system

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting relevant information from corporate documents, FAQs, and databases; means for inputting the information collected by the server to a generating AI; means for generating an answer to the query based on the information input by the generating AI; means for returning the answer generated by the generating AI to the server; means for transmitting the answer received by the server from the generating AI to the terminals; and means for displaying the answer received by the terminals to the users.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When responding to inquiries within a company, there are the following challenges. General inquiries and rare consultations often cannot be answered immediately, taking time and effort. Also, useful information that employees are unaware of may end up going unused. These issues reduce work efficiency and hinder productivity improvements. [Means for solving the problem]

[0005] To solve the above problems, the following means are provided. First, a means is provided for users to input and send inquiries from a terminal. Next, the terminal has a means for sending the inquiry content to a server. The server has a means for collecting relevant information from internal documents, FAQs, knowledge bases, etc., and a means for inputting the collected information into a generation AI. The generation AI has a means for generating an answer to the inquiry based on the input information, and also includes a means for returning the answer from the generation AI to the server. The server has a means for sending the answer received from the generation AI to the terminal, and provides a means for the terminal to display the received answer to the user. In addition, by including a means for the server to push useful information to the user based on the judgment of the generation AI, a system is constructed that provides timely and effective information. This system is expected to realize faster inquiry responses and more effective use of information, thereby improving business efficiency and productivity.

[0006] "Users" are the staff and employees within a company who use the system to make inquiries.

[0007] A "terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0008] A "server" is a computer system installed within a company or in the cloud that receives inquiries and provides the data necessary for the generation AI.

[0009] An "inquiry" is a question or inquiry that a user sends to the system via a terminal, requesting information or help regarding a business.

[0010] "Generative AI" refers to an artificial intelligence model that generates answers to user inquiries based on data within a company.

[0011] "In-house documents" refer to documents such as manuals, reports, and procedure manuals that are managed within a company.

[0012] A "FAQ" is a collection of frequently asked questions and their answers.

[0013] A "knowledge base" is an information resource that accumulates knowledge, know-how, past case studies, etc. within a company.

[0014] "Means of collecting information" refers to the functions and technologies that allow the server to search for and extract the necessary information from documents and knowledge bases within the company.

[0015] "Input means" refers to the functions and processes for inputting collected data into the generative AI.

[0016] "Means for generating answers" refers to the functions and algorithms that enable the generation AI to create appropriate answers to user inquiries based on the data provided.

[0017] "Push notification" refers to a notification system in which a generating AI or server automatically sends information to users. [Brief explanation of the drawings]

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

[0019] 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.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0039] The present invention is a system for quickly responding to inquiries within a company, and uses generative AI technology. The present invention is specifically implemented through the following processing steps.

[0040] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[0041] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[0042] The server analyzes the content of the received inquiry and collects related information from the company's internal documents, FAQs, knowledge base, etc. For example, if the keyword "expense report" is included, the server searches for related documents using a full-text search engine.

[0043] Next, the server inputs the collected information into the generative AI. Specifically, the collected data is converted into a format that the generative AI model can process. This generative AI model uses natural language processing technology.

[0044] The generative AI generates answers to user inquiries based on the input information. For example, in response to an inquiry such as "Please tell me the format of an expense report," the generative AI uses past examples and templates to create an answer such as "The format of an expense report is as follows..."

[0045] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[0046] Furthermore, the server will push necessary information to the user based on the judgment of the generation AI, allowing relevant new and updated information to be provided to the user in a timely manner.

[0047] A specific example is given below.

[0048] Example 1: Inquiry about expense report format

[0049] 1. User: What is the format for expense reports?

[0050] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[0051] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[0052] 4. Server: Extract documents with highly similar titles and content and input them into the generation AI.

[0053] 5. Generative AI: Generate answers such as, "The expense report format is as follows..."

[0054] 6. Generative AI: Returns the generated answer to the server.

[0055] 7. Server: Sends the answer as a response to the terminal and displays it to the user.

[0056] The system of the present invention allows users to receive prompt and appropriate answers. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[0060] Step 2:

[0061] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[0062] Step 3:

[0063] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[0064] Step 4:

[0065] The server collects relevant information from company documents, FAQs, and knowledge bases. The server uses a search engine to search for information that matches the query and extracts relevant documents and data.

[0066] Step 5:

[0067] The server prepares the collected information for input to the generative AI. Specifically, it converts the extracted data into an input format for the generative AI model and performs the necessary preprocessing.

[0068] Step 6:

[0069] The server inputs data into the generative AI. The server then inputs the preprocessed data into the generative AI model and requests it to generate an answer to the query.

[0070] Step 7:

[0071] Generative AI generates answers to queries based on input data. It uses natural language processing algorithms to generate answers that are context-appropriate.

[0072] Step 8:

[0073] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[0074] Step 9:

[0075] The server receives the generated answer and sends it to the user's device. Specifically, the server returns the answer from the generation AI to the user's device as an HTTP response.

[0076] Step 10:

[0077] The terminal displays the received answer to the user. The terminal analyzes the received answer, processes it for display on the user interface, and displays the answer to the user.

[0078] Step 11:

[0079] The server will send useful information to the user via push notification based on the AI's judgment. If the AI ​​detects relevant information, it will send that information to the user as a push notification. Specifically, the server will use a push notification service to send the notification.

[0080] The above steps realize a system that allows for quick and efficient response to inquiries within a company.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] Conventional inquiry response systems have had the problem of making it difficult for users to quickly obtain useful information from corporate documents, FAQs, and databases. Furthermore, previous systems lacked the accuracy and efficiency to generate appropriate answers based on the information obtained. Furthermore, it was difficult to provide users with the necessary information in a timely manner.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes: a means for a user to input and send a query from a terminal; a means for the terminal to send the query content to the server; a means for the server to collect related information from internal documents, FAQs, and databases; a means for the server to search the query content using a full-text search engine; a means for inputting the search results into a generative AI model; a means for the generative AI to generate an answer to the query based on the input information; a means for returning the answer generated by the generative AI to the server; a means for the server to send the answer received from the generative AI to the terminal; and a means for displaying the answer received by the terminal to the user. This allows users to receive prompt and appropriate answers, which is expected to improve business efficiency and productivity. It also makes it possible to provide related new and updated information in a timely manner.

[0086] A "user" is an entity that operates a terminal and makes inquiries to the system.

[0087] A "terminal" is a device through which a user enters input and sends queries to a server.

[0088] A "server" is a central processing unit that receives queries sent from terminals and collects and processes related information.

[0089] "In-house documents" refer to documents and materials managed internally by a company, and are used to provide information related to inquiries.

[0090] "FAQ" is a database of frequently asked questions and their answers.

[0091] A "database" is a system for storing structured information and quickly searching and retrieving required data.

[0092] A "full-text search engine" is software that quickly searches for text containing specific keywords and extracts related documents.

[0093] "Generative AI" is an artificial intelligence model that performs natural language processing based on collected information to generate answers to user inquiries.

[0094] The "JSON format" is a standard data description format used to store and transfer data in a structured manner.

[0095] "API Endpoint" refers to the URL or URI used to access a particular function of the system.

[0096] This invention is a system for quickly and accurately responding to inquiries within a company, and uses generative AI technology. This system is based on a series of steps in which a user inputs an inquiry from a terminal, and the content of the inquiry is sent to a server.

[0097] First, the user uses their own device to access the company's dedicated inquiry form. The user enters the inquiry details into the form and presses the "Submit" button. This action causes the device to convert the inquiry details into JSON format and send an HTTP POST request to the API endpoint / ask.

[0098] Next, the server receives this request and analyzes the request body. Based on the analyzed query, the server collects the necessary information from the company's internal documents, FAQ databases, and other relevant sources. During this process, the server uses a full-text search engine (e.g., Elasticsearch) to search for relevant documents based on the keywords contained in the query.

[0099] As a search result, the server extracts documents with a high degree of match in terms of title and content. The extracted information is converted into a format that can be processed by a generative AI model (e.g., OpenAI's GPT-3). The server then inputs the converted data into the generative AI.

[0100] The generation AI generates an answer to the user's inquiry based on the input information. The generated answer is returned to the server, which then sends it as a response to the user's device. Finally, the device displays the received answer to the user, completing the response to the inquiry.

[0101] Furthermore, the server can also push necessary information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[0102] As a specific example, let us consider the process when a user inquires, "Please tell me the format of the expense report."

[0103] 1. The user asks, "What is the format for an expense report?"

[0104] 2. The device sends an HTTP POST request to the API endpoint / ask, with the request body containing "What is the expense report format?"

[0105] 3. The server receives and analyzes the request. It searches for the keyword "expense report" in a full-text search engine and collects related documents.

[0106] 4. The server extracts documents with highly consistent titles and content from the collected materials and inputs them into the generative AI model.

[0107] 5. The generative AI generates an answer such as, "The expense report format is as follows..."

[0108] 6. The generation AI returns the generated answer to the server.

[0109] 7. The server sends the response to the terminal and displays it to the user.

[0110] As a result, the system of the present invention can provide users with prompt and appropriate answers, which is expected to improve business efficiency and productivity in companies.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] A user inputs and sends an inquiry from a terminal. The user inputs a question such as "Please tell me the format for expense reports" into the inquiry form on the terminal and presses the "Send" button. This operation converts the input inquiry into JSON format. The input is the inquiry, and the output is JSON format data.

[0114] Step 2:

[0115] The terminal sends the query content to the server. The terminal then converts the query content into JSON format and sends it as an HTTP POST request to the API endpoint / ask. The input is the query content in JSON format, and the output is an HTTP POST request.

[0116] Step 3:

[0117] The server receives and analyzes the HTTP POST request. The server analyzes the received request body and extracts the query content. The input is the HTTP POST request body, and the output is the analyzed query content.

[0118] Step 4:

[0119] The server collects relevant information from internal documents, FAQs, and databases. Based on the query, the server uses a full-text search engine to search internal documents, FAQs, and databases. The input is the query and the full-text search engine, and the output is a list of related documents.

[0120] Step 5:

[0121] The server collects information using a full-text search engine. The server searches for the keyword "expense report" in a full-text search engine such as Elasticsearch and extracts relevant documents from within the company. The input is the databases that have been searched so far and the keywords in the query, and the output is the relevant documents as search results.

[0122] Step 6:

[0123] The server inputs the collected information into the generative AI model. The server converts the extracted related documents into a format that can be processed by the generative AI model (e.g., OpenAI's GPT-3). The converted data is input to the generative AI model as a prompt sentence. The input is the related documents, and the output is the prompt sentence that is input to the generative AI.

[0124] Step 7:

[0125] The generation AI generates an answer to the query based on the input information. The generation AI analyzes the prompt sentence and generates an appropriate answer to the user's query. The input is the prompt sentence, and the output is the generated answer text.

[0126] Step 8:

[0127] The generation AI returns the generated answer to the server. The generation AI returns the created answer text to the server. The input is the generated answer text, and the output is the answer text returned to the server.

[0128] Step 9:

[0129] The server sends the answer received from the generation AI to the terminal. The server sends the received answer text to the user's terminal as an HTTP response. The input is the answer text from the generation AI, and the output is the HTTP response sent to the user's terminal.

[0130] Step 10:

[0131] The terminal displays the received answer to the user. The terminal displays the received answer text in the inquiry form so that the user can view it. The input is the answer text as an HTTP response, and the output is the answer displayed on the user's terminal.

[0132] Step 11:

[0133] The server pushes necessary information to the user based on the judgment of the generation AI. The server delivers relevant information and updated information provided by the generation AI to the user in a timely manner. The input is information based on the judgment of the generation AI, and the output is the information that is pushed to the user.

[0134] (Application example 1)

[0135] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0136] Work management in factories is required to be efficient and fast, but in many factories, it is still managed manually. This results in the problem of time-consuming confirmation of work procedures and obtaining parts lists, which leads to reduced productivity. In addition, delays in obtaining necessary information can lead to work delays and incorrect instructions, reducing overall efficiency.

[0137] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0138] In this invention, the server includes a means for collecting relevant information from the factory management system and database, a means for inputting the collected information into the generation AI, and a means for the generation AI to generate answers to inquiries based on the input information. This allows for quick and accurate answers to user inquiries, resulting in efficient work management within the factory and improved productivity.

[0139] "User" refers to a worker who performs work in a factory.

[0140] "Device" refers to the input and display device used by the user, such as a tablet device or smart glasses.

[0141] An "inquiry" refers to a question or request made by a user via a terminal seeking information related to a business.

[0142] "Server" refers to a central processing unit that receives the inquiry, performs the necessary processing, and inputs the relevant information into the generation AI.

[0143] A "factory management system" refers to a system that manages work stages, parts lists, inventory information, etc. within a factory.

[0144] "Database" refers to a data storage system for storing factory management systems and related information.

[0145] "Related information" refers to data such as factory information, work procedures, and parts lists that are necessary to respond to user inquiries.

[0146] "Generative AI" refers to artificial intelligence that automatically generates answers to user inquiries based on collected information.

[0147] "Natural language processing algorithm" refers to the technology that enables generative AI to analyze text data and generate appropriate answers.

[0148] "Push notification" refers to the function of sending information from a server to a user device in real time.

[0149] A system for implementing this invention is configured as follows: A user can make an inquiry using a tablet terminal or smart glasses. For example, the user can input, "Please tell me the parts list for the next work stage." The inquiry is sent to the server by the terminal.

[0150] When the server receives the query, it collects relevant information from the factory management system and database. The collected information is then input into the generative AI, which uses natural language processing algorithms to analyze the received information and generate an appropriate response. For example, the generated response might be, "The parts list for the next stage is as follows..."

[0151] The answer generated by the AI ​​is returned to the server, which then sends it to the user's device. The device then displays the received answer to the user, allowing the user to quickly and accurately obtain the information they need.

[0152] This system uses the following hardware and software:

[0153] Hardware: Tablets, smart glasses, servers, devices with access to factory management systems

[0154] Software: Backend servers that process API requests (e.g., Python, Node.js), generative AI models (e.g., OpenAI GPT-4), factory management systems (e.g., ERP systems), full-text search engines (e.g., Solr, Elasticsearch)

[0155] Data processing and calculation involves analyzing the inquiry, collecting related information, inputting the collected information into the generation AI, and sending the generated answer to the user's device. For example, the server side receives an API request, obtains information from a factory management system or database, and inputs it into the generative AI model. The generated answer is then sent to the user's device, where the user can view it.

[0156] As a specific example, the following prompt sentence could be input to a generative AI model:

[0157] Example prompt sentence:

[0158] "Please tell me the parts list for the next stage of work."

[0159] "Please tell me the parts list. The parts needed for the next stage are "Part A, Part B.""

[0160] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0161] Step 1:

[0162] The user inputs an inquiry using a tablet device or smart glasses. Specifically, for example, the user inputs something like "Please tell me the parts list for the next work stage" and presses the send button. The input data is the user's inquiry.

[0163] Step 2:

[0164] The terminal sends the query entered by the user to the server as an API request. Specifically, the terminal generates an HTTP POST request and includes the query in the request body. The input data is the query, and the output data is the HTTP request.

[0165] Step 3:

[0166] The server analyzes the received API request. Specifically, it extracts the query content from the HTTP request body. The input data is the API request body, and the output data is the extracted query content.

[0167] Step 4:

[0168] The server collects relevant information from the factory management system and database. Specifically, it executes a database query based on the query content to obtain the required information (e.g., a list of parts required for the next work stage). The input data is the extracted query content, and the output data is the collected relevant information.

[0169] Step 5:

[0170] The server inputs the collected information into the generative AI model. Specifically, it converts the collected information into a format that the generative AI can understand (e.g., prompt text) and inputs it. The input data is the collected relevant information, and the output data is the data input to the generative AI.

[0171] Step 6:

[0172] A generative AI model generates answers to queries based on input information. Specifically, it uses natural language processing algorithms to generate text that appropriately answers the user's query. The input data is the data entered into the generative AI, and the output data is the generated answer.

[0173] Step 7:

[0174] The server receives the answer generated by the generation AI and sends it to the user's device. Specifically, it returns the generated answer to the user's device as an HTTP response. The input data is the generated answer, and the output data is the HTTP response.

[0175] Step 8:

[0176] The terminal displays the received response to the user. Specifically, the response is displayed on the terminal's display. The input data is the HTTP response, and the output data is the response displayed to the user.

