system

Abstract

We provide the system. [Solution] A means for receiving analysis requests entered by users in natural language, A means of analyzing received analysis requests and identifying the requirements of the analysis flow, A means of determining the data analysis flow based on identified requirements and generating it as an image, A means of presenting the generated image to the user, 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 persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In data analysis, there is a problem that it is difficult for users without specialized knowledge to easily utilize analysis tools, and it requires a lot of time and effort to set up and understand the analysis flow. As a result, there is a problem that sufficient time cannot be allocated for efficient data utilization and highly valuable consideration and proposals.

Means for Solving the Problems

[0005] This invention provides a system that understands analysis requests entered by users in natural language, automatically determines an appropriate data analysis flow based on those requests, and presents it to the user as a visual image. This system analyzes the user's input and visualizes the optimal analysis procedure, taking into account the characteristics of known analysis tools. Furthermore, by adding explanatory text related to the generated image, it enables users to understand the analysis content quickly and supports efficient data analysis work.

[0006] A "user" refers to an individual or organization that makes analytical requests to the system using natural language.

[0007] "Natural language" refers to language used by humans on a daily basis, that is, language forms other than programming languages.

[0008] An "analysis request" refers to the instructions a user gives to the system in order to achieve a specific data analysis objective.

[0009] "Analysis" refers to the process of interpreting received input and extracting necessary information.

[0010] An "analysis flow" refers to a set of steps and processes necessary for performing data analysis.

[0011] "Generating as an image" refers to outputting the analysis flow as a digital image in order to visually represent it.

[0012] "Presentation" refers to the action of informing the user of generated information or images.

[0013] "Data analysis tools" refer to software and applications used for processing, analyzing, and visualizing data.

[0014] "Characteristics" refers to the specific functions and operational characteristics of a data analysis tool.

[0015] "Explanation text" refers to the text created to explain the generated image and its content.

Brief Explanation of Drawings

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

Embodiments for Carrying Out the Invention

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

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

[0019] In the following embodiments, a 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.

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

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention relates to a system that easily generates and assists users in understanding the workflows necessary for data analysis. This system automatically constructs an appropriate data analysis workflow based on natural language analysis requests entered by the user and presents it visually to the user, thereby streamlining the analysis process.

[0038] First, the user enters their analysis request in natural language through the terminal's chat interface. The terminal receives this input and sends the data to the server. The server is equipped with generative AI, which analyzes the input text to understand the analysis request. Specifically, the text analysis engine extracts important keywords and context from the natural language to identify the requirements.

[0039] The server constructs a data analysis flow based on the analysis results. This includes an algorithm that considers the characteristics of existing data analysis tools and determines a process that meets the user's needs. The determined flow is then generated as an image by a visualization engine. The generated flow image is presented in a visually easy-to-understand format, making it easily accessible to the user.

[0040] Furthermore, the server generates explanatory text accompanying the images. This text explains the purpose and role of each step in the analysis flow, supporting users in efficiently understanding the content. The system also optimizes itself according to the characteristics of the tools as needed, flexibly responding to diverse user requirements.

[0041] For example, if a user inputs "I want to calculate the average sales by region using sales data," the server uses its analysis engine to extract elements such as "sales data," "region," and "average sales," and builds a workflow that includes steps such as data import, filtering, grouping, and aggregation. The generated image and explanation are presented to the user, allowing them to easily understand and execute the workflow for data analysis that suits their needs. In this way, this system enables even users without specialized knowledge to perform data analysis quickly.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user enters their data analysis requests in natural language into the device's chat interface.

[0045] Step 2:

[0046] The terminal receives user input and sends that data to the server.

[0047] Step 3:

[0048] The server activates the generative AI to analyze the received input data.

[0049] Step 4:

[0050] The AI ​​within the server analyzes the input natural language and identifies the necessary elements of the analysis request. At this stage, important keywords and phrases are extracted from the text.

[0051] Step 5:

[0052] The server designs each step of the analysis flow based on the identified elements, taking into account the characteristics of existing data analysis tools.

[0053] Step 6:

[0054] The server runs a visualization engine to generate the designed analysis flow as a visual image.

[0055] Step 7:

[0056] The server combines the generated flow image with descriptive text about its contents to create a package for presentation to the user.

[0057] Step 8:

[0058] The terminal displays the flow image and explanatory text sent from the server to the user.

[0059] Step 9:

[0060] Based on the information provided, the user understands and executes the steps for the next analysis.

