system

Abstract

We provide the system. [Solution] A means of receiving data input in natural language, A natural language processing means that analyzes the received natural language data and identifies its intent, A means for automatically generating queries to the relevant database based on the identified intent, A means for extracting data from the relational database based on the generated query, A means for analyzing the extracted data using a generative model and generating results, A means for outputting the generated analysis results in a format that is easy for the user to understand, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern business environment, data analysis plays an important role, but specialized knowledge such as SQL is required to achieve this. Therefore, in occupations without specialized knowledge, the data analysis process is restricted, and it is difficult to solve problems quickly. Also, even when having specialized knowledge, there are problems such as it taking a lot of time and effort to create complex queries and handle data. This invention aims to solve these problems by providing a system that can intuitively perform data analysis using natural language.

Means for Solving the Problems

[0005] This invention provides a system that includes a natural language processing means for receiving and analyzing data input in natural language, and a means for automatically generating queries based on the analysis results. Furthermore, it includes means for extracting necessary data from a database using these queries and analyzing the data using a generative model. Ultimately, the aim is to provide an environment in which even users without specialized knowledge can easily perform data analysis and quickly solve problems by outputting the analysis results in a format that is easy for users to understand.

[0006] "Data entered in natural language" refers to data entered by users using natural language to provide instructions or questions to the system.

[0007] "Natural language processing means" refers to a system function that analyzes received natural language data and performs processing to identify the user's intent.

[0008] A "query against a relational database" is a structured question or command used to extract necessary information from a relational database based on specified conditions.

[0009] A "generative model" is a model that uses machine learning or AI algorithms to analyze patterns and characteristics in input data and generate results.

[0010] A "user-friendly format" refers to an output format that presents analysis results in a visual or textual format, making it easy for users to grasp the information. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention provides a data analysis system using natural language, and consists of three main components: a user, a terminal, and a server.

[0033] Users input the necessary instructions for data analysis in natural language through the terminal's interface. For example, a user might input, "I want to know the latest customer satisfaction trends." This input is immediately received by the terminal.

[0034] The terminal sends this natural language data to the server and also functions as an interface to provide input confirmation and feedback to the user.

[0035] The server analyzes the received natural language data using natural language processing tools to identify the user's intent. For example, it extracts keywords such as "customer satisfaction" or "trends" and generates database queries based on that intent.

[0036] Next, the server uses the generated query to access the database and extract the necessary data. The extracted data is analyzed by a generative model to identify data patterns and trends.

[0037] Finally, the server formats the analysis results into a user-friendly format, such as graphs or reports, and sends them to the terminal. The terminal then displays these results to the user, providing intuitive data insights. This entire process allows users to efficiently perform data analysis using natural language.

[0038] As a concrete example, when a user in the sales department enters the instruction "Analyze the sales data trends for the past three months" into their terminal, the server analyzes the intent and extracts and analyzes the relevant sales data. As a result, the analyzed sales trends are presented to the user in graph format, which helps in the early detection of performance issues and problems. This enables quick and efficient data analysis without requiring specialized knowledge.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user inputs the information they want to analyze into the device using natural language. For example, they might enter instructions such as, "Analyze last month's sales trends."

[0042] Step 2:

[0043] The terminal receives natural language input from the user and prepares to send that data to the server. It verifies the input and performs error checks to ensure the accuracy of the information.

[0044] Step 3:

[0045] The server receives natural language data sent from the terminal. The natural language processing engine installed on the server analyzes the received data to identify the intent and purpose of the instructions.

[0046] Step 4:

[0047] The server automatically generates SQL queries to access the database based on the analyzed intent. The generated queries are structured to extract data for a specific period or item.

[0048] Step 5:

[0049] The server uses the generated SQL query to extract the necessary data from the database. The extracted data is temporarily stored on the server in preparation for further processing.

[0050] Step 6:

[0051] The server analyzes the extracted data using a generative model. The model employs machine learning algorithms to identify patterns and trends within the data. This analysis leads to new insights and areas for improvement.

[0052] Step 7:

[0053] The server formats the obtained analysis results into a user-friendly format, such as visualized graphs or tables. During this process, processing is performed to improve the visibility and comprehensibility of the information.

[0054] Step 8:

[0055] The terminal receives analysis results sent from the server and displays them to the user. The user can then use the presented information to make decisions and improve their work or solve problems.

[0056] (Example 1)

[0057] 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."

[0058] In data analysis, it is difficult for users without specialized knowledge to obtain useful information without complex procedures. Furthermore, traditional systems often make it difficult for users to appropriately specify the intent behind the data, resulting in inaccurate data analysis. Therefore, there is a need for a system that allows users to easily provide analysis instructions in natural language and obtain results in an intuitively understandable format.

[0059] 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.

[0060] In this invention, the server includes a device for receiving instructions input in natural language, a natural language processing device for analyzing the received natural language instructions and extracting their intent, and a device for automatically generating query statements for an information storage structure based on the extracted intent. This makes it possible for users to quickly and accurately obtain information without specialized knowledge simply by giving instructions in natural language, and to intuitively understand the results.

[0061] A "device that receives instructions entered in natural language" is a device that directly receives commands entered by the user in natural language.

[0062] A "natural language processing device" is a device that analyzes received natural language instructions and extracts their intent.

[0063] A "device for automatically generating query statements for information storage structures" is a device that automatically generates query statements to access an information storage system based on the extracted intent.

[0064] An "information storage structure" refers to a system or method in which data is organized and stored, and typically includes relational databases, etc.

[0065] A "generative AI model" is a model that uses machine learning and artificial intelligence technologies to analyze data and derive evaluation results.

[0066] A "device that provides evaluation results in a format easily understandable to users" is a device that presents the generated evaluation results in a format that is intuitively easy for users to understand, such as graphs or reports.

[0067] A "feedback device" is a device that provides confirmation or a response to user input or commands.

[0068] This invention is a system for users to acquire information via natural language and perform data analysis. The system consists of a user, a terminal, and a server. The server is primarily responsible for natural language processing and data analysis, while the terminal functions as an interface with the user.

[0069] Users can use their terminal to input prompts in natural language. For example, they might input a command such as, "Tell me the sales data trends for last month." The terminal receives this natural language command and sends the data to the server.

[0070] The server uses a natural language processing unit (such as spaCy or NLTK software libraries) to analyze the received instructions. During this process, it extracts specific words and keywords to identify the data request intended by the user. Then, to efficiently extract the relevant data, it automatically generates query statements to access the information storage structure (usually a relational database).

[0071] The generated query prompts the server to access the database and extract the necessary data. The extracted data is then evaluated by a generating AI model (for example, a machine learning model using TENSORFLOW® or PyTorch) to analyze data patterns and trends.

[0072] The analysis results are formatted on the server into a user-friendly format (e.g., graphs or tables) and sent to the terminal. The terminal then presents this information to the user. This allows users to easily gain data insights using natural language, even without specialized knowledge.

[0073] For example, if a user enters the prompt "What is the average customer satisfaction rating for this week?", the server extracts relevant data and analyzes it using an AI model. The average value resulting from the analysis is then presented to the user, which can be used to aid in decision-making.

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

[0075] Step 1:

[0076] The user inputs data analysis instructions into the terminal in natural language. The input consists of prompts, such as "I want to know the latest sales trends." The terminal receives these instructions as text data based on their grammatical structure.

[0077] Step 2:

[0078] The terminal sends the received text data to the server. The input here is the user's prompt, which serves as the output data to the server. The terminal also checks for input errors and displays a warning to the user if there are any problems.

[0079] Step 3:

[0080] The server analyzes the received prompt text using a natural language processing unit (NLTK). For example, it uses spaCy or NLTK to extract keywords and intent from the text. The input is the user's prompt text, and the output is the extracted keywords and their intent.

[0081] Step 4:

[0082] The server automatically generates query statements to access the information storage structure based on the analyzed intent. The input here is the intent and keywords obtained through analysis, and the output is the generated query statement, such as an SQL query. In this process, the server generates queries according to the schema of the relevant database.

[0083] Step 5:

[0084] The server uses the generated query statement to extract data from the information storage structure. The SQL query is executed, and the necessary data is retrieved from the database. The input is the generated query, and the output is the raw data retrieved by the query.

[0085] Step 6:

[0086] The server analyzes the extracted data using a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze data patterns and trends. The input is raw data, and the output is the analyzed result, such as trends and insights.

[0087] Step 7:

[0088] The server formats the analysis results into a user-friendly format. The input here is the analysis results, and the output is a formatted graph or report. For example, the server generates a line graph to visualize increases and decreases in sales.

[0089] Step 8:

[0090] The terminal displays formatted analysis results to the user. Input is graphs and reports from the server, and output is data presented visually to the user. This allows the user to easily grasp data trends and patterns.

[0091] (Application Example 1)

[0092] 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."

[0093] In modern urban environments, there is a lack of means for residents to intuitively access and understand real-time urban information. This makes it difficult to efficiently grasp traffic conditions and environmental data and make appropriate decisions. In particular, there is a need for residents without specialized knowledge to easily obtain this information.

[0094] 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.

[0095] In this invention, the server includes means for receiving information input in natural language, natural language processing means for analyzing the received natural language information and identifying its intent, and means for automatically generating queries to an information storage device based on the identified intent. This makes it possible for residents to easily obtain and understand real-time information about the city in natural language.

[0096] "Natural language" refers to languages ​​that humans use on a daily basis, such as Japanese or English, which are analyzed in order to make them usable by computers.

[0097] An "information storage device" is a device or system that stores data and allows it to be retrieved as needed.

[0098] An "inquiry" is a request or question made in order to obtain information or data.

[0099] A "generative model" is a method of analyzing data, extracting patterns and features from it, and outputting results.

[0100] "Real-time information" refers to the latest information that immediately reflects the current state and situation.

[0101] "Residents" refers to people who live in a particular area or people who have an interest in that area.

[0102] "Natural language processing" refers to the technologies and methods that enable computers to understand and appropriately interpret human language.

[0103] "Information" refers to data, facts, and knowledge that are used for a specific purpose.

[0104] The system for implementing this invention mainly consists of user terminals, a server, and a central database. Users can query urban traffic conditions and environmental information in natural language via devices they use daily, such as smartphones or smart glasses.

[0105] The terminal receives natural language input from the user and then sends this information to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the user's intent and retrieves the necessary data from a central database via traffic data APIs and environmental data APIs.

[0106] The acquired data is analyzed in real time by a server, and patterns and trends are identified using a generative AI model. The analysis results are output to the user in a visually easy-to-understand format and displayed on the device screen or smart glasses display.

[0107] For example, if a user instructs their device to "check nearby traffic congestion immediately," the server will collect nearby traffic information and display the analysis results. Similarly, in response to the input "Tell me the current city temperature," the server will retrieve the latest temperature data and instantly visualize and display it. Through this process, a generative AI model is used, enabling users to efficiently obtain urban information.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The user inputs a question in natural language using a smartphone or smart glasses. For example, the input might be the phrase "Tell me the current traffic conditions," and the user's device receives this data. The input natural language data is then prepared for transmission to the server.

[0111] Step 2:

[0112] The terminal sends the received natural language input to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the input data and identify the user's intent. This analysis process identifies keywords such as "traffic conditions" and generates information retrieval requests based on them. The input is a natural language question, and the output is an internal query that reflects the intent.

[0113] Step 3:

[0114] The server constructs queries to contact traffic data APIs and environmental data APIs based on the identified intent. These queries retrieve the necessary data from global databases and sensor networks. The input is a query reflecting the user's intent, and the output is a request for the data to be retrieved.

[0115] Step 4:

[0116] The server analyzes the acquired data using a generative AI model. Data processing here includes time series analysis and trend forecasting. The generative model detects patterns related to traffic and the environment and generates predictions or summaries based on these. The input is raw data from query results, and the output is visualized information as analysis results.