[0177] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0178] The present invention is a system for quickly responding to inquiries within a company, which combines generative AI technology with an emotion engine that recognizes user emotions. The present invention is specifically implemented through the following processing steps.

[0179] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[0180] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[0181] The server analyzes the received inquiry and collects related information from the company's internal documents, FAQs, knowledge base, etc. The server uses a search engine to search for information that matches the inquiry and extracts relevant documents and data.

[0182] The server then uses an emotion engine to recognize the user's emotion from the query. The emotion engine uses natural language processing techniques to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text.

[0183] The server inputs the recognized user emotions and collected information into the generative AI. Specifically, it converts the extracted data and emotion data into an input format for the generative AI model and inputs it.

[0184] Generative AI generates answers to user queries based on input data and sentiment. It uses natural language processing algorithms to generate context-appropriate answers. For example, if a user expresses dissatisfaction, generative AI will generate a more polite and detailed answer.

[0185] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[0186] Furthermore, the user's emotion data recognized by the emotion engine is stored in the user profile by the server, so that the user's emotion data can be used as a reference for future inquiries.

[0187] The server also pushes useful information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[0188] A specific example is given below.

[0189] Example 1: Inquiry about expense report format

[0190] 1. User: What is the format for expense reports?

[0191] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[0192] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[0193] 4. Server: Uses the emotion engine to recognize the user's emotion from the inquiry content. For example, it recognizes that the user is in trouble.

[0194] 5. Server: Extract documents with high title and content matches and input them into the generation AI. Emotion data is also provided.

[0195] 6. Generative AI: Generates answers such as "The format for expense reports is as follows..." Using polite language that takes into consideration the user's feelings.

[0196] 7. Generative AI: Returns the generated answer to the server.

[0197] 8. Server: Sends the answer as a response to the terminal and displays it to the user.

[0198] The system of the present invention allows users to receive appropriate and polite responses that reflect their feelings. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[0199] The processing flow will be explained below.

[0200] Step 1:

[0201] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[0202] Step 2:

[0203] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[0204] Step 3:

[0205] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[0206] Step 4:

[0207] The server collects relevant information from company documents, FAQs, and knowledge bases. Using a full-text search engine, the server searches for information that matches the query and extracts relevant documents and data.

[0208] Step 5:

[0209] The server uses an emotion engine to recognize the user's emotion from the inquiry content. The emotion engine uses natural language processing technology to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text. For example, it can recognize the emotion "confusion" from a phrase such as "I'm in trouble, please help me."

[0210] Step 6:

[0211] The server inputs the collected information and recognized emotion data into the generation AI. Specifically, the information on the related documents and the emotion data are passed to the generation AI together as an input format. At this time, the emotion data is also provided along with the analysis results.

[0212] Step 7:

[0213] The generative AI generates answers to inquiries based on the input data. Using a natural language processing algorithm, the generative AI generates answers in wording appropriate to the recognized emotion. For example, if the user is recognized as "confused," it generates a polite answer such as "Don't worry, please use this format."

[0214] Step 8:

[0215] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[0216] Step 9:

[0217] The server receives the answer from the AI ​​generator and sends it to the user's device. Specifically, the server sends the answer text from the AI ​​generator to the user's device as an HTTP response.

[0218] Step 10:

[0219] The terminal displays the received response to the user. The terminal analyzes the received response, processes it for display on the user interface, and displays the response to the user. For example, it may display "The expense report format is as follows. Please use it for reference."

[0220] Step 11:

[0221] The server will push useful information to the user based on the judgment of the generation AI. If the generation AI detects relevant information, the server will use the push notification service to send the relevant information to the user. For example, a push notification saying, "New procedures for expense reports have been added. Please check." will be sent.

[0222] The above steps not only enable prompt and accurate responses to inquiries within a company, but also enable responses that take into consideration the feelings of users.

[0223] Example 2

[0224] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0225] Conventional in-company inquiry response systems were unable to generate responses that took the user's emotions into account, making it difficult to provide appropriate responses. This resulted in ineffective response to inquiries and reduced user satisfaction. Furthermore, it was difficult to provide relevant information quickly, leading to a demand for faster response times.

[0226] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0227] In this invention, the server includes a means for analyzing the content of the inquiry and recognizing the user's emotion using an emotion engine, a means for inputting the collected information and the recognized emotion data into a generative AI model, and a means for saving the emotion data in a user profile, thereby enabling the generation of appropriate and prompt answers that take the user's emotions into consideration.

[0228] "User" means any person or entity that uses the system to make inquiries within the enterprise.

[0229] "Terminal" refers to a device used by a user to input and send a query. Examples include personal computers and smartphones.

[0230] "Server" refers to a central processing unit that receives, analyzes, and processes inquiries sent by users.

[0231] "In-house documents" refers to various documents and materials managed internally by a company, including FAQs and knowledge bases.

[0232] An "emotion engine" is a program or algorithm that analyzes and recognizes a user's emotions from the content of their inquiry.

[0233] A "generative AI model" is an artificial intelligence model that generates answers to inquiries based on input information and emotional data. Specifically, it includes models that use natural language processing algorithms.

[0234] A "profile" is a database for storing a user's emotional data, past inquiry history, and the like.

[0235] "Push notification" is a mechanism by which a server automatically notifies a user of necessary information.

[0236] This invention is a system for quickly and efficiently responding to inquiries within a company. This system is characterized by the fact that a user makes an inquiry using a terminal, and the generative AI model takes the user's emotions into consideration in the process of generating an appropriate answer.

[0237] First, a user uses a device (e.g., a personal computer or smartphone) to enter a question into a company's internal inquiry form and presses the send button. For example, the user might enter, "Please tell me the format for expense reports." This inquiry is then sent from the device to the server as an API request.

[0238] The server receives this API request using the HTTP protocol. The received inquiry is temporarily stored in a database and analyzed. During this analysis, the server uses a search engine (e.g., Elasticsearch) to search and collect relevant information from internal documents, FAQs, knowledge bases, etc.

[0239] Next, the server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to analyze and recognize the user's emotion from the query text. For example, it recognizes that the user is distressed. This recognized emotion data is used in the next step.

[0240] The collected related information and user emotion data are input into a generative AI model (e.g., GPT-3). A prompt containing the query, related information, and emotion data is generated. An example of a prompt is shown below:

[0241] text

[0242] User Question: What is the format for expense reports?

[0243] User sentiment: Annoyed

[0244] Related information: Expense report format is as follows...

[0245] The generative AI model generates an answer to the query based on the input information, and the generated answer is returned to the server in JSON format.

[0246] The server receives the answer returned by the generative AI model and sends it to the user's device. The user can view the answer on their device. For example, the answer might say, "The format for an expense report is as follows..."

[0247] The server also stores the emotion data recognized by the emotion engine in the user profile. This allows past emotion data to be referenced when responding to future inquiries. Furthermore, the server can also push useful information to users based on the judgment of the generative AI model. For example, providing relevant new and updated information to users in a timely manner can provide further convenience.

[0248] This invention allows users to quickly receive appropriate and detailed answers that take their emotions into consideration, greatly improving the efficiency of inquiries within companies. Furthermore, the accumulation and utilization of emotion data is expected to improve the quality of future inquiries.

[0249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0250] Step 1:

[0251] The user uses a terminal to input the inquiry and presses the send button. The input is done by entering the question, such as "What is the format for the expense report?", into a form on the screen. The input here is in text format.

[0252] Step 2:

[0253] The device sends the query entered by the user to the server as an API request. Specifically, the entered query is included in the body of an HTTP POST request in JSON format and sent to the API endpoint / ask. The input data is a JSON object containing the query in the "query" key, and the output is an HTTP POST request.

[0254] Step 3:

[0255] The server analyzes the received API request and temporarily stores the query content in a database. At this time, it analyzes the query content and converts it to text format. The received input is an API request in JSON format, and the output is the analyzed text data stored in the database.

[0256] Step 4:

[0257] The server uses a search engine (e.g., Elasticsearch) to gather relevant information from company documents, FAQs, and knowledge bases. The search query is a keyword extracted from the inquiry (e.g., "expense report" or "format"), and the output is a document containing the relevant information. Specifically, the server sends the search query and extracts the resulting documents and data.

[0258] Step 5:

[0259] The server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to recognize the user's sentiment from the query content. The input is the query text, and it runs an emotion classification algorithm to obtain emotional data (e.g., "I'm in trouble") as the output. The specific operation is to perform text analysis and assign an emotional category.

[0260] Step 6:

[0261] The server inputs the collected related information and recognized emotion data into a generative AI model (e.g., GPT-3). At this time, the input data is converted into a prompt format. For example, a prompt sentence such as "User inquiry: What is the format for an expense report? User emotion: I'm in trouble. Related information: The format for an expense report is as follows..." is created and input, and the output is the prompt sent to the generative AI model.

[0262] Step 7:

[0263] The generative AI model generates an answer to a query based on the input prompt. For example, it generates an answer such as, "The expense report format is as follows. Please feel free to let me know if there is anything you would like to confirm." The input is the prompt, and the output is the answer data in JSON format.

[0264] Step 8:

[0265] The server receives the answer returned from the generative AI model and sends it to the user's device. The input is the answer data from the generative AI model, and the output is the answer as an HTTP response.

[0266] Step 9:

[0267] The user receives and views the answer from the generative AI model on their device, such as "The format for an expense report is as follows..." The input is the HTTP response, and the output is the answer displayed on the screen.

[0268] Step 10:

[0269] The server stores the emotion data recognized by the emotion engine in the user profile. The input is emotion data, and the output is storage in the database. Specifically, the emotion data is added to the profile and used to respond to future inquiries.

[0270] Step 11:

[0271] The server pushes useful information to the user based on the judgment of the generative AI model, such as providing relevant new or updated information. The input is the judgment result of the generative AI model, and the output is a push notification message.

[0272] Through these steps, the system is able to quickly provide appropriate and detailed answers that take the user's feelings into consideration.

[0273] (Application example 2)

[0274] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0275] In the food delivery industry, it is important to respond quickly and appropriately to user inquiries. In particular, careful responses that take the user's emotions into consideration are required. However, conventional systems have difficulty recognizing the user's emotions and providing appropriate responses accordingly. They also lack a mechanism for notifying users of new and updated information in a timely manner. An effective method to solve these issues is needed.

[0276] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0277] In this invention, the server includes a means for using an emotion engine that recognizes emotions from the content of a user's inquiry, a means for inputting collected information and recognized emotion data into a generation AI, and a means for the generation AI to generate an answer to the inquiry based on the input information and emotion data. This makes it possible to provide an appropriate and polite answer that corresponds to the user's emotion. In addition, by sending push notifications of new and updated information related to the user based on the judgment of the generation AI, it is possible to provide the user with timely and useful information.

[0278] "User" refers to a person who uses this system to make an inquiry.

[0279] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes smartphones, tablets, PCs, etc.

[0280] "Server" refers to a central processing unit that receives user inquiries, collects and analyzes information, and generates answers using AI.

[0281] "In-house documents" refers to information assets such as documents, FAQs, and databases that are managed within a company.

[0282] "FAQ" is a collection of information that compiles frequently asked questions and their answers.

[0283] A "database" refers to a system that systematically manages a collection of data and makes it easily accessible.

[0284] An "emotion engine" refers to a component that uses natural language processing technology to recognize emotions from the content of a user's inquiry.

[0285] "Generative AI" refers to an artificial intelligence model that generates answers to user inquiries based on input information and emotional data.

[0286] "Natural language processing algorithm" refers to the technology that enables computers to understand, analyze, and generate human language.

[0287] "Push notification" refers to a technology in which a server sends information to a user's device in a timely manner.

[0288] An embodiment of the present invention will be described.

[0289] A user inputs an inquiry using a terminal (e.g., a smartphone). For example, when a user inputs "What is the delivery time?", the inquiry is sent from the terminal to the server.

[0290] The server analyzes the inquiry received from the user and collects related information from internal documents, FAQs, and databases. At this time, the emotion engine uses natural language processing technology to recognize the user's emotion from the inquiry. For example, if it is determined that the user is in a hurry, this is recorded as emotion data.

[0291] The server inputs the collected information and recognized emotional data into the generation AI. The generation AI generates an answer to the inquiry based on this input data. The generation AI generates an answer that takes the user's emotions into consideration based on the input information and emotional data. For example, if the user is in a hurry, the generation AI generates an answer such as, "The usual delivery time is 30 minutes, but due to current high demand, it may take a little longer."

[0292] The generated answer is returned to the server, which then sends it to the user's terminal, where it is displayed and the user can confirm the information.

[0293] Furthermore, as one of the features of the invention, the server can push notifications of new and updated information relevant to the user based on the judgment of the generating AI, thereby providing useful information to the user in a timely manner.

[0294] In a real system, the following example prompt sentences would be used as input to a generative AI model:

[0295] Example prompt sentence:

[0296] Generate a polite response to the user about food delivery times based on the following information:

[0297] Typical delivery time: 30 minutes

[0298] User sentiment: Rushing

[0299] Generate an answer.

[0300] In this way, the present invention provides a system that can generate answers that take the user's emotions into consideration, thereby contributing to improving user satisfaction. The above processing steps enable a prompt and appropriate response to user inquiries.

[0301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0302] Step 1:

[0303] The user enters a query

[0304] The user uses a device (e.g., a smartphone) to input an inquiry. The input inquiry is temporarily saved on the device. Example: The user inputs, "What is the delivery time?" Input: Inquiry Output: Inquiry

[0305] Step 2:

[0306] The device sends the inquiry to the server

[0307] The device sends the inquiry content to the server as an API request. Specifically, the inquiry content is included in the body of the HTTP request and posted to the server's API endpoint. Input: Enquiry content Output: API request

[0308] Step 3:

[0309] The server receives and analyzes the query.

[0310] The server analyzes the inquiry received from the terminal. Through this analysis, keywords related to the inquiry are extracted. Example: Extract the keyword "delivery time" from the inquiry. Input: API request Output: Keywords

[0311] Step 4:

[0312] The server gathers relevant information from company documents, FAQs, and databases

[0313] The server searches the company's internal documents, FAQs, and databases based on the extracted keywords to collect related information. Specifically, it uses a full-text search engine to obtain the necessary information. Input: Keywords Output: Related information

[0314] Step 5:

[0315] The server recognizes the user's emotions from the content of the inquiry

[0316] The server uses an emotion engine to recognize the user's emotion from the inquiry content. Specifically, it analyzes text data using natural language processing technology and extracts the user's emotion (e.g., "I'm in a hurry"). Input: Enquiry content Output: Emotion data

[0317] Step 6:

[0318] The server inputs the collected information and recognized emotion data into the generation AI.

[0319] The server converts the collected related information and user emotion data into input format and inputs it to the generation AI. Input: Related information, emotion data Output: Input data for the generation AI

[0320] Step 7:

[0321] Generative AI generates answers to inquiries based on input information

[0322] Generative AI generates answers to inquiries based on input relevant information and sentiment data. Generative AI generates context-appropriate answers in natural language. Example: If the user is in a hurry, it generates an answer such as "Our usual delivery time is 30 minutes, but due to current high demand, it may take a little longer." Input: Input data for generative AI Output: Generated answer

[0323] Step 8:

[0324] The generated AI returns the answer to the server

[0325] The generation AI returns the generated answer to the server. Input: Generated answer Output: Server received data

[0326] Step 9:

[0327] The server sends the answer received from the generation AI to the device.

[0328] The server receives the generated response and sends it to the user's device. Specifically, it sends the response data to the device as an HTTP response. Input: Data received by the server Output: HTTP response

[0329] Step 10:

[0330] The device displays the received answer to the user.

[0331] The terminal displays the received answer to the user. The user can check the displayed answer. Input: HTTP response Output: Displayed answer

[0332] Step 11:

[0333] The server pushes relevant new information and updates to the user.

[0334] The server will push relevant new and updated information to the user based on the judgment of the generating AI. This allows the user to receive useful information in a timely manner. Input: New information, updated information Output: Push notification

[0335] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0336] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0337] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0338] [Second embodiment]

[0339] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0340] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0341] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0342] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0343] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0344] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0345] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0346] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0347] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0348] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0349] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0350] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0351] The present invention is a system for quickly responding to inquiries within a company, and uses generative AI technology. The present invention is specifically implemented through the following processing steps.

