system

Abstract

Provide a system. The method includes: receiving a question from a user in natural language; A means for analyzing the received question and generating data extraction conditions corresponding to the question; A means for extracting necessary information from a database using the generated data extraction conditions; means for analyzing the extracted information and generating an answer to the user's question; and means for providing the generated answer to the user.

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] Conventional data analysis systems require users to perform complex manual tasks to access the information they need, which takes time and effort. This makes it difficult to perform rapid data analysis, and it is not possible to immediately obtain the information needed, especially during meetings or business negotiations. Furthermore, there was no system that could properly respond to questions in natural language, which led to low efficiency in data analysis. [Means for solving the problem]

[0005] The present invention provides a system that receives a question in natural language from a user, analyzes the question to extract necessary data, and generates a specific answer based on the analysis results. Specifically, the system includes means for receiving a question in natural language from a user, means for analyzing the received question and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables a user to quickly obtain and analyze necessary data simply by intuitively inputting a question in natural language, allowing the information to be used immediately in meetings and business negotiations.

[0006] A "natural language" is a language that humans use on a daily basis to communicate without requiring special technical skills or specialized code.

[0007] A "question" is an inquiry that a user makes to the system to resolve a question they want to solve or to obtain information they need.

[0008] "Analysis" refers to the procedures and processes for understanding the content of the received question and generating appropriate data extraction conditions.

[0009] "Data extraction conditions" refer to specific conditions or queries set to retrieve required information from a database.

[0010] A "database" is a system that organizes large amounts of data and keeps them manageable and searchable.

[0011] "Information" refers to data such as numbers and text stored in a database, and is the basis for answering a user's question.

[0012] "Extraction" is the procedure of extracting necessary information from a database based on specific conditions.

[0013] "Analysis results" refer to the results obtained by performing calculations, statistics, and other analyses based on extracted information.

[0014] An "answer" is specific information or explanation provided in response to a user's question.

[0015] A "system" is a collection of functions and means configured to achieve a specific purpose.

[0016] "User" means an end-user who utilizes the System to ask questions and obtain information. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[0039] 1. Receive user questions

[0040] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[0041] 2. Submitting and analyzing questions

[0042] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[0043] 3. Data Extraction

[0044] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generative AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[0045] 4. Analyze the data and generate answers

[0046] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How is sales in the Tokyo metropolitan area compared to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated.

[0047] 5. Providing answers to users

[0048] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[0049] Specific examples

[0050] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[0051] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[0052] 2. Terminal: Sends the question to the server.

[0053] 3. Server: Analyzes the question and identifies the keywords "metropolitan area" and "year-on-year comparison."

[0054] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[0055] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[0056] 6. Server: Generates the calculation result as an answer and provides it to the user.

[0057] 7. Terminal: Display the answer in a user interface.

[0058] In this way, the present invention allows users to easily perform complex data analysis using natural language, eliminating the need for complex manual tasks, enabling them to quickly obtain necessary information and make instant decisions in situations such as meetings and business negotiations.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user inputs a question in natural language. The user inputs the question into the user interface displayed on the terminal and clicks the send button.

[0062] Step 2:

[0063] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[0064] Step 3:

[0065] The server passes the received question to the generative AI. The server inputs the question into the generative AI model for analysis, and natural language processing is performed. This analysis extracts important keywords and content contained in the question.

[0066] Step 4:

[0067] The server generates data extraction conditions based on the content of the question analyzed by the generation AI. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" will be identified.

[0068] Step 5:

[0069] The server extracts the required information from the database using the generated data extraction conditions, establishes a database connection, and executes an SQL query based on the extraction conditions to retrieve the target data.

[0070] Step 6:

[0071] The server analyzes the extracted data and generates a specific answer. For example, it compares sales data from the previous year with this year's and calculates the percentage increase or decrease to calculate a "year-on-year change."

[0072] Step 7:

[0073] The server sends the generated specific answer to the device. The answer is sent from the server to the device in JSON format.

[0074] Step 8:

[0075] The terminal displays the received answer on the user interface. The terminal analyzes the content of the answer and displays it to the user in an appropriate format.

[0076] Through this series of processes, users can quickly obtain the information they need and make timely decisions simply by entering their questions in natural language.

[0077] Example 1

[0078] 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."

[0079] There is a need for a system that allows users to input questions in natural language and automatically retrieves and analyzes the necessary information quickly. However, conventional systems have had difficulty accurately analyzing questions input by users in natural language, quickly extracting relevant data, and generating answers. In particular, the lack of a means to efficiently extract and analyze necessary information from databases has made business analysis and rapid decision-making difficult.

[0080] 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.

[0081] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the question using natural language processing technology that uses a generative AI model and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information using statistical, tabulation, and filtering techniques and generating an answer to the user's question, means for providing the generated answer to the user, and means for providing a user interface and for inputting and transmitting a question in natural language, thereby enabling a user to quickly and easily obtain a specific answer to a question input in natural language.

[0082] "User" refers to an individual or organization that uses the system and enters a question in natural language.

[0083] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that provides a user interface and allows a user to enter and submit a query.

[0084] "Server" refers to a central processing unit for receiving and analyzing user queries and extracting necessary data.

[0085] "Natural language processing technology" refers to technology that uses a generative AI model to analyze natural language questions entered by users and identify important keywords and data extraction conditions.

[0086] A "generative AI model" is a type of machine learning model used to provide natural language processing technology, specifically a model that understands and generates natural language.

[0087] "Database" refers to data storage that stores various data necessary for business analysis.

[0088] "Data extraction criteria" refers to specific conditions or queries for extracting required information from a database.

[0089] "Statistical, aggregation, and filtering techniques" refers to data analysis techniques used to analyze the extracted data and generate specific answers to the user's questions.

[0090] "User interface" refers to a graphical interface through which a user enters a question in natural language and clicks a submit button.

[0091] An "answer" is information generated in response to a user's question, and refers to specific information or numerical values ​​provided based on the results of data analysis.

[0092] The present invention is a system that quickly acquires and analyzes necessary information when a user inputs a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[0093] 1. Receive user questions

[0094] The terminal provides a user interface that allows the user to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system. For example, the user inputs a question such as "What is the year-on-year change in the metropolitan area?" This user interface is implemented using web technologies such as HTML, CSS, and JavaScript (registered trademark).

[0095] 2. Submitting and analyzing questions

[0096] The device sends the user's question to the server. This communication uses the HTTPS protocol to maintain data security. The server passes the question received from the user to a generation AI (for example, a model using natural language processing technology such as OpenAI's (registered trademark) GPT or BERT). The generation AI analyzes the received question, extracts important keywords and content, and generates data extraction conditions based on them.

[0097] 3. Data Extraction

[0098] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries. For example, to extract sales data for the previous year and this year, an SQL query such as "SELECT year, sales FROM sales_data WHERE area = 'Tokyo metropolitan area'" is used.

[0099] 4. Analyze the data and generate answers

[0100] The server analyzes the extracted data and generates a specific answer to the user's question. Methods such as statistical analysis, aggregation, and filtering are used for the analysis. For example, the following processing is performed using Python's pandas library. In response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated. The percentage increase or decrease is calculated as "(this year's sales - last year's sales) / last year's sales 100".

[0101] 5. Providing answers to users

[0102] The server sends the generated answer to the user's device, which then displays the answer on its user interface. This allows the user to instantly obtain the information they need. For example, if a user asks, "What is the year-on-year increase in the Tokyo metropolitan area?", the device will display, "The year-on-year increase in the Tokyo metropolitan area is 5%."

[0103] Specific examples

[0104] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[0105] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[0106] 2. Terminal: Sends the question to the server.

[0107] 3. Server: Analyzes the question and identifies the keywords "Tokyo metropolitan area" and "year-on-year comparison." Analysis is performed using generation AI.

[0108] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[0109] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[0110] 6. Server: Generates the calculation result as an answer and provides it to the user.

[0111] 7. Terminal: Display the answer in a user interface.

[0112] This allows users to omit complex manual work, easily perform complex data analysis in natural language, and quickly obtain the information they need.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1: Receive a question from the user

[0115] When a user inputs a question in natural language and clicks a submit button, the terminal receives the question. This input includes the question text written by the user in natural language. The terminal uses a user interface to provide a text box for inputting the question and a submit button. The user interface is implemented using web technologies such as HTML, CSS, and JavaScript.

[0116] Step 2: Submit your question

[0117] The terminal sends the question entered by the user to the server. The transmission uses the HTTPS protocol to ensure data security. The input is the question text entered by the user in natural language. The output is the question text securely sent to the server.

[0118] Step 3: Parsing the Question

[0119] The server passes the received question to the generative AI model for analysis. The generative AI model uses natural language processing technology (for example, OpenAI's GPT model). The input is the user's natural language question. The output is important keywords and data extraction conditions extracted from the question. Specifically, the generative AI analyzes the question text and identifies keywords such as "metropolitan area" and "year-on-year comparison."

[0120] Step 4: Extracting data

[0121] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data required for business analysis. Here, data is extracted using an SQL query. The input is the data extraction conditions. The output is the specific data retrieved from the database. For example, based on the SQL query "SELECT year, sales FROM sales_data WHERE area = 'Metropolitan area'", sales data for the previous year and this year is extracted.

[0122] Step 5: Analyze the data and generate answers

[0123] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses techniques such as statistical analysis, aggregation, and filtering. The input is the extracted data. The output is the answer obtained through the analysis. Specifically, it uses Python's pandas library to compare sales data from the previous year with this year's sales data and calculate the year-on-year change. The percentage change in sales between the previous year and this year is calculated using the formula "(This year's sales - Last year's sales) / Last year's sales 100".

[0124] Step 6: Provide the user with the answer

[0125] The server sends the generated answer to the user's device. The HTTPS protocol is used again for transmission. The input is the answer generated based on the analysis. The output is the answer provided to the user's device. Specifically, the generated answer (for example, "The metropolitan area has increased by 5% compared to the previous year") is displayed on the user interface, where the user can confirm it.

[0126] (Application example 1)

[0127] 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."

[0128] In conventional logistics centers, managers lacked the means to quickly obtain and analyze information on shipment quantities, inventory, and demand in real time, which led to delays in decision-making. In particular, there was a need for a system that would allow managers to intuitively input questions in natural language and instantly obtain the information they needed.

[0129] 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.

[0130] In this invention, the server includes means for receiving questions in natural language from a user, means for analyzing the received questions and generating data extraction conditions corresponding to the questions, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating answers to the user's questions, means for providing the generated answers to the users, and means for analyzing information regarding shipment numbers, inventory, and demand for logistics centers in natural language and generating answers in real time. This enables managers to intuitively input questions in natural language, instantly obtain and analyze necessary data, and make decisions quickly.

[0131] A "user" is someone who uses the system, such as a manager or worker at a logistics center.

[0132] "Natural language" refers to a language that humans use on a daily basis, such as Japanese or English.

[0133] A "means for receiving a question" is an interface or device that allows a user to input a question in natural language.

[0134] "Means for analyzing questions" refers to the technical means for interpreting received questions and extracting important keywords and meanings.

[0135] "Data extraction conditions" are conditions or filtering rules for retrieving necessary information from a database based on a question.

[0136] A "database" is an information storage system that stores business analysis data and data necessary for the operation of a logistics center.

[0137] "Means for analyzing information" refers to technical means for statistically and numerically analyzing extracted data and generating specific answers.

[0138] A "means for providing an answer" is an interface or device that displays or communicates the generated answer to the user.

[0139] "Number of shipments" refers to the total number of products shipped from a logistics center within a certain period of time.

[0140] "Inventory" refers to the total number of unshipped products and materials in a logistics center.

[0141] "Demand" refers to the number of orders or sales for a particular product.

[0142] The present invention is a system that analyzes information relating to shipments, inventory, and demand at a logistics center in natural language and generates answers in real time. Hereinafter, an embodiment of the present invention will be described in detail.

[0143] System configuration

[0144] The system of the present invention comprises a user interface, a server, a database, and a generative AI model.

[0145] User Interface

[0146] Users input questions in natural language using a device such as a smartphone. The interface has a function that allows users to input a question and then click a send button to pass the question to the system.

[0147] server

[0148] The server receives questions sent from the device and analyzes them using a generative AI model. This generative AI model uses OpenAI's API. When a user enters a question such as "How many units were shipped today?", the server analyzes the question and extracts the key keyword "number of units shipped." Based on the extracted keyword, the server generates an SQL query and extracts the necessary data from the database.

[0149] Database

[0150] The database stores various data necessary for business analysis of the distribution center, such as shipment quantities, inventory, order history, etc. The server uses the generated SQL queries to extract the required data in real time.

[0151] Generative AI Models

[0152] The generative AI model uses natural language processing technology to analyze the user's question and generate data extraction conditions. When the generative AI model receives a question, it extracts specific keywords and phrases. For example, in response to the question, "What are the shipment numbers today?", it focuses on the "shipment number" and generates conditions for extracting the relevant data.

[0153] Data analysis and answer generation

[0154] The server generates an answer to the user's question based on the extracted data. For example, it retrieves information about the number of shipments today from the database and returns an answer to the user such as "The number of shipments today is 500."

[0155] Providing answers to users

[0156] The generated answers are sent from the server to the user's device and displayed on the user interface, allowing the user to instantly obtain the information they need simply by entering their question in natural language.

[0157] Examples of prompt statements

[0158] Here are some examples of prompts:

[0159] User input: "How many units are shipped today?"

[0160] Prompt the generative AI model to identify the information needed based on the following question: "How many shipments are there today?"

[0161] Model response example: Shipment quantity

[0162] Example of a SQL query generated based on this answer:

[0163] SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE

[0164] Thus, the present invention is a system that enables users to intuitively input questions in natural language and obtain necessary information in real time.

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The user inputs a question in natural language using the user interface of the smartphone device. A specific example of input is "How many units are shipped today?" The input is received and the question is sent to the server.

[0168] Step 2:

[0169] The server receives a question sent from the device. An example question is "How many units were shipped today?" The server passes this question to the generative AI model. The generative AI model is used to analyze the question and extract important keywords. In this case, the generative AI model extracts the keyword "number of units shipped." The input is the question, and the output is the analyzed keywords.

[0170] Step 3:

[0171] The server generates data extraction conditions based on the extracted keywords. Specifically, it generates an SQL query. For example, if the keyword is "number of shipments," the generated SQL query will be "SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE." The input is the keyword, and the output is the SQL query.

[0172] Step 4:

[0173] The server uses the generated SQL query to extract the required information from the database. It connects to the database and actually executes the query to obtain today's shipment count. The input is the SQL query, and the output is the shipment count information obtained from the database.

[0174] Step 5:

[0175] The server analyzes the extracted data and generates a specific answer to the user's question. For example, if the number of shipments retrieved from the database is 500, the server generates the answer "Today's shipments are 500." The input is the extracted data, and the output is the answer presented to the user.

[0176] Step 6:

[0177] The server sends the generated answer to the user's terminal. The terminal displays the received answer on the user interface. The user can see an answer such as "Today's shipments are 500 units" on the interface. The input is the generated answer, and the output is the answer displayed on the terminal.

[0178] 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.

[0179] This invention is a system for quickly acquiring and analyzing necessary information by allowing users to input questions in natural language. The system analyzes the user's question and further recognizes the user's emotions using an emotion engine, thereby providing a more appropriate response.

[0180] 1. Receive user questions

[0181] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[0182] 2. Submitting and analyzing questions

[0183] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[0184] 3. Emotion recognition

[0185] The server uses an emotion engine to analyze the emotions from the user's input. For example, if the user's question contains an emotion of anger, the server recognizes this and responds accordingly.

[0186] 4. Data Extraction

[0187] The server generates data extraction conditions based on the content of the question analyzed by the generation AI and the emotion recognition results. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" are identified and reflected in the data extraction conditions. In addition, based on the emotion recognition results, the answer content is adjusted to a format that takes emotion into consideration.

[0188] 5. Data Acquisition

[0189] The server uses the generated data extraction conditions to extract the necessary information from the database. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[0190] 6. Analyze the data and generate answers

[0191] The server analyzes the extracted data and generates specific answers to the user's questions. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from the previous year and this year are compared and the percentage increase or decrease is calculated. An emotion engine also generates responses that take the user's emotions into consideration.

[0192] 7. Providing answers to users

[0193] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[0194] Specific examples

[0195] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?" the system will operate as follows:

[0196] 1. User: Type a question in natural language: "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-over-year performance?"

[0197] 2. Terminal: Sends the question to the server.

[0198] 3. Server: Analyzes the question and identifies the keywords "metropolitan area," "year-on-year comparison," and "details."

[0199] 4. Server: The emotion engine recognizes when the user has feelings of dissatisfaction or doubt.

[0200] 5. Server: Based on these keywords and emotion recognition results, extract sales data and detailed information for the previous and current years from the database.