[0117] Step 5:

[0118] The analysis results generated by the server are sent to the user's terminal and displayed in a format that is easy for the user to understand. Smart glasses display information in a visually easy-to-understand format, such as showing traffic congestion areas and weather conditions on a map. The input is processed analysis results, and the output is visualized information for the user to use.

[0119] 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.

[0120] This invention combines a natural language-based data analysis system with an emotion engine that recognizes user emotions. This enables more flexible and adaptive data analysis and result presentation.

[0121] The user inputs the information they want to analyze into the device using natural language. For example, they might input instructions that include emotions, such as, "I'm concerned about the recent decline in sales, so I'd like to know more details." The device receives this input and sends it to the server.

[0122] The server receives natural language input from the terminal and then analyzes it using natural language processing tools. This analysis process not only identifies keywords and intent from the user's input, but also includes a step where an emotion engine recognizes the user's emotions. For example, it can detect emotions such as "concern" or "worry."

[0123] After the server recognizes the user's emotions, it automatically generates a database query, taking into account the identified intentions and emotions. This query is used to access the database and extract data that matches the specified criteria.

[0124] The extracted data is analyzed using a generative model, and this process allows for adjustment of the analysis methods and output trends based on the user's emotional state. For example, if the user expresses an emotion such as "worry," the analysis results may be provided in a more detailed and solution-focused manner.

[0125] Finally, the analysis results are formatted in an easy-to-understand style that aligns with the user's emotions and sent to the device. The device displays these results on its user interface, allowing the user to make decisions based on the presented information. For example, if a manager inputs "I'm worried about market risks," the server prioritizes analyzing risk-related data and suggests potential countermeasures.

[0126] Thus, the present invention aims to improve the efficiency of data analysis and user satisfaction by performing analysis and presenting results that take user emotions into consideration.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] Users input information about the issues or subjects they want to analyze into their device using natural language. For example, they might input instructions such as, "I'm concerned about recent customer feedback, so I'd like you to analyze it in detail."

[0130] Step 2:

[0131] The terminal receives natural language input from the user and prepares to send that data to the server. It performs error checking and input format verification to ensure that accurate information is transferred.

[0132] Step 3:

[0133] The server receives natural language data transmitted from the terminal. The received data is analyzed using natural language processing tools to identify the user's intent and instructions.

[0134] Step 4:

[0135] The server uses an emotion engine to detect the user's emotions from the received input data. For example, it can determine the user's feelings of anxiety or concern from a word like "I'm worried."

[0136] Step 5:

[0137] The server automatically generates database queries based on identified intent and user sentiment. These queries are optimized to extract relevant data while considering the user's interests and emotions.

[0138] Step 6:

[0139] The server uses the generated query to access the database and extract the relevant data. The extracted data is checked to see if it meets the user's requirements and then passed on to the next analysis phase.

[0140] Step 7:

[0141] The server analyzes the extracted data using a generative model. During this process, the analysis focus and methods are adjusted according to the user's emotions. For example, it may highlight risk factors in the data based on emotions such as anxiety.

[0142] Step 8:

[0143] When the server formats the analysis results into a highly readable format, such as graphs or charts, it selects points to emphasize and display formats that match the user's emotions.

[0144] Step 9:

[0145] The terminal receives analysis results sent from the server and displays them in the user interface. Users can use this information to make decisions and apply the analysis to actual actions.

[0146] (Example 2)

[0147] 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".

[0148] In modern data analysis systems, analyses often disregard user emotions, making it difficult to provide the information and solutions that users truly seek. Furthermore, there is a need for flexible systems that accurately capture the emotions and intentions expressed by users and then present appropriate analytical results.

[0149] 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.

[0150] In this invention, the server includes means for analyzing data input in natural language and identifying its intent, means for using an emotion engine to recognize the user's emotions from the input data, and means for automatically generating queries to a database and extracting and analyzing data. This enables more intuitive and useful data analysis and information provision that takes user emotions into account.

[0151] "Natural language" refers to the language system that humans use in everyday life, and includes information expressed in dialogue and written form.

[0152] A "database" is a system for systematically organizing and storing data according to a specific purpose, and it is possible to search and retrieve data through queries.

[0153] An "emotion engine" is a technology that analyzes and recognizes emotions from user input, and can identify the type and intensity of emotions.

[0154] A "generating model" is a computational model used for analyzing data and recognizing patterns through machine learning, and it plays a role in making predictions and suggestions based on the data.

[0155] "Generating results" refers to the process of creating useful conclusions and suggestions for users based on information obtained through data analysis.

[0156] "A format tailored to the user's emotions" refers to a method of presenting information in the most easily understandable and appropriate format, taking into account the user's emotional state at the time of input.

[0157] A "query" is a command given to a database to search for and extract specific data, and it is written in a structured language.

[0158] This invention is embodied as a system in which a user inputs data analysis instructions into a terminal using natural language, and this information is processed on a server. The user inputs instructions in natural language, including questions and feelings about the data they are interested in. Examples of prompts could be, "I'm worried about recent sales and would like to know the reason," or "I'm concerned about market risks."

[0159] The terminal receives this input and sends it to the server. The server analyzes the received input using natural language processing. During the analysis process, it identifies the user's intent and identifies the user's emotions using an emotion engine. This system uses keyword extraction models and deep learning-based emotion recognition technology.

[0160] Based on identified intentions and emotions, the server automatically generates queries to the database and extracts the necessary data. The database often contains relational and time-series data. The extracted data is analyzed using a generative AI model. This model can identify data patterns and potential issues and generate analysis results that take into account the user's specific emotions.

[0161] Ultimately, the server formats the generated analysis results in an appropriate format that aligns with the user's emotions and sends them to the terminal. The terminal displays the results in a user interface, providing information in a way that is easy for the user to understand. This system enables advanced data analysis and effective information presentation that takes into account the user's emotions and intentions.

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

[0163] Step 1:

[0164] The user inputs the information they want analyzed into the device using natural language. This input may include the user's intentions and emotions. For example, the user might ask, "I'm worried about recent sales and want to know the reason." The device receives this input and sends it to the server.

[0165] Step 2:

[0166] The server analyzes natural language input received from the terminal. This process uses natural language processing tools to identify the user's intent and recognizes the emotions contained in the input using an emotion engine. For example, it identifies emotions such as "worry" and "concern." Based on the input data, keyword extraction and emotion analysis are performed to generate analysis results.

[0167] Step 3:

[0168] The server automatically generates queries to the database based on the analysis results. These queries are designed to retrieve appropriate data according to identified intentions and sentiments. For example, they may include conditions to search for unusual patterns in sales data. In this step, the analysis results are taken as input, and the generated queries are taken as output.

[0169] Step 4:

[0170] The server applies the generated query to the database and extracts the necessary data. The data extracted from the database is then fed into a generative AI model for analysis. The output is obtained in the form of data summaries, statistics, and so on.

[0171] Step 5:

[0172] The server analyzes the extracted data using a generating AI model. At this stage, the model identifies patterns in the data and performs analysis that takes user sentiment into account. For example, it examines in detail the causes of declining sales. This process yields analytical insights and potential issues, which are then output as analysis results.

[0173] Step 6:

[0174] The server formats the analysis results into an easy-to-understand format based on the user's emotions. This formatted information is then sent to the terminal for display on the user interface. The formatted results, including suggestions and solutions, are presented to the user.

[0175] Step 7:

[0176] The terminal receives formatted analysis results from the server and displays them in the user interface. The user then makes decisions based on this information. This display includes visually easy-to-understand elements such as graphs and charts.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] This aims to solve the problem that when users analyze data using natural language, the analysis and presentation of results do not take into account the emotions contained in the instructions, making it difficult to respond flexibly to the user's needs.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes means for receiving data and user sentiment input in natural language, natural language processing means for analyzing the received natural language data to identify the intent and sentiment, and means for automatically generating queries to a relational database based on the identified intent and sentiment. This enables flexible and adaptive data analysis and result presentation that takes user sentiment into consideration.

[0182] "Data entered in natural language" refers to data entered by a user using normal human language and processed by a computer system.

[0183] "User emotions" refers to information that indicates the emotional state or psychological tendencies expressed by the user.

[0184] "Natural language processing means" are technical means for analyzing the content of text data expressed in natural language and identifying its intent and structure.

[0185] "Methods for automatically generating queries" refer to technologies that automatically create queries to access a database based on user requests.

[0186] A "relational database" is a data management system that organizes data in a tabular format and systematically establishes relationships between different data items.

[0187] A "generative model" is a method or technique that uses machine learning or statistical models to extract patterns from data and generate analytical results.

[0188] "Means for outputting analysis results" refers to technologies that present information obtained from data analysis in a way that is easy for users to understand.

[0189] The system for realizing this invention consists of a user terminal, a server, and a database. First, the user inputs their emotions or the content they wish to analyze into the user terminal in natural language. The input data is expressed in natural language, and the user terminal receives it.

[0190] Data received from the user's terminal is sent to the server. The server has a natural language processing library (for example, Python's NLTK) installed, and uses this library to analyze the input data and identify the user's intent and emotions. In addition, sentiment analysis APIs such as Google Cloud Natural Language API are used for emotion recognition.

[0191] Subsequently, the server automatically generates queries to a relational database based on the identified intentions and emotions. These queries are used to extract relevant data from the database. The extracted data is then analyzed by a generative model (e.g., a machine learning model). Here, data analysis techniques that take user emotions into account are employed.

[0192] As a result, the generated analysis is formatted into an easy-to-understand format that reflects the user's emotions, sent to the user's terminal, and displayed on the user interface. The user can then make decisions based on this information.

[0193] For example, if a user enters "I'm worried about my household finances because of recent travel expenses," the server recognizes this concern, extracts and analyzes all travel-related expense data, and then suggests areas where expenses can be reduced and alternative options, along with the analysis results.

[0194] An example of a prompt for the generating AI model would be: "The user has described their household finances and explicitly stated feelings such as worry and anxiety. Please perform an expenditure analysis taking these feelings into consideration and provide the user with appropriate advice."

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The user enters "I'm worried about my household finances because of recent travel expenses" into the device in natural language. The device receives this input data and sends it to the server. The input data contains the user's emotions, which play an important role in subsequent processing.

[0198] Step 2:

[0199] The server analyzes the received natural language data using natural language processing libraries such as Python's NLTK. Keywords and emotions are extracted to identify the intent and emotion (worry) of the input. The input is natural language text, and the output provides the intent (anxiety about spending) and emotion.

[0200] Step 3:

[0201] The server uses the Google Cloud Natural Language API to perform sentiment analysis and gain a detailed understanding of the user's emotions. In this step, the analyzed data is taken as input and the emotional state is output. The server detects emotions such as worry and anxiety and adjusts subsequent processing accordingly.

[0202] Step 4:

[0203] The server automatically generates queries against the relational database, taking into account the identified intentions and emotions. These queries are designed to extract travel expense data related to the user's input. The input is the intention and emotion, and the output is the query for data extraction.

[0204] Step 5:

[0205] The server uses the generated query to extract the relevant data from the relational database. Specifically, all travel-related expense data is retrieved in this step. The input here is the query, and the output is a set of related expense data.

[0206] Step 6:

[0207] The server analyzes the extracted data using a generative model (machine learning model). This analysis generates more detailed data analysis and advice based on the user's emotional state. The data input includes details of travel expenses, and the output includes suggestions for areas where costs can be reduced and alternative options.

[0208] Step 7:

[0209] The server formats the analysis results into an easy-to-understand format that is tailored to the user's emotions and sends them to the terminal. For example, specific savings items and alternatives are presented. The terminal displays these results on its user interface, and the user ultimately reviews them and makes a decision.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] [Second Embodiment]

[0214] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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".