[0352] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[0353] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[0354] The server analyzes the received inquiry and collects related information from the company's internal documents, FAQs, knowledge base, etc. For example, if the inquiry contains the keyword "expense report," the server searches for related documents using a full-text search engine.

[0355] Next, the server inputs the collected information into the generative AI. Specifically, the collected data is converted into a format that the generative AI model can process. This generative AI model uses natural language processing technology.

[0356] The generative AI generates answers to user inquiries based on the input information. For example, in response to an inquiry such as "Please tell me the format of an expense report," the generative AI uses past examples and templates to create an answer such as "The format of an expense report is as follows..."

[0357] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[0358] Furthermore, the server will push necessary information to the user based on the judgment of the generation AI, allowing relevant new and updated information to be provided to the user in a timely manner.

[0359] A specific example is given below.

[0360] Example 1: Inquiry about expense report format

[0361] 1. User: What is the format for expense reports?

[0362] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[0363] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[0364] 4. Server: Extract documents with highly similar titles and content and input them into the generation AI.

[0365] 5. Generative AI: Generate answers such as, "The expense report format is as follows..."

[0366] 6. Generative AI: Returns the generated answer to the server.

[0367] 7. Server: Sends the answer as a response to the terminal and displays it to the user.

[0368] The system of the present invention allows users to receive prompt and appropriate answers. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[0369] The processing flow will be explained below.

[0370] Step 1:

[0371] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[0372] Step 2:

[0373] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[0374] Step 3:

[0375] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[0376] Step 4:

[0377] The server collects relevant information from company documents, FAQs, and knowledge bases. The server uses a search engine to search for information that matches the query and extracts relevant documents and data.

[0378] Step 5:

[0379] The server prepares the collected information for input to the generative AI. Specifically, it converts the extracted data into an input format for the generative AI model and performs the necessary preprocessing.

[0380] Step 6:

[0381] The server inputs data into the generative AI. The server then inputs the preprocessed data into the generative AI model and requests it to generate an answer to the query.

[0382] Step 7:

[0383] Generative AI generates answers to queries based on input data. It uses natural language processing algorithms to generate answers that are context-appropriate.

[0384] Step 8:

[0385] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[0386] Step 9:

[0387] The server receives the generated answer and sends it to the user's device. Specifically, the server returns the answer from the generation AI to the user's device as an HTTP response.

[0388] Step 10:

[0389] The terminal displays the received answer to the user. The terminal analyzes the received answer, processes it for display on the user interface, and displays the answer to the user.

[0390] Step 11:

[0391] The server will send useful information to the user via push notification based on the AI's judgment. If the AI ​​detects relevant information, it will send that information to the user as a push notification. Specifically, the server will use a push notification service to send the notification.

[0392] The above steps realize a system that allows for quick and efficient response to inquiries within a company.

[0393] Example 1

[0394] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0395] Conventional inquiry response systems have had the problem of making it difficult for users to quickly obtain useful information from corporate documents, FAQs, and databases. Furthermore, previous systems lacked the accuracy and efficiency to generate appropriate answers based on the information obtained. Furthermore, it was difficult to provide users with the necessary information in a timely manner.

[0396] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0397] In this invention, the server includes: a means for a user to input and send a query from a terminal; a means for the terminal to send the query content to the server; a means for the server to collect related information from internal documents, FAQs, and databases; a means for the server to search the query content using a full-text search engine; a means for inputting the search results into a generative AI model; a means for the generative AI to generate an answer to the query based on the input information; a means for returning the answer generated by the generative AI to the server; a means for the server to send the answer received from the generative AI to the terminal; and a means for displaying the answer received by the terminal to the user. This allows users to receive prompt and appropriate answers, which is expected to improve business efficiency and productivity. It also makes it possible to provide related new and updated information in a timely manner.

[0398] A "user" is an entity that operates a terminal and makes inquiries to the system.

[0399] A "terminal" is a device through which a user enters input and sends queries to a server.

[0400] A "server" is a central processing unit that receives queries sent from terminals and collects and processes related information.

[0401] "In-house documents" refer to documents and materials managed internally by a company, and are used to provide information related to inquiries.

[0402] "FAQ" is a database of frequently asked questions and their answers.

[0403] A "database" is a system for storing structured information and quickly searching and retrieving required data.

[0404] A "full-text search engine" is software that quickly searches for text containing specific keywords and extracts related documents.

[0405] "Generative AI" is an artificial intelligence model that performs natural language processing based on collected information to generate answers to user inquiries.

[0406] The "JSON format" is a standard data description format used to store and transfer data in a structured manner.

[0407] "API Endpoint" refers to the URL or URI used to access a particular function of the system.

[0408] This invention is a system for quickly and accurately responding to inquiries within a company, and uses generative AI technology. This system is based on a series of steps in which a user inputs an inquiry from a terminal, and the content of the inquiry is sent to a server.

[0409] First, the user uses their own device to access the company's dedicated inquiry form. The user enters the inquiry details into the form and presses the "Submit" button. This action causes the device to convert the inquiry details into JSON format and send an HTTP POST request to the API endpoint / ask.

[0410] Next, the server receives this request and analyzes the request body. Based on the analyzed query, the server collects the necessary information from the company's internal documents, FAQ databases, and other relevant sources. During this process, the server uses a full-text search engine (e.g., Elasticsearch) to search for relevant documents based on the keywords contained in the query.

[0411] As a search result, the server extracts documents with a high degree of match in terms of title and content. The extracted information is converted into a format that can be processed by a generative AI model (e.g., OpenAI's GPT-3). The server then inputs the converted data into the generative AI.

[0412] The generation AI generates an answer to the user's inquiry based on the input information. The generated answer is returned to the server, which then sends it as a response to the user's device. Finally, the device displays the received answer to the user, completing the response to the inquiry.

[0413] Furthermore, the server can also push necessary information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[0414] As a specific example, the process when a user makes an inquiry such as "Please tell me the format of the expense report" will be described.

[0415] 1. The user asks, "What is the format for an expense report?"

[0416] 2. The device sends an HTTP POST request to the API endpoint / ask, with the request body containing "What is the expense report format?"

[0417] 3. The server receives and analyzes the request. It searches for the keyword "expense report" in a full-text search engine and collects related documents.

[0418] 4. The server extracts documents with highly consistent titles and content from the collected materials and inputs them into the generative AI model.

[0419] 5. The generative AI generates an answer such as, "The expense report format is as follows..."

[0420] 6. The generation AI returns the generated answer to the server.

[0421] 7. The server sends the response to the terminal and displays it to the user.

[0422] As a result, the system of the present invention can provide users with prompt and appropriate answers, which is expected to improve business efficiency and productivity in companies.

[0423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0424] Step 1:

[0425] A user inputs and sends an inquiry from a terminal. The user inputs a question such as "Please tell me the format for expense reports" into the inquiry form on the terminal and presses the "Send" button. This operation converts the input inquiry into JSON format. The input is the inquiry, and the output is JSON format data.

[0426] Step 2:

[0427] The terminal sends the query content to the server. The terminal then converts the query content into JSON format and sends it as an HTTP POST request to the API endpoint / ask. The input is the query content in JSON format, and the output is an HTTP POST request.

[0428] Step 3:

[0429] The server receives and analyzes the HTTP POST request. The server analyzes the received request body and extracts the query content. The input is the HTTP POST request body, and the output is the analyzed query content.

[0430] Step 4:

[0431] The server collects relevant information from internal documents, FAQs, and databases. Based on the query, the server uses a full-text search engine to search internal documents, FAQs, and databases. The input is the query and the full-text search engine, and the output is a list of related documents.

[0432] Step 5:

[0433] The server collects information using a full-text search engine. The server searches for the keyword "expense report" in a full-text search engine such as Elasticsearch and extracts relevant documents from within the company. The input is the databases that have been searched so far and the keywords in the query, and the output is the relevant documents as search results.

[0434] Step 6:

[0435] The server inputs the collected information into the generative AI model. The server converts the extracted related documents into a format that can be processed by the generative AI model (e.g., OpenAI's GPT-3). The converted data is input to the generative AI model as a prompt sentence. The input is the related documents, and the output is the prompt sentence that is input to the generative AI.

[0436] Step 7:

[0437] The generation AI generates an answer to the query based on the input information. The generation AI analyzes the prompt sentence and generates an appropriate answer to the user's query. The input is the prompt sentence, and the output is the generated answer text.

[0438] Step 8:

[0439] The generation AI returns the generated answer to the server. The generation AI returns the created answer text to the server. The input is the generated answer text, and the output is the answer text returned to the server.

[0440] Step 9:

[0441] The server sends the answer received from the generation AI to the terminal. The server sends the received answer text to the user's terminal as an HTTP response. The input is the answer text from the generation AI, and the output is the HTTP response sent to the user's terminal.

[0442] Step 10:

[0443] The terminal displays the received answer to the user. The terminal displays the received answer text in the inquiry form so that the user can view it. The input is the answer text as an HTTP response, and the output is the answer displayed on the user's terminal.

[0444] Step 11:

[0445] The server pushes necessary information to the user based on the judgment of the generation AI. The server delivers relevant information and updated information provided by the generation AI to the user in a timely manner. The input is information based on the judgment of the generation AI, and the output is the information that is pushed to the user.

[0446] (Application example 1)

[0447] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0448] Work management in factories is required to be efficient and fast, but in many factories, it is still managed manually. This results in the problem of time-consuming confirmation of work procedures and obtaining parts lists, which leads to reduced productivity. In addition, delays in obtaining necessary information can lead to work delays and incorrect instructions, reducing overall efficiency.

[0449] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0450] In this invention, the server includes a means for collecting relevant information from the factory management system and database, a means for inputting the collected information into the generation AI, and a means for the generation AI to generate answers to inquiries based on the input information. This allows for quick and accurate answers to user inquiries, resulting in efficient work management within the factory and improved productivity.

[0451] "User" refers to a worker who performs work in a factory.

[0452] "Device" refers to the input and display device used by the user, such as a tablet device or smart glasses.

[0453] An "inquiry" refers to a question or request made by a user via a terminal seeking information related to a business.

[0454] "Server" refers to a central processing unit that receives the inquiry, performs the necessary processing, and inputs the relevant information into the generation AI.

[0455] A "factory management system" refers to a system that manages work stages, parts lists, inventory information, etc. within a factory.

[0456] "Database" refers to a data storage system for storing factory management systems and related information.

[0457] "Related information" refers to data such as factory information, work procedures, and parts lists that are necessary to respond to user inquiries.

[0458] "Generative AI" refers to artificial intelligence that automatically generates answers to user inquiries based on collected information.

[0459] "Natural language processing algorithm" refers to the technology that enables generative AI to analyze text data and generate appropriate answers.

[0460] "Push notification" refers to the function of sending information from a server to a user device in real time.

[0461] A system for implementing this invention is configured as follows: A user can make an inquiry using a tablet terminal or smart glasses. For example, the user can input, "Please tell me the parts list for the next work stage." The inquiry is sent to the server by the terminal.

[0462] When the server receives the query, it collects relevant information from the factory management system and database. The collected information is then input into the generative AI, which uses natural language processing algorithms to analyze the received information and generate an appropriate response. For example, the generated response might be, "The parts list for the next stage is as follows..."

[0463] The answer generated by the AI ​​is returned to the server, which then sends it to the user's device. The device then displays the received answer to the user, allowing the user to quickly and accurately obtain the information they need.

[0464] This system uses the following hardware and software:

[0465] Hardware: Tablets, smart glasses, servers, devices with access to factory management systems

[0466] Software: Backend servers that process API requests (e.g., Python, Node.js), generative AI models (e.g., OpenAI GPT-4), factory management systems (e.g., ERP systems), full-text search engines (e.g., Solr, Elasticsearch)

[0467] Data processing and calculation involves analyzing the inquiry, collecting related information, inputting the collected information into the generation AI, and sending the generated answer to the user's device. For example, the server side receives an API request, obtains information from a factory management system or database, and inputs it into the generative AI model. The generated answer is then sent to the user's device, where the user can view it.

[0468] As a specific example, the following prompt sentence could be input to a generative AI model:

[0469] Example prompt sentence:

[0470] "Please tell me the parts list for the next stage of work."

[0471] "Please tell me the parts list. The parts needed for the next stage are "Part A, Part B.""

[0472] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0473] Step 1:

[0474] The user inputs an inquiry using a tablet device or smart glasses. Specifically, for example, the user inputs something like "Please tell me the parts list for the next work stage" and presses the send button. The input data is the user's inquiry.

[0475] Step 2:

[0476] The terminal sends the query entered by the user to the server as an API request. Specifically, the terminal generates an HTTP POST request and includes the query in the request body. The input data is the query, and the output data is the HTTP request.

[0477] Step 3:

[0478] The server analyzes the received API request. Specifically, it extracts the query content from the HTTP request body. The input data is the API request body, and the output data is the extracted query content.

[0479] Step 4:

[0480] The server collects relevant information from the factory management system and database. Specifically, it executes a database query based on the query content to obtain the required information (e.g., a list of parts required for the next work stage). The input data is the extracted query content, and the output data is the collected relevant information.

[0481] Step 5:

[0482] The server inputs the collected information into the generative AI model. Specifically, it converts the collected information into a format that the generative AI can understand (e.g., prompt text) and inputs it. The input data is the collected relevant information, and the output data is the data input to the generative AI.

[0483] Step 6:

[0484] A generative AI model generates answers to queries based on input information. Specifically, it uses natural language processing algorithms to generate text that appropriately answers the user's query. The input data is the data entered into the generative AI, and the output data is the generated answer.

[0485] Step 7:

[0486] The server receives the answer generated by the generation AI and sends it to the user's device. Specifically, it returns the generated answer to the user's device as an HTTP response. The input data is the generated answer, and the output data is the HTTP response.

[0487] Step 8:

[0488] The terminal displays the received response to the user. Specifically, the response is displayed on the terminal's display. The input data is the HTTP response, and the output data is the response displayed to the user.

[0489] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0490] The present invention is a system for quickly responding to inquiries within a company, which combines generative AI technology with an emotion engine that recognizes user emotions. The present invention is specifically implemented through the following processing steps.

[0491] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[0492] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[0493] The server analyzes the received inquiry and collects related information from the company's internal documents, FAQs, knowledge bases, etc. The server uses a search engine to search for information that matches the inquiry and extracts relevant documents and data.

[0494] The server then uses an emotion engine to recognize the user's emotion from the query. The emotion engine uses natural language processing techniques to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text.

[0495] The server inputs the recognized user emotions and collected information into the generative AI. Specifically, it converts the extracted data and emotion data into an input format for the generative AI model and inputs it.

[0496] Generative AI generates answers to user queries based on input data and sentiment. It uses natural language processing algorithms to generate context-appropriate answers. For example, if a user expresses dissatisfaction, generative AI will generate a more polite and detailed answer.

[0497] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[0498] Furthermore, the user's emotion data recognized by the emotion engine is stored in the user profile by the server, so that the user's emotion data can be used as a reference for future inquiries.

[0499] The server also pushes useful information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[0500] A specific example is given below.

[0501] Example 1: Inquiry about expense report format

[0502] 1. User: What is the format for expense reports?

[0503] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[0504] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[0505] 4. Server: Uses the emotion engine to recognize the user's emotion from the inquiry content. For example, it recognizes that the user is in trouble.

[0506] 5. Server: Extract documents with high title and content matches and input them into the generation AI. Emotion data is also provided.

[0507] 6. Generative AI: Generates answers such as "The format for expense reports is as follows..." Using polite language that takes into consideration the user's feelings.

[0508] 7. Generative AI: Returns the generated answer to the server.

[0509] 8. Server: Sends the answer as a response to the terminal and displays it to the user.

[0510] The system of the present invention allows users to receive appropriate and polite responses that reflect their feelings. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[0511] The processing flow will be explained below.

[0512] Step 1:

[0513] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[0514] Step 2:

[0515] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[0516] Step 3:

[0517] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[0518] Step 4:

[0519] The server collects relevant information from company documents, FAQs, and knowledge bases. Using a full-text search engine, the server searches for information that matches the query and extracts relevant documents and data.

[0520] Step 5:

[0521] The server uses an emotion engine to recognize the user's emotion from the inquiry content. The emotion engine uses natural language processing technology to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text. For example, it can recognize the emotion "confusion" from a phrase such as "I'm in trouble, please help me."