[0201] 6. Server: Analyzes the acquired data and generates an emotionally sensitive response, such as, "Year-on-year sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of key customers and an increase in competition. For more details, please see this report."

[0202] 7. Terminal: Display the answer in a user interface.

[0203] In this way, the present invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, the emotion engine provides responses that take the user's emotions into consideration, improving the user experience.

[0204] The processing flow will be explained below.

[0205] Step 1:

[0206] The user inputs a question in natural language. The user inputs a question such as "Why is the year-on-year change in the Tokyo metropolitan area low? Can you tell me the details?" into the user interface displayed on the terminal, and clicks the send button.

[0207] Step 2:

[0208] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[0209] Step 3:

[0210] The server passes the received question to the generation AI. The server inputs the question into the generation AI model and performs natural language processing. The generation AI analyzes the question and extracts important keywords such as "metropolitan area," "year-on-year comparison," and "details."

[0211] Step 4:

[0212] The server uses an emotion engine to analyze the user's input to determine their feelings. For example, the emotion engine can recognize from the tone and wording of a question that the user is dissatisfied or suspicious.

[0213] Step 5:

[0214] The server generates data extraction conditions based on the analyzed question content and emotion recognition results. For example, in addition to the keywords "Tokyo metropolitan area," "year-on-year comparison," and "details," it generates data extraction conditions that reflect considerations based on the emotion recognition results.

[0215] Step 6:

[0216] The server uses the generated data extraction criteria to extract the required information from the database, establishes a database connection, and executes an interactive SQL query to obtain the target data (e.g., sales data and detailed information for the previous and current years).

[0217] Step 7:

[0218] The server analyzes the extracted data and generates specific answers to the user's questions. The server compares sales data from the previous year with this year's and analyzes the reasons for the decline. The emotion engine generates answers that take the user's emotions into consideration.

[0219] Step 8:

[0220] The server sends the generated answer to the user's device. The server converts the answer into JSON format and sends it to the device.

[0221] Step 9:

[0222] The terminal displays the received response on the user interface. The terminal analyzes the response and displays to the user the following: "Year-on-year sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of major customers and an increase in competition. For more details, please see this report."

[0223] This series of processes allows users to simply input their questions in natural language and instantly receive specific, emotionally sensitive answers, enabling them to quickly and efficiently obtain the information they need and make decisions.

[0224] Example 2

[0225] 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."

[0226] Conventional information retrieval systems have difficulty accurately understanding user questions and providing appropriate answers. Furthermore, answers generated without considering the user's emotions have the problem of failing to improve the user experience. Therefore, a new system that combines natural language processing technology and emotion analysis is needed.

[0227] 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.

[0228] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the received question and recognizing the user's emotion using emotion analysis technology, means for generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables the user to quickly obtain the necessary information by asking a question in natural language and receive an appropriate response that takes into consideration the user's emotion at the time.

[0229] A "natural language" is a language that humans use on a daily basis and is created without the expectation of being processed by a computer.

[0230] "Means for analyzing questions" refers to technology for understanding natural language questions received from users and extracting important keywords and content.

[0231] "Emotion analysis technology" is a technology that automatically determines emotions from user input and uses the results.

[0232] The "means for generating data extraction conditions" is a technology for creating conditions for extracting information from a database based on the analyzed questions and the results of emotion recognition.

[0233] A "database" is a system that systematically stores various types of information and allows for efficient search and extraction of that information as needed.

[0234] "Means for extracting information" refers to a technique for extracting necessary information from a database based on the generated data extraction conditions.

[0235] "Means for analyzing information" refers to technology that processes extracted information using methods such as statistics and aggregation to generate specific answers to users' questions.

[0236] The "means for providing an answer" refers to a technique for delivering the generated answer to the user, and is displayed through the user interface of the terminal.

[0237] MODE FOR CARRYING OUT THE INVENTION

[0238] The present invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system analyzes the user's question and further recognizes the user's emotions using emotion analysis technology, thereby providing a more appropriate response.

[0239] Hardware and software used

[0240] Terminal

[0241] Personal computers, smartphones, tablets, etc.

[0242] Providing a user interface using a web browser or mobile application

[0243] server

[0244] Cloud servers are used, and cloud service providers (e.g., AWS (registered trademark), Google (registered trademark), Microsoft (registered trademark) Azure (registered trademark)) are used.

[0245] Generation AI

[0246] Natural language processing models (e.g., GPT-3 (registered trademark), BERT) are used

[0247] Emotion Engine

[0248] Sentiment analysis tools (e.g., IBM Watson® Emotion Analysis) are used

[0249] Database

[0250] An SQL database (e.g., MySQL, PostgreSQL) is used

[0251] Specific operation of the system

[0252] The specific operation of this system will be explained in natural language below.

[0253] 1. Users

[0254] Enter a question in natural language and click the send button through the terminal's user interface. For example, enter the question, "Why is the year-on-year change in the metropolitan area low? Please tell me the details."

[0255] 2. Terminal

[0256] Use an HTTP POST request to send the question to the server.

[0257] 3. Server

[0258] The received question is passed to a generative AI model, which extracts key keywords and content. For example, it extracts keywords such as "metropolitan area," "year-on-year comparison," and "details."

[0259] Analyze user emotions using an emotion engine. The emotion engine recognizes emotions such as dissatisfaction and doubt from the user's questions.

[0260] Based on these keywords and the emotion recognition results, data extraction conditions (SQL queries) for retrieving data from the database are generated.

[0261] 4. Server

[0262] Use SQL queries to extract the required information from the database, for example, "Sales data for the Greater Tokyo area last year and this year."

[0263] The extracted data is analyzed using methods such as statistical processing and aggregation to generate specific answers to the user's questions. For example, it generates an answer such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is thought to be due to a decline in the purchasing power of major customers and an increase in competition."

[0264] 5. Server

[0265] The generated answer is sent to the user's terminal.

[0266] 6. Terminal

[0267] The received response is displayed in the user interface so that the user can review it.

[0268] Specific examples

[0269] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?", the following will happen:

[0270] The user types in "Why is the year-on-year change in the Tokyo metropolitan area low? Can you give me more details?" and clicks the submit button.

[0271] The terminal sends a question to the server.

[0272] The server passes the question to a generative AI model for analysis, which extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[0273] The server passes the question to the emotion engine, which recognizes the user's emotion as dissatisfaction or doubt.

[0274] The server generates SQL queries based on these keywords and sentiment results to retrieve sales data from a database.

[0275] The server executes an SQL query to retrieve "sales data for the previous year and this year."

[0276] The server analyzes the data and generates emotionally sensitive responses, such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to last year. This is due to a decline in the purchasing power of key customers and increased competition."

[0277] The server generates a response and sends it to the terminal.

[0278] The terminal displays the answer on the user interface and the user confirms it.

[0279] Examples of prompt statements

[0280] Here is an example of a prompt the user might enter:

[0281] Could you please explain in detail why the year-on-year figures for the Greater Tokyo area are low?

[0282] This invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, emotion analysis technology can be used to provide responses that take the user's emotions into consideration, improving the user experience.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1:

[0285] The user enters a question in natural language and clicks the submit button. Specifically, the user enters the question in an input box provided in the user interface. For example, the user enters, "Why is the year-on-year change in the metropolitan area low? Can you give me more details?"

[0286] Input: Question

[0287] Output: Question data from the user

[0288] Step 2:

[0289] The device sends the user's question to the server via an HTTP POST request. Specifically, communication is performed over the Internet to send the entered question data to the server.

[0290] Input: Question data from the user

[0291] Output: The query data sent to the server

[0292] Step 3:

[0293] The server passes the received question to a generative AI model. Specifically, natural language processing technology is used to analyze the question and extract key keywords and content. For example, a generative AI model, a natural language processing model (e.g., GPT-3), extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[0294] Input: Query data sent to the server

[0295] Output: Extracted keyword data

[0296] Step 4:

[0297] The server uses emotion analysis technology to analyze the user's emotions. Specifically, it uses an emotion analysis engine to recognize the user's emotions from the content of the question. For example, the emotion analysis engine recognizes emotions such as dissatisfaction and doubt.

[0298] Input: Query data sent to the server

[0299] Output: Recognized emotion data

[0300] Step 5:

[0301] The server generates data extraction conditions based on the generated keyword data and emotion data. Specifically, it constructs an SQL query based on this data and sets the conditions for extracting information from the database. For example, it generates an SQL query based on the conditions "Metropolitan area," "Year-on-year comparison," and "Details."

[0302] Input: extracted keyword data, recognized emotion data

[0303] Output: Generated data extraction criteria (SQL query)

[0304] Step 6:

[0305] The server uses the generated data extraction conditions (SQL query) to extract the necessary information from the database. Specifically, it executes a query on the database to obtain, for example, "sales data for the Tokyo metropolitan area for the previous year and this year."

[0306] Input: Generated data extraction conditions (SQL query)

[0307] Output: Extracted data

[0308] Step 7:

[0309] The server analyzes the extracted data and generates a specific answer to the user's question. Specifically, it processes the data using methods such as statistical processing and aggregation, and generates an answer such as, "Sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to factors such as a decline in the purchasing power of major customers and an increase in competition."

[0310] Input: Extracted data

[0311] Output: Generated response data

[0312] Step 8:

[0313] The server sends the generated answer data to the user's device. Specifically, it sends the answer data back to the device via an HTTP response.

[0314] Input: Generated response data

[0315] Output: Response data sent to the device

[0316] Step 9:

[0317] The device displays the received response data on the user interface. Specifically, the response is displayed on the screen as text or graphs, and the user can check the information.

[0318] Input: Answer data sent to the terminal

[0319] Output: The answer displayed to the user

[0320] (Application example 2)

[0321] 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."

[0322] While conventional information acquisition systems can quickly generate answers to user questions, they lack the ability to provide answers that take the user's emotions into consideration. This can result in a lack of appropriate communication regarding the user's questions and complaints, potentially resulting in a poor user experience. Furthermore, there are few systems specifically designed for questions regarding the status of autonomous vehicles, and these systems are particularly insufficient in situations where responses that take emotions into consideration are required. To solve these problems, a system that analyzes the user's emotions and generates responses based on those emotions is needed.

[0323] 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.

[0324] In this invention, the server includes means for receiving a question in natural language from a user, emotion recognition means for analyzing the emotion of the received question, means for analyzing the received question and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables a user to input a question about the status of an autonomous vehicle in natural language and receive a quick and appropriate answer to the question that takes emotion into consideration.

[0325] A "user" is a person who enters a question into the system in natural language.

[0326] A "question" is something a user inputs to a system in natural language, requesting information.

[0327] "Emotion recognition means" is a technology for analyzing the emotions contained in a user's question.

[0328] "Data extraction conditions" are conditions for analyzing a received question and extracting information corresponding to that question from a database.

[0329] "Natural language processing technology" is a technology that processes human language using a computer and analyzes its meaning and intent.

[0330] A "database" is a collection of data that stores necessary information.

[0331] A "business analysis database" is a database that stores various data necessary for business activities and analyzes and extracts that data.

[0332] The "information extraction means" is a means for extracting necessary information from a database using the generated data extraction conditions.

[0333] The "answer generation means" is a means for analyzing the extracted information and creating an answer to the user's question.

[0334] An "autonomous vehicle" is a vehicle that can drive itself without a driver.

[0335] MODE FOR CARRYING OUT THE INVENTION

[0336] The present invention provides a system for generating emotionally sensitive answers based on the status information of an autonomous vehicle in response to a question input by a user in natural language. This system uses the following specific method and configuration.

[0337] 1. The user enters a question in natural language from the device.

[0338] Users use an application installed on a device such as a smartphone or tablet to input a question in natural language, for example, "How safe is the current autonomous driving mode?"

[0339] 2. The device sends a question to the server

[0340] The terminal sends the entered question to the server, which converts the question into an appropriate format and passes it to the server.

[0341] 3. The server parses the question

[0342] The server analyzes the received question using natural language processing techniques, such as using a generative AI model to extract important keywords and intent from the question.

[0343] 4. Emotion analysis using emotion recognition methods

[0344] The server uses an emotion recognition engine (e.g., the transformers library) to analyze the emotion (e.g., anxiety or doubt) contained in the question.

[0345] 5. Creating data extraction conditions

[0346] The server generates data extraction conditions, including SQL queries, based on the analyzed question keywords and emotion recognition results.

[0347] 6. Extracting information from databases

[0348] The server uses the generated data extraction conditions to extract necessary information from a database related to autonomous vehicles, specifically data related to the status of autonomous driving modes and safety.

[0349] 7. Answer Generation

[0350] The server generates a specific answer to the question based on the extracted data. In doing so, it takes into account the emotion recognition results and adjusts the answer to take the user's emotions into consideration. For example, it generates an answer such as, "There's no need to worry. The current autonomous driving mode is operating normally. Everything is going smoothly."

[0351] 8. Providing answers to users

[0352] The server sends the generated answer to the user's terminal, which displays the answer on a user interface.

[0353] Hardware and software used

[0354] Device (smartphone or tablet)

[0355] It provides an interface for users to enter questions in natural language.

[0356] server

[0357] It analyzes the received questions, generates data extraction conditions, extracts and analyzes information from the database, and generates answers.

[0358] Database

[0359] It stores various data related to autonomous vehicles. For example, it uses SQLite.

[0360] Natural language processing technology

[0361] Uses generative AI models and emotion recognition engines (transformers library).

[0362] Specific examples

[0363] When a user inputs the question, "How safe is the current autonomous driving mode?", the system will pull relevant information from the autonomous vehicle's database and generate an answer taking into account the emotional state. For example, it may provide the user with a response such as, "There's nothing to worry about. The current autonomous driving mode is operating normally. Everything is going smoothly."

[0364] Prompt Sentence Examples

[0365] Question: How safe is the current autonomous driving mode?

[0366] Answer: There is no need to worry. The current autonomous driving mode is working normally. All driving conditions are normal.

[0367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0368] Step 1:

[0369] A user uses a terminal to input a question in natural language and submits the question.

[0370] The user opens the application on their smartphone or tablet and enters a question such as, "How safe is the current autonomous driving mode?" After confirming the input and pressing the send button, the question is sent from the device to the server.

[0371] Input: User's natural language question

[0372] Output: The user's question is sent to the server

[0373] Step 2:

[0374] The terminal receives the user's question and forwards it to the server.

[0375] The terminal receives a natural language question sent by the user and transmits the content of the question to the server in an appropriate format.

[0376] Input: The user's question received by the device

[0377] Output: The user's question sent to the server

[0378] Step 3:

[0379] The server analyzes the user's question and extracts keywords and intent.

[0380] The server uses a generative AI model to analyze the received question and extract important keywords and the intent of the question, for example, identifying the keywords "current autonomous driving mode" and "safety."

[0381] Input: The user's question received by the server

[0382] Output: Extracted keywords and question intent

[0383] Step 4:

[0384] The server uses an emotion recognition engine to analyze the user's emotions.

[0385] The server uses the transformers library to analyze the sentiment of the question, for example, to identify whether the question expresses frustration or anxiety.

[0386] Input: User question

[0387] Output: Parsed emotion information

[0388] Step 5:

[0389] The server generates the data extraction conditions.

[0390] The server generates data extraction conditions based on the analyzed keywords and emotion information. For example, it generates an SQL query for data that meets the conditions "autonomous driving mode" and "safety."

[0391] Input: Extracted keywords and sentiment information

[0392] Output: Generated data extraction criteria (SQL query)

[0393] Step 6:

[0394] The server extracts the necessary information from the database.

[0395] The server uses the generated data extraction conditions to extract the necessary information from a database related to autonomous vehicles.

[0396] Input: Data extraction conditions (SQL query)

[0397] Output: Extracted data (e.g., autonomous driving mode status data)

[0398] Step 7:

[0399] The server analyzes the extracted data and generates answers to the user's questions.

[0400] The server uses the extracted data to generate specific answers to the user's questions and adjusts the answers based on emotional information, such as "Don't worry, the current autonomous driving mode is working properly."

[0401] Input: Extracted data and sentiment information

[0402] Output: The generated answer

[0403] Step 8:

[0404] The server transmits the generated answer to the user's terminal and provides it to the user.

[0405] The server sends the generated answer to the user's terminal, which displays the answer on the user's screen.

[0406] Input: Generated Answer

[0407] Output: Answer displayed on the user's terminal

[0408] 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.

[0409] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0410] 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.

[0411] [Second embodiment]

[0412] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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."

[0424] This invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[0425] 1. Receive user questions

[0426] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[0427] 2. Submitting and analyzing questions

[0428] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[0429] 3. Data Extraction

[0430] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generative AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[0431] 4. Analyze the data and generate answers

[0432] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How is sales in the Tokyo metropolitan area compared to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated.

[0433] 5. Providing answers to users

[0434] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[0435] Specific examples

[0436] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[0437] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[0438] 2. Terminal: Sends the question to the server.

[0439] 3. Server: Analyzes the question and identifies the keywords "metropolitan area" and "year-on-year comparison."