[0226] This invention provides a data analysis system using natural language, and consists of three main components: a user, a terminal, and a server.

[0227] Users input the necessary instructions for data analysis in natural language through the terminal's interface. For example, a user might input, "I want to know the latest customer satisfaction trends." This input is immediately received by the terminal.

[0228] The terminal sends this natural language data to the server and also functions as an interface to provide input confirmation and feedback to the user.

[0229] The server analyzes the received natural language data using natural language processing tools to identify the user's intent. For example, it extracts keywords such as "customer satisfaction" or "trends" and generates database queries based on that intent.

[0230] Next, the server uses the generated query to access the database and extract the necessary data. The extracted data is analyzed by a generative model to identify data patterns and trends.

[0231] Finally, the server formats the analysis results into a user-friendly format, such as graphs or reports, and sends them to the terminal. The terminal then displays these results to the user, providing intuitive data insights. This entire process allows users to efficiently perform data analysis using natural language.

[0232] As a concrete example, when a user in the sales department enters the instruction "Analyze the sales data trends for the past three months" into their terminal, the server analyzes the intent and extracts and analyzes the relevant sales data. As a result, the analyzed sales trends are presented to the user in graph format, which helps in the early detection of performance issues and problems. This enables quick and efficient data analysis without requiring specialized knowledge.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The user inputs the information they want to analyze into the device using natural language. For example, they might enter instructions such as, "Analyze last month's sales trends."

[0236] Step 2:

[0237] The terminal receives natural language input from the user and prepares to send that data to the server. It verifies the input and performs error checks to ensure the accuracy of the information.

[0238] Step 3:

[0239] The server receives natural language data sent from the terminal. The natural language processing engine installed on the server analyzes the received data to identify the intent and purpose of the instructions.

[0240] Step 4:

[0241] The server automatically generates SQL queries to access the database based on the analyzed intent. The generated queries are structured to extract data for a specific period or item.

[0242] Step 5:

[0243] The server uses the generated SQL query to extract the necessary data from the database. The extracted data is temporarily stored on the server in preparation for further processing.

[0244] Step 6:

[0245] The server analyzes the extracted data using a generative model. The model employs machine learning algorithms to identify patterns and trends within the data. This analysis leads to new insights and areas for improvement.

[0246] Step 7:

[0247] The server formats the obtained analysis results into a user-friendly format, such as visualized graphs or tables. During this process, processing is performed to improve the visibility and comprehensibility of the information.

[0248] Step 8:

[0249] The terminal receives analysis results sent from the server and displays them to the user. The user can then use the presented information to make decisions and improve their work or solve problems.

[0250] (Example 1)

[0251] 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."

[0252] In data analysis, it is difficult for users without specialized knowledge to obtain useful information without complex procedures. Furthermore, traditional systems often make it difficult for users to appropriately specify the intent behind the data, resulting in inaccurate data analysis. Therefore, there is a need for a system that allows users to easily provide analysis instructions in natural language and obtain results in an intuitively understandable format.

[0253] 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.

[0254] In this invention, the server includes a device for receiving instructions input in natural language, a natural language processing device for analyzing the received natural language instructions and extracting their intent, and a device for automatically generating query statements for an information storage structure based on the extracted intent. This makes it possible for users to quickly and accurately obtain information without specialized knowledge simply by giving instructions in natural language, and to intuitively understand the results.

[0255] A "device that receives instructions entered in natural language" is a device that directly receives commands entered by the user in natural language.

[0256] A "natural language processing device" is a device that analyzes received natural language instructions and extracts their intent.

[0257] A "device for automatically generating query statements for information storage structures" is a device that automatically generates query statements to access an information storage system based on the extracted intent.

[0258] An "information storage structure" refers to a system or method in which data is organized and stored, and typically includes relational databases, etc.

[0259] A "generative AI model" is a model that uses machine learning and artificial intelligence technologies to analyze data and derive evaluation results.

[0260] A "device that provides evaluation results in a format easily understandable to users" is a device that presents the generated evaluation results in a format that is intuitively easy for users to understand, such as graphs or reports.

[0261] A "feedback device" is a device that provides confirmation or a response to user input or commands.

[0262] This invention is a system for users to acquire information via natural language and perform data analysis. The system consists of a user, a terminal, and a server. The server is primarily responsible for natural language processing and data analysis, while the terminal functions as an interface with the user.

[0263] Users can use their terminal to input prompts in natural language. For example, they might input a command such as, "Tell me the sales data trends for last month." The terminal receives this natural language command and sends the data to the server.

[0264] The server uses a natural language processing unit (such as spaCy or NLTK software libraries) to analyze the received instructions. During this process, it extracts specific words and keywords to identify the data request intended by the user. Then, to efficiently extract the relevant data, it automatically generates query statements to access the information storage structure (usually a relational database).

[0265] The generated query prompts the server to access the database and extract the necessary data. The extracted data is then evaluated by a generating AI model (for example, a machine learning model using TensorFlow or PyTorch) to analyze data patterns and trends.

[0266] The analysis results are formatted on the server into a user-friendly format (e.g., graphs or tables) and sent to the terminal. The terminal then presents this information to the user. This allows users to easily gain data insights using natural language, even without specialized knowledge.

[0267] For example, if a user enters the prompt "What is the average customer satisfaction rating for this week?", the server extracts relevant data and analyzes it using an AI model. The average value resulting from the analysis is then presented to the user, which can be used to aid in decision-making.

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The user inputs data analysis instructions into the terminal in natural language. The input consists of prompts, such as "I want to know the latest sales trends." The terminal receives these instructions as text data based on their grammatical structure.

[0271] Step 2:

[0272] The terminal sends the received text data to the server. The input here is the user's prompt, which serves as the output data to the server. The terminal also checks for input errors and displays a warning to the user if there are any problems.

[0273] Step 3:

[0274] The server analyzes the received prompt text using a natural language processing unit (NLTK). For example, it uses spaCy or NLTK to extract keywords and intent from the text. The input is the user's prompt text, and the output is the extracted keywords and their intent.

[0275] Step 4:

[0276] The server automatically generates query statements to access the information storage structure based on the analyzed intent. The input here is the intent and keywords obtained through analysis, and the output is the generated query statement, such as an SQL query. In this process, the server generates queries according to the schema of the relevant database.

[0277] Step 5:

[0278] The server uses the generated query statement to extract data from the information storage structure. The SQL query is executed, and the necessary data is retrieved from the database. The input is the generated query, and the output is the raw data retrieved by the query.

[0279] Step 6:

[0280] The server analyzes the extracted data using a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze data patterns and trends. The input is raw data, and the output is the analyzed result, such as trends and insights.

[0281] Step 7:

[0282] The server formats the analysis results into a user-friendly format. The input here is the analysis results, and the output is a formatted graph or report. For example, the server generates a line graph to visualize increases and decreases in sales.

[0283] Step 8:

[0284] The terminal displays the formatted analysis results to the user. The input is a graph or report from the server, and the output is data visually presented to the user. This enables the user to easily grasp the trends and patterns in the data.

[0285] (Application Example 1)

[0286] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0287] In the modern urban environment, there is a lack of means for residents to obtain and understand real-time urban information in an intuitive and accessible form. Therefore, it is difficult to efficiently grasp traffic conditions and environmental data and make appropriate decisions. In particular, it is required that residents without specialized knowledge can easily obtain this information.

[0288] 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.

[0289] In this invention, the server includes means for receiving information input in natural language, natural language processing means for analyzing the received natural language information to identify its intention, and means for automatically generating a query to the information storage device based on the identified intention. This enables residents to easily obtain and understand real-time urban information in natural language.

[0290] "Natural language" refers to the languages that humans use in daily life, such as Japanese and English, and is something that is analyzed to enable computers to handle it.

[0291] "Information storage device" refers to a device or system that stores data and can retrieve it as needed.

[0292] "Query" refers to a request or question made to obtain information or data.

[0293] A "generative model" is a method of analyzing data, extracting patterns and features from it, and outputting results.

[0294] "Real-time information" refers to the latest information that immediately reflects the current state and situation.

[0295] "Residents" refers to people who live in a particular area or people who have an interest in that area.

[0296] "Natural language processing" refers to the technologies and methods that enable computers to understand and appropriately interpret human language.

[0297] "Information" refers to data, facts, and knowledge that are used for a specific purpose.

[0298] The system for implementing this invention mainly consists of user terminals, a server, and a central database. Users can query urban traffic conditions and environmental information in natural language via devices they use daily, such as smartphones or smart glasses.

[0299] The terminal receives natural language input from the user and then sends this information to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the user's intent and retrieves the necessary data from a central database via traffic data APIs and environmental data APIs.

[0300] The acquired data is analyzed in real time by a server, and patterns and trends are identified using a generative AI model. The analysis results are output to the user in a visually easy-to-understand format and displayed on the device screen or smart glasses display.

[0301] For example, when a user instructs the terminal to "immediately check the nearby traffic congestion", the server collects the nearby traffic information and displays the analysis results. Also, for an input of "tell me the current temperature in the city", the server obtains the latest temperature data and instantaneously visualizes and displays it. In this process, by using the generative AI model, the user can efficiently obtain urban information.

[0302] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0303] Step 1:

[0304] The user inputs a question in natural language using a smartphone or smart glasses. There is a phrase like "tell me the current traffic situation" as this input, and the user terminal receives this data. The input natural language data is prepared to be sent to the server.

[0305] Step 2:

[0306] The terminal sends the received natural language input to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the input data and identify the user's intention. In this analysis process, keywords such as "traffic situation" are identified, and a request for information acquisition based on them is generated. The input is a natural language question, and the output is an internal query reflecting the intention.

[0307] Step 3:

[0308] The server constructs a query for making inquiries to the traffic data API and the environmental data API based on the identified intention. This query is for extracting the necessary data from a global database or a sensor network. The input is a query reflecting the user's intention, and the output is a request for the data to be acquired.

[0309] Step 4:

[0310] The server analyzes the acquired data using a generative AI model. Data processing here includes time series analysis and trend forecasting. The generative model detects patterns related to traffic and the environment and generates predictions or summaries based on these. The input is raw data from query results, and the output is visualized information as analysis results.

[0311] Step 5:

[0312] The analysis results generated by the server are sent to the user's terminal and displayed in a format that is easy for the user to understand. Smart glasses display information in a visually easy-to-understand format, such as showing traffic congestion areas and weather conditions on a map. The input is processed analysis results, and the output is visualized information for the user to use.

[0313] 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.

[0314] This invention combines a natural language-based data analysis system with an emotion engine that recognizes user emotions. This enables more flexible and adaptive data analysis and result presentation.

[0315] The user inputs the information they want to analyze into the device using natural language. For example, they might input instructions that include emotions, such as, "I'm concerned about the recent decline in sales, so I'd like to know more details." The device receives this input and sends it to the server.

[0316] The server receives natural language input from the terminal and then analyzes it using natural language processing tools. This analysis process not only identifies keywords and intent from the user's input, but also includes a step where an emotion engine recognizes the user's emotions. For example, it can detect emotions such as "concern" or "worry."

[0317] After the server recognizes the user's emotions, it automatically generates a database query, taking into account the identified intentions and emotions. This query is used to access the database and extract data that matches the specified criteria.

[0318] The extracted data is analyzed using a generative model, and this process allows for adjustment of the analysis methods and output trends based on the user's emotional state. For example, if the user expresses an emotion such as "worry," the analysis results may be provided in a more detailed and solution-focused manner.

[0319] Finally, the analysis results are formatted in an easy-to-understand style that aligns with the user's emotions and sent to the device. The device displays these results on its user interface, allowing the user to make decisions based on the presented information. For example, if a manager inputs "I'm worried about market risks," the server prioritizes analyzing risk-related data and suggests potential countermeasures.