[0061] (Example 1)

[0062] 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."

[0063] When users perform information analysis, it is difficult for them to construct and understand appropriate data processing procedures. In particular, for users without specialized knowledge, visually understanding and grasping data analysis procedures is a significant challenge.

[0064] 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.

[0065] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying requirements based on the requests, and means for determining data processing procedures based on the identified requirements and generating them as visual representations. This makes it possible for users to easily understand and execute data analysis procedures even without specialized knowledge.

[0066] A "user" is an entity that uses an information system to input or request data.

[0067] "Natural language" refers to the forms of language that humans use on a daily basis, and is used to express requests for analysis, etc.

[0068] An "analysis request" is a request that specifies the purpose and conditions that a user seeks when analyzing information.

[0069] "Means" refer to the specific methods or functions used to achieve a particular objective.

[0070] "Analysis" is the process of interpreting given information and extracting useful information from it.

[0071] A "requirement" is a condition or standard that is necessary to achieve a specific objective.

[0072] A "data processing procedure" is a set of steps for properly organizing and analyzing information to obtain results that align with the objective.

[0073] "Visual representation" refers to methods of making information easier to understand by visualizing it using diagrams and images.

[0074] This invention aims to lower the barriers to information analysis for users and provide a system that allows for easy analysis. The system begins with the user inputting data-related requests in natural language. Users can input specific analysis requests using a chat interface on their device. These inputs can take the form of, for example, "I would like to know the average sales by region using last year's sales data."

[0075] The device sends the natural language analysis request received from the user to the server. The server uses a generative AI model to analyze the received text and identify requirements based on the user's request. In this analysis process, the text analysis engine works to extract important keywords and understand the context.

[0076] The server automatically determines the data processing procedure based on the analysis results. Here, it assembles the optimal analysis flow, taking into account the characteristics of existing data processing tools and methods. This determined flow is then converted into a visual representation by a visualization engine. This representation is sent to the terminal in a format that is easy for the user to understand.

[0077] The terminal displays visual representations and explanatory text sent from the server to the user. By referring to this, the user can easily understand how to process the data. Furthermore, if necessary, the server provides detailed explanations in text related to the generated analysis flow. These explanations clearly describe the purpose and role of each step, allowing the user to proceed with the specific analysis while reading them.

[0078] For example, if a user inputs "I want to calculate the average sales by region using sales data," the server uses its analysis engine to extract elements such as "sales data," "region," and "average sales," and then builds a workflow that incorporates processes such as data import, filtering, grouping, and aggregation. Ultimately, the user can understand the presented workflow and easily execute the specific steps necessary to achieve excellent data analysis.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The user operates the terminal and enters an analysis request in natural language into the chat interface. An example of this input is, "I want to calculate the average sales by region using sales data." The purpose here is to capture the user's needs as concrete text. Once this request is entered, the terminal prepares to send it to the server.

[0082] Step 2:

[0083] The terminal sends input text data from the user to the server. This transmission process uses an appropriate communication protocol to ensure the input data is transmitted securely and quickly. The output is the text of the analysis request that reaches the server.

[0084] Step 3:

[0085] The server passes the text of the received analysis request to a generating AI model for natural language processing. This analysis utilizes a text analysis engine to extract key keywords (e.g., sales data, region, average sales) from the input text. The input is the user's analysis request, and the output is a list of extracted keywords and requirements.

[0086] Step 4:

[0087] The server constructs a data processing procedure based on the analyzed keywords and requirements. This procedure includes steps such as importing, filtering, grouping, and aggregating the necessary data. The server optimizes this procedure and prepares it for visualization. The output is a visualized data processing flow that meets the user's requirements.

[0088] Step 5:

[0089] The server passes the constructed data processing flow to the visualization engine, which converts it into a visually easy-to-understand format. The output of this process is an image or diagram that the user can intuitively understand.

[0090] Step 6:

[0091] The server generates explanatory text for each step, along with the generated visual representation, and sends it to the terminal. The explanatory text details the purpose and role of each step, aiding user understanding. The output is a visual data processing flow and its explanatory text.

[0092] Step 7:

[0093] The terminal presents the user with visual representations and explanatory text received from the server. This allows the user to decide how to proceed with data analysis using the presented information. At this stage, the output is the information and instructions received by the user.

[0094] (Application Example 1)

[0095] 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."

