system

Abstract

Provide a system. 【Solution means】 Means for receiving an information acquisition request, Means for analyzing the received request and generating a search query, Means for identifying an information source and executing a search query, Means for obtaining and organizing search results, Means for generating as a report that visually displays the organized information, Means for sending the generated report to the information acquisition requester, Means for analyzing the machine state and manufacturing progress in the manufacturing environment, Means for generating appropriate instructions for the operator based on the analysis results, A system including the above.

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 performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] In existing in-house information search systems, a lot of time and effort are required to efficiently obtain necessary information, which results in a problem of reduced work efficiency. Also, due to the dispersion of information, it is difficult to determine which information source should be accessed.

Means for Solving the Problems

[0005] This invention provides a means for identifying necessary information sources by using an AI agent that receives information acquisition requests, analyzes the requests, and generates search queries. Furthermore, it creates an environment for efficient and rapid information acquisition by organizing the acquired search results and providing the information in a user-friendly report format. In addition, the AI ​​agent can learn from the search results, thereby improving the accuracy of subsequent searches.

[0006] An "information retrieval request" is a request made by a user to a system for the purpose of obtaining specific information.

[0007] "Analysis" refers to the process of converting a received information retrieval request into a format that the system can understand and generating an appropriate search query.

[0008] A "search query" is a string of characters or a command created to find specific information from a source.

[0009] An "information source" refers to a database or system that stores the necessary information.

[0010] "Search results" refer to information obtained from sources through the execution of a search query.

[0011] "Organization" refers to the process of classifying, rearranging, and summarizing collected search results in a way that is easy for users to understand.

[0012] A "report" is a document that presents organized information in visual or written form to communicate it to a user.

[0013] An "AI agent" is a program or system that uses artificial intelligence to autonomously perform information analysis and retrieval.

[0014] "Learning" refers to the process by which an AI agent internally accumulates data and improves its search accuracy based on past search experiences and results.

Brief Description of the Drawings

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which 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.

Modes for Carrying Out the Invention

[0016] Next, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] 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.

[0019] 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.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. 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.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention begins with a user making an information retrieval request from a terminal, which the server receives and activates an AI agent. The AI ​​agent analyzes the received request using natural language processing technology and generates an appropriate search query to retrieve the relevant information. The server then uses the generated search query to identify the information source, such as internal databases or systems, and accesses them quickly and efficiently.

[0037] As a concrete example, consider a scenario where a user requests to know the development progress of a new product. The server receives this request and analyzes it using an AI agent. The AI ​​agent constructs a search query based on keywords such as "new product," "development," and "progress," and identifies project management systems and related documents. As a result, the server collects relevant information such as reports and meeting minutes.

[0038] The collected information is organized by the server and generated as a visually easy-to-understand report. This allows users to receive and easily understand the report on their own devices. The report uses graphs and tables to make the data explanation easier to understand.

[0039] Furthermore, this system allows the AI ​​agent to learn from past search experiences, enabling more accurate information retrieval in subsequent searches. As a result, users can access optimized information even with repeated requests, significantly improving work efficiency.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uses their device to input a request for specific information. The request is made in natural language and sent from the device to the server.

[0043] Step 2:

[0044] The server receives an information retrieval request from the user and begins preparing for analysis. This process requires converting the request into an easily understandable format.

[0045] Step 3:

[0046] The server activates an AI agent, which analyzes the request using natural language processing technology. The AI ​​agent analyzes the request and generates a search query.

[0047] Step 4:

[0048] The server identifies information sources based on the generated search queries. These sources can be diverse, including internal databases and project management systems.

[0049] Step 5:

[0050] The server applies search queries to identified information sources and retrieves the information. Access control is considered here, and necessary security authentication procedures are performed.

[0051] Step 6:

[0052] The server organizes the acquired information, classifies the data in a way that is easy for the user to understand, and creates a summarized report. It also generates graphs and tables as needed.

[0053] Step 7:

[0054] The server sends the organized report to the user's terminal. The user can then review the information and use it to improve their work.

[0055] Step 8:

[0056] The AI ​​agent learns from the current search process and updates its database to improve the accuracy of future searches, making it useful for future information retrievals.

[0057] (Example 1)

[0058] 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."

[0059] Conventional information retrieval systems suffered from limited efficiency and accuracy in information acquisition, making it difficult for users to obtain the information they needed quickly and accurately. In particular, correctly analyzing information retrieval requests entered in natural language and quickly identifying relevant information sources was difficult, resulting in users spending a lot of time on the process. Furthermore, there was a lack of technology to facilitate the visual understanding of retrieved information and to present it in an easily usable format. In addition, the system's mechanism for learning from past information retrieval experiences and applying that knowledge to subsequent searches was insufficient, thus requiring continuous improvement.

[0060] 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.

[0061] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received information acquisition requests using natural language processing technology and generating search queries, and means for identifying electronic information sources and acquiring information using the generated search queries. This enables the rapid identification and acquisition of relevant information from the analysis of requests in natural language.

[0062] An "information retrieval request" is a request made in natural language by a user to a system in order to obtain specific information.

[0063] A "receiving means" is a function that receives an information acquisition request and enables subsequent processing to be executed.

[0064] "Natural language processing technology" is a technology that enables computers to understand and analyze human natural language.

[0065] A "search query" is a command generated to search databases and information sources based on a user's request.

[0066] "Electronic information sources" refer to databases and information systems existing both inside and outside the company, and are information resources that contain the necessary information.

[0067] A "report" is a document or graphic representation that organizes acquired information and presents it to the user in a visually easy-to-understand format.

[0068] A "learning tool" is a function that improves the accuracy of future searches based on past search results.

[0069] "Patrol methods" refer to the function of regularly visiting information sources to collect new information.

[0070] This invention is initiated when a user sends an information retrieval request in natural language from a terminal. The user's input request is transmitted to a server via a communication network. The server is equipped with a dedicated receiving means for receiving requests, and after receiving the request, an AI agent is activated. This AI agent uses natural language processing technology to analyze the request and generate an appropriate search query. General machine learning algorithms and specific generative AI models are applied to the natural language processing.

[0071] The server uses these generated search queries to access various electronic information sources, both inside and outside the company. Examples of these sources include databases storing sales data and project management systems. The server efficiently organizes the information retrieved from these sources and generates user-friendly reports. These reports can present data clearly using visual elements such as graphs and tables.

[0072] The generated report is sent back to the user's terminal, allowing the user to quickly review the information and take action as requested. Furthermore, the system on the server has a built-in function to learn from past search experiences, enabling it to provide more accurate and efficient search results in subsequent information retrieval requests.

[0073] As a concrete example, if a user enters "I need sales data for the next monthly meeting" into their terminal, the server receives this request and begins analysis using an AI agent. Using the search query generated by the analysis, the server accesses the sales database to retrieve the information. The server then compiles the detailed sales data into a report in graph format and sends it to the user's terminal. An example of a prompt in this process would be, "Please retrieve the sales data needed for the next monthly meeting and generate a report."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user uses a terminal to input an information retrieval request in natural language and sends it to the server. An example input might be a request statement like, "I need sales data for the next monthly meeting." This request is sent from the terminal to the server via the network. The output is the server receiving the request.

[0077] Step 2:

[0078] When the server receives a request, it activates an AI agent. The AI ​​agent analyzes the received request using natural language processing techniques. The input is a natural language request from the user, and the AI ​​agent extracts keywords from this request. These keywords might include "sales data" or "monthly meeting." The output is a set of keywords to be used as a search query.

[0079] Step 3:

[0080] The server generates a search query using keywords extracted through natural language processing. The input is the set of keywords obtained in step 2, and an AI model is used to construct an effective search query. The output is the search query used to access the information source.

[0081] Step 4:

[0082] The server uses the generated search query to access internal databases and related systems. The input is the search query generated in step 3, and the server performs a search against the specified information source (e.g., sales database). The output is the required set of sales data and related information.

[0083] Step 5:

[0084] The server organizes the acquired data and generates a visually easy-to-understand report. The input is the set of information obtained in step 4, and data aggregation and analysis are performed. Specifically, the server aggregates sales data by month and creates a report in graph and table format. The output is the final report presented to the user.

[0085] Step 6:

[0086] The server sends the generated report to the user's terminal. The input is the report created in step 5, and the output is a visualized report on the user's terminal. This allows the user to quickly view the necessary data.

[0087] Step 7:

[0088] The server uses an AI agent to learn from past information retrieval experiences and improve the accuracy of subsequent searches. The input is data on previously processed search results and their efficiency, and the AI ​​agent adjusts its model based on this data. The output is the improved search algorithm.

[0089] (Application Example 1)

[0090] 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."

[0091] In the current manufacturing environment, information gathering and analysis are not performed efficiently, making it difficult to grasp manufacturing progress and machine status in real time. Furthermore, there is a lack of systems that generate appropriate instructions in situations requiring rapid response. As a result, there are challenges such as decreased work efficiency and problem-solving capabilities on the manufacturing floor, leading to impaired productivity.

[0092] 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.

[0093] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search queries, means for identifying information sources and executing search queries, means for acquiring and organizing search results, means for generating a report that visually displays the organized information, means for transmitting the generated report to the information acquisition request source, means for analyzing the machine status and manufacturing progress in the manufacturing environment, and means for generating appropriate instructions for the operator based on the analysis results. This improves the efficiency of information gathering and analysis at the manufacturing site, enabling real-time monitoring of machine status and manufacturing progress, and rapid generation of appropriate instructions.

[0094] "Means for receiving information acquisition requests" refers to a function that recognizes requests from users regarding information acquisition and delivers the content of those requests to the server.

[0095] "Means for analyzing received requests and generating search queries" refers to a function that analyzes received information retrieval requests and generates queries for efficiently searching for relevant information.

[0096] "Means for identifying information sources and executing search queries" refers to a function that uses the generated search query to identify appropriate information sources and retrieve data from them.

[0097] "Means for obtaining and organizing search results" refers to a function that efficiently collects search results obtained from information sources and organizes them in a format that is easy for users to understand.

[0098] "Means for generating reports that visually display organized information" refers to a function that generates data in a visually appealing and easy-to-understand report format based on organized information.

[0099] "Means for sending the generated report to the information requester" refers to a function that generates a visualized report and sends this report to the user who made the information request.

[0100] "Means for analyzing machine status and manufacturing progress in a manufacturing environment" refers to a function that analyzes the operating status and progress of equipment on the manufacturing floor to identify problems and areas for improvement.

[0101] "Means for generating appropriate instructions for operators based on analysis results" refers to a function that generates specific and appropriate instructions for operators on the manufacturing floor based on the analyzed data.

[0102] In the system for realizing this invention, the server, terminal, and user each play a specific role.

[0103] The server is programmed using Python and employs NLTK and spaCy for natural language processing. It also utilizes SQLAlchemy for database access and Matplotlib and Seaborn for data visualization. These software tools analyze user information requests and generate appropriate search queries. These queries are used to quickly retrieve data from information sources and generate visually organized reports. The reports prioritize visual appeal to ensure users can easily understand the data.

[0104] The system utilizes smartphones and tablets as terminals. Users submit information requests and receive reports of the acquired information through these devices. The terminals are equipped with an interface designed to allow users to easily input requests.

[0105] Users use terminals to request information to understand the situation on the manufacturing floor and the status of the machinery. Specifically, they might enter prompts such as, "Please check the manufacturing status of part X." The server responds to this request, analyzes data from the manufacturing environment, generates a clear visual report, and sends it to the terminal.

[0106] An example of a prompt message is, "Immediately identify any abnormalities in part Y during the manufacturing process and propose an appropriate solution." This allows the user to understand the situation on the manufacturing floor in real time and receive appropriate instructions for quick action.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The user uses a terminal to enter an information retrieval request. For example, they might enter a prompt message such as, "Please check the manufacturing status of part X." This input is sent to the server, where it is ready for processing.