[0440] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[0441] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[0442] 6. Server: Generates the calculation result as an answer and provides it to the user.

[0443] 7. Terminal: Display the answer in a user interface.

[0444] In this way, the present invention allows users to easily perform complex data analysis using natural language, eliminating the need for complex manual tasks, enabling them to quickly obtain necessary information and make instant decisions in situations such as meetings and business negotiations.

[0445] The processing flow will be explained below.

[0446] Step 1:

[0447] The user inputs a question in natural language. The user inputs the question into the user interface displayed on the terminal and clicks the send button.

[0448] Step 2:

[0449] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[0450] Step 3:

[0451] The server passes the received question to the generative AI. The server inputs the question into the generative AI model for analysis, and natural language processing is performed. This analysis extracts important keywords and content contained in the question.

[0452] Step 4:

[0453] The server generates data extraction conditions based on the content of the question analyzed by the generation AI. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" will be identified.

[0454] Step 5:

[0455] The server extracts the required information from the database using the generated data extraction conditions, establishes a database connection, and executes an SQL query based on the extraction conditions to retrieve the target data.

[0456] Step 6:

[0457] The server analyzes the extracted data and generates a specific answer. For example, it compares sales data from the previous year with this year's and calculates the percentage increase or decrease to calculate a "year-on-year change."

[0458] Step 7:

[0459] The server sends the generated specific answer to the device. The answer is sent from the server to the device in JSON format.

[0460] Step 8:

[0461] The terminal displays the received answer on the user interface. The terminal analyzes the content of the answer and displays it to the user in an appropriate format.

[0462] Through this series of processes, users can quickly obtain the information they need and make timely decisions simply by entering their questions in natural language.

[0463] Example 1

[0464] 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."

[0465] There is a need for a system that allows users to input questions in natural language and automatically retrieves and analyzes the necessary information quickly. However, conventional systems have had difficulty accurately analyzing questions input by users in natural language, quickly extracting relevant data, and generating answers. In particular, the lack of a means to efficiently extract and analyze necessary information from databases has made business analysis and rapid decision-making difficult.

[0466] 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.

[0467] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the question using natural language processing technology that uses a generative AI model and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information using statistical, tabulation, and filtering techniques and generating an answer to the user's question, means for providing the generated answer to the user, and means for providing a user interface and for inputting and transmitting a question in natural language, thereby enabling a user to quickly and easily obtain a specific answer to a question input in natural language.

[0468] "User" refers to an individual or organization that uses the system and enters a question in natural language.

[0469] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that provides a user interface and allows a user to enter and submit a query.

[0470] "Server" refers to a central processing unit for receiving and analyzing user queries and extracting necessary data.

[0471] "Natural language processing technology" refers to technology that uses a generative AI model to analyze natural language questions entered by users and identify important keywords and data extraction conditions.

[0472] A "generative AI model" is a type of machine learning model used to provide natural language processing technology, specifically a model that understands and generates natural language.

[0473] "Database" refers to data storage that stores various data necessary for business analysis.

[0474] "Data extraction criteria" refers to specific conditions or queries for extracting required information from a database.

[0475] "Statistical, aggregation, and filtering techniques" refers to data analysis techniques used to analyze the extracted data and generate specific answers to the user's questions.

[0476] "User interface" refers to a graphical interface through which a user enters a question in natural language and clicks a submit button.

[0477] An "answer" is information generated in response to a user's question, and refers to specific information or numerical values ​​provided based on the results of data analysis.

[0478] The present invention is a system that quickly acquires and analyzes necessary information when a user inputs a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[0479] 1. Receive user questions

[0480] The terminal provides a user interface that allows the user to input questions in natural language. The user inputs a question in natural language and clicks the submit button, which passes the question to the system. For example, a user inputs a question such as "What is the year-on-year change in the metropolitan area?" This user interface is implemented using web technologies such as HTML, CSS, and JavaScript.

[0481] 2. Submitting and analyzing questions

[0482] The device sends the user's question to the server. This communication uses the HTTPS protocol to ensure data security. The server then passes the question received from the user to a generation AI (for example, a model using natural language processing technology such as OpenAI's GPT or BERT). The generation AI analyzes the received question, extracts important keywords and content, and generates data extraction conditions based on that.

[0483] 3. Data Extraction

[0484] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries. For example, to extract sales data for the previous year and this year, an SQL query such as "SELECT year, sales FROM sales_data WHERE area = 'Tokyo metropolitan area'" is used.

[0485] 4. Analyze the data and generate answers

[0486] The server analyzes the extracted data and generates a specific answer to the user's question. Methods such as statistical analysis, aggregation, and filtering are used for the analysis. For example, the following processing is performed using Python's pandas library. In response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated. The percentage increase or decrease is calculated as "(this year's sales - last year's sales) / last year's sales 100".

[0487] 5. Providing answers to users

[0488] The server sends the generated answer to the user's device, which then displays the answer on its user interface. This allows the user to instantly obtain the information they need. For example, if a user asks, "What is the year-on-year increase in the Tokyo metropolitan area?", the device will display, "The year-on-year increase in the Tokyo metropolitan area is 5%."

[0489] Specific examples

[0490] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[0491] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[0492] 2. Terminal: Sends the question to the server.

[0493] 3. Server: Analyzes the question and identifies the keywords "Tokyo metropolitan area" and "year-on-year comparison." Analysis is performed using generation AI.

[0494] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[0495] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[0496] 6. Server: Generates the calculation result as an answer and provides it to the user.

[0497] 7. Terminal: Display the answer in a user interface.

[0498] This allows users to omit complex manual work, easily perform complex data analysis in natural language, and quickly obtain the information they need.

[0499] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0500] Step 1: Receive a question from the user

[0501] When a user inputs a question in natural language and clicks a submit button, the terminal receives the question. This input includes the question text written by the user in natural language. The terminal uses a user interface to provide a text box for inputting the question and a submit button. The user interface is implemented using web technologies such as HTML, CSS, and JavaScript.

[0502] Step 2: Submit your question

[0503] The terminal sends the question entered by the user to the server. The transmission uses the HTTPS protocol to ensure data security. The input is the question text entered by the user in natural language. The output is the question text securely sent to the server.

[0504] Step 3: Parsing the Question

[0505] The server passes the received question to the generative AI model for analysis. The generative AI model uses natural language processing technology (for example, OpenAI's GPT model). The input is the user's natural language question. The output is important keywords and data extraction conditions extracted from the question. Specifically, the generative AI analyzes the question text and identifies keywords such as "metropolitan area" and "year-on-year comparison."

[0506] Step 4: Extracting data

[0507] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data required for business analysis. Here, data is extracted using an SQL query. The input is the data extraction conditions. The output is the specific data retrieved from the database. For example, based on the SQL query "SELECT year, sales FROM sales_data WHERE area = 'Metropolitan area'", sales data for the previous year and this year is extracted.

[0508] Step 5: Analyze the data and generate answers

[0509] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses techniques such as statistical analysis, aggregation, and filtering. The input is the extracted data. The output is the answer obtained through the analysis. Specifically, it uses Python's pandas library to compare sales data from the previous year with this year's sales data and calculate the year-on-year change. The percentage change in sales between the previous year and this year is calculated using the formula "(This year's sales - Last year's sales) / Last year's sales 100".

[0510] Step 6: Provide the user with the answer

[0511] The server sends the generated answer to the user's device. The HTTPS protocol is used again for transmission. The input is the answer generated based on the analysis. The output is the answer provided to the user's device. Specifically, the generated answer (for example, "The metropolitan area has increased by 5% compared to the previous year") is displayed on the user interface, where the user can confirm it.

[0512] (Application example 1)

[0513] 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."

[0514] In conventional logistics centers, managers lacked the means to quickly obtain and analyze information on shipment quantities, inventory, and demand in real time, which led to delays in decision-making. In particular, there was a need for a system that would allow managers to intuitively input questions in natural language and instantly obtain the information they needed.

[0515] 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.

[0516] In this invention, the server includes means for receiving questions in natural language from a user, means for analyzing the received questions and generating data extraction conditions corresponding to the questions, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating answers to the user's questions, means for providing the generated answers to the users, and means for analyzing information regarding shipment numbers, inventory, and demand for logistics centers in natural language and generating answers in real time. This enables managers to intuitively input questions in natural language, instantly obtain and analyze necessary data, and make decisions quickly.

[0517] A "user" is someone who uses the system, such as a manager or worker at a logistics center.

[0518] "Natural language" refers to a language that humans use on a daily basis, such as Japanese or English.

[0519] A "means for receiving a question" is an interface or device that allows a user to input a question in natural language.

[0520] "Means for analyzing questions" refers to the technical means for interpreting received questions and extracting important keywords and meanings.

[0521] "Data extraction conditions" are conditions or filtering rules for retrieving necessary information from a database based on a question.

[0522] A "database" is an information storage system that stores business analysis data and data necessary for the operation of a logistics center.

[0523] "Means for analyzing information" refers to technical means for statistically and numerically analyzing extracted data and generating specific answers.

[0524] A "means for providing an answer" is an interface or device that displays or communicates the generated answer to the user.

[0525] "Number of shipments" refers to the total number of products shipped from a logistics center within a certain period of time.

[0526] "Inventory" refers to the total number of unshipped products and materials in a logistics center.

[0527] "Demand" refers to the number of orders or sales for a particular product.

[0528] The present invention is a system that analyzes information relating to shipments, inventory, and demand at a logistics center in natural language and generates answers in real time. Hereinafter, an embodiment of the present invention will be described in detail.

[0529] System configuration

[0530] The system of the present invention comprises a user interface, a server, a database, and a generative AI model.

[0531] User Interface

[0532] Users input questions in natural language using a device such as a smartphone. The interface has a function that allows users to input a question and then click a send button to pass the question to the system.

[0533] server

[0534] The server receives questions sent from the device and analyzes them using a generative AI model. This generative AI model uses OpenAI's API. When a user enters a question such as "How many units were shipped today?", the server analyzes the question and extracts the key keyword "number of units shipped." Based on the extracted keyword, the server generates an SQL query and extracts the necessary data from the database.

[0535] Database

[0536] The database stores various data necessary for business analysis of the distribution center, such as shipment quantities, inventory, order history, etc. The server uses the generated SQL queries to extract the required data in real time.

[0537] Generative AI Models

[0538] The generative AI model uses natural language processing technology to analyze the user's question and generate data extraction conditions. When the generative AI model receives a question, it extracts specific keywords and phrases. For example, in response to the question, "What are the shipment numbers today?", it focuses on the "shipment number" and generates conditions for extracting the relevant data.

[0539] Data analysis and answer generation

[0540] The server generates an answer to the user's question based on the extracted data. For example, it retrieves information about the number of shipments today from the database and returns an answer to the user such as "The number of shipments today is 500."

[0541] Providing answers to users

[0542] The generated answers are sent from the server to the user's device and displayed on the user interface, allowing the user to instantly obtain the information they need simply by entering their question in natural language.

[0543] Examples of prompt statements

[0544] Here are some examples of prompts:

[0545] User input: "How many units are shipped today?"

[0546] Prompt the generative AI model to identify the information needed based on the following question: "How many shipments are there today?"

[0547] Model response example: Shipment quantity

[0548] Example of a SQL query generated based on this answer:

[0549] SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE

[0550] Thus, the present invention is a system that enables users to intuitively input questions in natural language and obtain necessary information in real time.

[0551] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0552] Step 1:

[0553] The user inputs a question in natural language using the user interface of the smartphone device. A specific example of input is "How many units are shipped today?" The input is received and the question is sent to the server.

[0554] Step 2:

[0555] The server receives a question sent from the device. An example question is "How many units were shipped today?" The server passes this question to the generative AI model. The generative AI model is used to analyze the question and extract important keywords. In this case, the generative AI model extracts the keyword "number of units shipped." The input is the question, and the output is the analyzed keywords.

[0556] Step 3:

[0557] The server generates data extraction conditions based on the extracted keywords. Specifically, it generates an SQL query. For example, if the keyword is "number of shipments," the generated SQL query will be "SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE." The input is the keyword, and the output is the SQL query.

[0558] Step 4:

[0559] The server uses the generated SQL query to extract the required information from the database. It connects to the database and actually executes the query to obtain today's shipment count. The input is the SQL query, and the output is the shipment count information obtained from the database.

[0560] Step 5:

[0561] The server analyzes the extracted data and generates a specific answer to the user's question. For example, if the number of shipments retrieved from the database is 500, the server generates the answer "Today's shipments are 500." The input is the extracted data, and the output is the answer presented to the user.

[0562] Step 6:

[0563] The server sends the generated answer to the user's terminal. The terminal displays the received answer on the user interface. The user can see an answer such as "Today's shipments are 500 units" on the interface. The input is the generated answer, and the output is the answer displayed on the terminal.

[0564] 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.

[0565] This invention is a system for quickly acquiring and analyzing necessary information by allowing users to input questions in natural language. The system analyzes the user's question and further recognizes the user's emotions using an emotion engine, thereby providing a more appropriate response.

[0566] 1. Receive user questions

[0567] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[0568] 2. Submitting and analyzing questions

[0569] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[0570] 3. Emotion recognition

[0571] The server uses an emotion engine to analyze the emotions from the user's input. For example, if the user's question contains an emotion of anger, the server recognizes this and responds accordingly.

[0572] 4. Data Extraction

[0573] The server generates data extraction conditions based on the content of the question analyzed by the generation AI and the emotion recognition results. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" are identified and reflected in the data extraction conditions. In addition, based on the emotion recognition results, the answer content is adjusted to a format that takes emotion into consideration.

[0574] 5. Data Acquisition

[0575] The server uses the generated data extraction conditions to extract the necessary information from the database. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[0576] 6. Analyze the data and generate answers

[0577] The server analyzes the extracted data and generates specific answers to the user's questions. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from the previous year and this year are compared and the percentage increase or decrease is calculated. An emotion engine also generates responses that take the user's emotions into consideration.

[0578] 7. Providing answers to users

[0579] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[0580] Specific examples

[0581] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?" the system will operate as follows:

[0582] 1. User: Type a question in natural language: "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-over-year performance?"

[0583] 2. Terminal: Sends the question to the server.

[0584] 3. Server: Analyzes the question and identifies the keywords "metropolitan area," "year-on-year comparison," and "details."

[0585] 4. Server: The emotion engine recognizes when the user has feelings of dissatisfaction or doubt.

[0586] 5. Server: Based on these keywords and emotion recognition results, extract sales data and detailed information for the previous and current years from the database.

[0587] 6. Server: Analyzes the acquired data and generates an emotionally sensitive response, such as, "Year-on-year sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of key customers and an increase in competition. For more details, please see this report."

[0588] 7. Terminal: Display the answer in a user interface.

[0589] In this way, the present invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, the emotion engine provides responses that take the user's emotions into consideration, improving the user experience.

[0590] The processing flow will be explained below.

[0591] Step 1:

[0592] The user inputs a question in natural language. The user inputs a question such as "Why is the year-on-year change in the Tokyo metropolitan area low? Can you tell me the details?" into the user interface displayed on the terminal, and clicks the send button.

[0593] Step 2:

[0594] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[0595] Step 3:

[0596] The server passes the received question to the generation AI. The server inputs the question into the generation AI model and performs natural language processing. The generation AI analyzes the question and extracts important keywords such as "metropolitan area," "year-on-year comparison," and "details."

[0597] Step 4:

[0598] The server uses an emotion engine to analyze the user's input to determine their feelings. For example, the emotion engine can recognize from the tone and wording of a question that the user is dissatisfied or suspicious.

[0599] Step 5:

[0600] The server generates data extraction conditions based on the analyzed question content and emotion recognition results. For example, in addition to the keywords "Tokyo metropolitan area," "year-on-year comparison," and "details," it generates data extraction conditions that reflect considerations based on the emotion recognition results.

[0601] Step 6:

[0602] The server uses the generated data extraction criteria to extract the required information from the database, establishes a database connection, and executes an interactive SQL query to obtain the target data (e.g., sales data and detailed information for the previous and current years).

[0603] Step 7:

[0604] The server analyzes the extracted data and generates specific answers to the user's questions. The server compares sales data from the previous year with this year's and analyzes the reasons for the decline. The emotion engine generates answers that take the user's emotions into consideration.

[0605] Step 8:

[0606] The server sends the generated answer to the user's device. The server converts the answer into JSON format and sends it to the device.

[0607] Step 9:

[0608] The terminal displays the received response on the user interface. The terminal analyzes the response and displays to the user the following: "Year-on-year sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of major customers and an increase in competition. For more details, please see this report."

[0609] This series of processes allows users to simply input their questions in natural language and instantly receive specific, emotionally sensitive answers, enabling them to quickly and efficiently obtain the information they need and make decisions.

[0610] Example 2

[0611] 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."