[0320] Thus, the present invention aims to improve the efficiency of data analysis and user satisfaction by performing analysis and presenting results that take user emotions into consideration.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] Users input information about the issues or subjects they want to analyze into their device using natural language. For example, they might input instructions such as, "I'm concerned about recent customer feedback, so I'd like you to analyze it in detail."

[0324] Step 2:

[0325] The terminal receives natural language input from the user and prepares to send that data to the server. It performs error checking and input format verification to ensure that accurate information is transferred.

[0326] Step 3:

[0327] The server receives natural language data transmitted from the terminal. The received data is analyzed using natural language processing tools to identify the user's intent and instructions.

[0328] Step 4:

[0329] The server uses an emotion engine to detect the user's emotions from the received input data. For example, it can determine the user's feelings of anxiety or concern from a word like "I'm worried."

[0330] Step 5:

[0331] The server automatically generates database queries based on identified intent and user sentiment. These queries are optimized to extract relevant data while considering the user's interests and emotions.

[0332] Step 6:

[0333] The server uses the generated query to access the database and extract the relevant data. The extracted data is checked to see if it meets the user's requirements and then passed on to the next analysis phase.

[0334] Step 7:

[0335] The server analyzes the extracted data using a generative model. During this process, the analysis focus and methods are adjusted according to the user's emotions. For example, it may highlight risk factors in the data based on emotions such as anxiety.

[0336] Step 8:

[0337] When the server formats the analysis results into a highly readable format, such as graphs or charts, it selects points to emphasize and display formats that match the user's emotions.

[0338] Step 9:

[0339] The terminal receives analysis results sent from the server and displays them in the user interface. Users can use this information to make decisions and apply the analysis to actual actions.

[0340] (Example 2)

[0341] 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".

[0342] In modern data analysis systems, analyses often disregard user emotions, making it difficult to provide the information and solutions that users truly seek. Furthermore, there is a need for flexible systems that accurately capture the emotions and intentions expressed by users and then present appropriate analytical results.

[0343] 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.

[0344] In this invention, the server includes means for analyzing data input in natural language and identifying its intent, means for using an emotion engine to recognize the user's emotions from the input data, and means for automatically generating queries to a database and extracting and analyzing data. This enables more intuitive and useful data analysis and information provision that takes user emotions into account.

[0345] "Natural language" refers to the language system that humans use in everyday life, and includes information expressed in dialogue and written form.

[0346] A "database" is a system for systematically organizing and storing data according to a specific purpose, and it is possible to search and retrieve data through queries.

[0347] An "emotion engine" is a technology that analyzes and recognizes emotions from user input, and can identify the type and intensity of emotions.

[0348] A "generating model" is a computational model used for analyzing data and recognizing patterns through machine learning, and it plays a role in making predictions and suggestions based on the data.

[0349] "Generating results" refers to the process of creating useful conclusions and suggestions for users based on information obtained through data analysis.

[0350] "A format tailored to the user's emotions" refers to a method of presenting information in the most easily understandable and appropriate format, taking into account the user's emotional state at the time of input.

[0351] A "query" is a command given to a database to search for and extract specific data, and it is written in a structured language.

[0352] This invention is embodied as a system in which a user inputs data analysis instructions into a terminal using natural language, and this information is processed on a server. The user inputs instructions in natural language, including questions and feelings about the data they are interested in. Examples of prompts could be, "I'm worried about recent sales and would like to know the reason," or "I'm concerned about market risks."

[0353] The terminal receives this input and sends it to the server. The server analyzes the received input using natural language processing. During the analysis process, it identifies the user's intent and identifies the user's emotions using an emotion engine. This system uses keyword extraction models and deep learning-based emotion recognition technology.

[0354] Based on identified intentions and emotions, the server automatically generates queries to the database and extracts the necessary data. The database often contains relational and time-series data. The extracted data is analyzed using a generative AI model. This model can identify data patterns and potential issues and generate analysis results that take into account the user's specific emotions.

[0355] Ultimately, the server formats the generated analysis results in an appropriate format that aligns with the user's emotions and sends them to the terminal. The terminal displays the results in a user interface, providing information in a way that is easy for the user to understand. This system enables advanced data analysis and effective information presentation that takes into account the user's emotions and intentions.

[0356] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0357] Step 1:

[0358] The user inputs the information they want analyzed into the device using natural language. This input may include the user's intentions and emotions. For example, the user might ask, "I'm worried about recent sales and want to know the reason." The device receives this input and sends it to the server.

[0359] Step 2:

[0360] The server analyzes natural language input received from the terminal. This process uses natural language processing tools to identify the user's intent and recognizes the emotions contained in the input using an emotion engine. For example, it identifies emotions such as "worry" and "concern." Based on the input data, keyword extraction and emotion analysis are performed to generate analysis results.

[0361] Step 3:

[0362] The server automatically generates queries to the database based on the analysis results. These queries are designed to retrieve appropriate data according to identified intentions and sentiments. For example, they may include conditions to search for unusual patterns in sales data. In this step, the analysis results are taken as input, and the generated queries are taken as output.

[0363] Step 4:

[0364] The server applies the generated query to the database and extracts the necessary data. The data extracted from the database is then fed into a generative AI model for analysis. The output is obtained in the form of data summaries, statistics, and so on.

[0365] Step 5:

[0366] The server analyzes the extracted data using a generating AI model. At this stage, the model identifies patterns in the data and performs analysis that takes user sentiment into account. For example, it examines in detail the causes of declining sales. This process yields analytical insights and potential issues, which are then output as analysis results.

[0367] Step 6:

[0368] The server formats the analysis results into an easy-to-understand format based on the user's emotions. This formatted information is then sent to the terminal for display on the user interface. The formatted results, including suggestions and solutions, are presented to the user.

[0369] Step 7:

[0370] The terminal receives formatted analysis results from the server and displays them in the user interface. The user then makes decisions based on this information. This display includes visually easy-to-understand elements such as graphs and charts.

[0371] (Application Example 2)

[0372] 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".

[0373] This aims to solve the problem that when users analyze data using natural language, the analysis and presentation of results do not take into account the emotions contained in the instructions, making it difficult to respond flexibly to the user's needs.

[0374] 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.

[0375] In this invention, the server includes means for receiving data and user sentiment input in natural language, natural language processing means for analyzing the received natural language data to identify the intent and sentiment, and means for automatically generating queries to a relational database based on the identified intent and sentiment. This enables flexible and adaptive data analysis and result presentation that takes user sentiment into consideration.

[0376] "Data entered in natural language" refers to data entered by a user using normal human language and processed by a computer system.

[0377] "User emotions" refers to information that indicates the emotional state or psychological tendencies expressed by the user.

[0378] "Natural language processing means" are technical means for analyzing the content of text data expressed in natural language and identifying its intent and structure.

[0379] "Methods for automatically generating queries" refer to technologies that automatically create queries to access a database based on user requests.

[0380] A "relational database" is a data management system that organizes data in a tabular format and systematically establishes relationships between different data items.

[0381] A "generative model" is a method or technique that uses machine learning or statistical models to extract patterns from data and generate analytical results.

[0382] "Means for outputting analysis results" refers to technologies that present information obtained from data analysis in a way that is easy for users to understand.

[0383] The system for realizing this invention consists of a user terminal, a server, and a database. First, the user inputs their emotions or the content they wish to analyze into the user terminal in natural language. The input data is expressed in natural language, and the user terminal receives it.

[0384] Data received from the user's terminal is sent to the server. The server has a natural language processing library (for example, Python's NLTK) installed, and uses this library to analyze the input data and identify the user's intent and emotions. In addition, sentiment analysis APIs such as the Google Cloud Natural Language API are used for emotion recognition.

[0385] Subsequently, the server automatically generates queries to a relational database based on the identified intentions and emotions. These queries are used to extract relevant data from the database. The extracted data is then analyzed by a generative model (e.g., a machine learning model). Here, data analysis techniques that take user emotions into account are employed.

[0386] As a result, the generated analysis is formatted into an easy-to-understand format that reflects the user's emotions, sent to the user's terminal, and displayed on the user interface. The user can then make decisions based on this information.

[0387] For example, if a user enters "I'm worried about my household finances because of recent travel expenses," the server recognizes this concern, extracts and analyzes all travel-related expense data, and then suggests areas where expenses can be reduced and alternative options, along with the analysis results.

[0388] An example of a prompt for the generating AI model would be: "The user has described their household finances and explicitly stated feelings such as worry and anxiety. Please perform an expenditure analysis taking these feelings into consideration and provide the user with appropriate advice."

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] The user enters "I'm worried about my household finances because of recent travel expenses" into the device in natural language. The device receives this input data and sends it to the server. The input data contains the user's emotions, which play an important role in subsequent processing.

[0392] Step 2:

[0393] The server analyzes the received natural language data using natural language processing libraries such as Python's NLTK. Keywords and emotions are extracted to identify the intent and emotion (worry) of the input. The input is natural language text, and the output provides the intent (anxiety about spending) and emotion.

[0394] Step 3:

[0395] The server uses the Google Cloud Natural Language API to perform sentiment analysis and gain a detailed understanding of the user's emotions. In this step, the analyzed data is taken as input and the emotional state is output. The server detects emotions such as worry and anxiety and adjusts subsequent processing accordingly.

[0396] Step 4:

[0397] The server automatically generates queries against the relational database, taking into account the identified intentions and emotions. These queries are designed to extract travel expense data related to the user's input. The input is the intention and emotion, and the output is the query for data extraction.

[0398] Step 5:

[0399] The server uses the generated query to extract the relevant data from the relational database. Specifically, all travel-related expense data is retrieved in this step. The input here is the query, and the output is a set of related expense data.

[0400] Step 6:

[0401] The server analyzes the extracted data using a generative model (machine learning model). This analysis generates more detailed data analysis and advice based on the user's emotional state. The data input includes details of travel expenses, and the output includes suggestions for areas where costs can be reduced and alternative options.

[0402] Step 7:

[0403] The server formats the analysis results into an easy-to-understand format that is tailored to the user's emotions and sends them to the terminal. For example, specific savings items and alternatives are presented. The terminal displays these results on its user interface, and the user ultimately reviews them and makes a decision.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] [Third Embodiment]

[0408] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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".

[0420] This invention provides a data analysis system using natural language, and consists of three main components: a user, a terminal, and a server.

[0421] Users input the necessary instructions for data analysis in natural language through the terminal's interface. For example, a user might input, "I want to know the latest customer satisfaction trends." This input is immediately received by the terminal.

[0422] The terminal sends this natural language data to the server and also functions as an interface to provide input confirmation and feedback to the user.

[0423] The server analyzes the received natural language data using natural language processing tools to identify the user's intent. For example, it extracts keywords such as "customer satisfaction" or "trends" and generates database queries based on that intent.

[0424] Next, the server uses the generated query to access the database and extract the necessary data. The extracted data is analyzed by a generative model to identify data patterns and trends.

[0425] Finally, the server formats the analysis results into a user-friendly format, such as graphs or reports, and sends them to the terminal. The terminal then displays these results to the user, providing intuitive data insights. This entire process allows users to efficiently perform data analysis using natural language.

[0426] As a concrete example, when a user in the sales department enters the instruction "Analyze the sales data trends for the past three months" into their terminal, the server analyzes the intent and extracts and analyzes the relevant sales data. As a result, the analyzed sales trends are presented to the user in graph format, which helps in the early detection of performance issues and problems. This enables quick and efficient data analysis without requiring specialized knowledge.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The user inputs the information they want to analyze into the device using natural language. For example, they might enter instructions such as, "Analyze last month's sales trends."

[0430] Step 2:

[0431] The terminal receives natural language input from the user and prepares to send that data to the server. It verifies the input and performs error checks to ensure the accuracy of the information.

