

[0144] "Adjusting the method of information presentation" refers to the process of optimizing the format and content of information presentation according to the user's emotional state, so that users can receive information more effectively.

[0145] "Means of visual or auditory presentation" refers to processes and technologies that provide information to users using visual elements (diagrams, flowcharts, etc.) or auditory elements (audio guides, video explanations, etc.).

[0146] This invention is an information provision system based on technical information and the user's emotional state, and it realizes information presentation optimized for the user's emotions. This system mainly consists of processes of information collection, learning by a generative model, emotion analysis, and information presentation adjustment.

[0147] The server collects technical information from a wide range of sources and stores it in a database. Based on this information, a generative AI model is used to learn and summarize the information and extract relevant information. The generative AI model utilizes hardware such as high-performance computers equipped with GPUs to efficiently process diverse information using natural language processing techniques.

[0148] Users input technical questions and issues via the terminal in the form of prompts. Examples of such prompts include: "Please tell me how to configure the database," or "Please provide troubleshooting steps based on technical information. However, my current emotional state is frustration."

[0149] The device is equipped with an emotion engine to analyze the user's emotional state, acquiring and analyzing the user's facial expressions, voice tone, and biometric data in real time through the camera and microphone. Based on this information, the server adjusts how the information extracted by the generative model is presented, and the device provides the information in a format optimized for the user's emotions. Specifically, when the user is confused, it can generate visually easy-to-understand diagrams and flowcharts, while when the user is calm, it can present detailed information.

[0150] This system allows users to obtain information in a format that is optimal for their emotional state, making it easier to solve problems efficiently.

[0151] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0152] Step 1:

[0153] The server collects technical information from various data sources (the internet, specialized databases, etc.). Input consists of user requests and pre-configured information collection targets. The server uses crawling technology and natural language processing to organize the data and store it in a structured database. Output is a collection of technical information that can be efficiently searched and processed.

[0154] Step 2:

[0155] The server uses collected technical information as input to train a generative AI model. This model tokenizes the technical information and uses machine learning algorithms to summarize it and extract related information. If necessary, it classifies the data through clustering and topic modeling. The output consists of a summary of the information and a set of related pieces of information.

[0156] Step 3:

[0157] The user enters technical questions or queries into the terminal in the form of prompts. This serves as direct input to the system, clarifying the user's current technical concerns and problems. The output is data used to interpret what the user is asking for.

[0158] Step 4:

[0159] The device activates an emotion engine and uses its camera and microphone to analyze the user's facial expressions and voice in real time. The input consists of the user's facial movements and voice tone, which are passed to the emotion recognition algorithm as biometric data. The output is the user's emotional state (e.g., irritation, confusion, joy).

[0160] Step 5:

[0161] The server uses the user's emotional state obtained in step 4 as input to adjust how the information extracted from the generative model is presented. In this process, the format and level of detail of the information are optimized according to the user's emotions. The output is the format of information presentation that is easiest for the user to understand.

[0162] Step 6:

[0163] The terminal presents information to the user as visual data (diagrams, flowcharts) and auditory data (audio guides, video explanations) based on the adjusted information. Input is optimized information from the server, which is then processed for visualization and audio before being provided to the user. Output is the final information received by the user.

[0164] (Application Example 2)

[0165] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0166] In modern information systems, technical information is often provided in a one-way and general manner. This results in a lack of information delivery tailored to the emotional state of individual users, leading to challenges in information comprehension efficiency and optimized user experience. This is particularly true for technologies familiar to people, such as home assistant robots, where responses and support tailored to the user's emotions are required, but achieving this is difficult.

[0167] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0168] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for adjusting the method of presenting information. This makes it possible to present information in accordance with the user's emotional state.

[0169] "Technical information" refers to information that includes specialized or technical content and is provided as data necessary for the system to use.

[0170] A "generative model" is an algorithm or data model that learns from collected technical information and generates or transforms new information.

[0171] A "summary" refers to the result of a generative model concisely representing the information it has learned and extracting the most relevant points.

[0172] "Means of visual presentation" refers to functions that convey information to users in a visual format, such as diagrams, images, or flowcharts.

[0173] "Means of auditory presentation" refers to functions that provide information to users through auditory means such as sound and music.

[0174] "User" refers to any person who operates this system or receives information from it.

[0175] "Methods for analyzing emotions" refer to technologies for evaluating and analyzing a user's emotional state based on their facial expressions, voice, and other expressions.

[0176] "Means for adjusting the method of information presentation" refers to a function that changes the format and content of information based on analyzed emotions, and provides it to the user in the most optimal way.

[0177] In the system that implements this application, multiple components work together. First, a server collects a wide range of technical information and stores it in a database. This data is then used to train a generative AI model, which performs summarization and extracts relevant information. The server uses common cloud platforms and data processing software to perform these processes.

[0178] The device incorporates an emotion engine that analyzes the user's emotional state. The emotion engine monitors the user's facial expressions, voice, and biometric data in real time to identify specific emotions. Small hardware such as a Raspberry Pi is often used for this purpose. In addition, real-time emotion analysis is achieved by utilizing open-source emotion recognition libraries such as OpenCV.

[0179] Based on user input, the server adjusts how information extracted by the generative AI model is presented according to the user's emotional data. For example, if the user is irritated, information is provided in a concise and direct format; if the user is calm, more detailed and comprehensive information is presented.

[0180] For example, when a user asks for help with a complex setup process, the emotion engine recognizes the user's confusion and the server provides step-by-step instructions and charts in a visually easy-to-understand format. An example of a prompt message would be, "The user has been identified as tired. Please generate a message suggesting relaxing music."

[0181] In this way, the system provides optimal information tailored to the user's emotions and supports effective problem-solving. Furthermore, the system's flexible response allows for a more user-friendly experience.

[0182] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0183] Step 1:

[0184] The server collects technical information from the internet and internal networks and stores it in a database. The collection process gathers relevant information through web crawlers and APIs. The input is raw technical information, and the output is an organized dataset.

[0185] Step 2:

[0186] The server inputs the accumulated data into a generating AI model to train the model. The model is designed to summarize information and extract relevant information. The input is a large technical information dataset, and the output is summarized information and relevant information. Here, the model's algorithm is used to learn data patterns.

[0187] Step 3:

[0188] The user enters a technical query into the terminal. The terminal uses an emotion engine to analyze the user's facial expressions, voice, and biometric data in real time to identify their emotional state. The input consists of the user's physical and auditory characteristics, and the output is identified emotion data.

[0189] Step 4:

[0190] The server queries a generative AI model for the optimal information presentation method based on emotional data and technical queries. It provides the generative model with emotional data as prompts, generating user-friendly information. The input consists of emotional states and related technical information, while the output is adjusted information tailored to the user's state.

[0191] Step 5:

[0192] The terminal presents the user with pre-configured information. Visual information is displayed using a graphical user interface, and auditory information is played back as sound. Input is pre-configured information from the server, and output is visual or auditory feedback directed to the user.

[0193] These processing steps allow the system to consider the user's emotions and provide information in the most optimal format, effectively supporting problem-solving.

[0194] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0195] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0196] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0197] [Second Embodiment]

[0198] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0199] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0200] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0201] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0202] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0203] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0204] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0205] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0206] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0207] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0208] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0209] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0210] This invention is a system that consistently performs tasks from the collection of technical information to data processing using a generative model and the presentation of that information. The operation of this system is described below.

[0211] The server collects technical information. This technical information comes from databases, past cases, manuals, and industry standards. This collected information is cleansed into a specific format and managed centrally.

[0212] Next, the server trains a generative model based on this information. The generative model learns from a large amount of technical information and acquires the knowledge necessary to summarize technical documents and answer user queries. This learning process uses machine learning and natural language processing techniques.

[0213] Once information processing is complete, the terminal receives the user's query and contacts the server. The server uses a generative model to quickly summarize the information, extract relevant details, and organize them into structured data. This data is then presented visually or audibly in a format easily understood by engineers.

[0214] For example, if a user wants to know how to fix a base station communication failure, they enter a query into their terminal. In response, the server summarizes relevant past failure information and repair procedures and provides them to the terminal as a flowchart or video explanation. This allows users to quickly obtain accurate information based on past experience and respond to failures appropriately and quickly.

[0215] This system avoids delays caused by a lack of technical knowledge among engineers, significantly improving operational efficiency and responsiveness.

[0216] The following describes the processing flow.

[0217] Step 1:

[0218] The server periodically collects technical information from databases and external data sources. This includes technical documents, manuals, know-how, and records of past incident response. The collected information undergoes data cleansing to organize its content and format it correctly.

[0219] Step 2:

[0220] The server trains a generative model based on the cleansed information. This model improves its ability to summarize technical information and quickly extract relevant information in response to user queries.

[0221] Step 3:

[0222] Users input specific technical problems or questions through the terminal's interface. For example, they might enter a query about troubleshooting techniques for base stations.

[0223] Step 4:

[0224] The terminal sends queries from the user to the server and requests the provision of necessary information.

[0225] Step 5:

[0226] The server uses a pre-trained generative model to quickly extract relevant information from the database based on the received query. Furthermore, the extracted information is summarized by the generative model and organized into structured data.

[0227] Step 6:

[0228] The server uses computer vision technology to generate diagrams and flowcharts based on summarized information and related procedures. Furthermore, it creates video explanations to supplement the explanations using video generation technology.