[0096] In logistics centers and similar facilities, it is difficult for workers without specialized data analysis knowledge to perform real-time analysis of inventory and delivery patterns. Furthermore, current systems lack an intuitive interface for understanding efficient analysis flow data after voice input. To address this situation and improve work efficiency, it is necessary to provide effective solutions.

[0097] 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.

[0098] In this invention, the server includes means for acquiring user voice input and converting the acquired voice into text, means for acquiring data analysis processes based on the converted text, and means for displaying the acquired data analysis processes on a visual display device. This makes it possible for workers without specialized knowledge of data analysis to intuitively understand inventory management and delivery pattern analysis in a logistics center in real time, thereby improving work efficiency.

[0099] A "user" is an individual or legal entity that makes data analysis requests to the system through natural language or voice.

[0100] "Natural language" refers to written and spoken text expressed in the language that humans use on a daily basis, and is the format in which users input it into a system.

[0101] "Analysis request" refers to the wishes or instructions that a user communicates to the system for the purpose of analyzing data.

[0102] "Analysis" is the process by which a system understands the data it receives and extracts each element and meaning.

[0103] The "analysis process" refers to a series of procedures and steps involved in data analysis, which are automatically generated by the system.

[0104] "Visual representation" refers to showing the analysis process in an intuitive and easy-to-understand way using images and diagrams.

[0105] A "visual display device" is a device used to present visual representations to a user, and includes smart glasses and monitors.

[0106] The system for implementing this invention begins with a user using a visual display device such as smart glasses to make a data analysis request via voice. The server converts the user's voice input into text data using speech recognition software. The Python speech_recognition library is used for this conversion.

[0107] The server, equipped with a generative AI model, analyzes text data received from users. This analysis process uses natural language processing techniques to extract important keywords and context from the analyzed text. Based on the analysis results, the server automatically constructs data analysis processes. These processes can address tasks such as inventory optimization and delivery route analysis.

[0108] Users can view the generated visual representation through the visual display of their smart glasses. The display shows the analysis process in a visually easy-to-understand format, along with explanatory text about the purpose and role of each step.

[0109] For example, if a worker at a logistics center inputs via voice, "I want to analyze monthly shipping data and create a demand forecast for the next three months," the server will recognize elements such as "monthly," "shipping," and "demand forecast," and generate a corresponding analysis flow.

[0110] In this way, the system allows users to efficiently analyze data in real time and improve their operations, even without specialized knowledge.

[0111] An example of a prompt for a generating AI model is one that instructs it to visualize the data analysis flow when the input is, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The user inputs data analysis requests by voice through the microphone of smart glasses, which are a visual display device. The voice input might be something like, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0115] Step 2:

[0116] The device uses speech recognition software to convert the input speech into text data. In this process, the audio signal is converted into a digital format, and a string of text is generated. The output is the text, "I would like to analyze monthly shipment data to create a demand forecast for the next three months."

[0117] Step 3:

[0118] The server analyzes text data using a generative AI model. Keywords and important contextual information from the input text are extracted using natural language processing techniques. During this analysis stage, key elements such as "monthly," "shipments," and "demand forecast" are identified. These analyzed elements serve as the basis for constructing the data analysis process.

[0119] Step 4:

[0120] The server automatically constructs the data analysis process based on the extracted elements. This is done according to a pre-configured algorithm. The analysis flow best suited to the user's requirements is calculated, and the order of processes is determined accordingly. Specific data processing and calculations are then designed.

[0121] Step 5:

[0122] The server generates a visual representation of the constructed data analysis process and sends it to smart glasses. At this time, a generating AI model is used to shape the flow of each process as a visual diagram or chart. By displaying this on a visual display device, the user can intuitively understand the overall flow.

[0123] Step 6:

[0124] The server also generates and provides explanatory text related to the visual representation to the user. The generated text explains the purpose and role of each analysis step in detail, allowing the user to understand each point in the flow in detail. This explanation appears on the screen of the visual display device.

[0125] 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.

[0126] This invention relates to a system that integrates data analysis with user sentiment recognition to generate and present a more personalized analysis flow. This system assists the user in performing data analysis by easily generating the necessary steps and presenting them in an optimal format based on the user's sentiment.

[0127] The user enters analysis requests in natural language using a chat interface via their device. The device receives the user's text input and sends the data to the server. The server, which is equipped with a generative AI and an emotion engine, analyzes the entered analysis requests. The generative AI module extracts key elements from the analyzed text and identifies the requirements for the analysis flow. Simultaneously, the emotion engine recognizes the user's emotions and understands their emotional state.

