system

Abstract

We provide the system. [Solution] A processing unit that analyzes data extraction conditions entered in natural language, A generation device that automatically generates database queries based on the analyzed data extraction conditions, An execution device that executes the automatically generated database query and sends the results to a display device, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In data-driven businesses, the ability to quickly and accurately extract necessary information from a database is required. However, many business people do not have knowledge of specialized database query languages such as SQL. For this reason, data extraction is difficult, and as a result, there is a problem that decision-making is delayed. In addition, since it is difficult to allocate the time and resources for learning SQL, an efficient data extraction means is required.

Means for Solving the Problems

[0005] This invention provides a system that analyzes data extraction conditions entered by a user in natural language and automatically generates database queries based on the analysis results. This system uses natural language processing technology to analyze user input and generates optimal queries using a generation AI. Furthermore, it provides a means for users to review and customize the generated queries, thereby simplifying information extraction from databases and enabling rapid data utilization.

[0006] "Natural language" refers to the language that humans use on a daily basis and that can be used as input or output for computer systems.

[0007] "Data extraction criteria" are standards or filters set to extract specific information from a database, and are defined by the user.

[0008] A "processing unit" is a computer system or its components that are responsible for analyzing natural language input from a user.

[0009] A "generation device" is a computer program or hardware that automatically generates appropriate database queries based on analyzed data extraction conditions.

[0010] An "execution device" is a computer system or its components used to execute generated database queries and retrieve the results.

[0011] A "display device" is a hardware device that visually presents the results of an operation to the user.

[0012] "Natural language processing technology" refers to technologies within the field of computer science that enable computers to understand, analyze, and process natural language.

[0013] "Generative AI" is a type of artificial intelligence that generates output suitable for a given purpose based on the input information it receives.

[0014] A "database query" is code or a language construct that describes a question or instruction for retrieving specific information from a database.

[0015] "Customization" refers to the user's adjustment or modification of the generated query or output result according to specific purposes or requirements.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is a system that automatically extracts necessary information from a database simply by the user inputting data extraction conditions in natural language. One possible embodiment involves a configuration utilizing an internet-connected terminal and a server.

[0038] The user uses a terminal to input the conditions for extracting specific information in natural language. In this invention, the user does not need technical knowledge such as SQL and can easily specify data extraction.

[0039] The data extraction conditions entered in natural language are sent from the terminal to the server. The server uses natural language processing technology to analyze the data extraction conditions received from the user. During the analysis process, the server parses the conditional statements and identifies the key elements (elements to be extracted, filter conditions, etc.) necessary for the database query.

[0040] Next, the server uses a generation AI to automatically generate appropriate database queries based on the identified information. This process creates queries that match the user's intent.

[0041] The generated query is sent back from the server to the terminal, making it available for user review. Here, the user can review the query and add or modify detailed conditions as needed. This allows the user to optimize the extraction results to suit their specific needs.

[0042] After user verification, the terminal requests the server to execute a query. The server executes the query against the database and extracts data that matches the specified criteria.

[0043] The extracted data is organized by the server and sent to the user's terminal. The terminal displays this data visually, allowing the user to easily review the results.

[0044] For example, if a user enters a request to "display customers who achieved sales of 10 million yen or more in fiscal year 2023," this invention allows the server to analyze the conditions and automatically generate a query to extract appropriate information from the database based on key elements such as "2023," "10 million yen or more," "sales," and "customers."

[0045] This embodiment allows users to intuitively access the data they need without having to go through the complex steps of building a database or creating queries.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The user uses their device to input their desired data extraction criteria in natural language. For example, they might enter a condition such as "Show customers who generated sales of 10 million yen or more in 2023."

[0049] Step 2:

[0050] The terminal converts the input natural language information into digital data and sends it to the server.

[0051] Step 3:

[0052] The server passes the received natural language data to the natural language processing engine and begins analysis. The analysis identifies key elements for data extraction, such as "2023," "over 10 million yen," "sales," and "customers."

[0053] Step 4:

[0054] Based on the analysis results, the server uses a generative AI to generate the optimal database query. This query is constructed to satisfy the analyzed conditions.

[0055] Step 5:

[0056] The server sends the generated SQL query back to the terminal. On the terminal, the user can review and customize the query's contents. Conditions can be added or modified as needed.

[0057] Step 6:

[0058] After the user reviews the query and confirms that the conditions to be applied are correct, they send a command to execute the query to the server from their terminal.

[0059] Step 7:

[0060] The server receives instructions, executes queries against the database, and extracts the corresponding data.

[0061] Step 8:

[0062] The server organizes the extracted data and sends it to the terminal.

[0063] Step 9:

[0064] The device displays received data in a user-friendly format. This allows the user to intuitively check the necessary information.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] Traditional database query generation systems require users to possess technical knowledge, and a major challenge is the difficulty in directly setting data extraction conditions from natural language. This makes it difficult for non-technical users to effectively utilize the database, highlighting the need to improve the intuitiveness and usability of the interface.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes means for acquiring data extraction conditions entered by the user in natural language, a processing unit for analyzing the natural language data extraction conditions and extracting key elements, and a generation unit that utilizes generative artificial intelligence to automatically generate database queries based on the analyzed data extraction conditions. This makes it possible for users to generate and execute database queries in natural language and intuitively acquire and display the necessary information, even without technical knowledge.

[0070] A "user" refers to an individual or organization that uses the system to input data extraction criteria in natural language and attempts to obtain information.

[0071] "Natural language" refers to language that humans use on a daily basis, a form of language that can be easily understood and used even without technical knowledge.

[0072] "Data extraction conditions" refer to the search criteria and filter conditions necessary to retrieve specific information from a database.

[0073] A "processing device" refers to a hardware or software component that analyzes input data and information and performs the necessary operations.

[0074] A "generation device" is a device that has the function of generating output in a different format based on input data, and in this case, it refers to a device that automatically generates database queries.

[0075] "Generative artificial intelligence" refers to artificial intelligence technology that can understand natural language and provide responses and generate data according to the task.

[0076] "Automatic generation" refers to the process by which a system autonomously generates data or results without human intervention.

[0077] An "execution device" refers to hardware or software that executes a generated query and completes a specified operation.

[0078] "Key elements" refer to the main elements or components that constitute the data extraction criteria, and are the elements necessary for efficient searching of the database.

[0079] A "display device" refers to hardware or equipment used to visually present digital data and information to a user.

[0080] This invention is an automated database query generation system that enables data extraction using natural language. The system consists of a user terminal with an internet connection and a server that performs data processing and query generation.

[0081] The user uses a terminal to input conditions in natural language to extract specific information from the database. For example, when prompting with the message "Show customers who achieved sales of 10 million yen or more in fiscal year 2023," the user can set data extraction conditions using natural language without requiring advanced technical knowledge.

[0082] The terminal sends the input natural language conditions to the server. The server uses natural language processing technology and generative artificial intelligence models to analyze the input conditions and extract the necessary key elements. Based on the analysis, the server automatically generates an efficient database query. The generated query is sent to the terminal for the user to review and customize. The server organizes the query execution results and presents the data visually to the terminal.

[0083] The server can use generative AI models such as BERT or GPT for natural language processing, enabling accurate analysis of user input conditions. This allows the system to efficiently extract the data desired by the user and provide an intuitive and user-friendly interface.

[0084] This embodiment allows users to easily interact with the database and extract and utilize meaningful data, even without technical knowledge.

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

[0086] Step 1:

[0087] The user uses a terminal to input the information they want to retrieve from the database in natural language. The input is in text format through the terminal's interface. This prompt is a way for users to specify requests without specific technical skills. An example of input is, "Show customers who achieved sales of 10 million yen or more in fiscal year 2023."

[0088] Step 2:

[0089] The terminal sends data extraction criteria, received from the user in natural language, to the server. This prompt is sent as text data via an API designed for analysis by the server. The server places the received data in a waiting state for processing.

[0090] Step 3:

[0091] The server analyzes the prompt text using natural language processing techniques and generative AI models. The server first tokenizes the input natural language text and performs context-based semantic analysis. For example, it extracts specific key elements such as a particular year or amount, which are then used to generate the next query. This analysis produces a list of key elements as an intermediate output.

[0092] Step 4:

[0093] The server automatically constructs database queries based on key elements extracted through analysis using generation AI. The server creates query syntax from the key elements and converts it into a query language such as SQL. The output is a query in a format compatible with the database.

[0094] Step 5:

[0095] The generated query is sent from the server to the terminal. On the terminal, the user can review this query and customize or modify it as needed. At this stage, the user visually verifies whether the extraction criteria are appropriate by receiving the output query.

[0096] Step 6:

[0097] The user requests the server to execute a query via their terminal. The terminal sends the user's execution request to the server, asking the server to apply the query. Based on the received request, the server attempts to access the database.

[0098] Step 7:

[0099] The server executes the specified query against the database and extracts matching data records. The server executes the query through the database engine and processes the retrieved output data.

[0100] Step 8:

[0101] The acquired data is organized by the server and sent to the user's terminal. The terminal displays this data in a visually easy-to-understand format, such as graphs or tables, allowing the user to easily check the results.

[0102] (Application Example 1)

[0103] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0104] In conventional information retrieval systems, it was difficult for users to quickly and appropriately obtain the information they needed without requiring specific technical knowledge. Furthermore, there was a lack of means to instantly retrieve and visually confirm relevant sales trends and inventory information when users made inquiries using natural language. This resulted in reduced information retrieval efficiency and hindered the rapid processing of customer service.

[0105] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0106] In this invention, the server includes an information processing means for analyzing information retrieval conditions input in natural language, a generation means for automatically generating information queries based on the analyzed information retrieval conditions, and a processing means for executing the automatically generated information queries and transmitting the results to an output device. As a result, users can intuitively perform information retrieval using natural language without any specific technical knowledge, quickly obtain appropriate sales trends and inventory information, and visually confirm it.

[0107] "Natural language" refers to the ordinary words and forms of expression used in communication between humans.

[0108] An "information processing device" refers to a machine that analyzes input information and outputs it in an appropriate format.

[0109] "Information retrieval criteria" refer to the conditions or requirements set out to identify the information you want to obtain.

[0110] "Generating means" refers to a mechanism or device for producing a desired output from a specific input.

[0111] An "information inquiry" refers to a request or instruction to a source of information to obtain specific data or knowledge.

[0112] "Processing means" refers to processes and devices used to manipulate and transform input information to obtain the desired result.

[0113] An "output device" refers to a device that displays processed information in a format that is easily recognizable to humans.

[0114] "Sales trends" refer to information that shows changes and trends in sales and demand for a product or service over a specific period.

[0115] "Inventory information" refers to data that shows how much of a product or item is left and how ready it is for sale.

[0116] "Visual confirmation" means displaying and providing information in a way that allows humans to directly see and judge it.

[0117] This invention provides a system that enables information retrieval using natural language. The server uses a natural language processing engine to analyze information retrieval conditions entered in natural language. This engine utilizes technologies such as Google's Natural Language API. Furthermore, it leverages GPT-4® as a generative AI model to automatically generate appropriate information queries based on the analyzed conditions.

[0118] In this system, a smartphone is used as the primary user interface. When a user enters information search criteria in natural language into their smartphone, the input is sent to the server. The server uses a database management system (e.g., MySQL®) to execute the information query and obtain search results such as sales trends and inventory information. The obtained results are displayed visually on the smartphone screen. This display allows the user to quickly review the information and make necessary decisions.

[0119] For example, if a store employee types "What was the best-selling item this month?" into their smartphone, the server analyzes this natural language and issues an appropriate query to the database. It then identifies popular items from the monthly sales data and displays that information on the smartphone. This allows employees to quickly obtain the necessary information and adjust their sales strategies accordingly.

[0120] Examples of prompts for the generating AI model include "Tell me the best-selling product over the weekend" and "Tell me the product that experienced the most stock shortages in the first half of 2023." By using these prompts, users can input information in a natural way and obtain specific results.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The user uses their smartphone to enter information search criteria in natural language. The entered text is sent directly from the device to the server as a string.