[0229] Step 7:

[0230] The terminal presents the user with summary information, diagrams, flowcharts, and videos provided by the server. This allows the user to instantly understand the information necessary for problem-solving through both visual and auditory means.

[0231] (Example 1)

[0232] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0233] Modern engineers are required to make quick and accurate decisions, but efficiently extracting and understanding the necessary information from a vast amount of technical data is not easy. Furthermore, to cope with the rapid increase in technical information, detailed analysis and knowledge summarization are required, going beyond mere information retrieval. This invention aims to solve the problems of information processing delays and inaccuracies faced by such engineers.

[0234] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0235] In this invention, the server includes means for automatically extracting technical information from various sources and organizing and managing it in a unified format; means for training a generative model using machine learning techniques based on the organized technical information; and means for summarizing information based on received queries and generating it as structured data using the trained generative model. This enables engineers to obtain the necessary information more quickly and accurately than with conventional information processing, thereby improving the efficiency of their work.

[0236] "Technical information" refers to data and knowledge related to a technical field, and can be obtained from a variety of sources, such as databases, case studies, manuals, and standards.

[0237] "Information sources" refer to the sources from which technical information is obtained, and include databases, documented case studies, industry manuals, and standards.

[0238] A "format" is a framework for arranging information into a specific form and is used to maintain data consistency.

[0239] "Machine learning technology" refers to algorithms and methods that process large amounts of data and automatically learn patterns and rules from it.

[0240] A "generative model" is a mathematical model used to generate new information or data based on knowledge learned through machine learning.

[0241] "Structured data" refers to information that is organized according to certain rules and stored in a format that allows for efficient access and analysis.

[0242] "Inquiry" refers to a question or request that a user makes to a system in order to obtain specific information.

[0243] The following describes the "modes for carrying out the invention."

[0244] This invention describes a method for constructing a system that efficiently manages technical information and responds quickly to user inquiries.

[0245] The server collects technical information from a variety of sources. These sources include databases, historical cases, industry manuals, and standards. This information is organized into a unified format through data cleansing processes, enabling efficient management.

[0246] Next, the server uses the collected technical information to train a generative AI model. This process utilizes machine learning and natural language processing techniques. Specifically, deep learning frameworks such as TensorFlow and PyTorch are used to learn useful patterns and knowledge from large amounts of data.

[0247] After processing the information, the terminal receives inquiries from the user. The user can enter specific queries into the terminal, such as how to repair communication failures at the base station. Examples of prompt messages include: "Please tell me the repair procedure when a communication failure occurs at the base station," and "Please summarize the risks and countermeasures for introducing new technologies."

[0248] The server uses a generated AI model based on the received query to quickly search for and summarize relevant technical information. As a result, the technical information is organized as structured data and provided to the user via the terminal. By presenting the information visually as diagrams and flowcharts, and aurally as video explanations, engineers can easily understand the information and utilize it in their work.

[0249] Therefore, this system allows engineers to efficiently acquire necessary information and achieve faster and more accurate work.

[0250] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0251] Step 1:

[0252] The server collects technical information from diverse sources. Inputs include database connection information and access rights to documented technical data. Specifically, the server queries the database via an API to retrieve relevant information. The output is an initial dataset of the retrieved technical information.

[0253] Step 2:

[0254] The server organizes the collected technical information through a data cleansing process. The input is the raw technical information collected earlier. At this stage, natural language processing techniques are used to remove duplicate text and standardize the format. The output is a cleansed dataset organized in a standardized format.

[0255] Step 3:

[0256] The server trains a generative AI model using organized technical information. The input is a cleansed technical information dataset. Specifically, the server applies deep learning algorithms using TensorFlow or PyTorch to learn patterns and features. The output is an optimized generative model.

[0257] Step 4:

[0258] The terminal receives inquiries from the user. Input consists of prompts and query text entered by the user into the terminal. Specifically, the terminal receives queries through the user interface and sends them to the server. Output is the user query information sent to the server.

[0259] Step 5:

[0260] The server uses a generative model based on the received user query to retrieve and summarize relevant information. The input consists of the user query information and the trained generative model. At this stage, the model extracts and summarizes the technical information corresponding to the query. The output is the summarized technical information and related data.

[0261] Step 6:

[0262] The terminal provides the user with summarized information received from the server. Input consists of summarized technical information and related data. Specifically, the terminal visually converts the information into a flowchart or presents it audibly as a video explanation. Output is an easily understandable information display.

[0263] (Application Example 1)

[0264] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] In manufacturing environments such as factories, it is crucial for technicians to obtain information that allows them to respond quickly and accurately to equipment failures and problems. However, traditional methods require manual referencing of past cases and manuals, which is time-consuming and cumbersome. To solve this problem, a system is needed that efficiently collects and processes technical information and presents solutions in real time.

[0266] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0267] In this invention, the server includes means for collecting technical information, means for providing a generative model that learns based on the collected technical information, and means for processing the information learned by the generative model based on user queries received through speech recognition. This enables the user to quickly obtain appropriate technical information in response to a query made via voice and to confirm the information by visual or auditory means.

[0268] "Technical information" refers to knowledge and data related to the operation, repair, and maintenance of equipment, and is collected from sources such as past cases, manuals, and industry standards.

[0269] A "generative model" is a machine learning algorithm that learns from a large amount of technical information and generates summaries of that information or answers to user queries.

[0270] A "user query" is a question or request that a technician sends to a server via voice or text in order to obtain technical information.

[0271] "Speech recognition" is a technology that converts user-inputted speech into text data, playing a role in making voice input into a format that the server can understand.

[0272] "Visual presentation" refers to a method of displaying technical information on a screen using diagrams and interactive media, which helps users easily understand the information.

[0273] "Auditory presentation" refers to a method of conveying technical information to users through audio and video, with the aim of providing information without relying on visual means.

[0274] The system for implementing this invention mainly consists of a server, terminals, and users. The server is responsible for collecting a wide range of technical information and training a generative AI model based on that information. The server stores technical information obtained from industry standards and past cases in a database, cleanses the data into a certain format, and manages it centrally. The generative AI model also uses this information to learn and acquire the knowledge necessary for summarizing and extracting relevant information. TensorFlow and PyTorch, which are Python-based machine learning libraries, are used for training the generative AI model, and Transformers (Hugging Face) is used for natural language processing.

[0275] The device uses speech recognition technology to receive voice queries from users. The Google Cloud Speech-to-Text API is used for speech recognition, efficiently converting speech into text data. The user queries, now in text format, are sent to a server and rapidly processed by a generative AI model.

[0276] When users need technical information, such as when encountering robot problems on a factory production line, they can instantly obtain the necessary information via their smart devices. The server summarizes past troubleshooting cases and solutions corresponding to user queries and presents them as interactive media or visual content. This allows users to quickly take the necessary actions.

[0277] As a concrete example, consider a situation where a transport robot on a manufacturing line unexpectedly stops. In this case, the technician uses smart glasses to voice-input a prompt: "The transport robot has stopped. Please tell me the cause and repair procedure." Once this query is processed by the server, an appropriate diagnosis and repair procedure based on past repair history are visually displayed on the terminal. This consistent flow enables the technician to respond quickly and accurately.

[0278] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0279] Step 1:

[0280] The server collects technical information. It gathers extensive technical information from databases, past cases, manuals, and industry standards, cleans the data into a certain format, and manages it centrally. The input for this step is raw technical information, and the output is cleansed technical data.

[0281] Step 2:

[0282] The server trains a generated AI model based on the collected and cleansed technical information. In this step, machine learning is performed using TensorFlow or PyTorch, and natural language processing technology is applied using Transformers (Hugging Face). The input is the cleansed technical data, and the output is a generated model with knowledge to answer user queries.

[0283] Step 3:

[0284] The user inputs a voice query into the terminal. Specifically, a prompt sentence such as "The transport robot has stopped. Please tell me the cause and repair procedure." is input in voice. The input for this step is voice data, which is converted into text data using the Google Cloud Speech-to-Text API.

[0285] Step 4:

[0286] The terminal sends the voice-identified query as text data to the server. The input for this step is the text data of the voice query, and the output is the completion of the server's reception.

[0287] Step 5:

[0288] The server processes the text data of the received user query using a generative AI model to generate relevant technical information and summaries. Based on the query, the server searches a database to extract relevant past cases and repair procedures. The input consists of the user query text data and the generative model, and the output is a summary of the generated technical information.

[0289] Step 6:

[0290] The terminal presents generated information sent from the server to the user visually or audibly. The terminal displays interactive media and text on a smart device, providing information in a format easily understood by the user. The input is a summary of the generated information, and the output is a visual or audible presentation.

[0291] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0292] This invention is a system that combines an emotion engine with the provision of technical information, enabling more effective information transmission by adjusting the method of information presentation based on the user's emotions. This system integrates everything from the collection of technical information to learning by a generative model, and further to the provision of information based on the recognition of the user's emotions.

[0293] First, the server collects a wide range of technical information and stores it in a database. This information is then trained by a generative model, which efficiently performs summarization and extracts relevant information.

[0294] When a user enters a technical query into the terminal, the terminal uses an emotion engine to analyze the user's current emotional state. The emotion engine monitors the user's facial expressions, tone of voice, biometric data, etc., in real time to identify emotions such as joy, frustration, and confusion.

[0295] The server adjusts how it presents information extracted by the generative model based on the emotional data sent from the emotion engine. For example, if the user is irritated, it provides information in a more concise and direct format, while if the user is calm, it presents detailed and comprehensive information.