[0110] Step 2:

[0111] The server analyzes the information retrieval request received from the user. This analysis utilizes natural language processing techniques, employing libraries such as NLTK and spaCy. Here, prompt text is extracted, relevant keywords are identified, and the data is processed to generate search queries for use in the next step.

[0112] Step 3:

[0113] The server generates a search query based on keywords obtained from the analysis and uses this query to identify information sources. SQLAlchemy is used to quickly retrieve the necessary information from the database to access these information sources. The output of query generation and data access is a raw dataset containing the specified information.

[0114] Step 4:

[0115] The server organizes the acquired data and generates a visual report. This step involves data calculations using Matplotlib and Seaborn to visualize the data as graphs and charts. This generates a report that allows users to intuitively understand the data.

[0116] Step 5:

[0117] The organized reports are sent from the server to the terminal. The terminal provides an interface that allows the user to view the reports and understand the manufacturing status and machine condition in real time. This enables the user to quickly decide on the next course of action.

[0118] 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.

[0119] This invention begins when a user requests specific information via a terminal, the server receives the request, and activates an AI agent and an emotion engine. The AI ​​agent uses natural language processing technology to analyze the user's request and generate a search query. The server then uses the generated search query to retrieve the most relevant information from internal databases and related systems.

[0120] The emotion engine evaluates data transmitted from the user's device (such as voice tone, text expression, and user choices) to recognize the user's current emotions. For example, if a user feels "very rushed," the emotion engine detects this sense of urgency. Based on this emotion, it adjusts how the retrieved information is presented, highlighting key points for clarity.

[0121] As a concrete example, consider a scenario where a user requests to "learn more about project progress and risks" via their device. The server receives and analyzes the request, and the AI ​​agent searches for relevant project management documents and reports. Meanwhile, the emotion engine detects that the user is feeling anxious based on their input method and past emotional history. The server then organizes the acquired information, clearly highlights risk factors, and generates a report designed to alleviate the user's anxiety.

[0122] Furthermore, this system receives user feedback through its emotion engine and can fine-tune how information is delivered in the future. This provides a personalized experience for each user and ensures consistently convenient information delivery. Through this process, users can receive information that resonates with their emotions quickly and accurately, improving work efficiency and satisfaction.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The user enters a request to retrieve specific information from their device. This request is sent to the server in natural language.

[0126] Step 2:

[0127] The server receives an information retrieval request from the user and activates an AI agent to analyze the request.

[0128] Step 3:

[0129] The AI ​​agent uses natural language processing to analyze requests and generate search queries. This makes it clear exactly what information is needed.

[0130] Step 4:

[0131] The server identifies internal databases and related systems based on the generated search queries and collects the appropriate information.

[0132] Step 5:

[0133] The emotion engine built into the device analyzes input data to recognize the user's emotions. This data includes text sentence structure, input speed, and voice tone.

[0134] Step 6:

[0135] The emotion engine recognizes the user's current emotional state (e.g., anxiety, worry, relaxation) and sends that information to the server.

[0136] Step 7:

[0137] The server uses information from the emotion engine to organize the collected data and generate reports tailored to the user's emotional state. For example, if the user is feeling anxious, it will focus on providing detailed information about risks.

[0138] Step 8:

[0139] The server sends the generated report to the user's terminal. The user can receive this report on their terminal and review the information.

[0140] Step 9:

[0141] When users provide feedback on a report via their device, the sentiment engine re-analyzes that feedback and incorporates it into future information delivery. This enables more personalized information delivery.

[0142] (Example 2)

[0143] 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".

[0144] Conventional information acquisition systems provide information without considering the user's emotional state, resulting in a failure to adequately reflect the urgency and importance of the information the user is seeking, leading to decreased satisfaction. Furthermore, the uniform nature of information provision, lacking personalization tailored to individual users, is a significant problem.

[0145] 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.

[0146] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search items, and means for adjusting the method of presenting information based on the emotional state. This enables the provision of personalized information according to the user's emotional state.

[0147] An "information retrieval request" is a request that a user sends to a system to obtain specific information.

[0148] "Analysis" is the process of deciphering received information or data and understanding its content.

[0149] "Search items" are queries or inquiry conditions generated to retrieve necessary information from the information infrastructure.

[0150] "Information infrastructure" refers to all databases and storage systems where data and documents are stored.

[0151] "Emotional data" refers to data necessary to understand a user's emotional state, and includes things like voice tone and written expression.

[0152] "Emotional state" refers to the user's current psychological state or mood.

[0153] A "report" is a document or digital document that is generated after the information has been collected and compiled.

[0154] Personalization is the process of optimizing information and services according to the characteristics and needs of individual users.

[0155] This invention is a system in which, in response to a user's information retrieval request, a server executes a specific process and provides appropriately adjusted information. The following main components are necessary to carry out the invention.

[0156] First, the user enters an information retrieval request into a terminal. The terminal receives this request and sends it to the server over the network. The server can use any standard server device as hardware. The software includes a database management system (e.g., MySQL® or Oracle Database using SQL) and an AI module for natural language processing (e.g., Python's NLTK or spaCy).

[0157] The server uses an AI agent to analyze received information retrieval requests and generate relevant search items. This process utilizes a generative AI model. The AI ​​agent analyzes the requests using natural language processing and generates appropriate search items for the company's internal database.

[0158] Next, an emotion engine is used to analyze the user's emotional data and recognize the user's emotional state. The emotion engine evaluates voice tone and text expression to identify the user's psychological state. Based on this, the server adjusts how to appropriately structure and present the acquired information.

[0159] As a concrete example, consider a scenario where a user requests a detailed summary of the year-end report. The server receives the request, uses an AI model to search for relevant documents, and an emotion engine analyzes the user's emotions. If the server determines the user is in a hurry, it generates a report that concisely summarizes the information, highlights key points, and sends it to the user's device.

[0160] An example of a prompt message might be: "The user has requested an overview of the year-end report on their device. The server should use an AI agent and emotion engine to analyze the information and highlight the most important details."

[0161] This invention enables users to receive information quickly and appropriately in a way that resonates with their emotions, thereby improving work efficiency and satisfaction.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The user enters an information retrieval request into the terminal and sends the request. Specifically, the user enters a request as text, such as "I want to know the latest project progress." This text data is output from the terminal and sent to the server.

[0165] Step 2:

[0166] The server receives an information retrieval request from the terminal. Based on this input data, the server activates an AI agent and analyzes the request using natural language processing technology. As a result of the analysis, specific search items are output by the generating AI model. The next step is performed using these search items.

[0167] Step 3:

[0168] The server uses the generated search items to search the information infrastructure (e.g., a database system). The server executes the search query and extracts relevant data from the information infrastructure. The extracted data is obtained as the server's output, and this is used to proceed to the next processing step.

[0169] Step 4:

[0170] The server activates the emotion engine and analyzes the user's emotional state based on the information they submit. Specifically, it evaluates the tone of voice and the expression of the input text to identify the user's psychological state. This emotional state is output and used to determine how to present information next.

[0171] Step 5:

[0172] The server adjusts how the acquired information is presented based on the user's emotional state, which is the output of the emotion engine. For example, if the situation is deemed urgent, the information is summarized clearly and important points are highlighted. This adjusted information is generated as a report and proceeds to the next step as the server's output.

[0173] Step 6:

[0174] The server sends the generated report to the terminal. The terminal receives this information and presents it to the user. This output is displayed in a format that is compatible with the user's visual or auditory perception, allowing the user to review the requested information.

[0175] Step 7:

[0176] Users send feedback on the information provided to the server via their device. This feedback is used to improve the way information is provided in the future and serves as important data for the server to make adjustments.

[0177] (Application Example 2)

[0178] 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".

[0179] In today's information society, users are required to quickly and accurately obtain the information they need from a vast amount of data. However, conventional systems have struggled to present information in a way that suits the user's emotions and circumstances, posing a challenge to improving the user experience. Furthermore, search accuracy and information delivery methods were not optimized for each user, resulting in individual differences in how information was received. These problems need to be addressed.

[0180] 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.

[0181] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the user's emotional state, and means for adjusting the information presentation method based on the analysis results. This makes it possible to present optimal information according to the user's emotions and situation.

[0182] An "information retrieval request" is a request sent to a server when a user wishes to obtain specific information.

[0183] "Analysis" refers to understanding a received request and generating an appropriate search query based on that request.

[0184] A "search query" is input data used to find the desired information from a source.

[0185] "Information source" refers to the database or related system where the information requested by the user is stored.

[0186] "Organization" refers to the process of compiling the retrieved search results into a format that is easy for the user to understand.

[0187] A "report" is a document that compiles and organizes information.

[0188] "Emotional state" refers to the emotional expressions and circumstances a user displays when requesting information.

[0189] "Analysis" refers to the process of evaluating a user's emotional data and identifying their emotions at that time based on that data.

[0190] "Adjusting the information presentation method" refers to changing the display method to provide information in the most optimal format according to the user's emotional state.

[0191] "Customized information delivery" refers to presenting information in a format that suits specific needs, based on the user's requests and emotions.

[0192] This invention is a system that begins with a user making an information retrieval request. The user uses a terminal to request specific information and sends the request to the server. Upon receiving the request, the server first uses an AI agent to analyze the request and generate an appropriate search query. This AI agent uses a natural language processing library (e.g., spaCy) to clearly understand the user's intent.

[0193] The generated search queries are executed against the source database (e.g., MySQL). The retrieved search results are then organized. This organizing process prepares the information for clear and concise presentation to the user.

[0194] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This analysis uses data sent from the user's device, such as voice tone and voice quality picked up by the smartphone's microphone. The analysis utilizes an emotion analysis library (e.g., Google® Cloud Natural Language API).

[0195] The way information is presented is adjusted based on the user's emotional state. This allows for emphasizing key points to users in a tense state and presenting more detailed information to users in a calm state.

[0196] Finally, the generated report is sent to the user's device. The report contains optimized information and is customized to the user's situation. By using this system, users can quickly and appropriately meet their needs.

[0197] As an example of a program in action, a system might ask a user, "Where are the sale items?", and then, by removing unnecessary information, tell the user the shortest route to the sale items. In this case, an example of a prompt statement used by the generative AI model would be as follows:

[0198] User request: "Where are the sale items?"

[0199] Sentiment analysis: "Users are feeling confused."

[0200] Goal: "To simply explain the location of sale items."

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The user requests information from their device. The request is entered in natural language format, and the device sends it to the server. The information entered by the user includes specific requests (e.g., inventory status). The output is the request content sent to the server.

[0204] Step 2:

[0205] The server activates an AI agent and analyzes the received information retrieval request. From the data obtained through the analysis, it generates a search query. In this step, a natural language processing library (e.g., spaCy) is used to understand the intent of the request and form the query. The input is the user's request, and the output is a query suitable for searching.

[0206] Step 3:

[0207] The server uses the generated search query to execute a query against the database, which is the source of the information. It performs query operations to retrieve relevant information from the database (e.g., MySQL). The input is the generated query, and the output is the retrieved information result.

[0208] Step 4:

[0209] The server organizes the acquired information results. The organization process condenses the information into an easily understandable format for the user. The input is raw data, and the output is the organized information.

[0210] Step 5:

[0211] The server uses an emotion engine to analyze the user's emotional state based on data received from the terminal (such as voice tone). The analysis utilizes an emotion analysis library (e.g., Google Cloud Natural Language API). The input is the user's emotion-related data, and the output is the result of the user's emotional state.