[0522] Step 6:

[0523] The server inputs the collected information and recognized emotion data into the generation AI. Specifically, the information on the related documents and the emotion data are passed to the generation AI together as an input format. At this time, the emotion data is also provided along with the analysis results.

[0524] Step 7:

[0525] The generative AI generates answers to inquiries based on the input data. Using a natural language processing algorithm, the generative AI generates answers in wording appropriate to the recognized emotion. For example, if the user is recognized as "confused," it generates a polite answer such as "Don't worry, please use this format."

[0526] Step 8:

[0527] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[0528] Step 9:

[0529] The server receives the answer from the AI ​​generator and sends it to the user's device. Specifically, the server sends the answer text from the AI ​​generator to the user's device as an HTTP response.

[0530] Step 10:

[0531] The terminal displays the received response to the user. The terminal analyzes the received response, processes it for display on the user interface, and displays the response to the user. For example, it may display "The expense report format is as follows. Please use it for reference."

[0532] Step 11:

[0533] The server will push useful information to the user based on the judgment of the generation AI. If the generation AI detects relevant information, the server will use the push notification service to send the relevant information to the user. For example, a push notification saying, "New procedures for expense reports have been added. Please check." will be sent.

[0534] The above steps not only enable prompt and accurate responses to inquiries within a company, but also enable responses that take into consideration the feelings of users.

[0535] Example 2

[0536] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0537] Conventional in-company inquiry response systems were unable to generate responses that took the user's emotions into account, making it difficult to provide appropriate responses. This resulted in ineffective response to inquiries and reduced user satisfaction. Furthermore, it was difficult to provide relevant information quickly, leading to a demand for faster response times.

[0538] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0539] In this invention, the server includes a means for analyzing the content of the inquiry and recognizing the user's emotion using an emotion engine, a means for inputting the collected information and the recognized emotion data into a generative AI model, and a means for saving the emotion data in a user profile, thereby enabling the generation of appropriate and prompt answers that take the user's emotions into consideration.

[0540] "User" means any person or entity that uses the system to make inquiries within the enterprise.

[0541] "Terminal" refers to a device used by a user to input and send a query. Examples include personal computers and smartphones.

[0542] "Server" refers to a central processing unit that receives, analyzes, and processes inquiries sent by users.

[0543] "In-house documents" refers to various documents and materials managed internally by a company, including FAQs and knowledge bases.

[0544] An "emotion engine" is a program or algorithm that analyzes and recognizes a user's emotions from the content of their inquiry.

[0545] A "generative AI model" is an artificial intelligence model that generates answers to inquiries based on input information and emotional data. Specifically, it includes models that use natural language processing algorithms.

[0546] A "profile" is a database for storing a user's emotional data, past inquiry history, and the like.

[0547] "Push notification" is a mechanism by which a server automatically notifies a user of necessary information.

[0548] This invention is a system for quickly and efficiently responding to inquiries within a company. This system is characterized by the fact that a user makes an inquiry using a terminal, and the generative AI model takes the user's emotions into consideration in the process of generating an appropriate answer.

[0549] First, a user uses a device (e.g., a personal computer or smartphone) to enter a question into a company's internal inquiry form and presses the send button. For example, the user might enter, "Please tell me the format for expense reports." This inquiry is then sent from the device to the server as an API request.

[0550] The server receives this API request using the HTTP protocol. The received inquiry is temporarily stored in a database and analyzed. During this analysis, the server uses a search engine (e.g., Elasticsearch) to search and collect relevant information from internal documents, FAQs, knowledge bases, etc.

[0551] Next, the server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to analyze and recognize the user's emotion from the query text. For example, it recognizes that the user is distressed. This recognized emotion data is used in the next step.

[0552] The collected related information and user emotion data are input into a generative AI model (e.g., GPT-3). A prompt containing the query, related information, and emotion data is generated. An example of a prompt is shown below:

[0553] text

[0554] User Question: What is the format for expense reports?

[0555] User sentiment: Annoyed

[0556] Related information: Expense report format is as follows...

[0557] The generative AI model generates an answer to the query based on the input information, and the generated answer is returned to the server in JSON format.

[0558] The server receives the answer returned by the generative AI model and sends it to the user's device. The user can view the answer on their device. For example, the answer may say, "The format for an expense report is as follows..."

[0559] The server also stores the emotion data recognized by the emotion engine in the user profile. This allows past emotion data to be referenced when responding to future inquiries. Furthermore, the server can also push useful information to users based on the judgment of the generative AI model. For example, providing relevant new and updated information to users in a timely manner can provide further convenience.

[0560] This invention allows users to quickly receive appropriate and detailed answers that take their emotions into consideration, greatly improving the efficiency of inquiries within companies. Furthermore, the accumulation and utilization of emotion data is expected to improve the quality of future inquiries.

[0561] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0562] Step 1:

[0563] The user uses a terminal to input the inquiry and presses the send button. The input is done by entering a question such as "What is the format for an expense report?" into a form on the screen. The input here is in text format.

[0564] Step 2:

[0565] The device sends the query entered by the user to the server as an API request. Specifically, the entered query is included in the body of an HTTP POST request in JSON format and sent to the API endpoint / ask. The input data is a JSON object containing the query in the "query" key, and the output is an HTTP POST request.

[0566] Step 3:

[0567] The server analyzes the received API request and temporarily stores the query content in a database. At this time, it analyzes the query content and converts it to text format. The received input is an API request in JSON format, and the output is the analyzed text data stored in the database.

[0568] Step 4:

[0569] The server uses a search engine (e.g., Elasticsearch) to gather relevant information from company documents, FAQs, and knowledge bases. The search query is a keyword extracted from the inquiry (e.g., "expense report" or "format"), and the output is a document containing the relevant information. Specifically, the server sends the search query and extracts the resulting documents and data.

[0570] Step 5:

[0571] The server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to recognize the user's sentiment from the query content. The input is the query text, and it runs an emotion classification algorithm to obtain emotional data (e.g., "I'm in trouble") as the output. The specific operation is to perform text analysis and assign an emotional category.

[0572] Step 6:

[0573] The server inputs the collected related information and recognized emotion data into a generative AI model (e.g., GPT-3). At this time, the input data is converted into a prompt format. For example, a prompt sentence such as "User inquiry: What is the format for an expense report? User emotion: I'm in trouble. Related information: The format for an expense report is as follows..." is created and input, and the output is the prompt sent to the generative AI model.

[0574] Step 7:

[0575] The generative AI model generates an answer to a query based on the input prompt. For example, it generates an answer such as, "The expense report format is as follows. Please feel free to let me know if there is anything you would like to confirm." The input is the prompt, and the output is the answer data in JSON format.

[0576] Step 8:

[0577] The server receives the answer returned from the generative AI model and sends it to the user's device. The input is the answer data from the generative AI model, and the output is the answer as an HTTP response.

[0578] Step 9:

[0579] The user receives and views the answer from the generative AI model on their device, such as "The format for an expense report is as follows..." The input is the HTTP response, and the output is the answer displayed on the screen.

[0580] Step 10:

[0581] The server stores the emotion data recognized by the emotion engine in the user profile. The input is emotion data, and the output is storage in the database. Specifically, the emotion data is added to the profile and used to respond to future inquiries.

[0582] Step 11:

[0583] The server pushes useful information to the user based on the judgment of the generative AI model, such as providing relevant new or updated information. The input is the judgment result of the generative AI model, and the output is a push notification message.

[0584] Through these steps, the system is able to quickly provide appropriate and detailed answers that take the user's feelings into consideration.

[0585] (Application example 2)

[0586] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0587] In the food delivery industry, it is important to respond quickly and appropriately to user inquiries. In particular, careful responses that take the user's emotions into consideration are required. However, conventional systems have difficulty recognizing the user's emotions and providing appropriate responses accordingly. They also lack a mechanism for notifying users of new and updated information in a timely manner. An effective method to solve these issues is needed.

[0588] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0589] In this invention, the server includes a means for using an emotion engine that recognizes emotions from the content of a user's inquiry, a means for inputting collected information and recognized emotion data into a generation AI, and a means for the generation AI to generate an answer to the inquiry based on the input information and emotion data. This makes it possible to provide an appropriate and polite answer that corresponds to the user's emotion. In addition, by sending push notifications of new and updated information related to the user based on the judgment of the generation AI, it is possible to provide the user with timely and useful information.

[0590] "User" refers to a person who uses this system to make an inquiry.

[0591] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes smartphones, tablets, PCs, etc.

[0592] "Server" refers to a central processing unit that receives user inquiries, collects and analyzes information, and generates answers using AI.

[0593] "In-house documents" refers to information assets such as documents, FAQs, and databases that are managed within a company.

[0594] "FAQ" is a collection of information that compiles frequently asked questions and their answers.

[0595] A "database" refers to a system that systematically manages a collection of data and makes it easily accessible.

[0596] An "emotion engine" refers to a component that uses natural language processing technology to recognize emotions from the content of a user's inquiry.

[0597] "Generative AI" refers to an artificial intelligence model that generates answers to user inquiries based on input information and emotional data.

[0598] "Natural language processing algorithm" refers to the technology that enables computers to understand, analyze, and generate human language.

[0599] "Push notification" refers to a technology in which a server sends information to a user's device in a timely manner.

[0600] An embodiment of the present invention will be described.

[0601] A user inputs an inquiry using a terminal (e.g., a smartphone). For example, when a user inputs "What is the delivery time?", the inquiry is sent from the terminal to the server.

[0602] The server analyzes the inquiry received from the user and collects related information from internal documents, FAQs, and databases. At this time, the emotion engine uses natural language processing technology to recognize the user's emotion from the inquiry. For example, if it is determined that the user is in a hurry, this is recorded as emotion data.

[0603] The server inputs the collected information and recognized emotional data into the generation AI. The generation AI generates an answer to the inquiry based on this input data. The generation AI generates an answer that takes the user's emotions into consideration based on the input information and emotional data. For example, if the user is in a hurry, the generation AI generates an answer such as, "The usual delivery time is 30 minutes, but due to current high demand, it may take a little longer."

[0604] The generated answer is returned to the server, which then sends it to the user's terminal, where it is displayed and the user can confirm the information.

[0605] Furthermore, as one of the features of the invention, the server can push notifications of new and updated information relevant to the user based on the judgment of the generating AI, thereby providing useful information to the user in a timely manner.

[0606] In a real system, the following example prompt sentences would be used as input to a generative AI model:

[0607] Example prompt sentence:

[0608] Generate a polite response to the user about food delivery times based on the following information:

[0609] Typical delivery time: 30 minutes

[0610] User sentiment: Rushing

[0611] Generate an answer.

[0612] In this way, the present invention provides a system that can generate answers that take the user's emotions into consideration, thereby contributing to improving user satisfaction. The above processing steps enable a prompt and appropriate response to user inquiries.

[0613] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0614] Step 1:

[0615] The user enters a query

[0616] The user uses a device (e.g., a smartphone) to input an inquiry. The input inquiry is temporarily saved on the device. Example: The user inputs, "What is the delivery time?" Input: Inquiry Output: Inquiry

[0617] Step 2:

[0618] The device sends the inquiry to the server

[0619] The device sends the inquiry content to the server as an API request. Specifically, the inquiry content is included in the body of the HTTP request and posted to the server's API endpoint. Input: Enquiry content Output: API request

[0620] Step 3:

[0621] The server receives and analyzes the query.

[0622] The server analyzes the inquiry received from the terminal. Through this analysis, keywords related to the inquiry are extracted. Example: Extract the keyword "delivery time" from the inquiry. Input: API request Output: Keywords

[0623] Step 4:

[0624] The server gathers relevant information from company documents, FAQs, and databases

[0625] The server searches the company's internal documents, FAQs, and databases based on the extracted keywords to collect related information. Specifically, it uses a full-text search engine to obtain the necessary information. Input: Keywords Output: Related information

[0626] Step 5:

[0627] The server recognizes the user's emotions from the content of the inquiry

[0628] The server uses an emotion engine to recognize the user's emotion from the inquiry content. Specifically, it analyzes text data using natural language processing technology and extracts the user's emotion (e.g., "I'm in a hurry"). Input: Enquiry content Output: Emotion data

[0629] Step 6:

[0630] The server inputs the collected information and recognized emotion data into the generation AI.

[0631] The server converts the collected related information and user emotion data into input format and inputs it to the generation AI. Input: Related information, emotion data Output: Input data for the generation AI

[0632] Step 7:

[0633] Generative AI generates answers to inquiries based on input information

[0634] Generative AI generates answers to inquiries based on input relevant information and sentiment data. Generative AI generates context-appropriate answers in natural language. Example: If the user is in a hurry, it generates an answer such as "Our usual delivery time is 30 minutes, but due to current high demand, it may take a little longer." Input: Input data for generative AI Output: Generated answer

[0635] Step 8:

[0636] The generated AI returns the answer to the server

[0637] The generation AI returns the generated answer to the server. Input: Generated answer Output: Server received data

[0638] Step 9:

[0639] The server sends the answer received from the generation AI to the device.

[0640] The server receives the generated response and sends it to the user's device. Specifically, it sends the response data to the device as an HTTP response. Input: Data received by the server Output: HTTP response

[0641] Step 10:

[0642] The device displays the received answer to the user.

[0643] The terminal displays the received answer to the user. The user can check the displayed answer. Input: HTTP response Output: Displayed answer

[0644] Step 11:

[0645] The server pushes relevant new information and updates to the user.

[0646] The server will push relevant new and updated information to the user based on the judgment of the generating AI. This allows the user to receive useful information in a timely manner. Input: New information, updated information Output: Push notification

[0647] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0648] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0649] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0650] [Third embodiment]

[0651] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0652] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0653] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0654] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0655] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0656] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0657] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0658] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0659] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0660] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0661] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0662] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0663] The present invention is a system for quickly responding to inquiries within a company, and uses generative AI technology. The present invention is specifically implemented through the following processing steps.

[0664] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[0665] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[0666] The server analyzes the received inquiry and collects related information from the company's internal documents, FAQs, knowledge base, etc. For example, if the inquiry contains the keyword "expense report," the server searches for related documents using a full-text search engine.

[0667] Next, the server inputs the collected information into the generative AI. Specifically, the collected data is converted into a format that the generative AI model can process. This generative AI model uses natural language processing technology.

[0668] The generative AI generates answers to user inquiries based on the input information. For example, in response to an inquiry such as "Please tell me the format of an expense report," the generative AI uses past examples and templates to create an answer such as "The format of an expense report is as follows..."

[0669] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[0670] Furthermore, the server will push necessary information to the user based on the judgment of the generation AI, allowing relevant new and updated information to be provided to the user in a timely manner.

[0671] A specific example is given below.

[0672] Example 1: Inquiry about expense report format

[0673] 1. User: What is the format for expense reports?

[0674] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[0675] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[0676] 4. Server: Extract documents with highly similar titles and content and input them into the generation AI.

[0677] 5. Generative AI: Generate answers such as, "The expense report format is as follows..."

[0678] 6. Generative AI: Returns the generated answer to the server.

[0679] 7. Server: Sends the answer as a response to the terminal and displays it to the user.

[0680] The system of the present invention allows users to receive prompt and appropriate answers. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[0681] The processing flow will be explained below.

[0682] Step 1:

[0683] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[0684] Step 2:

[0685] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[0686] Step 3:

[0687] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[0688] Step 4:

[0689] The server collects relevant information from company documents, FAQs, and knowledge bases. The server uses a search engine to search for information that matches the query and extracts relevant documents and data.

[0690] Step 5:

[0691] The server prepares the collected information for input to the generative AI. Specifically, it converts the extracted data into an input format for the generative AI model and performs the necessary preprocessing.

[0692] Step 6:

[0693] The server inputs data into the generative AI. The server then inputs the preprocessed data into the generative AI model and requests it to generate an answer to the query.

[0694] Step 7:

[0695] Generative AI generates answers to queries based on input data. It uses natural language processing algorithms to generate answers that are context-appropriate.

[0696] Step 8:

[0697] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[0698] Step 9:

[0699] The server receives the generated answer and sends it to the user's device. Specifically, the server returns the answer from the generation AI to the user's device as an HTTP response.