[0296] The device provides users with adjusted information in the form of diagrams, flowcharts, or video explanations. This allows users to receive information tailored to their emotional state and effectively solve problems.

[0297] For example, if a user requests help with a complex setup process, and the emotion engine recognizes the user's frustration, the server will provide step-by-step instructions and charts, offering information in a visually easy-to-understand format. Conversely, if the user shows confidence, the system may provide more detailed information and alternative procedures. This ensures that the system always provides a user-friendly experience.

[0298] The following describes the processing flow.

[0299] Step 1:

[0300] The server collects technical information, including manuals, technical documents, and past troubleshooting examples from the database. The collected data is formatted and stored in the database.

[0301] Step 2:

[0302] The server trains a generative model based on this technical information. This model uses natural language processing techniques to enable information summarization and efficient extraction of relevant information.

[0303] Step 3:

[0304] The user inputs a query via the interface of the terminal. This query contains specific technical problems and details of the information sought.

[0305] Step 4:

[0306] Upon query input, the terminal activates the emotion engine and collects the user's expression, voice tone, and other biometric data through sensors to analyze the user's emotion.

[0307] Step 5:

[0308] The server receives the query and emotion data from the terminal, extracts relevant materials using the generation model, and creates a summary according to the user's emotion. It adjusts the focus and detail level of the information according to the emotion.

[0309] Step 6:

[0310] The server constructs the adjusted information as illustrations, flowcharts, or video explanations via computer vision and multimedia technologies.

[0311] Step 7:

[0312] The terminal presents the constructed information to the user. As a result, the user can receive information optimized according to their emotional state and use it to solve problems. For example, if the emotion engine detects the user's confusion, the system directly visualizes and presents detailed procedures in illustrations.

[0313] (Example 2)

[0314] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] Conventional systems that provide technical information present information uniformly and lack the flexibility to respond to the user's emotional state. As a result, users may find it difficult to understand the information. This invention aims to solve this problem and realize information provision optimized for the user's emotional state.

[0316] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0317] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for analyzing the user's emotional state. This makes it possible to adjust the information presentation method according to the user's emotional state and achieve optimal information provision.

[0318] "Technical information" is a general term for data and insights related to specialized knowledge and technology, and is part of the information sources provided by the system.

[0319] A "generative model" refers to an algorithm or system that processes and learns information based on collected data, and has the ability to summarize and extract relevant information.

[0320] "Means for analyzing a user's emotional state" refers to processes and technologies for identifying what emotions a user is currently experiencing, using the user's facial expressions, voice, and biometric data to identify emotions.

[0321] "Adjusting the method of information presentation" refers to the process of optimizing the format and content of information presentation according to the user's emotional state, so that users can receive information more effectively.

[0322] "Means of visual or auditory presentation" refers to processes and technologies that provide information to users using visual elements (diagrams, flowcharts, etc.) or auditory elements (audio guides, video explanations, etc.).

[0323] This invention is an information provision system based on technical information and the user's emotional state, and it realizes information presentation optimized for the user's emotions. This system mainly consists of processes of information collection, learning by a generative model, emotion analysis, and information presentation adjustment.

[0324] The server collects technical information from a wide range of sources and stores it in a database. Based on this information, a generative AI model is used to learn and summarize the information and extract relevant information. The generative AI model utilizes hardware such as high-performance computers equipped with GPUs to efficiently process diverse information using natural language processing techniques.

[0325] Users input technical questions and issues via the terminal in the form of prompts. Examples of such prompts include: "Please tell me how to configure the database," or "Please provide troubleshooting steps based on technical information. However, my current emotional state is frustration."

[0326] The device is equipped with an emotion engine to analyze the user's emotional state, acquiring and analyzing the user's facial expressions, voice tone, and biometric data in real time through the camera and microphone. Based on this information, the server adjusts how the information extracted by the generative model is presented, and the device provides the information in a format optimized for the user's emotions. Specifically, when the user is confused, it can generate visually easy-to-understand diagrams and flowcharts, while when the user is calm, it can present detailed information.

[0327] This system allows users to obtain information in a format that is optimal for their emotional state, making it easier to solve problems efficiently.

[0328] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0329] Step 1:

[0330] The server collects technical information from various data sources (the internet, specialized databases, etc.). Input consists of user requests and pre-configured information collection targets. The server uses crawling technology and natural language processing to organize the data and store it in a structured database. Output is a collection of technical information that can be efficiently searched and processed.

[0331] Step 2:

[0332] The server uses collected technical information as input to train a generative AI model. This model tokenizes the technical information and uses machine learning algorithms to summarize it and extract related information. If necessary, it classifies the data through clustering and topic modeling. The output consists of a summary of the information and a set of related pieces of information.

[0333] Step 3:

[0334] The user enters technical questions or queries into the terminal in the form of prompts. This serves as direct input to the system, clarifying the user's current technical concerns and problems. The output is data used to interpret what the user is asking for.

[0335] Step 4:

[0336] The device activates an emotion engine and uses its camera and microphone to analyze the user's facial expressions and voice in real time. The input consists of the user's facial movements and voice tone, which are passed to the emotion recognition algorithm as biometric data. The output is the user's emotional state (e.g., irritation, confusion, joy).

[0337] Step 5:

[0338] The server uses the user's emotional state obtained in step 4 as input to adjust how the information extracted from the generative model is presented. In this process, the format and level of detail of the information are optimized according to the user's emotions. The output is the format of information presentation that is easiest for the user to understand.

[0339] Step 6:

[0340] The terminal presents information to the user as visual data (diagrams, flowcharts) and auditory data (audio guides, video explanations) based on the adjusted information. Input is optimized information from the server, which is then processed for visualization and audio before being provided to the user. Output is the final information received by the user.

[0341] (Application Example 2)

[0342] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0343] In modern information systems, technical information is often provided in a one-way and general manner. This results in a lack of information delivery tailored to the emotional state of individual users, leading to challenges in information comprehension efficiency and optimized user experience. This is particularly true for technologies familiar to people, such as home assistant robots, where responses and support tailored to the user's emotions are required, but achieving this is difficult.

[0344] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0345] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for adjusting the method of presenting information. This makes it possible to present information in accordance with the user's emotional state.

[0346] "Technical information" refers to information that includes specialized or technical content and is provided as data necessary for the system to use.

[0347] A "generative model" is an algorithm or data model that learns from collected technical information and generates or transforms new information.

[0348] A "summary" refers to the result of a generative model concisely representing the information it has learned and extracting the most relevant points.

[0349] "Means of visual presentation" refers to functions that convey information to users in a visual format, such as diagrams, images, or flowcharts.

[0350] "Means of auditory presentation" refers to functions that provide information to users through auditory means such as sound and music.

[0351] "User" refers to any person who operates this system or receives information from it.

[0352] "Methods for analyzing emotions" refer to technologies for evaluating and analyzing a user's emotional state based on their facial expressions, voice, and other expressions.

[0353] "Means for adjusting the method of information presentation" refers to a function that changes the format and content of information based on analyzed emotions, and provides it to the user in the most optimal way.

[0354] In the system that implements this application, multiple components work together. First, a server collects a wide range of technical information and stores it in a database. This data is then used to train a generative AI model, which performs summarization and extracts relevant information. The server uses common cloud platforms and data processing software to perform these processes.

[0355] The device incorporates an emotion engine that analyzes the user's emotional state. The emotion engine monitors the user's facial expressions, voice, and biometric data in real time to identify specific emotions. Small hardware such as a Raspberry Pi is often used for this purpose. In addition, real-time emotion analysis is achieved by utilizing open-source emotion recognition libraries such as OpenCV.

[0356] Based on user input, the server adjusts how information extracted by the generative AI model is presented according to the user's emotional data. For example, if the user is irritated, information is provided in a concise and direct format; if the user is calm, more detailed and comprehensive information is presented.

[0357] For example, when a user asks for help with a complex setup process, the emotion engine recognizes the user's confusion and the server provides step-by-step instructions and charts in a visually easy-to-understand format. An example of a prompt message would be, "The user has been identified as tired. Please generate a message suggesting relaxing music."

[0358] In this way, the system provides optimal information tailored to the user's emotions and supports effective problem-solving. Furthermore, the system's flexible response allows for a more user-friendly experience.

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The server collects technical information from the internet and internal networks and stores it in a database. The collection process gathers relevant information through web crawlers and APIs. The input is raw technical information, and the output is an organized dataset.

[0362] Step 2:

[0363] The server inputs the accumulated data into a generating AI model to train the model. The model is designed to summarize information and extract relevant information. The input is a large technical information dataset, and the output is summarized information and relevant information. Here, the model's algorithm is used to learn data patterns.

[0364] Step 3:

[0365] The user enters a technical query into the terminal. The terminal uses an emotion engine to analyze the user's facial expressions, voice, and biometric data in real time to identify their emotional state. The input consists of the user's physical and auditory characteristics, and the output is identified emotion data.

[0366] Step 4:

[0367] The server queries a generative AI model for the optimal information presentation method based on emotional data and technical queries. It provides the generative model with emotional data as prompts, generating user-friendly information. The input consists of emotional states and related technical information, while the output is adjusted information tailored to the user's state.

[0368] Step 5:

[0369] The terminal presents the user with pre-configured information. Visual information is displayed using a graphical user interface, and auditory information is played back as sound. Input is pre-configured information from the server, and output is visual or auditory feedback directed to the user.