[0212] Step 6:

[0213] The server adjusts the information presentation method according to the analyzed emotional state. Based on a specific emotion, it changes the information format and the emphasis of the presented content. The input is the result of the emotional state and organized information, and the output is the adjusted information.

[0214] Step 7:

[0215] The server generates the final information as a report and sends it to the terminal. The user reviews this report and obtains the necessary information. The input is the adjusted information, and the output is the information provided to the user.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] This invention begins with a user making an information retrieval request from a terminal, which the server receives and activates an AI agent. The AI ​​agent analyzes the received request using natural language processing technology and generates an appropriate search query to retrieve the relevant information. The server then uses the generated search query to identify the information source, such as internal databases or systems, and accesses them quickly and efficiently.

[0233] As a concrete example, consider a scenario where a user requests to know the development progress of a new product. The server receives this request and analyzes it using an AI agent. The AI ​​agent constructs a search query based on keywords such as "new product," "development," and "progress," and identifies project management systems and related documents. As a result, the server collects relevant information such as reports and meeting minutes.

[0234] The collected information is organized by the server and generated as a visually easy-to-understand report. This allows users to receive and easily understand the report on their own devices. The report uses graphs and tables to make the data explanation easier to understand.

[0235] Furthermore, this system allows the AI ​​agent to learn from past search experiences, enabling more accurate information retrieval in subsequent searches. As a result, users can access optimized information even with repeated requests, significantly improving work efficiency.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The user uses their device to input a request for specific information. The request is made in natural language and sent from the device to the server.

[0239] Step 2:

[0240] The server receives an information retrieval request from the user and begins preparing for analysis. This process requires converting the request into an easily understandable format.

[0241] Step 3:

[0242] The server activates an AI agent, which analyzes the request using natural language processing technology. The AI ​​agent analyzes the request and generates a search query.

[0243] Step 4:

[0244] The server identifies information sources based on the generated search queries. These sources can be diverse, including internal databases and project management systems.

[0245] Step 5:

[0246] The server applies search queries to identified information sources and retrieves the information. Access control is considered here, and necessary security authentication procedures are performed.

[0247] Step 6:

[0248] The server organizes the acquired information, classifies the data in a way that is easy for the user to understand, and creates a summarized report. It also generates graphs and tables as needed.

[0249] Step 7:

[0250] The server sends the organized report to the user's terminal. The user can then review the information and use it to improve their work.

[0251] Step 8:

[0252] The AI ​​agent learns from the current search process and updates its database to improve the accuracy of future searches, making it useful for future information retrievals.

[0253] (Example 1)

[0254] 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."

[0255] Conventional information retrieval systems suffered from limited efficiency and accuracy in information acquisition, making it difficult for users to obtain the information they needed quickly and accurately. In particular, correctly analyzing information retrieval requests entered in natural language and quickly identifying relevant information sources was difficult, resulting in users spending a lot of time on the process. Furthermore, there was a lack of technology to facilitate the visual understanding of retrieved information and to present it in an easily usable format. In addition, the system's mechanism for learning from past information retrieval experiences and applying that knowledge to subsequent searches was insufficient, thus requiring continuous improvement.

[0256] 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.

[0257] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received information acquisition requests using natural language processing technology and generating search queries, and means for identifying electronic information sources and acquiring information using the generated search queries. This enables the rapid identification and acquisition of relevant information from the analysis of requests in natural language.

[0258] An "information retrieval request" is a request made in natural language by a user to a system in order to obtain specific information.

[0259] A "receiving means" is a function that receives an information acquisition request and enables subsequent processing to be executed.

[0260] "Natural language processing technology" is a technology that enables computers to understand and analyze human natural language.

[0261] A "search query" is a command generated to search databases and information sources based on a user's request.

[0262] "Electronic information sources" refer to databases and information systems existing both inside and outside the company, and are information resources that contain the necessary information.

[0263] A "report" is a document or graphic representation that organizes acquired information and presents it to the user in a visually easy-to-understand format.

[0264] A "learning tool" is a function that improves the accuracy of future searches based on past search results.

[0265] "Patrol methods" refer to the function of regularly visiting information sources to collect new information.

[0266] This invention is initiated when a user sends an information retrieval request in natural language from a terminal. The user's input request is transmitted to a server via a communication network. The server is equipped with a dedicated receiving means for receiving requests, and after receiving the request, an AI agent is activated. This AI agent uses natural language processing technology to analyze the request and generate an appropriate search query. General machine learning algorithms and specific generative AI models are applied to the natural language processing.

[0267] The server uses these generated search queries to access various electronic information sources, both inside and outside the company. Examples of these sources include databases storing sales data and project management systems. The server efficiently organizes the information retrieved from these sources and generates user-friendly reports. These reports can present data clearly using visual elements such as graphs and tables.

[0268] The generated report is sent back to the user's terminal, allowing the user to quickly review the information and take action as requested. Furthermore, the system on the server has a built-in function to learn from past search experiences, enabling it to provide more accurate and efficient search results in subsequent information retrieval requests.

[0269] As a concrete example, if a user enters "I need sales data for the next monthly meeting" into their terminal, the server receives this request and begins analysis using an AI agent. Using the search query generated by the analysis, the server accesses the sales database to retrieve the information. The server then compiles the detailed sales data into a report in graph format and sends it to the user's terminal. An example of a prompt in this process would be, "Please retrieve the sales data needed for the next monthly meeting and generate a report."

[0270] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0271] Step 1:

[0272] The user uses a terminal to input an information retrieval request in natural language and sends it to the server. An example input might be a request statement like, "I need sales data for the next monthly meeting." This request is sent from the terminal to the server via the network. The output is the server receiving the request.

[0273] Step 2:

[0274] When the server receives a request, it activates an AI agent. The AI ​​agent analyzes the received request using natural language processing techniques. The input is a natural language request from the user, and the AI ​​agent extracts keywords from this request. These keywords might include "sales data" or "monthly meeting." The output is a set of keywords to be used as a search query.

[0275] Step 3:

[0276] The server generates a search query using keywords extracted through natural language processing. The input is the set of keywords obtained in step 2, and an AI model is used to construct an effective search query. The output is the search query used to access the information source.

[0277] Step 4:

[0278] Using the search query generated by the server, access the in-house database and related systems. The input is the search query generated in Step 3, and the server executes a search on the specified information source (e.g., sales database). The output is a set of required sales data and related information.

[0279] Step 5:

[0280] The server organizes the data obtained and generates a visually understandable report. The input is the set of information obtained in Step 4, and data aggregation and analysis are performed. As specific operations, the server aggregates sales data monthly and creates reports in graph or table format. The output is the report finally presented to the user.

[0281] Step 6:

[0282] The server sends the report generated to the user's terminal. The input is the report created in Step 5, and the output is the report visualized on the user's terminal. Thus, the user can quickly check the required data.

[0283] Step 7:

[0284] The server uses an AI agent to learn the past information acquisition experience and improve the next search accuracy. The input is the search results processed so far and the data related to their efficiency, and the AI agent adjusts the model based on this data. The output is an improved search algorithm.

[0285] (Application Example 1)

[0286] Next, Application Example 1 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".

[0287] In the current manufacturing environment, information gathering and analysis are not performed efficiently, making it difficult to grasp manufacturing progress and machine status in real time. Furthermore, there is a lack of systems that generate appropriate instructions in situations requiring rapid response. As a result, there are challenges such as decreased work efficiency and problem-solving capabilities on the manufacturing floor, leading to impaired productivity.

[0288] 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.

[0289] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search queries, means for identifying information sources and executing search queries, means for acquiring and organizing search results, means for generating a report that visually displays the organized information, means for transmitting the generated report to the information acquisition request source, means for analyzing the machine status and manufacturing progress in the manufacturing environment, and means for generating appropriate instructions for the operator based on the analysis results. This improves the efficiency of information gathering and analysis at the manufacturing site, enabling real-time monitoring of machine status and manufacturing progress, and rapid generation of appropriate instructions.

[0290] "Means for receiving information acquisition requests" refers to a function that recognizes requests from users regarding information acquisition and delivers the content of those requests to the server.

[0291] "Means for analyzing received requests and generating search queries" refers to a function that analyzes received information retrieval requests and generates queries for efficiently searching for relevant information.

[0292] "Means for identifying information sources and executing search queries" refers to a function that uses the generated search query to identify appropriate information sources and retrieve data from them.

[0293] "Means for obtaining and organizing search results" refers to a function that efficiently collects search results obtained from information sources and organizes them in a format that is easy for users to understand.

[0294] "Means for generating reports that visually display organized information" refers to a function that generates data in a visually appealing and easy-to-understand report format based on organized information.

[0295] "Means for sending the generated report to the information requester" refers to a function that generates a visualized report and sends this report to the user who made the information request.

[0296] "Means for analyzing machine status and manufacturing progress in a manufacturing environment" refers to a function that analyzes the operating status and progress of equipment on the manufacturing floor to identify problems and areas for improvement.

[0297] "Means for generating appropriate instructions for operators based on analysis results" refers to a function that generates specific and appropriate instructions for operators on the manufacturing floor based on the analyzed data.

[0298] In the system for realizing this invention, the server, terminal, and user each play a specific role.

[0299] The server is programmed using Python and employs NLTK and spaCy for natural language processing. It also utilizes SQLAlchemy for database access and Matplotlib and Seaborn for data visualization. These software tools analyze user information requests and generate appropriate search queries. These queries are used to quickly retrieve data from information sources and generate visually organized reports. The reports prioritize visual appeal to ensure users can easily understand the data.

[0300] The system utilizes smartphones and tablets as terminals. Users submit information requests and receive reports of the acquired information through these devices. The terminals are equipped with an interface designed to allow users to easily input requests.

[0301] The user uses a terminal to make an information acquisition request in order to know the situation of the manufacturing site and the state of the machine. Specifically, a prompt such as "Please check the manufacturing status of part X" is input. The server responds to this request, analyzes the data of the manufacturing environment, generates a clear visual report, and sends it to the terminal.

[0302] As an example of a prompt sentence, there is "Please quickly identify abnormal situations of part Y during the manufacturing process and propose appropriate solutions". In this way, the user can grasp the situation of the manufacturing site in real time and receive appropriate instructions for prompt response.

[0303] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0304] Step 1:

[0305] The user uses a terminal to input an information acquisition request. For example, a prompt sentence such as "Please check the manufacturing status of part X" is input. This input is sent to the server and preparations are made for processing there.

[0306] Step 2:

[0307] The server analyzes the information acquisition request received from the user. For the analysis, natural language processing technology is utilized and libraries such as NLTK and spaCy are used. Here, data processing is performed to extract the prompt sentence and identify relevant keywords, and a search query to be used in the next step is generated.

[0308] Step 3:

[0309] The server generates a search query based on the keywords obtained from the analysis and uses this query to identify the information source. SQLAlchemy is utilized for accessing this information source to quickly obtain the necessary information from the database. The output of query generation and data access is a raw dataset containing the specified information.

[0310] Step 4:

[0311] The server organizes the acquired data and generates a visual report. This step involves data calculations using Matplotlib and Seaborn to visualize the data as graphs and charts. This generates a report that allows users to intuitively understand the data.

[0312] Step 5:

[0313] The organized reports are sent from the server to the terminal. The terminal provides an interface that allows the user to view the reports and understand the manufacturing status and machine condition in real time. This enables the user to quickly decide on the next course of action.

[0314] 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.

[0315] This invention begins when a user requests specific information via a terminal, the server receives the request, and activates an AI agent and an emotion engine. The AI ​​agent uses natural language processing technology to analyze the user's request and generate a search query. The server then uses the generated search query to retrieve the most relevant information from internal databases and related systems.

[0316] The emotion engine evaluates data transmitted from the user's device (such as voice tone, text expression, and user choices) to recognize the user's current emotions. For example, if a user feels "very rushed," the emotion engine detects this sense of urgency. Based on this emotion, it adjusts how the retrieved information is presented, highlighting key points for clarity.