[0700] Step 10:

[0701] The terminal displays the received answer to the user. The terminal analyzes the received answer, processes it for display on the user interface, and displays the answer to the user.

[0702] Step 11:

[0703] The server will send useful information to the user via push notification based on the AI's judgment. If the AI ​​detects relevant information, it will send that information to the user as a push notification. Specifically, the server will use a push notification service to send the notification.

[0704] The above steps realize a system that allows for quick and efficient response to inquiries within a company.

[0705] Example 1

[0706] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0707] Conventional inquiry response systems have had the problem of making it difficult for users to quickly obtain useful information from corporate documents, FAQs, and databases. Furthermore, previous systems lacked the accuracy and efficiency to generate appropriate answers based on the information obtained. Furthermore, it was difficult to provide users with the necessary information in a timely manner.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0709] In this invention, the server includes: a means for a user to input and send a query from a terminal; a means for the terminal to send the query content to the server; a means for the server to collect related information from internal documents, FAQs, and databases; a means for the server to search the query content using a full-text search engine; a means for inputting the search results into a generative AI model; a means for the generative AI to generate an answer to the query based on the input information; a means for returning the answer generated by the generative AI to the server; a means for the server to send the answer received from the generative AI to the terminal; and a means for displaying the answer received by the terminal to the user. This allows users to receive prompt and appropriate answers, which is expected to improve business efficiency and productivity. It also makes it possible to provide related new and updated information in a timely manner.

[0710] A "user" is an entity that operates a terminal and makes inquiries to the system.

[0711] A "terminal" is a device through which a user enters input and sends queries to a server.

[0712] A "server" is a central processing unit that receives queries sent from terminals and collects and processes related information.

[0713] "In-house documents" refer to documents and materials managed internally by a company, and are used to provide information related to inquiries.

[0714] "FAQ" is a database of frequently asked questions and their answers.

[0715] A "database" is a system for storing structured information and quickly searching and retrieving required data.

[0716] A "full-text search engine" is software that quickly searches for text containing specific keywords and extracts related documents.

[0717] "Generative AI" is an artificial intelligence model that performs natural language processing based on collected information to generate answers to user inquiries.

[0718] The "JSON format" is a standard data description format used to store and transfer data in a structured manner.

[0719] "API Endpoint" refers to the URL or URI used to access a particular function of the system.

[0720] This invention is a system for quickly and accurately responding to inquiries within a company, and uses generative AI technology. This system is based on a series of steps in which a user inputs an inquiry from a terminal, and the content of the inquiry is sent to a server.

[0721] First, the user uses their own device to access the company's dedicated inquiry form. The user enters the inquiry details into the form and presses the "Submit" button. This action causes the device to convert the inquiry details into JSON format and send an HTTP POST request to the API endpoint / ask.

[0722] Next, the server receives this request and analyzes the request body. Based on the analyzed query, the server collects the necessary information from the company's internal documents, FAQ databases, and other relevant sources. During this process, the server uses a full-text search engine (e.g., Elasticsearch) to search for relevant documents based on the keywords contained in the query.

[0723] As a search result, the server extracts documents with a high degree of match in terms of title and content. The extracted information is converted into a format that can be processed by a generative AI model (e.g., OpenAI's GPT-3). The server then inputs the converted data into the generative AI.

[0724] The generation AI generates an answer to the user's inquiry based on the input information. The generated answer is returned to the server, which then sends it as a response to the user's device. Finally, the device displays the received answer to the user, completing the response to the inquiry.

[0725] Furthermore, the server can also push necessary information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[0726] As a specific example, the process when a user makes an inquiry such as "Please tell me the format of the expense report" will be described.

[0727] 1. The user asks, "What is the format for an expense report?"

[0728] 2. The device sends an HTTP POST request to the API endpoint / ask, with the request body containing "What is the expense report format?"

[0729] 3. The server receives and analyzes the request. It searches for the keyword "expense report" in a full-text search engine and collects related documents.

[0730] 4. The server extracts documents with highly consistent titles and content from the collected materials and inputs them into the generative AI model.

[0731] 5. The generative AI generates an answer such as, "The expense report format is as follows..."

[0732] 6. The generation AI returns the generated answer to the server.

[0733] 7. The server sends the response to the terminal and displays it to the user.

[0734] As a result, the system of the present invention can provide users with prompt and appropriate answers, which is expected to improve business efficiency and productivity in companies.

[0735] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0736] Step 1:

[0737] A user inputs and sends an inquiry from a terminal. The user inputs a question such as "Please tell me the format for expense reports" into the inquiry form on the terminal and presses the "Send" button. This operation converts the input inquiry into JSON format. The input is the inquiry, and the output is JSON format data.

[0738] Step 2:

[0739] The terminal sends the query content to the server. The terminal then converts the query content into JSON format and sends it as an HTTP POST request to the API endpoint / ask. The input is the query content in JSON format, and the output is an HTTP POST request.

[0740] Step 3:

[0741] The server receives and analyzes the HTTP POST request. The server analyzes the received request body and extracts the query content. The input is the HTTP POST request body, and the output is the analyzed query content.

[0742] Step 4:

[0743] The server collects relevant information from internal documents, FAQs, and databases. Based on the query, the server uses a full-text search engine to search internal documents, FAQs, and databases. The input is the query and the full-text search engine, and the output is a list of related documents.

[0744] Step 5:

[0745] The server collects information using a full-text search engine. The server searches for the keyword "expense report" in a full-text search engine such as Elasticsearch and extracts relevant documents from within the company. The input is the databases that have been searched so far and the keywords in the query, and the output is the relevant documents as search results.

[0746] Step 6:

[0747] The server inputs the collected information into the generative AI model. The server converts the extracted related documents into a format that can be processed by the generative AI model (e.g., OpenAI's GPT-3). The converted data is input to the generative AI model as a prompt sentence. The input is the related documents, and the output is the prompt sentence that is input to the generative AI.

[0748] Step 7:

[0749] The generation AI generates an answer to the query based on the input information. The generation AI analyzes the prompt sentence and generates an appropriate answer to the user's query. The input is the prompt sentence, and the output is the generated answer text.

[0750] Step 8:

[0751] The generation AI returns the generated answer to the server. The generation AI returns the created answer text to the server. The input is the generated answer text, and the output is the answer text returned to the server.

[0752] Step 9:

[0753] The server sends the answer received from the generation AI to the terminal. The server sends the received answer text to the user's terminal as an HTTP response. The input is the answer text from the generation AI, and the output is the HTTP response sent to the user's terminal.

[0754] Step 10:

[0755] The terminal displays the received answer to the user. The terminal displays the received answer text in the inquiry form so that the user can view it. The input is the answer text as an HTTP response, and the output is the answer displayed on the user's terminal.

[0756] Step 11:

[0757] The server pushes necessary information to the user based on the judgment of the generation AI. The server delivers relevant information and updated information provided by the generation AI to the user in a timely manner. The input is information based on the judgment of the generation AI, and the output is the information that is pushed to the user.

[0758] (Application example 1)

[0759] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0760] Work management in factories is required to be efficient and fast, but in many factories, it is still managed manually. This results in the problem of time-consuming confirmation of work procedures and obtaining parts lists, which leads to reduced productivity. In addition, delays in obtaining necessary information can lead to work delays and incorrect instructions, reducing overall efficiency.

[0761] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0762] In this invention, the server includes a means for collecting relevant information from the factory management system and database, a means for inputting the collected information into the generation AI, and a means for the generation AI to generate answers to inquiries based on the input information. This allows for quick and accurate answers to user inquiries, resulting in efficient work management within the factory and improved productivity.

[0763] "User" refers to a worker who performs work in a factory.

[0764] "Device" refers to the input and display device used by the user, such as a tablet device or smart glasses.

[0765] An "inquiry" refers to a question or request made by a user via a terminal seeking information related to a business.

[0766] "Server" refers to a central processing unit that receives the inquiry, performs the necessary processing, and inputs the relevant information into the generation AI.

[0767] A "factory management system" refers to a system that manages work stages, parts lists, inventory information, etc. within a factory.

[0768] "Database" refers to a data storage system for storing factory management systems and related information.

[0769] "Related information" refers to data such as factory information, work procedures, and parts lists that are necessary to respond to user inquiries.

[0770] "Generative AI" refers to artificial intelligence that automatically generates answers to user inquiries based on collected information.

[0771] "Natural language processing algorithm" refers to the technology that enables generative AI to analyze text data and generate appropriate answers.

[0772] "Push notification" refers to the function of sending information from a server to a user device in real time.

[0773] A system for implementing this invention is configured as follows: A user can make an inquiry using a tablet terminal or smart glasses. For example, the user can input, "Please tell me the parts list for the next work stage." The inquiry is sent to the server by the terminal.

[0774] When the server receives the query, it collects relevant information from the factory management system and database. The collected information is then input into the generative AI, which uses natural language processing algorithms to analyze the received information and generate an appropriate response. For example, the generated response might be, "The parts list for the next stage is as follows..."

[0775] The answer generated by the AI ​​is returned to the server, which then sends it to the user's device. The device then displays the received answer to the user, allowing the user to quickly and accurately obtain the information they need.

[0776] This system uses the following hardware and software:

[0777] Hardware: Tablets, smart glasses, servers, devices with access to factory management systems

[0778] Software: Backend servers that process API requests (e.g., Python, Node.js), generative AI models (e.g., OpenAI GPT-4), factory management systems (e.g., ERP systems), full-text search engines (e.g., Solr, Elasticsearch)

[0779] Data processing and calculation involves analyzing the inquiry, collecting related information, inputting the collected information into the generation AI, and sending the generated answer to the user's device. For example, the server side receives an API request, obtains information from a factory management system or database, and inputs it into the generative AI model. The generated answer is then sent to the user's device, where the user can view it.

[0780] As a specific example, the following prompt sentence could be input to a generative AI model:

[0781] Example prompt sentence:

[0782] "Please tell me the parts list for the next stage of work."

[0783] "Please tell me the parts list. The parts needed for the next stage are "Part A, Part B.""

[0784] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0785] Step 1:

[0786] The user inputs an inquiry using a tablet device or smart glasses. Specifically, for example, the user inputs something like "Please tell me the parts list for the next work stage" and presses the send button. The input data is the user's inquiry.

[0787] Step 2:

[0788] The terminal sends the query entered by the user to the server as an API request. Specifically, the terminal generates an HTTP POST request and includes the query in the request body. The input data is the query, and the output data is the HTTP request.

[0789] Step 3:

[0790] The server analyzes the received API request. Specifically, it extracts the query content from the HTTP request body. The input data is the API request body, and the output data is the extracted query content.

[0791] Step 4:

[0792] The server collects relevant information from the factory management system and database. Specifically, it executes a database query based on the query content to obtain the required information (e.g., a list of parts required for the next work stage). The input data is the extracted query content, and the output data is the collected relevant information.

[0793] Step 5:

[0794] The server inputs the collected information into the generative AI model. Specifically, it converts the collected information into a format that the generative AI can understand (e.g., prompt text) and inputs it. The input data is the collected relevant information, and the output data is the data input to the generative AI.

[0795] Step 6:

[0796] A generative AI model generates answers to queries based on input information. Specifically, it uses natural language processing algorithms to generate text that appropriately answers the user's query. The input data is the data entered into the generative AI, and the output data is the generated answer.

[0797] Step 7:

[0798] The server receives the answer generated by the generation AI and sends it to the user's device. Specifically, it returns the generated answer to the user's device as an HTTP response. The input data is the generated answer, and the output data is the HTTP response.

[0799] Step 8:

[0800] The terminal displays the received response to the user. Specifically, the response is displayed on the terminal's display. The input data is the HTTP response, and the output data is the response displayed to the user.

[0801] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0802] The present invention is a system for quickly responding to inquiries within a company, which combines generative AI technology with an emotion engine that recognizes user emotions. The present invention is specifically implemented through the following processing steps.

[0803] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[0804] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[0805] The server analyzes the received inquiry and collects related information from the company's internal documents, FAQs, knowledge bases, etc. The server uses a search engine to search for information that matches the inquiry and extracts relevant documents and data.

[0806] The server then uses an emotion engine to recognize the user's emotion from the query. The emotion engine uses natural language processing techniques to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text.

[0807] The server inputs the recognized user emotions and collected information into the generative AI. Specifically, it converts the extracted data and emotion data into an input format for the generative AI model and inputs it.

[0808] Generative AI generates answers to user queries based on input data and sentiment. It uses natural language processing algorithms to generate context-appropriate answers. For example, if a user expresses dissatisfaction, generative AI will generate a more polite and detailed answer.

[0809] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[0810] Furthermore, the user's emotion data recognized by the emotion engine is stored in the user profile by the server, so that the user's emotion data can be used as a reference for future inquiries.

[0811] The server also pushes useful information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[0812] A specific example is given below.

[0813] Example 1: Inquiry about expense report format

[0814] 1. User: What is the format for expense reports?

[0815] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[0816] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[0817] 4. Server: Uses the emotion engine to recognize the user's emotion from the inquiry content. For example, it recognizes that the user is in trouble.

[0818] 5. Server: Extract documents with high title and content matches and input them into the generation AI. Emotion data is also provided.

[0819] 6. Generative AI: Generates answers such as "The format for expense reports is as follows..." Using polite language that takes into consideration the user's feelings.

[0820] 7. Generative AI: Returns the generated answer to the server.

[0821] 8. Server: Sends the answer as a response to the terminal and displays it to the user.

[0822] The system of the present invention allows users to receive appropriate and polite responses that reflect their feelings. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[0823] The processing flow will be explained below.

[0824] Step 1:

[0825] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[0826] Step 2:

[0827] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[0828] Step 3:

[0829] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[0830] Step 4:

[0831] The server collects relevant information from company documents, FAQs, and knowledge bases. Using a full-text search engine, the server searches for information that matches the query and extracts relevant documents and data.

[0832] Step 5:

[0833] The server uses an emotion engine to recognize the user's emotion from the inquiry content. The emotion engine uses natural language processing technology to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text. For example, it can recognize the emotion "confusion" from a phrase such as "I'm in trouble, please help me."

[0834] Step 6:

[0835] The server inputs the collected information and recognized emotion data into the generation AI. Specifically, the information on the related documents and the emotion data are passed to the generation AI together as an input format. At this time, the emotion data is also provided along with the analysis results.

[0836] Step 7:

[0837] The generative AI generates answers to inquiries based on the input data. Using a natural language processing algorithm, the generative AI generates answers in wording appropriate to the recognized emotion. For example, if the user is recognized as "confused," it generates a polite answer such as "Don't worry, please use this format."

[0838] Step 8:

[0839] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[0840] Step 9:

[0841] The server receives the answer from the AI ​​generator and sends it to the user's device. Specifically, the server sends the answer text from the AI ​​generator to the user's device as an HTTP response.

[0842] Step 10:

[0843] The terminal displays the received response to the user. The terminal analyzes the received response, processes it for display on the user interface, and displays the response to the user. For example, it may display "The expense report format is as follows. Please use it for reference."

[0844] Step 11:

[0845] The server will push useful information to the user based on the judgment of the generation AI. If the generation AI detects relevant information, the server will use the push notification service to send the relevant information to the user. For example, a push notification saying, "New procedures for expense reports have been added. Please check." will be sent.

[0846] The above steps not only enable prompt and accurate responses to inquiries within a company, but also enable responses that take into consideration the feelings of users.

[0847] Example 2

[0848] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0849] Conventional in-company inquiry response systems were unable to generate responses that took the user's emotions into account, making it difficult to provide appropriate responses. This resulted in ineffective response to inquiries and reduced user satisfaction. Furthermore, it was difficult to provide relevant information quickly, leading to a demand for faster response times.

[0850] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0851] In this invention, the server includes a means for analyzing the content of the inquiry and recognizing the user's emotion using an emotion engine, a means for inputting the collected information and the recognized emotion data into a generative AI model, and a means for saving the emotion data in a user profile, thereby enabling the generation of appropriate and prompt answers that take the user's emotions into consideration.

[0852] "User" means any person or entity that uses the system to make inquiries within the enterprise.

[0853] "Terminal" refers to a device used by a user to input and send a query. Examples include personal computers and smartphones.

[0854] "Server" refers to a central processing unit that receives, analyzes, and processes inquiries sent by users.

[0855] "In-house documents" refers to various documents and materials managed internally by a company, including FAQs and knowledge bases.