[0370] These processing steps allow the system to consider the user's emotions and provide information in the most optimal format, effectively supporting problem-solving.

[0371] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0372] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0373] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0374] [Third Embodiment]

[0375] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0376] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0377] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0378] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0379] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0380] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0381] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0382] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0383] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0384] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0385] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0386] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0387] This invention is a system that consistently performs tasks from the collection of technical information to data processing using a generative model and the presentation of that information. The operation of this system is described below.

[0388] The server collects technical information. This technical information comes from databases, past cases, manuals, and industry standards. This collected information is cleansed into a specific format and managed centrally.

[0389] Next, the server trains a generative model based on this information. The generative model learns from a large amount of technical information and acquires the knowledge necessary to summarize technical documents and answer user queries. This learning process uses machine learning and natural language processing techniques.

[0390] Once information processing is complete, the terminal receives the user's query and contacts the server. The server uses a generative model to quickly summarize the information, extract relevant details, and organize them into structured data. This data is then presented visually or audibly in a format easily understood by engineers.

[0391] For example, if a user wants to know how to fix a base station communication failure, they enter a query into their terminal. In response, the server summarizes relevant past failure information and repair procedures and provides them to the terminal as a flowchart or video explanation. This allows users to quickly obtain accurate information based on past experience and respond to failures appropriately and quickly.

[0392] This system avoids delays caused by a lack of technical knowledge among engineers, significantly improving operational efficiency and responsiveness.

[0393] The following describes the processing flow.

[0394] Step 1:

[0395] The server periodically collects technical information from databases and external data sources. This includes technical documents, manuals, know-how, and records of past incident response. The collected information undergoes data cleansing to organize its content and format it correctly.

[0396] Step 2:

[0397] The server trains a generative model based on the cleansed information. This model improves its ability to summarize technical information and quickly extract relevant information in response to user queries.

[0398] Step 3:

[0399] Users input specific technical problems or questions through the terminal's interface. For example, they might enter a query about troubleshooting techniques for base stations.

[0400] Step 4:

[0401] The terminal sends queries from the user to the server and requests the provision of necessary information.

[0402] Step 5:

[0403] The server uses a pre-trained generative model to quickly extract relevant information from the database based on the received query. Furthermore, the extracted information is summarized by the generative model and organized into structured data.

[0404] Step 6:

[0405] The server uses computer vision technology to generate diagrams and flowcharts based on summarized information and related procedures. Furthermore, it creates video explanations to supplement the explanations using video generation technology.

[0406] Step 7:

[0407] The terminal presents the user with summary information, diagrams, flowcharts, and videos provided by the server. This allows the user to instantly understand the information necessary for problem-solving through both visual and auditory means.

[0408] (Example 1)

[0409] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0410] Modern engineers are required to make quick and accurate decisions, but efficiently extracting and understanding the necessary information from a vast amount of technical data is not easy. Furthermore, to cope with the rapid increase in technical information, detailed analysis and knowledge summarization are required, going beyond mere information retrieval. This invention aims to solve the problems of information processing delays and inaccuracies faced by such engineers.

[0411] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0412] In this invention, the server includes means for automatically extracting technical information from various sources and organizing and managing it in a unified format; means for training a generative model using machine learning techniques based on the organized technical information; and means for summarizing information based on received queries and generating it as structured data using the trained generative model. This enables engineers to obtain the necessary information more quickly and accurately than with conventional information processing, thereby improving the efficiency of their work.

[0413] "Technical information" refers to data and knowledge related to a technical field, and can be obtained from a variety of sources, such as databases, case studies, manuals, and standards.

[0414] "Information sources" refer to the sources from which technical information is obtained, and include databases, documented case studies, industry manuals, and standards.

[0415] A "format" is a framework for arranging information into a specific form and is used to maintain data consistency.

[0416] "Machine learning technology" refers to algorithms and methods that process large amounts of data and automatically learn patterns and rules from it.

[0417] A "generative model" is a mathematical model used to generate new information or data based on knowledge learned through machine learning.

[0418] "Structured data" refers to information that is organized according to certain rules and stored in a format that allows for efficient access and analysis.

[0419] "Inquiry" refers to a question or request that a user makes to a system in order to obtain specific information.

[0420] The following describes the "modes for carrying out the invention."

[0421] This invention describes a method for constructing a system that efficiently manages technical information and responds quickly to user inquiries.

[0422] The server collects technical information from a variety of sources. These sources include databases, historical cases, industry manuals, and standards. This information is organized into a unified format through data cleansing processes, enabling efficient management.

[0423] Next, the server uses the collected technical information to train a generative AI model. This process utilizes machine learning and natural language processing techniques. Specifically, deep learning frameworks such as TensorFlow and PyTorch are used to learn useful patterns and knowledge from large amounts of data.

[0424] After processing the information, the terminal receives inquiries from the user. The user can enter specific queries into the terminal, such as how to repair communication failures at the base station. Examples of prompt messages include: "Please tell me the repair procedure when a communication failure occurs at the base station," and "Please summarize the risks and countermeasures for introducing new technologies."

[0425] The server uses a generated AI model based on the received query to quickly search for and summarize relevant technical information. As a result, the technical information is organized as structured data and provided to the user via the terminal. By presenting the information visually as diagrams and flowcharts, and aurally as video explanations, engineers can easily understand the information and utilize it in their work.

[0426] Therefore, this system allows engineers to efficiently acquire necessary information and achieve faster and more accurate work.

[0427] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0428] Step 1:

[0429] The server collects technical information from diverse sources. Inputs include database connection information and access rights to documented technical data. Specifically, the server queries the database via an API to retrieve relevant information. The output is an initial dataset of the retrieved technical information.

[0430] Step 2:

[0431] The server organizes the collected technical information through a data cleansing process. The input is the raw technical information collected earlier. At this stage, natural language processing techniques are used to remove duplicate text and standardize the format. The output is a cleansed dataset organized in a standardized format.

[0432] Step 3:

[0433] The server trains a generative AI model using organized technical information. The input is a cleansed technical information dataset. Specifically, the server applies deep learning algorithms using TensorFlow or PyTorch to learn patterns and features. The output is an optimized generative model.

[0434] Step 4:

[0435] The terminal receives inquiries from the user. Input consists of prompts and query text entered by the user into the terminal. Specifically, the terminal receives queries through the user interface and sends them to the server. Output is the user query information sent to the server.

[0436] Step 5:

[0437] The server uses a generative model based on the received user query to retrieve and summarize relevant information. The input consists of the user query information and the trained generative model. At this stage, the model extracts and summarizes the technical information corresponding to the query. The output is the summarized technical information and related data.

[0438] Step 6:

[0439] The terminal provides the user with summarized information received from the server. Input consists of summarized technical information and related data. Specifically, the terminal visually converts the information into a flowchart or presents it audibly as a video explanation. Output is an easily understandable information display.

[0440] (Application Example 1)

[0441] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0442] In manufacturing environments such as factories, it is crucial for technicians to obtain information that allows them to respond quickly and accurately to equipment failures and problems. However, traditional methods require manual referencing of past cases and manuals, which is time-consuming and cumbersome. To solve this problem, a system is needed that efficiently collects and processes technical information and presents solutions in real time.

[0443] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0444] In this invention, the server includes means for collecting technical information, means for providing a generative model that learns based on the collected technical information, and means for processing the information learned by the generative model based on user queries received through speech recognition. This enables the user to quickly obtain appropriate technical information in response to a query made via voice and to confirm the information by visual or auditory means.

[0445] "Technical information" refers to knowledge and data related to the operation, repair, and maintenance of equipment, and is collected from sources such as past cases, manuals, and industry standards.

[0446] A "generative model" is a machine learning algorithm that learns from a large amount of technical information and generates summaries of that information or answers to user queries.

[0447] A "user query" is a question or request that a technician sends to a server via voice or text in order to obtain technical information.

[0448] "Speech recognition" is a technology that converts user-inputted speech into text data, playing a role in making voice input into a format that the server can understand.

[0449] "Visual presentation" refers to a method of displaying technical information on a screen using diagrams and interactive media, which helps users easily understand the information.

[0450] "Auditory presentation" refers to a method of conveying technical information to users through audio and video, with the aim of providing information without relying on visual means.

[0451] The system for implementing this invention mainly consists of a server, terminals, and users. The server is responsible for collecting a wide range of technical information and training a generative AI model based on that information. The server stores technical information obtained from industry standards and past cases in a database, cleanses the data into a certain format, and manages it centrally. The generative AI model also uses this information to learn and acquire the knowledge necessary for summarizing and extracting relevant information. TensorFlow and PyTorch, which are Python-based machine learning libraries, are used for training the generative AI model, and Transformers (Hugging Face) is used for natural language processing.

[0452] The device uses speech recognition technology to receive voice queries from users. The Google Cloud Speech-to-Text API is used for speech recognition, efficiently converting speech into text data. The user queries, now in text format, are sent to a server and rapidly processed by a generative AI model.

[0453] When users need technical information, such as when encountering robot problems on a factory production line, they can instantly obtain the necessary information via their smart devices. The server summarizes past troubleshooting cases and solutions corresponding to user queries and presents them as interactive media or visual content. This allows users to quickly take the necessary actions.

[0454] As a concrete example, consider a situation where a transport robot on a manufacturing line unexpectedly stops. In this case, the technician uses smart glasses to voice-input a prompt: "The transport robot has stopped. Please tell me the cause and repair procedure." Once this query is processed by the server, an appropriate diagnosis and repair procedure based on past repair history are visually displayed on the terminal. This consistent flow enables the technician to respond quickly and accurately.