[0124] Step 2:

[0125] The server receives the natural language string and performs analysis using a natural language processing engine. This analysis uses the Google Natural Language API to extract keywords and query intent from the input text. The output of the analysis is a structured information retrieval query.

[0126] Step 3:

[0127] The server uses a generative AI model (e.g., GPT-4) to generate appropriate information queries based on structured information retrieval criteria. These generated queries are then converted into database query format, making them executable against the database.

[0128] Step 4:

[0129] The server executes the generated information query and accesses the database via a database management system (e.g., MySQL). As a result of executing this query, data matching the search criteria is retrieved.

[0130] Step 5:

[0131] The acquired data is organized on the server and converted into an output format. This result is then packaged into a visually easy-to-understand format.

[0132] Step 6:

[0133] The server sends the organized results to the terminal. The terminal has the ability to visually display the received information on its screen, allowing the user to immediately check the results. This enables the user to visually confirm the information they need and use it to guide their future actions.

[0134] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0135] This invention relates to a system that generates and executes database queries that take into account the user's emotional state by combining data extraction conditions entered by the user in natural language with an emotion engine. This system is implemented with a configuration including a terminal, a server, and an emotion engine.

[0136] First, the user enters data extraction criteria in natural language using their device. For example, the user might enter a request such as, "I want to know which product has generated the most profit over the past year."

[0137] The terminal sends user input to the server and simultaneously acquires information necessary for the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's tone of voice, facial expressions, and behavioral patterns during input to recognize the current emotional state (e.g., excitement, calmness, dissatisfaction, etc.).

[0138] The server analyzes the received natural language data using natural language processing technology. It extracts the elements necessary for generating database queries from the analysis results and automatically generates queries using a generation AI. At this time, the query priority and filter conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, the system might prioritize concise results to ensure a quick response.

[0139] The generated query is sent back from the server to the terminal for the user to review. The user can check the query content and adjust the conditions or configure detailed settings as needed.

[0140] Once the user confirms the query and commands it to run, the terminal sends an instruction to the server, which then executes the query against the database. The results are then sent back from the server to the terminal and displayed visually on the user's terminal.

[0141] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, they may be presented with additional information or analytical options regarding the results.

[0142] This embodiment enables flexible and interactive data extraction that takes user emotions into consideration. This improves the user experience and enables efficient data utilization.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The user uses their device to input their desired data extraction criteria in natural language. For example, they might input a condition such as, "Tell me which product has generated the most profit in the past year."

[0146] Step 2:

[0147] The terminal transmits the natural language information entered by the user to the emotion engine, and simultaneously sends the input content to the server as digital data.

[0148] Step 3:

[0149] The emotion engine analyzes the user's emotions based on the input information. For example, it analyzes voice tone, changes in input time, and operation patterns to determine whether the user is currently excited or calm.

[0150] Step 4:

[0151] The server uses a natural language processing engine to analyze user input. This analysis identifies the elements necessary for database queries (e.g., time period, profit, product name).

[0152] Step 5:

[0153] The server considers the emotion data identified in step 3 and uses generative AI to generate optimal database queries. For example, if user excitement is detected, the number of results may be limited to return query results quickly.

[0154] Step 6:

[0155] The server sends the generated SQL query back to the terminal. On the terminal, the user can review the query content and customize it as needed.

[0156] Step 7:

[0157] Once the user reviews the query and is satisfied with it, they send an execution command to the server via their terminal.

[0158] Step 8:

[0159] The server receives instructions and executes the generated query against the database to extract data that matches the conditions.

[0160] Step 9:

[0161] The server organizes the extracted data and sends it to the user's device, along with feedback. The device then displays the results visually, making it easy for the user to review.

[0162] Step 10:

[0163] Based on emotional data analyzed using an emotion engine, additional feedback and options are presented to the user. For example, if the user expresses dissatisfaction, additional details or support options may be displayed.

[0164] (Example 2)

[0165] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0166] Traditional systems failed to consider user emotions during data extraction, limiting user experience and interactivity. As a result, the usefulness and relevance of extracted information decreased, and users were unable to quickly access the information they needed.

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

[0168] In this invention, the server includes an information processing device means for analyzing request conditions input in natural language, a generation device means for automatically generating information queries based on the analyzed request conditions and sentiment analysis information, and an execution device means for executing the automatically generated information queries and transmitting the results to a display unit. This enables flexible and efficient information extraction according to the user's emotional state.

[0169] "Natural language" refers to the language that humans use on a daily basis, and it is a language that needs to be analyzed in order for a computer to understand and process it.

[0170] "Requirements" refer to the conditions or requests that a user submits to the system for obtaining specific information.

[0171] An "information processing device" is a device that has the function of analyzing input data and extracting, converting, or processing the necessary information.

[0172] "Emotional analysis information" refers to data analyzed by the system that indicates the user's emotional state.

[0173] A "generation device" is a device that automatically generates database queries and information inquiries based on analyzed requirements and sentiment analysis information.

[0174] An "information query" refers to a question or query that is automatically generated to retrieve information from a specific database or information source.

[0175] An "execution device" is a device that executes generated information queries and presents the results to the user.

[0176] The term "display unit" refers to an interface that allows users to visually confirm information results.

[0177] An "emotion engine" is a system with analytical capabilities that utilizes human interface materials to analyze the user's emotional state.

[0178] "Feedback" refers to the responses and additional information that a system provides in response to user actions or requests.

[0179] This invention is a system that generates and executes information queries that take into account the user's emotional state by combining a sentiment engine with the user's request conditions entered in natural language. This system is implemented with a configuration including a terminal, a server, and a sentiment engine.

[0180] The user enters their requirements in natural language using a terminal. For example, the user might enter a prompt such as, "I want to know which product has generated the most profit in the past year."

[0181] The device sends user input to the server. Simultaneously, the device retrieves data from the emotion engine and analyzes the user's tone of voice, facial expressions, and behavioral information during input. This analysis allows the device to recognize the user's current emotional state.

[0182] The server uses natural language processing technology and generative AI models to analyze incoming data and automatically generate information queries. During generation, the query priority and filtering conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, concise results are prioritized to allow for quick information retrieval.

[0183] The generated information query is sent back from the server to the terminal for confirmation by the user. If necessary, the user can fine-tune the request conditions and configure detailed settings. After confirmation, the user can instruct the terminal to execute, which then sends an instruction to the server, where the server executes the query. The results are then sent back from the server to the terminal and displayed visually.

[0184] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, additional information or further analysis options may be displayed.

[0185] Examples of prompts include, "Please tell me the top 5 best-selling products of 2023," or "I'd like to know the customer satisfaction trends for the past three months." By responding to such prompts, the system can extract information that reflects the user's emotions, enabling it to provide an efficient and satisfying user experience.

[0186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0187] Step 1:

[0188] The user uses a terminal to input their request in natural language. For example, they might input "I want to know which product has generated the most profit in the past year" as a prompt. The terminal receives the entered prompt as input data to send to the server.

[0189] Step 2:

[0190] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and actions during input. This analysis outputs the user's current emotional state (e.g., excitement, calmness, dissatisfaction). The emotion engine processes data acquired from the camera and microphone in real time.

[0191] Step 3:

[0192] The server uses natural language processing techniques and generative AI models to analyze the received request conditions. The input data is a prompt sentence from the user. This process extracts the elements necessary to generate the information query, resulting in structured information as output data that leads to automatic generation.

[0193] Step 4:

[0194] The server automatically generates information queries using a generative AI model, taking into account the analysis results of the emotion engine. In this step, priorities and filter conditions are adjusted based on the user's emotional state, and queries that enable quick and appropriate information provision are output.

[0195] Step 5:

[0196] The generated information query is sent back from the server to the terminal. On the terminal, the user can review the query content and adjust the request conditions or make detailed settings if necessary. Here, the user visually checks the displayed query prompts and optimizes them through the interface.

[0197] Step 6:

[0198] After the user confirms the inquiry details and issues an order to execute, the terminal sends that order to the server. The server receives this order and executes the generated query against the database. The output is a result set from the database based on the information retrieval query.

[0199] Step 7:

[0200] The obtained results are then sent back from the server to the terminal. The terminal displays the results visually, including data visualization and graphing. This process allows the user to quickly access the necessary information and receive the results in a visually easy-to-understand format.

[0201] (Application Example 2)

[0202] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0203] When users search for products on e-commerce sites, there is a need to solve the problem of not being able to provide them with optimal product information while taking their emotional state into consideration. This invention aims to improve the user's shopping experience by providing a system that analyzes the user's emotional state and prioritizes the display of product information based on the results.

[0204] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0205] In this invention, the server includes means for analyzing data extraction conditions entered in natural language, means for automatically generating database queries based on the analyzed data extraction conditions and emotional state, and emotion analysis means for analyzing the user's emotional state and prioritizing the results. This makes it possible to provide optimal product information according to the user's emotions.

[0206] "Data extraction criteria entered in natural language" refers to the conditions that users use when searching for data in a free-form language.

[0207] An "analytical processing device" is a device that analyzes data extraction conditions input in natural language in order to understand the linguistic structure and meaning.

[0208] A "database query generator" is a device that creates database query statements in a format that a computer can understand, based on analysis results.

[0209] "Emotional state" refers to the user's current psychological state and emotions, which are inferred from their voice, facial expressions, and behavior.

[0210] An "emotion analysis device" is a device that identifies the type of emotion a user is feeling based on their voice tone, facial expressions, etc., and provides that information to the system.

[0211] An "execution device" is a device that actually executes automatically generated database queries on the database and retrieves the results.

[0212] A "display device" is a device that allows the user to visually confirm the search results obtained by the execution device.

[0213] This invention is a system designed to enhance the user's shopping experience on e-commerce websites. The user uses a smartphone to input data extraction criteria related to products in natural language. The terminal first sends this input data, provided via voice or text, to a server. The server uses natural language processing technology to analyze the user input. This analysis utilizes representative natural language processing libraries such as spaCy and BERT. Based on the analyzed data extraction criteria, a generative AI model generates appropriate database queries.

[0214] Furthermore, the device also performs emotion analysis. This part estimates the user's emotional state by combining a speech emotion recognition library (e.g., Google Cloud Speech-to-Text) and facial expression analysis software (e.g., Microsoft® Azure® Face API). Based on the information obtained from the emotion analysis, the server prioritizes the results of the generated queries and displays the most appropriate product information preferentially.

[0215] For example, suppose a user excitedly requests to "find out about the latest gadgets that have just come out." In this case, the emotion analysis system detects this excitement, and the generating AI adjusts the query to prioritize displaying the latest gadgets and deals. An example of a prompt in this scenario might be: "A user is excited about finding recently released gadgets. Considering this emotion, how can we prioritize displaying information about new product sales?"

[0216] In this way, the present invention provides a richer and more intuitive user experience and a flexible system that responds immediately to user needs.

[0217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0218] Step 1:

[0219] The device receives data extraction criteria entered by the user in natural language, either as voice or text. It receives a user request as input: "I want to research recently released new gadgets." It then prepares to send this data to the server.

[0220] Step 2:

[0221] The device acquires the necessary audio data for voice input and extracts emotions from the audio data using a speech emotion recognition library. As output, it creates emotional state data based on the user's voice tone and prepares to send it to the server.

[0222] Step 3:

[0223] The server analyzes natural language data received from the terminal using natural language processing libraries (such as spaCy or BERT). It takes natural language sentences as input, analyzes them, and outputs the query structure necessary to generate database queries.

[0224] Step 4:

[0225] The server automatically generates database queries using a generative AI model, taking into account the sentiment analysis results. The input is the analyzed data extraction conditions and sentiment state, and the output is an optimized database query.

[0226] Step 5:

[0227] The server executes an automatically generated query and retrieves results from the database. The input is the generated query, and the output is the retrieved product data.

[0228] Step 6:

[0229] The server sorts the database results obtained according to a priority order that matches the user's sentiment and selects appropriate product information. The input is raw data from the database, and the output is prioritized product information.

