system

Abstract

To provide a system.SOLUTION: Provided is a system comprising: means for accumulating, in a knowledge database, highly accurate results generated by a user via a knowledge generation platform; means for providing the user with the knowledge accumulated by the accumulating means in an ecosystem manner; means for improving convenience and business efficiency; means in which the user uses search engines and interactive agents to acquire information through the providing means; means for transmitting information acquired by a terminal to the knowledge generation platform; means in which a server analyzes information on the knowledge generation platform; means for accumulating, in the knowledge database, the information analyzed by the server with the analyzing means; and means in which the user reuses the information in the knowledge database.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising: a step of receiving a user utterance; a step of adding the user utterance to a prompt including an instruction sentence associated with a description of a character of the chatbot; a step of encoding the prompt; and a step of inputting the encoded prompt to a language model to generate a chatbot utterance in response to the user utterance. [Prior Art Literature] [Patent Literature]

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

[0004] There is a problem in that high-precision results generated through conventional use of search and chatbots are stored in a distributed manner, making it difficult to efficiently utilize the results. [Means for Solving the Problem]

[0005] As a means for solving this problem, the present invention provides a system that accumulates high-precision results generated by a user in a knowledge database via a knowledge generation platform, and provides the accumulated knowledge to users in the form of an ecosystem. This makes it possible to improve convenience and work efficiency. [Brief Description of the Drawings]

[0006] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16] This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3. [Figure 17] FIG. 1 is a sequence diagram showing a processing flow of a data processing system according to Example 1 of Morphological Example 1 when an emotion engine is combined. [Figure 18] FIG. 1 is a sequence diagram showing a processing flow of a data processing system according to Application Example 1 of Morphological Example 1 when an emotion engine is combined. [Figure 19] FIG. 1 is a sequence diagram showing a processing flow of a data processing system according to Example 2 of Morphological Example 2 when an emotion engine is combined. [Figure 20] FIG. 1 is a sequence diagram showing a processing flow of a data processing system according to Application Example 2 of Morphological Example 2 when an emotion engine is combined. [Figure 21] FIG. 1 is a sequence diagram showing a processing flow of a data processing system according to Example 3 of Morphological Example 3 when an emotion engine is combined. [Figure 22] FIG. 1 is a sequence diagram showing a processing flow of a data processing system according to Application Example 3 of Morphological Example 3 when an emotion engine is combined. MODE FOR CARRYING OUT THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0008] First, terms used in the following description will be explained.

[0009] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic device, or may be a combination of a plurality of arithmetic devices. Further, the processor may be one type of arithmetic device, or may be a combination of a plurality of types of arithmetic devices. Examples of the arithmetic device 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), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, the labeled RAM (Random Access Memory) is a memory for temporarily storing information, and is used as a work memory by the processor.

[0011] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0012] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like.

[0013] 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."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] One embodiment of the present invention is a system that stores high-precision results generated by users through conventional search and chatbot usage in a knowledge database via a knowledge generation platform. Specifically, users transmit information obtained through search or chatbot usage to the knowledge generation platform, where that information is stored in the knowledge database. This knowledge database stores knowledge in various fields and provides that knowledge to users in the form of an ecosystem.

[0029] "Example of form 2"

[0030] As a concrete example, when a user searches for medical information, the search results are sent to a knowledge generation platform, where the information is stored in a knowledge database. Subsequently, when another user needs similar information, the relevant information is retrieved from the knowledge database and provided to the user. This allows users to efficiently obtain the information they need.

[0031] "Example of form 3"

[0032] Furthermore, the embodiment of the present invention is a system aimed at improving convenience and operational efficiency. Specifically, by providing information stored in a knowledge database to users at the time they need it, it shortens the time users spend searching for information and improves operational efficiency.

[0033] The following describes the processing flow for each example of the form.

[0034] "Example of form 1"

[0035] Step 1: Users generate information using traditional search and chatbot functions.

[0036] Step 2: Send the generated information to the knowledge generation platform.

[0037] Step 3: The knowledge generation platform stores the information in the knowledge database.

[0038] "Example of form 2"

[0039] Step 1: The user performs a search for medical information.

[0040] Step 2: Submit the search results to the knowledge generation platform.

[0041] Step 3: The knowledge generation platform stores the information in the knowledge database.

[0042] Step 4: If another user requires similar information, retrieve the relevant information from the knowledge database and provide it to the user.

[0043] "Example of form 3"

[0044] Step 1: The user searches for the information they need.

[0045] Step 2: Retrieve the relevant information from the knowledge database.

[0046] Step 3: Provide the acquired information to the user.

[0047] (Example 1)

[0048] Next, we will describe Example 1 of Form 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."

[0049] Information obtained through conventional search engines and conversational agents is temporary and difficult to reuse. Furthermore, there is a lack of means to guarantee the accuracy and reliability of the information obtained, making it difficult for users to efficiently obtain highly accurate information. Moreover, there is a need for methods to improve user convenience and enhance operational efficiency by providing accumulated knowledge as an ecosystem.

[0050] 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.

[0051] In this invention, the server includes means for accumulating high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the accumulated knowledge to users in the form of an ecosystem, and means for improving convenience and operational efficiency. This makes it possible for users to efficiently accumulate and reuse high-precision information obtained using search engines and conversational agents.

[0052] A "user" is an individual or organization that uses the system to acquire information and transmits the generated results to the knowledge generation platform.

[0053] "High-precision results" refer to accurate and reliable information obtained by users using search engines or conversational agents.

[0054] A "knowledge generation platform" is a system that analyzes information submitted by users, converts it into an appropriate format, and stores it in a knowledge database.

[0055] A "knowledge database" is a database system that stores analyzed information and saves it in a format that can be reused later.

[0056] An "ecosystem" is the overall structure of a system that provides accumulated knowledge to users, enabling them to acquire information efficiently.

[0057] A "search engine" is software that searches the internet for relevant information based on keywords entered by the user and provides the results.

[0058] A "conversational agent" is software that responds to user questions in natural language, and is also known as a chatbot.

[0059] A "device" refers to a device used by a user to access search engines or conversational agents, and includes PCs, smartphones, and other similar devices.

[0060] A "server" is a computer system that operates knowledge generation platforms and knowledge databases, and performs information analysis and storage.

[0061] "Natural language processing technology" is a technique that allows computers to understand and analyze human language, and is used to understand the meaning of information and convert it into an appropriate format.

[0062] The HTTPS protocol is a communication protocol used to securely send and receive data over the internet.

[0063] This invention is a system that stores high-precision results generated by users in a knowledge database via a knowledge generation platform, and provides the stored knowledge to users in the form of an ecosystem. Specific embodiments of this system are described below.

[0064] System Configuration

[0065] hardware

[0066] Devices: PCs, smartphones, tablets, and other devices. Users access search engines and conversational agents using these devices.

[0067] Server: A computer system used to operate knowledge generation platforms and knowledge databases. It is equipped with a high-performance processor and large-capacity storage.

[0068] software

[0069] Search engine: Software that searches the internet for relevant information based on keywords entered by the user and provides the results.

[0070] Conversational agent: Software that responds to user questions in natural language. It uses generative AI models to generate appropriate answers to questions.

[0071] Knowledge generation platform: A system that analyzes information submitted by users, converts it into an appropriate format, and stores it in a knowledge database. It uses natural language processing technologies such as Google® Cloud Natural Language API and IBM Watson® Natural Language Understanding.

[0072] Knowledge database: A database system that stores analyzed information and saves it in a format that can be reused later. It uses database management systems such as MySQL (registered trademark) or PostgreSQL.

[0073] Data processing and data calculation

[0074] Information acquisition and transmission

[0075] Users use their devices to access search engines and conversational agents to obtain information. For example, a user might ask a conversational agent, "Tell me about the latest AI technologies." The conversational agent uses a generative AI model to generate an appropriate answer to the question. If the answer is deemed highly accurate, the device sends this information to a knowledge generation platform. The HTTPS protocol is used for transmission.

[0076] Information analysis and storage

[0077] The server analyzes the information received by the knowledge generation platform. This analysis uses natural language processing technologies such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding. The server understands the meaning of the information and converts it into an appropriate format. The analyzed information is stored in a knowledge database.

[0078] Reuse of information

[0079] When a user uses a search engine or conversational agent again to obtain information, the information stored in the knowledge database is reused. For example, if another user asks, "Tell me about the latest AI technologies," the conversational agent retrieves information from the knowledge database such as "It includes generative AI models and deep learning" and answers accordingly.

[0080] Examples of specific cases and prompt statements

[0081] As a concrete example, consider a scenario where a user asks a conversational agent, "Tell me about the latest AI technologies." The conversational agent replies, "The latest AI technologies include generative AI models and deep learning." If this answer is deemed highly accurate, the device sends this information to a knowledge generation platform. The server analyzes the information using the Google Cloud Natural Language API and stores it in a MySQL database. This information is then reused when other users search for "the latest AI technologies."

[0082] Examples of prompts to input into a generative AI model include the following:

[0083] "Tell me about the latest AI technology."

[0084] By entering this prompt into the interactive agent, the user can obtain highly accurate information, which is then stored in a knowledge database.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] Users obtain information using search engines or conversational agents.

[0088] As a concrete example, the user uses their device to ask the conversational agent, "Tell me about the latest AI technology."

[0089] Input: User's question (prompt)

[0090] Output: Response from the conversational agent (response generated by the AI ​​model)

[0091] Step 2:

[0092] The device transmits the information it acquires to the knowledge generation platform.

[0093] Specifically, the device sends the response it received from the conversational agent, "The latest AI technologies include generative AI models and deep learning," to the knowledge generation platform using the HTTPS protocol.

[0094] Input: Response from the conversational agent

[0095] Output: Data to be sent to the knowledge generation platform

[0096] Step 3:

[0097] The server analyzes the information on the knowledge generation platform.

[0098] Specifically, the server uses the Google Cloud Natural Language API to analyze the information it receives, understand its meaning, and convert it into an appropriate format.

[0099] Input: Data sent to the knowledge generation platform

[0100] Output: Analyzed information (data converted to an appropriate format)

[0101] Step 4:

[0102] The server stores the analyzed information in a knowledge database.

[0103] Specifically, the server inserts the analyzed information into a MySQL database so that it can be reused later.

[0104] Input: Analyzed information

[0105] Output: Data stored in the knowledge database

[0106] Step 5:

[0107] Users reuse information from knowledge databases.

[0108] In a concrete example, if another user asks the conversational agent, "Tell me about the latest AI technologies," the conversational agent retrieves information from its knowledge database stating, "It includes generative AI models and deep learning," and then provides the answer.

[0109] Input: User's question (prompt)

[0110] Output: Information obtained from the knowledge database (response from the conversational agent)

[0111] (Application Example 1)

[0112] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0113] Traditional factory operations have faced challenges such as difficulty in quickly obtaining necessary information from workers, leading to decreased work efficiency. Furthermore, significant time was often spent troubleshooting and determining optimal work procedures, resulting in overall reduced productivity. While automation using robots is advancing, insufficient coordination with human workers has made efficient operation difficult.

[0114] 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.

[0115] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for providing a knowledge-sharing robot assistant to improve work efficiency within the factory, means for displaying information to workers in real time via smart devices, and means for robots to transport necessary parts or automate simple tasks according to the worker's instructions. This enables workers to quickly obtain necessary information and efficiently perform troubleshooting and optimal work procedures. Furthermore, collaboration with robots is enhanced, improving overall productivity.

[0116] "Users" refer to individuals who use the system to search for information or acquire knowledge.

[0117] "High-precision results" refers to accurate and reliable information obtained through search engines or chatbots.

[0118] A "knowledge generation platform" refers to a system that collects information obtained by users and stores it in a knowledge database.

[0119] A "knowledge database" refers to a database that accumulates knowledge from various fields and provides it to users in the form of an ecosystem.

[0120] An "ecosystem" refers to a system that provides users with information accumulated in a knowledge database, allowing them to use and share that information with one another.

[0121] "Improving convenience" refers to enabling users to quickly and easily obtain the information they need.

[0122] "Improving operational efficiency" refers to increasing the efficiency of work and improving productivity.

[0123] A "knowledge-sharing robot assistant" refers to a robot that retrieves information from a knowledge database and provides it to workers in order to improve work efficiency within a factory.

[0124] A "smart device" refers to a device used to display information, such as a smartphone, smart glasses, or a head-mounted display.

[0125] "Displaying information in real time" means instantly displaying necessary information so that workers can use it on the spot.

[0126] A "robot" refers to a machine that transports necessary parts or automates simple tasks according to the instructions of a worker.

[0127] In order to implement this invention, the following system configuration and program are required.

[0128] System Configuration

[0129] 1. Hardware

[0130] Smart devices: Smartphones, smart glasses, head-mounted displays (e.g., Google Glass®, Microsoft HoloLens®)

[0131] Factory robots: Robots that automate the handling of parts and simple tasks (e.g., Universal Robots UR series)

[0132] Server: A server to host the knowledge generation platform and knowledge database.

[0133] 2. Software

[0134] API Server: Server software (e.g., Flask) that provides the functionality of a knowledge generation platform.

[0135] Database: Database software that functions as a knowledge database (e.g., MongoDB)

[0136] Program processing

[0137] The server executes a program that includes the following actions:

[0138] 1. Knowledge Generation Platform

[0139] Users utilize search and chatbots via their smart devices and send the highly accurate results obtained to a knowledge generation platform.

[0140] The knowledge generation platform stores the received information in a knowledge database.

[0141] 2. Knowledge DB

[0142] The knowledge database accumulates knowledge from various fields and provides it to users in the form of an ecosystem.

[0143] When a user requests the information they need, the system retrieves the most relevant information from the knowledge database and displays it on their smart device in real time.

[0144] 3. Knowledge-sharing robot assistant

[0145] To improve work efficiency within the factory, information is retrieved from the knowledge database and provided to workers.

[0146] The robots transport necessary parts according to the worker's instructions and automate simple tasks.

[0147] Specific example

[0148] For example, when a worker searches for "optimal welding techniques," the knowledge generation platform stores that information in the knowledge database. Then, when another worker needs the same information, the information on "optimal welding techniques" is retrieved from the knowledge database and displayed in real time on smart glasses.

[0149] Furthermore, if troubleshooting is required, a worker can search for "Solution for Error Code 123," and the solution will be retrieved from the knowledge database and displayed on the head-mounted display. In addition, the robot will transport the necessary parts according to the worker's instructions, automating the work.

[0150] Example of a prompt

[0151] "Please tell me the optimal welding technique."

[0152] "Please tell me how to resolve error code 123."

[0153] This allows workers to quickly obtain necessary information and efficiently perform troubleshooting and optimal work procedures. Furthermore, it enhances collaboration with robots, improving overall productivity.

[0154] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0155] Step 1:

[0156] Users input information using smart devices via search queries or chatbots. The entered queries are sent to a knowledge generation platform. The input here is text data related to the information the user wants to know or the problem they want to solve. The output is the query data sent to the knowledge generation platform.

[0157] Step 2:

[0158] The server processes query data received through the knowledge generation platform and generates relevant high-accuracy results. This process uses a generative AI model to produce the best possible answers to queries. The input is the query data submitted by the user, and the output is the generated high-accuracy results.

[0159] Step 3:

[0160] The server stores the generated high-precision results in a knowledge database. The input here is the generated high-precision results, and the output is the data stored in the knowledge database. Data processing involves converting the result data into an appropriate format and saving it to the database.

[0161] Step 4:

[0162] If the user needs the information again, they send a request to the knowledge database via their smart device. The input is the request data about the information the user wants to know, and the output is the request data sent to the knowledge database.

[0163] Step 5:

[0164] The server retrieves information corresponding to the request from the knowledge database. The input is the request data from the user, and the output is the relevant information retrieved from the knowledge database. In terms of data calculation, the database is searched based on the request, and the most relevant information is extracted.

[0165] Step 6:

[0166] The server transmits the acquired information to the smart device and displays it to the user in real time. The input is information retrieved from the knowledge database, and the output is the information displayed on the smart device. Specifically, the server converts the information into an appropriate format and displays it on the smart device's screen.

[0167] Step 7:

[0168] When a user gives instructions to a robot, they send those instructions to the robot via a smart device. The input is the instruction data from the user, and the output is the instruction data sent to the robot.

[0169] Step 8:

[0170] The robot transports necessary parts or automates simple tasks based on received instructions. The input is instruction data from the user, and the output is the result of the performed work. Specifically, the robot operates according to the instructions and performs the specified task.

[0171] This allows users to quickly obtain the information they need and efficiently perform troubleshooting and optimal work procedures. Furthermore, it enhances collaboration with robots, improving overall productivity.

[0172] (Example 2)

[0173] Next, we will describe Example 2 of Form 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".

[0174] Conventional medical information retrieval systems made it difficult for users to efficiently obtain the information they needed. Furthermore, when multiple users searched for the same information, they had to repeat the same search process each time, which was time-consuming and labor-intensive. In addition, there was a lack of effective means to utilize accumulated knowledge, creating a need for improved convenience and operational efficiency.

[0175] 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.

[0176] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for users to search for medical information and transmit the search results to the knowledge generation platform, and means for retrieving relevant information from the knowledge database and providing it to other users when they require similar information. As a result, users can efficiently obtain the medical information they need, and the time and effort required when multiple users search for the same information can be reduced. Furthermore, by effectively utilizing the stored knowledge, convenience and operational efficiency can be improved.

[0177] A "user" is an individual or organization that uses the system to search for medical information.

[0178] "High-precision results" refer to accurate and reliable information obtained by users when they perform a search.

[0179] A "knowledge generation platform" is a system for processing search results and storing them in a knowledge database.

[0180] A "knowledge database" is a database system used to store and manage accumulated medical information and other knowledge.

[0181] An "ecosystem" is the overall environment of a system that provides accumulated knowledge to users and facilitates its mutual use.

[0182] "Improving convenience" refers to enabling users to quickly and easily obtain the information they need.

[0183] "Improving operational efficiency" refers to increasing the efficiency of work through the use of a system, thereby reducing time and effort.

[0184] "Medical information" refers to all information related to healthcare, such as disease treatments, symptoms, and medication information.

[0185] "Search results" refer to a list of information obtained when a user performs a search.

[0186] "Sending" refers to the act of sending data from a device to a server.

[0187] "Acquisition" refers to the act of a server retrieving necessary information from a knowledge database.

[0188] "Providing" refers to the act of displaying information acquired by the server to the user.

[0189] This invention is a system for users to efficiently acquire medical information. Specific embodiments of this system are described below.

[0190] System Configuration

[0191] This system mainly consists of the following components:

[0192] User's device (PC, smartphone, etc.)

[0193] server

[0194] Knowledge generation platform

[0195] Knowledge Database

[0196] Hardware and software to use

[0197] Device: A device such as a PC or smartphone. A web browser (e.g., Google Chrome®, Mozilla Firefox) is used to perform the search.

[0198] Server: Receives and processes search queries. Uses a web server (e.g., Apache® HTTP Server, Nginx) and a database management system (e.g., MySQL, PostgreSQL).

[0199] Knowledge generation platform: Processes search results and stores them in a knowledge database. Uses a data streaming platform (e.g., Apache Kafka).

[0200] Knowledge database: Stores and manages accumulated medical information. Uses a database management system (e.g., MySQL, PostgreSQL).

[0201] System operation

[0202] 1. Users search for medical information.

[0203] Users open a web browser on their PC or smartphone and access search engines or dedicated medical information search sites.

[0204] Enter keywords such as "diabetes treatments" into the search box and click the search button.

[0205] 2. The device sends the search results to the server.

[0206] The terminal sends the generated search query to the server as an HTTP request.

[0207] Example: The device sends the request "GET / search?q=diabetes treatment HTTP / 1.1" to the server.

[0208] 3. The server processes the data on the knowledge generation platform.

[0209] The server analyzes the received search queries and collects relevant medical information.

[0210] The server sends the collected information to the knowledge generation platform.

[0211] Example: A server collects information about "diabetes treatments" and sends it to a knowledge generation platform.

[0212] 4. The server stores data in the knowledge database.

[0213] The knowledge generation platform stores the received information in a knowledge database.

[0214] Example: Information about "treatments for diabetes" is stored in a knowledge database.

[0215] 5. Another user searches for similar information.

[0216] Another user similarly uses a PC or smartphone to search for medical information.

[0217] Enter "diabetes treatments" into the search box and click the search button.

[0218] 6. The server retrieves the relevant information from the knowledge database and provides it to the user.

[0219] The server searches for and retrieves the relevant information from the knowledge database.

[0220] The server sends the retrieved information to the user's terminal as an HTTP response.

[0221] Example: The server retrieves information about "treatments for diabetes" from a knowledge database and displays it to the user.

[0222] Examples of specific cases and prompt statements

[0223] Specific example

[0224] User A searches for "treatments for high blood pressure," and the results are saved in the knowledge database.

[0225] When user B later searches for "treatments for high blood pressure," information is retrieved from the knowledge database and provided to user B.

[0226] Example of a prompt

[0227] "Please provide me with the latest information on treatments for high blood pressure."

[0228] "Please provide detailed information regarding diabetes treatment options."

[0229] This system allows users to efficiently obtain necessary medical information. It also reduces the time and effort required for multiple users to search for the same information. By effectively utilizing accumulated knowledge, convenience and operational efficiency can be improved.

[0230] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0231] Step 1:

[0232] Users search for medical information.

[0233] Input: The user uses a PC or smartphone, opens a web browser, and accesses a search engine or a dedicated medical information search site. They enter keywords such as "diabetes treatment" into the search box and click the search button.

[0234] Data processing: Search queries are generated.

[0235] Output: The generated search query is retained on the terminal.

[0236] Specific operation: When a user enters "diabetes treatments" and clicks the search button, a search query is generated.

[0237] Step 2:

[0238] The device sends the search results to the server.

[0239] Input: The generated search query.

[0240] Data processing: The terminal sends the search query to the server as an HTTP request.

[0241] Output: The server receives the search query.

[0242] Specific action: The terminal sends a request to the server: "GET / search?q=diabetes treatment HTTP / 1.1".

[0243] Step 3:

[0244] The server processes the data on the knowledge generation platform.

[0245] Input: The search query received by the server.

[0246] Data processing: The server analyzes search queries and collects relevant medical information. The collected information is then sent to the knowledge generation platform.

[0247] Output: The knowledge generation platform receives the information.

[0248] Specific operation: The server collects information on "diabetes treatments" and sends it to the knowledge generation platform.

[0249] Step 4:

[0250] The server stores data in a knowledge database.

[0251] Input: Information received by the knowledge generation platform.

[0252] Data processing: The knowledge generation platform stores the received information in a knowledge database.

[0253] Output: Information is stored in the knowledge database.

[0254] Specific action: Information about "treatments for diabetes" is stored in the knowledge database.

[0255] Step 5:

[0256] Another user searches for similar information

[0257] Input: Another user uses a PC or smartphone, opens a web browser, and accesses a search engine or a dedicated medical information search site. They enter "diabetes treatments" into the search box and click the search button.