[0856] An "emotion engine" is a program or algorithm that analyzes and recognizes a user's emotions from the content of their inquiry.

[0857] A "generative AI model" is an artificial intelligence model that generates answers to inquiries based on input information and emotional data. Specifically, it includes models that use natural language processing algorithms.

[0858] A "profile" is a database for storing a user's emotional data, past inquiry history, and the like.

[0859] "Push notification" is a mechanism by which a server automatically notifies a user of necessary information.

[0860] This invention is a system for quickly and efficiently responding to inquiries within a company. This system is characterized by the fact that a user makes an inquiry using a terminal, and the generative AI model takes the user's emotions into consideration in the process of generating an appropriate answer.

[0861] First, a user uses a device (e.g., a personal computer or smartphone) to enter a question into a company's internal inquiry form and presses the send button. For example, the user might enter, "Please tell me the format for expense reports." This inquiry is then sent from the device to the server as an API request.

[0862] The server receives this API request using the HTTP protocol. The received inquiry is temporarily stored in a database and analyzed. During this analysis, the server uses a search engine (e.g., Elasticsearch) to search and collect relevant information from internal documents, FAQs, knowledge bases, etc.

[0863] Next, the server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to analyze and recognize the user's emotion from the query text. For example, it recognizes that the user is distressed. This recognized emotion data is used in the next step.

[0864] The collected related information and user emotion data are input into a generative AI model (e.g., GPT-3). A prompt containing the query, related information, and emotion data is generated. An example of a prompt is shown below:

[0865] text

[0866] User Question: What is the format for expense reports?

[0867] User sentiment: Annoyed

[0868] Related information: Expense report format is as follows...

[0869] The generative AI model generates an answer to the query based on the input information, and the generated answer is returned to the server in JSON format.

[0870] The server receives the answer returned by the generative AI model and sends it to the user's device. The user can view the answer on their device. For example, the answer may say, "The format for an expense report is as follows..."

[0871] The server also stores the emotion data recognized by the emotion engine in the user profile. This allows past emotion data to be referenced when responding to future inquiries. Furthermore, the server can also push useful information to users based on the judgment of the generative AI model. For example, providing relevant new and updated information to users in a timely manner can provide further convenience.

[0872] This invention allows users to quickly receive appropriate and detailed answers that take their emotions into consideration, greatly improving the efficiency of inquiries within companies. Furthermore, the accumulation and utilization of emotion data is expected to improve the quality of future inquiries.

[0873] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0874] Step 1:

[0875] The user uses a terminal to input the inquiry and presses the send button. The input is done by entering a question such as "What is the format for an expense report?" into a form on the screen. The input here is in text format.

[0876] Step 2:

[0877] The device sends the query entered by the user to the server as an API request. Specifically, the entered query is included in the body of an HTTP POST request in JSON format and sent to the API endpoint / ask. The input data is a JSON object containing the query in the "query" key, and the output is an HTTP POST request.

[0878] Step 3:

[0879] The server analyzes the received API request and temporarily stores the query content in a database. At this time, it analyzes the query content and converts it to text format. The received input is an API request in JSON format, and the output is the analyzed text data stored in the database.

[0880] Step 4:

[0881] The server uses a search engine (e.g., Elasticsearch) to gather relevant information from company documents, FAQs, and knowledge bases. The search query is a keyword extracted from the inquiry (e.g., "expense report" or "format"), and the output is a document containing the relevant information. Specifically, the server sends the search query and extracts the resulting documents and data.

[0882] Step 5:

[0883] The server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to recognize the user's sentiment from the query content. The input is the query text, and it runs an emotion classification algorithm to obtain emotional data (e.g., "I'm in trouble") as the output. The specific operation is to perform text analysis and assign an emotional category.

[0884] Step 6:

[0885] The server inputs the collected related information and recognized emotion data into a generative AI model (e.g., GPT-3). At this time, the input data is converted into a prompt format. For example, a prompt sentence such as "User inquiry: What is the format for an expense report? User emotion: I'm in trouble. Related information: The format for an expense report is as follows..." is created and input, and the output is the prompt sent to the generative AI model.

[0886] Step 7:

[0887] The generative AI model generates an answer to a query based on the input prompt. For example, it generates an answer such as, "The expense report format is as follows. Please feel free to let me know if there is anything you would like to confirm." The input is the prompt, and the output is the answer data in JSON format.

[0888] Step 8:

[0889] The server receives the answer returned from the generative AI model and sends it to the user's device. The input is the answer data from the generative AI model, and the output is the answer as an HTTP response.

[0890] Step 9:

[0891] The user receives and views the answer from the generative AI model on their device, such as "The format for an expense report is as follows..." The input is the HTTP response, and the output is the answer displayed on the screen.

[0892] Step 10:

[0893] The server stores the emotion data recognized by the emotion engine in the user profile. The input is emotion data, and the output is storage in the database. Specifically, the emotion data is added to the profile and used to respond to future inquiries.

[0894] Step 11:

[0895] The server pushes useful information to the user based on the judgment of the generative AI model, such as providing relevant new or updated information. The input is the judgment result of the generative AI model, and the output is a push notification message.

[0896] Through these steps, the system is able to quickly provide appropriate and detailed answers that take the user's feelings into consideration.

[0897] (Application example 2)

[0898] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0899] In the food delivery industry, it is important to respond quickly and appropriately to user inquiries. In particular, careful responses that take the user's emotions into consideration are required. However, conventional systems have difficulty recognizing the user's emotions and providing appropriate responses accordingly. They also lack a mechanism for notifying users of new and updated information in a timely manner. An effective method to solve these issues is needed.

[0900] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0901] In this invention, the server includes a means for using an emotion engine that recognizes emotions from the content of a user's inquiry, a means for inputting collected information and recognized emotion data into a generation AI, and a means for the generation AI to generate an answer to the inquiry based on the input information and emotion data. This makes it possible to provide an appropriate and polite answer that corresponds to the user's emotion. In addition, by sending push notifications of new and updated information related to the user based on the judgment of the generation AI, it is possible to provide the user with timely and useful information.

[0902] "User" refers to a person who uses this system to make an inquiry.

[0903] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes smartphones, tablets, PCs, etc.

[0904] "Server" refers to a central processing unit that receives user inquiries, collects and analyzes information, and generates answers using AI.

[0905] "In-house documents" refers to information assets such as documents, FAQs, and databases that are managed within a company.

[0906] "FAQ" is a collection of information that compiles frequently asked questions and their answers.

[0907] A "database" refers to a system that systematically manages a collection of data and makes it easily accessible.

[0908] An "emotion engine" refers to a component that uses natural language processing technology to recognize emotions from the content of a user's inquiry.

[0909] "Generative AI" refers to an artificial intelligence model that generates answers to user inquiries based on input information and emotional data.

[0910] "Natural language processing algorithm" refers to the technology that enables computers to understand, analyze, and generate human language.

[0911] "Push notification" refers to a technology in which a server sends information to a user's device in a timely manner.

[0912] An embodiment of the present invention will be described.

[0913] A user inputs an inquiry using a terminal (e.g., a smartphone). For example, when a user inputs "What is the delivery time?", the inquiry is sent from the terminal to the server.

[0914] The server analyzes the inquiry received from the user and collects related information from internal documents, FAQs, and databases. At this time, the emotion engine uses natural language processing technology to recognize the user's emotion from the inquiry. For example, if it is determined that the user is in a hurry, this is recorded as emotion data.

[0915] The server inputs the collected information and recognized emotional data into the generation AI. The generation AI generates an answer to the inquiry based on this input data. The generation AI generates an answer that takes the user's emotions into consideration based on the input information and emotional data. For example, if the user is in a hurry, the generation AI generates an answer such as, "The usual delivery time is 30 minutes, but due to current high demand, it may take a little longer."

[0916] The generated answer is returned to the server, which then sends it to the user's terminal, which displays the received answer so the user can confirm the information.

[0917] Furthermore, as one of the features of the invention, the server can push new and updated information relevant to the user based on the judgment of the generating AI, thereby providing useful information to the user in a timely manner.

[0918] In a real system, the following example prompt sentences would be used as input to a generative AI model:

[0919] Example prompt sentence:

[0920] Generate a polite response to the user about food delivery times based on the following information:

[0921] Typical delivery time: 30 minutes

[0922] User sentiment: Rushing

[0923] Generate an answer.

[0924] In this way, the present invention provides a system that can generate answers that take the user's emotions into consideration, thereby contributing to improving user satisfaction. The above processing steps enable a prompt and appropriate response to user inquiries.

[0925] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0926] Step 1:

[0927] The user enters a query

[0928] The user uses a device (e.g., a smartphone) to input an inquiry. The input inquiry is temporarily saved on the device. Example: The user inputs "What is the delivery time?" Input: Inquiry Output: Inquiry

[0929] Step 2:

[0930] The device sends the inquiry to the server

[0931] The device sends the inquiry content to the server as an API request. Specifically, the inquiry content is included in the body of the HTTP request and posted to the server's API endpoint. Input: Enquiry content Output: API request

[0932] Step 3:

[0933] The server receives and analyzes the query.

[0934] The server analyzes the inquiry received from the terminal. Through this analysis, keywords related to the inquiry are extracted. Example: Extract the keyword "delivery time" from the inquiry. Input: API request Output: Keywords

[0935] Step 4:

[0936] The server gathers relevant information from company documents, FAQs, and databases

[0937] The server searches corporate documents, FAQs, and databases based on the extracted keywords to collect related information. Specifically, it uses a full-text search engine to obtain the necessary information. Input: Keywords Output: Related information

[0938] Step 5:

[0939] The server recognizes the user's emotions from the content of the inquiry

[0940] The server uses an emotion engine to recognize the user's emotion from the inquiry content. Specifically, it analyzes text data using natural language processing technology and extracts the user's emotion (e.g., "I'm in a hurry"). Input: Enquiry content Output: Emotion data

[0941] Step 6:

[0942] The server inputs the collected information and recognized emotion data into the generation AI.

[0943] The server converts the collected related information and user emotion data into input format and inputs it to the generation AI. Input: Related information, emotion data Output: Input data for the generation AI

[0944] Step 7:

[0945] Generative AI generates answers to inquiries based on input information

[0946] Generative AI generates answers to inquiries based on input relevant information and sentiment data. Generative AI generates context-appropriate answers in natural language. Example: If the user is in a hurry, it generates an answer such as "Our usual delivery time is 30 minutes, but due to current high demand, it may take a little longer." Input: Input data for generative AI Output: Generated answer

[0947] Step 8:

[0948] The generated AI returns the answer to the server

[0949] The generation AI returns the generated answer to the server. Input: Generated answer Output: Server received data

[0950] Step 9:

[0951] The server sends the answer received from the generation AI to the device.

[0952] The server receives the generated response and sends it to the user's device. Specifically, it sends the response data to the device as an HTTP response. Input: Data received by the server Output: HTTP response

[0953] Step 10:

[0954] The device displays the received answer to the user.

[0955] The terminal displays the received answer to the user. The user can check the displayed answer. Input: HTTP response Output: Displayed answer

[0956] Step 11:

[0957] The server pushes relevant new information and updates to the user.

[0958] The server will push relevant new and updated information to the user based on the judgment of the generating AI. This allows the user to receive useful information in a timely manner. Input: New information, updated information Output: Push notification

[0959] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0960] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0961] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0962] [Fourth embodiment]

[0963] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0964] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0965] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0966] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0967] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0968] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0969] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0970] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0971] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0972] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0973] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0974] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0975] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0976] The present invention is a system for quickly responding to inquiries within a company, and uses generative AI technology. The present invention is specifically implemented through the following processing steps.

[0977] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[0978] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[0979] The server analyzes the received inquiry and collects related information from the company's internal documents, FAQs, knowledge base, etc. For example, if the inquiry contains the keyword "expense report," the server searches for related documents using a full-text search engine.

[0980] Next, the server inputs the collected information into the generative AI. Specifically, the collected data is converted into a format that the generative AI model can process. This generative AI model uses natural language processing technology.

[0981] The generative AI generates answers to user inquiries based on the input information. For example, in response to an inquiry such as "Please tell me the format of an expense report," the generative AI uses past examples and templates to create an answer such as "The format of an expense report is as follows..."

[0982] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[0983] Furthermore, the server will push necessary information to the user based on the judgment of the generation AI, allowing relevant new and updated information to be provided to the user in a timely manner.

[0984] A specific example is given below.

[0985] Example 1: Inquiry about expense report format

[0986] 1. User: What is the format for expense reports?

[0987] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[0988] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[0989] 4. Server: Extract documents with highly similar titles and content and input them into the generation AI.

[0990] 5. Generative AI: Generate answers such as, "The expense report format is as follows..."

[0991] 6. Generative AI: Returns the generated answer to the server.

[0992] 7. Server: Sends the answer as a response to the terminal and displays it to the user.

[0993] The system of the present invention allows users to receive prompt and appropriate answers. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[0994] The processing flow will be explained below.

[0995] Step 1:

[0996] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[0997] Step 2:

[0998] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[0999] Step 3:

[1000] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[1001] Step 4:

[1002] The server collects relevant information from company documents, FAQs, and knowledge bases. The server uses a search engine to search for information that matches the query and extracts relevant documents and data.

[1003] Step 5:

[1004] The server prepares the collected information for input to the generative AI. Specifically, it converts the extracted data into an input format for the generative AI model and performs the necessary preprocessing.

[1005] Step 6:

[1006] The server inputs data into the generative AI. The server then inputs the preprocessed data into the generative AI model and requests it to generate an answer to the query.

[1007] Step 7:

[1008] Generative AI generates answers to queries based on input data. It uses natural language processing algorithms to generate answers that are context-appropriate.

[1009] Step 8:

[1010] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[1011] Step 9:

[1012] The server receives the generated answer and sends it to the user's device. Specifically, the server returns the answer from the generation AI to the user's device as an HTTP response.

[1013] Step 10:

[1014] The terminal displays the received answer to the user. The terminal analyzes the received answer, processes it for display on the user interface, and displays the answer to the user.

[1015] Step 11:

[1016] The server will send useful information to the user via push notification based on the AI's judgment. If the AI ​​detects relevant information, it will send that information to the user as a push notification. Specifically, the server will use a push notification service to send the notification.

[1017] The above steps realize a system that allows for quick and efficient response to inquiries within a company.

[1018] Example 1

[1019] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1020] Conventional inquiry response systems have had the problem of making it difficult for users to quickly obtain useful information from corporate documents, FAQs, and databases. Furthermore, previous systems lacked the accuracy and efficiency to generate appropriate answers based on the information obtained. Furthermore, it was difficult to provide users with the necessary information in a timely manner.

[1021] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1022] In this invention, the server includes: a means for a user to input and send a query from a terminal; a means for the terminal to send the query content to the server; a means for the server to collect related information from internal documents, FAQs, and databases; a means for the server to search the query content using a full-text search engine; a means for inputting the search results into a generative AI model; a means for the generative AI to generate an answer to the query based on the input information; a means for returning the answer generated by the generative AI to the server; a means for the server to send the answer received from the generative AI to the terminal; and a means for displaying the answer received by the terminal to the user. This allows users to receive prompt and appropriate answers, which is expected to improve business efficiency and productivity. It also makes it possible to provide related new and updated information in a timely manner.

[1023] A "user" is an entity that operates a terminal and makes inquiries to the system.

[1024] A "terminal" is a device through which a user enters input and sends queries to a server.

[1025] A "server" is a central processing unit that receives queries sent from terminals and collects and processes related information.

[1026] "In-house documents" refer to documents and materials managed internally by a company, and are used to provide information related to inquiries.

[1027] "FAQ" is a database of frequently asked questions and their answers.

[1028] A "database" is a system for storing structured information and quickly searching and retrieving required data.

[1029] A "full-text search engine" is software that quickly searches for text containing specific keywords and extracts related documents.

[1030] "Generative AI" is an artificial intelligence model that performs natural language processing based on collected information to generate answers to user inquiries.

[1031] The "JSON format" is a standard data description format used to store and transfer data in a structured manner.

[1032] "API Endpoint" refers to the URL or URI used to access a particular function of the system.

[1033] This invention is a system for quickly and accurately responding to inquiries within a company, and uses generative AI technology. This system is based on a series of steps in which a user inputs an inquiry from a terminal, and the content of the inquiry is sent to a server.