[0317] As a concrete example, consider a scenario where a user requests to "learn more about project progress and risks" via their device. The server receives and analyzes the request, and the AI ​​agent searches for relevant project management documents and reports. Meanwhile, the emotion engine detects that the user is feeling anxious based on their input method and past emotional history. The server then organizes the acquired information, clearly highlights risk factors, and generates a report designed to alleviate the user's anxiety.

[0318] Furthermore, this system receives user feedback through its emotion engine and can fine-tune how information is delivered in the future. This provides a personalized experience for each user and ensures consistently convenient information delivery. Through this process, users can receive information that resonates with their emotions quickly and accurately, improving work efficiency and satisfaction.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The user enters a request to retrieve specific information from their device. This request is sent to the server in natural language.

[0322] Step 2:

[0323] The server receives an information retrieval request from the user and activates an AI agent to analyze the request.

[0324] Step 3:

[0325] The AI ​​agent uses natural language processing to analyze requests and generate search queries. This makes it clear exactly what information is needed.

[0326] Step 4:

[0327] The server identifies internal databases and related systems based on the generated search queries and collects the appropriate information.

[0328] Step 5:

[0329] The emotion engine built into the device analyzes input data to recognize the user's emotions. This data includes text sentence structure, input speed, and voice tone.

[0330] Step 6:

[0331] The emotion engine recognizes the user's current emotional state (e.g., anxiety, worry, relaxation) and sends that information to the server.

[0332] Step 7:

[0333] The server uses information from the emotion engine to organize the collected data and generate reports tailored to the user's emotional state. For example, if the user is feeling anxious, it will focus on providing detailed information about risks.

[0334] Step 8:

[0335] The server sends the generated report to the user's terminal. The user can receive this report on their terminal and review the information.

[0336] Step 9:

[0337] When users provide feedback on a report via their device, the sentiment engine re-analyzes that feedback and incorporates it into future information delivery. This enables more personalized information delivery.

[0338] (Example 2)

[0339] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0340] Conventional information acquisition systems provide information without considering the user's emotional state, resulting in a failure to adequately reflect the urgency and importance of the information the user is seeking, leading to decreased satisfaction. Furthermore, the uniform nature of information provision, lacking personalization tailored to individual users, is a significant problem.

[0341] 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.

[0342] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search items, and means for adjusting the method of presenting information based on the emotional state. This enables the provision of personalized information according to the user's emotional state.

[0343] An "information retrieval request" is a request that a user sends to a system to obtain specific information.

[0344] "Analysis" is the process of deciphering received information or data and understanding its content.

[0345] "Search items" are queries or inquiry conditions generated to retrieve necessary information from the information infrastructure.

[0346] "Information infrastructure" refers to all databases and storage systems where data and documents are stored.

[0347] "Emotional data" refers to data necessary to understand a user's emotional state, and includes things like voice tone and written expression.

[0348] "Emotional state" refers to the user's current psychological state or mood.

[0349] A "report" is a document or digital document that is generated after the information has been collected and compiled.

[0350] Personalization is the process of optimizing information and services according to the characteristics and needs of individual users.

[0351] This invention is a system in which, in response to a user's information retrieval request, a server executes a specific process and provides appropriately adjusted information. The following main components are necessary to carry out the invention.

[0352] First, the user enters an information retrieval request into a terminal. The terminal receives this request and sends it to the server over the network. The server can use any common server device as hardware. The software includes a database management system (e.g., MySQL or Oracle Database using SQL) and an AI module for natural language processing (e.g., Python's NLTK or spaCy).

[0353] The server uses an AI agent to analyze received information retrieval requests and generate relevant search items. This process utilizes a generative AI model. The AI ​​agent analyzes the requests using natural language processing and generates appropriate search items for the company's internal database.

[0354] Next, an emotion engine is used to analyze the user's emotional data and recognize the user's emotional state. The emotion engine evaluates voice tone and text expression to identify the user's psychological state. Based on this, the server adjusts how to appropriately structure and present the acquired information.

[0355] As a concrete example, consider a scenario where a user requests a detailed summary of the year-end report. The server receives the request, uses an AI model to search for relevant documents, and an emotion engine analyzes the user's emotions. If the server determines the user is in a hurry, it generates a report that concisely summarizes the information, highlights key points, and sends it to the user's device.

[0356] An example of a prompt message might be: "The user has requested an overview of the year-end report on their device. The server should use an AI agent and emotion engine to analyze the information and highlight the most important details."

[0357] This invention enables users to receive information quickly and appropriately in a way that resonates with their emotions, thereby improving work efficiency and satisfaction.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The user enters an information retrieval request into the terminal and sends the request. Specifically, the user enters a request as text, such as "I want to know the latest project progress." This text data is output from the terminal and sent to the server.

[0361] Step 2:

[0362] The server receives an information retrieval request from the terminal. Based on this input data, the server activates an AI agent and analyzes the request using natural language processing technology. As a result of the analysis, specific search items are output by the generating AI model. The next step is performed using these search items.

[0363] Step 3:

[0364] The server uses the generated search items to search the information infrastructure (e.g., a database system). The server executes the search query and extracts relevant data from the information infrastructure. The extracted data is obtained as the server's output, and this is used to proceed to the next processing step.

[0365] Step 4:

[0366] The server activates the emotion engine and analyzes the user's emotional state based on the information they submit. Specifically, it evaluates the tone of voice and the expression of the input text to identify the user's psychological state. This emotional state is output and used to determine how to present information next.

[0367] Step 5:

[0368] The server adjusts how the acquired information is presented based on the user's emotional state, which is the output of the emotion engine. For example, if the situation is deemed urgent, the information is summarized clearly and important points are highlighted. This adjusted information is generated as a report and proceeds to the next step as the server's output.

[0369] Step 6:

[0370] The server sends the generated report to the terminal. The terminal receives this information and presents it to the user. This output is displayed in a format that is compatible with the user's visual or auditory perception, allowing the user to review the requested information.

[0371] Step 7:

[0372] Users send feedback on the information provided to the server via their device. This feedback is used to improve the way information is provided in the future and serves as important data for the server to make adjustments.

[0373] (Application Example 2)

[0374] 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".

[0375] In today's information society, users are required to quickly and accurately obtain the information they need from a vast amount of data. However, conventional systems have struggled to present information in a way that suits the user's emotions and circumstances, posing a challenge to improving the user experience. Furthermore, search accuracy and information delivery methods were not optimized for each user, resulting in individual differences in how information was received. These problems need to be addressed.

[0376] 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.

[0377] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the user's emotional state, and means for adjusting the information presentation method based on the analysis results. This makes it possible to present optimal information according to the user's emotions and situation.

[0378] An "information retrieval request" is a request sent to a server when a user wishes to obtain specific information.

[0379] "Analysis" refers to understanding a received request and generating an appropriate search query based on that request.

[0380] A "search query" is input data used to find the desired information from a source.

[0381] "Information source" refers to the database or related system where the information requested by the user is stored.

[0382] "Organization" refers to the process of compiling the retrieved search results into a format that is easy for the user to understand.

[0383] A "report" is a document that compiles and organizes information.

[0384] "Emotional state" refers to the emotional expressions and circumstances a user displays when requesting information.

[0385] "Analysis" refers to the process of evaluating a user's emotional data and identifying their emotions at that time based on that data.

[0386] "Adjusting the information presentation method" refers to changing the display method to provide information in the most optimal format according to the user's emotional state.

[0387] "Customized information delivery" refers to presenting information in a format that suits specific needs, based on the user's requests and emotions.

[0388] This invention is a system that begins with a user making an information retrieval request. The user uses a terminal to request specific information and sends the request to the server. Upon receiving the request, the server first uses an AI agent to analyze the request and generate an appropriate search query. This AI agent uses a natural language processing library (e.g., spaCy) to clearly understand the user's intent.

[0389] The generated search queries are executed against the source database (e.g., MySQL). The retrieved search results are then organized. This organizing process prepares the information for clear and concise presentation to the user.

[0390] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This analysis uses data sent from the user's device, such as voice tone and voice quality picked up by the smartphone's microphone. The analysis utilizes an emotion analysis library (e.g., Google Cloud Natural Language API).

[0391] The way information is presented is adjusted based on the user's emotional state. This allows for emphasizing key points to users in a tense state and presenting more detailed information to users in a calm state.

[0392] Finally, the generated report is sent to the user's device. The report contains optimized information and is customized to the user's situation. By using this system, users can quickly and appropriately meet their needs.

[0393] As an example of a program in action, a system might ask a user, "Where are the sale items?", and then, by removing unnecessary information, tell the user the shortest route to the sale items. In this case, an example of a prompt statement used by the generative AI model would be as follows:

[0394] User request: "Where are the sale items?"

[0395] Sentiment analysis: "Users are feeling confused."

[0396] Goal: "To simply explain the location of sale items."

[0397] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0398] Step 1:

[0399] The user requests information from their device. The request is entered in natural language format, and the device sends it to the server. The information entered by the user includes specific requests (e.g., inventory status). The output is the request content sent to the server.

[0400] Step 2:

[0401] The server activates an AI agent and analyzes the received information retrieval request. From the data obtained through the analysis, it generates a search query. In this step, a natural language processing library (e.g., spaCy) is used to understand the intent of the request and form the query. The input is the user's request, and the output is a query suitable for searching.

[0402] Step 3:

[0403] The server uses the generated search query to execute a query against the database, which is the source of the information. It performs query operations to retrieve relevant information from the database (e.g., MySQL). The input is the generated query, and the output is the retrieved information result.

[0404] Step 4:

[0405] The server organizes the acquired information results. The organization process condenses the information into an easily understandable format for the user. The input is raw data, and the output is the organized information.

[0406] Step 5:

[0407] The server uses an emotion engine to analyze the user's emotional state based on data received from the terminal (such as voice tone). The analysis utilizes an emotion analysis library (e.g., Google Cloud Natural Language API). The input is the user's emotion-related data, and the output is the result of the user's emotional state.

[0408] Step 6:

[0409] The server adjusts the information presentation method according to the analyzed emotional state. Based on a specific emotion, it changes the information format and the emphasis of the presented content. The input is the result of the emotional state and organized information, and the output is the adjusted information.

[0410] Step 7:

[0411] The server generates the final information as a report and sends it to the terminal. The user reviews this report and obtains the necessary information. The input is the adjusted information, and the output is the information provided to the user.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] [Third Embodiment]

[0416] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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".

[0428] This invention begins with a user making an information retrieval request from a terminal, which the server receives and activates an AI agent. The AI ​​agent analyzes the received request using natural language processing technology and generates an appropriate search query to retrieve the relevant information. The server then uses the generated search query to identify the information source, such as internal databases or systems, and accesses them quickly and efficiently.

[0429] As a concrete example, consider a scenario where a user requests to know the development progress of a new product. The server receives this request and analyzes it using an AI agent. The AI ​​agent constructs a search query based on keywords such as "new product," "development," and "progress," and identifies project management systems and related documents. As a result, the server collects relevant information such as reports and meeting minutes.

[0430] The collected information is organized by the server and generated as a visually easy-to-understand report. This allows users to receive and easily understand the report on their own devices. The report uses graphs and tables to make the data explanation easier to understand.

[0431] Furthermore, this system allows the AI ​​agent to learn from past search experiences, enabling more accurate information retrieval in subsequent searches. As a result, users can access optimized information even with repeated requests, significantly improving work efficiency.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The user uses their device to input a request for specific information. The request is made in natural language and sent from the device to the server.

[0435] Step 2:

[0436] The server receives an information retrieval request from the user and begins preparing for analysis. This process requires converting the request into an easily understandable format.