[0258] Data processing: Search queries are generated.

[0259] Output: The generated search query is retained on the terminal.

[0260] Specific operation: When another user types "diabetes treatments" and clicks the search button, a search query is generated.

[0261] Step 6:

[0262] The server retrieves the relevant information from the knowledge database and provides it to the user.

[0263] Input: The search query received by the server.

[0264] Data processing: The server searches for and retrieves the relevant information from the knowledge database. The retrieved information is then sent to the user's terminal as an HTTP response.

[0265] Output: Information is displayed on the user's terminal.

[0266] Specific operation: The server retrieves information about "diabetes treatments" from the knowledge database and displays it to the user.

[0267] (Application Example 2)

[0268] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0269] In modern brick-and-mortar stores, there is a challenge in that it is difficult for customers to efficiently obtain product information. In particular, if a customer wants to know detailed information or stock status about a specific product, they have to ask a store employee, which is time-consuming and troublesome. Furthermore, if multiple customers request the same information, duplicate information retrieval occurs, which is inefficient. In addition, traditional search systems and chatbots have difficulty providing information in real time, which reduces customer convenience.

[0270] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing high-precision results generated by the user in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, means for improving convenience and operational efficiency, and means for providing product information in real time using smart devices in physical stores. As a result, users can improve their shopping experience in physical stores and quickly and efficiently obtain the necessary product information.

[0271] A "user" is an individual or organization that uses the system to search for and retrieve information.

[0272] "High-precision results" refer to search results that provide accurate and relevant information for the user's search query.

[0273] A "knowledge generation platform" is a system for collecting information generated by users and accumulating it in a knowledge database.

[0274] A "knowledge database" is a database for accumulating collected information and providing it to users as needed.

[0275] An "ecosystem" is an integrated system environment for providing information accumulated in the knowledge database to users.

[0276] "Improved convenience" refers to enabling users to acquire necessary information quickly and efficiently.

[0277] "Improved operational efficiency" refers to preventing duplicate acquisition of information and increasing the efficiency of the entire system.

[0278] A "physical store" is a store that sells products at a physical location.

[0279] A "smart device" is an electronic device connected to the Internet that can display and operate information.

[0280] "Real-time" refers to the immediate acquisition and provision of information.

[0281] The present invention is a system for providing product information in real time using a smart device in a physical store. Specific embodiments of this system are described below.

[0282] System Configuration

[0283] The system is composed of the following main components.

[0284] 1. Knowledge generation platform: collects high-precision results generated by users and accumulates them in the knowledge database.

[0285] 2. Knowledge Database: Stores accumulated information and provides it as needed.

[0286] 3. Smart devices: Devices used by customers in physical stores (e.g., smart glasses).

[0287] 4. Ecosystem: An integrated system that provides users with information accumulated in a knowledge database.

[0288] Program processing

[0289] The server stores the high-precision results generated by users in a knowledge database via the knowledge generation platform. Specifically, when a user searches for product information using a smart device, the search results are sent to the knowledge generation platform. The knowledge generation platform analyzes the search results and stores them in the knowledge database.

[0290] Next, if another user needs information about the same product, they can access the knowledge database via their smart device and retrieve the relevant information. The retrieved information is displayed in real time on the smart device's screen.

[0291] Hardware and software to use

[0292] Hardware: Smart glasses, servers

[0293] Software: Knowledge generation platform, knowledge database, API

[0294] Specific example

[0295] For example, suppose a user is looking for "medical masks" in a physical store. When the user, wearing smart glasses, searches for "medical masks" by voice, detailed information and stock availability of medical masks will be displayed on the smart glasses' screen. This information is retrieved in real time from a knowledge database.

[0296] Example of prompt sentence

[0297] "Search for information on medical masks."

[0298] "Retrieve information on medical masks from the knowledge database."

[0299] "Display information on medical masks on the smart glasses."

[0300] In this way, the user can improve the in-store shopping experience and quickly and efficiently obtain necessary product information.

[0301] The flow of the specific processing in Application Example 2 will be described with reference to FIG. 14.

[0302] Step 1:

[0303] A user searches for product information using a smart device (e.g., smart glasses). The user inputs a search query via voice input or touch operation. The input query is transmitted from the smart device to the server. The input data is the search query, and the output data is the search request transmitted to the server.

[0304] Step 2:

[0305] The server transmits the received search query to a knowledge generation platform. The knowledge generation platform analyzes the search query and generates relevant high-precision results. The input data is the search query, and the output data is the high-precision results. As a specific operation, the knowledge generation platform analyzes the search query and acquires relevant information from the database.

[0306] Step 3:

[0307] The knowledge generation platform stores the high-precision results it generates in a knowledge database. The input data consists of the high-precision results, while the output data is the information stored in the knowledge database. Specifically, the knowledge generation platform writes the high-precision results to the database.

[0308] Step 4:

[0309] When another user searches for information about the same product, they use their smart device to re-enter the search query. The entered query is sent from the smart device to the server. The input data is the search query, and the output data is the search request sent to the server.

[0310] Step 5:

[0311] The server accesses the knowledge database and retrieves the relevant information. The input data is a search query, and the output data is the information retrieved from the knowledge database. Specifically, the server sends a query to the knowledge database and retrieves the relevant information.

[0312] Step 6:

[0313] The server sends the acquired information to the smart device. The input data is information retrieved from the knowledge database, and the output data is the information sent to the smart device. Specifically, the server transfers the acquired information to the smart device.

[0314] Step 7:

[0315] A smart device displays received information to the user. Input data is information sent from the server, and output data is information displayed on the smart device's screen. Specifically, the smart device displays the received information on its screen.

[0316] In this way, users can improve their in-store shopping experience and obtain necessary product information quickly and efficiently.

[0317] (Example 3)

[0318] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0319] Conventional information retrieval systems often made it difficult for users to quickly obtain the information they needed, resulting in time-consuming information searches. Furthermore, search results frequently did not match user needs, hindering improvements in operational efficiency. Additionally, conventional systems lacked effective means of utilizing accumulated knowledge, making knowledge reuse difficult.

[0320] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0321] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform; means for providing the stored knowledge to users in the form of an ecosystem; means for receiving and analyzing queries sent by users from terminals; means for searching for relevant information from the knowledge database based on the analyzed queries; means for inputting the search results as prompt sentences into a generation AI model to generate appropriate answers; and means for providing the generated answers to users. As a result, users can quickly obtain the information they need, reduce information retrieval time, and improve work efficiency.

[0322] A "user" is an individual or organization that uses the system to search for information and obtain the necessary data.

[0323] "High-precision results" refer to search results that provide accurate and appropriate information in response to the user's query.

[0324] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[0325] A "knowledge database" is a database that stores accumulated information and knowledge, and allows it to be searched and retrieved as needed.

[0326] An "ecosystem" is the overall structure of a system that provides users with accumulated knowledge and promotes the reuse and sharing of information.

[0327] A "terminal" is a device (e.g., a personal computer or smartphone) used by a user to input queries and communicate with a server.

[0328] A "query" is a question or request that a user enters into a system to search for information.

[0329] A "server" is a computer system that receives and analyzes queries, retrieves information from a knowledge database, and generates answers using a generative AI model.

[0330] A "generative AI model" is an artificial intelligence model that generates appropriate responses in natural language based on input prompt sentences.

[0331] A "prompt sentence" is an instruction given to a generative AI model, and it is the sentence that forms the basis for the model to generate an appropriate response.

[0332] Modes for carrying out the invention

[0333] This invention is a system for quickly obtaining information that users need and improving work efficiency. Specific embodiments of this system are described below.

[0334] System Configuration

[0335] hardware

[0336] Server: High-performance server (e.g., general-purpose server)

[0337] Device: The device used by the user (e.g., personal computer, smartphone)

[0338] software

[0339] Database management system: Software for managing knowledge databases (e.g., MySQL)

[0340] Generative AI models: Artificial intelligence models that perform natural language processing (e.g., general-purpose generative AI models)

[0341] Program processing

[0342] The server receives and parses queries sent from the terminal. Based on the parsed queries, the server searches for relevant information in its knowledge database. The search results are input as prompts into a generative AI model, which generates appropriate answers. The generated answers are sent from the server to the terminal and provided to the user.

[0343] Specific example

[0344] For example, consider a case where a user enters the query, "Tell me about the latest project management tools."

[0345] 1. Query Reception: The user sends a query from their terminal saying, "Tell me about the latest project management tools."

[0346] 2. Query Analysis: The server analyzes the query and searches the knowledge database for information related to "project management tools."

[0347] 3. Information Retrieval: The server uses MySQL to retrieve relevant information from the knowledge database.

[0348] 4. Use of Generative AI Models: The server inputs the acquired information into a generative AI model, which then formats the information in a way that is easy for the user to understand.

[0349] 5. Information Provision: The server sends the formatted information to the user's terminal.

[0350] An example of a prompt to input into the generating AI model would be, "Please provide information about the latest project management tools. Please use the following data as a basis," followed by inputting information obtained from the knowledge database.

[0351] In this way, users can quickly obtain the necessary information, reduce information retrieval time, and improve work efficiency. The flow of the specific processing in Example 3 will be explained using Figure 15.

[0352] Step 1:

[0353] The user enters a query.

[0354] The user enters the information they want to retrieve from their device (e.g., a computer or smartphone). For example, they might enter, "Tell me about the latest project management tools." The entered query is saved in the input field on the device.

[0355] Step 2:

[0356] The terminal sends a query to the server.

[0357] The terminal sends the query entered by the user to the server as an HTTP request. This data is transmitted over the internet. The input is the user's query, and the output is the HTTP request to the server.

[0358] Step 3:

[0359] The server receives and parses the query.

[0360] The server receives HTTP requests sent from the terminal. It parses the received queries and identifies the type of information the user is seeking. The input is the HTTP request, and the output is the parsed query. Specifically, the server recognizes the query content as information related to "project management tools."

[0361] Step 4:

[0362] The server searches for relevant information from the knowledge database.

[0363] The server searches for relevant information from the knowledge database based on the analysis results. For example, it uses a database management system (e.g., MySQL) to retrieve the latest information on "project management tools". The input is the parsed query, and the output is the search result. Specifically, it executes the query "SELECT FROM knowledge_db WHERE topic='project management tools' ORDER BY date DESC LIMIT 1".

[0364] Step 5:

[0365] The server inputs prompt messages into the generated AI model.

[0366] The server inputs prompts to the generating AI model based on information retrieved from the knowledge database. An example of a prompt is, "Please provide information about the latest project management tools. Please use the following data as a basis." The input is the search results, and the output is the prompts to the generating AI model.

[0367] Step 6:

[0368] The generative AI model generates the appropriate answer.

[0369] The generative AI model generates appropriate answers based on the input prompt. The generated answers are expressed in natural language that is easy for the user to understand. The input is the prompt, and the output is the generated answer. Specifically, it generates answers such as, "Modern project management tools help with task management, visualization of project progress, and team collaboration."

[0370] Step 7:

[0371] The server sends the generated response to the user.

[0372] The server sends the response obtained from the generated AI model to the user's device. This data is transmitted over the internet. The input is the generated response, and the output is an HTTP response to the user's device. Specifically, the response is sent in JSON format.

[0373] Step 8:

[0374] The user receives the response.

[0375] The user receives the response from the server on their device and checks the displayed answer. This allows the user to quickly obtain the necessary information. The input is the HTTP response from the server, and the output is the answer displayed on the user's device.

[0376] (Application Example 3)

[0377] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0378] Conventional systems made it difficult for users to quickly obtain the information they needed, and in particular, information retrieval was time-consuming, leading to decreased operational efficiency, especially in the maintenance and troubleshooting of factory robots. Furthermore, the lack of means to provide appropriate information in response to error codes and maintenance requests made it difficult to respond quickly.

[0379] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0380] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, and means for robots to detect error codes and maintenance requests, and for retrieving and providing relevant information from the knowledge database. This enables users to quickly obtain the information they need and allows for quick and appropriate responses in the maintenance and troubleshooting of factory robots.

[0381] "User" refers to an individual or organization that uses the system to obtain information and perform tasks.

[0382] "High-precision results" refers to accurate and reliable information and data generated by users.

[0383] A "knowledge generation platform" refers to a system or tool that collects information generated by users and stores it in a knowledge database.

[0384] A "knowledge database" refers to a database that systematically stores accumulated information and knowledge, and makes it searchable and available as needed.

[0385] An "ecosystem" refers to an integrated system or environment for providing users with information accumulated in a knowledge database.

[0386] "Improving convenience" refers to enhancing the ease of use and comfort for users when using the system.

[0387] "Improving work efficiency" refers to reducing the time and effort required to perform tasks and thereby increasing productivity.

[0388] The term "robot" refers to automated machinery used in factories and other similar settings.

[0389] An "error code" refers to an identification number or string of characters displayed when a robot or system detects an abnormality.

[0390] A "maintenance request" refers to a notification or instruction issued by a robot or system when it requires regular maintenance or repair.

[0391] "Related information" refers to specific countermeasures and procedures for responding to error codes and maintenance requests.

[0392] As an example of how to implement this invention, we will describe a "smart maintenance assistant" system installed on a factory robot.

[0393] System program

[0394] The system consists of the following main components:

[0395] 1. Knowledge Generation Platform

[0396] 2. Knowledge Database

[0397] 3. Ecosystem

[0398] 4. Robot error detection and maintenance request detection function

[0399] Program Processing Description

[0400] Hardware to use

[0401] Factory robots (e.g., general industrial robots)

[0402] Computer installed in the robot

[0403] Software to use

[0404] Python program

[0405] Knowledge database (database management system)

[0406] Data processing and data calculation

[0407] 1. Knowledge Generation Platform

[0408] The server stores the high-precision results generated by users in a knowledge database via the knowledge generation platform. This ensures that the information generated by users is systematically stored.

[0409] 2. Knowledge Database

[0410] The server provides users with accumulated knowledge in the form of an ecosystem. The knowledge database includes maintenance information and troubleshooting guides.

[0411] 3. Ecosystem

[0412] The server provides users with the information they need quickly through the ecosystem. This improves convenience and operational efficiency.

[0413] 4. Robot error detection and maintenance request detection function

[0414] The robot detects error codes and maintenance requests, and retrieves relevant information from a knowledge database. This allows for quick and appropriate maintenance and troubleshooting of the robot.

[0415] Specific example

[0416] For example, if the robot detects "error_101," it retrieves the information "Please check the belt tension" from the knowledge database and displays it on the robot's display.

[0417] Example of a prompt

[0418] "If the robot detects an error code, retrieve the corresponding maintenance information from the knowledge database and display it."

[0419] The above describes the embodiment for carrying out this invention. This system allows users to quickly obtain necessary information and to respond quickly and appropriately to maintenance and troubleshooting of factory robots.

[0420] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0421] Step 1:

[0422] The server stores the high-precision results generated by users in a knowledge database via the knowledge generation platform.

[0423] Input: High-precision results generated by the user

[0424] Data processing: High-precision results are formalized using a knowledge generation platform and stored in a knowledge database.

[0425] Output: High-precision results stored in the knowledge database

[0426] Specific operation: The server receives the data entered by the user and saves it to the database in the appropriate format.

[0427] Step 2:

[0428] The server provides users with accumulated knowledge in the form of an ecosystem.

[0429] Input: Information stored in the knowledge database

[0430] Data processing: Search for necessary information from the knowledge database and provide it through the ecosystem.

[0431] Output: Knowledge information provided to users

[0432] Specific operation: When a user requests information, the server searches the database for the relevant information and provides it to the user through the ecosystem.

[0433] Step 3:

[0434] The robot detects error codes and maintenance requests.

[0435] Input: Data from the robot's sensors and internal systems.

[0436] Data processing: Analyze and identify error codes and maintenance requests.

[0437] Output: Detected error codes and maintenance requests

[0438] Specific operation: When the robot detects an anomaly during operation, it analyzes data from sensors and internal systems to identify error codes and maintenance requests.

[0439] Step 4:

[0440] The server searches the knowledge database for relevant information based on the detected error code and maintenance request.

[0441] Input: Detected error codes or maintenance requests

[0442] Data processing: Search for relevant information from the knowledge database.

[0443] Output: Related Information

[0444] Specific operation: The server receives error codes and maintenance requests and searches the knowledge database for the corresponding information.

[0445] Step 5:

[0446] The server provides the robot with the relevant information that was found.

[0447] Input: Related information retrieved from the knowledge database

[0448] Data processing: Converting information into a format that robots can understand.

[0449] Output: Relevant information provided to the robot

[0450] Specific operation: The server sends the retrieved information to the robot, which then displays it on the robot's display and audio output.

[0451] Step 6:

[0452] The robot performs maintenance and troubleshooting based on the information provided.

[0453] Input: Relevant information provided by the server

[0454] Data processing: Execute specific maintenance and troubleshooting procedures based on the information.

[0455] Output: Maintenance and troubleshooting complete

[0456] Specific actions: The robot performs necessary maintenance tasks and troubleshooting according to the information provided.

[0457] 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.

[0458] "Example of form 1"

[0459] One embodiment of the present invention provides a system that incorporates an emotion engine. This system includes means for storing high-precision results generated by the user in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, and means for improving convenience and operational efficiency. Furthermore, this system includes an emotion engine that recognizes the user's emotions. Specifically, the emotion engine recognizes emotions from the user's tone of voice, facial expressions, text input, etc., and adjusts the operation of the knowledge generation platform according to those emotions. For example, if the user is perceived as angry, the emotion engine sends instructions to the knowledge generation platform to prioritize the provision of knowledge that will quickly resolve the user's problem.

[0460] "Example of form 2"

[0461] Another embodiment of the present invention provides a system in which an emotion engine selects knowledge to provide in accordance with the user's emotions. This system includes means for storing high-precision results generated by the user in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, and means for improving convenience and operational efficiency. Furthermore, this system includes an emotion engine that recognizes the user's emotions. Specifically, the emotion engine recognizes the user's emotions and selects knowledge to provide in accordance with those emotions. For example, if the emotion engine senses that the user is happy, it sends instructions to the knowledge generation platform to provide knowledge that matches the user's interests and preferences.

[0462] "Example of form 3"

[0463] As a further embodiment of the present invention, a system is provided in which an emotion engine adjusts the operation of a knowledge generation platform in accordance with the user's emotions. This system includes means for storing high-precision results generated by the user in a knowledge database via the knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, and means for improving convenience and operational efficiency. Furthermore, this system includes an emotion engine that recognizes the user's emotions. Specifically, the emotion engine recognizes the user's emotions and adjusts the operation of the knowledge generation platform in accordance with those emotions. For example, if the user feels confused, the emotion engine sends instructions to the knowledge generation platform to quickly provide the information the user needs.

[0464] The following describes the processing flow for each example of the form.

[0465] "Example of form 1"

[0466] Step 1: The user uses the system to search for or inquire about information.

[0467] Step 2: The emotion engine recognizes the user's emotions from their tone of voice, facial expressions, text input, etc.

[0468] Step 3: Adjust the operation of the knowledge generation platform based on the emotions recognized by the emotion engine.

[0469] Step 4: The knowledge generation platform prioritizes providing knowledge to quickly resolve user problems.

[0470] "Example of form 2"

[0471] Step 1: The user uses the system to search for or inquire about information.

[0472] Step 2: The emotion engine recognizes the user's emotions from their tone of voice, facial expressions, text input, etc.

[0473] Step 3: Based on the emotions recognized by the emotion engine, select the knowledge to provide.

[0474] Step 4: The knowledge generation platform provides knowledge that matches the user's interests and preferences.

[0475] "Example of form 3"

[0476] Step 1: The user uses the system to search for or inquire about information.

[0477] Step 2: The emotion engine recognizes the user's emotions from their tone of voice, facial expressions, text input, etc.

[0478] Step 3: Adjust the operation of the knowledge generation platform based on the emotions recognized by the emotion engine.

[0479] Step 4: The knowledge generation platform quickly provides the information the user needs.

[0480] (Example 1)

[0481] Next, we will describe Example 1 of Form 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."

[0482] Information obtained through conventional search engines and chatbots is only used temporarily for individual users and is rarely accumulated as useful knowledge for other users or future users. Furthermore, because information is provided without considering the user's emotions, user satisfaction and work efficiency may decrease. To solve these problems, a system is needed that efficiently stores highly accurate information obtained by users and provides appropriate information tailored to their emotions.

[0483] 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.

[0484] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means including an emotion engine that recognizes the user's emotions, and means for adjusting the operation of the knowledge generation platform according to the emotions recognized by the emotion engine. This enables efficient storage of high-precision information obtained by users and the provision of appropriate information according to their emotions.

[0485] A "user" is an individual or organization that uses the system to search for information or obtains information using a chatbot.

[0486] "High-precision results" refer to accurate and reliable information obtained by users through search engines or chatbots.

[0487] A "knowledge generation platform" is a system that receives information obtained by users, analyzes it, and stores it in a knowledge database.

[0488] A "knowledge database" is a database that stores knowledge from various fields and provides it as needed.

[0489] An "ecosystem" is the overall structure of a system that provides accumulated knowledge to users and enables users to utilize that knowledge.

[0490] "Improving convenience" refers to increasing the ease of use and efficiency when using the system.

[0491] "Improving work efficiency" refers to increasing the efficiency of carrying out work tasks.

[0492] An "emotion engine" is an engine that recognizes emotions from the user's tone of voice, facial expressions, text input, etc., and adjusts the system's operation according to those emotions.

[0493] "Adjusting behavior" refers to changing the behavior of the knowledge generation platform based on the emotions recognized by the emotion engine.

[0494] This invention is a system that stores highly accurate results obtained by users using conventional search engines and chatbots in a knowledge database via a knowledge generation platform, and provides the accumulated knowledge to users in the form of an ecosystem. Furthermore, by combining it with an emotion engine, it provides knowledge that is tailored to the user's emotions.

[0495] System Configuration

[0496] 1. User actions

[0497] Users use their devices to input information into search engines and chatbots.

[0498] Example: The user types "Tell me about the latest AI technology."

[0499] 2. Device operation

[0500] The terminal sends the information entered by the user to the knowledge generation platform.

[0501] Software to use: A library for sending HTTP requests (e.g., Axios)

[0502] 3. Server operation

[0503] The server analyzes the received information and stores it in a knowledge database.

[0504] Hardware used: Server (e.g., cloud service)

[0505] Software to use: Database management system (e.g., MySQL)

[0506] 4. How the Emotion Engine Works

[0507] The emotion engine recognizes emotions from the user's voice tone, facial expressions, and text input.

[0508] Software to be used: Emotion recognition library (e.g., OpenCV, NLP library)

[0509] For example, if a user types "This problem isn't getting resolved!", the emotion engine will recognize that the user is angry.

[0510] 5. Coordination of knowledge sharing

[0511] The server receives instructions from the emotion engine and adjusts the knowledge delivery based on the user's emotions.