[0455] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0456] Step 1:

[0457] The server collects technical information. It gathers a wide range of technical information from databases, past cases, manuals, and industry standards, cleanses the data into a consistent format, and manages it centrally. The input for this step is raw technical information, and the output is cleansed technical data.

[0458] Step 2:

[0459] The server trains a generative AI model based on the collected, cleansed technical information. In this step, machine learning is performed using TensorFlow or PyTorch, and natural language processing techniques are applied using Transformers (Hugging Face). The input is cleansed technical data, and the output is a generative model with the knowledge to answer user queries.

[0460] Step 3:

[0461] The user enters a voice query into the terminal. Specifically, they voice the prompt, "The transport robot has stopped. Please tell me the cause and the repair procedure." This input is voice data, which is then converted into text data using the Google Cloud Speech-to-Text API.

[0462] Step 4:

[0463] The terminal sends the voice-recognized query as text data to the server. The input for this step is the text data of the voice query, and the server completes the reception as output.

[0464] Step 5:

[0465] The server processes the text data of the received user query using a generative AI model to generate relevant technical information and summaries. Based on the query, the server searches a database to extract relevant past cases and repair procedures. The input consists of the user query text data and the generative model, and the output is a summary of the generated technical information.

[0466] Step 6:

[0467] The terminal presents generated information sent from the server to the user visually or audibly. The terminal displays interactive media and text on a smart device, providing information in a format easily understood by the user. The input is a summary of the generated information, and the output is a visual or audible presentation.

[0468] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0469] This invention is a system that combines an emotion engine with the provision of technical information, enabling more effective information transmission by adjusting the method of information presentation based on the user's emotions. This system integrates everything from the collection of technical information to learning by a generative model, and further to the provision of information based on the recognition of the user's emotions.

[0470] First, the server collects a wide range of technical information and stores it in a database. This information is then trained by a generative model, which efficiently performs summarization and extracts relevant information.

[0471] When a user enters a technical query into the terminal, the terminal uses an emotion engine to analyze the user's current emotional state. The emotion engine monitors the user's facial expressions, tone of voice, biometric data, etc., in real time to identify emotions such as joy, frustration, and confusion.

[0472] The server adjusts how it presents information extracted by the generative model based on the emotional data sent from the emotion engine. For example, if the user is irritated, it provides information in a more concise and direct format, while if the user is calm, it presents detailed and comprehensive information.

[0473] The device provides users with adjusted information in the form of diagrams, flowcharts, or video explanations. This allows users to receive information tailored to their emotional state and effectively solve problems.

[0474] For example, if a user requests help with a complex setup process, and the emotion engine recognizes the user's frustration, the server will provide step-by-step instructions and charts, offering information in a visually easy-to-understand format. Conversely, if the user shows confidence, the system may provide more detailed information and alternative procedures. This ensures that the system always provides a user-friendly experience.

[0475] The following describes the processing flow.

[0476] Step 1:

[0477] The server collects technical information, including manuals, technical documents, and past troubleshooting examples from the database. The collected data is formatted and stored in the database.

[0478] Step 2:

[0479] The server trains a generative model based on this technical information. This model uses natural language processing techniques to enable information summarization and efficient extraction of relevant information.

[0480] Step 3:

[0481] The user enters a query through the terminal interface. This query includes details about a specific technical problem or the information they are seeking.

[0482] Step 4:

[0483] The device activates an emotion engine simultaneously with query input, collecting the user's facial expressions, voice tone, and other biometric data through sensors to analyze the user's emotions.

[0484] Step 5:

[0485] The server receives queries and sentiment data from the terminal, extracts relevant information using a generative model, and creates a summary tailored to the user's sentiment. It adjusts the focus and level of detail of the information according to the sentiment.

[0486] Step 6:

[0487] The server constructs the processed information as diagrams, flowcharts, or video explanations using computer vision and multimedia technologies.

[0488] Step 7:

[0489] The device presents the constructed information to the user. This allows the user to receive information optimized to their emotional state and use it to solve problems. For example, if the emotion engine detects the user's confusion, the system will directly visualize and present detailed steps in diagrams.

[0490] (Example 2)

[0491] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0492] Conventional systems that provide technical information present information uniformly and lack the flexibility to respond to the user's emotional state. As a result, users may find it difficult to understand the information. This invention aims to solve this problem and realize information provision optimized for the user's emotional state.

[0493] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0494] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for analyzing the user's emotional state. This makes it possible to adjust the information presentation method according to the user's emotional state and achieve optimal information provision.

[0495] "Technical information" is a general term for data and insights related to specialized knowledge and technology, and is part of the information sources provided by the system.

[0496] A "generative model" refers to an algorithm or system that processes and learns information based on collected data, and has the ability to summarize and extract relevant information.

[0497] "Means for analyzing a user's emotional state" refers to processes and technologies for identifying what emotions a user is currently experiencing, using the user's facial expressions, voice, and biometric data to identify emotions.

[0498] "Adjusting the method of information presentation" refers to the process of optimizing the format and content of information presentation according to the user's emotional state, so that users can receive information more effectively.

[0499] "Means of visual or auditory presentation" refers to processes and technologies that provide information to users using visual elements (diagrams, flowcharts, etc.) or auditory elements (audio guides, video explanations, etc.).

[0500] This invention is an information provision system based on technical information and the user's emotional state, and it realizes information presentation optimized for the user's emotions. This system mainly consists of processes of information collection, learning by a generative model, emotion analysis, and information presentation adjustment.

[0501] The server collects technical information from a wide range of sources and stores it in a database. Based on this information, a generative AI model is used to learn and summarize the information and extract relevant information. The generative AI model utilizes hardware such as high-performance computers equipped with GPUs to efficiently process diverse information using natural language processing techniques.

[0502] Users input technical questions and issues via the terminal in the form of prompts. Examples of such prompts include: "Please tell me how to configure the database," or "Please provide troubleshooting steps based on technical information. However, my current emotional state is frustration."

[0503] The device is equipped with an emotion engine to analyze the user's emotional state, acquiring and analyzing the user's facial expressions, voice tone, and biometric data in real time through the camera and microphone. Based on this information, the server adjusts how the information extracted by the generative model is presented, and the device provides the information in a format optimized for the user's emotions. Specifically, when the user is confused, it can generate visually easy-to-understand diagrams and flowcharts, while when the user is calm, it can present detailed information.

[0504] This system allows users to obtain information in a format that is optimal for their emotional state, making it easier to solve problems efficiently.

[0505] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0506] Step 1:

[0507] The server collects technical information from various data sources (the internet, specialized databases, etc.). Input consists of user requests and pre-configured information collection targets. The server uses crawling technology and natural language processing to organize the data and store it in a structured database. Output is a collection of technical information that can be efficiently searched and processed.

[0508] Step 2:

[0509] The server uses collected technical information as input to train a generative AI model. This model tokenizes the technical information and uses machine learning algorithms to summarize it and extract related information. If necessary, it classifies the data through clustering and topic modeling. The output consists of a summary of the information and a set of related pieces of information.

[0510] Step 3:

[0511] The user enters technical questions or queries into the terminal in the form of prompts. This serves as direct input to the system, clarifying the user's current technical concerns and problems. The output is data used to interpret what the user is asking for.

[0512] Step 4:

[0513] The device activates an emotion engine and uses its camera and microphone to analyze the user's facial expressions and voice in real time. The input consists of the user's facial movements and voice tone, which are passed to the emotion recognition algorithm as biometric data. The output is the user's emotional state (e.g., irritation, confusion, joy).

[0514] Step 5:

[0515] The server uses the user's emotional state obtained in step 4 as input to adjust how the information extracted from the generative model is presented. In this process, the format and level of detail of the information are optimized according to the user's emotions. The output is the format of information presentation that is easiest for the user to understand.

[0516] Step 6:

[0517] The terminal presents information to the user as visual data (diagrams, flowcharts) and auditory data (audio guides, video explanations) based on the adjusted information. Input is optimized information from the server, which is then processed for visualization and audio before being provided to the user. Output is the final information received by the user.

[0518] (Application Example 2)

[0519] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0520] In modern information systems, technical information is often provided in a one-way and general manner. This results in a lack of information delivery tailored to the emotional state of individual users, leading to challenges in information comprehension efficiency and optimized user experience. This is particularly true for technologies familiar to people, such as home assistant robots, where responses and support tailored to the user's emotions are required, but achieving this is difficult.

[0521] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0522] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for adjusting the method of presenting information. This makes it possible to present information in accordance with the user's emotional state.

[0523] "Technical information" refers to information that includes specialized or technical content and is provided as data necessary for the system to use.

[0524] A "generative model" is an algorithm or data model that learns from collected technical information and generates or transforms new information.

[0525] A "summary" refers to the result of a generative model concisely representing the information it has learned and extracting the most relevant points.

[0526] "Means of visual presentation" refers to functions that convey information to users in a visual format, such as diagrams, images, or flowcharts.

[0527] "Means of auditory presentation" refers to functions that provide information to users through auditory means such as sound and music.

[0528] "User" refers to any person who operates this system or receives information from it.

[0529] "Methods for analyzing emotions" refer to technologies for evaluating and analyzing a user's emotional state based on their facial expressions, voice, and other expressions.

[0530] "Means for adjusting the method of information presentation" refers to a function that changes the format and content of information based on analyzed emotions, and provides it to the user in the most optimal way.