[0230] Step 7:

[0231] The server sends sorted product information to the terminal, which then visually displays it to the user, providing a shopping experience. The input is the prioritized product information, and the output is the information displayed on the user's screen.

[0232] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0233] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0234] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0238] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0239] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0240] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0241] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0242] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0243] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0244] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0245] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0246] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0247] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0248] This invention is a system that automatically extracts necessary information from a database simply by the user inputting data extraction conditions in natural language. One possible embodiment involves a configuration utilizing an internet-connected terminal and a server.

[0249] The user uses a terminal to input the conditions for extracting specific information in natural language. In this invention, the user does not need technical knowledge such as SQL and can easily specify data extraction.

[0250] The data extraction conditions entered in natural language are sent from the terminal to the server. The server uses natural language processing technology to analyze the data extraction conditions received from the user. During the analysis process, the server parses the conditional statements and identifies the key elements (elements to be extracted, filter conditions, etc.) necessary for the database query.

[0251] Next, the server uses a generation AI to automatically generate appropriate database queries based on the identified information. This process creates queries that match the user's intent.

[0252] The generated query is sent back from the server to the terminal, making it available for user review. Here, the user can review the query and add or modify detailed conditions as needed. This allows the user to optimize the extraction results to suit their specific needs.

[0253] After user verification, the terminal requests the server to execute a query. The server executes the query against the database and extracts data that matches the specified criteria.

[0254] The extracted data is organized by the server and sent to the user's terminal. The terminal displays this data visually, allowing the user to easily review the results.

[0255] For example, if a user enters a request to "display customers who achieved sales of 10 million yen or more in fiscal year 2023," this invention allows the server to analyze the conditions and automatically generate a query to extract appropriate information from the database based on key elements such as "2023," "10 million yen or more," "sales," and "customers."

[0256] This embodiment allows users to intuitively access the data they need without having to go through the complex steps of building a database or creating queries.

[0257] The following describes the processing flow.

[0258] Step 1:

[0259] The user uses their device to input their desired data extraction criteria in natural language. For example, they might enter a condition such as "Show customers who generated sales of 10 million yen or more in 2023."

[0260] Step 2:

[0261] The terminal converts the input natural language information into digital data and sends it to the server.

[0262] Step 3:

[0263] The server passes the received natural language data to the natural language processing engine and begins analysis. The analysis identifies key elements for data extraction, such as "2023," "over 10 million yen," "sales," and "customers."

[0264] Step 4:

[0265] Based on the analysis results, the server uses a generative AI to generate the optimal database query. This query is constructed to satisfy the analyzed conditions.

[0266] Step 5:

[0267] The server sends the generated SQL query back to the terminal. On the terminal, the user can review and customize the query's contents. Conditions can be added or modified as needed.

[0268] Step 6:

[0269] After the user reviews the query and confirms that the conditions to be applied are correct, they send a command to execute the query to the server from their terminal.

[0270] Step 7:

[0271] The server receives instructions, executes queries against the database, and extracts the corresponding data.

[0272] Step 8:

[0273] The server organizes the extracted data and sends it to the terminal.

[0274] Step 9:

[0275] The device displays received data in a user-friendly format. This allows the user to intuitively check the necessary information.

[0276] (Example 1)

[0277] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] Traditional database query generation systems require users to possess technical knowledge, and a major challenge is the difficulty in directly setting data extraction conditions from natural language. This makes it difficult for non-technical users to effectively utilize the database, highlighting the need to improve the intuitiveness and usability of the interface.

[0279] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0280] In this invention, the server includes means for acquiring data extraction conditions entered by the user in natural language, a processing unit for analyzing the natural language data extraction conditions and extracting key elements, and a generation unit that utilizes generative artificial intelligence to automatically generate database queries based on the analyzed data extraction conditions. This makes it possible for users to generate and execute database queries in natural language and intuitively acquire and display the necessary information, even without technical knowledge.

[0281] "User" refers to an individual or group who attempts to input data extraction conditions in natural language using the system and obtain information.

[0282] "Natural language" is the language that people use in their daily lives and is a form of language that can be easily understood and used without technical knowledge.

[0283] "Data extraction conditions" refer to the search criteria and filter conditions necessary to obtain specific information from a database.

[0284] "Processing device" refers to the hardware or software components that analyze the input data and information and perform the necessary operations.

[0285] "Generation device" is a device with the function of generating an output in another form based on the input data, and in this case, it refers to a device that automatically generates a database query.

[0286] "Generative artificial intelligence" refers to artificial intelligence technology that can understand natural language and perform responses or data generation according to tasks.

[0287] "Automatic generation" refers to the process in which the system autonomously generates data or results without human intervention.

[0288] "Execution device" refers to the hardware or software that executes the generated query and completes the specified operations.

[0289] "Key element" refers to the main elements and components that make up the data extraction conditions and refers to the elements for performing an efficient search on the database.

[0290] "Display device" refers to the hardware or device for visually presenting digital data and information to the user.

[0291] This invention is an automated database query generation system that enables data extraction using natural language. The system consists of a user terminal with an internet connection and a server that performs data processing and query generation.

[0292] The user uses a terminal to input conditions in natural language to extract specific information from the database. For example, when prompting with the message "Show customers who achieved sales of 10 million yen or more in fiscal year 2023," the user can set data extraction conditions using natural language without requiring advanced technical knowledge.

[0293] The terminal sends the input natural language conditions to the server. The server uses natural language processing technology and generative artificial intelligence models to analyze the input conditions and extract the necessary key elements. Based on the analysis, the server automatically generates an efficient database query. The generated query is sent to the terminal for the user to review and customize. The server organizes the query execution results and presents the data visually to the terminal.

[0294] The server can use generative AI models such as BERT or GPT for natural language processing, enabling accurate analysis of user input conditions. This allows the system to efficiently extract the data desired by the user and provide an intuitive and user-friendly interface.

[0295] This embodiment allows users to easily interact with the database and extract and utilize meaningful data, even without technical knowledge.

[0296] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0297] Step 1:

[0298] The user uses a terminal to input the information they want to retrieve from the database in natural language. The input is in text format through the terminal's interface. This prompt is a way for users to specify requests without specific technical skills. An example of input is, "Show customers who achieved sales of 10 million yen or more in fiscal year 2023."

[0299] Step 2:

[0300] The terminal sends data extraction criteria, received from the user in natural language, to the server. This prompt is sent as text data via an API designed for analysis by the server. The server places the received data in a waiting state for processing.

[0301] Step 3:

[0302] The server analyzes the prompt text using natural language processing techniques and generative AI models. The server first tokenizes the input natural language text and performs context-based semantic analysis. For example, it extracts specific key elements such as a particular year or amount, which are then used to generate the next query. This analysis produces a list of key elements as an intermediate output.

[0303] Step 4:

[0304] The server automatically constructs database queries based on key elements extracted through analysis using generation AI. The server creates query syntax from the key elements and converts it into a query language such as SQL. The output is a query in a format compatible with the database.

[0305] Step 5:

[0306] The generated query is sent from the server to the terminal. On the terminal, the user can review this query and customize or modify it as needed. At this stage, the user visually verifies whether the extraction criteria are appropriate by receiving the output query.

[0307] Step 6:

[0308] The user requests the server to execute a query through the terminal. The terminal sends the execution request by the user to the server and requests the application of the query to the server. Based on the received request, the server attempts to access the database.

[0309] Step 7:

[0310] The server executes the specified query against the database and extracts matching data records. The server executes the query through the database engine and processes the obtained output data.

[0311] Step 8:

[0312] The obtained data is sorted by the server and sent to the user's terminal. The terminal displays this data in a visually easy-to-understand form such as a graph or table format, enabling the user to easily check the results.

[0313] (Application Example 1)

[0314] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] In a conventional information retrieval system, it has been difficult to quickly and appropriately obtain the information required by the user without specific technical knowledge. Also, when the user makes an inquiry in natural language, there has been a lack of means to immediately obtain and visually confirm relevant sales trends and inventory information. As a result, there has been a problem that the efficiency of information retrieval is reduced and quick processing is hindered in customer support.

[0316] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0317] In this invention, the server includes an information processing means for analyzing information retrieval conditions input in natural language, a generation means for automatically generating information queries based on the analyzed information retrieval conditions, and a processing means for executing the automatically generated information queries and transmitting the results to an output device. As a result, users can intuitively perform information retrieval using natural language without any specific technical knowledge, quickly obtain appropriate sales trends and inventory information, and visually confirm it.

[0318] "Natural language" refers to the ordinary words and forms of expression used in communication between humans.

[0319] An "information processing device" refers to a machine that analyzes input information and outputs it in an appropriate format.

[0320] "Information retrieval criteria" refer to the conditions or requirements set out to identify the information you want to obtain.

[0321] "Generating means" refers to a mechanism or device for producing a desired output from a specific input.

[0322] An "information inquiry" refers to a request or instruction to a source of information to obtain specific data or knowledge.

[0323] "Processing means" refers to processes and devices used to manipulate and transform input information to obtain the desired result.

[0324] An "output device" refers to a device that displays processed information in a format that is easily recognizable to humans.

[0325] "Sales trends" refer to information that shows changes and trends in sales and demand for a product or service over a specific period.

[0326] "Inventory information" refers to data that shows how much of a product or item is left and how ready it is for sale.

[0327] "Visual confirmation" means displaying and providing information in a way that allows humans to directly see and judge it.

[0328] This invention provides a system that enables information retrieval using natural language. The server uses a natural language processing engine to analyze information retrieval conditions entered in natural language. This engine utilizes technologies such as the Google Natural Language API. Furthermore, it leverages GPT-4 as a generative AI model to automatically generate appropriate information queries based on the analyzed conditions.

[0329] In this system, a smartphone is used as the primary user interface. When a user enters information search criteria in natural language into their smartphone, the input is sent to the server. The server uses a database management system (e.g., MySQL) to execute the information query and obtain search results such as sales trends and inventory information. The obtained results are displayed visually on the smartphone screen. This display allows the user to quickly review the information and make necessary decisions.

[0330] For example, if a store employee types "What was the best-selling item this month?" into their smartphone, the server analyzes this natural language and issues an appropriate query to the database. It then identifies popular items from the monthly sales data and displays that information on the smartphone. This allows employees to quickly obtain the necessary information and adjust their sales strategies accordingly.

[0331] Examples of prompts for the generating AI model include "Tell me the best-selling product over the weekend" and "Tell me the product that experienced the most stock shortages in the first half of 2023." By using these prompts, users can input information in a natural way and obtain specific results.

[0332] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0333] Step 1:

[0334] The user uses their smartphone to enter information search criteria in natural language. The entered text is sent directly from the device to the server as a string.

[0335] Step 2:

[0336] The server receives the natural language string and performs analysis using a natural language processing engine. This analysis uses the Google Natural Language API to extract keywords and query intent from the input text. The output of the analysis is a structured information retrieval query.

[0337] Step 3:

[0338] The server uses a generative AI model (e.g., GPT-4) to generate appropriate information queries based on structured information retrieval criteria. These generated queries are then converted into database query format, making them executable against the database.

[0339] Step 4:

[0340] The server executes the generated information query and accesses the database via a database management system (e.g., MySQL). As a result of executing this query, data matching the search criteria is retrieved.

[0341] Step 5:

[0342] The acquired data is organized on the server and converted into an output format. This result is then packaged into a visually easy-to-understand format.

[0343] Step 6:

[0344] The server sends the organized results to the terminal. The terminal has the ability to visually display the received information on its screen, allowing the user to immediately check the results. This enables the user to visually confirm the information they need and use it to guide their future actions.

[0345] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0346] This invention relates to a system that generates and executes database queries that take into account the user's emotional state by combining data extraction conditions entered by the user in natural language with an emotion engine. This system is implemented with a configuration including a terminal, a server, and an emotion engine.

[0347] First, the user enters data extraction criteria in natural language using their device. For example, the user might enter a request such as, "I want to know which product has generated the most profit over the past year."

[0348] The terminal sends user input to the server and simultaneously acquires information necessary for the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's tone of voice, facial expressions, and behavioral patterns during input to recognize the current emotional state (e.g., excitement, calmness, dissatisfaction, etc.).