[0512] Example: If a user is angry, the server quickly provides knowledge to help resolve the problem.

[0513] 6. Providing Knowledge

[0514] The server provides users with accumulated knowledge in the form of an ecosystem.

[0515] Software to use: Web application framework (e.g., Django)

[0516] Specific example

[0517] The user searches for information or enters it into the chatbot.

[0518] The user types, "Tell me about the latest AI technology."

[0519] The user types, "This problem is not resolved!"

[0520] The device sends information to the knowledge generation platform.

[0521] The device sends an HTTP request containing the information, "Tell me about the latest AI technology."

[0522] The device sends an HTTP request containing the information, "This problem cannot be resolved!"

[0523] The server analyzes the information and stores it in the knowledge database.

[0524] The server analyzes the information, such as "Tell me about the latest AI technology," and stores it in a knowledge database.

[0525] The server analyzes information indicating "This problem cannot be resolved!" and saves it to the knowledge database.

[0526] The emotion engine recognizes the user's emotions.

[0527] The emotion engine recognizes that the user is angry from the text, "This problem isn't getting solved!"

[0528] The emotion engine recognizes that the user is sad based on their facial expression.

[0529] The server adjusts knowledge delivery based on emotions.

[0530] The server receives information that "the user is angry" and provides high-priority knowledge.

[0531] The server receives information that "the user is sad" and provides comforting knowledge.

[0532] The server provides knowledge to the user.

[0533] The server displays a knowledge base page with the question, "Tell me about the latest AI technologies."

[0534] The server displays a knowledge base article on its webpage stating, "This problem cannot be resolved!"

[0535] This system allows users to efficiently obtain highly accurate information and receive appropriate support tailored to their emotions.

[0536] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0537] Step 1:

[0538] The user searches for information or enters it into the chatbot.

[0539] Input: The user enters information into a search engine or chatbot using their device.

[0540] Specific action: The user opens a browser and types "Tell me about the latest AI technology" into the search bar.

[0541] Output: The information entered by the user is sent to the terminal.

[0542] Step 2:

[0543] The device sends information to the knowledge generation platform.

[0544] Input: Information entered by the user.

[0545] Specific operation: The terminal generates an HTTP request and sends data containing the entered information to the server. The library used is Axios.

[0546] Output: The information entered by the user is sent to the knowledge generation platform.

[0547] Step 3:

[0548] The server analyzes the information and stores it in the knowledge database.

[0549] Input: Information sent from the device.

[0550] Specific operation: The server executes a Python script and parses the received data. The analysis results are saved to a MySQL database.

[0551] Output: The analyzed information is stored in the knowledge database.

[0552] Step 4:

[0553] The emotion engine recognizes the user's emotions.

[0554] Input: User's voice tone, facial expression, and text input.

[0555] Specific operation: The emotion engine uses OpenCV to analyze the user's facial expressions and an NLP library to extract emotions from text input.

[0556] Output: User's emotions are recognized.

[0557] Step 5:

[0558] The server adjusts knowledge delivery based on emotions.

[0559] Input: Emotion recognition result from the emotion engine.

[0560] Specific operation: The server receives information from the emotion engine that "the user is angry," searches for high-priority knowledge, and provides it.

[0561] Output: Instructions for providing knowledge, tailored to the user's emotions, are generated.

[0562] Step 6:

[0563] The server provides knowledge to the user.

[0564] Input: Information stored in the knowledge database and instructions from the emotion engine.

[0565] Specific operation: The server uses the Django framework to generate a web page and display knowledge to the user.

[0566] Output: The knowledge provided to the user is displayed on the web page.

[0567] (Application Example 1)

[0568] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0569] Traditional knowledge management systems struggled to efficiently store and appropriately provide user-generated information. Furthermore, they lacked the ability to consider user emotions, hindering customer satisfaction. In addition, physical stores lacked the means to provide staff with relevant knowledge in real time when interacting with customers.

[0570] 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. In this invention, the server includes means for storing high-precision results generated by the user in a knowledge DB via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, means for improving convenience and operational efficiency, means for recognizing the user's emotions using an emotion engine and adjusting the operation of the knowledge generation platform according to those emotions, and means for providing knowledge in real time through a smart device. This makes it possible to provide appropriate knowledge according to the user's emotions and improve the quality of customer service in physical stores.

[0571] A "user" is an individual or organization that uses the system to generate information and acquire knowledge.

[0572] "High-precision results" refer to accurate and reliable information obtained by users through searches or chatbots.

[0573] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[0574] A "knowledge database" is a database that stores knowledge from various fields.

[0575] An "ecosystem" is an integrated system environment for providing users with accumulated knowledge.

[0576] "Improving convenience" refers to making the system easier and more efficient for users to use.

[0577] "Improving business efficiency" refers to increasing the productivity and efficiency of business operations by using systems.

[0578] An "emotion engine" is a system that recognizes emotions from the user's voice tone, facial expressions, text input, and other factors.

[0579] A "smart device" is a device with internet connectivity, such as a smartphone, smart glasses, or a head-mounted display.

[0580] "Real-time" refers to processing or responding immediately without delay.

[0581] As an example of how to implement this invention, a customer service system using smart devices in a physical store will be described. This system stores high-precision results generated by users in a knowledge database via a knowledge generation platform, and provides the stored knowledge to users in the form of an ecosystem. Furthermore, it recognizes the user's emotions using an emotion engine and adjusts the operation of the knowledge generation platform according to those emotions.

[0582] Hardware and software to use

[0583] Hardware: Smart glasses (including camera, microphone, and display)

[0584] software:

[0585] EmotionRecognizer: A library for recognizing emotions from facial expressions.

[0586] KnowledgeDB: A library for accessing a knowledge database and retrieving answers to questions.

[0587] SmartGlassesInterface: An interface for controlling the camera, microphone, and display of smart glasses.

[0588] System operation

[0589] The server captures the customer's face through the smart glasses' camera and uses an EmotionRecognizer to recognize emotions from facial expressions. Next, it obtains the customer's question as voice input through the smart glasses' microphone and sends the question to the KnowledgeDB to obtain an appropriate answer. At this time, the knowledge generation platform adjusts its operation according to the recognized emotion and prioritizes providing the appropriate knowledge. Finally, the answer is displayed on the smart glasses' display.

[0590] Specific example

[0591] For example, if a customer asks a question about a product in a store and looks a little unsure, the emotion engine recognizes this. The server then prioritizes retrieving reassuring answers from the knowledge database and displays them on the smart glasses' screen. This allows the customer to choose products with confidence.

[0592] Example of a prompt

[0593] "If a customer looks anxious, provide a reassuring response."

[0594] In this way, the quality of customer service in physical stores can be improved.

[0595] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0596] Step 1:

[0597] The server captures the customer's face through the smart glasses' camera. The input is the camera feed, and the output is the captured image data. This image data is sent to the EmotionRecognizer.

[0598] Step 2:

[0599] The server recognizes customer emotions from captured image data using EmotionRecognizer. The input is image data, and the output is recognized emotion data. EmotionRecognizer analyzes facial expressions to identify emotions.

[0600] Step 3:

[0601] The server receives customer questions via voice input through the microphone of smart glasses. The input is voice data, and the output is text data. Speech recognition software is used to convert the voice data into text.

[0602] Step 4:

[0603] The server sends the acquired text data to KnowledgeDB to retrieve the appropriate answer. The input is text data and sentiment data, and the output is the answer text. KnowledgeDB searches for answers to the question and prioritizes providing the appropriate answer based on the sentiment data.

[0604] Step 5:

[0605] The server displays the retrieved response text on the smart glasses' display. The input is the response text, and the output is the text displayed on the display. The response is displayed using the smart glasses' display interface.

[0606] Step 6:

[0607] The user checks the answers displayed on the smart glasses' screen and responds appropriately to the customer. The input is the text displayed on the screen, and the output is the response to the customer. The user provides explanations and guidance to the customer based on the displayed information.

[0608] (Example 2)

[0609] Next, we will describe Example 2 of Form 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".

[0610] Conventional information retrieval systems have problems such as difficulty in efficiently obtaining the information users need, and a lack of information provision that responds to users' emotions, leading to decreased user satisfaction. Furthermore, there is a lack of means to effectively utilize accumulated knowledge, resulting in a failure to improve operational efficiency.

[0611] 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.

[0612] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for receiving user search queries and acquiring relevant information, means for transmitting the acquired information to the knowledge generation platform, and means for recognizing the user's emotions using an emotion engine and selecting knowledge to provide according to those emotions. As a result, users can efficiently acquire the information they need, information can be provided according to their emotions, and user satisfaction can be improved. Furthermore, operational efficiency can be improved by effectively utilizing the stored knowledge.

[0613] A "user" is an individual or organization that uses the system to search for information and receive the results.

[0614] "High-precision results" refer to search results that are highly relevant to the user's search query and contain accurate information.

[0615] A "knowledge generation platform" is a system for collecting and analyzing search results and other information, and storing it in a knowledge database.

[0616] A "knowledge database" is a database that stores accumulated knowledge and information, and allows it to be searched and retrieved as needed.

[0617] An "ecosystem" is an integrated system or environment designed to provide users with accumulated knowledge.

[0618] "Improving convenience" refers to increasing the ease of use and efficiency for users when using the system.

[0619] "Improving business efficiency" refers to increasing the speed and effectiveness of business processes by using systems.

[0620] A "search query" is a keyword or phrase that a user enters when searching for information.

[0621] An "emotion engine" is a system that recognizes the user's emotions and provides appropriate information in response to those emotions.

[0622] "Relevant information" refers to information that is appropriate and useful to the user's search query.

[0623] "Information provision" refers to the system presenting search results and other knowledge to the user.

[0624] This invention is a system that, when a user performs a search for medical information, transmits the search results to a knowledge generation platform and stores them in a knowledge database. Furthermore, it improves user satisfaction by providing information tailored to the user's emotions using an emotion engine.

[0625] Hardware and software to use

[0626] hardware

[0627] Devices (PC, smartphone, etc.)

[0628] Server (data processing and knowledge database management)

[0629] software

[0630] Knowledge generation platform (data storage and provision)

[0631] Emotion engine (recognition of user emotions)

[0632] Search engine (for searching medical information)

[0633] Program processing

[0634] 1. User search behavior

[0635] The user searches for medical information using their device. For example, the user opens a browser, enters "diabetes treatments" into the search bar, and clicks the search button.

[0636] 2. Retrieving and submitting search results

[0637] The device sends the search query to the server. Specifically, the device sends the search query "treatments for diabetes" to the server as an HTTP request.

[0638] The server processes the search query and retrieves relevant medical information. The server uses databases and external APIs to collect information about "diabetes treatments."

[0639] The server sends the retrieved search results to the knowledge generation platform. The server sends the search results to the knowledge generation platform in JSON format.

[0640] 3. Accumulation into a knowledge database

[0641] The knowledge generation platform stores the received search results in a knowledge database. The knowledge generation platform analyzes the search results and saves them to the knowledge database in an appropriate format.

[0642] 4. Providing information to other users

[0643] Another user searches for similar information. Another user uses their device to search for "diabetes treatments" again.

[0644] The server retrieves the relevant information from the knowledge database. The server sends a query to the knowledge database to retrieve information about "treatments for diabetes."

[0645] The server provides the acquired information to the user. The server sends the acquired information to the terminal, and the terminal displays that information to the user.

[0646] 5. How the Emotion Engine Works

[0647] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and input content to determine their emotions.

[0648] The emotion engine, when it senses that the user is happy, sends instructions to the knowledge generation platform to provide knowledge that matches the user's interests and preferences. When the emotion engine determines that the user is happy, it sends instructions to the knowledge generation platform to "provide information that matches the user's interests."

[0649] Specific examples and prompt statements

[0650] Specific example

[0651] User A searches for "diabetes treatments".

[0652] The server retrieves relevant medical information and sends it to the knowledge generation platform.

[0653] A knowledge generation platform stores information in a knowledge database.

[0654] When user B searches for "diabetes treatments," the server retrieves information from its knowledge database and provides it to user B.

[0655] If the emotion engine recognizes that user B is "happy," it will provide additional information tailored to user B's interests.

[0656] Example of a prompt

[0657] When a user searches for "diabetes treatments," send the search results to the knowledge generation platform and store them in the knowledge database. Then, when another user searches for similar information, retrieve the relevant information from the knowledge database and provide it to the user. Also, recognize the user's emotions and select the knowledge to provide accordingly.

[0658] This invention allows users to efficiently obtain necessary medical information and provides information tailored to their emotions. This improves user satisfaction and enhances operational efficiency.

[0659] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0660] Step 1:

[0661] User search behavior

[0662] Input: The user enters the search query using the terminal.

[0663] Specific action: The user opens a browser, enters "diabetes treatments" into the search bar, and clicks the search button.

[0664] Output: The terminal sends the search query to the server.

[0665] Step 2:

[0666] Retrieving search results

[0667] Input: Search query sent from the terminal.

[0668] Specific action: The device sends the search query "treatments for diabetes" to the server as an HTTP request.

[0669] Data processing: The server analyzes the search query and collects relevant medical information from databases and external APIs.

[0670] Output: The server generates search results based on the medical information it has acquired.

[0671] Step 3:

[0672] Submit search results

[0673] Input: Search results generated by the server.

[0674] Specific operation: The server sends the search results to the knowledge generation platform in JSON format.

[0675] Output: The knowledge generation platform receives the search results.

[0676] Step 4:

[0677] Storage in a knowledge database

[0678] Input: Search results received by the knowledge generation platform.

[0679] Specific operation: The knowledge generation platform analyzes the search results and stores them in the knowledge database in an appropriate format.

[0680] Data processing: Organize search results as structured data and store it in a knowledge database.

[0681] Output: Search results stored in the knowledge database.

[0682] Step 5:

[0683] Providing information to other users

[0684] Input: A query used by another user to search for similar information.

[0685] Specific action: Another user uses the device to search for "diabetes treatments" again.

[0686] Data processing: The server sends a query to the knowledge database to retrieve information about "diabetes treatments".

[0687] Output: The server sends the acquired information to the terminal, and the terminal displays that information to the user.

[0688] Step 6:

[0689] How the emotion engine works

[0690] Input: User's emotional data (facial expressions and input content).

[0691] Specific operation: The emotion engine analyzes the user's facial expressions and input content to determine their emotions.

[0692] Data processing: If the emotion engine determines that the user is "happy," it sends an instruction to the knowledge generation platform to "provide information that matches the user's interests."

[0693] Output: The knowledge generation platform provides additional information tailored to the user's interests.

[0694] Thus, the system processes the entire process as a series of steps, starting with the user's search behavior, retrieving search results, storing them in a knowledge database, providing information to other users, and finally, using an emotion engine to recognize emotions and optimize information delivery.

[0695] (Application Example 2)

[0696] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0697] Conventional knowledge delivery systems make it difficult for users to efficiently obtain the information they need, and in particular, they fail to provide appropriate information tailored to their emotions. Furthermore, there is a lack of effective means to utilize search results related to electronic payments, thus creating a need for improved user convenience and operational efficiency.

[0698] 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.

[0699] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for selecting knowledge according to the user's emotions using an emotion recognition engine, means for searching for information related to electronic payments and storing the results in the knowledge database, and means for filtering knowledge based on the user's emotions and providing appropriate information. As a result, users can efficiently acquire the information they need and receive appropriate information according to their emotions.

[0700] "High-precision results" refer to accurate and reliable information obtained by users through searches and operations.

[0701] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[0702] A "knowledge database" is a database that stores collected information and provides it as needed.

[0703] An "ecosystem" is an integrated system environment for providing users with accumulated knowledge.

[0704] "Improving convenience" refers to increasing the ease of use and efficiency for users when using the system.

[0705] "Improving work efficiency" refers to increasing the efficiency of performing work tasks.

[0706] An "emotion recognition engine" is an engine that recognizes the user's emotions and provides appropriate information based on those emotions.

[0707] "Electronic payment" refers to payment methods that utilize the internet and electronic devices.

[0708] "Filtering" refers to selecting information based on specific criteria.

[0709] The following system configuration will be described as an embodiment for carrying out this invention.

[0710] System Configuration

[0711] hardware

[0712] server

[0713] smartphone

[0714] Emotion recognition engine (EmotionEngine)

[0715] software

[0716] Knowledge generation platform

[0717] Knowledge Database (KnowledgeDB)

[0718] Search engine API (using the requests library)

[0719] Emotion recognition software (EmotionEngine)

[0720] Program processing

[0721] server

[0722] The server stores high-precision results generated by users in a knowledge database via a knowledge generation platform. Specifically, when a user searches for information related to electronic payments, the search results are sent to the knowledge generation platform and stored in the knowledge database. In addition, an emotion recognition engine is used to recognize the user's emotions, and knowledge is filtered based on those emotions to provide appropriate information.

[0723] smartphone

[0724] The smartphone provides an interface for users to search for information related to electronic payments. Search results are sent to a knowledge generation platform and stored in a knowledge database. If the user needs the same information again, an emotion recognition engine recognizes the user's emotions and provides appropriate knowledge.

[0725] Emotion recognition engine

[0726] The emotion recognition engine analyzes the user's voice and facial expression data to recognize emotions. Based on the recognized emotions, it filters and provides appropriate information from the knowledge database.

[0727] Specific example

[0728] For example, if a user searches for information on "electronic payment security," the search results are stored in the knowledge database. When another user needs the same information, if the emotion recognition engine recognizes that the user is "happy," it will prioritize providing positive information.

[0729] Example of a prompt

[0730] Create a Python program that, when a user searches for information on "electronic payment security," saves the search results to a knowledge database and uses an emotion recognition engine to provide appropriate information when another user needs the same information.

[0731] In this way, users can efficiently acquire the information they need, and appropriate information tailored to their emotions can be provided.

[0732] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0733] Step 1:

[0734] Users search for information about electronic payments using their smartphones.

[0735] Input: User's search query (e.g., "security for electronic payments")

[0736] Output: The search query is sent to the server.

[0737] Specific action: The user enters "electronic payment security" into the search bar on their smartphone and presses the search button.

[0738] Step 2:

[0739] The server receives the search query and sends a request to an external search engine API.

[0740] Input: User's search query

[0741] Output: Search results from the search engine API

[0742] Specific operation: The server sends a search query to the search engine API and receives the search results.

[0743] Step 3:

[0744] The server sends the received search results to the knowledge generation platform and stores them in the knowledge database.

[0745] Input: Search results from search engine API

[0746] Output: Search results stored in the knowledge database

[0747] Specific operation: The server sends the search results to the knowledge generation platform and stores them in the knowledge database.

[0748] Step 4:

[0749] Another user searches for the same information using their smartphone.

[0750] Input: Another user's search query (e.g., "security for electronic payments")

[0751] Output: The search query is sent to the server.

[0752] Specific action: Another user types "electronic payment security" into the search bar on their smartphone and presses the search button.

[0753] Step 5:

[0754] The server receives the search query and retrieves relevant information from the knowledge database.

[0755] Input: Search query from another user

[0756] Output: Related information retrieved from the knowledge database

[0757] Specific operation: The server sends a query to the knowledge database and retrieves relevant information.

[0758] Step 6:

[0759] The server uses an emotion recognition engine to recognize the emotions of another user.

[0760] Input: Voice and facial expression data from another user

[0761] Output: Recognized emotion (e.g., "happy")

[0762] Specific operation: The server sends voice and facial expression data from another user to the emotion recognition engine and recognizes their emotions.

[0763] Step 7:

[0764] The server filters information retrieved from the knowledge database based on the emotions it recognizes.

[0765] Input: Relevant information retrieved from the knowledge database, perceived emotions

[0766] Output: Filtered information

[0767] Specific operation: The server filters information retrieved from the knowledge database based on the recognized emotions.

[0768] Step 8:

[0769] The server provides filtered information to another user.

[0770] Input: Filtered information

[0771] Output: Information provided to another user

[0772] Specific operation: The server sends filtered information to another user's smartphone and displays it.

[0773] (Example 3)

[0774] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0775] Conventional information retrieval systems struggled to quickly provide users with the information they needed, and especially when users were confused, it took a long time for them to find the right information. Furthermore, because information was not provided in a way that reflected the user's emotions, improvements in convenience and operational efficiency were not sufficiently achieved.

[0776] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0777] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for adjusting the operation of the knowledge generation platform using an emotion engine that recognizes the user's emotions, means for generating appropriate information based on the analysis results of the emotion engine, means for providing the generated information to users, and means for storing the generated information in a knowledge database. This makes it possible to quickly provide appropriate information according to the user's emotions, thereby shortening information retrieval time and improving operational efficiency.

[0778] A "user" is an individual or organization that uses the system to search for information and improve the efficiency of their work.

[0779] "High-precision results" refer to accurate and reliable information and data generated by users.

[0780] A "knowledge generation platform" is a system that processes information generated by users and stores it in a knowledge database.

[0781] A "knowledge database" is a database used to store accumulated information and data and to provide it as needed.

[0782] An "ecosystem" is an integrated system environment designed to provide users with accumulated knowledge.

[0783] "Improving convenience" means enhancing the ease of use and comfort for users when using the system.

[0784] "Improving operational efficiency" means enabling users to perform their tasks more quickly and effectively.

[0785] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's operation accordingly.

[0786] "Analysis results" refer to the results of the emotion engine's analysis of the user's emotions.

[0787] "Appropriate information" refers to the most useful and relevant information provided in accordance with the user's emotions and circumstances.

[0788] Modes for carrying out the invention

[0789] This invention is a system that stores high-precision results generated by users in a knowledge database via a knowledge generation platform, and provides the stored knowledge to users in the form of an ecosystem. Furthermore, it aims to improve convenience and operational efficiency by recognizing the user's emotions using an emotion engine and adjusting the operation of the knowledge generation platform according to those emotions.

[0790] Hardware and software to be used

[0791] The server uses a common cloud service as its knowledge generation platform. Specifically, it uses a cloud service that provides an "emotion recognition API" as its emotion engine and a cloud service that provides a "natural language processing API" as its knowledge generation platform. This makes it possible to analyze the user's emotions and generate appropriate information.

[0792] A terminal is a device that users use to access the system, and includes PCs, smartphones, and tablets. Terminals are equipped with cameras and microphones, which are used to capture the user's facial expressions and voice.

[0793] Program processing

[0794] The server receives facial and voice data from the user transmitted from the terminal and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotions. For example, if it determines that the user is confused, the server sends instructions to the knowledge generation platform to generate the information the user needs.

[0795] The generated information is provided to the user's terminal via the server. Users can then review the information provided on their terminal and proceed with their work efficiently. Furthermore, the generated information is stored in a knowledge database, allowing other users to quickly obtain similar information in the future.

[0796] Specific example

[0797] For example, if a user is confused about how to use new software, the following actions will occur:

[0798] 1. The user accesses the system through a terminal and enters "I don't know how to use the new software."

[0799] 2. The device's camera captures the user's confused facial expression and sends that data to the emotion engine.

[0800] 3. The emotion engine analyzes the user's facial expressions and determines that they are "confused."