[0612] Conventional information retrieval systems have difficulty accurately understanding user questions and providing appropriate answers. Furthermore, answers generated without considering the user's emotions have the problem of failing to improve the user experience. Therefore, a new system that combines natural language processing technology and emotion analysis is needed.

[0613] 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.

[0614] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the received question and recognizing the user's emotion using emotion analysis technology, means for generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables the user to quickly obtain the necessary information by asking a question in natural language and receive an appropriate response that takes into consideration the user's emotion at the time.

[0615] A "natural language" is a language that humans use on a daily basis and is created without the expectation of being processed by a computer.

[0616] "Means for analyzing questions" refers to technology for understanding natural language questions received from users and extracting important keywords and content.

[0617] "Emotion analysis technology" is a technology that automatically determines emotions from user input and uses the results.

[0618] The "means for generating data extraction conditions" is a technology for creating conditions for extracting information from a database based on the analyzed questions and the results of emotion recognition.

[0619] A "database" is a system that systematically stores various types of information and allows for efficient search and extraction of that information as needed.

[0620] "Means for extracting information" refers to a technique for extracting necessary information from a database based on the generated data extraction conditions.

[0621] "Means for analyzing information" refers to technology that processes extracted information using methods such as statistics and aggregation to generate specific answers to users' questions.

[0622] The "means for providing an answer" refers to a technique for delivering the generated answer to the user, and is displayed through the user interface of the terminal.

[0623] MODE FOR CARRYING OUT THE INVENTION

[0624] The present invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system analyzes the user's question and further recognizes the user's emotions using emotion analysis technology, thereby providing a more appropriate response.

[0625] Hardware and software used

[0626] Terminal

[0627] Personal computers, smartphones, tablets, etc.

[0628] Providing a user interface using a web browser or mobile application

[0629] server

[0630] Cloud servers are used and cloud service providers (e.g. AWS, Google Cloud, Microsoft Azure) are used.

[0631] Generation AI

[0632] Natural language processing models (e.g., GPT-3, BERT) are used

[0633] Emotion Engine

[0634] Sentiment analysis tools (e.g. IBM Watson Emotion Analysis) are used

[0635] Database

[0636] An SQL database (e.g., MySQL, PostgreSQL) is used

[0637] Specific operation of the system

[0638] The specific operation of this system will be explained in natural language below.

[0639] 1. Users

[0640] Enter a question in natural language and click the send button through the terminal's user interface. For example, enter the question, "Why is the year-on-year change in the metropolitan area low? Please tell me the details."

[0641] 2. Terminal

[0642] Use an HTTP POST request to send the question to the server.

[0643] 3. Server

[0644] The received question is passed to a generative AI model, which extracts key keywords and content. For example, it extracts keywords such as "metropolitan area," "year-on-year comparison," and "details."

[0645] Analyze user emotions using an emotion engine. The emotion engine recognizes emotions such as dissatisfaction and doubt from the user's questions.

[0646] Based on these keywords and the emotion recognition results, data extraction conditions (SQL queries) for retrieving data from the database are generated.

[0647] 4. Server

[0648] Use SQL queries to extract the required information from the database, for example, "Sales data for the Greater Tokyo area last year and this year."

[0649] The extracted data is analyzed using methods such as statistical processing and aggregation to generate specific answers to the user's questions. For example, it generates an answer such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is thought to be due to a decline in the purchasing power of major customers and an increase in competition."

[0650] 5. Server

[0651] The generated answer is sent to the user's terminal.

[0652] 6. Terminal

[0653] The received response is displayed in the user interface so that the user can review it.

[0654] Specific examples

[0655] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?", the following will happen:

[0656] The user types in "Why is the year-on-year change in the Tokyo metropolitan area low? Can you give me more details?" and clicks the submit button.

[0657] The terminal sends a question to the server.

[0658] The server passes the question to a generative AI model for analysis, which extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[0659] The server passes the question to the emotion engine, which recognizes the user's emotion as dissatisfaction or doubt.

[0660] The server generates SQL queries based on these keywords and sentiment results to retrieve sales data from a database.

[0661] The server executes an SQL query to retrieve "sales data for the previous year and this year."

[0662] The server analyzes the data and generates emotionally sensitive responses, such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to last year. This is due to a decline in the purchasing power of key customers and increased competition."

[0663] The server generates a response and sends it to the terminal.

[0664] The terminal displays the answer on the user interface and the user confirms it.

[0665] Examples of prompt statements

[0666] Here is an example of a prompt the user might enter:

[0667] Could you please explain in detail why the year-on-year figures for the Greater Tokyo area are low?

[0668] This invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, emotion analysis technology can be used to provide responses that take the user's emotions into consideration, improving the user experience.

[0669] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0670] Step 1:

[0671] The user enters a question in natural language and clicks the submit button. Specifically, the user enters the question in an input box provided in the user interface. For example, the user enters, "Why is the year-on-year change in the metropolitan area low? Can you give me more details?"

[0672] Input: Question

[0673] Output: Question data from the user

[0674] Step 2:

[0675] The device sends the user's question to the server via an HTTP POST request. Specifically, communication is performed over the Internet to send the entered question data to the server.

[0676] Input: Question data from the user

[0677] Output: The query data sent to the server

[0678] Step 3:

[0679] The server passes the received question to a generative AI model. Specifically, natural language processing technology is used to analyze the question and extract key keywords and content. For example, a generative AI model, a natural language processing model (e.g., GPT-3), extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[0680] Input: Query data sent to the server

[0681] Output: Extracted keyword data

[0682] Step 4:

[0683] The server uses emotion analysis technology to analyze the user's emotions. Specifically, it uses an emotion analysis engine to recognize the user's emotions from the content of the question. For example, the emotion analysis engine recognizes emotions such as dissatisfaction and doubt.

[0684] Input: Query data sent to the server

[0685] Output: Recognized emotion data

[0686] Step 5:

[0687] The server generates data extraction conditions based on the generated keyword data and emotion data. Specifically, it constructs an SQL query based on this data and sets the conditions for extracting information from the database. For example, it generates an SQL query based on the conditions "Metropolitan area," "Year-on-year comparison," and "Details."

[0688] Input: extracted keyword data, recognized emotion data

[0689] Output: Generated data extraction criteria (SQL query)

[0690] Step 6:

[0691] The server uses the generated data extraction conditions (SQL query) to extract the necessary information from the database. Specifically, it executes a query on the database to obtain, for example, "sales data for the Tokyo metropolitan area for the previous year and this year."

[0692] Input: Generated data extraction conditions (SQL query)

[0693] Output: Extracted data

[0694] Step 7:

[0695] The server analyzes the extracted data and generates a specific answer to the user's question. Specifically, it processes the data using methods such as statistical processing and aggregation, and generates an answer such as, "Sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to factors such as a decline in the purchasing power of major customers and an increase in competition."

[0696] Input: Extracted data

[0697] Output: Generated response data

[0698] Step 8:

[0699] The server sends the generated answer data to the user's device. Specifically, it sends the answer data back to the device via an HTTP response.

[0700] Input: Generated response data

[0701] Output: Response data sent to the device

[0702] Step 9:

[0703] The device displays the received response data on the user interface. Specifically, the response is displayed on the screen as text or graphs, and the user can check the information.

[0704] Input: Answer data sent to the terminal

[0705] Output: The answer displayed to the user

[0706] (Application example 2)

[0707] 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."

[0708] While conventional information acquisition systems can quickly generate answers to user questions, they lack the ability to provide answers that take the user's emotions into consideration. This can result in a lack of appropriate communication regarding the user's questions and complaints, potentially resulting in a poor user experience. Furthermore, there are few systems specifically designed for questions regarding the status of autonomous vehicles, and these systems are particularly insufficient in situations where responses that take emotions into consideration are required. To solve these problems, a system that analyzes the user's emotions and generates responses based on those emotions is needed.

[0709] 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.

[0710] In this invention, the server includes means for receiving a question in natural language from a user, emotion recognition means for analyzing the emotion of the received question, means for analyzing the received question and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables a user to input a question about the status of an autonomous vehicle in natural language and receive a quick and appropriate answer to the question that takes emotion into consideration.

[0711] A "user" is a person who enters a question into the system in natural language.

[0712] A "question" is something a user inputs to a system in natural language, requesting information.

[0713] "Emotion recognition means" is a technology for analyzing the emotions contained in a user's question.

[0714] "Data extraction conditions" are conditions for analyzing a received question and extracting information corresponding to that question from a database.

[0715] "Natural language processing technology" is a technology that processes human language using a computer and analyzes its meaning and intent.

[0716] A "database" is a collection of data that stores necessary information.

[0717] A "business analysis database" is a database that stores various data necessary for business activities and analyzes and extracts that data.

[0718] The "information extraction means" is a means for extracting necessary information from a database using the generated data extraction conditions.

[0719] The "answer generation means" is a means for analyzing the extracted information and creating an answer to the user's question.

[0720] An "autonomous vehicle" is a vehicle that can drive itself without a driver.

[0721] MODE FOR CARRYING OUT THE INVENTION

[0722] The present invention provides a system for generating emotionally sensitive answers based on the status information of an autonomous vehicle in response to a question input by a user in natural language. This system uses the following specific method and configuration.

[0723] 1. The user enters a question in natural language from the device.

[0724] Users use an application installed on a device such as a smartphone or tablet to input a question in natural language, for example, "How safe is the current autonomous driving mode?"

[0725] 2. The device sends a question to the server

[0726] The terminal sends the entered question to the server, which converts the question into an appropriate format and passes it to the server.

[0727] 3. The server parses the question

[0728] The server analyzes the received question using natural language processing techniques, such as using a generative AI model to extract important keywords and intent from the question.

[0729] 4. Emotion analysis using emotion recognition methods

[0730] The server uses an emotion recognition engine (e.g., the transformers library) to analyze the emotion (e.g., anxiety or doubt) contained in the question.

[0731] 5. Creating data extraction conditions

[0732] The server generates data extraction conditions, including SQL queries, based on the analyzed question keywords and emotion recognition results.

[0733] 6. Extracting information from databases

[0734] The server uses the generated data extraction conditions to extract necessary information from a database related to autonomous vehicles, specifically data related to the status of autonomous driving modes and safety.

[0735] 7. Answer Generation

[0736] The server generates a specific answer to the question based on the extracted data. In doing so, it takes into account the emotion recognition results and adjusts the answer to take the user's emotions into consideration. For example, it generates an answer such as, "There's no need to worry. The current autonomous driving mode is operating normally. Everything is going smoothly."

[0737] 8. Providing answers to users

[0738] The server sends the generated answer to the user's terminal, which displays the answer on a user interface.

[0739] Hardware and software used

[0740] Device (smartphone or tablet)

[0741] It provides an interface for users to enter questions in natural language.

[0742] server

[0743] It analyzes the received questions, generates data extraction conditions, extracts and analyzes information from the database, and generates answers.

[0744] Database

[0745] It stores various data related to autonomous vehicles. For example, it uses SQLite.

[0746] Natural language processing technology

[0747] Uses generative AI models and emotion recognition engines (transformers library).

[0748] Specific examples

[0749] When a user inputs the question, "How safe is the current autonomous driving mode?", the system will pull relevant information from the autonomous vehicle's database and generate an answer taking into account the emotional state. For example, it may provide the user with a response such as, "There's nothing to worry about. The current autonomous driving mode is operating normally. Everything is going smoothly."

[0750] Prompt Sentence Examples

[0751] Question: How safe is the current autonomous driving mode?

[0752] Answer: There is no need to worry. The current autonomous driving mode is working normally. All driving conditions are normal.

[0753] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0754] Step 1:

[0755] A user uses a terminal to input a question in natural language and submits the question.

[0756] The user opens the application on their smartphone or tablet and enters a question such as, "How safe is the current autonomous driving mode?" After confirming the input and pressing the send button, the question is sent from the device to the server.

[0757] Input: User's natural language question

[0758] Output: The user's question is sent to the server

[0759] Step 2:

[0760] The terminal receives the user's question and forwards it to the server.

[0761] The terminal receives a natural language question sent by the user and transmits the content of the question to the server in an appropriate format.

[0762] Input: The user's question received by the device

[0763] Output: The user's question sent to the server

[0764] Step 3:

[0765] The server analyzes the user's question and extracts keywords and intent.

[0766] The server uses a generative AI model to analyze the received question and extract important keywords and the intent of the question, for example, identifying the keywords "current autonomous driving mode" and "safety."

[0767] Input: The user's question received by the server

[0768] Output: Extracted keywords and question intent

[0769] Step 4:

[0770] The server uses an emotion recognition engine to analyze the user's emotions.

[0771] The server uses the transformers library to analyze the sentiment of the question, for example, to identify whether the question expresses frustration or anxiety.

[0772] Input: User question

[0773] Output: Parsed emotion information

[0774] Step 5:

[0775] The server generates the data extraction conditions.

[0776] The server generates data extraction conditions based on the analyzed keywords and emotion information. For example, it generates an SQL query for data that meets the conditions "autonomous driving mode" and "safety."

[0777] Input: Extracted keywords and sentiment information

[0778] Output: Generated data extraction criteria (SQL query)

[0779] Step 6:

[0780] The server extracts the necessary information from the database.

[0781] The server uses the generated data extraction conditions to extract the necessary information from a database related to autonomous vehicles.

[0782] Input: Data extraction conditions (SQL query)

[0783] Output: Extracted data (e.g., autonomous driving mode status data)

[0784] Step 7:

[0785] The server analyzes the extracted data and generates answers to the user's questions.

[0786] The server uses the extracted data to generate specific answers to the user's questions and adjusts the answers based on emotional information, such as "Don't worry, the current autonomous driving mode is working properly."

[0787] Input: Extracted data and sentiment information

[0788] Output: The generated answer

[0789] Step 8:

[0790] The server transmits the generated answer to the user's terminal and provides it to the user.

[0791] The server sends the generated answer to the user's terminal, which displays the answer on the user's screen.

[0792] Input: Generated Answer

[0793] Output: Answer displayed on the user's terminal

[0794] 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.

[0795] 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.

[0796] 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.

[0797] [Third embodiment]

[0798] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0799] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0800] 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).

[0801] 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.

[0802] 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.

[0803] 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).

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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."

[0810] This invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[0811] 1. Receive user questions

[0812] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[0813] 2. Submitting and analyzing questions

[0814] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[0815] 3. Data Extraction

[0816] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generative AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[0817] 4. Analyze the data and generate answers

[0818] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How is sales in the Tokyo metropolitan area compared to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated.

[0819] 5. Providing answers to users

[0820] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[0821] Specific examples

[0822] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[0823] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[0824] 2. Terminal: Sends the question to the server.

[0825] 3. Server: Analyzes the question and identifies the keywords "metropolitan area" and "year-on-year comparison."

[0826] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[0827] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[0828] 6. Server: Generates the calculation result as an answer and provides it to the user.

[0829] 7. Terminal: Display the answer in a user interface.

[0830] In this way, the present invention allows users to easily perform complex data analysis using natural language, eliminating the need for complex manual tasks, enabling them to quickly obtain necessary information and make instant decisions in situations such as meetings and business negotiations.

[0831] The processing flow will be explained below.

[0832] Step 1:

[0833] The user inputs a question in natural language. The user inputs the question into the user interface displayed on the terminal and clicks the send button.

[0834] Step 2:

[0835] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[0836] Step 3:

[0837] The server passes the received question to the generative AI. The server inputs the question into the generative AI model for analysis, and natural language processing is performed. This analysis extracts important keywords and content contained in the question.

[0838] Step 4:

[0839] The server generates data extraction conditions based on the content of the question analyzed by the generation AI. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" will be identified.

[0840] Step 5:

[0841] The server extracts the required information from the database using the generated data extraction conditions, establishes a database connection, and executes an SQL query based on the extraction conditions to retrieve the target data.

[0842] Step 6:

[0843] The server analyzes the extracted data and generates a specific answer. For example, it compares sales data from the previous year with this year's and calculates the percentage increase or decrease to calculate a "year-on-year change."

[0844] Step 7:

[0845] The server sends the generated specific answer to the device. The answer is sent from the server to the device in JSON format.

[0846] Step 8:

[0847] The terminal displays the received answer on the user interface. The terminal analyzes the content of the answer and displays it to the user in an appropriate format.

[0848] Through this series of processes, users can quickly obtain the information they need and make timely decisions simply by entering their questions in natural language.

[0849] Example 1

[0850] 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."

[0851] There is a need for a system that allows users to input questions in natural language and automatically retrieves and analyzes the necessary information quickly. However, conventional systems have had difficulty accurately analyzing questions input by users in natural language, quickly extracting relevant data, and generating answers. In particular, the lack of a means to efficiently extract and analyze necessary information from databases has made business analysis and rapid decision-making difficult.

[0852] 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.

[0853] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the question using natural language processing technology that uses a generative AI model and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information using statistical, tabulation, and filtering techniques and generating an answer to the user's question, means for providing the generated answer to the user, and means for providing a user interface and for inputting and transmitting a question in natural language, thereby enabling a user to quickly and easily obtain a specific answer to a question input in natural language.