[0437] Step 3:

[0438] The server activates an AI agent, which analyzes the request using natural language processing technology. The AI ​​agent analyzes the request and generates a search query.

[0439] Step 4:

[0440] The server identifies information sources based on the generated search queries. These sources can be diverse, including internal databases and project management systems.

[0441] Step 5:

[0442] The server applies search queries to identified information sources and retrieves the information. Access control is considered here, and necessary security authentication procedures are performed.

[0443] Step 6:

[0444] The server organizes the acquired information, classifies the data in a way that is easy for the user to understand, and creates a summarized report. It also generates graphs and tables as needed.

[0445] Step 7:

[0446] The server sends the organized report to the user's terminal. The user can then review the information and use it to improve their work.

[0447] Step 8:

[0448] The AI ​​agent learns from the current search process and updates its database to improve the accuracy of future searches, making it useful for future information retrievals.

[0449] (Example 1)

[0450] 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."

[0451] Conventional information retrieval systems suffered from limited efficiency and accuracy in information acquisition, making it difficult for users to obtain the information they needed quickly and accurately. In particular, correctly analyzing information retrieval requests entered in natural language and quickly identifying relevant information sources was difficult, resulting in users spending a lot of time on the process. Furthermore, there was a lack of technology to facilitate the visual understanding of retrieved information and to present it in an easily usable format. In addition, the system's mechanism for learning from past information retrieval experiences and applying that knowledge to subsequent searches was insufficient, thus requiring continuous improvement.

[0452] 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.

[0453] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received information acquisition requests using natural language processing technology and generating search queries, and means for identifying electronic information sources and acquiring information using the generated search queries. This enables the rapid identification and acquisition of relevant information from the analysis of requests in natural language.

[0454] An "information retrieval request" is a request made in natural language by a user to a system in order to obtain specific information.

[0455] A "receiving means" is a function that receives an information acquisition request and enables subsequent processing to be executed.

[0456] "Natural language processing technology" is a technology that enables computers to understand and analyze human natural language.

[0457] A "search query" is a command generated to search databases and information sources based on a user's request.

[0458] "Electronic information sources" refer to databases and information systems existing both inside and outside the company, and are information resources that contain the necessary information.

[0459] A "report" is a document or graphic representation that organizes acquired information and presents it to the user in a visually easy-to-understand format.

[0460] A "learning tool" is a function that improves the accuracy of future searches based on past search results.

[0461] "Patrol methods" refer to the function of regularly visiting information sources to collect new information.

[0462] This invention is initiated when a user sends an information retrieval request in natural language from a terminal. The user's input request is transmitted to a server via a communication network. The server is equipped with a dedicated receiving means for receiving requests, and after receiving the request, an AI agent is activated. This AI agent uses natural language processing technology to analyze the request and generate an appropriate search query. General machine learning algorithms and specific generative AI models are applied to the natural language processing.

[0463] The server uses these generated search queries to access various electronic information sources, both inside and outside the company. Examples of these sources include databases storing sales data and project management systems. The server efficiently organizes the information retrieved from these sources and generates user-friendly reports. These reports can present data clearly using visual elements such as graphs and tables.

[0464] The generated report is sent back to the user's terminal, allowing the user to quickly review the information and take action as requested. Furthermore, the system on the server has a built-in function to learn from past search experiences, enabling it to provide more accurate and efficient search results in subsequent information retrieval requests.

[0465] As a concrete example, if a user enters "I need sales data for the next monthly meeting" into their terminal, the server receives this request and begins analysis using an AI agent. Using the search query generated by the analysis, the server accesses the sales database to retrieve the information. The server then compiles the detailed sales data into a report in graph format and sends it to the user's terminal. An example of a prompt in this process would be, "Please retrieve the sales data needed for the next monthly meeting and generate a report."

[0466] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0467] Step 1:

[0468] The user uses a terminal to input an information retrieval request in natural language and sends it to the server. An example input might be a request statement like, "I need sales data for the next monthly meeting." This request is sent from the terminal to the server via the network. The output is the server receiving the request.

[0469] Step 2:

[0470] When the server receives a request, it activates an AI agent. The AI ​​agent analyzes the received request using natural language processing techniques. The input is a natural language request from the user, and the AI ​​agent extracts keywords from this request. These keywords might include "sales data" or "monthly meeting." The output is a set of keywords to be used as a search query.

[0471] Step 3:

[0472] The server generates a search query using keywords extracted through natural language processing. The input is the set of keywords obtained in step 2, and an AI model is used to construct an effective search query. The output is the search query used to access the information source.

[0473] Step 4:

[0474] The server uses the generated search query to access internal databases and related systems. The input is the search query generated in step 3, and the server performs a search against the specified information source (e.g., sales database). The output is the required set of sales data and related information.

[0475] Step 5:

[0476] The server organizes the acquired data and generates a visually easy-to-understand report. The input is the set of information obtained in step 4, and data aggregation and analysis are performed. Specifically, the server aggregates sales data by month and creates a report in graph and table format. The output is the final report presented to the user.

[0477] Step 6:

[0478] The server sends the generated report to the user's terminal. The input is the report created in step 5, and the output is a visualized report on the user's terminal. This allows the user to quickly view the necessary data.

[0479] Step 7:

[0480] The server uses an AI agent to learn from past information retrieval experiences and improve the accuracy of subsequent searches. The input is data on previously processed search results and their efficiency, and the AI ​​agent adjusts its model based on this data. The output is the improved search algorithm.

[0481] (Application Example 1)

[0482] 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."

[0483] In the current manufacturing environment, information gathering and analysis are not performed efficiently, making it difficult to grasp manufacturing progress and machine status in real time. Furthermore, there is a lack of systems that generate appropriate instructions in situations requiring rapid response. As a result, there are challenges such as decreased work efficiency and problem-solving capabilities on the manufacturing floor, leading to impaired productivity.

[0484] 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.

[0485] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search queries, means for identifying information sources and executing search queries, means for acquiring and organizing search results, means for generating a report that visually displays the organized information, means for transmitting the generated report to the information acquisition request source, means for analyzing the machine status and manufacturing progress in the manufacturing environment, and means for generating appropriate instructions for the operator based on the analysis results. This improves the efficiency of information gathering and analysis at the manufacturing site, enabling real-time monitoring of machine status and manufacturing progress, and rapid generation of appropriate instructions.

[0486] "Means for receiving information acquisition requests" refers to a function that recognizes requests from users regarding information acquisition and delivers the content of those requests to the server.

[0487] "Means for analyzing received requests and generating search queries" refers to a function that analyzes received information retrieval requests and generates queries for efficiently searching for relevant information.

[0488] "Means for identifying information sources and executing search queries" refers to a function that uses the generated search query to identify appropriate information sources and retrieve data from them.

[0489] "Means for obtaining and organizing search results" refers to a function that efficiently collects search results obtained from information sources and organizes them in a format that is easy for users to understand.

[0490] "Means for generating reports that visually display organized information" refers to a function that generates data in a visually appealing and easy-to-understand report format based on organized information.

[0491] "Means for sending the generated report to the information requester" refers to a function that generates a visualized report and sends this report to the user who made the information request.

[0492] "Means for analyzing machine status and manufacturing progress in a manufacturing environment" refers to a function that analyzes the operating status and progress of equipment on the manufacturing floor to identify problems and areas for improvement.

[0493] "Means for generating appropriate instructions for operators based on analysis results" refers to a function that generates specific and appropriate instructions for operators on the manufacturing floor based on the analyzed data.

[0494] In the system for realizing this invention, the server, terminal, and user each play a specific role.

[0495] The server is programmed using Python and employs NLTK and spaCy for natural language processing. It also utilizes SQLAlchemy for database access and Matplotlib and Seaborn for data visualization. These software tools analyze user information requests and generate appropriate search queries. These queries are used to quickly retrieve data from information sources and generate visually organized reports. The reports prioritize visual appeal to ensure users can easily understand the data.

[0496] The system utilizes smartphones and tablets as terminals. Users submit information requests and receive reports of the acquired information through these devices. The terminals are equipped with an interface designed to allow users to easily input requests.

[0497] Users use terminals to request information to understand the situation on the manufacturing floor and the status of the machinery. Specifically, they might enter prompts such as, "Please check the manufacturing status of part X." The server responds to this request, analyzes data from the manufacturing environment, generates a clear visual report, and sends it to the terminal.

[0498] An example of a prompt message is, "Immediately identify any abnormalities in part Y during the manufacturing process and propose an appropriate solution." This allows the user to understand the situation on the manufacturing floor in real time and receive appropriate instructions for quick action.

[0499] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0500] Step 1:

[0501] The user uses a terminal to enter an information retrieval request. For example, they might enter a prompt message such as, "Please check the manufacturing status of part X." This input is sent to the server, where it is ready for processing.

[0502] Step 2:

[0503] The server analyzes the information retrieval request received from the user. This analysis utilizes natural language processing techniques, employing libraries such as NLTK and spaCy. Here, prompt text is extracted, relevant keywords are identified, and the data is processed to generate search queries for use in the next step.

[0504] Step 3:

[0505] The server generates a search query based on keywords obtained from the analysis and uses this query to identify information sources. SQLAlchemy is used to quickly retrieve the necessary information from the database to access these information sources. The output of query generation and data access is a raw dataset containing the specified information.

[0506] Step 4:

[0507] The server organizes the acquired data and generates a visual report. This step involves data calculations using Matplotlib and Seaborn to visualize the data as graphs and charts. This generates a report that allows users to intuitively understand the data.

[0508] Step 5:

[0509] The organized reports are sent from the server to the terminal. The terminal provides an interface that allows the user to view the reports and understand the manufacturing status and machine condition in real time. This enables the user to quickly decide on the next course of action.

[0510] 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.

[0511] This invention begins when a user requests specific information via a terminal, the server receives the request, and activates an AI agent and an emotion engine. The AI ​​agent uses natural language processing technology to analyze the user's request and generate a search query. The server then uses the generated search query to retrieve the most relevant information from internal databases and related systems.

[0512] The emotion engine evaluates data transmitted from the user's device (such as voice tone, text expression, and user choices) to recognize the user's current emotions. For example, if a user feels "very rushed," the emotion engine detects this sense of urgency. Based on this emotion, it adjusts how the retrieved information is presented, highlighting key points for clarity.

[0513] As a concrete example, consider a scenario where a user requests to "learn more about project progress and risks" via their device. The server receives and analyzes the request, and the AI ​​agent searches for relevant project management documents and reports. Meanwhile, the emotion engine detects that the user is feeling anxious based on their input method and past emotional history. The server then organizes the acquired information, clearly highlights risk factors, and generates a report designed to alleviate the user's anxiety.

[0514] Furthermore, this system receives user feedback through its emotion engine and can fine-tune how information is delivered in the future. This provides a personalized experience for each user and ensures consistently convenient information delivery. Through this process, users can receive information that resonates with their emotions quickly and accurately, improving work efficiency and satisfaction.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] The user enters a request to retrieve specific information from their device. This request is sent to the server in natural language.

[0518] Step 2:

[0519] The server receives an information retrieval request from the user and activates an AI agent to analyze the request.

[0520] Step 3:

[0521] The AI ​​agent uses natural language processing to analyze requests and generate search queries. This makes it clear exactly what information is needed.

[0522] Step 4:

[0523] The server identifies internal databases and related systems based on the generated search queries and collects the appropriate information.

[0524] Step 5:

[0525] The emotion engine built into the device analyzes input data to recognize the user's emotions. This data includes text sentence structure, input speed, and voice tone.

[0526] Step 6:

[0527] The emotion engine recognizes the user's current emotional state (e.g., anxiety, worry, relaxation) and sends that information to the server.