[0801] 4. The server receives the analysis results from the emotion engine and instructs the knowledge generation platform to "generate a detailed guide on how to use the software."

[0802] 5. The knowledge generation platform generates a detailed guide and sends it to the server.

[0803] 6. The server displays the generated guide on the user's terminal.

[0804] 7. Users understand how to use the software by looking at the guide.

[0805] 8. The server stores the generated guides in a knowledge database so that other users can quickly retrieve the same information in the future.

[0806] Example of a prompt

[0807] "I'm having trouble figuring out how to use the new software. Could you please explain the specific steps?"

[0808] In this way, the system improves operational efficiency by quickly providing appropriate information that responds to the user's emotions, thereby reducing information retrieval time. The flow of specific processing in Example 3 will be explained using Figure 21.

[0809] Step 1:

[0810] The user accesses the system through their device.

[0811] Input: The user accesses the system's URL using a terminal.

[0812] Output: The system's homepage is displayed on the terminal.

[0813] Specific operation: The user opens a web browser and enters the system's URL to access it. The system's homepage is displayed, and the user is ready to begin searching for information.

[0814] Step 2:

[0815] The device sends the user's emotions to the emotion engine.

[0816] Input: The device's camera and microphone capture the user's facial expressions and voice.

[0817] Output: The captured data is sent to the emotion engine.

[0818] Specific operation: The device's camera captures the user's face, and the microphone records the user's voice. This data is sent to the emotion engine in real time.

[0819] Step 3:

[0820] The emotion engine analyzes the user's emotions.

[0821] Input: Facial expression and audio data sent from the device.

[0822] Output: Analysis results showing the user's emotions.

[0823] Specific operation: The emotion engine analyzes the received data and identifies emotions such as whether the user is confused, happy, or angry. For example, if it determines that the user is confused, the result is sent to the server.

[0824] Step 4:

[0825] The server receives the results of the emotion engine's analysis.

[0826] Input: Analysis results sent from the emotion engine.

[0827] Output: Instructions are generated based on the analysis results.

[0828] Specific operation: The server receives the analysis results sent from the emotion engine and generates instructions to provide appropriate information according to the user's emotions.

[0829] Step 5:

[0830] The server sends instructions to the knowledge generation platform.

[0831] Input: Instructions based on the analysis results of the emotion engine.

[0832] Output: Instructions to send to the knowledge generation platform.

[0833] Specific operation: If the server determines that the user is confused, it instructs the knowledge generation platform to "generate a detailed guide on how to use the software."

[0834] Step 6:

[0835] The knowledge generation platform generates the appropriate information.

[0836] Input: Instructions sent from the server.

[0837] Output: Generated information.

[0838] Specific operation: Based on the instructions, the knowledge generation platform generates detailed guides on how to use software that the user is having trouble with. For example, guides containing specific operating procedures and troubleshooting information are generated.

[0839] Step 7:

[0840] The server provides the user with the generated information.

[0841] Input: Information submitted from the knowledge generation platform.

[0842] Output: Information displayed on the user's device.

[0843] Specific operation: The server receives the generated guide and sends it to the user's terminal. The user then reviews the detailed guide on their terminal and understands how to use the software.

[0844] Step 8:

[0845] The server stores the generated information in the knowledge database.

[0846] Input: Information submitted from the knowledge generation platform.

[0847] Output: Information stored in the knowledge database.

[0848] Specific operation: The server stores the generated guides in a knowledge database so that other users can quickly retrieve the same information in the future. For example, it can be accessed by other users who are having trouble using the same software.

[0849] (Application Example 3)

[0850] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0851] A challenge exists in providing timely and appropriate knowledge to robots operating within factories when they encounter confusion or errors during their work. Furthermore, there is a need to efficiently store new knowledge gained during work in a knowledge database and utilize it in real time. Additionally, it is necessary to improve convenience and operational efficiency by adjusting the operation of the knowledge generation platform according to the user's emotions.

[0852] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0853] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform; means for providing the stored knowledge to users in the form of an ecosystem; means for improving convenience and operational efficiency; means for recognizing the user's emotions using an emotion engine and adjusting the operation of the knowledge generation platform according to those emotions; means for being installed on robots working in a factory and providing knowledge in real time; means for quickly providing appropriate knowledge when the robot senses confusion or an error; and means for automatically storing new knowledge acquired during work in a knowledge database. This makes it possible to significantly improve the operational efficiency within the factory.

[0854] A "user" is a person or machine that uses the system to obtain information or perform tasks.

[0855] "High-precision results" refer to accurate and reliable information and data generated by users.

[0856] A "knowledge generation platform" is a system that collects, organizes, and stores information generated by users, and provides it as needed.

[0857] A "knowledge database" is a database where information accumulated by a knowledge generation platform is stored.

[0858] An "ecosystem" is a mechanism that provides users with information accumulated in a knowledge database and facilitates the sharing of information among them.

[0859] "Improving convenience" means increasing the ease of use and efficiency for users when using the system.

[0860] "Improving operational efficiency" means enabling tasks and operations to be performed more quickly and effectively.

[0861] An "emotion engine" is an engine that recognizes the user's emotions and adjusts the system's operation accordingly.

[0862] A "robot that performs work in a factory" is a machine that automatically performs specific tasks within a factory.

[0863] "A means of providing knowledge in real time" refers to a function that provides necessary information immediately.

[0864] "A means of quickly providing appropriate knowledge when confusion or errors are detected" refers to a function that immediately provides solutions and relevant information when a robot detects a problem.

[0865] "A means of automatically accumulating new knowledge gained during work in a knowledge database" refers to a function that automatically saves new information and knowledge discovered during work to a database.

[0866] As an embodiment of this invention, a system installed in a robot performing work in a factory is described. This system stores high-precision results generated by the user in a knowledge database via a knowledge generation platform, and provides the stored knowledge to the user in the form of an ecosystem. It also recognizes the user's emotions using an emotion engine and adjusts the operation of the knowledge generation platform according to those emotions.

[0867] Hardware and software to use

[0868] Hardware: Factory robots, cameras (for emotion recognition)

[0869] Software: Python, emotion_recognition library, knowledge_db library

[0870] Data processing and data calculation

[0871] emotion recognition

[0872] The system uses a camera to capture the robot's movements and errors, and the emotion_recognition library to recognize emotions. The emotion engine detects when the robot feels confused or makes an error and sends instructions to the knowledge generation platform to provide appropriate knowledge.

[0873] Knowledge provision

[0874] Based on the emotions recognized by the emotion engine, the knowledge generation platform uses the knowledge_db library to retrieve appropriate information from the knowledge database and provide it to the robot. This allows the robot to quickly resolve confusion and errors.

[0875] Knowledge database update

[0876] New knowledge and information gained during the work process are automatically stored in the knowledge database through the knowledge generation platform. This allows for quick responses if similar problems occur in subsequent tasks.

[0877] Specific example

[0878] For example, if an error occurs while a robot is assembling part A, the emotion engine recognizes the robot's confusion and retrieves and provides information about how to assemble part A from the knowledge database. Based on this information, the robot can resolve the error and continue working.

[0879] Example of a prompt

[0880] If an error occurs while the robot is assembling part A, the emotion engine should recognize the robot's confusion and retrieve and provide information from the knowledge database regarding how to assemble part A.

[0881] In this way, it is possible to significantly improve work efficiency within the factory.

[0882] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0883] Step 1:

[0884] The server acquires video data in real time from the factory robot's camera.

[0885] Input: Camera footage from a factory robot

[0886] Output: Video data

[0887] Specific operation: The server receives video data in streaming format from a camera mounted on a factory robot.

[0888] Step 2:

[0889] The server uses the emotion_recognition library to recognize the robot's emotions from the video data.

[0890] Input: Video data

[0891] Output: Sentiment data (e.g., confusion, error)

[0892] Specific operation: The server inputs the received video data into the emotion_recognition library and analyzes the robot's emotions from its facial expressions and movements.

[0893] Step 3:

[0894] The server sends instructions to the knowledge generation platform based on the recognized sentiment data.

[0895] Input: Sentiment data

[0896] Output: Instructions for the knowledge generation platform

[0897] Specific operation: If the sentiment data is "confused" or "error," the server sends an instruction to the knowledge generation platform to provide appropriate knowledge.

[0898] Step 4:

[0899] The knowledge generation platform uses the knowledge_db library to retrieve the appropriate information from the knowledge database.

[0900] Input: Instructions for the knowledge generation platform

[0901] Output: Appropriate knowledge information

[0902] Specific operation: The knowledge generation platform queries the knowledge database based on the instructions and retrieves relevant information.

[0903] Step 5:

[0904] The server provides the acquired knowledge information to the factory robots.

[0905] Input: Appropriate knowledge information

[0906] Output: Providing knowledge information to factory robots

[0907] Specific operation: The server sends the acquired knowledge information to the factory robot, allowing the robot to continue its work based on that information.

[0908] Step 6:

[0909] The server automatically stores new knowledge gained during the process in the knowledge database through the knowledge generation platform.

[0910] Input: New knowledge or information

[0911] Output: Storage in the Knowledge Database

[0912] Specific operation: The server sends new knowledge and information acquired by the robot during its work to the knowledge generation platform and automatically saves it to the knowledge database.

[0913] In this way, it is possible to significantly improve work efficiency within the factory.

[0914] 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.

[0915] Data generation model 58 is a form of 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> 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.

[0916] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are some examples.

[0917] 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.

[0918] [Second Embodiment]

[0919] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0920] 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.

[0921] 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).

[0922] 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.

[0923] 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.

[0924] 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).

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0931] "Example of form 1"

[0932] One embodiment of the present invention is a system that stores high-precision results generated by users through conventional search and chatbot usage in a knowledge database via a knowledge generation platform. Specifically, users transmit information obtained through search or chatbot usage to the knowledge generation platform, where that information is stored in the knowledge database. This knowledge database stores knowledge in various fields and provides that knowledge to users in the form of an ecosystem.

[0933] "Example of form 2"

[0934] As a concrete example, when a user searches for medical information, the search results are sent to a knowledge generation platform, where the information is stored in a knowledge database. Subsequently, when another user needs similar information, the relevant information is retrieved from the knowledge database and provided to the user. This allows users to efficiently obtain the information they need.

[0935] "Example of form 3"

[0936] Furthermore, the embodiment of the present invention is a system aimed at improving convenience and operational efficiency. Specifically, by providing information stored in a knowledge database to users at the time they need it, it shortens the time users spend searching for information and improves operational efficiency.

[0937] The following describes the processing flow for each example of the form.

[0938] "Example of form 1"

[0939] Step 1: Users generate information using traditional search and chatbot functions.

[0940] Step 2: Send the generated information to the knowledge generation platform.

[0941] Step 3: The knowledge generation platform stores the information in the knowledge database.

[0942] "Example of form 2"

[0943] Step 1: The user performs a search for medical information.

[0944] Step 2: Submit the search results to the knowledge generation platform.

[0945] Step 3: The knowledge generation platform stores the information in the knowledge database.

[0946] Step 4: If another user requires similar information, retrieve the relevant information from the knowledge database and provide it to the user.

[0947] "Example of form 3"

[0948] Step 1: The user searches for the information they need.

[0949] Step 2: Retrieve the relevant information from the knowledge database.

[0950] Step 3: Provide the acquired information to the user.

[0951] (Example 1)

[0952] Next, we will describe Embodiment 1 of Embodiment 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".

[0953] Information obtained through conventional search engines and conversational agents is temporary and difficult to reuse. Furthermore, there is a lack of means to guarantee the accuracy and reliability of the information obtained, making it difficult for users to efficiently obtain highly accurate information. Moreover, there is a need for methods to improve user convenience and enhance operational efficiency by providing accumulated knowledge as an ecosystem.

[0954] 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.

[0955] In this invention, the server includes means for accumulating high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the accumulated knowledge to users in the form of an ecosystem, and means for improving convenience and operational efficiency. This makes it possible for users to efficiently accumulate and reuse high-precision information obtained using search engines and conversational agents.

[0956] A "user" is an individual or organization that uses the system to acquire information and transmits the generated results to the knowledge generation platform.

[0957] "High-precision results" refer to accurate and reliable information obtained by users using search engines or conversational agents.

[0958] A "knowledge generation platform" is a system that analyzes information submitted by users, converts it into an appropriate format, and stores it in a knowledge database.

[0959] A "knowledge database" is a database system that stores analyzed information and saves it in a format that can be reused later.

[0960] An "ecosystem" is the overall structure of a system that provides accumulated knowledge to users, enabling them to acquire information efficiently.

[0961] A "search engine" is software that searches the internet for relevant information based on keywords entered by the user and provides the results.

[0962] A "conversational agent" is software that responds to user questions in natural language, and is also known as a chatbot.

[0963] A "device" refers to a device used by a user to access search engines or conversational agents, and includes PCs, smartphones, and other similar devices.

[0964] A "server" is a computer system that operates knowledge generation platforms and knowledge databases, and performs information analysis and storage.

[0965] "Natural language processing technology" is a technique that allows computers to understand and analyze human language, and is used to understand the meaning of information and convert it into an appropriate format.

[0966] The HTTPS protocol is a communication protocol used to securely send and receive data over the internet.

[0967] This invention is a system that stores high-precision results generated by users in a knowledge database via a knowledge generation platform, and provides the stored knowledge to users in the form of an ecosystem. Specific embodiments of this system are described below.

[0968] System Configuration

[0969] hardware

[0970] Devices: PCs, smartphones, tablets, and other devices. Users access search engines and conversational agents using these devices.

[0971] Server: A computer system used to operate knowledge generation platforms and knowledge databases. It is equipped with a high-performance processor and large-capacity storage.

[0972] software

[0973] Search engine: Software that searches the internet for relevant information based on keywords entered by the user and provides the results.

[0974] Conversational agent: Software that responds to user questions in natural language. It uses generative AI models to generate appropriate answers to questions.

[0975] Knowledge generation platform: A system that analyzes information submitted by users, converts it into an appropriate format, and stores it in a knowledge database. It uses natural language processing technologies such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0976] Knowledge database: A database system that stores analyzed information and saves it in a format that can be reused later. It uses database management systems such as MySQL or PostgreSQL.

[0977] Data processing and data calculation

[0978] Information acquisition and transmission

[0979] Users use their devices to access search engines and conversational agents to obtain information. For example, a user might ask a conversational agent, "Tell me about the latest AI technologies." The conversational agent uses a generative AI model to generate an appropriate answer to the question. If the answer is deemed highly accurate, the device sends this information to a knowledge generation platform. The HTTPS protocol is used for transmission.

[0980] Information analysis and storage

[0981] The server analyzes the information received by the knowledge generation platform. This analysis uses natural language processing technologies such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding. The server understands the meaning of the information and converts it into an appropriate format. The analyzed information is stored in a knowledge database.

[0982] Reuse of information

[0983] When a user uses a search engine or conversational agent again to obtain information, the information stored in the knowledge database is reused. For example, if another user asks, "Tell me about the latest AI technologies," the conversational agent retrieves information from the knowledge database such as "It includes generative AI models and deep learning" and answers accordingly.

[0984] Examples of specific cases and prompt statements

[0985] As a concrete example, consider a scenario where a user asks a conversational agent, "Tell me about the latest AI technologies." The conversational agent replies, "The latest AI technologies include generative AI models and deep learning." If this answer is deemed highly accurate, the device sends this information to a knowledge generation platform. The server analyzes the information using the Google Cloud Natural Language API and stores it in a MySQL database. This information is then reused when other users search for "the latest AI technologies."

[0986] Examples of prompts to input into a generative AI model include the following:

[0987] "Tell me about the latest AI technology."

[0988] By entering this prompt into the interactive agent, the user can obtain highly accurate information, which is then stored in a knowledge database.

[0989] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0990] Step 1:

[0991] Users obtain information using search engines or conversational agents.

[0992] As a concrete example, the user uses their device to ask the conversational agent, "Tell me about the latest AI technology."

[0993] Input: User's question (prompt)

[0994] Output: Response from the conversational agent (response generated by the AI ​​model)

[0995] Step 2:

[0996] The device transmits the information it acquires to the knowledge generation platform.

[0997] Specifically, the device sends the response it received from the conversational agent, "The latest AI technologies include generative AI models and deep learning," to the knowledge generation platform using the HTTPS protocol.

[0998] Input: Response from the conversational agent

[0999] Output: Data to be sent to the knowledge generation platform

[1000] Step 3:

[1001] The server analyzes the information on the knowledge generation platform.

[1002] Specifically, the server uses the Google Cloud Natural Language API to analyze the information it receives, understand its meaning, and convert it into an appropriate format.

[1003] Input: Data sent to the knowledge generation platform

[1004] Output: Analyzed information (data converted to an appropriate format)

[1005] Step 4:

[1006] The server stores the analyzed information in a knowledge database.

[1007] Specifically, the server inserts the analyzed information into a MySQL database so that it can be reused later.

[1008] Input: Analyzed information

[1009] Output: Data stored in the knowledge database

[1010] Step 5:

[1011] Users reuse information from knowledge databases.

[1012] In a concrete example, if another user asks the conversational agent, "Tell me about the latest AI technologies," the conversational agent retrieves information from its knowledge database stating, "It includes generative AI models and deep learning," and then provides the answer.

[1013] Input: User's question (prompt)

[1014] Output: Information obtained from the knowledge database (response from the conversational agent)

[1015] (Application Example 1)

[1016] Next, we will describe Application Example 1 of Form 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."

[1017] Traditional factory operations have faced challenges such as difficulty in quickly obtaining necessary information from workers, leading to decreased work efficiency. Furthermore, significant time was often spent troubleshooting and determining optimal work procedures, resulting in overall reduced productivity. While automation using robots is advancing, insufficient coordination with human workers has made efficient operation difficult.

[1018] 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.

[1019] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for providing a knowledge-sharing robot assistant to improve work efficiency within the factory, means for displaying information to workers in real time via smart devices, and means for robots to transport necessary parts or automate simple tasks according to the worker's instructions. This enables workers to quickly obtain necessary information and efficiently perform troubleshooting and optimal work procedures. Furthermore, collaboration with robots is enhanced, improving overall productivity.

[1020] "Users" refer to individuals who use the system to search for information or acquire knowledge.

[1021] "High-precision results" refers to accurate and reliable information obtained through search engines or chatbots.

[1022] A "knowledge generation platform" refers to a system that collects information obtained by users and stores it in a knowledge database.

[1023] A "knowledge database" refers to a database that accumulates knowledge from various fields and provides it to users in the form of an ecosystem.

[1024] An "ecosystem" refers to a system that provides users with information accumulated in a knowledge database, allowing them to use and share that information with one another.

[1025] "Improving convenience" refers to enabling users to quickly and easily obtain the information they need.

[1026] "Improving operational efficiency" refers to increasing the efficiency of work and improving productivity.

[1027] A "knowledge-sharing robot assistant" refers to a robot that retrieves information from a knowledge database and provides it to workers in order to improve work efficiency within a factory.

[1028] A "smart device" refers to a device used to display information, such as a smartphone, smart glasses, or a head-mounted display.

[1029] "Displaying information in real time" means instantly displaying necessary information so that workers can use it on the spot.

[1030] A "robot" refers to a machine that transports necessary parts or automates simple tasks according to the instructions of a worker.

[1031] In order to implement this invention, the following system configuration and program are required.

[1032] System Configuration

[1033] 1. Hardware

[1034] Smart devices: Smartphones, smart glasses, head-mounted displays (e.g., Google Glass, Microsoft HoloLens)

[1035] Factory robots: Robots that automate the handling of parts and simple tasks (e.g., Universal Robots UR series)

[1036] Server: A server to host the knowledge generation platform and knowledge database.

[1037] 2. Software

[1038] API Server: Server software (e.g., Flask) that provides the functionality of a knowledge generation platform.

[1039] Database: Database software that functions as a knowledge database (e.g., MongoDB)

[1040] Program processing

[1041] The server executes a program that includes the following actions:

[1042] 1. Knowledge Generation Platform

[1043] Users utilize search and chatbots via their smart devices and send the highly accurate results obtained to a knowledge generation platform.

[1044] The knowledge generation platform stores the received information in a knowledge database.

[1045] 2. Knowledge DB

[1046] The knowledge database accumulates knowledge from various fields and provides it to users in the form of an ecosystem.

[1047] When a user requests the information they need, the system retrieves the most relevant information from the knowledge database and displays it on their smart device in real time.

[1048] 3. Knowledge-sharing robot assistant

[1049] To improve work efficiency within the factory, information is retrieved from the knowledge database and provided to workers.

[1050] The robots transport necessary parts according to the worker's instructions and automate simple tasks.

[1051] Specific example

[1052] For example, when a worker searches for "optimal welding techniques," the knowledge generation platform stores that information in the knowledge database. Then, when another worker needs the same information, the information on "optimal welding techniques" is retrieved from the knowledge database and displayed in real time on smart glasses.

[1053] Furthermore, if troubleshooting is required, a worker can search for "Solution for Error Code 123," and the solution will be retrieved from the knowledge database and displayed on the head-mounted display. In addition, the robot will transport the necessary parts according to the worker's instructions, automating the work.

[1054] Example of a prompt

[1055] "Please tell me the optimal welding technique."

[1056] "Please tell me how to resolve error code 123."

[1057] This allows workers to quickly obtain necessary information and efficiently perform troubleshooting and optimal work procedures. Furthermore, it enhances collaboration with robots, improving overall productivity.

[1058] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1059] Step 1:

[1060] Users input information using smart devices via search queries or chatbots. The entered queries are sent to a knowledge generation platform. The input here is text data related to the information the user wants to know or the problem they want to solve. The output is the query data sent to the knowledge generation platform.

[1061] Step 2:

[1062] The server processes query data received through the knowledge generation platform and generates relevant high-accuracy results. This process uses a generative AI model to produce the best possible answers to queries. The input is the query data submitted by the user, and the output is the generated high-accuracy results.

[1063] Step 3:

[1064] The server stores the generated high-precision results in a knowledge database. The input here is the generated high-precision results, and the output is the data stored in the knowledge database. Data processing involves converting the result data into an appropriate format and saving it to the database.

[1065] Step 4:

[1066] If the user needs the information again, they send a request to the knowledge database via their smart device. The input is the request data about the information the user wants to know, and the output is the request data sent to the knowledge database.

[1067] Step 5:

[1068] The server retrieves information corresponding to the request from the knowledge database. The input is the request data from the user, and the output is the relevant information retrieved from the knowledge database. In terms of data calculation, the database is searched based on the request, and the most relevant information is extracted.

[1069] Step 6:

[1070] The server transmits the acquired information to the smart device and displays it to the user in real time. The input is information retrieved from the knowledge database, and the output is the information displayed on the smart device. Specifically, the server converts the information into an appropriate format and displays it on the smart device's screen.

[1071] Step 7:

[1072] When a user gives instructions to a robot, they send those instructions to the robot via a smart device. The input is the instruction data from the user, and the output is the instruction data sent to the robot.