[0128] The server determines the data analysis flow based on the analysis results and the output of the emotion engine. In doing so, it takes into account the characteristics of existing data analysis tools and constructs an appropriate flow tailored to the user's emotional state. For example, if the system detects that the user is tired, it can generate a simpler and more intuitive flow.

[0129] The generated analysis flow is produced as a visual image using a visualization engine. This image is presented to the user with a color scheme and format that matches the user's emotional state. Furthermore, the server creates descriptive text related to the generated image and provides emotion-sensitive feedback. This feedback explains the purpose and role of each step in the analysis flow, helping the user to efficiently understand its content.

[0130] For example, if a user inputs "I want to calculate the average sales by region using sales data" and expresses concern, the server will generate an interface that is as clear and reassuring as possible, providing instructions in simple steps. In this way, even users without specialized knowledge can perform efficient data analysis by utilizing an analysis flow that is tailored to their emotional state.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] Users enter their analysis requests in natural language via the terminal's chat interface.

[0134] Step 2:

[0135] The terminal receives user input and sends it to the server.

[0136] Step 3:

[0137] The server passes the received input data to the generating AI and begins the analysis.

[0138] Step 4:

[0139] The AI ​​within the server analyzes the input language and extracts the key elements and context of the analysis request.

[0140] Step 5:

[0141] In parallel, the server uses an emotion engine to analyze and identify the user's emotional state from the text input.

[0142] Step 6:

[0143] The server combines the requirements and emotional states obtained from the analysis to design the data analysis flow. In this process, the characteristics of existing data analysis tools and adjustments based on user emotions are taken into consideration.

[0144] Step 7:

[0145] The server launches a visualization engine to generate the designed data analysis flow as a visual image.

[0146] Step 8:

[0147] The server creates text descriptions related to the generated flow images and adds feedback tailored to the user's emotional state.

[0148] Step 9:

[0149] The server sends the flow image and explanatory text as a package to the terminal.

[0150] Step 10:

[0151] The device displays the received package and presents it to the user in an appropriate format. This allows the user to receive an analysis flow that takes their emotional state into consideration and prepares them to proceed to the next step.

[0152] (Example 2)

[0153] 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".

[0154] In the field of data analysis, there is a problem in that it is difficult for users without specialized knowledge to intuitively analyze data. Furthermore, depending on the user's emotional state, the analysis process can become stressful. To solve these problems, it is necessary to provide personalized analysis flows that take user emotions into consideration.

[0155] 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.

[0156] In this invention, the server includes means for receiving analysis requests entered by the user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, and means for recognizing the user's emotions and understanding their emotional state. This makes it possible to execute an optimal data analysis flow based on the user's requests and emotions and present it in a visually easy-to-understand format.

[0157] A "user" refers to a person who uses the system to make data analysis requests in natural language.

[0158] "Natural language" refers to the forms of language that humans use in everyday life, and is a free-form text that is not structured.

[0159] An "analysis request" refers to a user's wish or instruction to request specific data analysis through the system.

[0160] "Means" refers to a specific function or the specific methods and processes used to achieve that function.

[0161] "Analysis" refers to the act of examining received data and requests to identify their meaning and importance.

[0162] "Identifying requirements" refers to clarifying the necessary procedures and conditions based on user requests and inputs.

[0163] "Recognizing emotions" refers to the process of understanding a user's mental state and feelings from their written statements and behavior.

[0164] "Emotional state" refers to the psychological or emotional situation or condition that a user is experiencing.

[0165] A "data processing flow" refers to a series of steps and processes for performing data analysis, and is built based on defined requirements.

[0166] "Visual format" refers to a format in which information is represented using visual elements such as shapes and images.

[0167] "Color tone" refers to the way in which visual elements are expressed in terms of color, and is used to convey specific emotions or impressions.

[0168] "Format" refers to the structured form or shape of data or information.

[0169] "Feedback" refers to the results and opinions that a system provides to a user, and may include information for improvement.

[0170] This system is implemented by combining multiple technologies to facilitate users making data analysis requests in natural language. The system mainly consists of terminals and servers, which work together to perform their functions.

[0171] Users access the chat interface through their device and input using natural language. For example, a user can enter an analytical request such as, "I want to forecast sales for the next quarter." This input is then sent to the server by the device.

[0172] The server is equipped with a generative AI model and an emotion engine. After receiving an analysis request, this software analyzes the request. The generative AI model extracts key elements from the input text and identifies the requirements for the analysis flow. This clarifies the analysis procedure best suited to the user's needs.