[0531] In the system that implements this application, multiple components work together. First, a server collects a wide range of technical information and stores it in a database. This data is then used to train a generative AI model, which performs summarization and extracts relevant information. The server uses common cloud platforms and data processing software to perform these processes.

[0532] The device incorporates an emotion engine that analyzes the user's emotional state. The emotion engine monitors the user's facial expressions, voice, and biometric data in real time to identify specific emotions. Small hardware such as a Raspberry Pi is often used for this purpose. In addition, real-time emotion analysis is achieved by utilizing open-source emotion recognition libraries such as OpenCV.

[0533] Based on user input, the server adjusts how information extracted by the generative AI model is presented according to the user's emotional data. For example, if the user is irritated, information is provided in a concise and direct format; if the user is calm, more detailed and comprehensive information is presented.

[0534] For example, when a user asks for help with a complex setup process, the emotion engine recognizes the user's confusion and the server provides step-by-step instructions and charts in a visually easy-to-understand format. An example of a prompt message would be, "The user has been identified as tired. Please generate a message suggesting relaxing music."

[0535] In this way, the system provides optimal information tailored to the user's emotions and supports effective problem-solving. Furthermore, the system's flexible response allows for a more user-friendly experience.

[0536] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0537] Step 1:

[0538] The server collects technical information from the internet and internal networks and stores it in a database. The collection process gathers relevant information through web crawlers and APIs. The input is raw technical information, and the output is an organized dataset.

[0539] Step 2:

[0540] The server inputs the accumulated data into a generating AI model to train the model. The model is designed to summarize information and extract relevant information. The input is a large technical information dataset, and the output is summarized information and relevant information. Here, the model's algorithm is used to learn data patterns.

[0541] Step 3:

[0542] The user enters a technical query into the terminal. The terminal uses an emotion engine to analyze the user's facial expressions, voice, and biometric data in real time to identify their emotional state. The input consists of the user's physical and auditory characteristics, and the output is identified emotion data.

[0543] Step 4:

[0544] The server queries a generative AI model for the optimal information presentation method based on emotional data and technical queries. It provides the generative model with emotional data as prompts, generating user-friendly information. The input consists of emotional states and related technical information, while the output is adjusted information tailored to the user's state.

[0545] Step 5:

[0546] The terminal presents the user with pre-configured information. Visual information is displayed using a graphical user interface, and auditory information is played back as sound. Input is pre-configured information from the server, and output is visual or auditory feedback directed to the user.

[0547] These processing steps allow the system to consider the user's emotions and provide information in the most optimal format, effectively supporting problem-solving.

[0548] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0549] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0550] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0551] [Fourth Embodiment]

[0552] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0553] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0554] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0555] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0556] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0557] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0558] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0559] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0560] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0561] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0562] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0563] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0564] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0565] This invention is a system that consistently performs tasks from the collection of technical information to data processing using a generative model and the presentation of that information. The operation of this system is described below.

[0566] The server collects technical information. This technical information comes from databases, past cases, manuals, and industry standards. This collected information is cleansed into a specific format and managed centrally.

[0567] Next, the server trains a generative model based on this information. The generative model learns from a large amount of technical information and acquires the knowledge necessary to summarize technical documents and answer user queries. This learning process uses machine learning and natural language processing techniques.

[0568] Once information processing is complete, the terminal receives the user's query and contacts the server. The server uses a generative model to quickly summarize the information, extract relevant details, and organize them into structured data. This data is then presented visually or audibly in a format easily understood by engineers.

[0569] For example, if a user wants to know how to fix a base station communication failure, they enter a query into their terminal. In response, the server summarizes relevant past failure information and repair procedures and provides them to the terminal as a flowchart or video explanation. This allows users to quickly obtain accurate information based on past experience and respond to failures appropriately and quickly.

[0570] This system avoids delays caused by a lack of technical knowledge among engineers, significantly improving operational efficiency and responsiveness.

[0571] The following describes the processing flow.

[0572] Step 1:

[0573] The server periodically collects technical information from databases and external data sources. This includes technical documents, manuals, know-how, and records of past incident response. The collected information undergoes data cleansing to organize its content and format it correctly.

[0574] Step 2:

[0575] The server trains a generative model based on the cleansed information. This model improves its ability to summarize technical information and quickly extract relevant information in response to user queries.

[0576] Step 3:

[0577] Users input specific technical problems or questions through the terminal's interface. For example, they might enter a query about troubleshooting techniques for base stations.

[0578] Step 4:

[0579] The terminal sends queries from the user to the server and requests the provision of necessary information.

[0580] Step 5:

[0581] The server uses a pre-trained generative model to quickly extract relevant information from the database based on the received query. Furthermore, the extracted information is summarized by the generative model and organized into structured data.

[0582] Step 6:

[0583] The server uses computer vision technology to generate diagrams and flowcharts based on summarized information and related procedures. Furthermore, it creates video explanations to supplement the explanations using video generation technology.

[0584] Step 7:

[0585] The terminal presents the user with summary information, diagrams, flowcharts, and videos provided by the server. This allows the user to instantly understand the information necessary for problem-solving through both visual and auditory means.

[0586] (Example 1)

[0587] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0588] Modern engineers are required to make quick and accurate decisions, but efficiently extracting and understanding the necessary information from a vast amount of technical data is not easy. Furthermore, to cope with the rapid increase in technical information, detailed analysis and knowledge summarization are required, going beyond mere information retrieval. This invention aims to solve the problems of information processing delays and inaccuracies faced by such engineers.

[0589] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0590] In this invention, the server includes means for automatically extracting technical information from various sources and organizing and managing it in a unified format; means for training a generative model using machine learning techniques based on the organized technical information; and means for summarizing information based on received queries and generating it as structured data using the trained generative model. This enables engineers to obtain the necessary information more quickly and accurately than with conventional information processing, thereby improving the efficiency of their work.

[0591] "Technical information" refers to data and knowledge related to a technical field, and can be obtained from a variety of sources, such as databases, case studies, manuals, and standards.

[0592] "Information sources" refer to the sources from which technical information is obtained, and include databases, documented case studies, industry manuals, and standards.

[0593] A "format" is a framework for arranging information into a specific form and is used to maintain data consistency.

[0594] "Machine learning technology" refers to algorithms and methods that process large amounts of data and automatically learn patterns and rules from it.

[0595] A "generative model" is a mathematical model used to generate new information or data based on knowledge learned through machine learning.

[0596] "Structured data" refers to information that is organized according to certain rules and stored in a format that allows for efficient access and analysis.

[0597] "Inquiry" refers to a question or request that a user makes to a system in order to obtain specific information.

[0598] The following describes the "modes for carrying out the invention."

[0599] This invention describes a method for constructing a system that efficiently manages technical information and responds quickly to user inquiries.

[0600] The server collects technical information from a variety of sources. These sources include databases, historical cases, industry manuals, and standards. This information is organized into a unified format through data cleansing processes, enabling efficient management.

[0601] Next, the server uses the collected technical information to train a generative AI model. This process utilizes machine learning and natural language processing techniques. Specifically, deep learning frameworks such as TensorFlow and PyTorch are used to learn useful patterns and knowledge from large amounts of data.

[0602] After processing the information, the terminal receives inquiries from the user. The user can enter specific queries into the terminal, such as how to repair communication failures at the base station. Examples of prompt messages include: "Please tell me the repair procedure when a communication failure occurs at the base station," and "Please summarize the risks and countermeasures for introducing new technologies."

[0603] The server uses a generated AI model based on the received query to quickly search for and summarize relevant technical information. As a result, the technical information is organized as structured data and provided to the user via the terminal. By presenting the information visually as diagrams and flowcharts, and aurally as video explanations, engineers can easily understand the information and utilize it in their work.

[0604] Therefore, this system allows engineers to efficiently acquire necessary information and achieve faster and more accurate work.

[0605] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0606] Step 1:

[0607] The server collects technical information from diverse sources. Inputs include database connection information and access rights to documented technical data. Specifically, the server queries the database via an API to retrieve relevant information. The output is an initial dataset of the retrieved technical information.

[0608] Step 2:

[0609] The server organizes the collected technical information through a data cleansing process. The input is the raw technical information collected earlier. At this stage, natural language processing techniques are used to remove duplicate text and standardize the format. The output is a cleansed dataset organized in a standardized format.

[0610] Step 3:

[0611] The server trains a generative AI model using organized technical information. The input is a cleansed technical information dataset. Specifically, the server applies deep learning algorithms using TensorFlow or PyTorch to learn patterns and features. The output is an optimized generative model.

[0612] Step 4:

[0613] The terminal receives inquiries from the user. Input consists of prompts and query text entered by the user into the terminal. Specifically, the terminal receives queries through the user interface and sends them to the server. Output is the user query information sent to the server.

[0614] Step 5:

[0615] The server uses a generative model based on the received user query to retrieve and summarize relevant information. The input consists of the user query information and the trained generative model. At this stage, the model extracts and summarizes the technical information corresponding to the query. The output is the summarized technical information and related data.

[0616] Step 6:

[0617] The terminal provides the user with summarized information received from the server. Input consists of summarized technical information and related data. Specifically, the terminal visually converts the information into a flowchart or presents it audibly as a video explanation. Output is an easily understandable information display.