[1034] First, the user uses their own device to access the company's dedicated inquiry form. The user enters the inquiry details into the form and presses the "Submit" button. This action causes the device to convert the inquiry details into JSON format and send an HTTP POST request to the API endpoint / ask.

[1035] Next, the server receives this request and analyzes the request body. Based on the analyzed query, the server collects the necessary information from the company's internal documents, FAQ databases, and other relevant sources. During this process, the server uses a full-text search engine (e.g., Elasticsearch) to search for relevant documents based on the keywords contained in the query.

[1036] As a search result, the server extracts documents with a high degree of match in terms of title and content. The extracted information is converted into a format that can be processed by a generative AI model (e.g., OpenAI's GPT-3). The server then inputs the converted data into the generative AI.

[1037] The generation AI generates an answer to the user's inquiry based on the input information. The generated answer is returned to the server, which then sends it as a response to the user's device. Finally, the device displays the received answer to the user, completing the response to the inquiry.

[1038] Furthermore, the server can also push necessary information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[1039] As a specific example, the process when a user makes an inquiry such as "Please tell me the format of the expense report" will be described.

[1040] 1. The user asks, "What is the format for an expense report?"

[1041] 2. The device sends an HTTP POST request to the API endpoint / ask, with the request body containing "What is the expense report format?"

[1042] 3. The server receives and analyzes the request. It searches for the keyword "expense report" in a full-text search engine and collects related documents.

[1043] 4. The server extracts documents with highly consistent titles and content from the collected materials and inputs them into the generative AI model.

[1044] 5. The generative AI generates an answer such as, "The expense report format is as follows..."

[1045] 6. The generation AI returns the generated answer to the server.

[1046] 7. The server sends the response to the terminal and displays it to the user.

[1047] As a result, the system of the present invention can provide users with prompt and appropriate answers, which is expected to improve business efficiency and productivity in companies.

[1048] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1049] Step 1:

[1050] A user inputs and sends an inquiry from a terminal. The user inputs a question such as "Please tell me the format for expense reports" into the inquiry form on the terminal and presses the "Send" button. This operation converts the input inquiry into JSON format. The input is the inquiry, and the output is JSON format data.

[1051] Step 2:

[1052] The terminal sends the query content to the server. The terminal then converts the query content into JSON format and sends it as an HTTP POST request to the API endpoint / ask. The input is the query content in JSON format, and the output is an HTTP POST request.

[1053] Step 3:

[1054] The server receives and analyzes the HTTP POST request. The server analyzes the received request body and extracts the query content. The input is the HTTP POST request body, and the output is the analyzed query content.

[1055] Step 4:

[1056] The server collects relevant information from internal documents, FAQs, and databases. Based on the query, the server uses a full-text search engine to search internal documents, FAQs, and databases. The input is the query and the full-text search engine, and the output is a list of related documents.

[1057] Step 5:

[1058] The server collects information using a full-text search engine. The server searches for the keyword "expense report" in a full-text search engine such as Elasticsearch and extracts relevant documents from within the company. The input is the databases that have been searched so far and the keywords in the query, and the output is the relevant documents as search results.

[1059] Step 6:

[1060] The server inputs the collected information into the generative AI model. The server converts the extracted related documents into a format that can be processed by the generative AI model (e.g., OpenAI's GPT-3). The converted data is input to the generative AI model as a prompt sentence. The input is the related documents, and the output is the prompt sentence that is input to the generative AI.

[1061] Step 7:

[1062] The generation AI generates an answer to the query based on the input information. The generation AI analyzes the prompt sentence and generates an appropriate answer to the user's query. The input is the prompt sentence, and the output is the generated answer text.

[1063] Step 8:

[1064] The generation AI returns the generated answer to the server. The generation AI returns the created answer text to the server. The input is the generated answer text, and the output is the answer text returned to the server.

[1065] Step 9:

[1066] The server sends the answer received from the generation AI to the terminal. The server sends the received answer text to the user's terminal as an HTTP response. The input is the answer text from the generation AI, and the output is the HTTP response sent to the user's terminal.

[1067] Step 10:

[1068] The terminal displays the received answer to the user. The terminal displays the received answer text in the inquiry form so that the user can view it. The input is the answer text as an HTTP response, and the output is the answer displayed on the user's terminal.

[1069] Step 11:

[1070] The server pushes necessary information to the user based on the judgment of the generation AI. The server delivers relevant information and updated information provided by the generation AI to the user in a timely manner. The input is information based on the judgment of the generation AI, and the output is the information that is pushed to the user.

[1071] (Application example 1)

[1072] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1073] Work management in factories is required to be efficient and fast, but in many factories, it is still managed manually. This results in the problem of time-consuming confirmation of work procedures and obtaining parts lists, which leads to reduced productivity. In addition, delays in obtaining necessary information can lead to work delays and incorrect instructions, reducing overall efficiency.

[1074] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1075] In this invention, the server includes a means for collecting relevant information from the factory management system and database, a means for inputting the collected information into the generation AI, and a means for the generation AI to generate answers to inquiries based on the input information. This allows for quick and accurate answers to user inquiries, resulting in efficient work management within the factory and improved productivity.

[1076] "User" refers to a worker who performs work in a factory.

[1077] "Device" refers to the input and display device used by the user, such as a tablet device or smart glasses.

[1078] An "inquiry" refers to a question or request made by a user via a terminal seeking information related to a business.

[1079] "Server" refers to a central processing unit that receives the inquiry, performs the necessary processing, and inputs the relevant information into the generation AI.

[1080] A "factory management system" refers to a system that manages work stages, parts lists, inventory information, etc. within a factory.

[1081] "Database" refers to a data storage system for storing factory management systems and related information.

[1082] "Related information" refers to data such as factory information, work procedures, and parts lists that are necessary to respond to user inquiries.

[1083] "Generative AI" refers to artificial intelligence that automatically generates answers to user inquiries based on collected information.

[1084] "Natural language processing algorithm" refers to the technology that enables generative AI to analyze text data and generate appropriate answers.

[1085] "Push notification" refers to the function of sending information from a server to a user device in real time.

[1086] A system for implementing this invention is configured as follows: A user can make an inquiry using a tablet terminal or smart glasses. For example, the user can input, "Please tell me the parts list for the next work stage." The inquiry is sent to the server by the terminal.

[1087] When the server receives the query, it collects relevant information from the factory management system and database. The collected information is then input into the generative AI, which uses natural language processing algorithms to analyze the received information and generate an appropriate response. For example, the generated response might be, "The parts list for the next stage is as follows..."

[1088] The answer generated by the AI ​​is returned to the server, which then sends it to the user's device. The device then displays the received answer to the user, allowing the user to quickly and accurately obtain the information they need.

[1089] This system uses the following hardware and software:

[1090] Hardware: Tablets, smart glasses, servers, devices with access to factory management systems

[1091] Software: Backend servers that process API requests (e.g., Python, Node.js), generative AI models (e.g., OpenAI GPT-4), factory management systems (e.g., ERP systems), full-text search engines (e.g., Solr, Elasticsearch)

[1092] Data processing and calculation involves analyzing the inquiry, collecting related information, inputting the collected information into the generation AI, and sending the generated answer to the user's device. For example, the server side receives an API request, obtains information from a factory management system or database, and inputs it into the generative AI model. The generated answer is then sent to the user's device, where the user can view it.

[1093] As a specific example, the following prompt sentence could be input to a generative AI model:

[1094] Example prompt sentence:

[1095] "Please tell me the parts list for the next stage of work."

[1096] "Please tell me the parts list. The parts needed for the next stage are "Part A, Part B.""

[1097] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1098] Step 1:

[1099] The user inputs an inquiry using a tablet device or smart glasses. Specifically, for example, the user inputs something like "Please tell me the parts list for the next work stage" and presses the send button. The input data is the user's inquiry.

[1100] Step 2:

[1101] The terminal sends the query entered by the user to the server as an API request. Specifically, the terminal generates an HTTP POST request and includes the query in the request body. The input data is the query, and the output data is the HTTP request.

[1102] Step 3:

[1103] The server analyzes the received API request. Specifically, it extracts the query content from the HTTP request body. The input data is the API request body, and the output data is the extracted query content.

[1104] Step 4:

[1105] The server collects relevant information from the factory management system and database. Specifically, it executes a database query based on the query content to obtain the required information (e.g., a list of parts required for the next work stage). The input data is the extracted query content, and the output data is the collected relevant information.

[1106] Step 5:

[1107] The server inputs the collected information into the generative AI model. Specifically, it converts the collected information into a format that the generative AI can understand (e.g., prompt text) and inputs it. The input data is the collected relevant information, and the output data is the data input to the generative AI.

[1108] Step 6:

[1109] A generative AI model generates answers to queries based on input information. Specifically, it uses natural language processing algorithms to generate text that appropriately answers the user's query. The input data is the data entered into the generative AI, and the output data is the generated answer.

[1110] Step 7:

[1111] The server receives the answer generated by the generation AI and sends it to the user's device. Specifically, it returns the generated answer to the user's device as an HTTP response. The input data is the generated answer, and the output data is the HTTP response.

[1112] Step 8:

[1113] The terminal displays the received response to the user. Specifically, the response is displayed on the terminal's display. The input data is the HTTP response, and the output data is the response displayed to the user.

[1114] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1115] The present invention is a system for quickly responding to inquiries within a company, which combines generative AI technology with an emotion engine that recognizes user emotions. The present invention is specifically implemented through the following processing steps.

[1116] First, the user makes an inquiry using a terminal. Specifically, the user enters the question in an input field on the terminal and presses the "Send" button, which sends the inquiry to the server.

[1117] Next, the device sends the inquiry entered by the user to the server as an API request, with the inquiry details included in the body of the HTTP request.

[1118] The server analyzes the received inquiry and collects related information from the company's internal documents, FAQs, knowledge bases, etc. The server uses a search engine to search for information that matches the inquiry and extracts relevant documents and data.

[1119] The server then uses an emotion engine to recognize the user's emotion from the query. The emotion engine uses natural language processing techniques to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text.

[1120] The server inputs the recognized user emotions and collected information into the generative AI. Specifically, it converts the extracted data and emotion data into an input format for the generative AI model and inputs it.

[1121] Generative AI generates answers to user queries based on input data and sentiment. It uses natural language processing algorithms to generate context-appropriate answers. For example, if a user expresses dissatisfaction, generative AI will generate a more polite and detailed answer.

[1122] The AI ​​returns the generated answer to the server. The server receives the generated answer and sends it to the user's device. This allows the user to view the answer from the AI ​​through their device.

[1123] Furthermore, the user's emotion data recognized by the emotion engine is stored in the user profile by the server, so that the user's emotion data can be used as a reference for future inquiries.

[1124] The server also pushes useful information to users based on the judgment of the generating AI, allowing relevant new and updated information to be provided to users in a timely manner.

[1125] A specific example is given below.

[1126] Example 1: Inquiry about expense report format

[1127] 1. User: What is the format for expense reports?

[1128] 2. Device: Send a POST request to the API endpoint / ask. The request body contains "What is the expense report format?"

[1129] 3. Server: After receiving the endpoint, it performs a full-text search using "expense report" as the query to find relevant documents.

[1130] 4. Server: Uses the emotion engine to recognize the user's emotion from the inquiry content. For example, it recognizes that the user is in trouble.

[1131] 5. Server: Extract documents with high title and content matches and input them into the generation AI. Emotion data is also provided.

[1132] 6. Generative AI: Generates answers such as "The format for expense reports is as follows..." Using polite language that takes into consideration the user's feelings.

[1133] 7. Generative AI: Returns the generated answer to the server.

[1134] 8. Server: Sends the answer as a response to the terminal and displays it to the user.

[1135] The system of the present invention allows users to receive appropriate and polite responses that reflect their feelings. Furthermore, the push notification function allows users to receive the information they need in a timely manner. This is expected to improve work efficiency and productivity.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] The user inputs a query from the terminal and sends it. The user inputs the question into the input field of the terminal and clicks the "Send" button. At this point, the query is temporarily saved in the terminal.

[1139] Step 2:

[1140] The device sends the query to the server. Specifically, the device sends the query entered to the server's API endpoint as an HTTP POST request. The query is included in the request body.

[1141] Step 3:

[1142] The server receives the query and begins analyzing it. The server extracts the query from the body of the received request and performs keyword and context analysis.

[1143] Step 4:

[1144] The server collects relevant information from company documents, FAQs, and knowledge bases. Using a full-text search engine, the server searches for information that matches the query and extracts relevant documents and data.

[1145] Step 5:

[1146] The server uses an emotion engine to recognize the user's emotion from the inquiry content. The emotion engine uses natural language processing technology to extract the user's emotion (e.g., joy, anger, sadness, fear) from the text. For example, it can recognize the emotion "confusion" from a phrase such as "I'm in trouble, please help me."

[1147] Step 6:

[1148] The server inputs the collected information and recognized emotion data into the generation AI. Specifically, the information on the related documents and the emotion data are passed to the generation AI together as an input format. At this time, the emotion data is also provided along with the analysis results.

[1149] Step 7:

[1150] The generative AI generates answers to inquiries based on the input data. Using a natural language processing algorithm, the generative AI generates answers in wording appropriate to the recognized emotion. For example, if the user is recognized as "confused," it generates a polite answer such as "Don't worry, please use this format."

[1151] Step 8:

[1152] The generation AI returns the generated answer to the server. Once the generation AI has finished generating the answer, it returns the answer to the server as an API response.

[1153] Step 9:

[1154] The server receives the answer from the AI ​​generator and sends it to the user's device. Specifically, the server sends the answer text from the AI ​​generator to the user's device as an HTTP response.

[1155] Step 10:

[1156] The terminal displays the received response to the user. The terminal analyzes the received response, processes it for display on the user interface, and displays the response to the user. For example, it may display "The expense report format is as follows. Please use it for reference."

[1157] Step 11:

[1158] The server will push useful information to the user based on the judgment of the generation AI. If the generation AI detects relevant information, the server will use the push notification service to send the relevant information to the user. For example, a push notification saying, "New procedures for expense reports have been added. Please check." will be sent.

[1159] The above steps not only enable prompt and accurate responses to inquiries within a company, but also enable responses that take into consideration the feelings of users.

[1160] Example 2

[1161] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1162] Conventional in-company inquiry response systems were unable to generate responses that took the user's emotions into account, making it difficult to provide appropriate responses. This resulted in ineffective response to inquiries and reduced user satisfaction. Furthermore, it was difficult to provide relevant information quickly, leading to a demand for faster response times.

[1163] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1164] In this invention, the server includes a means for analyzing the content of the inquiry and recognizing the user's emotion using an emotion engine, a means for inputting the collected information and the recognized emotion data into a generative AI model, and a means for saving the emotion data in a user profile, thereby enabling the generation of appropriate and prompt answers that take the user's emotions into consideration.

[1165] "User" means any person or entity that uses the system to make inquiries within the enterprise.

[1166] "Terminal" refers to a device used by a user to input and send a query. Examples include personal computers and smartphones.

[1167] "Server" refers to a central processing unit that receives, analyzes, and processes inquiries sent by users.

[1168] "In-house documents" refers to various documents and materials managed internally by a company, including FAQs and knowledge bases.

[1169] An "emotion engine" is a program or algorithm that analyzes and recognizes a user's emotions from the content of their inquiry.

[1170] A "generative AI model" is an artificial intelligence model that generates answers to inquiries based on input information and emotional data. Specifically, it includes models that use natural language processing algorithms.

[1171] A "profile" is a database for storing a user's emotional data, past inquiry history, and the like.

[1172] "Push notification" is a mechanism by which a server automatically notifies a user of necessary information.

[1173] This invention is a system for quickly and efficiently responding to inquiries within a company. This system is characterized by the fact that a user makes an inquiry using a terminal, and the generative AI model takes the user's emotions into consideration in the process of generating an appropriate answer.

[1174] First, a user uses a device (e.g., a personal computer or smartphone) to enter a question into a company's internal inquiry form and presses the send button. For example, the user might enter, "Please tell me the format for expense reports." This inquiry is then sent from the device to the server as an API request.

[1175] The server receives this API request using the HTTP protocol. The received inquiry is temporarily stored in a database and analyzed. During this analysis, the server uses a search engine (e.g., Elasticsearch) to search and collect relevant information from internal documents, FAQs, knowledge bases, etc.