[0173] In parallel, the emotion engine recognizes emotions from the user's input text and monitors their emotional state. This process allows the server to understand the user's psychological state and build emotion-based data analysis flows.

[0174] In designing analytical flows, the server takes into account the characteristics of existing data analysis software. For example, common tools for visually analyzing data, such as Tableau or Power BI, may be used. This allows for the design of flows that leverage standardized data processing methods while being optimized for the individual emotional state of the user.

[0175] The designed analysis flow is generated as a visual image using a visualization engine. This image is presented to the user via their device, with a color scheme and format tailored to the user's emotional state. This allows the user to intuitively grasp the overall picture of the analysis.

[0176] Furthermore, the server generates descriptive text related to the generated images and provides sentiment-based feedback. This feedback helps users efficiently understand the purpose and process of each step in the analysis flow.

[0177] As a concrete example, prompt statements are used as follows:

[0178] "I want to make sales forecasts for the next quarter, but I don't know which data to use. I need help."

[0179] This system allows even users without specialized knowledge to intuitively perform complex data analysis processes.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The user accesses a chat interface through their device and enters an analysis request in natural language. This request indicates the purpose of the data analysis the user wishes to achieve. The input data is in natural language text format. This input is received by the device and sent to the server.

[0183] Step 2:

[0184] The server passes text data sent from the terminal to a generative AI model for analysis. The generative AI model processes the natural language analysis request and extracts keywords and important elements. This extraction process allows the server to identify the requirements for the analysis flow. The input is text data, and the output is structured data containing the extracted requirements.

[0185] Step 3:

[0186] The server simultaneously uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions from text to understand the user's emotional state. This process is performed using NLP techniques, and metadata related to emotions is output. The input is text data, and the output is data indicating the emotional state.

[0187] Step 4:

[0188] The server designs a data analysis flow based on the analyzed requests and emotional states. This design takes into account generative AI models and existing data analysis techniques. For example, an intuitively operable flow is constructed. The inputs are structured data and emotional state data, and the output is a visualized analysis flow.

[0189] Step 5:

[0190] The server constructs the analysis flow generated using the visualization engine as a visual image. This image is expressed in emotionally appropriate colors and formats and sent to the terminal. The input is the designed analysis flow, and the output is the visualized image.

[0191] Step 6:

[0192] The server generates descriptive text related to the generated images and sends it to the user. The descriptive text clarifies the purpose and intent of each step. The input is the visualized flow and emotional state data, and the output is the descriptive text for the user.

[0193] This series of steps allows users to intuitively understand and perform data analysis.

[0194] (Application Example 2)

[0195] 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".

[0196] In e-commerce, personalized recommendations based on user preferences and emotions are crucial for improving the user's purchasing experience. However, conventional systems lack sufficient means to present visual information and recommend products in a way that takes user emotions into account. Therefore, there is a need for a system that provides purchasing support that reflects the user's emotional state in real time.

[0197] 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.

[0198] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, means for determining a data analysis flow based on the identified requirements and generating it as a visual representation, means for recognizing the user's emotional state based on the generated visual representation and providing personalized recommended items, and means for presenting the generated visual representation to the user. This enables personalized purchase support that takes the user's emotions into consideration.

[0199] "Natural language" refers to the language that humans use on a daily basis, and is a text data format that can be processed by computers.

[0200] An "analysis request" is a request that indicates the type of analysis and results that the user wants to perform on the data.

[0201] An "analysis flow" refers to a series of steps and processes used to carry out data analysis.

[0202] "Visual representation" refers to a format for presenting data and information visually, including graphs and charts.

[0203] "Emotional state" refers to the emotional state a user is experiencing at a particular point in time, and includes feelings such as joy, sadness, and fatigue.

[0204] "Personalized recommendations" refer to recommendations for products and services selected based on the user's individual preferences and emotional state.

[0205] The system for implementing this invention is realized using a user's device (e.g., a smartphone or smart glasses) and a powerful server. First, the user inputs their analysis request in natural language using the device. This input is transmitted to the server via an interface installed on the terminal.

[0206] On the server, a generative AI model is used to analyze the received natural language input. During the analysis process, the server extracts user requests and identifies an analysis flow based on those requests. Furthermore, it prepares the corresponding data analysis flow using the provided database and external data sources. To take user emotions into consideration, an emotion recognition engine recognizes the emotional state from the user's facial expressions and voice. Based on this information, the server generates optimized visual representations and personalized recommendations.