[0854] "User" refers to an individual or organization that uses the system and enters a question in natural language.

[0855] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that provides a user interface and allows a user to enter and submit a query.

[0856] "Server" refers to a central processing unit for receiving and analyzing user queries and extracting necessary data.

[0857] "Natural language processing technology" refers to technology that uses a generative AI model to analyze natural language questions entered by users and identify important keywords and data extraction conditions.

[0858] A "generative AI model" is a type of machine learning model used to provide natural language processing technology, specifically a model that understands and generates natural language.

[0859] "Database" refers to data storage that stores various data necessary for business analysis.

[0860] "Data extraction criteria" refers to specific conditions or queries for extracting required information from a database.

[0861] "Statistical, aggregation, and filtering techniques" refers to data analysis techniques used to analyze the extracted data and generate specific answers to the user's questions.

[0862] "User interface" refers to a graphical interface through which a user enters a question in natural language and clicks a submit button.

[0863] An "answer" is information generated in response to a user's question, and refers to specific information or numerical values ​​provided based on the results of data analysis.

[0864] The present invention is a system that quickly acquires and analyzes necessary information when a user inputs a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[0865] 1. Receive user questions

[0866] The terminal provides a user interface that allows the user to input questions in natural language. The user inputs a question in natural language and clicks the submit button, which passes the question to the system. For example, a user inputs a question such as "What is the year-on-year change in the metropolitan area?" This user interface is implemented using web technologies such as HTML, CSS, and JavaScript.

[0867] 2. Submitting and analyzing questions

[0868] The device sends the user's question to the server. This communication uses the HTTPS protocol to ensure data security. The server then passes the question received from the user to a generation AI (for example, a model using natural language processing technology such as OpenAI's GPT or BERT). The generation AI analyzes the received question, extracts important keywords and content, and generates data extraction conditions based on that.

[0869] 3. Data Extraction

[0870] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries. For example, to extract sales data for the previous year and this year, an SQL query such as "SELECT year, sales FROM sales_data WHERE area = 'Tokyo metropolitan area'" is used.

[0871] 4. Analyze the data and generate answers

[0872] The server analyzes the extracted data and generates a specific answer to the user's question. Methods such as statistical analysis, aggregation, and filtering are used for the analysis. For example, the following processing is performed using Python's pandas library. In response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated. The percentage increase or decrease is calculated as "(this year's sales - last year's sales) / last year's sales 100".

[0873] 5. Providing answers to users

[0874] The server sends the generated answer to the user's device, which then displays the answer on its user interface. This allows the user to instantly obtain the information they need. For example, if a user asks, "What is the year-on-year increase in the Tokyo metropolitan area?", the device will display, "The year-on-year increase in the Tokyo metropolitan area is 5%."

[0875] Specific examples

[0876] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[0877] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[0878] 2. Terminal: Sends the question to the server.

[0879] 3. Server: Analyzes the question and identifies the keywords "Tokyo metropolitan area" and "year-on-year comparison." Analysis is performed using generation AI.

[0880] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[0881] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[0882] 6. Server: Generates the calculation result as an answer and provides it to the user.

[0883] 7. Terminal: Display the answer in a user interface.

[0884] This allows users to omit complex manual work, easily perform complex data analysis in natural language, and quickly obtain the information they need.

[0885] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0886] Step 1: Receive a question from the user

[0887] When a user inputs a question in natural language and clicks a submit button, the terminal receives the question. This input includes the question text written by the user in natural language. The terminal uses a user interface to provide a text box for inputting the question and a submit button. The user interface is implemented using web technologies such as HTML, CSS, and JavaScript.

[0888] Step 2: Submit your question

[0889] The terminal sends the question entered by the user to the server. The transmission uses the HTTPS protocol to ensure data security. The input is the question text entered by the user in natural language. The output is the question text securely sent to the server.

[0890] Step 3: Parsing the Question

[0891] The server passes the received question to the generative AI model for analysis. The generative AI model uses natural language processing technology (for example, OpenAI's GPT model). The input is the user's natural language question. The output is important keywords and data extraction conditions extracted from the question. Specifically, the generative AI analyzes the question text and identifies keywords such as "metropolitan area" and "year-on-year comparison."

[0892] Step 4: Extracting data

[0893] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data required for business analysis. Here, data is extracted using an SQL query. The input is the data extraction conditions. The output is the specific data retrieved from the database. For example, based on the SQL query "SELECT year, sales FROM sales_data WHERE area = 'Metropolitan area'", sales data for the previous year and this year is extracted.

[0894] Step 5: Analyze the data and generate answers

[0895] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses techniques such as statistical analysis, aggregation, and filtering. The input is the extracted data. The output is the answer obtained through the analysis. Specifically, it uses Python's pandas library to compare sales data from the previous year with this year's sales data and calculate the year-on-year change. The percentage change in sales between the previous year and this year is calculated using the formula "(This year's sales - Last year's sales) / Last year's sales 100".

[0896] Step 6: Provide the user with the answer

[0897] The server sends the generated answer to the user's device. The HTTPS protocol is used again for transmission. The input is the answer generated based on the analysis. The output is the answer provided to the user's device. Specifically, the generated answer (for example, "The metropolitan area has increased by 5% compared to the previous year") is displayed on the user interface, where the user can confirm it.

[0898] (Application example 1)

[0899] 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."

[0900] In conventional logistics centers, managers lacked the means to quickly obtain and analyze information on shipment quantities, inventory, and demand in real time, which led to delays in decision-making. In particular, there was a need for a system that would allow managers to intuitively input questions in natural language and instantly obtain the information they needed.

[0901] 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.

[0902] In this invention, the server includes means for receiving questions in natural language from a user, means for analyzing the received questions and generating data extraction conditions corresponding to the questions, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating answers to the user's questions, means for providing the generated answers to the users, and means for analyzing information regarding shipment numbers, inventory, and demand for logistics centers in natural language and generating answers in real time. This enables managers to intuitively input questions in natural language, instantly obtain and analyze necessary data, and make decisions quickly.

[0903] A "user" is someone who uses the system, such as a manager or worker at a logistics center.

[0904] "Natural language" refers to a language that humans use on a daily basis, such as Japanese or English.

[0905] A "means for receiving a question" is an interface or device that allows a user to input a question in natural language.

[0906] "Means for analyzing questions" refers to the technical means for interpreting received questions and extracting important keywords and meanings.

[0907] "Data extraction conditions" are conditions or filtering rules for retrieving necessary information from a database based on a question.

[0908] A "database" is an information storage system that stores business analysis data and data necessary for the operation of a logistics center.

[0909] "Means for analyzing information" refers to technical means for statistically and numerically analyzing extracted data and generating specific answers.

[0910] A "means for providing an answer" is an interface or device that displays or communicates the generated answer to the user.

[0911] "Number of shipments" refers to the total number of products shipped from a logistics center within a certain period of time.

[0912] "Inventory" refers to the total number of unshipped products and materials in a logistics center.

[0913] "Demand" refers to the number of orders or sales for a particular product.

[0914] The present invention is a system that analyzes information relating to shipments, inventory, and demand at a logistics center in natural language and generates answers in real time. Hereinafter, an embodiment of the present invention will be described in detail.

[0915] System configuration

[0916] The system of the present invention comprises a user interface, a server, a database, and a generative AI model.

[0917] User Interface

[0918] Users input questions in natural language using a device such as a smartphone. The interface has a function that allows users to input a question and then click a send button to pass the question to the system.

[0919] server

[0920] The server receives questions sent from the device and analyzes them using a generative AI model. This generative AI model uses OpenAI's API. When a user enters a question such as "How many units were shipped today?", the server analyzes the question and extracts the key keyword "number of units shipped." Based on the extracted keyword, the server generates an SQL query and extracts the necessary data from the database.

[0921] Database

[0922] The database stores various data necessary for business analysis of the distribution center, such as shipment quantities, inventory, order history, etc. The server uses the generated SQL queries to extract the required data in real time.

[0923] Generative AI Models

[0924] The generative AI model uses natural language processing technology to analyze the user's question and generate data extraction conditions. When the generative AI model receives a question, it extracts specific keywords and phrases. For example, in response to the question, "What are the shipment numbers today?", it focuses on the "shipment number" and generates conditions for extracting the relevant data.

[0925] Data analysis and answer generation

[0926] The server generates an answer to the user's question based on the extracted data. For example, it retrieves information about the number of shipments today from the database and returns an answer to the user such as "The number of shipments today is 500."

[0927] Providing answers to users

[0928] The generated answers are sent from the server to the user's device and displayed on the user interface, allowing the user to instantly obtain the information they need simply by entering their question in natural language.

[0929] Examples of prompt statements

[0930] Here are some examples of prompts:

[0931] User input: "How many units are shipped today?"

[0932] Prompt the generative AI model to identify the information needed based on the following question: "How many shipments are there today?"

[0933] Model response example: Shipment quantity

[0934] Example of a SQL query generated based on this answer:

[0935] SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE

[0936] Thus, the present invention is a system that enables users to intuitively input questions in natural language and obtain necessary information in real time.

[0937] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0938] Step 1:

[0939] The user inputs a question in natural language using the user interface of the smartphone device. A specific example of input is "How many units are shipped today?" The input is received and the question is sent to the server.

[0940] Step 2:

[0941] The server receives a question sent from the device. An example question is "How many units were shipped today?" The server passes this question to the generative AI model. The generative AI model is used to analyze the question and extract important keywords. In this case, the generative AI model extracts the keyword "number of units shipped." The input is the question, and the output is the analyzed keywords.

[0942] Step 3:

[0943] The server generates data extraction conditions based on the extracted keywords. Specifically, it generates an SQL query. For example, if the keyword is "number of shipments," the generated SQL query will be "SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE." The input is the keyword, and the output is the SQL query.

[0944] Step 4:

[0945] The server uses the generated SQL query to extract the required information from the database. It connects to the database and actually executes the query to obtain today's shipment count. The input is the SQL query, and the output is the shipment count information obtained from the database.

[0946] Step 5:

[0947] The server analyzes the extracted data and generates a specific answer to the user's question. For example, if the number of shipments retrieved from the database is 500, the server generates the answer "Today's shipments are 500." The input is the extracted data, and the output is the answer presented to the user.

[0948] Step 6:

[0949] The server sends the generated answer to the user's terminal. The terminal displays the received answer on the user interface. The user can see an answer such as "Today's shipments are 500 units" on the interface. The input is the generated answer, and the output is the answer displayed on the terminal.

[0950] 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.

[0951] This invention is a system for quickly acquiring and analyzing necessary information by allowing users to input questions in natural language. The system analyzes the user's question and further recognizes the user's emotions using an emotion engine, thereby providing a more appropriate response.

[0952] 1. Receive user questions

[0953] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[0954] 2. Submitting and analyzing questions

[0955] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[0956] 3. Emotion recognition

[0957] The server uses an emotion engine to analyze the emotions from the user's input. For example, if the user's question contains an emotion of anger, the server recognizes this and responds accordingly.

[0958] 4. Data Extraction

[0959] The server generates data extraction conditions based on the content of the question analyzed by the generation AI and the emotion recognition results. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" are identified and reflected in the data extraction conditions. In addition, based on the emotion recognition results, the answer content is adjusted to a format that takes emotion into consideration.

[0960] 5. Data Acquisition

[0961] The server uses the generated data extraction conditions to extract the necessary information from the database. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[0962] 6. Analyze the data and generate answers

[0963] The server analyzes the extracted data and generates specific answers to the user's questions. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from the previous year and this year are compared and the percentage increase or decrease is calculated. An emotion engine also generates responses that take the user's emotions into consideration.

[0964] 7. Providing answers to users

[0965] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[0966] Specific examples

[0967] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?" the system will operate as follows:

[0968] 1. User: Type a question in natural language: "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-over-year performance?"

[0969] 2. Terminal: Sends the question to the server.

[0970] 3. Server: Analyzes the question and identifies the keywords "metropolitan area," "year-on-year comparison," and "details."

[0971] 4. Server: The emotion engine recognizes when the user has feelings of dissatisfaction or doubt.

[0972] 5. Server: Based on these keywords and emotion recognition results, extract sales data and detailed information for the previous and current years from the database.

[0973] 6. Server: Analyzes the acquired data and generates an emotionally sensitive response, such as, "Year-on-year sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of key customers and an increase in competition. For more details, please see this report."

[0974] 7. Terminal: Display the answer in a user interface.

[0975] In this way, the present invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, the emotion engine provides responses that take the user's emotions into consideration, improving the user experience.

[0976] The processing flow will be explained below.

[0977] Step 1:

[0978] The user inputs a question in natural language. The user inputs a question such as "Why is the year-on-year change in the Tokyo metropolitan area low? Can you tell me the details?" into the user interface displayed on the terminal, and clicks the send button.

[0979] Step 2:

[0980] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[0981] Step 3:

[0982] The server passes the received question to the generation AI. The server inputs the question into the generation AI model and performs natural language processing. The generation AI analyzes the question and extracts important keywords such as "metropolitan area," "year-on-year comparison," and "details."

[0983] Step 4:

[0984] The server uses an emotion engine to analyze the user's input to determine their feelings. For example, the emotion engine can recognize from the tone and wording of a question that the user is dissatisfied or suspicious.

[0985] Step 5:

[0986] The server generates data extraction conditions based on the analyzed question content and emotion recognition results. For example, in addition to the keywords "Tokyo metropolitan area," "year-on-year comparison," and "details," it generates data extraction conditions that reflect considerations based on the emotion recognition results.

[0987] Step 6:

[0988] The server uses the generated data extraction criteria to extract the required information from the database, establishes a database connection, and executes an interactive SQL query to obtain the target data (e.g., sales data and detailed information for the previous and current years).

[0989] Step 7:

[0990] The server analyzes the extracted data and generates specific answers to the user's questions. The server compares sales data from the previous year with this year's and analyzes the reasons for the decline. The emotion engine generates answers that take the user's emotions into consideration.

[0991] Step 8:

[0992] The server sends the generated answer to the user's device. The server converts the answer into JSON format and sends it to the device.

[0993] Step 9:

[0994] The terminal displays the received response on the user interface. The terminal analyzes the response and displays to the user the following: "Year-on-year sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of major customers and an increase in competition. For more details, please see this report."

[0995] This series of processes allows users to simply input their questions in natural language and instantly receive specific, emotionally sensitive answers, enabling them to quickly and efficiently obtain the information they need and make decisions.

[0996] Example 2

[0997] 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."

[0998] Conventional information retrieval systems have difficulty accurately understanding user questions and providing appropriate answers. Furthermore, answers generated without considering the user's emotions have the problem of failing to improve the user experience. Therefore, a new system that combines natural language processing technology and emotion analysis is needed.

[0999] 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.

[1000] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the received question and recognizing the user's emotion using emotion analysis technology, means for generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables the user to quickly obtain the necessary information by asking a question in natural language and receive an appropriate response that takes into consideration the user's emotion at the time.

[1001] A "natural language" is a language that humans use on a daily basis and is created without the expectation of being processed by a computer.

[1002] "Means for analyzing questions" refers to technology for understanding natural language questions received from users and extracting important keywords and content.

[1003] "Emotion analysis technology" is a technology that automatically determines emotions from user input and uses the results.

[1004] The "means for generating data extraction conditions" is a technology for creating conditions for extracting information from a database based on the analyzed questions and the results of emotion recognition.

[1005] A "database" is a system that systematically stores various types of information and allows for efficient search and extraction of that information as needed.

[1006] "Means for extracting information" refers to a technique for extracting necessary information from a database based on the generated data extraction conditions.

[1007] "Means for analyzing information" refers to technology that processes extracted information using methods such as statistics and aggregation to generate specific answers to users' questions.

[1008] The "means for providing an answer" refers to a technique for delivering the generated answer to the user, and is displayed through the user interface of the terminal.

[1009] MODE FOR CARRYING OUT THE INVENTION

[1010] The present invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system analyzes the user's question and further recognizes the user's emotions using emotion analysis technology, thereby providing a more appropriate response.

[1011] Hardware and software used

[1012] Terminal

[1013] Personal computers, smartphones, tablets, etc.

[1014] Providing a user interface using a web browser or mobile application

[1015] server

[1016] Cloud servers are used and cloud service providers (e.g. AWS, Google Cloud, Microsoft Azure) are used.

[1017] Generation AI

[1018] Natural language processing models (e.g., GPT-3, BERT) are used

[1019] Emotion Engine

[1020] Sentiment analysis tools (e.g. IBM Watson Emotion Analysis) are used

[1021] Database

[1022] An SQL database (e.g., MySQL, PostgreSQL) is used

[1023] Specific operation of the system

[1024] The specific operation of this system will be explained in natural language below.