[0432] Step 3:

[0433] The server receives natural language data sent from the terminal. The natural language processing engine installed on the server analyzes the received data to identify the intent and purpose of the instructions.

[0434] Step 4:

[0435] The server automatically generates SQL queries to access the database based on the analyzed intent. The generated queries are structured to extract data for a specific period or item.

[0436] Step 5:

[0437] The server uses the generated SQL query to extract the necessary data from the database. The extracted data is temporarily stored on the server in preparation for further processing.

[0438] Step 6:

[0439] The server analyzes the extracted data using a generative model. The model employs machine learning algorithms to identify patterns and trends within the data. This analysis leads to new insights and areas for improvement.

[0440] Step 7:

[0441] The server formats the obtained analysis results into a user-friendly format, such as visualized graphs or tables. During this process, processing is performed to improve the visibility and comprehensibility of the information.

[0442] Step 8:

[0443] The terminal receives analysis results sent from the server and displays them to the user. The user can then use the presented information to make decisions and improve their work or solve problems.

[0444] (Example 1)

[0445] 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."

[0446] In data analysis, it is difficult for users without specialized knowledge to obtain useful information without complex procedures. Furthermore, traditional systems often make it difficult for users to appropriately specify the intent behind the data, resulting in inaccurate data analysis. Therefore, there is a need for a system that allows users to easily provide analysis instructions in natural language and obtain results in an intuitively understandable format.

[0447] 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.

[0448] In this invention, the server includes a device for receiving instructions input in natural language, a natural language processing device for analyzing the received natural language instructions and extracting their intent, and a device for automatically generating query statements for an information storage structure based on the extracted intent. This makes it possible for users to quickly and accurately obtain information without specialized knowledge simply by giving instructions in natural language, and to intuitively understand the results.

[0449] A "device that receives instructions entered in natural language" is a device that directly receives commands entered by the user in natural language.

[0450] A "natural language processing device" is a device that analyzes received natural language instructions and extracts their intent.

[0451] A "device for automatically generating query statements for information storage structures" is a device that automatically generates query statements to access an information storage system based on the extracted intent.

[0452] An "information storage structure" refers to a system or method in which data is organized and stored, and typically includes relational databases, etc.

[0453] A "generative AI model" is a model that uses machine learning and artificial intelligence technologies to analyze data and derive evaluation results.

[0454] A "device that provides evaluation results in a format easily understandable to users" is a device that presents the generated evaluation results in a format that is intuitively easy for users to understand, such as graphs or reports.

[0455] A "feedback device" is a device that provides confirmation or a response to user input or commands.

[0456] This invention is a system for users to acquire information via natural language and perform data analysis. The system consists of a user, a terminal, and a server. The server is primarily responsible for natural language processing and data analysis, while the terminal functions as an interface with the user.

[0457] Users can use their terminal to input prompts in natural language. For example, they might input a command such as, "Tell me the sales data trends for last month." The terminal receives this natural language command and sends the data to the server.

[0458] The server uses a natural language processing unit (such as spaCy or NLTK software libraries) to analyze the received instructions. During this process, it extracts specific words and keywords to identify the data request intended by the user. Then, to efficiently extract the relevant data, it automatically generates query statements to access the information storage structure (usually a relational database).

[0459] The generated query prompts the server to access the database and extract the necessary data. The extracted data is then evaluated by a generating AI model (for example, a machine learning model using TensorFlow or PyTorch) to analyze data patterns and trends.

[0460] The analysis results are formatted on the server into a user-friendly format (e.g., graphs or tables) and sent to the terminal. The terminal then presents this information to the user. This allows users to easily gain data insights using natural language, even without specialized knowledge.

[0461] For example, if a user enters the prompt "What is the average customer satisfaction rating for this week?", the server extracts relevant data and analyzes it using an AI model. The average value resulting from the analysis is then presented to the user, which can be used to aid in decision-making.

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The user inputs data analysis instructions into the terminal in natural language. The input consists of prompts, such as "I want to know the latest sales trends." The terminal receives these instructions as text data based on their grammatical structure.

[0465] Step 2:

[0466] The terminal sends the received text data to the server. The input here is the user's prompt, which serves as the output data to the server. The terminal also checks for input errors and displays a warning to the user if there are any problems.

[0467] Step 3:

[0468] The server analyzes the received prompt text using a natural language processing unit (NLTK). For example, it uses spaCy or NLTK to extract keywords and intent from the text. The input is the user's prompt text, and the output is the extracted keywords and their intent.

[0469] Step 4:

[0470] The server automatically generates query statements to access the information storage structure based on the analyzed intent. The input here is the intent and keywords obtained through analysis, and the output is the generated query statement, such as an SQL query. In this process, the server generates queries according to the schema of the relevant database.

[0471] Step 5:

[0472] The server uses the generated query statement to extract data from the information storage structure. The SQL query is executed, and the necessary data is retrieved from the database. The input is the generated query, and the output is the raw data retrieved by the query.

[0473] Step 6:

[0474] The server analyzes the extracted data using a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze data patterns and trends. The input is raw data, and the output is the analyzed result, such as trends and insights.

[0475] Step 7:

[0476] The server formats the analysis results into a user-friendly format. The input here is the analysis results, and the output is a formatted graph or report. For example, the server generates a line graph to visualize increases and decreases in sales.

[0477] Step 8:

[0478] The terminal displays formatted analysis results to the user. Input is graphs and reports from the server, and output is data presented visually to the user. This allows the user to easily grasp data trends and patterns.

[0479] (Application Example 1)

[0480] 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."

[0481] In modern urban environments, there is a lack of means for residents to intuitively access and understand real-time urban information. This makes it difficult to efficiently grasp traffic conditions and environmental data and make appropriate decisions. In particular, there is a need for residents without specialized knowledge to easily obtain this information.

[0482] 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.

[0483] In this invention, the server includes means for receiving information input in natural language, natural language processing means for analyzing the received natural language information and identifying its intent, and means for automatically generating queries to an information storage device based on the identified intent. This makes it possible for residents to easily obtain and understand real-time information about the city in natural language.

[0484] "Natural language" refers to languages ​​that humans use on a daily basis, such as Japanese or English, which are analyzed in order to make them usable by computers.

[0485] An "information storage device" is a device or system that stores data and allows it to be retrieved as needed.

[0486] An "inquiry" is a request or question made in order to obtain information or data.

[0487] A "generative model" is a method of analyzing data, extracting patterns and features from it, and outputting results.

[0488] "Real-time information" refers to the latest information that immediately reflects the current state and situation.

[0489] "Residents" refers to people who live in a particular area or people who have an interest in that area.

[0490] "Natural language processing" refers to the technologies and methods that enable computers to understand and appropriately interpret human language.

[0491] "Information" refers to data, facts, and knowledge that are used for a specific purpose.

[0492] The system for implementing this invention mainly consists of user terminals, a server, and a central database. Users can query urban traffic conditions and environmental information in natural language via devices they use daily, such as smartphones or smart glasses.

[0493] The terminal receives natural language input from the user and then sends this information to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the user's intent and retrieves the necessary data from a central database via traffic data APIs and environmental data APIs.

[0494] The acquired data is analyzed in real time by a server, and patterns and trends are identified using a generative AI model. The analysis results are output to the user in a visually easy-to-understand format and displayed on the device screen or smart glasses display.

[0495] For example, if a user instructs their device to "check nearby traffic congestion immediately," the server will collect nearby traffic information and display the analysis results. Similarly, in response to the input "Tell me the current city temperature," the server will retrieve the latest temperature data and instantly visualize and display it. Through this process, a generative AI model is used, enabling users to efficiently obtain urban information.

[0496] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0497] Step 1:

[0498] The user inputs a question in natural language using a smartphone or smart glasses. For example, the input might be the phrase "Tell me the current traffic conditions," and the user's device receives this data. The input natural language data is then prepared for transmission to the server.

[0499] Step 2:

[0500] The terminal sends the received natural language input to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the input data and identify the user's intent. This analysis process identifies keywords such as "traffic conditions" and generates information retrieval requests based on them. The input is a natural language question, and the output is an internal query that reflects the intent.

[0501] Step 3:

[0502] The server constructs queries to contact traffic data APIs and environmental data APIs based on the identified intent. These queries retrieve the necessary data from global databases and sensor networks. The input is a query reflecting the user's intent, and the output is a request for the data to be retrieved.

[0503] Step 4:

[0504] The server analyzes the acquired data using a generative AI model. Data processing here includes time series analysis and trend forecasting. The generative model detects patterns related to traffic and the environment and generates predictions or summaries based on these. The input is raw data from query results, and the output is visualized information as analysis results.

[0505] Step 5:

[0506] The analysis results generated by the server are sent to the user's terminal and displayed in a format that is easy for the user to understand. Smart glasses display information in a visually easy-to-understand format, such as showing traffic congestion areas and weather conditions on a map. The input is processed analysis results, and the output is visualized information for the user to use.

[0507] 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.

[0508] This invention combines a natural language-based data analysis system with an emotion engine that recognizes user emotions. This enables more flexible and adaptive data analysis and result presentation.

[0509] The user inputs the information they want to analyze into the device using natural language. For example, they might input instructions that include emotions, such as, "I'm concerned about the recent decline in sales, so I'd like to know more details." The device receives this input and sends it to the server.

[0510] The server receives natural language input from the terminal and then analyzes it using natural language processing tools. This analysis process not only identifies keywords and intent from the user's input, but also includes a step where an emotion engine recognizes the user's emotions. For example, it can detect emotions such as "concern" or "worry."

[0511] After the server recognizes the user's emotions, it automatically generates a database query, taking into account the identified intentions and emotions. This query is used to access the database and extract data that matches the specified criteria.

[0512] The extracted data is analyzed using a generative model, and this process allows for adjustment of the analysis methods and output trends based on the user's emotional state. For example, if the user expresses an emotion such as "worry," the analysis results may be provided in a more detailed and solution-focused manner.

[0513] Finally, the analysis results are formatted in an easy-to-understand style that aligns with the user's emotions and sent to the device. The device displays these results on its user interface, allowing the user to make decisions based on the presented information. For example, if a manager inputs "I'm worried about market risks," the server prioritizes analyzing risk-related data and suggests potential countermeasures.

[0514] Thus, the present invention aims to improve the efficiency of data analysis and user satisfaction by performing analysis and presenting results that take user emotions into consideration.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] Users input information about the issues or subjects they want to analyze into their device using natural language. For example, they might input instructions such as, "I'm concerned about recent customer feedback, so I'd like you to analyze it in detail."

[0518] Step 2:

[0519] The terminal receives natural language input from the user and prepares to send that data to the server. It performs error checking and input format verification to ensure that accurate information is transferred.

[0520] Step 3:

[0521] The server receives natural language data transmitted from the terminal. The received data is analyzed using natural language processing tools to identify the user's intent and instructions.

[0522] Step 4:

[0523] The server uses an emotion engine to detect the user's emotions from the received input data. For example, it can determine the user's feelings of anxiety or concern from a word like "I'm worried."

[0524] Step 5:

[0525] The server automatically generates database queries based on identified intent and user sentiment. These queries are optimized to extract relevant data while considering the user's interests and emotions.

[0526] Step 6:

[0527] The server uses the generated query to access the database and extract the relevant data. The extracted data is checked to see if it meets the user's requirements and then passed on to the next analysis phase.

[0528] Step 7:

[0529] The server analyzes the extracted data using a generative model. During this process, the analysis focus and methods are adjusted according to the user's emotions. For example, it may highlight risk factors in the data based on emotions such as anxiety.

[0530] Step 8:

[0531] When the server formats the analysis results into a highly readable format, such as graphs or charts, it selects points to emphasize and display formats that match the user's emotions.

[0532] Step 9:

[0533] The terminal receives analysis results sent from the server and displays them in the user interface. Users can use this information to make decisions and apply the analysis to actual actions.