[0618] (Application Example 1)

[0619] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0620] In manufacturing environments such as factories, it is crucial for technicians to obtain information that allows them to respond quickly and accurately to equipment failures and problems. However, traditional methods require manual referencing of past cases and manuals, which is time-consuming and cumbersome. To solve this problem, a system is needed that efficiently collects and processes technical information and presents solutions in real time.

[0621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0622] In this invention, the server includes means for collecting technical information, means for providing a generative model that learns based on the collected technical information, and means for processing the information learned by the generative model based on user queries received through speech recognition. This enables the user to quickly obtain appropriate technical information in response to a query made via voice and to confirm the information by visual or auditory means.

[0623] "Technical information" refers to knowledge and data related to the operation, repair, and maintenance of equipment, and is collected from sources such as past cases, manuals, and industry standards.

[0624] A "generative model" is a machine learning algorithm that learns from a large amount of technical information and generates summaries of that information or answers to user queries.

[0625] A "user query" is a question or request that a technician sends to a server via voice or text in order to obtain technical information.

[0626] "Speech recognition" is a technology that converts user-inputted speech into text data, playing a role in making voice input into a format that the server can understand.

[0627] "Visual presentation" refers to a method of displaying technical information on a screen using diagrams and interactive media, which helps users easily understand the information.

[0628] "Auditory presentation" refers to a method of conveying technical information to users through audio and video, with the aim of providing information without relying on visual means.

[0629] The system for implementing this invention mainly consists of a server, terminals, and users. The server is responsible for collecting a wide range of technical information and training a generative AI model based on that information. The server stores technical information obtained from industry standards and past cases in a database, cleanses the data into a certain format, and manages it centrally. The generative AI model also uses this information to learn and acquire the knowledge necessary for summarizing and extracting relevant information. TensorFlow and PyTorch, which are Python-based machine learning libraries, are used for training the generative AI model, and Transformers (Hugging Face) is used for natural language processing.

[0630] The device uses speech recognition technology to receive voice queries from users. The Google Cloud Speech-to-Text API is used for speech recognition, efficiently converting speech into text data. The user queries, now in text format, are sent to a server and rapidly processed by a generative AI model.

[0631] When users need technical information, such as when encountering robot problems on a factory production line, they can instantly obtain the necessary information via their smart devices. The server summarizes past troubleshooting cases and solutions corresponding to user queries and presents them as interactive media or visual content. This allows users to quickly take the necessary actions.

[0632] As a concrete example, consider a situation where a transport robot on a manufacturing line unexpectedly stops. In this case, the technician uses smart glasses to voice-input a prompt: "The transport robot has stopped. Please tell me the cause and repair procedure." Once this query is processed by the server, an appropriate diagnosis and repair procedure based on past repair history are visually displayed on the terminal. This consistent flow enables the technician to respond quickly and accurately.

[0633] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0634] Step 1:

[0635] The server collects technical information. It gathers a wide range of technical information from databases, past cases, manuals, and industry standards, cleanses the data into a consistent format, and manages it centrally. The input for this step is raw technical information, and the output is cleansed technical data.

[0636] Step 2:

[0637] The server trains a generative AI model based on the collected, cleansed technical information. In this step, machine learning is performed using TensorFlow or PyTorch, and natural language processing techniques are applied using Transformers (Hugging Face). The input is cleansed technical data, and the output is a generative model with the knowledge to answer user queries.

[0638] Step 3:

[0639] The user enters a voice query into the terminal. Specifically, they voice the prompt, "The transport robot has stopped. Please tell me the cause and the repair procedure." This input is voice data, which is then converted into text data using the Google Cloud Speech-to-Text API.

[0640] Step 4:

[0641] The terminal sends the voice-recognized query as text data to the server. The input for this step is the text data of the voice query, and the server completes the reception as output.

[0642] Step 5:

[0643] The server processes the text data of the received user query using a generative AI model to generate relevant technical information and summaries. Based on the query, the server searches a database to extract relevant past cases and repair procedures. The input consists of the user query text data and the generative model, and the output is a summary of the generated technical information.

[0644] Step 6:

[0645] The terminal presents generated information sent from the server to the user visually or audibly. The terminal displays interactive media and text on a smart device, providing information in a format easily understood by the user. The input is a summary of the generated information, and the output is a visual or audible presentation.

[0646] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0647] This invention is a system that combines an emotion engine with the provision of technical information, enabling more effective information transmission by adjusting the method of information presentation based on the user's emotions. This system integrates everything from the collection of technical information to learning by a generative model, and further to the provision of information based on the recognition of the user's emotions.

[0648] First, the server collects a wide range of technical information and stores it in a database. This information is then trained by a generative model, which efficiently performs summarization and extracts relevant information.

[0649] When a user enters a technical query into the terminal, the terminal uses an emotion engine to analyze the user's current emotional state. The emotion engine monitors the user's facial expressions, tone of voice, biometric data, etc., in real time to identify emotions such as joy, frustration, and confusion.

[0650] The server adjusts how it presents information extracted by the generative model based on the emotional data sent from the emotion engine. For example, if the user is irritated, it provides information in a more concise and direct format, while if the user is calm, it presents detailed and comprehensive information.

[0651] The device provides users with adjusted information in the form of diagrams, flowcharts, or video explanations. This allows users to receive information tailored to their emotional state and effectively solve problems.

[0652] For example, if a user requests help with a complex setup process, and the emotion engine recognizes the user's frustration, the server will provide step-by-step instructions and charts, offering information in a visually easy-to-understand format. Conversely, if the user shows confidence, the system may provide more detailed information and alternative procedures. This ensures that the system always provides a user-friendly experience.

[0653] The following describes the processing flow.

[0654] Step 1:

[0655] The server collects technical information, including manuals, technical documents, and past troubleshooting examples from the database. The collected data is formatted and stored in the database.

[0656] Step 2:

[0657] The server trains a generative model based on this technical information. This model uses natural language processing techniques to enable information summarization and efficient extraction of relevant information.

[0658] Step 3:

[0659] The user enters a query through the terminal interface. This query includes details about a specific technical problem or the information they are seeking.

[0660] Step 4:

[0661] The device activates an emotion engine simultaneously with query input, collecting the user's facial expressions, voice tone, and other biometric data through sensors to analyze the user's emotions.

[0662] Step 5:

[0663] The server receives queries and sentiment data from the terminal, extracts relevant information using a generative model, and creates a summary tailored to the user's sentiment. It adjusts the focus and level of detail of the information according to the sentiment.

[0664] Step 6:

[0665] The server constructs the processed information as diagrams, flowcharts, or video explanations using computer vision and multimedia technologies.

[0666] Step 7:

[0667] The device presents the constructed information to the user. This allows the user to receive information optimized to their emotional state and use it to solve problems. For example, if the emotion engine detects the user's confusion, the system will directly visualize and present detailed steps in diagrams.

[0668] (Example 2)

[0669] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0670] Conventional systems that provide technical information present information uniformly and lack the flexibility to respond to the user's emotional state. As a result, users may find it difficult to understand the information. This invention aims to solve this problem and realize information provision optimized for the user's emotional state.

[0671] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0672] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for analyzing the user's emotional state. This makes it possible to adjust the information presentation method according to the user's emotional state and achieve optimal information provision.

[0673] "Technical information" is a general term for data and insights related to specialized knowledge and technology, and is part of the information sources provided by the system.

[0674] A "generative model" refers to an algorithm or system that processes and learns information based on collected data, and has the ability to summarize and extract relevant information.

[0675] "Means for analyzing a user's emotional state" refers to processes and technologies for identifying what emotions a user is currently experiencing, using the user's facial expressions, voice, and biometric data to identify emotions.

[0676] "Adjusting the method of information presentation" refers to the process of optimizing the format and content of information presentation according to the user's emotional state, so that users can receive information more effectively.

[0677] "Means of visual or auditory presentation" refers to processes and technologies that provide information to users using visual elements (diagrams, flowcharts, etc.) or auditory elements (audio guides, video explanations, etc.).

[0678] This invention is an information provision system based on technical information and the user's emotional state, and it realizes information presentation optimized for the user's emotions. This system mainly consists of processes of information collection, learning by a generative model, emotion analysis, and information presentation adjustment.

[0679] The server collects technical information from a wide range of sources and stores it in a database. Based on this information, a generative AI model is used to learn and summarize the information and extract relevant information. The generative AI model utilizes hardware such as high-performance computers equipped with GPUs to efficiently process diverse information using natural language processing techniques.

[0680] Users input technical questions and issues via the terminal in the form of prompts. Examples of such prompts include: "Please tell me how to configure the database," or "Please provide troubleshooting steps based on technical information. However, my current emotional state is frustration."

[0681] The device is equipped with an emotion engine to analyze the user's emotional state, acquiring and analyzing the user's facial expressions, voice tone, and biometric data in real time through the camera and microphone. Based on this information, the server adjusts how the information extracted by the generative model is presented, and the device provides the information in a format optimized for the user's emotions. Specifically, when the user is confused, it can generate visually easy-to-understand diagrams and flowcharts, while when the user is calm, it can present detailed information.

[0682] This system allows users to obtain information in a format that is optimal for their emotional state, making it easier to solve problems efficiently.

[0683] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0684] Step 1:

[0685] The server collects technical information from various data sources (the internet, specialized databases, etc.). Input consists of user requests and pre-configured information collection targets. The server uses crawling technology and natural language processing to organize the data and store it in a structured database. Output is a collection of technical information that can be efficiently searched and processed.