[1025] 1. Users

[1026] Enter a question in natural language and click the send button through the terminal's user interface. For example, enter the question, "Why is the year-on-year change in the metropolitan area low? Please tell me the details."

[1027] 2. Terminal

[1028] Use an HTTP POST request to send the question to the server.

[1029] 3. Server

[1030] The received question is passed to a generative AI model, which extracts key keywords and content. For example, it extracts keywords such as "metropolitan area," "year-on-year comparison," and "details."

[1031] Analyze user emotions using an emotion engine. The emotion engine recognizes emotions such as dissatisfaction and doubt from the user's questions.

[1032] Based on these keywords and the emotion recognition results, data extraction conditions (SQL queries) for retrieving data from the database are generated.

[1033] 4. Server

[1034] Use SQL queries to extract the required information from the database, for example, "Sales data for the Greater Tokyo area last year and this year."

[1035] The extracted data is analyzed using methods such as statistical processing and aggregation to generate specific answers to the user's questions. For example, it generates an answer such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is thought to be due to a decline in the purchasing power of major customers and an increase in competition."

[1036] 5. Server

[1037] The generated answer is sent to the user's terminal.

[1038] 6. Terminal

[1039] The received response is displayed in the user interface so that the user can review it.

[1040] Specific examples

[1041] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?", the following will happen:

[1042] The user types in "Why is the year-on-year change in the Tokyo metropolitan area low? Can you give me more details?" and clicks the submit button.

[1043] The terminal sends a question to the server.

[1044] The server passes the question to a generative AI model for analysis, which extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[1045] The server passes the question to the emotion engine, which recognizes the user's emotion as dissatisfaction or doubt.

[1046] The server generates SQL queries based on these keywords and sentiment results to retrieve sales data from a database.

[1047] The server executes an SQL query to retrieve "sales data for the previous year and this year."

[1048] The server analyzes the data and generates emotionally sensitive responses, such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to last year. This is due to a decline in the purchasing power of key customers and increased competition."

[1049] The server generates a response and sends it to the terminal.

[1050] The terminal displays the answer on the user interface and the user confirms it.

[1051] Examples of prompt statements

[1052] Here is an example of a prompt the user might enter:

[1053] Could you please explain in detail why the year-on-year figures for the Greater Tokyo area are low?

[1054] This invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, emotion analysis technology can be used to provide responses that take the user's emotions into consideration, improving the user experience.

[1055] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1056] Step 1:

[1057] The user enters a question in natural language and clicks the submit button. Specifically, the user enters the question in an input box provided in the user interface. For example, the user enters, "Why is the year-on-year change in the metropolitan area low? Can you give me more details?"

[1058] Input: Question

[1059] Output: Question data from the user

[1060] Step 2:

[1061] The device sends the user's question to the server via an HTTP POST request. Specifically, communication is performed over the Internet to send the entered question data to the server.

[1062] Input: Question data from the user

[1063] Output: The query data sent to the server

[1064] Step 3:

[1065] The server passes the received question to a generative AI model. Specifically, natural language processing technology is used to analyze the question and extract key keywords and content. For example, a generative AI model, a natural language processing model (e.g., GPT-3), extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[1066] Input: Query data sent to the server

[1067] Output: Extracted keyword data

[1068] Step 4:

[1069] The server uses emotion analysis technology to analyze the user's emotions. Specifically, it uses an emotion analysis engine to recognize the user's emotions from the content of the question. For example, the emotion analysis engine recognizes emotions such as dissatisfaction and doubt.

[1070] Input: Query data sent to the server

[1071] Output: Recognized emotion data

[1072] Step 5:

[1073] The server generates data extraction conditions based on the generated keyword data and emotion data. Specifically, it constructs an SQL query based on this data and sets the conditions for extracting information from the database. For example, it generates an SQL query based on the conditions "Metropolitan area," "Year-on-year comparison," and "Details."

[1074] Input: extracted keyword data, recognized emotion data

[1075] Output: Generated data extraction criteria (SQL query)

[1076] Step 6:

[1077] The server uses the generated data extraction conditions (SQL query) to extract the necessary information from the database. Specifically, it executes a query on the database to obtain, for example, "sales data for the Tokyo metropolitan area for the previous year and this year."

[1078] Input: Generated data extraction conditions (SQL query)

[1079] Output: Extracted data

[1080] Step 7:

[1081] The server analyzes the extracted data and generates a specific answer to the user's question. Specifically, it processes the data using methods such as statistical processing and aggregation, and generates an answer such as, "Sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to factors such as a decline in the purchasing power of major customers and an increase in competition."

[1082] Input: Extracted data

[1083] Output: Generated response data

[1084] Step 8:

[1085] The server sends the generated answer data to the user's device. Specifically, it sends the answer data back to the device via an HTTP response.

[1086] Input: Generated response data

[1087] Output: Response data sent to the device

[1088] Step 9:

[1089] The device displays the received response data on the user interface. Specifically, the response is displayed on the screen as text or graphs, and the user can check the information.

[1090] Input: Answer data sent to the terminal

[1091] Output: The answer displayed to the user

[1092] (Application example 2)

[1093] 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."

[1094] While conventional information acquisition systems can quickly generate answers to user questions, they lack the ability to provide answers that take the user's emotions into consideration. This can result in a lack of appropriate communication regarding the user's questions and complaints, potentially resulting in a poor user experience. Furthermore, there are few systems specifically designed for questions regarding the status of autonomous vehicles, and these systems are particularly insufficient in situations where responses that take emotions into consideration are required. To solve these problems, a system that analyzes the user's emotions and generates responses based on those emotions is needed.

[1095] 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.

[1096] In this invention, the server includes means for receiving a question in natural language from a user, emotion recognition means for analyzing the emotion of the received question, means for analyzing the received question and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables a user to input a question about the status of an autonomous vehicle in natural language and receive a quick and appropriate answer to the question that takes emotion into consideration.

[1097] A "user" is a person who enters a question into the system in natural language.

[1098] A "question" is something a user inputs to a system in natural language, requesting information.

[1099] "Emotion recognition means" is a technology for analyzing the emotions contained in a user's question.

[1100] "Data extraction conditions" are conditions for analyzing a received question and extracting information corresponding to that question from a database.

[1101] "Natural language processing technology" is a technology that processes human language using a computer and analyzes its meaning and intent.

[1102] A "database" is a collection of data that stores necessary information.

[1103] A "business analysis database" is a database that stores various data necessary for business activities and analyzes and extracts that data.

[1104] The "information extraction means" is a means for extracting necessary information from a database using the generated data extraction conditions.

[1105] The "answer generation means" is a means for analyzing the extracted information and creating an answer to the user's question.

[1106] An "autonomous vehicle" is a vehicle that can drive itself without a driver.

[1107] MODE FOR CARRYING OUT THE INVENTION

[1108] The present invention provides a system for generating emotionally sensitive answers based on the status information of an autonomous vehicle in response to a question input by a user in natural language. This system uses the following specific method and configuration.

[1109] 1. The user enters a question in natural language from the device.

[1110] Users use an application installed on a device such as a smartphone or tablet to input a question in natural language, for example, "How safe is the current autonomous driving mode?"

[1111] 2. The device sends a question to the server

[1112] The terminal sends the entered question to the server, which converts the question into an appropriate format and passes it to the server.

[1113] 3. The server parses the question

[1114] The server analyzes the received question using natural language processing techniques, such as using a generative AI model to extract important keywords and intent from the question.

[1115] 4. Emotion analysis using emotion recognition methods

[1116] The server uses an emotion recognition engine (e.g., the transformers library) to analyze the emotion (e.g., anxiety or doubt) contained in the question.

[1117] 5. Creating data extraction conditions

[1118] The server generates data extraction conditions, including SQL queries, based on the analyzed question keywords and emotion recognition results.

[1119] 6. Extracting information from databases

[1120] The server uses the generated data extraction conditions to extract necessary information from a database related to autonomous vehicles, specifically data related to the status of autonomous driving modes and safety.

[1121] 7. Answer Generation

[1122] The server generates a specific answer to the question based on the extracted data. In doing so, it takes into account the emotion recognition results and adjusts the answer to take the user's emotions into consideration. For example, it generates an answer such as, "There's no need to worry. The current autonomous driving mode is operating normally. Everything is going smoothly."

[1123] 8. Providing answers to users

[1124] The server sends the generated answer to the user's terminal, which displays the answer on a user interface.

[1125] Hardware and software used

[1126] Device (smartphone or tablet)

[1127] It provides an interface for users to enter questions in natural language.

[1128] server

[1129] It analyzes the received questions, generates data extraction conditions, extracts and analyzes information from the database, and generates answers.

[1130] Database

[1131] It stores various data related to autonomous vehicles. For example, it uses SQLite.

[1132] Natural language processing technology

[1133] Uses generative AI models and emotion recognition engines (transformers library).

[1134] Specific examples

[1135] When a user inputs the question, "How safe is the current autonomous driving mode?", the system will pull relevant information from the autonomous vehicle's database and generate an answer taking into account the emotional state. For example, it may provide the user with a response such as, "There's nothing to worry about. The current autonomous driving mode is operating normally. Everything is going smoothly."

[1136] Prompt Sentence Examples

[1137] Question: How safe is the current autonomous driving mode?

[1138] Answer: There is no need to worry. The current autonomous driving mode is working normally. All driving conditions are normal.

[1139] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1140] Step 1:

[1141] A user uses a terminal to input a question in natural language and submits the question.

[1142] The user opens the application on their smartphone or tablet and enters a question such as, "How safe is the current autonomous driving mode?" After confirming the input and pressing the send button, the question is sent from the device to the server.

[1143] Input: User's natural language question

[1144] Output: The user's question is sent to the server

[1145] Step 2:

[1146] The terminal receives the user's question and forwards it to the server.

[1147] The terminal receives a natural language question sent by the user and transmits the content of the question to the server in an appropriate format.

[1148] Input: The user's question received by the device

[1149] Output: The user's question sent to the server

[1150] Step 3:

[1151] The server analyzes the user's question and extracts keywords and intent.

[1152] The server uses a generative AI model to analyze the received question and extract important keywords and the intent of the question, for example, identifying the keywords "current autonomous driving mode" and "safety."

[1153] Input: The user's question received by the server

[1154] Output: Extracted keywords and question intent

[1155] Step 4:

[1156] The server uses an emotion recognition engine to analyze the user's emotions.

[1157] The server uses the transformers library to analyze the sentiment of the question, for example, to identify whether the question expresses frustration or anxiety.

[1158] Input: User question

[1159] Output: Parsed emotion information

[1160] Step 5:

[1161] The server generates the data extraction conditions.

[1162] The server generates data extraction conditions based on the analyzed keywords and emotion information. For example, it generates an SQL query for data that meets the conditions "autonomous driving mode" and "safety."

[1163] Input: Extracted keywords and sentiment information

[1164] Output: Generated data extraction criteria (SQL query)

[1165] Step 6:

[1166] The server extracts the necessary information from the database.

[1167] The server uses the generated data extraction conditions to extract the necessary information from a database related to autonomous vehicles.

[1168] Input: Data extraction conditions (SQL query)

[1169] Output: Extracted data (e.g., autonomous driving mode status data)

[1170] Step 7:

[1171] The server analyzes the extracted data and generates answers to the user's questions.

[1172] The server uses the extracted data to generate specific answers to the user's questions and adjusts the answers based on emotional information, such as "Don't worry, the current autonomous driving mode is working properly."

[1173] Input: Extracted data and sentiment information

[1174] Output: The generated answer

[1175] Step 8:

[1176] The server transmits the generated answer to the user's terminal and provides it to the user.

[1177] The server sends the generated answer to the user's terminal, which displays the answer on the user's screen.

[1178] Input: Generated Answer

[1179] Output: Answer displayed on the user's terminal

[1180] 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.

[1181] 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.

[1182] 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.

[1183] [Fourth embodiment]

[1184] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1185] 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.

[1186] 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).

[1187] 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.

[1188] 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.

[1189] 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).

[1190] 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.

[1191] 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.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] 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.

[1196] 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."

[1197] This invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[1198] 1. Receive user questions

[1199] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[1200] 2. Submitting and analyzing questions

[1201] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[1202] 3. Data Extraction

[1203] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generative AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[1204] 4. Analyze the data and generate answers

[1205] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How is sales in the Tokyo metropolitan area compared to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated.

[1206] 5. Providing answers to users

[1207] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[1208] Specific examples

[1209] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[1210] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[1211] 2. Terminal: Sends the question to the server.

[1212] 3. Server: Analyzes the question and identifies the keywords "metropolitan area" and "year-on-year comparison."

[1213] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[1214] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[1215] 6. Server: Generates the calculation result as an answer and provides it to the user.

[1216] 7. Terminal: Display the answer in a user interface.

[1217] In this way, the present invention allows users to easily perform complex data analysis using natural language, eliminating the need for complex manual tasks, enabling them to quickly obtain necessary information and make instant decisions in situations such as meetings and business negotiations.

[1218] The processing flow will be explained below.

[1219] Step 1:

[1220] The user inputs a question in natural language. The user inputs the question into the user interface displayed on the terminal and clicks the send button.

[1221] Step 2:

[1222] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[1223] Step 3:

[1224] The server passes the received question to the generative AI. The server inputs the question into the generative AI model for analysis, and natural language processing is performed. This analysis extracts important keywords and content contained in the question.

[1225] Step 4:

[1226] The server generates data extraction conditions based on the content of the question analyzed by the generation AI. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" will be identified.

[1227] Step 5:

[1228] The server extracts the required information from the database using the generated data extraction conditions, establishes a database connection, and executes an SQL query based on the extraction conditions to retrieve the target data.

[1229] Step 6:

[1230] The server analyzes the extracted data and generates a specific answer. For example, it compares sales data from the previous year with this year's and calculates the percentage increase or decrease to calculate a "year-on-year change."

[1231] Step 7:

[1232] The server sends the generated specific answer to the device. The answer is sent from the server to the device in JSON format.

[1233] Step 8:

[1234] The terminal displays the received answer on the user interface. The terminal analyzes the content of the answer and displays it to the user in an appropriate format.

[1235] Through this series of processes, users can quickly obtain the information they need and make timely decisions simply by entering their questions in natural language.

[1236] Example 1

[1237] 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."

[1238] There is a need for a system that allows users to input questions in natural language and automatically retrieves and analyzes the necessary information quickly. However, conventional systems have had difficulty accurately analyzing questions input by users in natural language, quickly extracting relevant data, and generating answers. In particular, the lack of a means to efficiently extract and analyze necessary information from databases has made business analysis and rapid decision-making difficult.

[1239] 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.

[1240] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the question using natural language processing technology that uses a generative AI model and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information using statistical, tabulation, and filtering techniques and generating an answer to the user's question, means for providing the generated answer to the user, and means for providing a user interface and for inputting and transmitting a question in natural language, thereby enabling a user to quickly and easily obtain a specific answer to a question input in natural language.

[1241] "User" refers to an individual or organization that uses the system and enters a question in natural language.

[1242] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that provides a user interface and allows a user to enter and submit a query.

[1243] "Server" refers to a central processing unit for receiving and analyzing user queries and extracting necessary data.

[1244] "Natural language processing technology" refers to technology that uses a generative AI model to analyze natural language questions entered by users and identify important keywords and data extraction conditions.

[1245] A "generative AI model" is a type of machine learning model used to provide natural language processing technology, specifically a model that understands and generates natural language.

[1246] "Database" refers to data storage that stores various data necessary for business analysis.

[1247] "Data extraction criteria" refers to specific conditions or queries for extracting required information from a database.

[1248] "Statistical, aggregation, and filtering techniques" refers to data analysis techniques used to analyze the extracted data and generate specific answers to the user's questions.

[1249] "User interface" refers to a graphical interface through which a user enters a question in natural language and clicks a submit button.

[1250] An "answer" is information generated in response to a user's question, and refers to specific information or numerical values ​​provided based on the results of data analysis.

[1251] The present invention is a system that quickly acquires and analyzes necessary information when a user inputs a question in natural language. This system receives a question from the user, analyzes it, extracts necessary information from a database, and generates a specific answer based on the analysis results and provides it to the user.

[1252] 1. Receive user questions

[1253] The terminal provides a user interface that allows the user to input questions in natural language. The user inputs a question in natural language and clicks the submit button, which passes the question to the system. For example, a user inputs a question such as "What is the year-on-year change in the metropolitan area?" This user interface is implemented using web technologies such as HTML, CSS, and JavaScript.

[1254] 2. Submitting and analyzing questions

[1255] The device sends the user's question to the server. This communication uses the HTTPS protocol to ensure data security. The server then passes the question received from the user to a generation AI (for example, a model using natural language processing technology such as OpenAI's GPT or BERT). The generation AI analyzes the received question, extracts important keywords and content, and generates data extraction conditions based on that.

[1256] 3. Data Extraction

[1257] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries. For example, to extract sales data for the previous year and this year, an SQL query such as "SELECT year, sales FROM sales_data WHERE area = 'Tokyo metropolitan area'" is used.