[0534] (Example 2)

[0535] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0536] In modern data analysis systems, analyses often disregard user emotions, making it difficult to provide the information and solutions that users truly seek. Furthermore, there is a need for flexible systems that accurately capture the emotions and intentions expressed by users and then present appropriate analytical results.

[0537] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0538] In this invention, the server includes means for analyzing data input in natural language and identifying its intent, means for using an emotion engine to recognize the user's emotions from the input data, and means for automatically generating queries to a database and extracting and analyzing data. This enables more intuitive and useful data analysis and information provision that takes user emotions into account.

[0539] "Natural language" refers to the language system that humans use in everyday life, and includes information expressed in dialogue and written form.

[0540] A "database" is a system for systematically organizing and storing data according to a specific purpose, and it is possible to search and retrieve data through queries.

[0541] An "emotion engine" is a technology that analyzes and recognizes emotions from user input, and can identify the type and intensity of emotions.

[0542] A "generating model" is a computational model used for analyzing data and recognizing patterns through machine learning, and it plays a role in making predictions and suggestions based on the data.

[0543] "Generating results" refers to the process of creating useful conclusions and suggestions for users based on information obtained through data analysis.

[0544] "A format tailored to the user's emotions" refers to a method of presenting information in the most easily understandable and appropriate format, taking into account the user's emotional state at the time of input.

[0545] A "query" is a command given to a database to search for and extract specific data, and it is written in a structured language.

[0546] This invention is embodied as a system in which a user inputs data analysis instructions into a terminal using natural language, and this information is processed on a server. The user inputs instructions in natural language, including questions and feelings about the data they are interested in. Examples of prompts could be, "I'm worried about recent sales and would like to know the reason," or "I'm concerned about market risks."

[0547] The terminal receives this input and sends it to the server. The server analyzes the received input using natural language processing. During the analysis process, it identifies the user's intent and identifies the user's emotions using an emotion engine. This system uses keyword extraction models and deep learning-based emotion recognition technology.

[0548] Based on identified intentions and emotions, the server automatically generates queries to the database and extracts the necessary data. The database often contains relational and time-series data. The extracted data is analyzed using a generative AI model. This model can identify data patterns and potential issues and generate analysis results that take into account the user's specific emotions.

[0549] Ultimately, the server formats the generated analysis results in an appropriate format that aligns with the user's emotions and sends them to the terminal. The terminal displays the results in a user interface, providing information in a way that is easy for the user to understand. This system enables advanced data analysis and effective information presentation that takes into account the user's emotions and intentions.

[0550] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0551] Step 1:

[0552] The user inputs the information they want analyzed into the device using natural language. This input may include the user's intentions and emotions. For example, the user might ask, "I'm worried about recent sales and want to know the reason." The device receives this input and sends it to the server.

[0553] Step 2:

[0554] The server analyzes natural language input received from the terminal. This process uses natural language processing tools to identify the user's intent and recognizes the emotions contained in the input using an emotion engine. For example, it identifies emotions such as "worry" and "concern." Based on the input data, keyword extraction and emotion analysis are performed to generate analysis results.

[0555] Step 3:

[0556] The server automatically generates queries to the database based on the analysis results. These queries are designed to retrieve appropriate data according to identified intentions and sentiments. For example, they may include conditions to search for unusual patterns in sales data. In this step, the analysis results are taken as input, and the generated queries are taken as output.

[0557] Step 4:

[0558] The server applies the generated query to the database and extracts the necessary data. The data extracted from the database is then fed into a generative AI model for analysis. The output is obtained in the form of data summaries, statistics, and so on.

[0559] Step 5:

[0560] The server analyzes the extracted data using a generating AI model. At this stage, the model identifies patterns in the data and performs analysis that takes user sentiment into account. For example, it examines in detail the causes of declining sales. This process yields analytical insights and potential issues, which are then output as analysis results.

[0561] Step 6:

[0562] The server formats the analysis results into an easy-to-understand format based on the user's emotions. This formatted information is then sent to the terminal for display on the user interface. The formatted results, including suggestions and solutions, are presented to the user.

[0563] Step 7:

[0564] The terminal receives formatted analysis results from the server and displays them in the user interface. The user then makes decisions based on this information. This display includes visually easy-to-understand elements such as graphs and charts.

[0565] (Application Example 2)

[0566] 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."

[0567] This aims to solve the problem that when users analyze data using natural language, the analysis and presentation of results do not take into account the emotions contained in the instructions, making it difficult to respond flexibly to the user's needs.

[0568] 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.

[0569] In this invention, the server includes means for receiving data and user sentiment input in natural language, natural language processing means for analyzing the received natural language data to identify the intent and sentiment, and means for automatically generating queries to a relational database based on the identified intent and sentiment. This enables flexible and adaptive data analysis and result presentation that takes user sentiment into consideration.

[0570] "Data entered in natural language" refers to data entered by a user using normal human language and processed by a computer system.

[0571] "User emotions" refers to information that indicates the emotional state or psychological tendencies expressed by the user.

[0572] "Natural language processing means" are technical means for analyzing the content of text data expressed in natural language and identifying its intent and structure.

[0573] "Methods for automatically generating queries" refer to technologies that automatically create queries to access a database based on user requests.

[0574] A "relational database" is a data management system that organizes data in a tabular format and systematically establishes relationships between different data items.

[0575] A "generative model" is a method or technique that uses machine learning or statistical models to extract patterns from data and generate analytical results.

[0576] "Means for outputting analysis results" refers to technologies that present information obtained from data analysis in a way that is easy for users to understand.

[0577] The system for realizing this invention consists of a user terminal, a server, and a database. First, the user inputs their emotions or the content they wish to analyze into the user terminal in natural language. The input data is expressed in natural language, and the user terminal receives it.

[0578] Data received from the user's terminal is sent to the server. The server has a natural language processing library (for example, Python's NLTK) installed, and uses this library to analyze the input data and identify the user's intent and emotions. In addition, sentiment analysis APIs such as the Google Cloud Natural Language API are used for emotion recognition.

[0579] Subsequently, the server automatically generates queries to a relational database based on the identified intentions and emotions. These queries are used to extract relevant data from the database. The extracted data is then analyzed by a generative model (e.g., a machine learning model). Here, data analysis techniques that take user emotions into account are employed.

[0580] As a result, the generated analysis is formatted into an easy-to-understand format that reflects the user's emotions, sent to the user's terminal, and displayed on the user interface. The user can then make decisions based on this information.

[0581] For example, if a user enters "I'm worried about my household finances because of recent travel expenses," the server recognizes this concern, extracts and analyzes all travel-related expense data, and then suggests areas where expenses can be reduced and alternative options, along with the analysis results.

[0582] An example of a prompt for the generating AI model would be: "The user has described their household finances and explicitly stated feelings such as worry and anxiety. Please perform an expenditure analysis taking these feelings into consideration and provide the user with appropriate advice."

[0583] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0584] Step 1:

[0585] The user enters "I'm worried about my household finances because of recent travel expenses" into the device in natural language. The device receives this input data and sends it to the server. The input data contains the user's emotions, which play an important role in subsequent processing.

[0586] Step 2:

[0587] The server analyzes the received natural language data using natural language processing libraries such as Python's NLTK. Keywords and emotions are extracted to identify the intent and emotion (worry) of the input. The input is natural language text, and the output provides the intent (anxiety about spending) and emotion.

[0588] Step 3:

[0589] The server uses the Google Cloud Natural Language API to perform sentiment analysis and gain a detailed understanding of the user's emotions. In this step, the analyzed data is taken as input and the emotional state is output. The server detects emotions such as worry and anxiety and adjusts subsequent processing accordingly.

[0590] Step 4:

[0591] The server automatically generates queries against the relational database, taking into account the identified intentions and emotions. These queries are designed to extract travel expense data related to the user's input. The input is the intention and emotion, and the output is the query for data extraction.

[0592] Step 5:

[0593] The server uses the generated query to extract the relevant data from the relational database. Specifically, all travel-related expense data is retrieved in this step. The input here is the query, and the output is a set of related expense data.

[0594] Step 6:

[0595] The server analyzes the extracted data using a generative model (machine learning model). This analysis generates more detailed data analysis and advice based on the user's emotional state. The data input includes details of travel expenses, and the output includes suggestions for areas where costs can be reduced and alternative options.

[0596] Step 7:

[0597] The server formats the analysis results into an easy-to-understand format that is tailored to the user's emotions and sends them to the terminal. For example, specific savings items and alternatives are presented. The terminal displays these results on its user interface, and the user ultimately reviews them and makes a decision.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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".

[0615] This invention provides a data analysis system using natural language, and consists of three main components: a user, a terminal, and a server.

[0616] Users input the necessary instructions for data analysis in natural language through the terminal's interface. For example, a user might input, "I want to know the latest customer satisfaction trends." This input is immediately received by the terminal.

[0617] The terminal sends this natural language data to the server and also functions as an interface to provide input confirmation and feedback to the user.

[0618] The server analyzes the received natural language data using natural language processing tools to identify the user's intent. For example, it extracts keywords such as "customer satisfaction" or "trends" and generates database queries based on that intent.

[0619] Next, the server uses the generated query to access the database and extract the necessary data. The extracted data is analyzed by a generative model to identify data patterns and trends.

[0620] Finally, the server formats the analysis results into a user-friendly format, such as graphs or reports, and sends them to the terminal. The terminal then displays these results to the user, providing intuitive data insights. This entire process allows users to efficiently perform data analysis using natural language.

[0621] As a concrete example, when a user in the sales department enters the instruction "Analyze the sales data trends for the past three months" into their terminal, the server analyzes the intent and extracts and analyzes the relevant sales data. As a result, the analyzed sales trends are presented to the user in graph format, which helps in the early detection of performance issues and problems. This enables quick and efficient data analysis without requiring specialized knowledge.

[0622] The following describes the processing flow.

[0623] Step 1:

[0624] The user inputs the information they want to analyze into the device using natural language. For example, they might enter instructions such as, "Analyze last month's sales trends."

[0625] Step 2:

[0626] The terminal receives natural language input from the user and prepares to send that data to the server. It verifies the input and performs error checks to ensure the accuracy of the information.

[0627] Step 3:

[0628] The server receives natural language data sent from the terminal. The natural language processing engine installed on the server analyzes the received data to identify the intent and purpose of the instructions.

[0629] Step 4:

[0630] The server automatically generates SQL queries to access the database based on the analyzed intent. The generated queries are structured to extract data for a specific period or item.

[0631] Step 5:

[0632] The server uses the generated SQL query to extract the necessary data from the database. The extracted data is temporarily stored on the server in preparation for further processing.

[0633] Step 6:

[0634] The server analyzes the extracted data using a generative model. The model employs machine learning algorithms to identify patterns and trends within the data. This analysis leads to new insights and areas for improvement.

[0635] Step 7:

[0636] The server formats the obtained analysis results into a user-friendly format, such as visualized graphs or tables. During this process, processing is performed to improve the visibility and comprehensibility of the information.

[0637] Step 8:

[0638] The terminal receives analysis results sent from the server and displays them to the user. The user can then use the presented information to make decisions and improve their work or solve problems.

[0639] (Example 1)

[0640] 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".

[0641] In data analysis, it is difficult for users without specialized knowledge to obtain useful information without complex procedures. Furthermore, traditional systems often make it difficult for users to appropriately specify the intent behind the data, resulting in inaccurate data analysis. Therefore, there is a need for a system that allows users to easily provide analysis instructions in natural language and obtain results in an intuitively understandable format.

[0642] 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.

[0643] In this invention, the server includes a device for receiving instructions input in natural language, a natural language processing device for analyzing the received natural language instructions and extracting their intent, and a device for automatically generating query statements for an information storage structure based on the extracted intent. This makes it possible for users to quickly and accurately obtain information without specialized knowledge simply by giving instructions in natural language, and to intuitively understand the results.