[0349] The server analyzes the received natural language data using natural language processing technology. It extracts the elements necessary for generating database queries from the analysis results and automatically generates queries using a generation AI. At this time, the query priority and filter conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, the system might prioritize concise results to ensure a quick response.

[0350] The generated query is sent back from the server to the terminal for the user to review. The user can check the query content and adjust the conditions or configure detailed settings as needed.

[0351] Once the user confirms the query and commands it to run, the terminal sends an instruction to the server, which then executes the query against the database. The results are then sent back from the server to the terminal and displayed visually on the user's terminal.

[0352] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, they may be presented with additional information or analytical options regarding the results.

[0353] This embodiment enables flexible and interactive data extraction that takes user emotions into consideration. This improves the user experience and enables efficient data utilization.

[0354] The following describes the processing flow.

[0355] Step 1:

[0356] The user uses their device to input their desired data extraction criteria in natural language. For example, they might input a condition such as, "Tell me which product has generated the most profit in the past year."

[0357] Step 2:

[0358] The terminal transmits the natural language information entered by the user to the emotion engine, and simultaneously sends the input content to the server as digital data.

[0359] Step 3:

[0360] The emotion engine analyzes the user's emotions based on the input information. For example, it analyzes voice tone, changes in input time, and operation patterns to determine whether the user is currently excited or calm.

[0361] Step 4:

[0362] The server uses a natural language processing engine to analyze user input. This analysis identifies the elements necessary for database queries (e.g., time period, profit, product name).

[0363] Step 5:

[0364] The server considers the emotion data identified in step 3 and uses generative AI to generate optimal database queries. For example, if user excitement is detected, the number of results may be limited to return query results quickly.

[0365] Step 6:

[0366] The server sends the generated SQL query back to the terminal. On the terminal, the user can review the query content and customize it as needed.

[0367] Step 7:

[0368] Once the user reviews the query and is satisfied with it, they send an execution command to the server via their terminal.

[0369] Step 8:

[0370] The server receives instructions and executes the generated query against the database to extract data that matches the conditions.

[0371] Step 9:

[0372] The server organizes the extracted data and sends it to the user's device, along with feedback. The device then displays the results visually, making it easy for the user to review.

[0373] Step 10:

[0374] Based on emotional data analyzed using an emotion engine, additional feedback and options are presented to the user. For example, if the user expresses dissatisfaction, additional details or support options may be displayed.

[0375] (Example 2)

[0376] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0377] Traditional systems failed to consider user emotions during data extraction, limiting user experience and interactivity. As a result, the usefulness and relevance of extracted information decreased, and users were unable to quickly access the information they needed.

[0378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0379] In this invention, the server includes an information processing device means for analyzing request conditions input in natural language, a generation device means for automatically generating information queries based on the analyzed request conditions and sentiment analysis information, and an execution device means for executing the automatically generated information queries and transmitting the results to a display unit. This enables flexible and efficient information extraction according to the user's emotional state.

[0380] "Natural language" refers to the language that humans use on a daily basis, and it is a language that needs to be analyzed in order for a computer to understand and process it.

[0381] "Requirements" refer to the conditions or requests that a user submits to the system for obtaining specific information.

[0382] An "information processing device" is a device that has the function of analyzing input data and extracting, converting, or processing the necessary information.

[0383] "Emotional analysis information" refers to data analyzed by the system that indicates the user's emotional state.

[0384] A "generation device" is a device that automatically generates database queries and information inquiries based on analyzed requirements and sentiment analysis information.

[0385] An "information query" refers to a question or query that is automatically generated to retrieve information from a specific database or information source.

[0386] An "execution device" is a device that executes generated information queries and presents the results to the user.

[0387] The term "display unit" refers to an interface that allows users to visually confirm information results.

[0388] An "emotion engine" is a system with analytical capabilities that utilizes human interface materials to analyze the user's emotional state.

[0389] "Feedback" refers to the responses and additional information that a system provides in response to user actions or requests.

[0390] This invention is a system that generates and executes information queries that take into account the user's emotional state by combining a sentiment engine with the user's request conditions entered in natural language. This system is implemented with a configuration including a terminal, a server, and a sentiment engine.

[0391] The user enters their requirements in natural language using a terminal. For example, the user might enter a prompt such as, "I want to know which product has generated the most profit in the past year."

[0392] The device sends user input to the server. Simultaneously, the device retrieves data from the emotion engine and analyzes the user's tone of voice, facial expressions, and behavioral information during input. This analysis allows the device to recognize the user's current emotional state.

[0393] The server uses natural language processing technology and generative AI models to analyze incoming data and automatically generate information queries. During generation, the query priority and filtering conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, concise results are prioritized to allow for quick information retrieval.

[0394] The generated information query is sent back from the server to the terminal for confirmation by the user. If necessary, the user can fine-tune the request conditions and configure detailed settings. After confirmation, the user can instruct the terminal to execute, which then sends an instruction to the server, where the server executes the query. The results are then sent back from the server to the terminal and displayed visually.

[0395] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, additional information or further analysis options may be displayed.

[0396] Examples of prompts include, "Please tell me the top 5 best-selling products of 2023," or "I'd like to know the customer satisfaction trends for the past three months." By responding to such prompts, the system can extract information that reflects the user's emotions, enabling it to provide an efficient and satisfying user experience.

[0397] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0398] Step 1:

[0399] The user uses a terminal to input their request in natural language. For example, they might input "I want to know which product has generated the most profit in the past year" as a prompt. The terminal receives the entered prompt as input data to send to the server.

[0400] Step 2:

[0401] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and actions during input. This analysis outputs the user's current emotional state (e.g., excitement, calmness, dissatisfaction). The emotion engine processes data acquired from the camera and microphone in real time.

[0402] Step 3:

[0403] The server uses natural language processing techniques and generative AI models to analyze the received request conditions. The input data is a prompt sentence from the user. This process extracts the elements necessary to generate the information query, resulting in structured information as output data that leads to automatic generation.

[0404] Step 4:

[0405] The server automatically generates information queries using a generative AI model, taking into account the analysis results of the emotion engine. In this step, priorities and filter conditions are adjusted based on the user's emotional state, and queries that enable quick and appropriate information provision are output.

[0406] Step 5:

[0407] The generated information query is sent back from the server to the terminal. On the terminal, the user can review the query content and adjust the request conditions or make detailed settings if necessary. Here, the user visually checks the displayed query prompts and optimizes them through the interface.

[0408] Step 6:

[0409] After the user confirms the inquiry details and issues an order to execute, the terminal sends that order to the server. The server receives this order and executes the generated query against the database. The output is a result set from the database based on the information retrieval query.

[0410] Step 7:

[0411] The obtained results are then sent back from the server to the terminal. The terminal displays the results visually, including data visualization and graphing. This process allows the user to quickly access the necessary information and receive the results in a visually easy-to-understand format.

[0412] (Application Example 2)

[0413] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0414] When users search for products on e-commerce sites, there is a need to solve the problem of not being able to provide them with optimal product information while taking their emotional state into consideration. This invention aims to improve the user's shopping experience by providing a system that analyzes the user's emotional state and prioritizes the display of product information based on the results.

[0415] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0416] In this invention, the server includes means for analyzing data extraction conditions entered in natural language, means for automatically generating database queries based on the analyzed data extraction conditions and emotional state, and emotion analysis means for analyzing the user's emotional state and prioritizing the results. This makes it possible to provide optimal product information according to the user's emotions.

[0417] "Data extraction criteria entered in natural language" refers to the conditions that users use when searching for data in a free-form language.

[0418] An "analytical processing device" is a device that analyzes data extraction conditions input in natural language in order to understand the linguistic structure and meaning.

[0419] A "database query generator" is a device that creates database query statements in a format that a computer can understand, based on analysis results.

[0420] "Emotional state" refers to the user's current psychological state and emotions, which are inferred from their voice, facial expressions, and behavior.

[0421] An "emotion analysis device" is a device that identifies the type of emotion a user is feeling based on their voice tone, facial expressions, etc., and provides that information to the system.

[0422] An "execution device" is a device that actually executes automatically generated database queries on the database and retrieves the results.

[0423] A "display device" is a device that allows the user to visually confirm the search results obtained by the execution device.

[0424] This invention is a system designed to enhance the user's shopping experience on e-commerce websites. The user uses a smartphone to input data extraction criteria related to products in natural language. The terminal first sends this input data, provided via voice or text, to a server. The server uses natural language processing technology to analyze the user input. This analysis utilizes representative natural language processing libraries such as spaCy and BERT. Based on the analyzed data extraction criteria, a generative AI model generates appropriate database queries.

[0425] Furthermore, the device also performs emotion analysis. This part estimates the user's emotional state by combining a speech emotion recognition library (e.g., Google Cloud Speech-to-Text) and facial expression analysis software (e.g., Microsoft Azure Face API). Based on the information obtained from the emotion analysis, the server prioritizes the results of the generated queries and displays the most appropriate product information preferentially.

[0426] For example, suppose a user excitedly requests to "find out about the latest gadgets that have just come out." In this case, the emotion analysis system detects this excitement, and the generating AI adjusts the query to prioritize displaying the latest gadgets and deals. An example of a prompt in this scenario might be: "A user is excited about finding recently released gadgets. Considering this emotion, how can we prioritize displaying information about new product sales?"

[0427] In this way, the present invention provides a richer and more intuitive user experience and a flexible system that responds immediately to user needs.

[0428] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0429] Step 1:

[0430] The device receives data extraction criteria entered by the user in natural language, either as voice or text. It receives a user request as input: "I want to research recently released new gadgets." It then prepares to send this data to the server.

[0431] Step 2:

[0432] The device acquires the necessary audio data for voice input and extracts emotions from the audio data using a speech emotion recognition library. As output, it creates emotional state data based on the user's voice tone and prepares to send it to the server.

[0433] Step 3:

[0434] The server analyzes natural language data received from the terminal using natural language processing libraries (such as spaCy or BERT). It takes natural language sentences as input, analyzes them, and outputs the query structure necessary to generate database queries.

[0435] Step 4:

[0436] The server automatically generates database queries using a generative AI model, taking into account the sentiment analysis results. The input is the analyzed data extraction conditions and sentiment state, and the output is an optimized database query.

[0437] Step 5:

[0438] The server executes an automatically generated query and retrieves results from the database. The input is the generated query, and the output is the retrieved product data.

[0439] Step 6:

[0440] The server sorts the database results obtained according to a priority order that matches the user's sentiment and selects appropriate product information. The input is raw data from the database, and the output is prioritized product information.

[0441] Step 7:

[0442] The server sends sorted product information to the terminal, which then visually displays it to the user, providing a shopping experience. The input is the prioritized product information, and the output is the information displayed on the user's screen.

[0443] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0444] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0445] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0446] [Third Embodiment]

[0447] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0448] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0449] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0450] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0451] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0453] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0454] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0455] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0456] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0457] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0458] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0459] This invention is a system that automatically extracts necessary information from a database simply by the user inputting data extraction conditions in natural language. One possible embodiment involves a configuration utilizing an internet-connected terminal and a server.

[0460] The user uses a terminal to input the conditions for extracting specific information in natural language. In this invention, the user does not need technical knowledge such as SQL and can easily specify data extraction.

[0461] The data extraction conditions entered in natural language are sent from the terminal to the server. The server uses natural language processing technology to analyze the data extraction conditions received from the user. During the analysis process, the server parses the conditional statements and identifies the key elements (elements to be extracted, filter conditions, etc.) necessary for the database query.

[0462] Next, the server uses a generation AI to automatically generate appropriate database queries based on the identified information. This process creates queries that match the user's intent.

[0463] The generated query is sent back from the server to the terminal, making it available for user review. Here, the user can review the query and add or modify detailed conditions as needed. This allows the user to optimize the extraction results to suit their specific needs.

[0464] After user verification, the terminal requests the server to execute a query. The server executes the query against the database and extracts data that matches the specified criteria.

[0465] The extracted data is organized by the server and sent to the user's terminal. The terminal displays this data visually, allowing the user to easily review the results.