[0207] For example, if a user enters "I'm looking for a Mother's Day gift, but there are too many options and I'm worried about not being able to choose. Please recommend something simple and nice," the server will analyze this request and, taking into account the user's anxiety, provide a reassuring and intuitive interface. Based on the generated visual representation, appropriate gift suggestions will be made.

[0208] This system allows users to have a personalized shopping experience that takes their emotions into consideration. These processes performed by the server enable users to make efficient and satisfying purchases.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] Users input analysis requests in natural language through the interface of their smart devices. This input is sent from the device to the server as text data. The input includes specific wishes and emotional expressions.

[0212] Step 2:

[0213] The server analyzes the received text data. Here, it utilizes a generative AI model to extract important elements from the input. For example, it analyzes requests such as "I'm looking for a Mother's Day gift." It also identifies the user's emotional state from their expressions.

[0214] Step 3:

[0215] The emotion recognition engine analyzes user input and additional emotional data (such as facial expressions and tone of voice) to evaluate the user's emotional state. This evaluation is output as emotional labels such as feeling safe or anxious.

[0216] Step 4:

[0217] The server identifies the data analysis flow based on the extracted elements and emotional state, and generates an appropriate visual representation. In this process, if the user is seeking a sense of security, a brightly colored interface will be generated.

[0218] Step 5:

[0219] Based on the generated visual representation, the server determines personalized recommended items. In this process, it retrieves appropriate product information from the database and outputs a list of products that correspond to the user's emotions.

[0220] Step 6:

[0221] Finally, personalized recommended items, along with the generated visual representation, are sent to the device and presented to the user. This allows the user to receive choices that are relevant to their emotions.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] This invention relates to a system that easily generates and assists users in understanding the workflows necessary for data analysis. This system automatically constructs an appropriate data analysis workflow based on natural language analysis requests entered by the user and presents it visually to the user, thereby streamlining the analysis process.

[0239] First, the user enters their analysis request in natural language through the terminal's chat interface. The terminal receives this input and sends the data to the server. The server is equipped with generative AI, which analyzes the input text to understand the analysis request. Specifically, the text analysis engine extracts important keywords and context from the natural language to identify the requirements.

[0240] The server constructs a data analysis flow based on the analysis results. This includes an algorithm that considers the characteristics of existing data analysis tools and determines a process that meets the user's needs. The determined flow is then generated as an image by a visualization engine. The generated flow image is presented in a visually easy-to-understand format, making it easily accessible to the user.

[0241] Furthermore, the server generates explanatory text accompanying the images. This text explains the purpose and role of each step in the analysis flow, supporting users in efficiently understanding the content. The system also optimizes itself according to the characteristics of the tools as needed, flexibly responding to diverse user requirements.

[0242] For example, if a user inputs "I want to calculate the average sales by region using sales data," the server uses its analysis engine to extract elements such as "sales data," "region," and "average sales," and builds a workflow that includes steps such as data import, filtering, grouping, and aggregation. The generated image and explanation are presented to the user, allowing them to easily understand and execute the workflow for data analysis that suits their needs. In this way, this system enables even users without specialized knowledge to perform data analysis quickly.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The user enters their data analysis requests in natural language into the device's chat interface.

[0246] Step 2:

[0247] The terminal receives user input and sends that data to the server.

[0248] Step 3:

[0249] The server activates the generative AI to analyze the received input data.

[0250] Step 4:

[0251] The AI ​​within the server analyzes the input natural language and identifies the necessary elements of the analysis request. At this stage, important keywords and phrases are extracted from the text.

[0252] Step 5:

[0253] The server designs each step of the analysis flow based on the identified elements, taking into account the characteristics of existing data analysis tools.

[0254] Step 6:

[0255] The server runs a visualization engine to generate the designed analysis flow as a visual image.

[0256] Step 7:

[0257] The server combines the generated flow image with descriptive text about its contents to create a package for presentation to the user.

[0258] Step 8:

[0259] The terminal displays the flow image and explanatory text sent from the server to the user.

[0260] Step 9:

[0261] Based on the information provided, the user understands and executes the steps for the next analysis.

[0262] (Example 1)

[0263] 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."

[0264] When users perform information analysis, it is difficult for them to construct and understand appropriate data processing procedures. In particular, for users without specialized knowledge, visually understanding and grasping data analysis procedures is a significant challenge.

[0265] 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.