[1176] Next, the server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to analyze and recognize the user's emotion from the query text. For example, it recognizes that the user is distressed. This recognized emotion data is used in the next step.

[1177] The collected related information and user emotion data are input into a generative AI model (e.g., GPT-3). A prompt containing the query, related information, and emotion data is generated. An example of a prompt is shown below:

[1178] text

[1179] User Question: What is the format for expense reports?

[1180] User sentiment: Annoyed

[1181] Related information: Expense report format is as follows...

[1182] The generative AI model generates an answer to the query based on the input information, and the generated answer is returned to the server in JSON format.

[1183] The server receives the answer returned by the generative AI model and sends it to the user's device. The user can view the answer on their device. For example, the answer may say, "The format for an expense report is as follows..."

[1184] The server also stores the emotion data recognized by the emotion engine in the user profile. This allows past emotion data to be referenced when responding to future inquiries. Furthermore, the server can also push useful information to users based on the judgment of the generative AI model. For example, providing relevant new and updated information to users in a timely manner can provide further convenience.

[1185] This invention allows users to quickly receive appropriate and detailed answers that take their emotions into consideration, greatly improving the efficiency of inquiries within companies. Furthermore, the accumulation and utilization of emotion data is expected to improve the quality of future inquiries.

[1186] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1187] Step 1:

[1188] The user uses a terminal to input the inquiry and presses the send button. The input is done by entering a question such as "What is the format for an expense report?" into a form on the screen. The input here is in text format.

[1189] Step 2:

[1190] The device sends the query entered by the user to the server as an API request. Specifically, the entered query is included in the body of an HTTP POST request in JSON format and sent to the API endpoint / ask. The input data is a JSON object containing the query in the "query" key, and the output is an HTTP POST request.

[1191] Step 3:

[1192] The server analyzes the received API request and temporarily stores the query content in a database. At this time, it analyzes the query content and converts it to text format. The received input is an API request in JSON format, and the output is the analyzed text data stored in the database.

[1193] Step 4:

[1194] The server uses a search engine (e.g., Elasticsearch) to gather relevant information from company documents, FAQs, and knowledge bases. The search query is a keyword extracted from the inquiry (e.g., "expense report" or "format"), and the output is a document containing the relevant information. Specifically, the server sends the search query and extracts the resulting documents and data.

[1195] Step 5:

[1196] The server uses an emotion engine (e.g., a sentiment analysis model based on TensorFlow) to recognize the user's sentiment from the query content. The input is the query text, and it runs an emotion classification algorithm to obtain emotional data (e.g., "I'm in trouble") as the output. The specific operation is to perform text analysis and assign an emotional category.

[1197] Step 6:

[1198] The server inputs the collected related information and recognized emotion data into a generative AI model (e.g., GPT-3). At this time, the input data is converted into a prompt format. For example, a prompt sentence such as "User inquiry: What is the format for an expense report? User emotion: I'm in trouble. Related information: The format for an expense report is as follows..." is created and input, and the output is the prompt sent to the generative AI model.

[1199] Step 7:

[1200] The generative AI model generates an answer to a query based on the input prompt. For example, it generates an answer such as, "The expense report format is as follows. Please feel free to let me know if there is anything you would like to confirm." The input is the prompt, and the output is the answer data in JSON format.

[1201] Step 8:

[1202] The server receives the answer returned from the generative AI model and sends it to the user's device. The input is the answer data from the generative AI model, and the output is the answer as an HTTP response.

[1203] Step 9:

[1204] The user receives and views the answer from the generative AI model on their device, such as "The format for an expense report is as follows..." The input is the HTTP response, and the output is the answer displayed on the screen.

[1205] Step 10:

[1206] The server stores the emotion data recognized by the emotion engine in the user profile. The input is emotion data, and the output is storage in the database. Specifically, the emotion data is added to the profile and used to respond to future inquiries.

[1207] Step 11:

[1208] The server pushes useful information to the user based on the judgment of the generative AI model, such as providing relevant new or updated information. The input is the judgment result of the generative AI model, and the output is a push notification message.

[1209] Through these steps, the system is able to quickly provide appropriate and detailed answers that take the user's feelings into consideration.

[1210] (Application example 2)

[1211] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1212] In the food delivery industry, it is important to respond quickly and appropriately to user inquiries. In particular, careful responses that take the user's emotions into consideration are required. However, conventional systems have difficulty recognizing the user's emotions and providing appropriate responses accordingly. They also lack a mechanism for notifying users of new and updated information in a timely manner. An effective method to solve these issues is needed.

[1213] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1214] In this invention, the server includes a means for using an emotion engine that recognizes emotions from the content of a user's inquiry, a means for inputting collected information and recognized emotion data into a generation AI, and a means for the generation AI to generate an answer to the inquiry based on the input information and emotion data. This makes it possible to provide an appropriate and polite answer that corresponds to the user's emotion. In addition, by sending push notifications of new and updated information related to the user based on the judgment of the generation AI, it is possible to provide the user with timely and useful information.

[1215] "User" refers to a person who uses this system to make an inquiry.

[1216] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes smartphones, tablets, PCs, etc.

[1217] "Server" refers to a central processing unit that receives user inquiries, collects and analyzes information, and generates answers using AI.

[1218] "In-house documents" refers to information assets such as documents, FAQs, and databases that are managed within a company.

[1219] "FAQ" is a collection of information that compiles frequently asked questions and their answers.

[1220] A "database" refers to a system that systematically manages a collection of data and makes it easily accessible.

[1221] An "emotion engine" refers to a component that uses natural language processing technology to recognize emotions from the content of a user's inquiry.

[1222] "Generative AI" refers to an artificial intelligence model that generates answers to user inquiries based on input information and emotional data.

[1223] "Natural language processing algorithm" refers to the technology that enables computers to understand, analyze, and generate human language.

[1224] "Push notification" refers to a technology in which a server sends information to a user's device in a timely manner.

[1225] An embodiment of the present invention will be described.

[1226] A user inputs an inquiry using a terminal (e.g., a smartphone). For example, when a user inputs "What is the delivery time?", the inquiry is sent from the terminal to the server.

[1227] The server analyzes the inquiry received from the user and collects related information from internal documents, FAQs, and databases. At this time, the emotion engine uses natural language processing technology to recognize the user's emotion from the inquiry. For example, if it is determined that the user is in a hurry, this is recorded as emotion data.

[1228] The server inputs the collected information and recognized emotional data into the generation AI. The generation AI generates an answer to the inquiry based on this input data. The generation AI generates an answer that takes the user's emotions into consideration based on the input information and emotional data. For example, if the user is in a hurry, the generation AI generates an answer such as, "The usual delivery time is 30 minutes, but due to current high demand, it may take a little longer."

[1229] The generated answer is returned to the server, which then sends it to the user's terminal, which displays the received answer so the user can confirm the information.

[1230] Furthermore, as one of the features of the invention, the server can push new and updated information relevant to the user based on the judgment of the generating AI, thereby providing useful information to the user in a timely manner.

[1231] In a real system, the following example prompt sentences would be used as input to a generative AI model:

[1232] Example prompt sentence:

[1233] Generate a polite response to the user about food delivery times based on the following information:

[1234] Typical delivery time: 30 minutes

[1235] User sentiment: Rushing

[1236] Generate an answer.

[1237] In this way, the present invention provides a system that can generate answers that take the user's emotions into consideration, thereby contributing to improving user satisfaction. The above processing steps enable a prompt and appropriate response to user inquiries.

[1238] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1239] Step 1:

[1240] The user enters a query

[1241] The user uses a device (e.g., a smartphone) to input an inquiry. The input inquiry is temporarily saved on the device. Example: The user inputs "What is the delivery time?" Input: Inquiry Output: Inquiry

[1242] Step 2:

[1243] The device sends the inquiry to the server

[1244] The device sends the inquiry content to the server as an API request. Specifically, the inquiry content is included in the body of the HTTP request and posted to the server's API endpoint. Input: Enquiry content Output: API request

[1245] Step 3:

[1246] The server receives and analyzes the query.

[1247] The server analyzes the inquiry received from the terminal. Through this analysis, keywords related to the inquiry are extracted. Example: Extract the keyword "delivery time" from the inquiry. Input: API request Output: Keywords

[1248] Step 4:

[1249] The server gathers relevant information from company documents, FAQs, and databases

[1250] The server searches corporate documents, FAQs, and databases based on the extracted keywords to collect related information. Specifically, it uses a full-text search engine to obtain the necessary information. Input: Keywords Output: Related information

[1251] Step 5:

[1252] The server recognizes the user's emotions from the content of the inquiry

[1253] The server uses an emotion engine to recognize the user's emotion from the inquiry content. Specifically, it analyzes text data using natural language processing technology and extracts the user's emotion (e.g., "I'm in a hurry"). Input: Enquiry content Output: Emotion data

[1254] Step 6:

[1255] The server inputs the collected information and recognized emotion data into the generation AI.

[1256] The server converts the collected related information and user emotion data into input format and inputs it to the generation AI. Input: Related information, emotion data Output: Input data for the generation AI

[1257] Step 7:

[1258] Generative AI generates answers to inquiries based on input information

[1259] Generative AI generates answers to inquiries based on input relevant information and sentiment data. Generative AI generates context-appropriate answers in natural language. Example: If the user is in a hurry, it generates an answer such as "Our usual delivery time is 30 minutes, but due to current high demand, it may take a little longer." Input: Input data for generative AI Output: Generated answer

[1260] Step 8:

[1261] The generated AI returns the answer to the server

[1262] The generation AI returns the generated answer to the server. Input: Generated answer Output: Server received data

[1263] Step 9:

[1264] The server sends the answer received from the generation AI to the device.

[1265] The server receives the generated response and sends it to the user's device. Specifically, it sends the response data to the device as an HTTP response. Input: Data received by the server Output: HTTP response

[1266] Step 10:

[1267] The device displays the received answer to the user.

[1268] The terminal displays the received answer to the user. The user can check the displayed answer. Input: HTTP response Output: Displayed answer

[1269] Step 11:

[1270] The server pushes relevant new information and updates to the user.

[1271] The server will push relevant new and updated information to the user based on the judgment of the generating AI. This allows the user to receive useful information in a timely manner. Input: New information, updated information Output: Push notification

[1272] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1273] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1274] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1275] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1276] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1277] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1278] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1279] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1280] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1281] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1282] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1283] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1284] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1285] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1286] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1287] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1288] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1289] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1290] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1291] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1292] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1293] The following is further disclosed regarding the above embodiment.

[1294] (Claim 1)

[1295] A means for a user to input and send a query from a terminal;

[1296] A means for the terminal to transmit the inquiry content to the server;

[1297] A means for the server to gather relevant information from company documents, FAQs, and databases;

[1298] A means for inputting the information collected by the server into the generation AI,

[1299] A means for the generation AI to generate an answer to the inquiry based on the input information;

[1300] A means for returning the answer generated by the generation AI to the server;

[1301] A means for the server to transmit the answer received from the generation AI to the terminal;

[1302] means for displaying the answer received by the terminal to the user;

[1303] A system including:

[1304] (Claim 2)

[1305] The system according to claim 1, wherein the server includes means for pushing necessary information to the user based on the judgment of the generating AI.

[1306] (Claim 3)

[1307] 2. The system of claim 1, wherein the generating AI includes means for analyzing the user's inquiry and internal company information and using a natural language processing algorithm to generate an answer.

[1308] "Example 1"

[1309] (Claim 1)

[1310] A means for a user to input and send a query from a terminal;

[1311] A means for the terminal to transmit the inquiry content to the server;

[1312] A means for the server to gather relevant information from company documents, FAQs, and databases;

[1313] A means for inputting the information collected by the server into the generation AI,

[1314] A means for the generation AI to generate an answer to the inquiry based on the input information;

[1315] A means for returning the answer generated by the generation AI to the server;

[1316] A means for the server to transmit the answer received from the generation AI to the terminal;

[1317] means for displaying the answer received by the terminal to the user;

[1318] A means for searching the content of the inquiry using a full-text search engine;

[1319] A means of inputting search results into a generative AI model; and

[1320] A system including:

[1321] (Claim 2)

[1322] The system according to claim 1, wherein the server includes means for pushing necessary information to the user based on the judgment of the generating AI.

[1323] (Claim 3)

[1324] 2. The system of claim 1, wherein the generating AI includes means for analyzing the user's inquiry and internal company information and using a natural language processing algorithm to generate an answer.

[1325] "Application Example 1"

[1326] (Claim 1)

[1327] A means for a user to input and send a query from a terminal;

[1328] A means for the terminal to transmit the inquiry content to the server;

[1329] A means for the server to collect relevant information from the factory management system and database;

[1330] A means for inputting the information collected by the server into the generation AI,

[1331] A means for the generation AI to generate an answer to the inquiry based on the input information;

[1332] A means for returning the answer generated by the generation AI to the server;

[1333] A means for the server to transmit the answer received from the generation AI to the terminal;

[1334] means for displaying the answer received by the terminal to the user;

[1335] A system including:

[1336] (Claim 2)

[1337] The system according to claim 1, wherein the server includes means for pushing necessary information to the user based on the judgment of the generating AI.

[1338] (Claim 3)

[1339] 2. The system of claim 1, wherein the generating AI includes means for analyzing the user's inquiry and in-factory information and using a natural language processing algorithm to generate an answer.

[1340] "Example 2: Combining Emotion Engines"

[1341] (Claim 1)

[1342] A means for a user to input and send a query from a terminal;

[1343] A means for the terminal to transmit the inquiry content to the server;

[1344] A means for the server to gather relevant information from company documents, FAQs, and databases;

[1345] A means for the server to analyze the content of the query and recognize the user's emotion using an emotion engine;

[1346] A means for inputting the information collected by the server and the recognized emotion data into the generative AI model;

[1347] A means for the generative AI model to generate an answer to the query based on the input information and emotion data;

[1348] A means for returning the answer generated by the generative AI model to the server;

[1349] A means for transmitting the answer received by the server from the generative AI model to the terminal;

[1350] means for displaying the answer received by the terminal to the user;

[1351] a means for the server to store the emotion data in a user profile;

[1352] A system including:

[1353] (Claim 2)

[1354] The system according to claim 1, wherein the server includes means for pushing necessary information to the user based on the judgment of the generating AI model.

[1355] (Claim 3)

[1356] 10. The system of claim 1, wherein the generative AI model includes means for analyzing the user's inquiry and enterprise information and using natural language processing algorithms to generate an answer.

[1357] "Application example 2 when combining emotion engines"

[1358] (Claim 1)

[1359] A means for a user to input and send a query from a terminal;

[1360] A means for the terminal to transmit the inquiry content to the server;

[1361] A means for the server to gather relevant information from company documents, FAQs, and databases;

[1362] A means for the server to use an emotion engine to recognize the emotion of the user from the query content;

[1363] A means for inputting the information collected by the server and the recognized emotion data into the generation AI;

[1364] A means for the generative AI to generate an answer to the inquiry based on the input information and emotion data;

[1365] A means for returning the answer generated by the generation AI to the server;

[1366] A means for the server to transmit the answer received from the generation AI to the terminal;

[1367] means for displaying the answer received by the terminal to the user;

[1368] A system including:

[1369] (Claim 2)

[1370] The system of claim 1, further comprising means for the server to push relevant new and updated information to the user based on the judgment of the generating AI.

[1371] (Claim 3)

[1372] 2. The system of claim 1, wherein the generating AI analyzes the user's inquiry, internal enterprise information, and emotional data, and uses a natural language processing algorithm to generate an answer. [Explanation of symbols]

[1373] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for a user to input and send a query from a terminal; A means for the terminal to transmit the inquiry content to the server; A means for the server to gather relevant information from company documents, FAQs, and databases; A means for inputting the information collected by the server into the generation AI, A means for the generation AI to generate an answer to the inquiry based on the input information; A means for returning the answer generated by the generation AI to the server; A means for the server to transmit the answer received from the generation AI to the terminal; means for displaying the answer received by the terminal to the user; A system including:

2. The system according to claim 1, wherein the server includes means for pushing necessary information to the user based on the judgment of the generating AI.

3. 2. The system of claim 1, wherein the generating AI includes means for analyzing the content of the user's inquiry and company information and using a natural language processing algorithm to generate an answer.

Images