[0528] Step 7:

[0529] The server uses information from the emotion engine to organize the collected data and generate reports tailored to the user's emotional state. For example, if the user is feeling anxious, it will focus on providing detailed information about risks.

[0530] Step 8:

[0531] The server sends the generated report to the user's terminal. The user can receive this report on their terminal and review the information.

[0532] Step 9:

[0533] When users provide feedback on a report via their device, the sentiment engine re-analyzes that feedback and incorporates it into future information delivery. This enables more personalized information delivery.

[0534] (Example 2)

[0535] 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."

[0536] Conventional information acquisition systems provide information without considering the user's emotional state, resulting in a failure to adequately reflect the urgency and importance of the information the user is seeking, leading to decreased satisfaction. Furthermore, the uniform nature of information provision, lacking personalization tailored to individual users, is a significant problem.

[0537] 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.

[0538] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search items, and means for adjusting the method of presenting information based on the emotional state. This enables the provision of personalized information according to the user's emotional state.

[0539] An "information retrieval request" is a request that a user sends to a system to obtain specific information.

[0540] "Analysis" is the process of deciphering received information or data and understanding its content.

[0541] "Search items" are queries or inquiry conditions generated to retrieve necessary information from the information infrastructure.

[0542] "Information infrastructure" refers to all databases and storage systems where data and documents are stored.

[0543] "Emotional data" refers to data necessary to understand a user's emotional state, and includes things like voice tone and written expression.

[0544] "Emotional state" refers to the user's current psychological state or mood.

[0545] A "report" is a document or digital document that is generated after the information has been collected and compiled.

[0546] Personalization is the process of optimizing information and services according to the characteristics and needs of individual users.

[0547] This invention is a system in which, in response to a user's information retrieval request, a server executes a specific process and provides appropriately adjusted information. The following main components are necessary to carry out the invention.

[0548] First, the user enters an information retrieval request into a terminal. The terminal receives this request and sends it to the server over the network. The server can use any common server device as hardware. The software includes a database management system (e.g., MySQL or Oracle Database using SQL) and an AI module for natural language processing (e.g., Python's NLTK or spaCy).

[0549] The server uses an AI agent to analyze received information retrieval requests and generate relevant search items. This process utilizes a generative AI model. The AI ​​agent analyzes the requests using natural language processing and generates appropriate search items for the company's internal database.

[0550] Next, an emotion engine is used to analyze the user's emotional data and recognize the user's emotional state. The emotion engine evaluates voice tone and text expression to identify the user's psychological state. Based on this, the server adjusts how to appropriately structure and present the acquired information.

[0551] As a concrete example, consider a scenario where a user requests a detailed summary of the year-end report. The server receives the request, uses an AI model to search for relevant documents, and an emotion engine analyzes the user's emotions. If the server determines the user is in a hurry, it generates a report that concisely summarizes the information, highlights key points, and sends it to the user's device.

[0552] An example of a prompt message might be: "The user has requested an overview of the year-end report on their device. The server should use an AI agent and emotion engine to analyze the information and highlight the most important details."

[0553] This invention enables users to receive information quickly and appropriately in a way that resonates with their emotions, thereby improving work efficiency and satisfaction.

[0554] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0555] Step 1:

[0556] The user enters an information retrieval request into the terminal and sends the request. Specifically, the user enters a request as text, such as "I want to know the latest project progress." This text data is output from the terminal and sent to the server.

[0557] Step 2:

[0558] The server receives an information retrieval request from the terminal. Based on this input data, the server activates an AI agent and analyzes the request using natural language processing technology. As a result of the analysis, specific search items are output by the generating AI model. The next step is performed using these search items.

[0559] Step 3:

[0560] The server uses the generated search items to search the information infrastructure (e.g., a database system). The server executes the search query and extracts relevant data from the information infrastructure. The extracted data is obtained as the server's output, and this is used to proceed to the next processing step.

[0561] Step 4:

[0562] The server activates the emotion engine and analyzes the user's emotional state based on the information they submit. Specifically, it evaluates the tone of voice and the expression of the input text to identify the user's psychological state. This emotional state is output and used to determine how to present information next.

[0563] Step 5:

[0564] The server adjusts how the acquired information is presented based on the user's emotional state, which is the output of the emotion engine. For example, if the situation is deemed urgent, the information is summarized clearly and important points are highlighted. This adjusted information is generated as a report and proceeds to the next step as the server's output.

[0565] Step 6:

[0566] The server sends the generated report to the terminal. The terminal receives this information and presents it to the user. This output is displayed in a format that is compatible with the user's visual or auditory perception, allowing the user to review the requested information.

[0567] Step 7:

[0568] Users send feedback on the information provided to the server via their device. This feedback is used to improve the way information is provided in the future and serves as important data for the server to make adjustments.

[0569] (Application Example 2)

[0570] 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."

[0571] In today's information society, users are required to quickly and accurately obtain the information they need from a vast amount of data. However, conventional systems have struggled to present information in a way that suits the user's emotions and circumstances, posing a challenge to improving the user experience. Furthermore, search accuracy and information delivery methods were not optimized for each user, resulting in individual differences in how information was received. These problems need to be addressed.

[0572] 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.

[0573] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the user's emotional state, and means for adjusting the information presentation method based on the analysis results. This makes it possible to present optimal information according to the user's emotions and situation.

[0574] An "information retrieval request" is a request sent to a server when a user wishes to obtain specific information.

[0575] "Analysis" refers to understanding a received request and generating an appropriate search query based on that request.

[0576] A "search query" is input data used to find the desired information from a source.

[0577] "Information source" refers to the database or related system where the information requested by the user is stored.

[0578] "Organization" refers to the process of compiling the retrieved search results into a format that is easy for the user to understand.

[0579] A "report" is a document that compiles and organizes information.

[0580] "Emotional state" refers to the emotional expressions and circumstances a user displays when requesting information.

[0581] "Analysis" refers to the process of evaluating a user's emotional data and identifying their emotions at that time based on that data.

[0582] "Adjusting the information presentation method" refers to changing the display method to provide information in the most optimal format according to the user's emotional state.

[0583] "Customized information delivery" refers to presenting information in a format that suits specific needs, based on the user's requests and emotions.

[0584] This invention is a system that begins with a user making an information retrieval request. The user uses a terminal to request specific information and sends the request to the server. Upon receiving the request, the server first uses an AI agent to analyze the request and generate an appropriate search query. This AI agent uses a natural language processing library (e.g., spaCy) to clearly understand the user's intent.

[0585] The generated search queries are executed against the source database (e.g., MySQL). The retrieved search results are then organized. This organizing process prepares the information for clear and concise presentation to the user.

[0586] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This analysis uses data sent from the user's device, such as voice tone and voice quality picked up by the smartphone's microphone. The analysis utilizes an emotion analysis library (e.g., Google Cloud Natural Language API).

[0587] The way information is presented is adjusted based on the user's emotional state. This allows for emphasizing key points to users in a tense state and presenting more detailed information to users in a calm state.

[0588] Finally, the generated report is sent to the user's device. The report contains optimized information and is customized to the user's situation. By using this system, users can quickly and appropriately meet their needs.

[0589] As an example of a program in action, a system might ask a user, "Where are the sale items?", and then, by removing unnecessary information, tell the user the shortest route to the sale items. In this case, an example of a prompt statement used by the generative AI model would be as follows:

[0590] User request: "Where are the sale items?"

[0591] Sentiment analysis: "Users are feeling confused."

[0592] Goal: "To simply explain the location of sale items."

[0593] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0594] Step 1:

[0595] The user requests information from their device. The request is entered in natural language format, and the device sends it to the server. The information entered by the user includes specific requests (e.g., inventory status). The output is the request content sent to the server.

[0596] Step 2:

[0597] The server activates an AI agent and analyzes the received information retrieval request. From the data obtained through the analysis, it generates a search query. In this step, a natural language processing library (e.g., spaCy) is used to understand the intent of the request and form the query. The input is the user's request, and the output is a query suitable for searching.

[0598] Step 3:

[0599] The server uses the generated search query to execute a query against the database, which is the source of the information. It performs query operations to retrieve relevant information from the database (e.g., MySQL). The input is the generated query, and the output is the retrieved information result.

[0600] Step 4:

[0601] The server organizes the acquired information results. The organization process condenses the information into an easily understandable format for the user. The input is raw data, and the output is the organized information.

[0602] Step 5:

[0603] The server uses an emotion engine to analyze the user's emotional state based on data received from the terminal (such as voice tone). The analysis utilizes an emotion analysis library (e.g., Google Cloud Natural Language API). The input is the user's emotion-related data, and the output is the result of the user's emotional state.

[0604] Step 6:

[0605] The server adjusts the information presentation method according to the analyzed emotional state. Based on a specific emotion, it changes the information format and the emphasis of the presented content. The input is the result of the emotional state and organized information, and the output is the adjusted information.

[0606] Step 7:

[0607] The server generates the final information as a report and sends it to the terminal. The user reviews this report and obtains the necessary information. The input is the adjusted information, and the output is the information provided to the user.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] [Fourth Embodiment]

[0612] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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".

[0625] This invention begins with a user making an information retrieval request from a terminal, which the server receives and activates an AI agent. The AI ​​agent analyzes the received request using natural language processing technology and generates an appropriate search query to retrieve the relevant information. The server then uses the generated search query to identify the information source, such as internal databases or systems, and accesses them quickly and efficiently.

[0626] As a concrete example, consider a scenario where a user requests to know the development progress of a new product. The server receives this request and analyzes it using an AI agent. The AI ​​agent constructs a search query based on keywords such as "new product," "development," and "progress," and identifies project management systems and related documents. As a result, the server collects relevant information such as reports and meeting minutes.

[0627] The collected information is organized by the server and generated as a visually easy-to-understand report. This allows users to receive and easily understand the report on their own devices. The report uses graphs and tables to make the data explanation easier to understand.

[0628] Furthermore, this system allows the AI ​​agent to learn from past search experiences, enabling more accurate information retrieval in subsequent searches. As a result, users can access optimized information even with repeated requests, significantly improving work efficiency.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] The user uses their device to input a request for specific information. The request is made in natural language and sent from the device to the server.

[0632] Step 2:

[0633] The server receives an information retrieval request from the user and begins preparing for analysis. This process requires converting the request into an easily understandable format.

[0634] Step 3:

[0635] The server activates an AI agent, which analyzes the request using natural language processing technology. The AI ​​agent analyzes the request and generates a search query.

[0636] Step 4:

[0637] The server identifies information sources based on the generated search queries. These sources can be diverse, including internal databases and project management systems.

[0638] Step 5:

[0639] The server applies search queries to identified information sources and retrieves the information. Access control is considered here, and necessary security authentication procedures are performed.

[0640] Step 6:

[0641] The server organizes the acquired information, classifies the data in a way that is easy for the user to understand, and creates a summarized report. It also generates graphs and tables as needed.

[0642] Step 7:

[0643] The server sends the organized report to the user's terminal. The user can then review the information and use it to improve their work.

[0644] Step 8:

[0645] The AI ​​agent learns from the current search process and updates its database to improve the accuracy of future searches, making it useful for future information retrievals.

[0646] (Example 1)

[0647] 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".

[0648] Conventional information retrieval systems suffered from limited efficiency and accuracy in information acquisition, making it difficult for users to obtain the information they needed quickly and accurately. In particular, correctly analyzing information retrieval requests entered in natural language and quickly identifying relevant information sources was difficult, resulting in users spending a lot of time on the process. Furthermore, there was a lack of technology to facilitate the visual understanding of retrieved information and to present it in an easily usable format. In addition, the system's mechanism for learning from past information retrieval experiences and applying that knowledge to subsequent searches was insufficient, thus requiring continuous improvement.