[0266] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying requirements based on the requests, and means for determining data processing procedures based on the identified requirements and generating them as visual representations. This makes it possible for users to easily understand and execute data analysis procedures even without specialized knowledge.

[0267] A "user" is an entity that uses an information system to input or request data.

[0268] "Natural language" refers to the forms of language that humans use on a daily basis, and is used to express requests for analysis, etc.

[0269] An "analysis request" is a request that specifies the purpose and conditions that a user seeks when analyzing information.

[0270] "Means" refer to the specific methods or functions used to achieve a particular objective.

[0271] "Analysis" is the process of interpreting given information and extracting useful information from it.

[0272] A "requirement" is a condition or standard that is necessary to achieve a specific objective.

[0273] A "data processing procedure" is a set of steps for properly organizing and analyzing information to obtain results that align with the objective.

[0274] "Visual representation" refers to methods of making information easier to understand by visualizing it using diagrams and images.

[0275] This invention aims to lower the barriers to information analysis for users and provide a system that allows for easy analysis. The system begins with the user inputting data-related requests in natural language. Users can input specific analysis requests using a chat interface on their device. These inputs can take the form of, for example, "I would like to know the average sales by region using last year's sales data."

[0276] The device sends the natural language analysis request received from the user to the server. The server uses a generative AI model to analyze the received text and identify requirements based on the user's request. In this analysis process, the text analysis engine works to extract important keywords and understand the context.

[0277] The server automatically determines the data processing procedure based on the analysis results. Here, it assembles the optimal analysis flow, taking into account the characteristics of existing data processing tools and methods. This determined flow is then converted into a visual representation by a visualization engine. This representation is sent to the terminal in a format that is easy for the user to understand.

[0278] The terminal presents the visual representation and explanatory text sent from the server to the user. By referring to this, the user can easily understand how to process the data. Furthermore, if necessary, the server provides detailed explanations related to the generated analysis flow as text. In this explanation, the purpose and role of each procedure are clearly stated, and the user can move on to performing specific analysis while reading it.

[0279] As a specific example, when the user inputs "I want to calculate the average sales for each region using sales data", the server utilizes the analysis engine to extract elements such as "sales data", "region", and "average sales", and constructs a flow incorporating processes such as data import, filtering, grouping, and aggregation based on these. Finally, the user can understand the presented flow and easily execute the specific steps to achieve excellent data analysis.

[0280] The flow of the specific process in Example 1 will be described using FIG. 11.

[0281] Step 1:

[0282] The user operates the terminal and inputs an analysis request in natural language into the chat interface. An example of this input is "I want to calculate the average sales for each region using sales data". Here, the purpose is to capture the user's needs as specific text. When this request is input, the terminal prepares to send it to the server.

[0283] Step 2:

[0284] The terminal sends the input text data from the user to the server. In this transmission process, an appropriate communication protocol is used to ensure that the input data is sent safely and quickly. The output is the text of the analysis request that reaches the server.

[0285] Step 3:

[0286] The server passes the received analysis request text to the generative AI model and performs natural language analysis. In this analysis, the text analysis engine works to extract important keywords (e.g., sales data, region, average sales) from the input text. The input is the user's analysis request, and the output is a list of the extracted keywords and requirements.

[0287] Step 4:

[0288] Based on the analyzed keywords and requirements, the server constructs a data processing procedure. This procedure includes steps such as importing, filtering, grouping, and aggregating the necessary data. The server optimizes this procedure and prepares it for visualization. The output is a visualizable data processing flow that meets the user's requirements.

[0289] Step 5:

[0290] The server passes the constructed data processing flow to the visualization engine and converts it into a visually understandable format. The output of this process is an image or chart that the user can intuitively understand.

[0291] Step 6:

[0292] The server generates explanatory text for each step along with the generated visual representation and sends it to the terminal. The explanatory text describes in detail the purpose and role of each procedure, helping the user to understand. The output is the visual data processing flow and its explanatory text.

[0293] Step 7:

[0294] The terminal presents the visual representation and explanatory text received from the server to the user. This allows the user to determine how to specifically proceed with the data analysis using the presented information. At this stage, the output is the information and instructions that the user receives.

[0295] (Application Example 1)

[0296] 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 glasses 214 will be referred to as the "terminal."

[0297] In logistics centers and similar facilities, it is difficult for workers without specialized data analysis knowledge to perform real-time analysis of inventory and delivery patterns. Furthermore, current systems lack an intuitive interface for understanding efficient analysis flow data after voice input. To address this situation and improve work efficiency, it is necessary to provide effective solutions.