[1073] Step 8:

[1074] The robot transports necessary parts or automates simple tasks based on received instructions. The input is instruction data from the user, and the output is the result of the performed work. Specifically, the robot operates according to the instructions and performs the specified task.

[1075] This allows users to quickly obtain the information they need and efficiently perform troubleshooting and optimal work procedures. Furthermore, it enhances collaboration with robots, improving overall productivity.

[1076] (Example 2)

[1077] Next, we will describe Example 2 of Form 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".

[1078] Conventional medical information retrieval systems made it difficult for users to efficiently obtain the information they needed. Furthermore, when multiple users searched for the same information, they had to repeat the same search process each time, which was time-consuming and labor-intensive. In addition, there was a lack of effective means to utilize accumulated knowledge, creating a need for improved convenience and operational efficiency.

[1079] 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.

[1080] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for users to search for medical information and transmit the search results to the knowledge generation platform, and means for retrieving relevant information from the knowledge database and providing it to other users when they require similar information. As a result, users can efficiently obtain the medical information they need, and the time and effort required when multiple users search for the same information can be reduced. Furthermore, by effectively utilizing the stored knowledge, convenience and operational efficiency can be improved.

[1081] A "user" is an individual or organization that uses the system to search for medical information.

[1082] "High-precision results" refer to accurate and reliable information obtained by users when they perform a search.

[1083] A "knowledge generation platform" is a system for processing search results and storing them in a knowledge database.

[1084] A "knowledge database" is a database system used to store and manage accumulated medical information and other knowledge.

[1085] An "ecosystem" is the overall environment of a system that provides accumulated knowledge to users and facilitates its mutual use.

[1086] "Improving convenience" refers to enabling users to quickly and easily obtain the information they need.

[1087] "Improving operational efficiency" refers to increasing the efficiency of work through the use of a system, thereby reducing time and effort.

[1088] "Medical information" refers to all information related to healthcare, such as disease treatments, symptoms, and medication information.

[1089] "Search results" refer to a list of information obtained when a user performs a search.

[1090] "Sending" refers to the act of sending data from a device to a server.

[1091] "Acquisition" refers to the act of a server retrieving necessary information from a knowledge database.

[1092] "Providing" refers to the act of displaying information acquired by the server to the user.

[1093] This invention is a system for users to efficiently acquire medical information. Specific embodiments of this system are described below.

[1094] System Configuration

[1095] This system mainly consists of the following components:

[1096] User's device (PC, smartphone, etc.)

[1097] server

[1098] Knowledge generation platform

[1099] Knowledge Database

[1100] Hardware and software to use

[1101] Device: A device such as a PC or smartphone. A web browser (e.g., Google Chrome, Mozilla Firefox) is used to perform the search.

[1102] Server: Receives and processes search queries. Uses a web server (e.g., Apache HTTP Server, Nginx) and a database management system (e.g., MySQL, PostgreSQL).

[1103] Knowledge generation platform: Processes search results and stores them in a knowledge database. Uses a data streaming platform (e.g., Apache Kafka).

[1104] Knowledge database: Stores and manages accumulated medical information. Uses a database management system (e.g., MySQL, PostgreSQL).

[1105] System operation

[1106] 1. Users search for medical information.

[1107] Users open a web browser on their PC or smartphone and access search engines or dedicated medical information search sites.

[1108] Enter keywords such as "diabetes treatments" into the search box and click the search button.

[1109] 2. The device sends the search results to the server.

[1110] The terminal sends the generated search query to the server as an HTTP request.

[1111] Example: The device sends the request "GET / search?q=diabetes treatment HTTP / 1.1" to the server.

[1112] 3. The server processes the data on the knowledge generation platform.

[1113] The server analyzes the received search queries and collects relevant medical information.

[1114] The server sends the collected information to the knowledge generation platform.

[1115] Example: A server collects information about "diabetes treatments" and sends it to a knowledge generation platform.

[1116] 4. The server stores data in the knowledge database.

[1117] The knowledge generation platform stores the received information in a knowledge database.

[1118] Example: Information about "treatments for diabetes" is stored in a knowledge database.

[1119] 5. Another user searches for similar information.

[1120] Another user similarly uses a PC or smartphone to search for medical information.

[1121] Enter "diabetes treatments" into the search box and click the search button.

[1122] 6. The server retrieves the relevant information from the knowledge database and provides it to the user.

[1123] The server searches for and retrieves the relevant information from the knowledge database.

[1124] The server sends the retrieved information to the user's terminal as an HTTP response.

[1125] Example: The server retrieves information about "treatments for diabetes" from a knowledge database and displays it to the user.

[1126] Examples of specific cases and prompt statements

[1127] Specific example

[1128] User A searches for "treatments for high blood pressure," and the results are saved in the knowledge database.

[1129] When user B later searches for "treatments for high blood pressure," information is retrieved from the knowledge database and provided to user B.

[1130] Example of a prompt

[1131] "Please provide me with the latest information on treatments for high blood pressure."

[1132] "Please provide detailed information regarding diabetes treatment options."

[1133] This system allows users to efficiently obtain necessary medical information. It also reduces the time and effort required for multiple users to search for the same information. By effectively utilizing accumulated knowledge, convenience and operational efficiency can be improved.

[1134] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1135] Step 1:

[1136] Users search for medical information.

[1137] Input: The user uses a PC or smartphone, opens a web browser, and accesses a search engine or a dedicated medical information search site. They enter keywords such as "diabetes treatment" into the search box and click the search button.

[1138] Data processing: Search queries are generated.

[1139] Output: The generated search query is retained on the terminal.

[1140] Specific operation: When a user enters "diabetes treatments" and clicks the search button, a search query is generated.

[1141] Step 2:

[1142] The device sends the search results to the server.

[1143] Input: The generated search query.

[1144] Data processing: The terminal sends the search query to the server as an HTTP request.

[1145] Output: The server receives the search query.

[1146] Specific action: The terminal sends a request to the server: "GET / search?q=diabetes treatment HTTP / 1.1".

[1147] Step 3:

[1148] The server processes the data on the knowledge generation platform.

[1149] Input: The search query received by the server.

[1150] Data processing: The server analyzes search queries and collects relevant medical information. The collected information is then sent to the knowledge generation platform.

[1151] Output: The knowledge generation platform receives the information.

[1152] Specific operation: The server collects information on "diabetes treatments" and sends it to the knowledge generation platform.

[1153] Step 4:

[1154] The server stores data in a knowledge database.

[1155] Input: Information received by the knowledge generation platform.

[1156] Data processing: The knowledge generation platform stores the received information in a knowledge database.

[1157] Output: Information is stored in the knowledge database.

[1158] Specific action: Information about "treatments for diabetes" is stored in the knowledge database.

[1159] Step 5:

[1160] Another user searches for similar information

[1161] Input: Another user uses a PC or smartphone, opens a web browser, and accesses a search engine or a dedicated medical information search site. They enter "diabetes treatments" into the search box and click the search button.

[1162] Data processing: Search queries are generated.

[1163] Output: The generated search query is retained on the terminal.

[1164] Specific operation: When another user types "diabetes treatments" and clicks the search button, a search query is generated.

[1165] Step 6:

[1166] The server retrieves the relevant information from the knowledge database and provides it to the user.

[1167] Input: The search query received by the server.

[1168] Data processing: The server searches for and retrieves the relevant information from the knowledge database. The retrieved information is then sent to the user's terminal as an HTTP response.

[1169] Output: Information is displayed on the user's terminal.

[1170] Specific operation: The server retrieves information about "diabetes treatments" from the knowledge database and displays it to the user.

[1171] (Application Example 2)

[1172] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1173] In modern brick-and-mortar stores, there is a challenge in that it is difficult for customers to efficiently obtain product information. In particular, if a customer wants to know detailed information or stock status about a specific product, they have to ask a store employee, which is time-consuming and troublesome. Furthermore, if multiple customers request the same information, duplicate information retrieval occurs, which is inefficient. In addition, traditional search systems and chatbots have difficulty providing information in real time, which reduces customer convenience.

[1174] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing high-precision results generated by the user in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, means for improving convenience and operational efficiency, and means for providing product information in real time using smart devices in physical stores. As a result, users can improve their shopping experience in physical stores and quickly and efficiently obtain the necessary product information.

[1175] A "user" is an individual or organization that uses the system to search for and retrieve information.

[1176] "High-precision results" refer to search results that provide accurate and relevant information for the user's search query.

[1177] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[1178] A "knowledge database" is a database that stores collected information and provides it to users as needed.

[1179] An "ecosystem" is an integrated system environment for providing users with information accumulated in a knowledge database.

[1180] "Improving convenience" refers to enabling users to quickly and efficiently obtain the information they need.

[1181] "Improving operational efficiency" refers to preventing duplicate information acquisition and increasing the overall efficiency of the system.

[1182] A "physical store" is a store that sells goods in a physical location.

[1183] A "smart device" is an electronic device that is connected to the internet and can display and operate information.

[1184] "Real-time" refers to the immediate acquisition and provision of information.

[1185] This invention is a system that provides product information in real time using smart devices in physical stores. A specific embodiment of this system is described below.

[1186] System Configuration

[1187] The system consists of the following main components:

[1188] 1. Knowledge Generation Platform: Collects high-precision results generated by users and stores them in a knowledge database.

[1189] 2. Knowledge Database: Stores accumulated information and provides it as needed.

[1190] 3. Smart devices: Devices used by customers in physical stores (e.g., smart glasses).

[1191] 4. Ecosystem: An integrated system that provides users with information accumulated in a knowledge database.

[1192] Program processing

[1193] The server stores the high-precision results generated by users in a knowledge database via the knowledge generation platform. Specifically, when a user searches for product information using a smart device, the search results are sent to the knowledge generation platform. The knowledge generation platform analyzes the search results and stores them in the knowledge database.

[1194] Next, if another user needs information about the same product, they can access the knowledge database via their smart device and retrieve the relevant information. The retrieved information is displayed in real time on the smart device's screen.

[1195] Hardware and software to use

[1196] Hardware: Smart glasses, servers

[1197] Software: Knowledge generation platform, knowledge database, API

[1198] Specific example

[1199] For example, suppose a user is looking for "medical masks" in a physical store. When the user, wearing smart glasses, searches for "medical masks" by voice, detailed information and stock availability of medical masks will be displayed on the smart glasses' screen. This information is retrieved in real time from a knowledge database.

[1200] Example of a prompt

[1201] "Please search for information on medical masks."

[1202] "Please retrieve information on medical masks from the knowledge database."

[1203] "Please display information about medical masks on smart glasses."

[1204] In this way, users can improve their in-store shopping experience and obtain necessary product information quickly and efficiently.

[1205] The flow of the specific processing in Application Example 2 will be explained using Figure 14.

[1206] Step 1:

[1207] A user searches for product information using a smart device (e.g., smart glasses). The user enters the search query via voice input or touch operation. The entered query is sent from the smart device to the server. The input data is the search query, and the output data is the search request sent to the server.

[1208] Step 2:

[1209] The server sends the received search query to the knowledge generation platform. The knowledge generation platform analyzes the search query and generates relevant high-accuracy results. The input data is the search query, and the output data is the high-accuracy results. Specifically, the knowledge generation platform analyzes the search query and retrieves relevant information from the database.

[1210] Step 3:

[1211] The knowledge generation platform stores the high-precision results it generates in a knowledge database. The input data consists of the high-precision results, while the output data is the information stored in the knowledge database. Specifically, the knowledge generation platform writes the high-precision results to the database.

[1212] Step 4:

[1213] When another user searches for information about the same product, they use their smart device to re-enter the search query. The entered query is sent from the smart device to the server. The input data is the search query, and the output data is the search request sent to the server.

[1214] Step 5:

[1215] The server accesses the knowledge database and retrieves the relevant information. The input data is a search query, and the output data is the information retrieved from the knowledge database. Specifically, the server sends a query to the knowledge database and retrieves the relevant information.

[1216] Step 6:

[1217] The server sends the acquired information to the smart device. The input data is information retrieved from the knowledge database, and the output data is the information sent to the smart device. Specifically, the server transfers the acquired information to the smart device.

[1218] Step 7:

[1219] A smart device displays received information to the user. Input data is information sent from the server, and output data is information displayed on the smart device's screen. Specifically, the smart device displays the received information on its screen.

[1220] In this way, users can improve their in-store shopping experience and obtain necessary product information quickly and efficiently.

[1221] (Example 3)

[1222] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[1223] Conventional information retrieval systems often made it difficult for users to quickly obtain the information they needed, resulting in time-consuming information searches. Furthermore, search results frequently did not match user needs, hindering improvements in operational efficiency. Additionally, conventional systems lacked effective means of utilizing accumulated knowledge, making knowledge reuse difficult.

[1224] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1225] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform; means for providing the stored knowledge to users in the form of an ecosystem; means for receiving and analyzing queries sent by users from terminals; means for searching for relevant information from the knowledge database based on the analyzed queries; means for inputting the search results as prompt sentences into a generation AI model to generate appropriate answers; and means for providing the generated answers to users. As a result, users can quickly obtain the information they need, reduce information retrieval time, and improve work efficiency.

[1226] A "user" is an individual or organization that uses the system to search for information and obtain the necessary data.

[1227] "High-precision results" refer to search results that provide accurate and appropriate information in response to the user's query.

[1228] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[1229] A "knowledge database" is a database that stores accumulated information and knowledge, and allows it to be searched and retrieved as needed.

[1230] An "ecosystem" is the overall structure of a system that provides users with accumulated knowledge and promotes the reuse and sharing of information.

[1231] A "terminal" is a device (e.g., a personal computer or smartphone) used by a user to input queries and communicate with a server.

[1232] A "query" is a question or request that a user enters into a system to search for information.

[1233] A "server" is a computer system that receives and analyzes queries, retrieves information from a knowledge database, and generates answers using a generative AI model.

[1234] A "generative AI model" is an artificial intelligence model that generates appropriate responses in natural language based on input prompt sentences.

[1235] A "prompt sentence" is an instruction given to a generative AI model, and it is the sentence that forms the basis for the model to generate an appropriate response.

[1236] Modes for carrying out the invention

[1237] This invention is a system for quickly obtaining information that users need and improving work efficiency. Specific embodiments of this system are described below.

[1238] System Configuration

[1239] hardware

[1240] Server: High-performance server (e.g., general-purpose server)

[1241] Device: The device used by the user (e.g., personal computer, smartphone)

[1242] software

[1243] Database management system: Software for managing knowledge databases (e.g., MySQL)

[1244] Generative AI models: Artificial intelligence models that perform natural language processing (e.g., general-purpose generative AI models)

[1245] Program processing

[1246] The server receives and parses queries sent from the terminal. Based on the parsed queries, the server searches for relevant information in its knowledge database. The search results are input as prompts into a generative AI model, which generates appropriate answers. The generated answers are sent from the server to the terminal and provided to the user.

[1247] Specific example

[1248] For example, consider a case where a user enters the query, "Tell me about the latest project management tools."

[1249] 1. Query Reception: The user sends a query from their terminal saying, "Tell me about the latest project management tools."

[1250] 2. Query Analysis: The server analyzes the query and searches the knowledge database for information related to "project management tools."

[1251] 3. Information Retrieval: The server uses MySQL to retrieve relevant information from the knowledge database.

[1252] 4. Use of Generative AI Models: The server inputs the acquired information into a generative AI model, which then formats the information in a way that is easy for the user to understand.

[1253] 5. Information Provision: The server sends the formatted information to the user's terminal.

[1254] An example of a prompt to input into the generating AI model would be, "Please provide information about the latest project management tools. Please use the following data as a basis," followed by inputting information obtained from the knowledge database.

[1255] In this way, users can quickly obtain the necessary information, reduce information retrieval time, and improve work efficiency. The flow of the specific processing in Example 3 will be explained using Figure 15.

[1256] Step 1:

[1257] The user enters a query.

[1258] The user enters the information they want to retrieve from their device (e.g., a computer or smartphone). For example, they might enter, "Tell me about the latest project management tools." The entered query is saved in the input field on the device.

[1259] Step 2:

[1260] The terminal sends a query to the server.

[1261] The terminal sends the query entered by the user to the server as an HTTP request. This data is transmitted over the internet. The input is the user's query, and the output is the HTTP request to the server.

[1262] Step 3:

[1263] The server receives and parses the query.

[1264] The server receives HTTP requests sent from the terminal. It parses the received queries and identifies the type of information the user is seeking. The input is the HTTP request, and the output is the parsed query. Specifically, the server recognizes the query content as information related to "project management tools."

[1265] Step 4:

[1266] The server searches for relevant information from the knowledge database.

[1267] The server searches for relevant information from the knowledge database based on the analysis results. For example, it uses a database management system (e.g., MySQL) to retrieve the latest information on "project management tools". The input is the parsed query, and the output is the search result. Specifically, it executes the query "SELECT FROM knowledge_db WHERE topic='project management tools' ORDER BY date DESC LIMIT 1".

[1268] Step 5:

[1269] The server inputs prompt messages into the generated AI model.

[1270] The server inputs prompts to the generating AI model based on information retrieved from the knowledge database. An example of a prompt is, "Please provide information about the latest project management tools. Please use the following data as a basis." The input is the search results, and the output is the prompts to the generating AI model.

[1271] Step 6:

[1272] The generative AI model generates the appropriate answer.

[1273] The generative AI model generates appropriate answers based on the input prompt. The generated answers are expressed in natural language that is easy for the user to understand. The input is the prompt, and the output is the generated answer. Specifically, it generates answers such as, "Modern project management tools help with task management, visualization of project progress, and team collaboration."

[1274] Step 7:

[1275] The server sends the generated response to the user.

[1276] The server sends the response obtained from the generated AI model to the user's device. This data is transmitted over the internet. The input is the generated response, and the output is an HTTP response to the user's device. Specifically, the response is sent in JSON format.

[1277] Step 8:

[1278] The user receives the response.

[1279] The user receives the response from the server on their device and checks the displayed answer. This allows the user to quickly obtain the necessary information. The input is the HTTP response from the server, and the output is the answer displayed on the user's device.

[1280] (Application Example 3)

[1281] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 as a "terminal".

[1282] Conventional systems made it difficult for users to quickly obtain the information they needed, and in particular, information retrieval was time-consuming, leading to decreased operational efficiency, especially in the maintenance and troubleshooting of factory robots. Furthermore, the lack of means to provide appropriate information in response to error codes and maintenance requests made it difficult to respond quickly.

[1283] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1284] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, and means for robots to detect error codes and maintenance requests, and for retrieving and providing relevant information from the knowledge database. This enables users to quickly obtain the information they need and allows for quick and appropriate responses in the maintenance and troubleshooting of factory robots.

[1285] "User" refers to an individual or organization that uses the system to obtain information and perform tasks.

[1286] "High-precision results" refers to accurate and reliable information and data generated by users.

[1287] A "knowledge generation platform" refers to a system or tool that collects information generated by users and stores it in a knowledge database.

[1288] A "knowledge database" refers to a database that systematically stores accumulated information and knowledge, and makes it searchable and available as needed.

[1289] An "ecosystem" refers to an integrated system or environment for providing users with information accumulated in a knowledge database.

[1290] "Improving convenience" refers to enhancing the ease of use and comfort for users when using the system.

[1291] "Improving work efficiency" refers to reducing the time and effort required to perform tasks and thereby increasing productivity.

[1292] The term "robot" refers to automated machinery used in factories and other similar settings.

[1293] An "error code" refers to an identification number or string of characters displayed when a robot or system detects an abnormality.

[1294] A "maintenance request" refers to a notification or instruction issued by a robot or system when it requires regular maintenance or repair.

[1295] "Related information" refers to specific countermeasures and procedures for responding to error codes and maintenance requests.

[1296] As an example of how to implement this invention, we will describe a "smart maintenance assistant" system installed on a factory robot.

[1297] System program

[1298] The system consists of the following main components:

[1299] 1. Knowledge Generation Platform

[1300] 2. Knowledge Database

[1301] 3. Ecosystem

[1302] 4. Robot error detection and maintenance request detection function

[1303] Program Processing Description

[1304] Hardware to use

[1305] Factory robots (e.g., general industrial robots)

[1306] Computer installed in the robot

[1307] Software to use

[1308] Python program

[1309] Knowledge database (database management system)

[1310] Data processing and data calculation

[1311] 1. Knowledge Generation Platform

[1312] The server stores the high-precision results generated by users in a knowledge database via the knowledge generation platform. This ensures that the information generated by users is systematically stored.

[1313] 2. Knowledge Database

[1314] The server provides users with accumulated knowledge in the form of an ecosystem. The knowledge database includes maintenance information and troubleshooting guides.

[1315] 3. Ecosystem

[1316] The server provides users with the information they need quickly through the ecosystem. This improves convenience and operational efficiency.

[1317] 4. Robot error detection and maintenance request detection function

[1318] The robot detects error codes and maintenance requests, and retrieves relevant information from a knowledge database. This allows for quick and appropriate maintenance and troubleshooting of the robot.

[1319] Specific example

[1320] For example, if the robot detects "error_101," it retrieves the information "Please check the belt tension" from the knowledge database and displays it on the robot's display.

[1321] Example of a prompt

[1322] "If the robot detects an error code, retrieve the corresponding maintenance information from the knowledge database and display it."

[1323] The above describes the embodiment for carrying out this invention. This system allows users to quickly obtain necessary information and to respond quickly and appropriately to maintenance and troubleshooting of factory robots.

[1324] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1325] Step 1:

[1326] The server stores the high-precision results generated by users in a knowledge database via the knowledge generation platform.

[1327] Input: High-precision results generated by the user

[1328] Data processing: High-precision results are formalized using a knowledge generation platform and stored in a knowledge database.

[1329] Output: High-precision results stored in the knowledge database

[1330] Specific operation: The server receives the data entered by the user and saves it to the database in the appropriate format.

[1331] Step 2:

[1332] The server provides users with accumulated knowledge in the form of an ecosystem.

[1333] Input: Information stored in the knowledge database

[1334] Data processing: Search for necessary information from the knowledge database and provide it through the ecosystem.

[1335] Output: Knowledge information provided to users

[1336] Specific operation: When a user requests information, the server searches the database for the relevant information and provides it to the user through the ecosystem.

[1337] Step 3:

[1338] The robot detects error codes and maintenance requests.

[1339] Input: Data from the robot's sensors and internal systems.

[1340] Data processing: Analyze and identify error codes and maintenance requests.

[1341] Output: Detected error codes and maintenance requests

[1342] Specific operation: When the robot detects an anomaly during operation, it analyzes data from sensors and internal systems to identify error codes and maintenance requests.

[1343] Step 4:

[1344] The server searches the knowledge database for relevant information based on the detected error code and maintenance request.

[1345] Input: Detected error codes or maintenance requests

[1346] Data processing: Search for relevant information from the knowledge database.

[1347] Output: Related Information

[1348] Specific operation: The server receives error codes and maintenance requests and searches the knowledge database for the corresponding information.