[0649] 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.

[0650] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received information acquisition requests using natural language processing technology and generating search queries, and means for identifying electronic information sources and acquiring information using the generated search queries. This enables the rapid identification and acquisition of relevant information from the analysis of requests in natural language.

[0651] An "information retrieval request" is a request made in natural language by a user to a system in order to obtain specific information.

[0652] A "receiving means" is a function that receives an information acquisition request and enables subsequent processing to be executed.

[0653] "Natural language processing technology" is a technology that enables computers to understand and analyze human natural language.

[0654] A "search query" is a command generated to search databases and information sources based on a user's request.

[0655] "Electronic information sources" refer to databases and information systems existing both inside and outside the company, and are information resources that contain the necessary information.

[0656] A "report" is a document or graphic representation that organizes acquired information and presents it to the user in a visually easy-to-understand format.

[0657] A "learning tool" is a function that improves the accuracy of future searches based on past search results.

[0658] "Patrol methods" refer to the function of regularly visiting information sources to collect new information.

[0659] This invention is initiated when a user sends an information retrieval request in natural language from a terminal. The user's input request is transmitted to a server via a communication network. The server is equipped with a dedicated receiving means for receiving requests, and after receiving the request, an AI agent is activated. This AI agent uses natural language processing technology to analyze the request and generate an appropriate search query. General machine learning algorithms and specific generative AI models are applied to the natural language processing.

[0660] The server uses these generated search queries to access various electronic information sources, both inside and outside the company. Examples of these sources include databases storing sales data and project management systems. The server efficiently organizes the information retrieved from these sources and generates user-friendly reports. These reports can present data clearly using visual elements such as graphs and tables.

[0661] The generated report is sent back to the user's terminal, allowing the user to quickly review the information and take action as requested. Furthermore, the system on the server has a built-in function to learn from past search experiences, enabling it to provide more accurate and efficient search results in subsequent information retrieval requests.

[0662] As a concrete example, if a user enters "I need sales data for the next monthly meeting" into their terminal, the server receives this request and begins analysis using an AI agent. Using the search query generated by the analysis, the server accesses the sales database to retrieve the information. The server then compiles the detailed sales data into a report in graph format and sends it to the user's terminal. An example of a prompt in this process would be, "Please retrieve the sales data needed for the next monthly meeting and generate a report."

[0663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0664] Step 1:

[0665] The user uses a terminal to input an information retrieval request in natural language and sends it to the server. An example input might be a request statement like, "I need sales data for the next monthly meeting." This request is sent from the terminal to the server via the network. The output is the server receiving the request.

[0666] Step 2:

[0667] When the server receives a request, it activates an AI agent. The AI ​​agent analyzes the received request using natural language processing techniques. The input is a natural language request from the user, and the AI ​​agent extracts keywords from this request. These keywords might include "sales data" or "monthly meeting." The output is a set of keywords to be used as a search query.

[0668] Step 3:

[0669] The server generates a search query using keywords extracted through natural language processing. The input is the set of keywords obtained in step 2, and an AI model is used to construct an effective search query. The output is the search query used to access the information source.

[0670] Step 4:

[0671] The server uses the generated search query to access internal databases and related systems. The input is the search query generated in step 3, and the server performs a search against the specified information source (e.g., sales database). The output is the required set of sales data and related information.

[0672] Step 5:

[0673] The server organizes the acquired data and generates a visually easy-to-understand report. The input is the set of information obtained in step 4, and data aggregation and analysis are performed. Specifically, the server aggregates sales data by month and creates a report in graph and table format. The output is the final report presented to the user.

[0674] Step 6:

[0675] The server sends the generated report to the user's terminal. The input is the report created in step 5, and the output is a visualized report on the user's terminal. This allows the user to quickly view the necessary data.

[0676] Step 7:

[0677] The server uses an AI agent to learn from past information retrieval experiences and improve the accuracy of subsequent searches. The input is data on previously processed search results and their efficiency, and the AI ​​agent adjusts its model based on this data. The output is the improved search algorithm.

[0678] (Application Example 1)

[0679] 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".

[0680] In the current manufacturing environment, information gathering and analysis are not performed efficiently, making it difficult to grasp manufacturing progress and machine status in real time. Furthermore, there is a lack of systems that generate appropriate instructions in situations requiring rapid response. As a result, there are challenges such as decreased work efficiency and problem-solving capabilities on the manufacturing floor, leading to impaired productivity.

[0681] 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.

[0682] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search queries, means for identifying information sources and executing search queries, means for acquiring and organizing search results, means for generating a report that visually displays the organized information, means for transmitting the generated report to the information acquisition request source, means for analyzing the machine status and manufacturing progress in the manufacturing environment, and means for generating appropriate instructions for the operator based on the analysis results. This improves the efficiency of information gathering and analysis at the manufacturing site, enabling real-time monitoring of machine status and manufacturing progress, and rapid generation of appropriate instructions.

[0683] "Means for receiving information acquisition requests" refers to a function that recognizes requests from users regarding information acquisition and delivers the content of those requests to the server.

[0684] "Means for analyzing received requests and generating search queries" refers to a function that analyzes received information retrieval requests and generates queries for efficiently searching for relevant information.

[0685] "Means for identifying information sources and executing search queries" refers to a function that uses the generated search query to identify appropriate information sources and retrieve data from them.

[0686] "Means for obtaining and organizing search results" refers to a function that efficiently collects search results obtained from information sources and organizes them in a format that is easy for users to understand.

[0687] "Means for generating reports that visually display organized information" refers to a function that generates data in a visually appealing and easy-to-understand report format based on organized information.

[0688] "Means for sending the generated report to the information requester" refers to a function that generates a visualized report and sends this report to the user who made the information request.

[0689] "Means for analyzing machine status and manufacturing progress in a manufacturing environment" refers to a function that analyzes the operating status and progress of equipment on the manufacturing floor to identify problems and areas for improvement.

[0690] "Means for generating appropriate instructions for operators based on analysis results" refers to a function that generates specific and appropriate instructions for operators on the manufacturing floor based on the analyzed data.

[0691] In the system for realizing this invention, the server, terminal, and user each play a specific role.

[0692] The server is programmed using Python and employs NLTK and spaCy for natural language processing. It also utilizes SQLAlchemy for database access and Matplotlib and Seaborn for data visualization. These software tools analyze user information requests and generate appropriate search queries. These queries are used to quickly retrieve data from information sources and generate visually organized reports. The reports prioritize visual appeal to ensure users can easily understand the data.

[0693] The system utilizes smartphones and tablets as terminals. Users submit information requests and receive reports of the acquired information through these devices. The terminals are equipped with an interface designed to allow users to easily input requests.

[0694] Users use terminals to request information to understand the situation on the manufacturing floor and the status of the machinery. Specifically, they might enter prompts such as, "Please check the manufacturing status of part X." The server responds to this request, analyzes data from the manufacturing environment, generates a clear visual report, and sends it to the terminal.

[0695] An example of a prompt message is, "Immediately identify any abnormalities in part Y during the manufacturing process and propose an appropriate solution." This allows the user to understand the situation on the manufacturing floor in real time and receive appropriate instructions for quick action.

[0696] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0697] Step 1:

[0698] The user uses a terminal to enter an information retrieval request. For example, they might enter a prompt message such as, "Please check the manufacturing status of part X." This input is sent to the server, where it is ready for processing.

[0699] Step 2:

[0700] The server analyzes the information retrieval request received from the user. This analysis utilizes natural language processing techniques, employing libraries such as NLTK and spaCy. Here, prompt text is extracted, relevant keywords are identified, and the data is processed to generate search queries for use in the next step.

[0701] Step 3:

[0702] The server generates a search query based on keywords obtained from the analysis and uses this query to identify information sources. SQLAlchemy is used to quickly retrieve the necessary information from the database to access these information sources. The output of query generation and data access is a raw dataset containing the specified information.

[0703] Step 4:

[0704] The server organizes the acquired data and generates a visual report. This step involves data calculations using Matplotlib and Seaborn to visualize the data as graphs and charts. This generates a report that allows users to intuitively understand the data.

[0705] Step 5:

[0706] The organized reports are sent from the server to the terminal. The terminal provides an interface that allows the user to view the reports and understand the manufacturing status and machine condition in real time. This enables the user to quickly decide on the next course of action.

[0707] 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.

[0708] This invention begins when a user requests specific information via a terminal, the server receives the request, and activates an AI agent and an emotion engine. The AI ​​agent uses natural language processing technology to analyze the user's request and generate a search query. The server then uses the generated search query to retrieve the most relevant information from internal databases and related systems.

[0709] The emotion engine evaluates data transmitted from the user's device (such as voice tone, text expression, and user choices) to recognize the user's current emotions. For example, if a user feels "very rushed," the emotion engine detects this sense of urgency. Based on this emotion, it adjusts how the retrieved information is presented, highlighting key points for clarity.

[0710] As a concrete example, consider a scenario where a user requests to "learn more about project progress and risks" via their device. The server receives and analyzes the request, and the AI ​​agent searches for relevant project management documents and reports. Meanwhile, the emotion engine detects that the user is feeling anxious based on their input method and past emotional history. The server then organizes the acquired information, clearly highlights risk factors, and generates a report designed to alleviate the user's anxiety.

[0711] Furthermore, this system receives user feedback through its emotion engine and can fine-tune how information is delivered in the future. This provides a personalized experience for each user and ensures consistently convenient information delivery. Through this process, users can receive information that resonates with their emotions quickly and accurately, improving work efficiency and satisfaction.

[0712] The following describes the processing flow.

[0713] Step 1:

[0714] The user enters a request to retrieve specific information from their device. This request is sent to the server in natural language.

[0715] Step 2:

[0716] The server receives an information retrieval request from the user and activates an AI agent to analyze the request.

[0717] Step 3:

[0718] The AI ​​agent uses natural language processing to analyze requests and generate search queries. This makes it clear exactly what information is needed.

[0719] Step 4:

[0720] The server identifies internal databases and related systems based on the generated search queries and collects the appropriate information.

[0721] Step 5:

[0722] The emotion engine built into the device analyzes input data to recognize the user's emotions. This data includes text sentence structure, input speed, and voice tone.

[0723] Step 6:

[0724] The emotion engine recognizes the user's current emotional state (e.g., anxiety, worry, relaxation) and sends that information to the server.

[0725] Step 7:

[0726] The server uses information from the emotion engine to organize the collected data and generate reports tailored to the user's emotional state. For example, if the user is feeling anxious, it will focus on providing detailed information about risks.

[0727] Step 8:

[0728] The server sends the generated report to the user's terminal. The user can receive this report on their terminal and review the information.

[0729] Step 9:

[0730] When users provide feedback on a report via their device, the sentiment engine re-analyzes that feedback and incorporates it into future information delivery. This enables more personalized information delivery.

[0731] (Example 2)

[0732] 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".

[0733] Conventional information acquisition systems provide information without considering the user's emotional state, resulting in a failure to adequately reflect the urgency and importance of the information the user is seeking, leading to decreased satisfaction. Furthermore, the uniform nature of information provision, lacking personalization tailored to individual users, is a significant problem.

[0734] 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.

[0735] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the received requests and generating search items, and means for adjusting the method of presenting information based on the emotional state. This enables the provision of personalized information according to the user's emotional state.

[0736] An "information retrieval request" is a request that a user sends to a system to obtain specific information.

[0737] "Analysis" is the process of deciphering received information or data and understanding its content.

[0738] "Search items" are queries or inquiry conditions generated to retrieve necessary information from the information infrastructure.

[0739] "Information infrastructure" refers to all databases and storage systems where data and documents are stored.

[0740] "Emotional data" refers to data necessary to understand a user's emotional state, and includes things like voice tone and written expression.