[0466] For example, if a user enters a request to "display customers who achieved sales of 10 million yen or more in fiscal year 2023," this invention allows the server to analyze the conditions and automatically generate a query to extract appropriate information from the database based on key elements such as "2023," "10 million yen or more," "sales," and "customers."

[0467] This embodiment allows users to intuitively access the data they need without having to go through the complex steps of building a database or creating queries.

[0468] The following describes the processing flow.

[0469] Step 1:

[0470] The user uses their device to input their desired data extraction criteria in natural language. For example, they might enter a condition such as "Show customers who generated sales of 10 million yen or more in 2023."

[0471] Step 2:

[0472] The terminal converts the input natural language information into digital data and sends it to the server.

[0473] Step 3:

[0474] The server passes the received natural language data to the natural language processing engine and begins analysis. The analysis identifies key elements for data extraction, such as "2023," "over 10 million yen," "sales," and "customers."

[0475] Step 4:

[0476] Based on the analysis results, the server uses a generative AI to generate the optimal database query. This query is constructed to satisfy the analyzed conditions.

[0477] Step 5:

[0478] The server sends the generated SQL query back to the terminal. On the terminal, the user can review and customize the query's contents. Conditions can be added or modified as needed.

[0479] Step 6:

[0480] After the user reviews the query and confirms that the conditions to be applied are correct, they send a command to execute the query to the server from their terminal.

[0481] Step 7:

[0482] The server receives instructions, executes queries against the database, and extracts the corresponding data.

[0483] Step 8:

[0484] The server organizes the extracted data and sends it to the terminal.

[0485] Step 9:

[0486] The device displays received data in a user-friendly format. This allows the user to intuitively check the necessary information.

[0487] (Example 1)

[0488] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0489] Traditional database query generation systems require users to possess technical knowledge, and a major challenge is the difficulty in directly setting data extraction conditions from natural language. This makes it difficult for non-technical users to effectively utilize the database, highlighting the need to improve the intuitiveness and usability of the interface.

[0490] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0491] In this invention, the server includes means for acquiring data extraction conditions entered by the user in natural language, a processing unit for analyzing the natural language data extraction conditions and extracting key elements, and a generation unit that utilizes generative artificial intelligence to automatically generate database queries based on the analyzed data extraction conditions. This makes it possible for users to generate and execute database queries in natural language and intuitively acquire and display the necessary information, even without technical knowledge.

[0492] A "user" refers to an individual or organization that uses the system to input data extraction criteria in natural language and attempts to obtain information.

[0493] "Natural language" refers to language that humans use on a daily basis, a form of language that can be easily understood and used even without technical knowledge.

[0494] "Data extraction conditions" refer to the search criteria and filter conditions necessary to retrieve specific information from a database.

[0495] A "processing device" refers to a hardware or software component that analyzes input data and information and performs the necessary operations.

[0496] A "generation device" is a device that has the function of generating output in a different format based on input data, and in this case, it refers to a device that automatically generates database queries.

[0497] "Generative artificial intelligence" refers to artificial intelligence technology that can understand natural language and provide responses and generate data according to the task.

[0498] "Automatic generation" refers to the process by which a system autonomously generates data or results without human intervention.

[0499] An "execution device" refers to hardware or software that executes a generated query and completes a specified operation.

[0500] "Key elements" refer to the main elements or components that constitute the data extraction criteria, and are the elements necessary for efficient searching of the database.

[0501] A "display device" refers to hardware or equipment used to visually present digital data and information to a user.

[0502] This invention is an automated database query generation system that enables data extraction using natural language. The system consists of a user terminal with an internet connection and a server that performs data processing and query generation.

[0503] The user uses a terminal to input conditions in natural language to extract specific information from the database. For example, when prompting with the message "Show customers who achieved sales of 10 million yen or more in fiscal year 2023," the user can set data extraction conditions using natural language without requiring advanced technical knowledge.

[0504] The terminal sends the input natural language conditions to the server. The server uses natural language processing technology and generative artificial intelligence models to analyze the input conditions and extract the necessary key elements. Based on the analysis, the server automatically generates an efficient database query. The generated query is sent to the terminal for the user to review and customize. The server organizes the query execution results and presents the data visually to the terminal.

[0505] The server can use generative AI models such as BERT or GPT for natural language processing, enabling accurate analysis of user input conditions. This allows the system to efficiently extract the data desired by the user and provide an intuitive and user-friendly interface.

[0506] This embodiment allows users to easily interact with the database and extract and utilize meaningful data, even without technical knowledge.

[0507] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0508] Step 1:

[0509] The user uses a terminal to input the information they want to retrieve from the database in natural language. The input is in text format through the terminal's interface. This prompt is a way for users to specify requests without specific technical skills. An example of input is, "Show customers who achieved sales of 10 million yen or more in fiscal year 2023."

[0510] Step 2:

[0511] The terminal sends data extraction criteria, received from the user in natural language, to the server. This prompt is sent as text data via an API designed for analysis by the server. The server places the received data in a waiting state for processing.

[0512] Step 3:

[0513] The server analyzes the prompt text using natural language processing techniques and generative AI models. The server first tokenizes the input natural language text and performs context-based semantic analysis. For example, it extracts specific key elements such as a particular year or amount, which are then used to generate the next query. This analysis produces a list of key elements as an intermediate output.

[0514] Step 4:

[0515] The server automatically constructs database queries based on key elements extracted through analysis using generation AI. The server creates query syntax from the key elements and converts it into a query language such as SQL. The output is a query in a format compatible with the database.

[0516] Step 5:

[0517] The generated query is sent from the server to the terminal. On the terminal, the user can review this query and customize or modify it as needed. At this stage, the user visually verifies whether the extraction criteria are appropriate by receiving the output query.

[0518] Step 6:

[0519] The user requests the server to execute a query via their terminal. The terminal sends the user's execution request to the server, asking the server to apply the query. Based on the received request, the server attempts to access the database.

[0520] Step 7:

[0521] The server executes the specified query against the database and extracts matching data records. The server executes the query through the database engine and processes the retrieved output data.

[0522] Step 8:

[0523] The acquired data is organized by the server and sent to the user's terminal. The terminal displays this data in a visually easy-to-understand format, such as graphs or tables, allowing the user to easily check the results.

[0524] (Application Example 1)

[0525] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0526] In conventional information retrieval systems, it was difficult for users to quickly and appropriately obtain the information they needed without requiring specific technical knowledge. Furthermore, there was a lack of means to instantly retrieve and visually confirm relevant sales trends and inventory information when users made inquiries using natural language. This resulted in reduced information retrieval efficiency and hindered the rapid processing of customer service.

[0527] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0528] In this invention, the server includes an information processing means for analyzing information retrieval conditions input in natural language, a generation means for automatically generating information queries based on the analyzed information retrieval conditions, and a processing means for executing the automatically generated information queries and transmitting the results to an output device. As a result, users can intuitively perform information retrieval using natural language without any specific technical knowledge, quickly obtain appropriate sales trends and inventory information, and visually confirm it.

[0529] "Natural language" refers to the ordinary words and forms of expression used in communication between humans.

[0530] An "information processing device" refers to a machine that analyzes input information and outputs it in an appropriate format.

[0531] "Information retrieval criteria" refer to the conditions or requirements set out to identify the information you want to obtain.

[0532] "Generating means" refers to a mechanism or device for producing a desired output from a specific input.

[0533] An "information inquiry" refers to a request or instruction to a source of information to obtain specific data or knowledge.

[0534] "Processing means" refers to processes and devices used to manipulate and transform input information to obtain the desired result.

[0535] An "output device" refers to a device that displays processed information in a format that is easily recognizable to humans.

[0536] "Sales trends" refer to information that shows changes and trends in sales and demand for a product or service over a specific period.

[0537] "Inventory information" refers to data that shows how much of a product or item is left and how ready it is for sale.

[0538] "Visual confirmation" means displaying and providing information in a way that allows humans to directly see and judge it.

[0539] This invention provides a system that enables information retrieval using natural language. The server uses a natural language processing engine to analyze information retrieval conditions entered in natural language. This engine utilizes technologies such as the Google Natural Language API. Furthermore, it leverages GPT-4 as a generative AI model to automatically generate appropriate information queries based on the analyzed conditions.

[0540] In this system, a smartphone is used as the primary user interface. When a user enters information search criteria in natural language into their smartphone, the input is sent to the server. The server uses a database management system (e.g., MySQL) to execute the information query and obtain search results such as sales trends and inventory information. The obtained results are displayed visually on the smartphone screen. This display allows the user to quickly review the information and make necessary decisions.

[0541] For example, if a store employee types "What was the best-selling item this month?" into their smartphone, the server analyzes this natural language and issues an appropriate query to the database. It then identifies popular items from the monthly sales data and displays that information on the smartphone. This allows employees to quickly obtain the necessary information and adjust their sales strategies accordingly.

[0542] Examples of prompts for the generating AI model include "Tell me the best-selling product over the weekend" and "Tell me the product that experienced the most stock shortages in the first half of 2023." By using these prompts, users can input information in a natural way and obtain specific results.

[0543] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0544] Step 1:

[0545] The user uses their smartphone to enter information search criteria in natural language. The entered text is sent directly from the device to the server as a string.

[0546] Step 2:

[0547] The server receives the natural language string and performs analysis using a natural language processing engine. This analysis uses the Google Natural Language API to extract keywords and query intent from the input text. The output of the analysis is a structured information retrieval query.

[0548] Step 3:

[0549] The server uses a generative AI model (e.g., GPT-4) to generate appropriate information queries based on structured information retrieval criteria. These generated queries are then converted into database query format, making them executable against the database.

[0550] Step 4:

[0551] The server executes the generated information query and accesses the database via a database management system (e.g., MySQL). As a result of executing this query, data matching the search criteria is retrieved.

[0552] Step 5:

[0553] The acquired data is organized on the server and converted into an output format. This result is then packaged into a visually easy-to-understand format.

[0554] Step 6:

[0555] The server sends the organized results to the terminal. The terminal has the ability to visually display the received information on its screen, allowing the user to immediately check the results. This enables the user to visually confirm the information they need and use it to guide their future actions.

[0556] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0557] This invention relates to a system that generates and executes database queries that take into account the user's emotional state by combining data extraction conditions entered by the user in natural language with an emotion engine. This system is implemented with a configuration including a terminal, a server, and an emotion engine.

[0558] First, the user enters data extraction criteria in natural language using their device. For example, the user might enter a request such as, "I want to know which product has generated the most profit over the past year."

[0559] The terminal sends user input to the server and simultaneously acquires information necessary for the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's tone of voice, facial expressions, and behavioral patterns during input to recognize the current emotional state (e.g., excitement, calmness, dissatisfaction, etc.).

[0560] The server analyzes the received natural language data using natural language processing technology. It extracts the elements necessary for generating database queries from the analysis results and automatically generates queries using a generation AI. At this time, the query priority and filter conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, the system might prioritize concise results to ensure a quick response.

[0561] The generated query is sent back from the server to the terminal for the user to review. The user can check the query content and adjust the conditions or configure detailed settings as needed.

[0562] Once the user confirms the query and commands it to run, the terminal sends an instruction to the server, which then executes the query against the database. The results are then sent back from the server to the terminal and displayed visually on the user's terminal.

[0563] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, they may be presented with additional information or analytical options regarding the results.

[0564] This embodiment enables flexible and interactive data extraction that takes user emotions into consideration. This improves the user experience and enables efficient data utilization.

[0565] The following describes the processing flow.

[0566] Step 1:

[0567] The user uses their device to input their desired data extraction criteria in natural language. For example, they might input a condition such as, "Tell me which product has generated the most profit in the past year."

[0568] Step 2:

[0569] The terminal transmits the natural language information entered by the user to the emotion engine, and simultaneously sends the input content to the server as digital data.

[0570] Step 3:

[0571] The emotion engine analyzes the user's emotions based on the input information. For example, it analyzes voice tone, changes in input time, and operation patterns to determine whether the user is currently excited or calm.