[1349] Step 5:

[1350] The server provides the robot with the relevant information that was found.

[1351] Input: Related information retrieved from the knowledge database

[1352] Data processing: Converting information into a format that robots can understand.

[1353] Output: Relevant information provided to the robot

[1354] Specific operation: The server sends the retrieved information to the robot, which then displays it on the robot's display and audio output.

[1355] Step 6:

[1356] The robot performs maintenance and troubleshooting based on the information provided.

[1357] Input: Relevant information provided by the server

[1358] Data processing: Execute specific maintenance and troubleshooting procedures based on the information.

[1359] Output: Maintenance and troubleshooting complete

[1360] Specific actions: The robot performs necessary maintenance tasks and troubleshooting according to the information provided.

[1361] 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.

[1362] "Example of form 1"

[1363] One embodiment of the present invention provides a system that incorporates an emotion engine. This system includes means for storing high-precision results generated by the user in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, and means for improving convenience and operational efficiency. Furthermore, this system includes an emotion engine that recognizes the user's emotions. Specifically, the emotion engine recognizes emotions from the user's tone of voice, facial expressions, text input, etc., and adjusts the operation of the knowledge generation platform according to those emotions. For example, if the user is perceived as angry, the emotion engine sends instructions to the knowledge generation platform to prioritize the provision of knowledge that will quickly resolve the user's problem.

[1364] "Example of form 2"

[1365] Another embodiment of the present invention provides a system in which an emotion engine selects knowledge to provide in accordance with the user's emotions. This system includes means for storing high-precision results generated by the user in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, and means for improving convenience and operational efficiency. Furthermore, this system includes an emotion engine that recognizes the user's emotions. Specifically, the emotion engine recognizes the user's emotions and selects knowledge to provide in accordance with those emotions. For example, if the emotion engine senses that the user is happy, it sends instructions to the knowledge generation platform to provide knowledge that matches the user's interests and preferences.

[1366] "Example of form 3"

[1367] As a further embodiment of the present invention, a system is provided in which an emotion engine adjusts the operation of a knowledge generation platform in accordance with the user's emotions. This system includes means for storing high-precision results generated by the user in a knowledge database via the knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, and means for improving convenience and operational efficiency. Furthermore, this system includes an emotion engine that recognizes the user's emotions. Specifically, the emotion engine recognizes the user's emotions and adjusts the operation of the knowledge generation platform in accordance with those emotions. For example, if the user feels confused, the emotion engine sends instructions to the knowledge generation platform to quickly provide the information the user needs.

[1368] The following describes the processing flow for each example of the form.

[1369] "Example of form 1"

[1370] Step 1: The user uses the system to search for or inquire about information.

[1371] Step 2: The emotion engine recognizes the user's emotions from their tone of voice, facial expressions, text input, etc.

[1372] Step 3: Adjust the operation of the knowledge generation platform based on the emotions recognized by the emotion engine.

[1373] Step 4: The knowledge generation platform prioritizes providing knowledge to quickly resolve user problems.

[1374] "Example of form 2"

[1375] Step 1: The user uses the system to search for or inquire about information.

[1376] Step 2: The emotion engine recognizes the user's emotions from their tone of voice, facial expressions, text input, etc.

[1377] Step 3: Based on the emotions recognized by the emotion engine, select the knowledge to provide.

[1378] Step 4: The knowledge generation platform provides knowledge that matches the user's interests and preferences.

[1379] "Example of form 3"

[1380] Step 1: The user uses the system to search for or inquire about information.

[1381] Step 2: The emotion engine recognizes the user's emotions from their tone of voice, facial expressions, text input, etc.

[1382] Step 3: Adjust the operation of the knowledge generation platform based on the emotions recognized by the emotion engine.

[1383] Step 4: The knowledge generation platform quickly provides the information the user needs.

[1384] (Example 1)

[1385] Next, we will describe Embodiment 1 of Embodiment 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".

[1386] Information obtained through conventional search engines and chatbots is only used temporarily for individual users and is rarely accumulated as useful knowledge for other users or future users. Furthermore, because information is provided without considering the user's emotions, user satisfaction and work efficiency may decrease. To solve these problems, a system is needed that efficiently stores highly accurate information obtained by users and provides appropriate information tailored to their emotions.

[1387] 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.

[1388] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means including an emotion engine that recognizes the user's emotions, and means for adjusting the operation of the knowledge generation platform according to the emotions recognized by the emotion engine. This enables efficient storage of high-precision information obtained by users and the provision of appropriate information according to their emotions.

[1389] A "user" is an individual or organization that uses the system to search for information or obtains information using a chatbot.

[1390] "High-precision results" refer to accurate and reliable information obtained by users through search engines or chatbots.

[1391] A "knowledge generation platform" is a system that receives information obtained by users, analyzes it, and stores it in a knowledge database.

[1392] A "knowledge database" is a database that stores knowledge from various fields and provides it as needed.

[1393] An "ecosystem" is the overall structure of a system that provides accumulated knowledge to users and enables users to utilize that knowledge.

[1394] "Improving convenience" refers to increasing the ease of use and efficiency when using the system.

[1395] "Improving work efficiency" refers to increasing the efficiency of carrying out work tasks.

[1396] An "emotion engine" is an engine that recognizes emotions from the user's tone of voice, facial expressions, text input, etc., and adjusts the system's operation according to those emotions.

[1397] "Adjusting behavior" refers to changing the behavior of the knowledge generation platform based on the emotions recognized by the emotion engine.

[1398] This invention is a system that stores highly accurate results obtained by users using conventional search engines and chatbots in a knowledge database via a knowledge generation platform, and provides the accumulated knowledge to users in the form of an ecosystem. Furthermore, by combining it with an emotion engine, it provides knowledge that is tailored to the user's emotions.

[1399] System Configuration

[1400] 1. User actions

[1401] Users use their devices to input information into search engines and chatbots.

[1402] Example: The user types "Tell me about the latest AI technology."

[1403] 2. Device operation

[1404] The terminal sends the information entered by the user to the knowledge generation platform.

[1405] Software to use: A library for sending HTTP requests (e.g., Axios)

[1406] 3. Server operation

[1407] The server analyzes the received information and stores it in a knowledge database.

[1408] Hardware used: Server (e.g., cloud service)

[1409] Software to use: Database management system (e.g., MySQL)

[1410] 4. How the Emotion Engine Works

[1411] The emotion engine recognizes emotions from the user's voice tone, facial expressions, and text input.

[1412] Software to be used: Emotion recognition library (e.g., OpenCV, NLP library)

[1413] For example, if a user types "This problem isn't getting resolved!", the emotion engine will recognize that the user is angry.

[1414] 5. Coordination of knowledge sharing

[1415] The server receives instructions from the emotion engine and adjusts the knowledge delivery based on the user's emotions.

[1416] Example: If a user is angry, the server quickly provides knowledge to help resolve the problem.

[1417] 6. Providing Knowledge

[1418] The server provides users with accumulated knowledge in the form of an ecosystem.

[1419] Software to use: Web application framework (e.g., Django)

[1420] Specific example

[1421] The user searches for information or enters it into the chatbot.

[1422] The user types, "Tell me about the latest AI technology."

[1423] The user types, "This problem is not resolved!"

[1424] The device sends information to the knowledge generation platform.

[1425] The device sends an HTTP request containing the information, "Tell me about the latest AI technology."

[1426] The device sends an HTTP request containing the information, "This problem cannot be resolved!"

[1427] The server analyzes the information and stores it in the knowledge database.

[1428] The server analyzes the information, such as "Tell me about the latest AI technology," and stores it in a knowledge database.

[1429] The server analyzes information indicating "This problem cannot be resolved!" and saves it to the knowledge database.

[1430] The emotion engine recognizes the user's emotions.

[1431] The emotion engine recognizes that the user is angry from the text, "This problem isn't getting solved!"

[1432] The emotion engine recognizes that the user is sad based on their facial expression.

[1433] The server adjusts knowledge delivery based on emotions.

[1434] The server receives information that "the user is angry" and provides high-priority knowledge.

[1435] The server receives information that "the user is sad" and provides comforting knowledge.

[1436] The server provides knowledge to the user.

[1437] The server displays a knowledge base page with the question, "Tell me about the latest AI technologies."

[1438] The server displays a knowledge base article on its webpage stating, "This problem cannot be resolved!"

[1439] This system allows users to efficiently obtain highly accurate information and receive appropriate support tailored to their emotions.

[1440] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1441] Step 1:

[1442] The user searches for information or enters it into the chatbot.

[1443] Input: The user enters information into a search engine or chatbot using their device.

[1444] Specific action: The user opens a browser and types "Tell me about the latest AI technology" into the search bar.

[1445] Output: The information entered by the user is sent to the terminal.

[1446] Step 2:

[1447] The device sends information to the knowledge generation platform.

[1448] Input: Information entered by the user.

[1449] Specific operation: The terminal generates an HTTP request and sends data containing the entered information to the server. The library used is Axios.

[1450] Output: The information entered by the user is sent to the knowledge generation platform.

[1451] Step 3:

[1452] The server analyzes the information and stores it in the knowledge database.

[1453] Input: Information sent from the device.

[1454] Specific operation: The server executes a Python script and parses the received data. The analysis results are saved to a MySQL database.

[1455] Output: The analyzed information is stored in the knowledge database.

[1456] Step 4:

[1457] The emotion engine recognizes the user's emotions.

[1458] Input: User's voice tone, facial expression, and text input.

[1459] Specific operation: The emotion engine uses OpenCV to analyze the user's facial expressions and an NLP library to extract emotions from text input.

[1460] Output: User's emotions are recognized.

[1461] Step 5:

[1462] The server adjusts knowledge delivery based on emotions.

[1463] Input: Emotion recognition result from the emotion engine.

[1464] Specific operation: The server receives information from the emotion engine that "the user is angry," searches for high-priority knowledge, and provides it.

[1465] Output: Instructions for providing knowledge, tailored to the user's emotions, are generated.

[1466] Step 6:

[1467] The server provides knowledge to the user.

[1468] Input: Information stored in the knowledge database and instructions from the emotion engine.

[1469] Specific operation: The server uses the Django framework to generate a web page and display knowledge to the user.

[1470] Output: The knowledge provided to the user is displayed on the web page.

[1471] (Application Example 1)

[1472] Next, we will describe Application Example 1 of Form 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."

[1473] Traditional knowledge management systems struggled to efficiently store and appropriately provide user-generated information. Furthermore, they lacked the ability to consider user emotions, hindering customer satisfaction. In addition, physical stores lacked the means to provide staff with relevant knowledge in real time when interacting with customers.

[1474] 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. In this invention, the server includes means for storing high-precision results generated by the user in a knowledge DB via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, means for improving convenience and operational efficiency, means for recognizing the user's emotions using an emotion engine and adjusting the operation of the knowledge generation platform according to those emotions, and means for providing knowledge in real time through a smart device. This makes it possible to provide appropriate knowledge according to the user's emotions and improve the quality of customer service in physical stores.

[1475] A "user" is an individual or organization that uses the system to generate information and acquire knowledge.

[1476] "High-precision results" refer to accurate and reliable information obtained by users through searches or chatbots.

[1477] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[1478] A "knowledge database" is a database that stores knowledge from various fields.

[1479] An "ecosystem" is an integrated system environment for providing users with accumulated knowledge.

[1480] "Improving convenience" refers to making the system easier and more efficient for users to use.

[1481] "Improving business efficiency" refers to increasing the productivity and efficiency of business operations by using systems.

[1482] An "emotion engine" is a system that recognizes emotions from the user's voice tone, facial expressions, text input, and other factors.

[1483] A "smart device" is a device with internet connectivity, such as a smartphone, smart glasses, or a head-mounted display.

[1484] "Real-time" refers to processing or responding immediately without delay.

[1485] As an example of how to implement this invention, a customer service system using smart devices in a physical store will be described. This system stores high-precision results generated by users in a knowledge database via a knowledge generation platform, and provides the stored knowledge to users in the form of an ecosystem. Furthermore, it recognizes the user's emotions using an emotion engine and adjusts the operation of the knowledge generation platform according to those emotions.

[1486] Hardware and software to use

[1487] Hardware: Smart glasses (including camera, microphone, and display)

[1488] software:

[1489] EmotionRecognizer: A library for recognizing emotions from facial expressions.

[1490] KnowledgeDB: A library for accessing a knowledge database and retrieving answers to questions.

[1491] SmartGlassesInterface: An interface for controlling the camera, microphone, and display of smart glasses.

[1492] System operation

[1493] The server captures the customer's face through the smart glasses' camera and uses an EmotionRecognizer to recognize emotions from facial expressions. Next, it obtains the customer's question as voice input through the smart glasses' microphone and sends the question to the KnowledgeDB to obtain an appropriate answer. At this time, the knowledge generation platform adjusts its operation according to the recognized emotion and prioritizes providing the appropriate knowledge. Finally, the answer is displayed on the smart glasses' display.

[1494] Specific example

[1495] For example, if a customer asks a question about a product in a store and looks a little unsure, the emotion engine recognizes this. The server then prioritizes retrieving reassuring answers from the knowledge database and displays them on the smart glasses' screen. This allows the customer to choose products with confidence.

[1496] Example of a prompt

[1497] "If a customer looks anxious, provide a reassuring response."

[1498] In this way, the quality of customer service in physical stores can be improved.

[1499] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[1500] Step 1:

[1501] The server captures the customer's face through the smart glasses' camera. The input is the camera feed, and the output is the captured image data. This image data is sent to the EmotionRecognizer.

[1502] Step 2:

[1503] The server recognizes customer emotions from captured image data using EmotionRecognizer. The input is image data, and the output is recognized emotion data. EmotionRecognizer analyzes facial expressions to identify emotions.

[1504] Step 3:

[1505] The server receives customer questions via voice input through the microphone of smart glasses. The input is voice data, and the output is text data. Speech recognition software is used to convert the voice data into text.

[1506] Step 4:

[1507] The server sends the acquired text data to KnowledgeDB to retrieve the appropriate answer. The input is text data and sentiment data, and the output is the answer text. KnowledgeDB searches for answers to the question and prioritizes providing the appropriate answer based on the sentiment data.

[1508] Step 5:

[1509] The server displays the retrieved response text on the smart glasses' display. The input is the response text, and the output is the text displayed on the display. The response is displayed using the smart glasses' display interface.

[1510] Step 6:

[1511] The user checks the answers displayed on the smart glasses' screen and responds appropriately to the customer. The input is the text displayed on the screen, and the output is the response to the customer. The user provides explanations and guidance to the customer based on the displayed information.

[1512] (Example 2)

[1513] Next, we will describe Example 2 of Form 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".

[1514] Conventional information retrieval systems have problems such as difficulty in efficiently obtaining the information users need, and a lack of information provision that responds to users' emotions, leading to decreased user satisfaction. Furthermore, there is a lack of means to effectively utilize accumulated knowledge, resulting in a failure to improve operational efficiency.

[1515] 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.

[1516] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for receiving user search queries and acquiring relevant information, means for transmitting the acquired information to the knowledge generation platform, and means for recognizing the user's emotions using an emotion engine and selecting knowledge to provide according to those emotions. As a result, users can efficiently acquire the information they need, information can be provided according to their emotions, and user satisfaction can be improved. Furthermore, operational efficiency can be improved by effectively utilizing the stored knowledge.

[1517] A "user" is an individual or organization that uses the system to search for information and receive the results.

[1518] "High-precision results" refer to search results that are highly relevant to the user's search query and contain accurate information.

[1519] A "knowledge generation platform" is a system for collecting and analyzing search results and other information, and storing it in a knowledge database.

[1520] A "knowledge database" is a database that stores accumulated knowledge and information, and allows it to be searched and retrieved as needed.

[1521] An "ecosystem" is an integrated system or environment designed to provide users with accumulated knowledge.

[1522] "Improving convenience" refers to increasing the ease of use and efficiency for users when using the system.

[1523] "Improving business efficiency" refers to increasing the speed and effectiveness of business processes by using systems.

[1524] A "search query" is a keyword or phrase that a user enters when searching for information.

[1525] An "emotion engine" is a system that recognizes the user's emotions and provides appropriate information in response to those emotions.

[1526] "Relevant information" refers to information that is appropriate and useful to the user's search query.

[1527] "Information provision" refers to the system presenting search results and other knowledge to the user.

[1528] This invention is a system that, when a user performs a search for medical information, transmits the search results to a knowledge generation platform and stores them in a knowledge database. Furthermore, it improves user satisfaction by providing information tailored to the user's emotions using an emotion engine.

[1529] Hardware and software to use

[1530] hardware

[1531] Devices (PC, smartphone, etc.)

[1532] Server (data processing and knowledge database management)

[1533] software

[1534] Knowledge generation platform (data storage and provision)

[1535] Emotion engine (recognition of user emotions)

[1536] Search engine (for searching medical information)

[1537] Program processing

[1538] 1. User search behavior

[1539] The user searches for medical information using their device. For example, the user opens a browser, enters "diabetes treatments" into the search bar, and clicks the search button.

[1540] 2. Retrieving and submitting search results

[1541] The device sends the search query to the server. Specifically, the device sends the search query "treatments for diabetes" to the server as an HTTP request.

[1542] The server processes the search query and retrieves relevant medical information. The server uses databases and external APIs to collect information about "diabetes treatments."

[1543] The server sends the retrieved search results to the knowledge generation platform. The server sends the search results to the knowledge generation platform in JSON format.

[1544] 3. Accumulation into a knowledge database

[1545] The knowledge generation platform stores the received search results in a knowledge database. The knowledge generation platform analyzes the search results and saves them to the knowledge database in an appropriate format.

[1546] 4. Providing information to other users

[1547] Another user searches for similar information. Another user uses their device to search for "diabetes treatments" again.

[1548] The server retrieves the relevant information from the knowledge database. The server sends a query to the knowledge database to retrieve information about "treatments for diabetes."

[1549] The server provides the acquired information to the user. The server sends the acquired information to the terminal, and the terminal displays that information to the user.

[1550] 5. How the Emotion Engine Works

[1551] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and input content to determine their emotions.

[1552] The emotion engine, when it senses that the user is happy, sends instructions to the knowledge generation platform to provide knowledge that matches the user's interests and preferences. When the emotion engine determines that the user is happy, it sends instructions to the knowledge generation platform to "provide information that matches the user's interests."

[1553] Specific examples and prompt statements

[1554] Specific example

[1555] User A searches for "diabetes treatments".

[1556] The server retrieves relevant medical information and sends it to the knowledge generation platform.

[1557] A knowledge generation platform stores information in a knowledge database.

[1558] When user B searches for "diabetes treatments," the server retrieves information from its knowledge database and provides it to user B.

[1559] If the emotion engine recognizes that user B is "happy," it will provide additional information tailored to user B's interests.

[1560] Example of a prompt

[1561] When a user searches for "diabetes treatments," send the search results to the knowledge generation platform and store them in the knowledge database. Then, when another user searches for similar information, retrieve the relevant information from the knowledge database and provide it to the user. Also, recognize the user's emotions and select the knowledge to provide accordingly.

[1562] This invention allows users to efficiently obtain necessary medical information and provides information tailored to their emotions. This improves user satisfaction and enhances operational efficiency.

[1563] The flow of the specific processing in Example 2 will be explained using Figure 19.

[1564] Step 1:

[1565] User search behavior

[1566] Input: The user enters the search query using the terminal.

[1567] Specific action: The user opens a browser, enters "diabetes treatments" into the search bar, and clicks the search button.

[1568] Output: The terminal sends the search query to the server.

[1569] Step 2:

[1570] Retrieving search results

[1571] Input: Search query sent from the terminal.

[1572] Specific action: The device sends the search query "treatments for diabetes" to the server as an HTTP request.

[1573] Data processing: The server analyzes the search query and collects relevant medical information from databases and external APIs.

[1574] Output: The server generates search results based on the medical information it has acquired.

[1575] Step 3:

[1576] Submit search results

[1577] Input: Search results generated by the server.

[1578] Specific operation: The server sends the search results to the knowledge generation platform in JSON format.

[1579] Output: The knowledge generation platform receives the search results.

[1580] Step 4:

[1581] Storage in a knowledge database

[1582] Input: Search results received by the knowledge generation platform.

[1583] Specific operation: The knowledge generation platform analyzes the search results and stores them in the knowledge database in an appropriate format.

[1584] Data processing: Organize search results as structured data and store it in a knowledge database.

[1585] Output: Search results stored in the knowledge database.

[1586] Step 5:

[1587] Providing information to other users

[1588] Input: A query used by another user to search for similar information.

[1589] Specific action: Another user uses the device to search for "diabetes treatments" again.

[1590] Data processing: The server sends a query to the knowledge database to retrieve information about "diabetes treatments".

[1591] Output: The server sends the acquired information to the terminal, and the terminal displays that information to the user.

[1592] Step 6:

[1593] How the emotion engine works

[1594] Input: User's emotional data (facial expressions and input content).

[1595] Specific operation: The emotion engine analyzes the user's facial expressions and input content to determine their emotions.

[1596] Data processing: If the emotion engine determines that the user is "happy," it sends an instruction to the knowledge generation platform to "provide information that matches the user's interests."

[1597] Output: The knowledge generation platform provides additional information tailored to the user's interests.

[1598] Thus, the system processes the entire process as a series of steps, starting with the user's search behavior, retrieving search results, storing them in a knowledge database, providing information to other users, and finally, using an emotion engine to recognize emotions and optimize information delivery.

[1599] (Application Example 2)

[1600] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1601] Conventional knowledge delivery systems make it difficult for users to efficiently obtain the information they need, and in particular, they fail to provide appropriate information tailored to their emotions. Furthermore, there is a lack of effective means to utilize search results related to electronic payments, thus creating a need for improved user convenience and operational efficiency.

[1602] 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.

[1603] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for selecting knowledge according to the user's emotions using an emotion recognition engine, means for searching for information related to electronic payments and storing the results in the knowledge database, and means for filtering knowledge based on the user's emotions and providing appropriate information. As a result, users can efficiently acquire the information they need and receive appropriate information according to their emotions.

[1604] "High-precision results" refer to accurate and reliable information obtained by users through searches and operations.

[1605] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[1606] A "knowledge database" is a database that stores collected information and provides it as needed.

[1607] An "ecosystem" is an integrated system environment for providing users with accumulated knowledge.

[1608] "Improving convenience" refers to increasing the ease of use and efficiency for users when using the system.

[1609] "Improving work efficiency" refers to increasing the efficiency of performing work tasks.

[1610] An "emotion recognition engine" is an engine that recognizes the user's emotions and provides appropriate information based on those emotions.

[1611] "Electronic payment" refers to payment methods that utilize the internet and electronic devices.

[1612] "Filtering" refers to selecting information based on specific criteria.

[1613] The following system configuration will be described as an embodiment for carrying out this invention.