[0644] A "device that receives instructions entered in natural language" is a device that directly receives commands entered by the user in natural language.

[0645] A "natural language processing device" is a device that analyzes received natural language instructions and extracts their intent.

[0646] A "device for automatically generating query statements for information storage structures" is a device that automatically generates query statements to access an information storage system based on the extracted intent.

[0647] An "information storage structure" refers to a system or method in which data is organized and stored, and typically includes relational databases, etc.

[0648] A "generative AI model" is a model that uses machine learning and artificial intelligence technologies to analyze data and derive evaluation results.

[0649] A "device that provides evaluation results in a format easily understandable to users" is a device that presents the generated evaluation results in a format that is intuitively easy for users to understand, such as graphs or reports.

[0650] A "feedback device" is a device that provides confirmation or a response to user input or commands.

[0651] This invention is a system for users to acquire information via natural language and perform data analysis. The system consists of a user, a terminal, and a server. The server is primarily responsible for natural language processing and data analysis, while the terminal functions as an interface with the user.

[0652] Users can use their terminal to input prompts in natural language. For example, they might input a command such as, "Tell me the sales data trends for last month." The terminal receives this natural language command and sends the data to the server.

[0653] The server uses a natural language processing unit (such as spaCy or NLTK software libraries) to analyze the received instructions. During this process, it extracts specific words and keywords to identify the data request intended by the user. Then, to efficiently extract the relevant data, it automatically generates query statements to access the information storage structure (usually a relational database).

[0654] The generated query prompts the server to access the database and extract the necessary data. The extracted data is then evaluated by a generating AI model (for example, a machine learning model using TensorFlow or PyTorch) to analyze data patterns and trends.

[0655] The analysis results are formatted on the server into a user-friendly format (e.g., graphs or tables) and sent to the terminal. The terminal then presents this information to the user. This allows users to easily gain data insights using natural language, even without specialized knowledge.

[0656] For example, if a user enters the prompt "What is the average customer satisfaction rating for this week?", the server extracts relevant data and analyzes it using an AI model. The average value resulting from the analysis is then presented to the user, which can be used to aid in decision-making.

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] The user inputs data analysis instructions into the terminal in natural language. The input consists of prompts, such as "I want to know the latest sales trends." The terminal receives these instructions as text data based on their grammatical structure.

[0660] Step 2:

[0661] The terminal sends the received text data to the server. The input here is the user's prompt, which serves as the output data to the server. The terminal also checks for input errors and displays a warning to the user if there are any problems.

[0662] Step 3:

[0663] The server analyzes the received prompt text using a natural language processing unit (NLTK). For example, it uses spaCy or NLTK to extract keywords and intent from the text. The input is the user's prompt text, and the output is the extracted keywords and their intent.

[0664] Step 4:

[0665] The server automatically generates query statements to access the information storage structure based on the analyzed intent. The input here is the intent and keywords obtained through analysis, and the output is the generated query statement, such as an SQL query. In this process, the server generates queries according to the schema of the relevant database.

[0666] Step 5:

[0667] The server uses the generated query statement to extract data from the information storage structure. The SQL query is executed, and the necessary data is retrieved from the database. The input is the generated query, and the output is the raw data retrieved by the query.

[0668] Step 6:

[0669] The server analyzes the extracted data using a generative AI model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze data patterns and trends. The input is raw data, and the output is the analyzed result, such as trends and insights.

[0670] Step 7:

[0671] The server formats the analysis results into a user-friendly format. The input here is the analysis results, and the output is a formatted graph or report. For example, the server generates a line graph to visualize increases and decreases in sales.

[0672] Step 8:

[0673] The terminal displays formatted analysis results to the user. Input is graphs and reports from the server, and output is data presented visually to the user. This allows the user to easily grasp data trends and patterns.

[0674] (Application Example 1)

[0675] 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".

[0676] In modern urban environments, there is a lack of means for residents to intuitively access and understand real-time urban information. This makes it difficult to efficiently grasp traffic conditions and environmental data and make appropriate decisions. In particular, there is a need for residents without specialized knowledge to easily obtain this information.

[0677] 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.

[0678] In this invention, the server includes means for receiving information input in natural language, natural language processing means for analyzing the received natural language information and identifying its intent, and means for automatically generating queries to an information storage device based on the identified intent. This makes it possible for residents to easily obtain and understand real-time information about the city in natural language.

[0679] "Natural language" refers to languages ​​that humans use on a daily basis, such as Japanese or English, which are analyzed in order to make them usable by computers.

[0680] An "information storage device" is a device or system that stores data and allows it to be retrieved as needed.

[0681] An "inquiry" is a request or question made in order to obtain information or data.

[0682] A "generative model" is a method of analyzing data, extracting patterns and features from it, and outputting results.

[0683] "Real-time information" refers to the latest information that immediately reflects the current state and situation.

[0684] "Residents" refers to people who live in a particular area or people who have an interest in that area.

[0685] "Natural language processing" refers to the technologies and methods that enable computers to understand and appropriately interpret human language.

[0686] "Information" refers to data, facts, and knowledge that are used for a specific purpose.

[0687] The system for implementing this invention mainly consists of user terminals, a server, and a central database. Users can query urban traffic conditions and environmental information in natural language via devices they use daily, such as smartphones or smart glasses.

[0688] The terminal receives natural language input from the user and then sends this information to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the user's intent and retrieves the necessary data from a central database via traffic data APIs and environmental data APIs.

[0689] The acquired data is analyzed in real time by a server, and patterns and trends are identified using a generative AI model. The analysis results are output to the user in a visually easy-to-understand format and displayed on the device screen or smart glasses display.

[0690] For example, if a user instructs their device to "check nearby traffic congestion immediately," the server will collect nearby traffic information and display the analysis results. Similarly, in response to the input "Tell me the current city temperature," the server will retrieve the latest temperature data and instantly visualize and display it. Through this process, a generative AI model is used, enabling users to efficiently obtain urban information.

[0691] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0692] Step 1:

[0693] The user inputs a question in natural language using a smartphone or smart glasses. For example, the input might be the phrase "Tell me the current traffic conditions," and the user's device receives this data. The input natural language data is then prepared for transmission to the server.

[0694] Step 2:

[0695] The terminal sends the received natural language input to the server. The server uses a natural language processing library (e.g., SpaCy or NLTK) to analyze the input data and identify the user's intent. This analysis process identifies keywords such as "traffic conditions" and generates information retrieval requests based on them. The input is a natural language question, and the output is an internal query that reflects the intent.

[0696] Step 3:

[0697] The server constructs queries to contact traffic data APIs and environmental data APIs based on the identified intent. These queries retrieve the necessary data from global databases and sensor networks. The input is a query reflecting the user's intent, and the output is a request for the data to be retrieved.

[0698] Step 4:

[0699] The server analyzes the acquired data using a generative AI model. Data processing here includes time series analysis and trend forecasting. The generative model detects patterns related to traffic and the environment and generates predictions or summaries based on these. The input is raw data from query results, and the output is visualized information as analysis results.

[0700] Step 5:

[0701] The analysis results generated by the server are sent to the user's terminal and displayed in a format that is easy for the user to understand. Smart glasses display information in a visually easy-to-understand format, such as showing traffic congestion areas and weather conditions on a map. The input is processed analysis results, and the output is visualized information for the user to use.

[0702] 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.

[0703] This invention combines a natural language-based data analysis system with an emotion engine that recognizes user emotions. This enables more flexible and adaptive data analysis and result presentation.

[0704] The user inputs the information they want to analyze into the device using natural language. For example, they might input instructions that include emotions, such as, "I'm concerned about the recent decline in sales, so I'd like to know more details." The device receives this input and sends it to the server.

[0705] The server receives natural language input from the terminal and then analyzes it using natural language processing tools. This analysis process not only identifies keywords and intent from the user's input, but also includes a step where an emotion engine recognizes the user's emotions. For example, it can detect emotions such as "concern" or "worry."

[0706] After the server recognizes the user's emotions, it automatically generates a database query, taking into account the identified intentions and emotions. This query is used to access the database and extract data that matches the specified criteria.

[0707] The extracted data is analyzed using a generative model, and this process allows for adjustment of the analysis methods and output trends based on the user's emotional state. For example, if the user expresses an emotion such as "worry," the analysis results may be provided in a more detailed and solution-focused manner.

[0708] Finally, the analysis results are formatted in an easy-to-understand style that aligns with the user's emotions and sent to the device. The device displays these results on its user interface, allowing the user to make decisions based on the presented information. For example, if a manager inputs "I'm worried about market risks," the server prioritizes analyzing risk-related data and suggests potential countermeasures.

[0709] Thus, the present invention aims to improve the efficiency of data analysis and user satisfaction by performing analysis and presenting results that take user emotions into consideration.

[0710] The following describes the processing flow.

[0711] Step 1:

[0712] Users input information about the issues or subjects they want to analyze into their device using natural language. For example, they might input instructions such as, "I'm concerned about recent customer feedback, so I'd like you to analyze it in detail."

[0713] Step 2:

[0714] The terminal receives natural language input from the user and prepares to send that data to the server. It performs error checking and input format verification to ensure that accurate information is transferred.

[0715] Step 3:

[0716] The server receives natural language data transmitted from the terminal. The received data is analyzed using natural language processing tools to identify the user's intent and instructions.

[0717] Step 4:

[0718] The server uses an emotion engine to detect the user's emotions from the received input data. For example, it can determine the user's feelings of anxiety or concern from a word like "I'm worried."

[0719] Step 5:

[0720] The server automatically generates database queries based on identified intent and user sentiment. These queries are optimized to extract relevant data while considering the user's interests and emotions.

[0721] Step 6:

[0722] The server uses the generated query to access the database and extract the relevant data. The extracted data is checked to see if it meets the user's requirements and then passed on to the next analysis phase.

[0723] Step 7:

[0724] The server analyzes the extracted data using a generative model. During this process, the analysis focus and methods are adjusted according to the user's emotions. For example, it may highlight risk factors in the data based on emotions such as anxiety.

[0725] Step 8:

[0726] When the server formats the analysis results into a highly readable format, such as graphs or charts, it selects points to emphasize and display formats that match the user's emotions.

[0727] Step 9:

[0728] The terminal receives analysis results sent from the server and displays them in the user interface. Users can use this information to make decisions and apply the analysis to actual actions.

[0729] (Example 2)

[0730] 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".

[0731] In modern data analysis systems, analyses often disregard user emotions, making it difficult to provide the information and solutions that users truly seek. Furthermore, there is a need for flexible systems that accurately capture the emotions and intentions expressed by users and then present appropriate analytical results.

[0732] 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.

[0733] In this invention, the server includes means for analyzing data input in natural language and identifying its intent, means for using an emotion engine to recognize the user's emotions from the input data, and means for automatically generating queries to a database and extracting and analyzing data. This enables more intuitive and useful data analysis and information provision that takes user emotions into account.

[0734] "Natural language" refers to the language system that humans use in everyday life, and includes information expressed in dialogue and written form.

[0735] A "database" is a system for systematically organizing and storing data according to a specific purpose, and it is possible to search and retrieve data through queries.

[0736] An "emotion engine" is a technology that analyzes and recognizes emotions from user input, and can identify the type and intensity of emotions.

[0737] A "generating model" is a computational model used for analyzing data and recognizing patterns through machine learning, and it plays a role in making predictions and suggestions based on the data.

[0738] "Generating results" refers to the process of creating useful conclusions and suggestions for users based on information obtained through data analysis.

[0739] "A format tailored to the user's emotions" refers to a method of presenting information in the most easily understandable and appropriate format, taking into account the user's emotional state at the time of input.