[0572] Step 4:

[0573] The server uses a natural language processing engine to analyze user input. This analysis identifies the elements necessary for database queries (e.g., time period, profit, product name).

[0574] Step 5:

[0575] The server considers the emotion data identified in step 3 and uses generative AI to generate optimal database queries. For example, if user excitement is detected, the number of results may be limited to return query results quickly.

[0576] Step 6:

[0577] The server sends the generated SQL query back to the terminal. On the terminal, the user can review the query content and customize it as needed.

[0578] Step 7:

[0579] Once the user reviews the query and is satisfied with it, they send an execution command to the server via their terminal.

[0580] Step 8:

[0581] The server receives instructions and executes the generated query against the database to extract data that matches the conditions.

[0582] Step 9:

[0583] The server organizes the extracted data and sends it to the user's device, along with feedback. The device then displays the results visually, making it easy for the user to review.

[0584] Step 10:

[0585] Based on emotional data analyzed using an emotion engine, additional feedback and options are presented to the user. For example, if the user expresses dissatisfaction, additional details or support options may be displayed.

[0586] (Example 2)

[0587] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0588] Traditional systems failed to consider user emotions during data extraction, limiting user experience and interactivity. As a result, the usefulness and relevance of extracted information decreased, and users were unable to quickly access the information they needed.

[0589] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0590] In this invention, the server includes an information processing device means for analyzing request conditions input in natural language, a generation device means for automatically generating information queries based on the analyzed request conditions and sentiment analysis information, and an execution device means for executing the automatically generated information queries and transmitting the results to a display unit. This enables flexible and efficient information extraction according to the user's emotional state.

[0591] "Natural language" refers to the language that humans use on a daily basis, and it is a language that needs to be analyzed in order for a computer to understand and process it.

[0592] "Requirements" refer to the conditions or requests that a user submits to the system for obtaining specific information.

[0593] An "information processing device" is a device that has the function of analyzing input data and extracting, converting, or processing the necessary information.

[0594] "Emotional analysis information" refers to data analyzed by the system that indicates the user's emotional state.

[0595] A "generation device" is a device that automatically generates database queries and information inquiries based on analyzed requirements and sentiment analysis information.

[0596] An "information query" refers to a question or query that is automatically generated to retrieve information from a specific database or information source.

[0597] An "execution device" is a device that executes generated information queries and presents the results to the user.

[0598] The term "display unit" refers to an interface that allows users to visually confirm information results.

[0599] An "emotion engine" is a system with analytical capabilities that utilizes human interface materials to analyze the user's emotional state.

[0600] "Feedback" refers to the responses and additional information that a system provides in response to user actions or requests.

[0601] This invention is a system that generates and executes information queries that take into account the user's emotional state by combining a sentiment engine with the user's request conditions entered in natural language. This system is implemented with a configuration including a terminal, a server, and a sentiment engine.

[0602] The user enters their requirements in natural language using a terminal. For example, the user might enter a prompt such as, "I want to know which product has generated the most profit in the past year."

[0603] The device sends user input to the server. Simultaneously, the device retrieves data from the emotion engine and analyzes the user's tone of voice, facial expressions, and behavioral information during input. This analysis allows the device to recognize the user's current emotional state.

[0604] The server uses natural language processing technology and generative AI models to analyze incoming data and automatically generate information queries. During generation, the query priority and filtering conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, concise results are prioritized to allow for quick information retrieval.

[0605] The generated information query is sent back from the server to the terminal for confirmation by the user. If necessary, the user can fine-tune the request conditions and configure detailed settings. After confirmation, the user can instruct the terminal to execute, which then sends an instruction to the server, where the server executes the query. The results are then sent back from the server to the terminal and displayed visually.

[0606] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, additional information or further analysis options may be displayed.

[0607] Examples of prompts include, "Please tell me the top 5 best-selling products of 2023," or "I'd like to know the customer satisfaction trends for the past three months." By responding to such prompts, the system can extract information that reflects the user's emotions, enabling it to provide an efficient and satisfying user experience.

[0608] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0609] Step 1:

[0610] The user uses a terminal to input their request in natural language. For example, they might input "I want to know which product has generated the most profit in the past year" as a prompt. The terminal receives the entered prompt as input data to send to the server.

[0611] Step 2:

[0612] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and actions during input. This analysis outputs the user's current emotional state (e.g., excitement, calmness, dissatisfaction). The emotion engine processes data acquired from the camera and microphone in real time.

[0613] Step 3:

[0614] The server uses natural language processing techniques and generative AI models to analyze the received request conditions. The input data is a prompt sentence from the user. This process extracts the elements necessary to generate the information query, resulting in structured information as output data that leads to automatic generation.

[0615] Step 4:

[0616] The server automatically generates information queries using a generative AI model, taking into account the analysis results of the emotion engine. In this step, priorities and filter conditions are adjusted based on the user's emotional state, and queries that enable quick and appropriate information provision are output.

[0617] Step 5:

[0618] The generated information query is sent back from the server to the terminal. On the terminal, the user can review the query content and adjust the request conditions or make detailed settings if necessary. Here, the user visually checks the displayed query prompts and optimizes them through the interface.

[0619] Step 6:

[0620] After the user confirms the inquiry details and issues an order to execute, the terminal sends that order to the server. The server receives this order and executes the generated query against the database. The output is a result set from the database based on the information retrieval query.

[0621] Step 7:

[0622] The obtained results are then sent back from the server to the terminal. The terminal displays the results visually, including data visualization and graphing. This process allows the user to quickly access the necessary information and receive the results in a visually easy-to-understand format.

[0623] (Application Example 2)

[0624] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0625] When users search for products on e-commerce sites, there is a need to solve the problem of not being able to provide them with optimal product information while taking their emotional state into consideration. This invention aims to improve the user's shopping experience by providing a system that analyzes the user's emotional state and prioritizes the display of product information based on the results.

[0626] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0627] In this invention, the server includes means for analyzing data extraction conditions entered in natural language, means for automatically generating database queries based on the analyzed data extraction conditions and emotional state, and emotion analysis means for analyzing the user's emotional state and prioritizing the results. This makes it possible to provide optimal product information according to the user's emotions.

[0628] "Data extraction criteria entered in natural language" refers to the conditions that users use when searching for data in a free-form language.

[0629] An "analytical processing device" is a device that analyzes data extraction conditions input in natural language in order to understand the linguistic structure and meaning.

[0630] A "database query generator" is a device that creates database query statements in a format that a computer can understand, based on analysis results.

[0631] "Emotional state" refers to the user's current psychological state and emotions, which are inferred from their voice, facial expressions, and behavior.

[0632] An "emotion analysis device" is a device that identifies the type of emotion a user is feeling based on their voice tone, facial expressions, etc., and provides that information to the system.

[0633] An "execution device" is a device that actually executes automatically generated database queries on the database and retrieves the results.

[0634] A "display device" is a device that allows the user to visually confirm the search results obtained by the execution device.

[0635] This invention is a system designed to enhance the user's shopping experience on e-commerce websites. The user uses a smartphone to input data extraction criteria related to products in natural language. The terminal first sends this input data, provided via voice or text, to a server. The server uses natural language processing technology to analyze the user input. This analysis utilizes representative natural language processing libraries such as spaCy and BERT. Based on the analyzed data extraction criteria, a generative AI model generates appropriate database queries.

[0636] Furthermore, the device also performs emotion analysis. This part estimates the user's emotional state by combining a speech emotion recognition library (e.g., Google Cloud Speech-to-Text) and facial expression analysis software (e.g., Microsoft Azure Face API). Based on the information obtained from the emotion analysis, the server prioritizes the results of the generated queries and displays the most appropriate product information preferentially.

[0637] For example, suppose a user excitedly requests to "find out about the latest gadgets that have just come out." In this case, the emotion analysis system detects this excitement, and the generating AI adjusts the query to prioritize displaying the latest gadgets and deals. An example of a prompt in this scenario might be: "A user is excited about finding recently released gadgets. Considering this emotion, how can we prioritize displaying information about new product sales?"

[0638] In this way, the present invention provides a richer and more intuitive user experience and a flexible system that responds immediately to user needs.

[0639] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0640] Step 1:

[0641] The device receives data extraction criteria entered by the user in natural language, either as voice or text. It receives a user request as input: "I want to research recently released new gadgets." It then prepares to send this data to the server.

[0642] Step 2:

[0643] The device acquires the necessary audio data for voice input and extracts emotions from the audio data using a speech emotion recognition library. As output, it creates emotional state data based on the user's voice tone and prepares to send it to the server.

[0644] Step 3:

[0645] The server analyzes natural language data received from the terminal using natural language processing libraries (such as spaCy or BERT). It takes natural language sentences as input, analyzes them, and outputs the query structure necessary to generate database queries.

[0646] Step 4:

[0647] The server automatically generates database queries using a generative AI model, taking into account the sentiment analysis results. The input is the analyzed data extraction conditions and sentiment state, and the output is an optimized database query.

[0648] Step 5:

[0649] The server executes an automatically generated query and retrieves results from the database. The input is the generated query, and the output is the retrieved product data.

[0650] Step 6:

[0651] The server sorts the database results obtained according to a priority order that matches the user's sentiment and selects appropriate product information. The input is raw data from the database, and the output is prioritized product information.

[0652] Step 7:

[0653] The server sends sorted product information to the terminal, which then visually displays it to the user, providing a shopping experience. The input is the prioritized product information, and the output is the information displayed on the user's screen.

[0654] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0655] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0656] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0657] [Fourth Embodiment]

[0658] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0659] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0660] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0661] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0662] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0663] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0664] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0665] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0666] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0667] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0668] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0669] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0670] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0671] This invention is a system that automatically extracts necessary information from a database simply by the user inputting data extraction conditions in natural language. One possible embodiment involves a configuration utilizing an internet-connected terminal and a server.

[0672] The user uses a terminal to input the conditions for extracting specific information in natural language. In this invention, the user does not need technical knowledge such as SQL and can easily specify data extraction.

[0673] The data extraction conditions entered in natural language are sent from the terminal to the server. The server uses natural language processing technology to analyze the data extraction conditions received from the user. During the analysis process, the server parses the conditional statements and identifies the key elements (elements to be extracted, filter conditions, etc.) necessary for the database query.

[0674] Next, the server uses a generation AI to automatically generate appropriate database queries based on the identified information. This process creates queries that match the user's intent.

[0675] The generated query is sent back from the server to the terminal, making it available for user review. Here, the user can review the query and add or modify detailed conditions as needed. This allows the user to optimize the extraction results to suit their specific needs.

[0676] After user verification, the terminal requests the server to execute a query. The server executes the query against the database and extracts data that matches the specified criteria.

[0677] The extracted data is organized by the server and sent to the user's terminal. The terminal displays this data visually, allowing the user to easily review the results.

[0678] For example, if a user enters a request to "display customers who achieved sales of 10 million yen or more in fiscal year 2023," this invention allows the server to analyze the conditions and automatically generate a query to extract appropriate information from the database based on key elements such as "2023," "10 million yen or more," "sales," and "customers."

[0679] This embodiment allows users to intuitively access the data they need without having to go through the complex steps of building a database or creating queries.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The user uses their device to input their desired data extraction criteria in natural language. For example, they might enter a condition such as "Show customers who generated sales of 10 million yen or more in 2023."

[0683] Step 2:

[0684] The terminal converts the input natural language information into digital data and sends it to the server.

[0685] Step 3:

[0686] The server passes the received natural language data to the natural language processing engine and begins analysis. The analysis identifies key elements for data extraction, such as "2023," "over 10 million yen," "sales," and "customers."

[0687] Step 4:

[0688] Based on the analysis results, the server uses a generative AI to generate the optimal database query. This query is constructed to satisfy the analyzed conditions.

[0689] Step 5:

[0690] The server sends the generated SQL query back to the terminal. On the terminal, the user can review and customize the query's contents. Conditions can be added or modified as needed.

[0691] Step 6:

[0692] After the user reviews the query and confirms that the conditions to be applied are correct, they send a command to execute the query to the server from their terminal.