[1614] System Configuration

[1615] hardware

[1616] server

[1617] smartphone

[1618] Emotion recognition engine (EmotionEngine)

[1619] software

[1620] Knowledge generation platform

[1621] Knowledge Database (KnowledgeDB)

[1622] Search engine API (using the requests library)

[1623] Emotion recognition software (EmotionEngine)

[1624] Program processing

[1625] server

[1626] The server stores high-precision results generated by users in a knowledge database via a knowledge generation platform. Specifically, when a user searches for information related to electronic payments, the search results are sent to the knowledge generation platform and stored in the knowledge database. In addition, an emotion recognition engine is used to recognize the user's emotions, and knowledge is filtered based on those emotions to provide appropriate information.

[1627] smartphone

[1628] The smartphone provides an interface for users to search for information related to electronic payments. Search results are sent to a knowledge generation platform and stored in a knowledge database. If the user needs the same information again, an emotion recognition engine recognizes the user's emotions and provides appropriate knowledge.

[1629] Emotion recognition engine

[1630] The emotion recognition engine analyzes the user's voice and facial expression data to recognize emotions. Based on the recognized emotions, it filters and provides appropriate information from the knowledge database.

[1631] Specific example

[1632] For example, if a user searches for information on "electronic payment security," the search results are stored in the knowledge database. When another user needs the same information, if the emotion recognition engine recognizes that the user is "happy," it will prioritize providing positive information.

[1633] Example of a prompt

[1634] Create a Python program that, when a user searches for information on "electronic payment security," saves the search results to a knowledge database and uses an emotion recognition engine to provide appropriate information when another user needs the same information.

[1635] In this way, users can efficiently acquire the information they need, and appropriate information tailored to their emotions can be provided.

[1636] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[1637] Step 1:

[1638] Users search for information about electronic payments using their smartphones.

[1639] Input: User's search query (e.g., "security for electronic payments")

[1640] Output: The search query is sent to the server.

[1641] Specific action: The user enters "electronic payment security" into the search bar on their smartphone and presses the search button.

[1642] Step 2:

[1643] The server receives the search query and sends a request to an external search engine API.

[1644] Input: User's search query

[1645] Output: Search results from the search engine API

[1646] Specific operation: The server sends a search query to the search engine API and receives the search results.

[1647] Step 3:

[1648] The server sends the received search results to the knowledge generation platform and stores them in the knowledge database.

[1649] Input: Search results from search engine API

[1650] Output: Search results stored in the knowledge database

[1651] Specific operation: The server sends the search results to the knowledge generation platform and stores them in the knowledge database.

[1652] Step 4:

[1653] Another user searches for the same information using their smartphone.

[1654] Input: Another user's search query (e.g., "security for electronic payments")

[1655] Output: The search query is sent to the server.

[1656] Specific action: Another user types "electronic payment security" into the search bar on their smartphone and presses the search button.

[1657] Step 5:

[1658] The server receives the search query and retrieves relevant information from the knowledge database.

[1659] Input: Search query from another user

[1660] Output: Related information retrieved from the knowledge database

[1661] Specific operation: The server sends a query to the knowledge database and retrieves relevant information.

[1662] Step 6:

[1663] The server uses an emotion recognition engine to recognize the emotions of another user.

[1664] Input: Voice and facial expression data from another user

[1665] Output: Recognized emotion (e.g., "happy")

[1666] Specific operation: The server sends voice and facial expression data from another user to the emotion recognition engine and recognizes their emotions.

[1667] Step 7:

[1668] The server filters information retrieved from the knowledge database based on the emotions it recognizes.

[1669] Input: Relevant information retrieved from the knowledge database, perceived emotions

[1670] Output: Filtered information

[1671] Specific operation: The server filters information retrieved from the knowledge database based on the recognized emotions.

[1672] Step 8:

[1673] The server provides filtered information to another user.

[1674] Input: Filtered information

[1675] Output: Information provided to another user

[1676] Specific operation: The server sends filtered information to another user's smartphone and displays it.

[1677] (Example 3)

[1678] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[1679] Conventional information retrieval systems struggled to quickly provide users with the information they needed, and especially when users were confused, it took a long time for them to find the right information. Furthermore, because information was not provided in a way that reflected the user's emotions, improvements in convenience and operational efficiency were not sufficiently achieved.

[1680] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1681] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for adjusting the operation of the knowledge generation platform using an emotion engine that recognizes the user's emotions, means for generating appropriate information based on the analysis results of the emotion engine, means for providing the generated information to users, and means for storing the generated information in a knowledge database. This makes it possible to quickly provide appropriate information according to the user's emotions, thereby shortening information retrieval time and improving operational efficiency.

[1682] A "user" is an individual or organization that uses the system to search for information and improve the efficiency of their work.

[1683] "High-precision results" refer to accurate and reliable information and data generated by users.

[1684] A "knowledge generation platform" is a system that processes information generated by users and stores it in a knowledge database.

[1685] A "knowledge database" is a database used to store accumulated information and data and to provide it as needed.

[1686] An "ecosystem" is an integrated system environment designed to provide users with accumulated knowledge.

[1687] "Improving convenience" means enhancing the ease of use and comfort for users when using the system.

[1688] "Improving operational efficiency" means enabling users to perform their tasks more quickly and effectively.

[1689] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's operation accordingly.

[1690] "Analysis results" refer to the results of the emotion engine's analysis of the user's emotions.

[1691] "Appropriate information" refers to the most useful and relevant information provided in accordance with the user's emotions and circumstances.

[1692] Modes for carrying out the invention

[1693] This invention is a system that stores high-precision results generated by users in a knowledge database via a knowledge generation platform, and provides the stored knowledge to users in the form of an ecosystem. Furthermore, it aims to improve convenience and operational efficiency by recognizing the user's emotions using an emotion engine and adjusting the operation of the knowledge generation platform according to those emotions.

[1694] Hardware and software to be used

[1695] The server uses a common cloud service as its knowledge generation platform. Specifically, it uses a cloud service that provides an "emotion recognition API" as its emotion engine and a cloud service that provides a "natural language processing API" as its knowledge generation platform. This makes it possible to analyze the user's emotions and generate appropriate information.

[1696] A terminal is a device that users use to access the system, and includes PCs, smartphones, and tablets. Terminals are equipped with cameras and microphones, which are used to capture the user's facial expressions and voice.

[1697] Program processing

[1698] The server receives facial and voice data from the user transmitted from the terminal and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotions. For example, if it determines that the user is confused, the server sends instructions to the knowledge generation platform to generate the information the user needs.

[1699] The generated information is provided to the user's terminal via the server. Users can then review the information provided on their terminal and proceed with their work efficiently. Furthermore, the generated information is stored in a knowledge database, allowing other users to quickly obtain similar information in the future.

[1700] Specific example

[1701] For example, if a user is confused about how to use new software, the following actions will occur:

[1702] 1. The user accesses the system through a terminal and enters "I don't know how to use the new software."

[1703] 2. The device's camera captures the user's confused facial expression and sends that data to the emotion engine.

[1704] 3. The emotion engine analyzes the user's facial expressions and determines that they are "confused."

[1705] 4. The server receives the analysis results from the emotion engine and instructs the knowledge generation platform to "generate a detailed guide on how to use the software."

[1706] 5. The knowledge generation platform generates a detailed guide and sends it to the server.

[1707] 6. The server displays the generated guide on the user's terminal.

[1708] 7. Users understand how to use the software by looking at the guide.

[1709] 8. The server stores the generated guides in a knowledge database so that other users can quickly retrieve the same information in the future.

[1710] Example of a prompt

[1711] "I'm having trouble figuring out how to use the new software. Could you please explain the specific steps?"

[1712] In this way, the system improves operational efficiency by quickly providing appropriate information that responds to the user's emotions, thereby reducing information retrieval time. The flow of specific processing in Example 3 will be explained using Figure 21.

[1713] Step 1:

[1714] The user accesses the system through their device.

[1715] Input: The user accesses the system's URL using a terminal.

[1716] Output: The system's homepage is displayed on the terminal.

[1717] Specific operation: The user opens a web browser and enters the system's URL to access it. The system's homepage is displayed, and the user is ready to begin searching for information.

[1718] Step 2:

[1719] The device sends the user's emotions to the emotion engine.

[1720] Input: The device's camera and microphone capture the user's facial expressions and voice.

[1721] Output: The captured data is sent to the emotion engine.

[1722] Specific operation: The device's camera captures the user's face, and the microphone records the user's voice. This data is sent to the emotion engine in real time.

[1723] Step 3:

[1724] The emotion engine analyzes the user's emotions.

[1725] Input: Facial expression and audio data sent from the device.

[1726] Output: Analysis results showing the user's emotions.

[1727] Specific operation: The emotion engine analyzes the received data and identifies emotions such as whether the user is confused, happy, or angry. For example, if it determines that the user is confused, the result is sent to the server.

[1728] Step 4:

[1729] The server receives the results of the emotion engine's analysis.

[1730] Input: Analysis results sent from the emotion engine.

[1731] Output: Instructions are generated based on the analysis results.

[1732] Specific operation: The server receives the analysis results sent from the emotion engine and generates instructions to provide appropriate information according to the user's emotions.

[1733] Step 5:

[1734] The server sends instructions to the knowledge generation platform.

[1735] Input: Instructions based on the analysis results of the emotion engine.

[1736] Output: Instructions to send to the knowledge generation platform.

[1737] Specific operation: If the server determines that the user is confused, it instructs the knowledge generation platform to "generate a detailed guide on how to use the software."

[1738] Step 6:

[1739] The knowledge generation platform generates the appropriate information.

[1740] Input: Instructions sent from the server.

[1741] Output: Generated information.

[1742] Specific operation: Based on the instructions, the knowledge generation platform generates detailed guides on how to use software that the user is having trouble with. For example, guides containing specific operating procedures and troubleshooting information are generated.

[1743] Step 7:

[1744] The server provides the user with the generated information.

[1745] Input: Information submitted from the knowledge generation platform.

[1746] Output: Information displayed on the user's device.

[1747] Specific operation: The server receives the generated guide and sends it to the user's terminal. The user then reviews the detailed guide on their terminal and understands how to use the software.

[1748] Step 8:

[1749] The server stores the generated information in the knowledge database.

[1750] Input: Information submitted from the knowledge generation platform.

[1751] Output: Information stored in the knowledge database.

[1752] Specific operation: The server stores the generated guides in a knowledge database so that other users can quickly retrieve the same information in the future. For example, it can be accessed by other users who are having trouble using the same software.

[1753] (Application Example 3)

[1754] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 as a "terminal".

[1755] A challenge exists in providing timely and appropriate knowledge to robots operating within factories when they encounter confusion or errors during their work. Furthermore, there is a need to efficiently store new knowledge gained during work in a knowledge database and utilize it in real time. Additionally, it is necessary to improve convenience and operational efficiency by adjusting the operation of the knowledge generation platform according to the user's emotions.

[1756] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1757] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform; means for providing the stored knowledge to users in the form of an ecosystem; means for improving convenience and operational efficiency; means for recognizing the user's emotions using an emotion engine and adjusting the operation of the knowledge generation platform according to those emotions; means for being installed on robots working in a factory and providing knowledge in real time; means for quickly providing appropriate knowledge when the robot senses confusion or an error; and means for automatically storing new knowledge acquired during work in a knowledge database. This makes it possible to significantly improve the operational efficiency within the factory.

[1758] A "user" is a person or machine that uses the system to obtain information or perform tasks.

[1759] "High-precision results" refer to accurate and reliable information and data generated by users.

[1760] A "knowledge generation platform" is a system that collects, organizes, and stores information generated by users, and provides it as needed.

[1761] A "knowledge database" is a database where information accumulated by a knowledge generation platform is stored.

[1762] An "ecosystem" is a mechanism that provides users with information accumulated in a knowledge database and facilitates the sharing of information among them.

[1763] "Improving convenience" means increasing the ease of use and efficiency for users when using the system.

[1764] "Improving operational efficiency" means enabling tasks and operations to be performed more quickly and effectively.

[1765] An "emotion engine" is an engine that recognizes the user's emotions and adjusts the system's operation accordingly.

[1766] A "robot that performs work in a factory" is a machine that automatically performs specific tasks within a factory.

[1767] "A means of providing knowledge in real time" refers to a function that provides necessary information immediately.

[1768] "A means of quickly providing appropriate knowledge when confusion or errors are detected" refers to a function that immediately provides solutions and relevant information when a robot detects a problem.

[1769] "A means of automatically accumulating new knowledge gained during work in a knowledge database" refers to a function that automatically saves new information and knowledge discovered during work to a database.

[1770] As an embodiment of this invention, a system installed in a robot performing work in a factory is described. This system stores high-precision results generated by the user in a knowledge database via a knowledge generation platform, and provides the stored knowledge to the user in the form of an ecosystem. It also recognizes the user's emotions using an emotion engine and adjusts the operation of the knowledge generation platform according to those emotions.

[1771] Hardware and software to use

[1772] Hardware: Factory robots, cameras (for emotion recognition)

[1773] Software: Python, emotion_recognition library, knowledge_db library

[1774] Data processing and data calculation

[1775] emotion recognition

[1776] The system uses a camera to capture the robot's movements and errors, and the emotion_recognition library to recognize emotions. The emotion engine detects when the robot feels confused or makes an error and sends instructions to the knowledge generation platform to provide appropriate knowledge.

[1777] Knowledge provision

[1778] Based on the emotions recognized by the emotion engine, the knowledge generation platform uses the knowledge_db library to retrieve appropriate information from the knowledge database and provide it to the robot. This allows the robot to quickly resolve confusion and errors.

[1779] Knowledge database update

[1780] New knowledge and information gained during the work process are automatically stored in the knowledge database through the knowledge generation platform. This allows for quick responses if similar problems occur in subsequent tasks.

[1781] Specific example

[1782] For example, if an error occurs while a robot is assembling part A, the emotion engine recognizes the robot's confusion and retrieves and provides information about how to assemble part A from the knowledge database. Based on this information, the robot can resolve the error and continue working.

[1783] Example of a prompt

[1784] If an error occurs while the robot is assembling part A, the emotion engine should recognize the robot's confusion and retrieve and provide information from the knowledge database regarding how to assemble part A.

[1785] In this way, it is possible to significantly improve work efficiency within the factory.

[1786] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[1787] Step 1:

[1788] The server acquires video data in real time from the factory robot's camera.

[1789] Input: Camera footage from a factory robot

[1790] Output: Video data

[1791] Specific operation: The server receives video data in streaming format from a camera mounted on a factory robot.

[1792] Step 2:

[1793] The server uses the emotion_recognition library to recognize the robot's emotions from the video data.

[1794] Input: Video data

[1795] Output: Sentiment data (e.g., confusion, error)

[1796] Specific operation: The server inputs the received video data into the emotion_recognition library and analyzes the robot's emotions from its facial expressions and movements.

[1797] Step 3:

[1798] The server sends instructions to the knowledge generation platform based on the recognized sentiment data.

[1799] Input: Sentiment data

[1800] Output: Instructions for the knowledge generation platform

[1801] Specific operation: If the sentiment data is "confused" or "error," the server sends an instruction to the knowledge generation platform to provide appropriate knowledge.

[1802] Step 4:

[1803] The knowledge generation platform uses the knowledge_db library to retrieve the appropriate information from the knowledge database.

[1804] Input: Instructions for the knowledge generation platform

[1805] Output: Appropriate knowledge information

[1806] Specific operation: The knowledge generation platform queries the knowledge database based on the instructions and retrieves relevant information.

[1807] Step 5:

[1808] The server provides the acquired knowledge information to the factory robots.

[1809] Input: Appropriate knowledge information

[1810] Output: Providing knowledge information to factory robots

[1811] Specific operation: The server sends the acquired knowledge information to the factory robot, allowing the robot to continue its work based on that information.

[1812] Step 6:

[1813] The server automatically stores new knowledge gained during the process in the knowledge database through the knowledge generation platform.

[1814] Input: New knowledge or information

[1815] Output: Storage in the Knowledge Database

[1816] Specific operation: The server sends new knowledge and information acquired by the robot during its work to the knowledge generation platform and automatically saves it to the knowledge database.

[1817] In this way, it is possible to significantly improve work efficiency within the factory.

[1818] 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.

[1819] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> 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.

[1820] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[1821] 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.

[1822] [Third Embodiment]

[1823] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1824] 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.

[1825] 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).

[1826] 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.

[1827] 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.

[1828] 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).

[1829] 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.

[1830] 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.

[1831] 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.

[1832] 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.

[1833] 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.

[1834] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[1835] "Example of form 1"

[1836] One embodiment of the present invention is a system that stores high-precision results generated by users through conventional search and chatbot usage in a knowledge database via a knowledge generation platform. Specifically, users transmit information obtained through search or chatbot usage to the knowledge generation platform, where that information is stored in the knowledge database. This knowledge database stores knowledge in various fields and provides that knowledge to users in the form of an ecosystem.

[1837] "Example of form 2"

[1838] As a concrete example, when a user searches for medical information, the search results are sent to a knowledge generation platform, where the information is stored in a knowledge database. Subsequently, when another user needs similar information, the relevant information is retrieved from the knowledge database and provided to the user. This allows users to efficiently obtain the information they need.

[1839] "Example of form 3"

[1840] Furthermore, the embodiment of the present invention is a system aimed at improving convenience and operational efficiency. Specifically, by providing information stored in a knowledge database to users at the time they need it, it shortens the time users spend searching for information and improves operational efficiency.

[1841] The following describes the processing flow for each example of the form.

[1842] "Example of form 1"

[1843] Step 1: Users generate information using traditional search and chatbot functions.

[1844] Step 2: Send the generated information to the knowledge generation platform.

[1845] Step 3: The knowledge generation platform stores the information in the knowledge database.

[1846] "Example of form 2"

[1847] Step 1: The user performs a search for medical information.

[1848] Step 2: Submit the search results to the knowledge generation platform.

[1849] Step 3: The knowledge generation platform stores the information in the knowledge database.

[1850] Step 4: If another user requires similar information, retrieve the relevant information from the knowledge database and provide it to the user.

[1851] "Example of form 3"

[1852] Step 1: The user searches for the information they need.

[1853] Step 2: Retrieve the relevant information from the knowledge database.

[1854] Step 3: Provide the acquired information to the user.

[1855] (Example 1)

[1856] Next, we will describe Embodiment 1 of 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."

[1857] Information obtained through conventional search engines and conversational agents is temporary and difficult to reuse. Furthermore, there is a lack of means to guarantee the accuracy and reliability of the information obtained, making it difficult for users to efficiently obtain highly accurate information. Moreover, there is a need for methods to improve user convenience and enhance operational efficiency by providing accumulated knowledge as an ecosystem.

[1858] 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.

[1859] In this invention, the server includes means for accumulating high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the accumulated knowledge to users in the form of an ecosystem, and means for improving convenience and operational efficiency. This makes it possible for users to efficiently accumulate and reuse high-precision information obtained using search engines and conversational agents.

[1860] A "user" is an individual or organization that uses the system to acquire information and transmits the generated results to the knowledge generation platform.

[1861] "High-precision results" refer to accurate and reliable information obtained by users using search engines or conversational agents.

[1862] A "knowledge generation platform" is a system that analyzes information submitted by users, converts it into an appropriate format, and stores it in a knowledge database.

[1863] A "knowledge database" is a database system that stores analyzed information and saves it in a format that can be reused later.

[1864] An "ecosystem" is the overall structure of a system that provides accumulated knowledge to users, enabling them to acquire information efficiently.

[1865] A "search engine" is software that searches the internet for relevant information based on keywords entered by the user and provides the results.

[1866] A "conversational agent" is software that responds to user questions in natural language, and is also known as a chatbot.

[1867] A "device" refers to a device used by a user to access search engines or conversational agents, and includes PCs, smartphones, and other similar devices.

[1868] A "server" is a computer system that operates knowledge generation platforms and knowledge databases, and performs information analysis and storage.

[1869] "Natural language processing technology" is a technique that allows computers to understand and analyze human language, and is used to understand the meaning of information and convert it into an appropriate format.

[1870] The HTTPS protocol is a communication protocol used to securely send and receive data over the internet.

[1871] This invention is a system that stores high-precision results generated by users in a knowledge database via a knowledge generation platform, and provides the stored knowledge to users in the form of an ecosystem. Specific embodiments of this system are described below.

[1872] System Configuration

[1873] hardware

[1874] Devices: PCs, smartphones, tablets, and other devices. Users access search engines and conversational agents using these devices.

[1875] Server: A computer system used to operate knowledge generation platforms and knowledge databases. It is equipped with a high-performance processor and large-capacity storage.

[1876] software

[1877] Search engine: Software that searches the internet for relevant information based on keywords entered by the user and provides the results.

[1878] Conversational agent: Software that responds to user questions in natural language. It uses generative AI models to generate appropriate answers to questions.

[1879] Knowledge generation platform: A system that analyzes information submitted by users, converts it into an appropriate format, and stores it in a knowledge database. It uses natural language processing technologies such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1880] Knowledge database: A database system that stores analyzed information and saves it in a format that can be reused later. It uses database management systems such as MySQL or PostgreSQL.

[1881] Data processing and data calculation

[1882] Information acquisition and transmission

[1883] Users use their devices to access search engines and conversational agents to obtain information. For example, a user might ask a conversational agent, "Tell me about the latest AI technologies." The conversational agent uses a generative AI model to generate an appropriate answer to the question. If the answer is deemed highly accurate, the device sends this information to a knowledge generation platform. The HTTPS protocol is used for transmission.

[1884] Information analysis and storage

[1885] The server analyzes the information received by the knowledge generation platform. This analysis uses natural language processing technologies such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding. The server understands the meaning of the information and converts it into an appropriate format. The analyzed information is stored in a knowledge database.

[1886] Reuse of information

[1887] When a user uses a search engine or conversational agent again to obtain information, the information stored in the knowledge database is reused. For example, if another user asks, "Tell me about the latest AI technologies," the conversational agent retrieves information from the knowledge database such as "It includes generative AI models and deep learning" and answers accordingly.

[1888] Examples of specific cases and prompt statements

[1889] As a concrete example, consider a scenario where a user asks a conversational agent, "Tell me about the latest AI technologies." The conversational agent replies, "The latest AI technologies include generative AI models and deep learning." If this answer is deemed highly accurate, the device sends this information to a knowledge generation platform. The server analyzes the information using the Google Cloud Natural Language API and stores it in a MySQL database. This information is then reused when other users search for "the latest AI technologies."

[1890] Examples of prompts to input into a generative AI model include the following:

[1891] "Tell me about the latest AI technology."

[1892] By entering this prompt into the interactive agent, the user can obtain highly accurate information, which is then stored in a knowledge database.

[1893] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1894] Step 1:

[1895] Users obtain information using search engines or conversational agents.

[1896] As a concrete example, the user uses their device to ask the conversational agent, "Tell me about the latest AI technology."

[1897] Input: User's question (prompt)

[1898] Output: Response from the conversational agent (response generated by the AI ​​model)

[1899] Step 2:

[1900] The device transmits the information it acquires to the knowledge generation platform.