[1258] 4. Analyze the data and generate answers

[1259] The server analyzes the extracted data and generates a specific answer to the user's question. Methods such as statistical analysis, aggregation, and filtering are used for the analysis. For example, the following processing is performed using Python's pandas library. In response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from last year and this year are compared and the percentage increase or decrease is calculated. The percentage increase or decrease is calculated as "(this year's sales - last year's sales) / last year's sales 100".

[1260] 5. Providing answers to users

[1261] The server sends the generated answer to the user's device, which then displays the answer on its user interface. This allows the user to instantly obtain the information they need. For example, if a user asks, "What is the year-on-year increase in the Tokyo metropolitan area?", the device will display, "The year-on-year increase in the Tokyo metropolitan area is 5%."

[1262] Specific examples

[1263] For example, if a user asks, "What is the year-on-year change in the metropolitan area?" the system operates as follows:

[1264] 1. User: Enters a question in natural language: "What is the year-over-year change in the Greater Tokyo area?"

[1265] 2. Terminal: Sends the question to the server.

[1266] 3. Server: Analyzes the question and identifies the keywords "Tokyo metropolitan area" and "year-on-year comparison." Analysis is performed using generation AI.

[1267] 4. Server: Based on these keywords, extract the previous year's and current year's sales data from the database.

[1268] 5. Server: Analyzes the acquired data and calculates year-on-year comparisons.

[1269] 6. Server: Generates the calculation result as an answer and provides it to the user.

[1270] 7. Terminal: Display the answer in a user interface.

[1271] This allows users to omit complex manual work, easily perform complex data analysis in natural language, and quickly obtain the information they need.

[1272] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1273] Step 1: Receive a question from the user

[1274] When a user inputs a question in natural language and clicks a submit button, the terminal receives the question. This input includes the question text written by the user in natural language. The terminal uses a user interface to provide a text box for inputting the question and a submit button. The user interface is implemented using web technologies such as HTML, CSS, and JavaScript.

[1275] Step 2: Submit your question

[1276] The terminal sends the question entered by the user to the server. The transmission uses the HTTPS protocol to ensure data security. The input is the question text entered by the user in natural language. The output is the question text securely sent to the server.

[1277] Step 3: Parsing the Question

[1278] The server passes the received question to the generative AI model for analysis. The generative AI model uses natural language processing technology (for example, OpenAI's GPT model). The input is the user's natural language question. The output is important keywords and data extraction conditions extracted from the question. Specifically, the generative AI analyzes the question text and identifies keywords such as "metropolitan area" and "year-on-year comparison."

[1279] Step 4: Extracting data

[1280] The server extracts the necessary information from the database based on the data extraction conditions analyzed by the generated AI. The database stores various data required for business analysis. Here, data is extracted using an SQL query. The input is the data extraction conditions. The output is the specific data retrieved from the database. For example, based on the SQL query "SELECT year, sales FROM sales_data WHERE area = 'Metropolitan area'", sales data for the previous year and this year is extracted.

[1281] Step 5: Analyze the data and generate answers

[1282] The server analyzes the extracted data and generates a specific answer to the user's question. The analysis uses techniques such as statistical analysis, aggregation, and filtering. The input is the extracted data. The output is the answer obtained through the analysis. Specifically, it uses Python's pandas library to compare sales data from the previous year with this year's sales data and calculate the year-on-year change. The percentage change in sales between the previous year and this year is calculated using the formula "(This year's sales - Last year's sales) / Last year's sales 100".

[1283] Step 6: Provide the user with the answer

[1284] The server sends the generated answer to the user's device. The HTTPS protocol is used again for transmission. The input is the answer generated based on the analysis. The output is the answer provided to the user's device. Specifically, the generated answer (for example, "The metropolitan area has increased by 5% compared to the previous year") is displayed on the user interface, where the user can confirm it.

[1285] (Application example 1)

[1286] 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."

[1287] In conventional logistics centers, managers lacked the means to quickly obtain and analyze information on shipment quantities, inventory, and demand in real time, which led to delays in decision-making. In particular, there was a need for a system that would allow managers to intuitively input questions in natural language and instantly obtain the information they needed.

[1288] 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.

[1289] In this invention, the server includes means for receiving questions in natural language from a user, means for analyzing the received questions and generating data extraction conditions corresponding to the questions, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating answers to the user's questions, means for providing the generated answers to the users, and means for analyzing information regarding shipment numbers, inventory, and demand for logistics centers in natural language and generating answers in real time. This enables managers to intuitively input questions in natural language, instantly obtain and analyze necessary data, and make decisions quickly.

[1290] A "user" is someone who uses the system, such as a manager or worker at a logistics center.

[1291] "Natural language" refers to a language that humans use on a daily basis, such as Japanese or English.

[1292] A "means for receiving a question" is an interface or device that allows a user to input a question in natural language.

[1293] "Means for analyzing questions" refers to the technical means for interpreting received questions and extracting important keywords and meanings.

[1294] "Data extraction conditions" are conditions or filtering rules for retrieving necessary information from a database based on a question.

[1295] A "database" is an information storage system that stores business analysis data and data necessary for the operation of a logistics center.

[1296] "Means for analyzing information" refers to technical means for statistically and numerically analyzing extracted data and generating specific answers.

[1297] A "means for providing an answer" is an interface or device that displays or communicates the generated answer to the user.

[1298] "Number of shipments" refers to the total number of products shipped from a logistics center within a certain period of time.

[1299] "Inventory" refers to the total number of unshipped products and materials in a logistics center.

[1300] "Demand" refers to the number of orders or sales for a particular product.

[1301] The present invention is a system that analyzes information relating to shipments, inventory, and demand at a logistics center in natural language and generates answers in real time. Hereinafter, an embodiment of the present invention will be described in detail.

[1302] System configuration

[1303] The system of the present invention comprises a user interface, a server, a database, and a generative AI model.

[1304] User Interface

[1305] Users input questions in natural language using a device such as a smartphone. The interface has a function that allows users to input a question and then click a send button to pass the question to the system.

[1306] server

[1307] The server receives questions sent from the device and analyzes them using a generative AI model. This generative AI model uses OpenAI's API. When a user enters a question such as "How many units were shipped today?", the server analyzes the question and extracts the key keyword "number of units shipped." Based on the extracted keyword, the server generates an SQL query and extracts the necessary data from the database.

[1308] Database

[1309] The database stores various data necessary for business analysis of the distribution center, such as shipment quantities, inventory, order history, etc. The server uses the generated SQL queries to extract the required data in real time.

[1310] Generative AI Models

[1311] The generative AI model uses natural language processing technology to analyze the user's question and generate data extraction conditions. When the generative AI model receives a question, it extracts specific keywords and phrases. For example, in response to the question, "What are the shipment numbers today?", it focuses on the "shipment number" and generates conditions for extracting the relevant data.

[1312] Data analysis and answer generation

[1313] The server generates an answer to the user's question based on the extracted data. For example, it retrieves information about the number of shipments today from the database and returns an answer to the user such as "The number of shipments today is 500."

[1314] Providing answers to users

[1315] The generated answers are sent from the server to the user's device and displayed on the user interface, allowing the user to instantly obtain the information they need simply by entering their question in natural language.

[1316] Examples of prompt statements

[1317] Here are some examples of prompts:

[1318] User input: "How many units are shipped today?"

[1319] Prompt the generative AI model to identify the information needed based on the following question: "How many shipments are there today?"

[1320] Model response example: Shipment quantity

[1321] Example of a SQL query generated based on this answer:

[1322] SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE

[1323] Thus, the present invention is a system that enables users to intuitively input questions in natural language and obtain necessary information in real time.

[1324] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1325] Step 1:

[1326] The user inputs a question in natural language using the user interface of the smartphone device. A specific example of input is "How many units are shipped today?" The input is received and the question is sent to the server.

[1327] Step 2:

[1328] The server receives a question sent from the device. An example question is "How many units were shipped today?" The server passes this question to the generative AI model. The generative AI model is used to analyze the question and extract important keywords. In this case, the generative AI model extracts the keyword "number of units shipped." The input is the question, and the output is the analyzed keywords.

[1329] Step 3:

[1330] The server generates data extraction conditions based on the extracted keywords. Specifically, it generates an SQL query. For example, if the keyword is "number of shipments," the generated SQL query will be "SELECT COUNT() FROM shipments WHERE date = CURRENT_DATE." The input is the keyword, and the output is the SQL query.

[1331] Step 4:

[1332] The server uses the generated SQL query to extract the required information from the database. It connects to the database and actually executes the query to obtain today's shipment count. The input is the SQL query, and the output is the shipment count information obtained from the database.

[1333] Step 5:

[1334] The server analyzes the extracted data and generates a specific answer to the user's question. For example, if the number of shipments retrieved from the database is 500, the server generates the answer "Today's shipments are 500." The input is the extracted data, and the output is the answer presented to the user.

[1335] Step 6:

[1336] The server sends the generated answer to the user's terminal. The terminal displays the received answer on the user interface. The user can see an answer such as "Today's shipments are 500 units" on the interface. The input is the generated answer, and the output is the answer displayed on the terminal.

[1337] 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.

[1338] This invention is a system for quickly acquiring and analyzing necessary information by allowing users to input questions in natural language. The system analyzes the user's question and further recognizes the user's emotions using an emotion engine, thereby providing a more appropriate response.

[1339] 1. Receive user questions

[1340] The terminal provides a user interface that allows users to input questions in natural language. The user inputs a question in natural language and clicks a submit button, which passes the question to the system.

[1341] 2. Submitting and analyzing questions

[1342] The device sends the user's question to the server. The server receives the question and passes it to a generation AI (specifically, a model using natural language processing technology). The generation AI analyzes the received question, extracts important keywords and content from the question, and generates data extraction conditions based on that.

[1343] 3. Emotion recognition

[1344] The server uses an emotion engine to analyze the emotions from the user's input. For example, if the user's question contains an emotion of anger, the server recognizes this and responds accordingly.

[1345] 4. Data Extraction

[1346] The server generates data extraction conditions based on the content of the question analyzed by the generation AI and the emotion recognition results. For example, if a user asks, "What is the year-on-year change in the Tokyo metropolitan area?", the keywords "Tokyo metropolitan area" and "year-on-year change" are identified and reflected in the data extraction conditions. In addition, based on the emotion recognition results, the answer content is adjusted to a format that takes emotion into consideration.

[1347] 5. Data Acquisition

[1348] The server uses the generated data extraction conditions to extract the necessary information from the database. The database stores various data necessary for business analysis, and the server extracts this data using methods such as SQL queries.

[1349] 6. Analyze the data and generate answers

[1350] The server analyzes the extracted data and generates specific answers to the user's questions. The analysis uses methods such as statistics, aggregation, and filtering. For example, in response to the question, "How does the Tokyo metropolitan area compare to last year?", sales data from the previous year and this year are compared and the percentage increase or decrease is calculated. An emotion engine also generates responses that take the user's emotions into consideration.

[1351] 7. Providing answers to users

[1352] The server sends the generated answer to the user's terminal, which then displays the answer on its user interface, allowing the user to instantly obtain the information they need.

[1353] Specific examples

[1354] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?" the system will operate as follows:

[1355] 1. User: Type a question in natural language: "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-over-year performance?"

[1356] 2. Terminal: Sends the question to the server.

[1357] 3. Server: Analyzes the question and identifies the keywords "metropolitan area," "year-on-year comparison," and "details."

[1358] 4. Server: The emotion engine recognizes when the user has feelings of dissatisfaction or doubt.

[1359] 5. Server: Based on these keywords and emotion recognition results, extract sales data and detailed information for the previous and current years from the database.

[1360] 6. Server: Analyzes the acquired data and generates an emotionally sensitive response, such as, "Year-on-year sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of key customers and an increase in competition. For more details, please see this report."

[1361] 7. Terminal: Display the answer in a user interface.

[1362] In this way, the present invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, the emotion engine provides responses that take the user's emotions into consideration, improving the user experience.

[1363] The processing flow will be explained below.

[1364] Step 1:

[1365] The user inputs a question in natural language. The user inputs a question such as "Why is the year-on-year change in the Tokyo metropolitan area low? Can you tell me the details?" into the user interface displayed on the terminal, and clicks the send button.

[1366] Step 2:

[1367] The device receives the question entered by the user and sends it to the server, where it converts the question into JSON format and sends it as an HTTP POST request to the server's API endpoint.

[1368] Step 3:

[1369] The server passes the received question to the generation AI. The server inputs the question into the generation AI model and performs natural language processing. The generation AI analyzes the question and extracts important keywords such as "metropolitan area," "year-on-year comparison," and "details."

[1370] Step 4:

[1371] The server uses an emotion engine to analyze the user's input to determine their feelings. For example, the emotion engine can recognize from the tone and wording of a question that the user is dissatisfied or suspicious.

[1372] Step 5:

[1373] The server generates data extraction conditions based on the analyzed question content and emotion recognition results. For example, in addition to the keywords "Tokyo metropolitan area," "year-on-year comparison," and "details," it generates data extraction conditions that reflect considerations based on the emotion recognition results.

[1374] Step 6:

[1375] The server uses the generated data extraction criteria to extract the required information from the database, establishes a database connection, and executes an interactive SQL query to obtain the target data (e.g., sales data and detailed information for the previous and current years).

[1376] Step 7:

[1377] The server analyzes the extracted data and generates specific answers to the user's questions. The server compares sales data from the previous year with this year's and analyzes the reasons for the decline. The emotion engine generates answers that take the user's emotions into consideration.

[1378] Step 8:

[1379] The server sends the generated answer to the user's device. The server converts the answer into JSON format and sends it to the device.

[1380] Step 9:

[1381] The terminal displays the received response on the user interface. The terminal analyzes the response and displays to the user the following: "Year-on-year sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is due to a decline in the purchasing power of major customers and an increase in competition. For more details, please see this report."

[1382] This series of processes allows users to simply input their questions in natural language and instantly receive specific, emotionally sensitive answers, enabling them to quickly and efficiently obtain the information they need and make decisions.

[1383] Example 2

[1384] 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."

[1385] Conventional information retrieval systems have difficulty accurately understanding user questions and providing appropriate answers. Furthermore, answers generated without considering the user's emotions have the problem of failing to improve the user experience. Therefore, a new system that combines natural language processing technology and emotion analysis is needed.

[1386] 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.

[1387] In this invention, the server includes means for receiving a question in natural language from a user, means for analyzing the received question and recognizing the user's emotion using emotion analysis technology, means for generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables the user to quickly obtain the necessary information by asking a question in natural language and receive an appropriate response that takes into consideration the user's emotion at the time.

[1388] A "natural language" is a language that humans use on a daily basis and is created without the expectation of being processed by a computer.

[1389] "Means for analyzing questions" refers to technology for understanding natural language questions received from users and extracting important keywords and content.

[1390] "Emotion analysis technology" is a technology that automatically determines emotions from user input and uses the results.

[1391] The "means for generating data extraction conditions" is a technology for creating conditions for extracting information from a database based on the analyzed questions and the results of emotion recognition.

[1392] A "database" is a system that systematically stores various types of information and allows for efficient search and extraction of that information as needed.

[1393] "Means for extracting information" refers to a technique for extracting necessary information from a database based on the generated data extraction conditions.

[1394] "Means for analyzing information" refers to technology that processes extracted information using methods such as statistics and aggregation to generate specific answers to users' questions.

[1395] The "means for providing an answer" refers to a technique for delivering the generated answer to the user, and is displayed through the user interface of the terminal.

[1396] MODE FOR CARRYING OUT THE INVENTION

[1397] The present invention is a system for quickly acquiring and analyzing necessary information by allowing a user to input a question in natural language. This system analyzes the user's question and further recognizes the user's emotions using emotion analysis technology, thereby providing a more appropriate response.

[1398] Hardware and software used

[1399] Terminal

[1400] Personal computers, smartphones, tablets, etc.

[1401] Providing a user interface using a web browser or mobile application

[1402] server

[1403] Cloud servers are used and cloud service providers (e.g. AWS, Google Cloud, Microsoft Azure) are used.

[1404] Generation AI

[1405] Natural language processing models (e.g., GPT-3, BERT) are used

[1406] Emotion Engine

[1407] Sentiment analysis tools (e.g. IBM Watson Emotion Analysis) are used

[1408] Database

[1409] An SQL database (e.g., MySQL, PostgreSQL) is used

[1410] Specific operation of the system

[1411] The specific operation of this system will be explained in natural language below.

[1412] 1. Users

[1413] Enter a question in natural language and click the send button through the terminal's user interface. For example, enter the question, "Why is the year-on-year change in the metropolitan area low? Please tell me the details."

[1414] 2. Terminal

[1415] Use an HTTP POST request to send the question to the server.

[1416] 3. Server

[1417] The received question is passed to a generative AI model, which extracts key keywords and content. For example, it extracts keywords such as "metropolitan area," "year-on-year comparison," and "details."