[0740] A "query" is a command given to a database to search for and extract specific data, and it is written in a structured language.

[0741] This invention is embodied as a system in which a user inputs data analysis instructions into a terminal using natural language, and this information is processed on a server. The user inputs instructions in natural language, including questions and feelings about the data they are interested in. Examples of prompts could be, "I'm worried about recent sales and would like to know the reason," or "I'm concerned about market risks."

[0742] The terminal receives this input and sends it to the server. The server analyzes the received input using natural language processing. During the analysis process, it identifies the user's intent and identifies the user's emotions using an emotion engine. This system uses keyword extraction models and deep learning-based emotion recognition technology.

[0743] Based on identified intentions and emotions, the server automatically generates queries to the database and extracts the necessary data. The database often contains relational and time-series data. The extracted data is analyzed using a generative AI model. This model can identify data patterns and potential issues and generate analysis results that take into account the user's specific emotions.

[0744] Ultimately, the server formats the generated analysis results in an appropriate format that aligns with the user's emotions and sends them to the terminal. The terminal displays the results in a user interface, providing information in a way that is easy for the user to understand. This system enables advanced data analysis and effective information presentation that takes into account the user's emotions and intentions.

[0745] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0746] Step 1:

[0747] The user inputs the information they want analyzed into the device using natural language. This input may include the user's intentions and emotions. For example, the user might ask, "I'm worried about recent sales and want to know the reason." The device receives this input and sends it to the server.

[0748] Step 2:

[0749] The server analyzes natural language input received from the terminal. This process uses natural language processing tools to identify the user's intent and recognizes the emotions contained in the input using an emotion engine. For example, it identifies emotions such as "worry" and "concern." Based on the input data, keyword extraction and emotion analysis are performed to generate analysis results.

[0750] Step 3:

[0751] The server automatically generates queries to the database based on the analysis results. These queries are designed to retrieve appropriate data according to identified intentions and sentiments. For example, they may include conditions to search for unusual patterns in sales data. In this step, the analysis results are taken as input, and the generated queries are taken as output.

[0752] Step 4:

[0753] The server applies the generated query to the database and extracts the necessary data. The data extracted from the database is then fed into a generative AI model for analysis. The output is obtained in the form of data summaries, statistics, and so on.

[0754] Step 5:

[0755] The server analyzes the extracted data using a generating AI model. At this stage, the model identifies patterns in the data and performs analysis that takes user sentiment into account. For example, it examines in detail the causes of declining sales. This process yields analytical insights and potential issues, which are then output as analysis results.

[0756] Step 6:

[0757] The server formats the analysis results into an easy-to-understand format based on the user's emotions. This formatted information is then sent to the terminal for display on the user interface. The formatted results, including suggestions and solutions, are presented to the user.

[0758] Step 7:

[0759] The terminal receives formatted analysis results from the server and displays them in the user interface. The user then makes decisions based on this information. This display includes visually easy-to-understand elements such as graphs and charts.

[0760] (Application Example 2)

[0761] 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".

[0762] This aims to solve the problem that when users analyze data using natural language, the analysis and presentation of results do not take into account the emotions contained in the instructions, making it difficult to respond flexibly to the user's needs.

[0763] 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.

[0764] In this invention, the server includes means for receiving data and user sentiment input in natural language, natural language processing means for analyzing the received natural language data to identify the intent and sentiment, and means for automatically generating queries to a relational database based on the identified intent and sentiment. This enables flexible and adaptive data analysis and result presentation that takes user sentiment into consideration.

[0765] "Data entered in natural language" refers to data entered by a user using normal human language and processed by a computer system.

[0766] "User emotions" refers to information that indicates the emotional state or psychological tendencies expressed by the user.

[0767] "Natural language processing means" are technical means for analyzing the content of text data expressed in natural language and identifying its intent and structure.

[0768] "Methods for automatically generating queries" refer to technologies that automatically create queries to access a database based on user requests.

[0769] A "relational database" is a data management system that organizes data in a tabular format and systematically establishes relationships between different data items.

[0770] A "generative model" is a method or technique that uses machine learning or statistical models to extract patterns from data and generate analytical results.

[0771] "Means for outputting analysis results" refers to technologies that present information obtained from data analysis in a way that is easy for users to understand.

[0772] The system for realizing this invention consists of a user terminal, a server, and a database. First, the user inputs their emotions or the content they wish to analyze into the user terminal in natural language. The input data is expressed in natural language, and the user terminal receives it.

[0773] Data received from the user's terminal is sent to the server. The server has a natural language processing library (for example, Python's NLTK) installed, and uses this library to analyze the input data and identify the user's intent and emotions. In addition, sentiment analysis APIs such as the Google Cloud Natural Language API are used for emotion recognition.

[0774] Subsequently, the server automatically generates queries to a relational database based on the identified intentions and emotions. These queries are used to extract relevant data from the database. The extracted data is then analyzed by a generative model (e.g., a machine learning model). Here, data analysis techniques that take user emotions into account are employed.

[0775] As a result, the generated analysis is formatted into an easy-to-understand format that reflects the user's emotions, sent to the user's terminal, and displayed on the user interface. The user can then make decisions based on this information.

[0776] For example, if a user enters "I'm worried about my household finances because of recent travel expenses," the server recognizes this concern, extracts and analyzes all travel-related expense data, and then suggests areas where expenses can be reduced and alternative options, along with the analysis results.

[0777] An example of a prompt for the generating AI model would be: "The user has described their household finances and explicitly stated feelings such as worry and anxiety. Please perform an expenditure analysis taking these feelings into consideration and provide the user with appropriate advice."

[0778] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0779] Step 1:

[0780] The user enters "I'm worried about my household finances because of recent travel expenses" into the device in natural language. The device receives this input data and sends it to the server. The input data contains the user's emotions, which play an important role in subsequent processing.

[0781] Step 2:

[0782] The server analyzes the received natural language data using natural language processing libraries such as Python's NLTK. Keywords and emotions are extracted to identify the intent and emotion (worry) of the input. The input is natural language text, and the output provides the intent (anxiety about spending) and emotion.

[0783] Step 3:

[0784] The server uses the Google Cloud Natural Language API to perform sentiment analysis and gain a detailed understanding of the user's emotions. In this step, the analyzed data is taken as input and the emotional state is output. The server detects emotions such as worry and anxiety and adjusts subsequent processing accordingly.

[0785] Step 4:

[0786] The server automatically generates queries against the relational database, taking into account the identified intentions and emotions. These queries are designed to extract travel expense data related to the user's input. The input is the intention and emotion, and the output is the query for data extraction.

[0787] Step 5:

[0788] The server uses the generated query to extract the relevant data from the relational database. Specifically, all travel-related expense data is retrieved in this step. The input here is the query, and the output is a set of related expense data.

[0789] Step 6:

[0790] The server analyzes the extracted data using a generative model (machine learning model). This analysis generates more detailed data analysis and advice based on the user's emotional state. The data input includes details of travel expenses, and the output includes suggestions for areas where costs can be reduced and alternative options.

[0791] Step 7:

[0792] The server formats the analysis results into an easy-to-understand format that is tailored to the user's emotions and sends them to the terminal. For example, specific savings items and alternatives are presented. The terminal displays these results on its user interface, and the user ultimately reviews them and makes a decision.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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."

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] The following is further disclosed regarding the embodiments described above.

[0815] (Claim 1)

[0816] A means of receiving data input in natural language,

[0817] A natural language processing means that analyzes the received natural language data and identifies its intent,

[0818] A means for automatically generating queries to the relevant database based on the identified intent,

[0819] A means for extracting data from the relational database based on the generated query,

[0820] A means for analyzing the extracted data using a generative model and generating results,

[0821] A means for outputting the generated analysis results in a format that is easy for the user to understand,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, wherein the natural language processing means includes a model for identifying specific words or keywords.

[0825] (Claim 3)

[0826] The system according to claim 1, wherein the generative model is configured to identify patterns in data and present potential problems using machine learning.

[0827] "Example 1"

[0828] (Claim 1)

[0829] A device that receives instructions input in natural language,

[0830] A natural language processing device that analyzes the received natural language instruction and extracts its intent,

[0831] A device that automatically generates query statements for an information storage structure based on the extracted intent,

[0832] A device for extracting information from the information storage structure based on the generated query statement,

[0833] A device that evaluates the extracted information using a generating AI model to derive results,

[0834] A device that provides the generated evaluation results in a format that is easily understandable to the user,

[0835] A device that provides feedback to the user,

[0836] A data processing system that includes this.

[0837] (Claim 2)

[0838] The data processing system according to claim 1, wherein the natural language processing device includes a model for extracting specific words or keywords.

[0839] (Claim 3)

[0840] The data processing system according to claim 1, wherein the generating AI model is configured to identify patterns in information and present potential problems through machine learning.

[0841] "Application Example 1"

[0842] (Claim 1)

[0843] A means of receiving information input in natural language,

[0844] A natural language processing means that analyzes the received natural language information and identifies its intent,

[0845] A means for automatically generating inquiries to the information storage device based on the identified intent,

[0846] Means for extracting information from the information storage device based on the generated query,

[0847] A means for analyzing the extracted information using a generative model and generating results,

[0848] A means for outputting the generated analysis results in a format that is easy for the user to understand,

[0849] Means for acquiring and analyzing information from urban sensor devices or monitoring systems,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, wherein the natural language processing means includes a model for identifying specific words or keywords, and further comprises a function for analyzing real-time urban information.

[0853] (Claim 3)

[0854] The system according to claim 1, wherein the generative model is configured to identify patterns in data by machine learning and to present potential urban challenges.

[0855] "Example 2 of combining an emotion engine"

[0856] (Claim 1)

[0857] A means of receiving data input in natural language,

[0858] A natural language processing means that analyzes the received natural language data and identifies its intent,

[0859] In this analysis, a means is used that employs an emotion engine to recognize the user's emotions from the input data,

[0860] A means for automatically generating queries to a database based on the identified intentions and emotions,

[0861] A means for extracting data from the database based on the generated query,

[0862] A means for analyzing the extracted data using a model that generates the data and for generating results,

[0863] A means for outputting the generated analysis results in a format that matches the user's emotions,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, wherein the natural language processing means includes a model for identifying specific words or keywords.

[0867] (Claim 3)

[0868] The system according to claim 1, wherein the generated model is configured to identify patterns in data by machine learning and to present potential problems and solutions while taking user sentiment into consideration.

[0869] "Application example 2 when combining with an emotional engine"

[0870] (Claim 1)

[0871] A means of receiving data entered in natural language and user sentiment,

[0872] A natural language processing means that analyzes the received natural language data to identify its intent and emotion,

[0873] A means for automatically generating queries to a relational database based on the identified intentions and emotions,

[0874] A means for extracting data from the relational database based on the generated query,

[0875] A means for analyzing data extracted with regard to the emotion using a generative model and generating results,

[0876] A means for outputting the generated analysis results in a format that is easy for the user to understand,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, wherein the natural language processing means is configured to identify specific words or keywords and to recognize the user's emotions.

[0880] (Claim 3)

[0881] The system according to claim 1, wherein the generative model is configured to identify patterns in data by machine learning and to present analytical results and related potential solutions based on user sentiment. [Explanation of Symbols]

[0882] 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 means of receiving data input in natural language, A natural language processing means that analyzes the received natural language data and identifies its intent, A means for automatically generating queries to the relevant database based on the identified intent, A means for extracting data from the relational database based on the generated query, A means for analyzing the extracted data using a generative model and generating results, A means for outputting the generated analysis results in a format that is easy for the user to understand, A system that includes this.

2. The system according to claim 1, wherein the natural language processing means includes a model for identifying specific words or keywords.

3. The system according to claim 1, wherein the generative model is configured to identify patterns in data by machine learning and to present potential problems.

Images