[0686] Step 2:

[0687] The server uses collected technical information as input to train a generative AI model. This model tokenizes the technical information and uses machine learning algorithms to summarize it and extract related information. If necessary, it classifies the data through clustering and topic modeling. The output consists of a summary of the information and a set of related pieces of information.

[0688] Step 3:

[0689] The user enters technical questions or queries into the terminal in the form of prompts. This serves as direct input to the system, clarifying the user's current technical concerns and problems. The output is data used to interpret what the user is asking for.

[0690] Step 4:

[0691] The device activates an emotion engine and uses its camera and microphone to analyze the user's facial expressions and voice in real time. The input consists of the user's facial movements and voice tone, which are passed to the emotion recognition algorithm as biometric data. The output is the user's emotional state (e.g., irritation, confusion, joy).

[0692] Step 5:

[0693] The server uses the user's emotional state obtained in step 4 as input to adjust how the information extracted from the generative model is presented. In this process, the format and level of detail of the information are optimized according to the user's emotions. The output is the format of information presentation that is easiest for the user to understand.

[0694] Step 6:

[0695] The terminal presents information to the user as visual data (diagrams, flowcharts) and auditory data (audio guides, video explanations) based on the adjusted information. Input is optimized information from the server, which is then processed for visualization and audio before being provided to the user. Output is the final information received by the user.

[0696] (Application Example 2)

[0697] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In modern information systems, technical information is often provided in a one-way and general manner. This results in a lack of information delivery tailored to the emotional state of individual users, leading to challenges in information comprehension efficiency and optimized user experience. This is particularly true for technologies familiar to people, such as home assistant robots, where responses and support tailored to the user's emotions are required, but achieving this is difficult.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0700] In this invention, the server includes means for collecting technical information, means for providing a generative model, and means for adjusting the method of presenting information. This makes it possible to present information in accordance with the user's emotional state.

[0701] "Technical information" refers to information that includes specialized or technical content and is provided as data necessary for the system to use.

[0702] A "generative model" is an algorithm or data model that learns from collected technical information and generates or transforms new information.

[0703] A "summary" refers to the result of a generative model concisely representing the information it has learned and extracting the most relevant points.

[0704] "Means of visual presentation" refers to functions that convey information to users in a visual format, such as diagrams, images, or flowcharts.

[0705] "Means of auditory presentation" refers to functions that provide information to users through auditory means such as sound and music.

[0706] "User" refers to any person who operates this system or receives information from it.

[0707] "Methods for analyzing emotions" refer to technologies for evaluating and analyzing a user's emotional state based on their facial expressions, voice, and other expressions.

[0708] "Means for adjusting the method of information presentation" refers to a function that changes the format and content of information based on analyzed emotions, and provides it to the user in the most optimal way.

[0709] In the system that implements this application, multiple components work together. First, a server collects a wide range of technical information and stores it in a database. This data is then used to train a generative AI model, which performs summarization and extracts relevant information. The server uses common cloud platforms and data processing software to perform these processes.

[0710] The device incorporates an emotion engine that analyzes the user's emotional state. The emotion engine monitors the user's facial expressions, voice, and biometric data in real time to identify specific emotions. Small hardware such as a Raspberry Pi is often used for this purpose. In addition, real-time emotion analysis is achieved by utilizing open-source emotion recognition libraries such as OpenCV.

[0711] Based on user input, the server adjusts how information extracted by the generative AI model is presented according to the user's emotional data. For example, if the user is irritated, information is provided in a concise and direct format; if the user is calm, more detailed and comprehensive information is presented.

[0712] For example, when a user asks for help with a complex setup process, the emotion engine recognizes the user's confusion and the server provides step-by-step instructions and charts in a visually easy-to-understand format. An example of a prompt message would be, "The user has been identified as tired. Please generate a message suggesting relaxing music."

[0713] In this way, the system provides optimal information tailored to the user's emotions and supports effective problem-solving. Furthermore, the system's flexible response allows for a more user-friendly experience.

[0714] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0715] Step 1:

[0716] The server collects technical information from the internet and internal networks and stores it in a database. The collection process gathers relevant information through web crawlers and APIs. The input is raw technical information, and the output is an organized dataset.

[0717] Step 2:

[0718] The server inputs the accumulated data into a generating AI model to train the model. The model is designed to summarize information and extract relevant information. The input is a large technical information dataset, and the output is summarized information and relevant information. Here, the model's algorithm is used to learn data patterns.

[0719] Step 3:

[0720] The user enters a technical query into the terminal. The terminal uses an emotion engine to analyze the user's facial expressions, voice, and biometric data in real time to identify their emotional state. The input consists of the user's physical and auditory characteristics, and the output is identified emotion data.

[0721] Step 4:

[0722] The server queries a generative AI model for the optimal information presentation method based on emotional data and technical queries. It provides the generative model with emotional data as prompts, generating user-friendly information. The input consists of emotional states and related technical information, while the output is adjusted information tailored to the user's state.

[0723] Step 5:

[0724] The terminal presents the user with pre-configured information. Visual information is displayed using a graphical user interface, and auditory information is played back as sound. Input is pre-configured information from the server, and output is visual or auditory feedback directed to the user.

[0725] These processing steps allow the system to consider the user's emotions and provide information in the most optimal format, effectively supporting problem-solving.

[0726] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0727] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0728] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0729] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0730] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0731] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0732] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0733] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0734] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0735] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0736] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0737] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0738] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0739] 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.

[0740] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0741] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0742] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0743] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0744] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0745] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0746] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0747] The following is further disclosed regarding the embodiments described above.

[0748] (Claim 1)

[0749] Means of collecting technical information,

[0750] A means for providing a generative model that learns based on the aforementioned collected technical information,

[0751] A means for summarizing the information learned by the aforementioned generative model and generating it as related information,

[0752] Means for presenting the generated information visually or audibly,

[0753] A system that includes this.

[0754] (Claim 2)

[0755] The system according to claim 1, wherein the means for visual presentation includes means for generating diagrams or flowcharts.

[0756] (Claim 3)

[0757] The system according to claim 1, wherein the means for presenting information aurally includes means for generating a video explanation.

[0758] "Example 1"

[0759] (Claim 1)

[0760] A means of automatically extracting technical information from diverse sources and organizing and managing it in a unified format,

[0761] A means for training a generative model using machine learning techniques based on the aforementioned organized technical information,

[0762] A means for summarizing information based on an received query and generating it as structured data using the aforementioned trained generative model,

[0763] Means for providing the generated structured data to the user in a visual or auditory format that is easy for the user to understand,

[0764] A system that includes this.

[0765] (Claim 2)

[0766] The system according to claim 1, wherein the means of providing information visually includes means of representing the information in diagrammatic or flowchart format.

[0767] (Claim 3)

[0768] The system according to claim 1, wherein the means of providing information audibly includes means of generating information as a video explanation.

[0769] "Application Example 1"

[0770] (Claim 1)

[0771] Means of collecting technical information,

[0772] A means for providing a generative model that learns based on the aforementioned collected technical information,

[0773] A means for summarizing the information learned by the aforementioned generative model and generating it as related information,

[0774] The means for processing the generated information based on user queries received through speech recognition,

[0775] Means for presenting the processed information visually or audibly,

[0776] A system that includes this.

[0777] (Claim 2)

[0778] The system according to claim 1, wherein the means of visual or auditory presentation includes structured data or interactive media displayed on a smart device.

[0779] (Claim 3)

[0780] The system according to claim 1, wherein the means for processing information based on user queries received through the speech recognition includes means for converting speech input into text.

[0781] "Example 2 of combining an emotion engine"

[0782] (Claim 1)

[0783] Means of collecting technical information,

[0784] A means for providing a generative model that learns based on the aforementioned collected technical information,

[0785] A means for summarizing the information learned by the aforementioned generative model and generating it as related information,

[0786] A means of analyzing the user's emotional state,

[0787] Means for adjusting the information presentation method based on the aforementioned analysis,

[0788] Means for presenting the adjusted information visually or audibly,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, wherein the means for visual presentation includes means for generating diagrams or flowcharts.

[0792] (Claim 3)

[0793] The system according to claim 1, wherein the means for presenting information aurally includes means for generating an audio guide or video commentary.

[0794] "Application example 2 when combining with an emotional engine"

[0795] (Claim 1)

[0796] Means of collecting technical information,

[0797] A means for providing a generative model that learns based on the aforementioned collected technical information,

[0798] A means for summarizing the information learned by the aforementioned generative model and generating it as related information,

[0799] Means for presenting the generated information visually or audibly,

[0800] A means of analyzing user emotions,

[0801] A means for adjusting the method of presenting information based on the analyzed emotions,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, wherein the means for visual presentation further includes means for adjusting the visual information based on the analyzed emotion, which includes means for generating a diagram or flowchart.

[0805] (Claim 3)

[0806] The system according to claim 1, wherein the means for presenting information aurally further includes means for adjusting auditory information based on the analyzed emotion, which includes means for generating a video commentary. [Explanation of Symbols]

[0807] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting technical information, A means for providing a generative model that learns based on the aforementioned collected technical information, A means for summarizing the information learned by the aforementioned generative model and generating it as related information, The means for processing the generated information based on user queries received through speech recognition, Means for presenting the processed information visually or audibly, A system that includes this.

2. The system according to claim 1, wherein the means of visual or auditory presentation includes structured data or interactive media displayed on a smart device.

3. The system according to claim 1, wherein the means for processing information based on user queries received through the speech recognition includes means for converting speech input into text.

Images