[1418] Analyze user emotions using an emotion engine. The emotion engine recognizes emotions such as dissatisfaction and doubt from the user's questions.

[1419] Based on these keywords and the emotion recognition results, data extraction conditions (SQL queries) for retrieving data from the database are generated.

[1420] 4. Server

[1421] Use SQL queries to extract the required information from the database, for example, "Sales data for the Greater Tokyo area last year and this year."

[1422] The extracted data is analyzed using methods such as statistical processing and aggregation to generate specific answers to the user's questions. For example, it generates an answer such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to the previous year. This is thought to be due to a decline in the purchasing power of major customers and an increase in competition."

[1423] 5. Server

[1424] The generated answer is sent to the user's terminal.

[1425] 6. Terminal

[1426] The received response is displayed in the user interface so that the user can review it.

[1427] Specific examples

[1428] For example, if a user asks, "Can you give me more details on why the Tokyo metropolitan area is showing a lower year-on-year increase?", the following will happen:

[1429] The user types in "Why is the year-on-year change in the Tokyo metropolitan area low? Can you give me more details?" and clicks the submit button.

[1430] The terminal sends a question to the server.

[1431] The server passes the question to a generative AI model for analysis, which extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[1432] The server passes the question to the emotion engine, which recognizes the user's emotion as dissatisfaction or doubt.

[1433] The server generates SQL queries based on these keywords and sentiment results to retrieve sales data from a database.

[1434] The server executes an SQL query to retrieve "sales data for the previous year and this year."

[1435] The server analyzes the data and generates emotionally sensitive responses, such as, "Sales in the Tokyo metropolitan area have decreased by 10% compared to last year. This is due to a decline in the purchasing power of key customers and increased competition."

[1436] The server generates a response and sends it to the terminal.

[1437] The terminal displays the answer on the user interface and the user confirms it.

[1438] Examples of prompt statements

[1439] Here is an example of a prompt the user might enter:

[1440] Could you please explain in detail why the year-on-year figures for the Greater Tokyo area are low?

[1441] This invention allows users to quickly obtain the information they need simply by inputting a question in natural language. Furthermore, emotion analysis technology can be used to provide responses that take the user's emotions into consideration, improving the user experience.

[1442] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1443] Step 1:

[1444] The user enters a question in natural language and clicks the submit button. Specifically, the user enters the question in an input box provided in the user interface. For example, the user enters, "Why is the year-on-year change in the metropolitan area low? Can you give me more details?"

[1445] Input: Question

[1446] Output: Question data from the user

[1447] Step 2:

[1448] The device sends the user's question to the server via an HTTP POST request. Specifically, communication is performed over the Internet to send the entered question data to the server.

[1449] Input: Question data from the user

[1450] Output: The query data sent to the server

[1451] Step 3:

[1452] The server passes the received question to a generative AI model. Specifically, natural language processing technology is used to analyze the question and extract key keywords and content. For example, a generative AI model, a natural language processing model (e.g., GPT-3), extracts the keywords "metropolitan area," "year-on-year comparison," and "details."

[1453] Input: Query data sent to the server

[1454] Output: Extracted keyword data

[1455] Step 4:

[1456] The server uses emotion analysis technology to analyze the user's emotions. Specifically, it uses an emotion analysis engine to recognize the user's emotions from the content of the question. For example, the emotion analysis engine recognizes emotions such as dissatisfaction and doubt.

[1457] Input: Query data sent to the server

[1458] Output: Recognized emotion data

[1459] Step 5:

[1460] The server generates data extraction conditions based on the generated keyword data and emotion data. Specifically, it constructs an SQL query based on this data and sets the conditions for extracting information from the database. For example, it generates an SQL query based on the conditions "Metropolitan area," "Year-on-year comparison," and "Details."

[1461] Input: extracted keyword data, recognized emotion data

[1462] Output: Generated data extraction criteria (SQL query)

[1463] Step 6:

[1464] The server uses the generated data extraction conditions (SQL query) to extract the necessary information from the database. Specifically, it executes a query on the database to obtain, for example, "sales data for the Tokyo metropolitan area for the previous year and this year."

[1465] Input: Generated data extraction conditions (SQL query)

[1466] Output: Extracted data

[1467] Step 7:

[1468] The server analyzes the extracted data and generates a specific answer to the user's question. Specifically, it processes the data using methods such as statistical processing and aggregation, and generates an answer such as, "Sales in the metropolitan area have decreased by 10% compared to the previous year. This is due to factors such as a decline in the purchasing power of major customers and an increase in competition."

[1469] Input: Extracted data

[1470] Output: Generated response data

[1471] Step 8:

[1472] The server sends the generated answer data to the user's device. Specifically, it sends the answer data back to the device via an HTTP response.

[1473] Input: Generated response data

[1474] Output: Response data sent to the device

[1475] Step 9:

[1476] The device displays the received response data on the user interface. Specifically, the response is displayed on the screen as text or graphs, and the user can check the information.

[1477] Input: Answer data sent to the terminal

[1478] Output: The answer displayed to the user

[1479] (Application example 2)

[1480] 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."

[1481] While conventional information acquisition systems can quickly generate answers to user questions, they lack the ability to provide answers that take the user's emotions into consideration. This can result in a lack of appropriate communication regarding the user's questions and complaints, potentially resulting in a poor user experience. Furthermore, there are few systems specifically designed for questions regarding the status of autonomous vehicles, and these systems are particularly insufficient in situations where responses that take emotions into consideration are required. To solve these problems, a system that analyzes the user's emotions and generates responses based on those emotions is needed.

[1482] 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.

[1483] In this invention, the server includes means for receiving a question in natural language from a user, emotion recognition means for analyzing the emotion of the received question, means for analyzing the received question and generating data extraction conditions corresponding to the question, means for extracting necessary information from a database using the generated data extraction conditions, means for analyzing the extracted information and generating an answer to the user's question, and means for providing the generated answer to the user. This enables a user to input a question about the status of an autonomous vehicle in natural language and receive a quick and appropriate answer to the question that takes emotion into consideration.

[1484] A "user" is a person who enters a question into the system in natural language.

[1485] A "question" is something a user inputs to a system in natural language, requesting information.

[1486] "Emotion recognition means" is a technology for analyzing the emotions contained in a user's question.

[1487] "Data extraction conditions" are conditions for analyzing a received question and extracting information corresponding to that question from a database.

[1488] "Natural language processing technology" is a technology that processes human language using a computer and analyzes its meaning and intent.

[1489] A "database" is a collection of data that stores necessary information.

[1490] A "business analysis database" is a database that stores various data necessary for business activities and analyzes and extracts that data.

[1491] The "information extraction means" is a means for extracting necessary information from a database using the generated data extraction conditions.

[1492] The "answer generation means" is a means for analyzing the extracted information and creating an answer to the user's question.

[1493] An "autonomous vehicle" is a vehicle that can drive itself without a driver.

[1494] MODE FOR CARRYING OUT THE INVENTION

[1495] The present invention provides a system for generating emotionally sensitive answers based on the status information of an autonomous vehicle in response to a question input by a user in natural language. This system uses the following specific method and configuration.

[1496] 1. The user enters a question in natural language from the device.

[1497] Users use an application installed on a device such as a smartphone or tablet to input a question in natural language, for example, "How safe is the current autonomous driving mode?"

[1498] 2. The device sends a question to the server

[1499] The terminal sends the entered question to the server, which converts the question into an appropriate format and passes it to the server.

[1500] 3. The server parses the question

[1501] The server analyzes the received question using natural language processing techniques, such as using a generative AI model to extract important keywords and intent from the question.

[1502] 4. Emotion analysis using emotion recognition methods

[1503] The server uses an emotion recognition engine (e.g., the transformers library) to analyze the emotion (e.g., anxiety or doubt) contained in the question.

[1504] 5. Creating data extraction conditions

[1505] The server generates data extraction conditions, including SQL queries, based on the analyzed question keywords and emotion recognition results.

[1506] 6. Extracting information from databases

[1507] The server uses the generated data extraction conditions to extract necessary information from a database related to autonomous vehicles, specifically data related to the status of autonomous driving modes and safety.

[1508] 7. Answer Generation

[1509] The server generates a specific answer to the question based on the extracted data. In doing so, it takes into account the emotion recognition results and adjusts the answer to take the user's emotions into consideration. For example, it generates an answer such as, "There's no need to worry. The current autonomous driving mode is operating normally. Everything is going smoothly."

[1510] 8. Providing answers to users

[1511] The server sends the generated answer to the user's terminal, which displays the answer on a user interface.

[1512] Hardware and software used

[1513] Device (smartphone or tablet)

[1514] It provides an interface for users to enter questions in natural language.

[1515] server

[1516] It analyzes the received questions, generates data extraction conditions, extracts and analyzes information from the database, and generates answers.

[1517] Database

[1518] It stores various data related to autonomous vehicles. For example, it uses SQLite.

[1519] Natural language processing technology

[1520] Uses generative AI models and emotion recognition engines (transformers library).

[1521] Specific examples

[1522] When a user inputs the question, "How safe is the current autonomous driving mode?", the system will pull relevant information from the autonomous vehicle's database and generate an answer taking into account the emotional state. For example, it may provide the user with a response such as, "There's nothing to worry about. The current autonomous driving mode is operating normally. Everything is going smoothly."

[1523] Prompt Sentence Examples

[1524] Question: How safe is the current autonomous driving mode?

[1525] Answer: There is no need to worry. The current autonomous driving mode is working normally. All driving conditions are normal.

[1526] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1527] Step 1:

[1528] A user uses a terminal to input a question in natural language and submits the question.

[1529] The user opens the application on their smartphone or tablet and enters a question such as, "How safe is the current autonomous driving mode?" After confirming the input and pressing the send button, the question is sent from the device to the server.

[1530] Input: User's natural language question

[1531] Output: The user's question is sent to the server

[1532] Step 2:

[1533] The terminal receives the user's question and forwards it to the server.

[1534] The terminal receives a natural language question sent by the user and transmits the content of the question to the server in an appropriate format.

[1535] Input: The user's question received by the device

[1536] Output: The user's question sent to the server

[1537] Step 3:

[1538] The server analyzes the user's question and extracts keywords and intent.

[1539] The server uses a generative AI model to analyze the received question and extract important keywords and the intent of the question, for example, identifying the keywords "current autonomous driving mode" and "safety."

[1540] Input: The user's question received by the server

[1541] Output: Extracted keywords and question intent

[1542] Step 4:

[1543] The server uses an emotion recognition engine to analyze the user's emotions.

[1544] The server uses the transformers library to analyze the sentiment of the question, for example, to identify whether the question expresses frustration or anxiety.

[1545] Input: User question

[1546] Output: Parsed emotion information

[1547] Step 5:

[1548] The server generates the data extraction conditions.

[1549] The server generates data extraction conditions based on the analyzed keywords and emotion information. For example, it generates an SQL query for data that meets the conditions "autonomous driving mode" and "safety."

[1550] Input: Extracted keywords and sentiment information

[1551] Output: Generated data extraction criteria (SQL query)

[1552] Step 6:

[1553] The server extracts the necessary information from the database.

[1554] The server uses the generated data extraction conditions to extract the necessary information from a database related to autonomous vehicles.

[1555] Input: Data extraction conditions (SQL query)

[1556] Output: Extracted data (e.g., autonomous driving mode status data)

[1557] Step 7:

[1558] The server analyzes the extracted data and generates answers to the user's questions.

[1559] The server uses the extracted data to generate specific answers to the user's questions and adjusts the answers based on emotional information, such as "Don't worry, the current autonomous driving mode is working properly."

[1560] Input: Extracted data and sentiment information

[1561] Output: The generated answer

[1562] Step 8:

[1563] The server transmits the generated answer to the user's terminal and provides it to the user.

[1564] The server sends the generated answer to the user's terminal, which displays the answer on the user's screen.

[1565] Input: Generated Answer

[1566] Output: Answer displayed on the user's terminal

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] FIG. 9 illustrates 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 behaviors 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.

[1572] 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.

[1573] 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).

[1574] 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.

[1575] 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."

[1576] 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.

[1577] 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).

[1578] 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.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] The following is further disclosed regarding the above embodiment.

[1589] (Claim 1)

[1590] means for receiving a question from a user in natural language;

[1591] A means for analyzing the received question and generating data extraction conditions corresponding to the question;

[1592] A means for extracting necessary information from a database using the generated data extraction conditions;

[1593] means for analyzing the extracted information and generating an answer to the user's question;

[1594] The system includes a means for providing the generated answer to a user.

[1595] (Claim 2)

[1596] 2. The system according to claim 1, wherein the means for analyzing the received question performs the analysis using natural language processing technology.

[1597] (Claim 3)

[1598] 2. The system of claim 1, wherein the database is a business analysis database and the extracted information is a business analysis index.

[1599] "Example 1"

[1600] (Claim 1)

[1601] means for receiving a question from a user in natural language;

[1602] A means for analyzing the received question and generating data extraction conditions corresponding to the question;

[1603] A means for extracting necessary information from a database using the generated data extraction conditions;

[1604] means for analyzing the extracted information and generating an answer to the user's question;

[1605] The system includes a means for providing the generated answer to a user.

[1606] (Claim 2)

[1607] The system of claim 1, which analyzes received questions using natural language processing technology with a generative AI model.

[1608] (Claim 3)

[1609] 10. The system of claim 1, wherein the database is a business analytics database and the extracted information is business metrics.

[1610] (Claim 4)

[1611] 10. The system of claim 1, including means for providing a user interface and for inputting and submitting queries in natural language.

[1612] (Claim 5)

[1613] 10. The system of claim 1, further comprising means for analyzing the extracted information using statistical, aggregation, and filtering techniques to generate a specific response.

[1614] "Application Example 1"

[1615] (Claim 1)

[1616] means for receiving a question from a user in natural language;

[1617] A means for analyzing the received question and generating data extraction conditions corresponding to the question;

[1618] A means for extracting necessary information from a database using the generated data extraction conditions;

[1619] means for analyzing the extracted information and generating an answer to the user's question;

[1620] means for providing the generated answer to the user;

[1621] A system that includes a means for analyzing shipment, inventory, and demand information for a distribution center in natural language and generating answers in real time.

[1622] (Claim 2)

[1623] 2. The system according to claim 1, wherein the means for analyzing the received question performs the analysis using natural language processing technology.

[1624] (Claim 3)

[1625] 2. The system of claim 1, wherein the database is a business analysis database and the extracted information is a business analysis index.

[1626] "Example 2: Combining Emotion Engines"

[1627] (Claim 1)

[1628] means for receiving a question from a user in natural language;

[1629] means for analyzing the received question and recognizing the user's emotion using emotion analysis technology;

[1630] means for generating data extraction conditions corresponding to the query;

[1631] A means for extracting necessary information from a database using the generated data extraction conditions;

[1632] means for analyzing the extracted information and generating an answer to the user's question;

[1633] The system includes a means for providing the generated answer to a user.

[1634] (Claim 2)

[1635] 2. The system according to claim 1, wherein the means for analyzing the received question performs the analysis using natural language processing technology.

[1636] (Claim 3)

[1637] 2. The system of claim 1, wherein the database is a business analysis database and the extracted information is a business analysis index.

[1638] "Application example 2 when combining emotion engines"

[1639] (Claim 1)

[1640] means for receiving a question from a user in natural language;

[1641] A means for analyzing the received question and generating data extraction conditions corresponding to the question;

[1642] A means for extracting necessary information from a database using the generated data extraction conditions;

[1643] means for analyzing the extracted information and generating an answer to the user's question;

[1644] means for providing the generated answer to the user;

[1645] A system including an emotion recognition means for analyzing the emotion of a received question and generating a response that takes that emotion into consideration.

[1646] (Claim 2)

[1647] 2. The system according to claim 1, wherein the means for analyzing the received question performs the analysis using natural language processing technology.

[1648] (Claim 3)

[1649] 2. The system of claim 1, wherein the database is a business analysis database and the extracted information is a business analysis index.

[1650] (Claim 4)

[1651] 10. The system of claim 1, wherein the means for analyzing the emotion of the received question uses an emotion recognition engine.

[1652] (Claim 5)

[1653] 10. The system of claim 1, further comprising: means for receiving a query regarding the status of the autonomous vehicle and means for retrieving information corresponding to the query from a database related to autonomous vehicles. [Explanation of symbols]

[1654] 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. means for receiving a question from a user in natural language; A means for analyzing the received question and generating data extraction conditions corresponding to the question; A means for extracting necessary information from a database using the generated data extraction conditions; means for analyzing the extracted information and generating an answer to the user's question; and means for providing the generated answer to the user.

2. 2. The system of claim 1, wherein the means for analyzing the received question performs the analysis using natural language processing techniques.

3. 2. The system of claim 1, wherein the database is a business analysis database and the extracted information is a business analysis index.

Images