[0741] "Emotional state" refers to the user's current psychological state or mood.

[0742] A "report" is a document or digital document that is generated after the information has been collected and compiled.

[0743] Personalization is the process of optimizing information and services according to the characteristics and needs of individual users.

[0744] This invention is a system in which, in response to a user's information retrieval request, a server executes a specific process and provides appropriately adjusted information. The following main components are necessary to carry out the invention.

[0745] First, the user enters an information retrieval request into a terminal. The terminal receives this request and sends it to the server over the network. The server can use any common server device as hardware. The software includes a database management system (e.g., MySQL or Oracle Database using SQL) and an AI module for natural language processing (e.g., Python's NLTK or spaCy).

[0746] The server uses an AI agent to analyze received information retrieval requests and generate relevant search items. This process utilizes a generative AI model. The AI ​​agent analyzes the requests using natural language processing and generates appropriate search items for the company's internal database.

[0747] Next, an emotion engine is used to analyze the user's emotional data and recognize the user's emotional state. The emotion engine evaluates voice tone and text expression to identify the user's psychological state. Based on this, the server adjusts how to appropriately structure and present the acquired information.

[0748] As a concrete example, consider a scenario where a user requests a detailed summary of the year-end report. The server receives the request, uses an AI model to search for relevant documents, and an emotion engine analyzes the user's emotions. If the server determines the user is in a hurry, it generates a report that concisely summarizes the information, highlights key points, and sends it to the user's device.

[0749] An example of a prompt message might be: "The user has requested an overview of the year-end report on their device. The server should use an AI agent and emotion engine to analyze the information and highlight the most important details."

[0750] This invention enables users to receive information quickly and appropriately in a way that resonates with their emotions, thereby improving work efficiency and satisfaction.

[0751] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0752] Step 1:

[0753] The user enters an information retrieval request into the terminal and sends the request. Specifically, the user enters a request as text, such as "I want to know the latest project progress." This text data is output from the terminal and sent to the server.

[0754] Step 2:

[0755] The server receives an information retrieval request from the terminal. Based on this input data, the server activates an AI agent and analyzes the request using natural language processing technology. As a result of the analysis, specific search items are output by the generating AI model. The next step is performed using these search items.

[0756] Step 3:

[0757] The server uses the generated search items to search the information infrastructure (e.g., a database system). The server executes the search query and extracts relevant data from the information infrastructure. The extracted data is obtained as the server's output, and this is used to proceed to the next processing step.

[0758] Step 4:

[0759] The server activates the emotion engine and analyzes the user's emotional state based on the information they submit. Specifically, it evaluates the tone of voice and the expression of the input text to identify the user's psychological state. This emotional state is output and used to determine how to present information next.

[0760] Step 5:

[0761] The server adjusts how the acquired information is presented based on the user's emotional state, which is the output of the emotion engine. For example, if the situation is deemed urgent, the information is summarized clearly and important points are highlighted. This adjusted information is generated as a report and proceeds to the next step as the server's output.

[0762] Step 6:

[0763] The server sends the generated report to the terminal. The terminal receives this information and presents it to the user. This output is displayed in a format that is compatible with the user's visual or auditory perception, allowing the user to review the requested information.

[0764] Step 7:

[0765] Users send feedback on the information provided to the server via their device. This feedback is used to improve the way information is provided in the future and serves as important data for the server to make adjustments.

[0766] (Application Example 2)

[0767] 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".

[0768] In today's information society, users are required to quickly and accurately obtain the information they need from a vast amount of data. However, conventional systems have struggled to present information in a way that suits the user's emotions and circumstances, posing a challenge to improving the user experience. Furthermore, search accuracy and information delivery methods were not optimized for each user, resulting in individual differences in how information was received. These problems need to be addressed.

[0769] 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.

[0770] In this invention, the server includes means for receiving information acquisition requests, means for analyzing the user's emotional state, and means for adjusting the information presentation method based on the analysis results. This makes it possible to present optimal information according to the user's emotions and situation.

[0771] An "information retrieval request" is a request sent to a server when a user wishes to obtain specific information.

[0772] "Analysis" refers to understanding a received request and generating an appropriate search query based on that request.

[0773] A "search query" is input data used to find the desired information from a source.

[0774] "Information source" refers to the database or related system where the information requested by the user is stored.

[0775] "Organization" refers to the process of compiling the retrieved search results into a format that is easy for the user to understand.

[0776] A "report" is a document that compiles and organizes information.

[0777] "Emotional state" refers to the emotional expressions and circumstances a user displays when requesting information.

[0778] "Analysis" refers to the process of evaluating a user's emotional data and identifying their emotions at that time based on that data.

[0779] "Adjusting the information presentation method" refers to changing the display method to provide information in the most optimal format according to the user's emotional state.

[0780] "Customized information delivery" refers to presenting information in a format that suits specific needs, based on the user's requests and emotions.

[0781] This invention is a system that begins with a user making an information retrieval request. The user uses a terminal to request specific information and sends the request to the server. Upon receiving the request, the server first uses an AI agent to analyze the request and generate an appropriate search query. This AI agent uses a natural language processing library (e.g., spaCy) to clearly understand the user's intent.

[0782] The generated search queries are executed against the source database (e.g., MySQL). The retrieved search results are then organized. This organizing process prepares the information for clear and concise presentation to the user.

[0783] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This analysis uses data sent from the user's device, such as voice tone and voice quality picked up by the smartphone's microphone. The analysis utilizes an emotion analysis library (e.g., Google Cloud Natural Language API).

[0784] The way information is presented is adjusted based on the user's emotional state. This allows for emphasizing key points to users in a tense state and presenting more detailed information to users in a calm state.

[0785] Finally, the generated report is sent to the user's device. The report contains optimized information and is customized to the user's situation. By using this system, users can quickly and appropriately meet their needs.

[0786] As an example of a program in action, a system might ask a user, "Where are the sale items?", and then, by removing unnecessary information, tell the user the shortest route to the sale items. In this case, an example of a prompt statement used by the generative AI model would be as follows:

[0787] User request: "Where are the sale items?"

[0788] Sentiment analysis: "Users are feeling confused."

[0789] Goal: "To simply explain the location of sale items."

[0790] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0791] Step 1:

[0792] The user requests information from their device. The request is entered in natural language format, and the device sends it to the server. The information entered by the user includes specific requests (e.g., inventory status). The output is the request content sent to the server.

[0793] Step 2:

[0794] The server activates an AI agent and analyzes the received information retrieval request. From the data obtained through the analysis, it generates a search query. In this step, a natural language processing library (e.g., spaCy) is used to understand the intent of the request and form the query. The input is the user's request, and the output is a query suitable for searching.

[0795] Step 3:

[0796] The server uses the generated search query to execute a query against the database, which is the source of the information. It performs query operations to retrieve relevant information from the database (e.g., MySQL). The input is the generated query, and the output is the retrieved information result.

[0797] Step 4:

[0798] The server organizes the acquired information results. The organization process condenses the information into an easily understandable format for the user. The input is raw data, and the output is the organized information.

[0799] Step 5:

[0800] The server uses an emotion engine to analyze the user's emotional state based on data received from the terminal (such as voice tone). The analysis utilizes an emotion analysis library (e.g., Google Cloud Natural Language API). The input is the user's emotion-related data, and the output is the result of the user's emotional state.

[0801] Step 6:

[0802] The server adjusts the information presentation method according to the analyzed emotional state. Based on a specific emotion, it changes the information format and the emphasis of the presented content. The input is the result of the emotional state and organized information, and the output is the adjusted information.

[0803] Step 7:

[0804] The server generates the final information as a report and sends it to the terminal. The user reviews this report and obtains the necessary information. The input is the adjusted information, and the output is the information provided to the user.

[0805] 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.

[0806] 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.

[0807] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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."

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] The following is further disclosed regarding the embodiments described above.

[0827] (Claim 1)

[0828] Means for receiving information acquisition requests,

[0829] A means for analyzing received requests and generating search queries,

[0830] A means of identifying information sources and executing search queries,

[0831] A means of obtaining and organizing search results,

[0832] A means of generating organized information as a report,

[0833] A means of sending the generated report to the information requester,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, characterized by comprising means for learning from search results and improving the accuracy of subsequent searches.

[0837] (Claim 3)

[0838] The system according to claim 1, characterized by including means for visiting information sources and collecting new data.

[0839] "Example 1"

[0840] (Claim 1)

[0841] Means for receiving information acquisition requests,

[0842] A means for analyzing a received information retrieval request using natural language processing technology and generating a search query,

[0843] A means of identifying electronic information sources and obtaining information using generated search queries,

[0844] A means of visually organizing the acquired information in an easy-to-understand way and generating a report,

[0845] A means of visualizing the generated report and sending it to the information requester,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, characterized by having means for learning from acquired information and improving the accuracy of information acquisition in subsequent instances.

[0849] (Claim 3)

[0850] The system according to claim 1, characterized by including means for periodically circulating electronic information sources to collect new information.

[0851] "Application Example 1"

[0852] (Claim 1)

[0853] Means for receiving information acquisition requests,

[0854] A means for analyzing received requests and generating search queries,

[0855] A means of identifying information sources and executing search queries,

[0856] A means of obtaining and organizing search results,

[0857] A means of generating a report that visually displays organized information,

[0858] A means of sending the generated report to the information requester,

[0859] A means of analyzing machine conditions and manufacturing progress in the manufacturing environment,

[0860] A means for generating appropriate instructions for the operator based on the analysis results,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, characterized by comprising means for learning from search results and improving the accuracy of subsequent searches.

[0864] (Claim 3)

[0865] The system according to claim 1, characterized by comprising means for patrolling information sources to collect new information.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] Means for receiving information acquisition requests,

[0869] A means for analyzing received requests and generating search items,

[0870] A means of identifying the information infrastructure and executing the search items,

[0871] Means for obtaining and configuring search results,

[0872] A means of analyzing user emotional data to identify emotional states,

[0873] Means for adjusting the method of presenting information structured based on emotional state,

[0874] A means of generating the adjusted information as a report,

[0875] A means of sending the generated report to the information requester,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, characterized by comprising means for adjusting the method of providing information in subsequent instances based on the emotional state, thereby enhancing personalization.

[0879] (Claim 3)

[0880] The system according to claim 1, characterized by including means for patrolling an information infrastructure to collect new information.

[0881] "Application example 2 when combining with an emotional engine"

[0882] (Claim 1)

[0883] Means for receiving information acquisition requests,

[0884] A means for analyzing received requests and generating search queries,

[0885] A means of identifying information sources and executing search queries,

[0886] A means of obtaining and organizing search results,

[0887] A means of generating organized information as a report,

[0888] A means of analyzing the emotional state of users,

[0889] A means of adjusting the information presentation method based on the analysis results,

[0890] A means of sending the generated report to the information requester,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, characterized by comprising means for learning from search results and improving the accuracy of subsequent searches and the method of presenting information.

[0894] (Claim 3)

[0895] A means of collecting new data by visiting information sources,

[0896] The system according to claim 1, characterized by including means for providing customized information that corresponds to the user's emotional state. [Explanation of Symbols]

[0897] 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 for receiving information acquisition requests, A means for analyzing received requests and generating search queries, A means of identifying information sources and executing search queries, A means of obtaining and organizing search results, A means of generating a report that visually displays organized information, A means of sending the generated report to the information requester, A means of analyzing machine conditions and manufacturing progress in the manufacturing environment, A means for generating appropriate instructions for the operator based on the analysis results, A system that includes this.

2. The system according to claim 1, characterized by comprising means for learning from search results and improving the accuracy of subsequent searches.

3. The system according to claim 1, characterized by comprising means for circulating information sources to collect new information.

Images