[0693] Step 7:

[0694] The server receives instructions, executes queries against the database, and extracts the corresponding data.

[0695] Step 8:

[0696] The server organizes the extracted data and sends it to the terminal.

[0697] Step 9:

[0698] The device displays received data in a user-friendly format. This allows the user to intuitively check the necessary information.

[0699] (Example 1)

[0700] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0701] Traditional database query generation systems require users to possess technical knowledge, and a major challenge is the difficulty in directly setting data extraction conditions from natural language. This makes it difficult for non-technical users to effectively utilize the database, highlighting the need to improve the intuitiveness and usability of the interface.

[0702] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0703] In this invention, the server includes means for acquiring data extraction conditions entered by the user in natural language, a processing unit for analyzing the natural language data extraction conditions and extracting key elements, and a generation unit that utilizes generative artificial intelligence to automatically generate database queries based on the analyzed data extraction conditions. This makes it possible for users to generate and execute database queries in natural language and intuitively acquire and display the necessary information, even without technical knowledge.

[0704] A "user" refers to an individual or organization that uses the system to input data extraction criteria in natural language and attempts to obtain information.

[0705] "Natural language" refers to language that humans use on a daily basis, a form of language that can be easily understood and used even without technical knowledge.

[0706] "Data extraction conditions" refer to the search criteria and filter conditions necessary to retrieve specific information from a database.

[0707] A "processing device" refers to a hardware or software component that analyzes input data and information and performs the necessary operations.

[0708] A "generation device" is a device that has the function of generating output in a different format based on input data, and in this case, it refers to a device that automatically generates database queries.

[0709] "Generative artificial intelligence" refers to artificial intelligence technology that can understand natural language and provide responses and generate data according to the task.

[0710] "Automatic generation" refers to the process by which a system autonomously generates data or results without human intervention.

[0711] An "execution device" refers to hardware or software that executes a generated query and completes a specified operation.

[0712] "Key elements" refer to the main elements or components that constitute the data extraction criteria, and are the elements necessary for efficient searching of the database.

[0713] A "display device" refers to hardware or equipment used to visually present digital data and information to a user.

[0714] This invention is an automated database query generation system that enables data extraction using natural language. The system consists of a user terminal with an internet connection and a server that performs data processing and query generation.

[0715] The user uses a terminal to input conditions in natural language to extract specific information from the database. For example, when prompting with the message "Show customers who achieved sales of 10 million yen or more in fiscal year 2023," the user can set data extraction conditions using natural language without requiring advanced technical knowledge.

[0716] The terminal sends the input natural language conditions to the server. The server uses natural language processing technology and generative artificial intelligence models to analyze the input conditions and extract the necessary key elements. Based on the analysis, the server automatically generates an efficient database query. The generated query is sent to the terminal for the user to review and customize. The server organizes the query execution results and presents the data visually to the terminal.

[0717] The server can use generative AI models such as BERT or GPT for natural language processing, enabling accurate analysis of user input conditions. This allows the system to efficiently extract the data desired by the user and provide an intuitive and user-friendly interface.

[0718] This embodiment allows users to easily interact with the database and extract and utilize meaningful data, even without technical knowledge.

[0719] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0720] Step 1:

[0721] The user uses a terminal to input the information they want to retrieve from the database in natural language. The input is in text format through the terminal's interface. This prompt is a way for users to specify requests without specific technical skills. An example of input is, "Show customers who achieved sales of 10 million yen or more in fiscal year 2023."

[0722] Step 2:

[0723] The terminal sends data extraction criteria, received from the user in natural language, to the server. This prompt is sent as text data via an API designed for analysis by the server. The server places the received data in a waiting state for processing.

[0724] Step 3:

[0725] The server analyzes the prompt text using natural language processing techniques and generative AI models. The server first tokenizes the input natural language text and performs context-based semantic analysis. For example, it extracts specific key elements such as a particular year or amount, which are then used to generate the next query. This analysis produces a list of key elements as an intermediate output.

[0726] Step 4:

[0727] The server automatically constructs database queries based on key elements extracted through analysis using generation AI. The server creates query syntax from the key elements and converts it into a query language such as SQL. The output is a query in a format compatible with the database.

[0728] Step 5:

[0729] The generated query is sent from the server to the terminal. On the terminal, the user can review this query and customize or modify it as needed. At this stage, the user visually verifies whether the extraction criteria are appropriate by receiving the output query.

[0730] Step 6:

[0731] The user requests the server to execute a query via their terminal. The terminal sends the user's execution request to the server, asking the server to apply the query. Based on the received request, the server attempts to access the database.

[0732] Step 7:

[0733] The server executes the specified query against the database and extracts matching data records. The server executes the query through the database engine and processes the retrieved output data.

[0734] Step 8:

[0735] The acquired data is organized by the server and sent to the user's terminal. The terminal displays this data in a visually easy-to-understand format, such as graphs or tables, allowing the user to easily check the results.

[0736] (Application Example 1)

[0737] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0738] In conventional information retrieval systems, it was difficult for users to quickly and appropriately obtain the information they needed without requiring specific technical knowledge. Furthermore, there was a lack of means to instantly retrieve and visually confirm relevant sales trends and inventory information when users made inquiries using natural language. This resulted in reduced information retrieval efficiency and hindered the rapid processing of customer service.

[0739] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0740] In this invention, the server includes an information processing means for analyzing information retrieval conditions input in natural language, a generation means for automatically generating information queries based on the analyzed information retrieval conditions, and a processing means for executing the automatically generated information queries and transmitting the results to an output device. As a result, users can intuitively perform information retrieval using natural language without any specific technical knowledge, quickly obtain appropriate sales trends and inventory information, and visually confirm it.

[0741] "Natural language" refers to the ordinary words and forms of expression used in communication between humans.

[0742] An "information processing device" refers to a machine that analyzes input information and outputs it in an appropriate format.

[0743] "Information retrieval criteria" refer to the conditions or requirements set out to identify the information you want to obtain.

[0744] "Generating means" refers to a mechanism or device for producing a desired output from a specific input.

[0745] An "information inquiry" refers to a request or instruction to a source of information to obtain specific data or knowledge.

[0746] "Processing means" refers to processes and devices used to manipulate and transform input information to obtain the desired result.

[0747] An "output device" refers to a device that displays processed information in a format that is easily recognizable to humans.

[0748] "Sales trends" refer to information that shows changes and trends in sales and demand for a product or service over a specific period.

[0749] "Inventory information" refers to data that shows how much of a product or item is left and how ready it is for sale.

[0750] "Visual confirmation" means displaying and providing information in a way that allows humans to directly see and judge it.

[0751] This invention provides a system that enables information retrieval using natural language. The server uses a natural language processing engine to analyze information retrieval conditions entered in natural language. This engine utilizes technologies such as the Google Natural Language API. Furthermore, it leverages GPT-4 as a generative AI model to automatically generate appropriate information queries based on the analyzed conditions.

[0752] In this system, a smartphone is used as the primary user interface. When a user enters information search criteria in natural language into their smartphone, the input is sent to the server. The server uses a database management system (e.g., MySQL) to execute the information query and obtain search results such as sales trends and inventory information. The obtained results are displayed visually on the smartphone screen. This display allows the user to quickly review the information and make necessary decisions.

[0753] For example, if a store employee types "What was the best-selling item this month?" into their smartphone, the server analyzes this natural language and issues an appropriate query to the database. It then identifies popular items from the monthly sales data and displays that information on the smartphone. This allows employees to quickly obtain the necessary information and adjust their sales strategies accordingly.

[0754] Examples of prompts for the generating AI model include "Tell me the best-selling product over the weekend" and "Tell me the product that experienced the most stock shortages in the first half of 2023." By using these prompts, users can input information in a natural way and obtain specific results.

[0755] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0756] Step 1:

[0757] The user uses their smartphone to enter information search criteria in natural language. The entered text is sent directly from the device to the server as a string.

[0758] Step 2:

[0759] The server receives the natural language string and performs analysis using a natural language processing engine. This analysis uses the Google Natural Language API to extract keywords and query intent from the input text. The output of the analysis is a structured information retrieval query.

[0760] Step 3:

[0761] The server uses a generative AI model (e.g., GPT-4) to generate appropriate information queries based on structured information retrieval criteria. These generated queries are then converted into database query format, making them executable against the database.

[0762] Step 4:

[0763] The server executes the generated information query and accesses the database via a database management system (e.g., MySQL). As a result of executing this query, data matching the search criteria is retrieved.

[0764] Step 5:

[0765] The acquired data is organized on the server and converted into an output format. This result is then packaged into a visually easy-to-understand format.

[0766] Step 6:

[0767] The server sends the organized results to the terminal. The terminal has the ability to visually display the received information on its screen, allowing the user to immediately check the results. This enables the user to visually confirm the information they need and use it to guide their future actions.

[0768] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0769] This invention relates to a system that generates and executes database queries that take into account the user's emotional state by combining data extraction conditions entered by the user in natural language with an emotion engine. This system is implemented with a configuration including a terminal, a server, and an emotion engine.

[0770] First, the user enters data extraction criteria in natural language using their device. For example, the user might enter a request such as, "I want to know which product has generated the most profit over the past year."

[0771] The terminal sends user input to the server and simultaneously acquires information necessary for the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's tone of voice, facial expressions, and behavioral patterns during input to recognize the current emotional state (e.g., excitement, calmness, dissatisfaction, etc.).

[0772] The server analyzes the received natural language data using natural language processing technology. It extracts the elements necessary for generating database queries from the analysis results and automatically generates queries using a generation AI. At this time, the query priority and filter conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, the system might prioritize concise results to ensure a quick response.

[0773] The generated query is sent back from the server to the terminal for the user to review. The user can check the query content and adjust the conditions or configure detailed settings as needed.

[0774] Once the user confirms the query and commands it to run, the terminal sends an instruction to the server, which then executes the query against the database. The results are then sent back from the server to the terminal and displayed visually on the user's terminal.

[0775] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, they may be presented with additional information or analytical options regarding the results.

[0776] This embodiment enables flexible and interactive data extraction that takes user emotions into consideration. This improves the user experience and enables efficient data utilization.

[0777] The following describes the processing flow.

[0778] Step 1:

[0779] The user uses their device to input their desired data extraction criteria in natural language. For example, they might input a condition such as, "Tell me which product has generated the most profit in the past year."

[0780] Step 2:

[0781] The terminal transmits the natural language information entered by the user to the emotion engine, and simultaneously sends the input content to the server as digital data.

[0782] Step 3:

[0783] The emotion engine analyzes the user's emotions based on the input information. For example, it analyzes voice tone, changes in input time, and operation patterns to determine whether the user is currently excited or calm.

[0784] Step 4:

[0785] The server uses a natural language processing engine to analyze user input. This analysis identifies the elements necessary for database queries (e.g., time period, profit, product name).

[0786] Step 5:

[0787] The server considers the emotion data identified in step 3 and uses generative AI to generate optimal database queries. For example, if user excitement is detected, the number of results may be limited to return query results quickly.

[0788] Step 6:

[0789] The server sends the generated SQL query back to the terminal. On the terminal, the user can review the query content and customize it as needed.

[0790] Step 7:

[0791] Once the user reviews the query and is satisfied with it, they send an execution command to the server via their terminal.

[0792] Step 8:

[0793] The server receives instructions and executes the generated query against the database to extract data that matches the conditions.

[0794] Step 9:

[0795] The server organizes the extracted data and sends it to the user's device, along with feedback. The device then displays the results visually, making it easy for the user to review.

[0796] Step 10:

[0797] Based on emotional data analyzed using an emotion engine, additional feedback and options are presented to the user. For example, if the user expresses dissatisfaction, additional details or support options may be displayed.

[0798] (Example 2)

[0799] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0800] Traditional systems failed to consider user emotions during data extraction, limiting user experience and interactivity. As a result, the usefulness and relevance of extracted information decreased, and users were unable to quickly access the information they needed.