[1901] Specifically, the device sends the response it received from the conversational agent, "The latest AI technologies include generative AI models and deep learning," to the knowledge generation platform using the HTTPS protocol.

[1902] Input: Response from the conversational agent

[1903] Output: Data to be sent to the knowledge generation platform

[1904] Step 3:

[1905] The server analyzes the information on the knowledge generation platform.

[1906] Specifically, the server uses the Google Cloud Natural Language API to analyze the information it receives, understand its meaning, and convert it into an appropriate format.

[1907] Input: Data sent to the knowledge generation platform

[1908] Output: Analyzed information (data converted to an appropriate format)

[1909] Step 4:

[1910] The server stores the analyzed information in a knowledge database.

[1911] Specifically, the server inserts the analyzed information into a MySQL database so that it can be reused later.

[1912] Input: Analyzed information

[1913] Output: Data stored in the knowledge database

[1914] Step 5:

[1915] Users reuse information from knowledge databases.

[1916] In a concrete example, if another user asks the conversational agent, "Tell me about the latest AI technologies," the conversational agent retrieves information from its knowledge database stating, "It includes generative AI models and deep learning," and then provides the answer.

[1917] Input: User's question (prompt)

[1918] Output: Information obtained from the knowledge database (response from the conversational agent)

[1919] (Application Example 1)

[1920] Next, we will describe Application Example 1 of Form 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."

[1921] Traditional factory operations have faced challenges such as difficulty in quickly obtaining necessary information from workers, leading to decreased work efficiency. Furthermore, significant time was often spent troubleshooting and determining optimal work procedures, resulting in overall reduced productivity. While automation using robots is advancing, insufficient coordination with human workers has made efficient operation difficult.

[1922] 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.

[1923] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for providing a knowledge-sharing robot assistant to improve work efficiency within the factory, means for displaying information to workers in real time via smart devices, and means for robots to transport necessary parts or automate simple tasks according to the worker's instructions. This enables workers to quickly obtain necessary information and efficiently perform troubleshooting and optimal work procedures. Furthermore, collaboration with robots is enhanced, improving overall productivity.

[1924] "Users" refer to individuals who use the system to search for information or acquire knowledge.

[1925] "High-precision results" refers to accurate and reliable information obtained through search engines or chatbots.

[1926] A "knowledge generation platform" refers to a system that collects information obtained by users and stores it in a knowledge database.

[1927] A "knowledge database" refers to a database that accumulates knowledge from various fields and provides it to users in the form of an ecosystem.

[1928] An "ecosystem" refers to a system that provides users with information accumulated in a knowledge database, allowing them to use and share that information with one another.

[1929] "Improving convenience" refers to enabling users to quickly and easily obtain the information they need.

[1930] "Improving operational efficiency" refers to increasing the efficiency of work and improving productivity.

[1931] A "knowledge-sharing robot assistant" refers to a robot that retrieves information from a knowledge database and provides it to workers in order to improve work efficiency within a factory.

[1932] A "smart device" refers to a device used to display information, such as a smartphone, smart glasses, or a head-mounted display.

[1933] "Displaying information in real time" means instantly displaying necessary information so that workers can use it on the spot.

[1934] A "robot" refers to a machine that transports necessary parts or automates simple tasks according to the instructions of a worker.

[1935] In order to implement this invention, the following system configuration and program are required.

[1936] System Configuration

[1937] 1. Hardware

[1938] Smart devices: Smartphones, smart glasses, head-mounted displays (e.g., Google Glass, Microsoft HoloLens)

[1939] Factory robots: Robots that automate the handling of parts and simple tasks (e.g., Universal Robots UR series)

[1940] Server: A server to host the knowledge generation platform and knowledge database.

[1941] 2. Software

[1942] API Server: Server software (e.g., Flask) that provides the functionality of a knowledge generation platform.

[1943] Database: Database software that functions as a knowledge database (e.g., MongoDB)

[1944] Program processing

[1945] The server executes a program that includes the following actions:

[1946] 1. Knowledge Generation Platform

[1947] Users utilize search and chatbots via their smart devices and send the highly accurate results obtained to a knowledge generation platform.

[1948] The knowledge generation platform stores the received information in a knowledge database.

[1949] 2. Knowledge DB

[1950] The knowledge database accumulates knowledge from various fields and provides it to users in the form of an ecosystem.

[1951] When a user requests the information they need, the system retrieves the most relevant information from the knowledge database and displays it on their smart device in real time.

[1952] 3. Knowledge-sharing robot assistant

[1953] To improve work efficiency within the factory, information is retrieved from the knowledge database and provided to workers.

[1954] The robots transport necessary parts according to the worker's instructions and automate simple tasks.

[1955] Specific example

[1956] For example, when a worker searches for "optimal welding techniques," the knowledge generation platform stores that information in the knowledge database. Then, when another worker needs the same information, the information on "optimal welding techniques" is retrieved from the knowledge database and displayed in real time on smart glasses.

[1957] Furthermore, if troubleshooting is required, a worker can search for "Solution for Error Code 123," and the solution will be retrieved from the knowledge database and displayed on the head-mounted display. In addition, the robot will transport the necessary parts according to the worker's instructions, automating the work.

[1958] Example of a prompt

[1959] "Please tell me the optimal welding technique."

[1960] "Please tell me how to resolve error code 123."

[1961] This allows workers to quickly obtain necessary information and efficiently perform troubleshooting and optimal work procedures. Furthermore, it enhances collaboration with robots, improving overall productivity.

[1962] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1963] Step 1:

[1964] Users input information using smart devices via search queries or chatbots. The entered queries are sent to a knowledge generation platform. The input here is text data related to the information the user wants to know or the problem they want to solve. The output is the query data sent to the knowledge generation platform.

[1965] Step 2:

[1966] The server processes query data received through the knowledge generation platform and generates relevant high-accuracy results. This process uses a generative AI model to produce the best possible answers to queries. The input is the query data submitted by the user, and the output is the generated high-accuracy results.

[1967] Step 3:

[1968] The server stores the generated high-precision results in a knowledge database. The input here is the generated high-precision results, and the output is the data stored in the knowledge database. Data processing involves converting the result data into an appropriate format and saving it to the database.

[1969] Step 4:

[1970] If the user needs the information again, they send a request to the knowledge database via their smart device. The input is the request data about the information the user wants to know, and the output is the request data sent to the knowledge database.

[1971] Step 5:

[1972] The server retrieves information corresponding to the request from the knowledge database. The input is the request data from the user, and the output is the relevant information retrieved from the knowledge database. In terms of data calculation, the database is searched based on the request, and the most relevant information is extracted.

[1973] Step 6:

[1974] The server transmits the acquired information to the smart device and displays it to the user in real time. The input is information retrieved from the knowledge database, and the output is the information displayed on the smart device. Specifically, the server converts the information into an appropriate format and displays it on the smart device's screen.

[1975] Step 7:

[1976] When a user gives instructions to a robot, they send those instructions to the robot via a smart device. The input is the instruction data from the user, and the output is the instruction data sent to the robot.

[1977] Step 8:

[1978] The robot transports necessary parts or automates simple tasks based on received instructions. The input is instruction data from the user, and the output is the result of the performed work. Specifically, the robot operates according to the instructions and performs the specified task.

[1979] This allows users to quickly obtain the information they need and efficiently perform troubleshooting and optimal work procedures. Furthermore, it enhances collaboration with robots, improving overall productivity.

[1980] (Example 2)

[1981] Next, we will describe Example 2 of the morphological example. 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."

[1982] Conventional medical information retrieval systems made it difficult for users to efficiently obtain the information they needed. Furthermore, when multiple users searched for the same information, they had to repeat the same search process each time, which was time-consuming and labor-intensive. In addition, there was a lack of effective means to utilize accumulated knowledge, creating a need for improved convenience and operational efficiency.

[1983] 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.

[1984] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to users in the form of an ecosystem, means for improving convenience and operational efficiency, means for users to search for medical information and transmit the search results to the knowledge generation platform, and means for retrieving relevant information from the knowledge database and providing it to other users when they require similar information. As a result, users can efficiently obtain the medical information they need, and the time and effort required when multiple users search for the same information can be reduced. Furthermore, by effectively utilizing the stored knowledge, convenience and operational efficiency can be improved.

[1985] A "user" is an individual or organization that uses the system to search for medical information.

[1986] "High-precision results" refer to accurate and reliable information obtained by users when they perform a search.

[1987] A "knowledge generation platform" is a system for processing search results and storing them in a knowledge database.

[1988] A "knowledge database" is a database system used to store and manage accumulated medical information and other knowledge.

[1989] An "ecosystem" is the overall environment of a system that provides accumulated knowledge to users and facilitates its mutual use.

[1990] "Improving convenience" refers to enabling users to quickly and easily obtain the information they need.

[1991] "Improving operational efficiency" refers to increasing the efficiency of work through the use of a system, thereby reducing time and effort.

[1992] "Medical information" refers to all information related to healthcare, such as disease treatments, symptoms, and medication information.

[1993] "Search results" refer to a list of information obtained when a user performs a search.

[1994] "Sending" refers to the act of sending data from a device to a server.

[1995] "Acquisition" refers to the act of a server retrieving necessary information from a knowledge database.

[1996] "Providing" refers to the act of displaying information acquired by the server to the user.

[1997] This invention is a system for users to efficiently acquire medical information. Specific embodiments of this system are described below.

[1998] System Configuration

[1999] This system mainly consists of the following components:

[2000] User's device (PC, smartphone, etc.)

[2001] server

[2002] Knowledge generation platform

[2003] Knowledge Database

[2004] Hardware and software to use

[2005] Device: A device such as a PC or smartphone. A web browser (e.g., Google Chrome, Mozilla Firefox) is used to perform the search.

[2006] Server: Receives and processes search queries. Uses a web server (e.g., Apache HTTP Server, Nginx) and a database management system (e.g., MySQL, PostgreSQL).

[2007] Knowledge generation platform: Processes search results and stores them in a knowledge database. Uses a data streaming platform (e.g., Apache Kafka).

[2008] Knowledge database: Stores and manages accumulated medical information. Uses a database management system (e.g., MySQL, PostgreSQL).

[2009] System operation

[2010] 1. Users search for medical information.

[2011] Users open a web browser on their PC or smartphone and access search engines or dedicated medical information search sites.

[2012] Enter keywords such as "diabetes treatments" into the search box and click the search button.

[2013] 2. The device sends the search results to the server.

[2014] The terminal sends the generated search query to the server as an HTTP request.

[2015] Example: The device sends the request "GET / search?q=diabetes treatment HTTP / 1.1" to the server.

[2016] 3. The server processes the data on the knowledge generation platform.

[2017] The server analyzes the received search queries and collects relevant medical information.

[2018] The server sends the collected information to the knowledge generation platform.

[2019] Example: A server collects information about "diabetes treatments" and sends it to a knowledge generation platform.

[2020] 4. The server stores data in the knowledge database.

[2021] The knowledge generation platform stores the received information in a knowledge database.

[2022] Example: Information about "treatments for diabetes" is stored in a knowledge database.

[2023] 5. Another user searches for similar information.

[2024] Another user similarly uses a PC or smartphone to search for medical information.

[2025] Enter "diabetes treatments" into the search box and click the search button.

[2026] 6. The server retrieves the relevant information from the knowledge database and provides it to the user.

[2027] The server searches for and retrieves the relevant information from the knowledge database.

[2028] The server sends the retrieved information to the user's terminal as an HTTP response.

[2029] Example: The server retrieves information about "treatments for diabetes" from a knowledge database and displays it to the user.

[2030] Examples of specific cases and prompt statements

[2031] Specific example

[2032] User A searches for "treatments for high blood pressure," and the results are saved in the knowledge database.

[2033] When user B later searches for "treatments for high blood pressure," information is retrieved from the knowledge database and provided to user B.

[2034] Example of a prompt

[2035] "Please provide me with the latest information on treatments for high blood pressure."

[2036] "Please provide detailed information regarding diabetes treatment options."

[2037] This system allows users to efficiently obtain necessary medical information. It also reduces the time and effort required for multiple users to search for the same information. By effectively utilizing accumulated knowledge, convenience and operational efficiency can be improved.

[2038] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2039] Step 1:

[2040] Users search for medical information.

[2041] Input: The user uses a PC or smartphone, opens a web browser, and accesses a search engine or a dedicated medical information search site. They enter keywords such as "diabetes treatment" into the search box and click the search button.

[2042] Data processing: Search queries are generated.

[2043] Output: The generated search query is retained on the terminal.

[2044] Specific operation: When a user enters "diabetes treatments" and clicks the search button, a search query is generated.

[2045] Step 2:

[2046] The device sends the search results to the server.

[2047] Input: The generated search query.

[2048] Data processing: The terminal sends the search query to the server as an HTTP request.

[2049] Output: The server receives the search query.

[2050] Specific action: The terminal sends a request to the server: "GET / search?q=diabetes treatment HTTP / 1.1".

[2051] Step 3:

[2052] The server processes the data on the knowledge generation platform.

[2053] Input: The search query received by the server.

[2054] Data processing: The server analyzes search queries and collects relevant medical information. The collected information is then sent to the knowledge generation platform.

[2055] Output: The knowledge generation platform receives the information.

[2056] Specific operation: The server collects information on "diabetes treatments" and sends it to the knowledge generation platform.

[2057] Step 4:

[2058] The server stores data in a knowledge database.

[2059] Input: Information received by the knowledge generation platform.

[2060] Data processing: The knowledge generation platform stores the received information in a knowledge database.

[2061] Output: Information is stored in the knowledge database.

[2062] Specific action: Information about "treatments for diabetes" is stored in the knowledge database.

[2063] Step 5:

[2064] Another user searches for similar information

[2065] Input: Another user uses a PC or smartphone, opens a web browser, and accesses a search engine or a dedicated medical information search site. They enter "diabetes treatments" into the search box and click the search button.

[2066] Data processing: Search queries are generated.

[2067] Output: The generated search query is retained on the terminal.

[2068] Specific operation: When another user types "diabetes treatments" and clicks the search button, a search query is generated.

[2069] Step 6:

[2070] The server retrieves the relevant information from the knowledge database and provides it to the user.

[2071] Input: The search query received by the server.

[2072] Data processing: The server searches for and retrieves the relevant information from the knowledge database. The retrieved information is then sent to the user's terminal as an HTTP response.

[2073] Output: Information is displayed on the user's terminal.

[2074] Specific operation: The server retrieves information about "diabetes treatments" from the knowledge database and displays it to the user.

[2075] (Application Example 2)

[2076] Next, we will describe application example 2 of form 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."

[2077] In modern brick-and-mortar stores, there is a challenge in that it is difficult for customers to efficiently obtain product information. In particular, if a customer wants to know detailed information or stock status about a specific product, they have to ask a store employee, which is time-consuming and troublesome. Furthermore, if multiple customers request the same information, duplicate information retrieval occurs, which is inefficient. In addition, traditional search systems and chatbots have difficulty providing information in real time, which reduces customer convenience.

[2078] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing high-precision results generated by the user in a knowledge database via a knowledge generation platform, means for providing the stored knowledge to the user in the form of an ecosystem, means for improving convenience and operational efficiency, and means for providing product information in real time using smart devices in physical stores. As a result, users can improve their shopping experience in physical stores and quickly and efficiently obtain the necessary product information.

[2079] A "user" is an individual or organization that uses the system to search for and retrieve information.

[2080] "High-precision results" refer to search results that provide accurate and relevant information for the user's search query.

[2081] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[2082] A "knowledge database" is a database that stores collected information and provides it to users as needed.

[2083] An "ecosystem" is an integrated system environment for providing users with information accumulated in a knowledge database.

[2084] "Improving convenience" refers to enabling users to quickly and efficiently obtain the information they need.

[2085] "Improving operational efficiency" refers to preventing duplicate information acquisition and increasing the overall efficiency of the system.

[2086] A "physical store" is a store that sells goods in a physical location.

[2087] A "smart device" is an electronic device that is connected to the internet and can display and operate information.

[2088] "Real-time" refers to the immediate acquisition and provision of information.

[2089] This invention is a system that provides product information in real time using smart devices in physical stores. A specific embodiment of this system is described below.

[2090] System Configuration

[2091] The system consists of the following main components:

[2092] 1. Knowledge Generation Platform: Collects high-precision results generated by users and stores them in a knowledge database.

[2093] 2. Knowledge Database: Stores accumulated information and provides it as needed.

[2094] 3. Smart devices: Devices used by customers in physical stores (e.g., smart glasses).

[2095] 4. Ecosystem: An integrated system that provides users with information accumulated in a knowledge database.

[2096] Program processing

[2097] The server stores the high-precision results generated by users in a knowledge database via the knowledge generation platform. Specifically, when a user searches for product information using a smart device, the search results are sent to the knowledge generation platform. The knowledge generation platform analyzes the search results and stores them in the knowledge database.

[2098] Next, if another user needs information about the same product, they can access the knowledge database via their smart device and retrieve the relevant information. The retrieved information is displayed in real time on the smart device's screen.

[2099] Hardware and software to use

[2100] Hardware: Smart glasses, servers

[2101] Software: Knowledge generation platform, knowledge database, API

[2102] Specific example

[2103] For example, suppose a user is looking for "medical masks" in a physical store. When the user, wearing smart glasses, searches for "medical masks" by voice, detailed information and stock availability of medical masks will be displayed on the smart glasses' screen. This information is retrieved in real time from a knowledge database.

[2104] Example of a prompt

[2105] "Please search for information on medical masks."

[2106] "Please retrieve information on medical masks from the knowledge database."

[2107] "Please display information about medical masks on smart glasses."

[2108] In this way, users can improve their in-store shopping experience and obtain necessary product information quickly and efficiently.

[2109] The flow of the specific processing in Application Example 2 will be explained using Figure 14.

[2110] Step 1:

[2111] A user searches for product information using a smart device (e.g., smart glasses). The user enters the search query via voice input or touch operation. The entered query is sent from the smart device to the server. The input data is the search query, and the output data is the search request sent to the server.

[2112] Step 2:

[2113] The server sends the received search query to the knowledge generation platform. The knowledge generation platform analyzes the search query and generates relevant high-accuracy results. The input data is the search query, and the output data is the high-accuracy results. Specifically, the knowledge generation platform analyzes the search query and retrieves relevant information from the database.

[2114] Step 3:

[2115] The knowledge generation platform stores the high-precision results it generates in a knowledge database. The input data consists of the high-precision results, while the output data is the information stored in the knowledge database. Specifically, the knowledge generation platform writes the high-precision results to the database.

[2116] Step 4:

[2117] When another user searches for information about the same product, they use their smart device to re-enter the search query. The entered query is sent from the smart device to the server. The input data is the search query, and the output data is the search request sent to the server.

[2118] Step 5:

[2119] The server accesses the knowledge database and retrieves the relevant information. The input data is a search query, and the output data is the information retrieved from the knowledge database. Specifically, the server sends a query to the knowledge database and retrieves the relevant information.

[2120] Step 6:

[2121] The server sends the acquired information to the smart device. The input data is information retrieved from the knowledge database, and the output data is the information sent to the smart device. Specifically, the server transfers the acquired information to the smart device.

[2122] Step 7:

[2123] A smart device displays received information to the user. Input data is information sent from the server, and output data is information displayed on the smart device's screen. Specifically, the smart device displays the received information on its screen.

[2124] In this way, users can improve their in-store shopping experience and obtain necessary product information quickly and efficiently.

[2125] (Example 3)

[2126] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[2127] Conventional information retrieval systems often made it difficult for users to quickly obtain the information they needed, resulting in time-consuming information searches. Furthermore, search results frequently did not match user needs, hindering improvements in operational efficiency. Additionally, conventional systems lacked effective means of utilizing accumulated knowledge, making knowledge reuse difficult.

[2128] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[2129] In this invention, the server includes means for storing high-precision results generated by users in a knowledge database via a knowledge generation platform; means for providing the stored knowledge to users in the form of an ecosystem; means for receiving and analyzing queries sent by users from terminals; means for searching for relevant information from the knowledge database based on the analyzed queries; means for inputting the search results as prompt sentences into a generation AI model to generate appropriate answers; and means for providing the generated answers to users. As a result, users can quickly obtain the information they need, reduce information retrieval time, and improve work efficiency.

[2130] A "user" is an individual or organization that uses the system to search for information and obtain the necessary data.

[2131] "High-precision results" refer to search results that provide accurate and appropriate information in response to the user's query.

[2132] A "knowledge generation platform" is a system for collecting information generated by users and storing it in a knowledge database.

[2133] A "knowledge database" is a database that stores accumulated information and knowledge, and allows it to be searched and retrieved as needed.

[2134] An "ecosystem" is the overall structure of a system that provides users with accumulated knowledge and promotes the reuse and sharing of information.

[2135] A "terminal" is a device (e.g., a personal computer or smartphone) used by a user to input queries and communicate with a server.

[2136] A "query" is a question or request that a user enters into a system to search for information.

[2137] A "server" is a computer system that receives and analyzes queries, retrieves information from a knowledge database, and generates answers using a generative AI model.

[2138] A "generative AI model" is an artificial intelligence model that generates appropriate responses in natural language based on input prompt sentences.

[2139] A "prompt sentence" is an instruction given to a generative AI model, and it is the sentence that forms the basis for the model to generate an appropriate response.

[2140] Modes for carrying out the invention

[2141] This invention is a system for quickly obtaining information that users need and improving work efficiency. Specific embodiments of this system are described below.

[2142] System Configuration

[2143] hardware

[2144] Server: High-performance server (e.g., general-purpose server)

[2145] Device: The device used by the user (e.g., personal computer, smartphone)

[2146] software

[2147] Database management system: Software for managing knowledge databases (e.g., MySQL)

[2148] Generative AI models: Artificial intelligence models that perform natural language processing (e.g., general-purpose generative AI models)

[2149] Program processing

[2150] The server receives and parses queries sent from the terminal. Based on the parsed queries, the server searches for relevant information in its knowledge database. The search results are input as prompts into a generative AI model, which generates appropriate answers. The generated answers are sent from the server to the terminal and provided to the user.

[2151] Specific example

[2152] For example, consider a case where a user enters the query, "Tell me about the latest project management tools."

[2153] 1. Query Reception: The user sends a query from their terminal saying, "Tell me about the latest project management tools."

[2154] 2. Q...

Claims

1. A server that receives queries sent from a user terminal, Equipped with a knowledge database, The aforementioned server, The query sent from the user terminal is analyzed using natural language processing technology. Based on the analyzed query, relevant information is retrieved from the knowledge database. The prompt sentence containing the analyzed query and the retrieved related information is input to the AI ​​model to generate a response. The generated response is provided to the user terminal. The responses generated by the aforementioned AI model are stored in the knowledge database as high-precision results. The information stored in the aforementioned knowledge database is reused to generate answers to queries from other users. system.

2. The system according to claim 1, wherein the server retrieves knowledge relating to multiple different domains as related information from the knowledge database.

Images