[0801] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0802] In this invention, the server includes an information processing device means for analyzing request conditions input in natural language, a generation device means for automatically generating information queries based on the analyzed request conditions and sentiment analysis information, and an execution device means for executing the automatically generated information queries and transmitting the results to a display unit. This enables flexible and efficient information extraction according to the user's emotional state.

[0803] "Natural language" refers to the language that humans use on a daily basis, and it is a language that needs to be analyzed in order for a computer to understand and process it.

[0804] "Requirements" refer to the conditions or requests that a user submits to the system for obtaining specific information.

[0805] An "information processing device" is a device that has the function of analyzing input data and extracting, converting, or processing the necessary information.

[0806] "Emotional analysis information" refers to data analyzed by the system that indicates the user's emotional state.

[0807] A "generation device" is a device that automatically generates database queries and information inquiries based on analyzed requirements and sentiment analysis information.

[0808] An "information query" refers to a question or query that is automatically generated to retrieve information from a specific database or information source.

[0809] An "execution device" is a device that executes generated information queries and presents the results to the user.

[0810] The term "display unit" refers to an interface that allows users to visually confirm information results.

[0811] An "emotion engine" is a system with analytical capabilities that utilizes human interface materials to analyze the user's emotional state.

[0812] "Feedback" refers to the responses and additional information that a system provides in response to user actions or requests.

[0813] This invention is a system that generates and executes information queries that take into account the user's emotional state by combining a sentiment engine with the user's request conditions entered in natural language. This system is implemented with a configuration including a terminal, a server, and a sentiment engine.

[0814] The user enters their requirements in natural language using a terminal. For example, the user might enter a prompt such as, "I want to know which product has generated the most profit in the past year."

[0815] The device sends user input to the server. Simultaneously, the device retrieves data from the emotion engine and analyzes the user's tone of voice, facial expressions, and behavioral information during input. This analysis allows the device to recognize the user's current emotional state.

[0816] The server uses natural language processing technology and generative AI models to analyze incoming data and automatically generate information queries. During generation, the query priority and filtering conditions are adjusted based on the analysis results of the emotion engine. For example, if the user is in an excited state, concise results are prioritized to allow for quick information retrieval.

[0817] The generated information query is sent back from the server to the terminal for confirmation by the user. If necessary, the user can fine-tune the request conditions and configure detailed settings. After confirmation, the user can instruct the terminal to execute, which then sends an instruction to the server, where the server executes the query. The results are then sent back from the server to the terminal and displayed visually.

[0818] Furthermore, the user receives feedback tailored to the emotions recognized by the emotion engine. For example, if the user expresses dissatisfaction, additional information or further analysis options may be displayed.

[0819] Examples of prompts include, "Please tell me the top 5 best-selling products of 2023," or "I'd like to know the customer satisfaction trends for the past three months." By responding to such prompts, the system can extract information that reflects the user's emotions, enabling it to provide an efficient and satisfying user experience.

[0820] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0821] Step 1:

[0822] The user uses a terminal to input their request in natural language. For example, they might input "I want to know which product has generated the most profit in the past year" as a prompt. The terminal receives the entered prompt as input data to send to the server.

[0823] Step 2:

[0824] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and actions during input. This analysis outputs the user's current emotional state (e.g., excitement, calmness, dissatisfaction). The emotion engine processes data acquired from the camera and microphone in real time.

[0825] Step 3:

[0826] The server uses natural language processing techniques and generative AI models to analyze the received request conditions. The input data is a prompt sentence from the user. This process extracts the elements necessary to generate the information query, resulting in structured information as output data that leads to automatic generation.

[0827] Step 4:

[0828] The server automatically generates information queries using a generative AI model, taking into account the analysis results of the emotion engine. In this step, priorities and filter conditions are adjusted based on the user's emotional state, and queries that enable quick and appropriate information provision are output.

[0829] Step 5:

[0830] The generated information query is sent back from the server to the terminal. On the terminal, the user can review the query content and adjust the request conditions or make detailed settings if necessary. Here, the user visually checks the displayed query prompts and optimizes them through the interface.

[0831] Step 6:

[0832] After the user confirms the inquiry details and issues an order to execute, the terminal sends that order to the server. The server receives this order and executes the generated query against the database. The output is a result set from the database based on the information retrieval query.

[0833] Step 7:

[0834] The obtained results are then sent back from the server to the terminal. The terminal displays the results visually, including data visualization and graphing. This process allows the user to quickly access the necessary information and receive the results in a visually easy-to-understand format.

[0835] (Application Example 2)

[0836] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0837] When users search for products on e-commerce sites, there is a need to solve the problem of not being able to provide them with optimal product information while taking their emotional state into consideration. This invention aims to improve the user's shopping experience by providing a system that analyzes the user's emotional state and prioritizes the display of product information based on the results.

[0838] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0839] In this invention, the server includes means for analyzing data extraction conditions entered in natural language, means for automatically generating database queries based on the analyzed data extraction conditions and emotional state, and emotion analysis means for analyzing the user's emotional state and prioritizing the results. This makes it possible to provide optimal product information according to the user's emotions.

[0840] "Data extraction criteria entered in natural language" refers to the conditions that users use when searching for data in a free-form language.

[0841] An "analytical processing device" is a device that analyzes data extraction conditions input in natural language in order to understand the linguistic structure and meaning.

[0842] A "database query generator" is a device that creates database query statements in a format that a computer can understand, based on analysis results.

[0843] "Emotional state" refers to the user's current psychological state and emotions, which are inferred from their voice, facial expressions, and behavior.

[0844] An "emotion analysis device" is a device that identifies the type of emotion a user is feeling based on their voice tone, facial expressions, etc., and provides that information to the system.

[0845] An "execution device" is a device that actually executes automatically generated database queries on the database and retrieves the results.

[0846] A "display device" is a device that allows the user to visually confirm the search results obtained by the execution device.

[0847] This invention is a system designed to enhance the user's shopping experience on e-commerce websites. The user uses a smartphone to input data extraction criteria related to products in natural language. The terminal first sends this input data, provided via voice or text, to a server. The server uses natural language processing technology to analyze the user input. This analysis utilizes representative natural language processing libraries such as spaCy and BERT. Based on the analyzed data extraction criteria, a generative AI model generates appropriate database queries.

[0848] Furthermore, the device also performs emotion analysis. This part estimates the user's emotional state by combining a speech emotion recognition library (e.g., Google Cloud Speech-to-Text) and facial expression analysis software (e.g., Microsoft Azure Face API). Based on the information obtained from the emotion analysis, the server prioritizes the results of the generated queries and displays the most appropriate product information preferentially.

[0849] For example, suppose a user excitedly requests to "find out about the latest gadgets that have just come out." In this case, the emotion analysis system detects this excitement, and the generating AI adjusts the query to prioritize displaying the latest gadgets and deals. An example of a prompt in this scenario might be: "A user is excited about finding recently released gadgets. Considering this emotion, how can we prioritize displaying information about new product sales?"

[0850] In this way, the present invention provides a richer and more intuitive user experience and a flexible system that responds immediately to user needs.

[0851] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0852] Step 1:

[0853] The device receives data extraction criteria entered by the user in natural language, either as voice or text. It receives a user request as input: "I want to research recently released new gadgets." It then prepares to send this data to the server.

[0854] Step 2:

[0855] The device acquires the necessary audio data for voice input and extracts emotions from the audio data using a speech emotion recognition library. As output, it creates emotional state data based on the user's voice tone and prepares to send it to the server.

[0856] Step 3:

[0857] The server analyzes natural language data received from the terminal using natural language processing libraries (such as spaCy or BERT). It takes natural language sentences as input, analyzes them, and outputs the query structure necessary to generate database queries.

[0858] Step 4:

[0859] The server automatically generates database queries using a generative AI model, taking into account the sentiment analysis results. The input is the analyzed data extraction conditions and sentiment state, and the output is an optimized database query.

[0860] Step 5:

[0861] The server executes an automatically generated query and retrieves results from the database. The input is the generated query, and the output is the retrieved product data.

[0862] Step 6:

[0863] The server sorts the database results obtained according to a priority order that matches the user's sentiment and selects appropriate product information. The input is raw data from the database, and the output is prioritized product information.

[0864] Step 7:

[0865] The server sends sorted product information to the terminal, which then visually displays it to the user, providing a shopping experience. The input is the prioritized product information, and the output is the information displayed on the user's screen.

[0866] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0867] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0868] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0869] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0870] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0871] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0872] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0873] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0874] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0875] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0876] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0877] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0878] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0879] 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.

[0880] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0881] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0882] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0883] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0884] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0885] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0886] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0887] The following is further disclosed regarding the embodiments described above.

[0888] (Claim 1)

[0889] A processing unit that analyzes data extraction conditions entered in natural language,

[0890] A generation device that automatically generates database queries based on the analyzed data extraction conditions,

[0891] An execution device that executes the automatically generated database query and sends the results to a display device,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, which analyzes the data extraction conditions using natural language processing technology.

[0895] (Claim 3)

[0896] The system according to claim 1, which provides the display device with means for a user to check and customize a database query generated by the user.

[0897] "Example 1"

[0898] (Claim 1)

[0899] A means of obtaining data extraction conditions entered by the user in natural language,

[0900] A processing device that analyzes the data extraction conditions for the aforementioned natural language and extracts key elements,

[0901] A generation device that uses artificial intelligence to automatically generate database queries based on the analyzed data extraction conditions,

[0902] A means of providing the generated database queries in a state that users can review and customize,

[0903] An execution device that executes the automatically generated database query and sends the processing results to a display device,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, which uses natural language processing technology to analyze the data extraction conditions and identify key elements.

[0907] (Claim 3)

[0908] The system according to claim 1, wherein a user can request the execution of the query, and the system provides means for visualizing and displaying data based on the query.

[0909] "Application Example 1"

[0910] (Claim 1)

[0911] An information processing device that analyzes information retrieval conditions entered in natural language,

[0912] A generation means for automatically generating information queries based on the analyzed information retrieval conditions,

[0913] Processing means for executing the automatically generated information query and transmitting the result to an output device,

[0914] Output means for visually displaying the responded information,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, which uses natural language processing technology to analyze the information retrieval conditions and extract sales trends and inventory information.

[0918] (Claim 3)

[0919] The system according to claim 1, which provides the output device with means for confirming and adjusting information queries generated by the user, and generates a response immediately based on the user's input.

[0920] "Example 2 of combining an emotion engine"

[0921] (Claim 1)

[0922] An information processing device that analyzes requirements input in natural language,

[0923] A generator that automatically generates information queries based on the analyzed requirements and sentiment analysis information,

[0924] An execution device that executes the automatically generated information query and transmits the results to the display unit,

[0925] An emotion engine that analyzes the user's emotional state,

[0926] A means for providing feedback according to the analysis results of the emotion engine,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, which analyzes the requirements using natural language processing technology and a generative AI model.

[0930] (Claim 3)

[0931] The system according to claim 1, which provides the display unit with means for confirming and customizing information queries generated by the user.

[0932] "Application example 2 of combining emotional engines"

[0933] (Claim 1)

[0934] A processing unit that analyzes data extraction conditions entered in natural language,

[0935] A generator that automatically generates database queries based on the analyzed data extraction conditions and emotional states,

[0936] An emotion analysis device for analyzing the emotional state of the user and prioritizing the results,

[0937] An execution device that executes the automatically generated database query and sends the results to a display device,

[0938] A system that includes this.

[0939] (Claim 2)

[0940] The system according to claim 1, which uses natural language processing technology to analyze the data extraction conditions and generates queries using a generative AI model.

[0941] (Claim 3)

[0942] The system according to claim 1, which provides the display device with means for the user to review and customize database queries generated by the user and to provide emotion-responsive feedback. [Explanation of Symbols]

[0943] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A processing unit that analyzes data extraction conditions entered in natural language, A generation device that automatically generates database queries based on the analyzed data extraction conditions, An execution device that executes the automatically generated database query and sends the results to a display device, A system that includes this.

2. The system according to claim 1, which analyzes the data extraction conditions using natural language processing technology.

3. The system according to claim 1, which provides the display device with means for a user to check and customize a database query generated by the user.

Images