[0298] 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.

[0299] In this invention, the server includes means for acquiring user voice input and converting the acquired voice into text, means for acquiring data analysis processes based on the converted text, and means for displaying the acquired data analysis processes on a visual display device. This makes it possible for workers without specialized knowledge of data analysis to intuitively understand inventory management and delivery pattern analysis in a logistics center in real time, thereby improving work efficiency.

[0300] A "user" is an individual or legal entity that makes data analysis requests to the system through natural language or voice.

[0301] "Natural language" refers to written and spoken text expressed in the language that humans use on a daily basis, and is the format in which users input it into a system.

[0302] "Analysis request" refers to the wishes or instructions that a user communicates to the system for the purpose of analyzing data.

[0303] "Analysis" is the process by which a system understands the data it receives and extracts each element and meaning.

[0304] The "analysis process" refers to a series of procedures and steps in data analysis, which are automatically constructed by the system.

[0305] The "visual representation" is to show the analysis process as images or diagrams in a form that is intuitive and easy for users to understand.

[0306] The "visual display device" is a device used to present the visual representation to the user, including smart glasses, monitors, etc.

[0307] The system for implementing this invention begins when the user uses a visual display device such as smart glasses to make a data analysis request through voice. The server uses speech recognition software to convert the user's voice input into text data. For the conversion, libraries such as the speech_recognition library in Python are utilized.

[0308] The server is equipped with a generative AI model and analyzes the text data received from the user. In this analysis process, natural language processing technology is used to extract important keywords and context from the analyzed text. Based on the analysis results, the server automatically constructs the data analysis process. In this process, processes corresponding to, for example, inventory optimization and delivery route analysis are set.

[0309] The user can view the generated visual representation through the visual display device of the smart glasses. On the display, the analysis process is shown in a visually understandable form, and explanatory text regarding the purpose and role of each step is also displayed.

[0310] As a specific example, when an operator at a logistics center inputs "I want to analyze the monthly shipping data and create a demand forecast for the next three months" by voice, the server recognizes elements such as "monthly", "shipping", and "demand forecast", and generates the corresponding analysis flow.

[0311] In this way, the system allows users to efficiently analyze data in real time and improve their operations, even without specialized knowledge.

[0312] An example of a prompt for a generating AI model is one that instructs it to visualize the data analysis flow when the input is, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The user inputs data analysis requests by voice through the microphone of smart glasses, which are a visual display device. The voice input might be something like, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0316] Step 2:

[0317] The device uses speech recognition software to convert the input speech into text data. In this process, the audio signal is converted into a digital format, and a string of text is generated. The output is the text, "I would like to analyze monthly shipment data to create a demand forecast for the next three months."

[0318] Step 3:

[0319] The server analyzes text data using a generative AI model. Keywords and important contextual information from the input text are extracted using natural language processing techniques. During this analysis stage, key elements such as "monthly," "shipments," and "demand forecast" are identified. These analyzed elements serve as the basis for constructing the data analysis process.

[0320] Step 4:

[0321] The server automatically constructs the data analysis process based on the extracted elements. This is done according to a pre-configured algorithm. The analysis flow best suited to the user's requirements is calculated, and the order of processes is determined accordingly. Specific data processing and calculations are then designed.

[0322] Step 5:

[0323] The server generates a visual representation of the constructed data analysis process and sends it to smart glasses. At this time, a generating AI model is used to shape the flow of each process as a visual diagram or chart. By displaying this on a visual display device, the user can intuitively understand the overall flow.

[0324] Step 6:

[0325] The server also generates and provides explanatory text related to the visual representation to the user. The generated text explains the purpose and role of each analysis step in detail, allowing the user to understand each point in the flow in detail. This explanation appears on the screen of the visual display device.

[0326] 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.

[0327] This invention relates to a system that integrates data analysis with user sentiment recognition to generate and present a more personalized analysis flow. This system assists the user in performing data analysis by easily generating the necessary steps and presenting them in an optimal format based on the user's sentiment.

[0328] The user enters analysis requests in natural language using a chat interface via their device. The device receives the user's text input and sends the data to the server. The server, which is equipped with a generative AI and an emotion engine, analyzes the entered analysis requests. The generative AI module extracts key elements from the analyzed text and identifies the requirements for the analysis flow. Simultaneously, the emotion engine recognizes the user's emotions and understands their emotional state.

[0329] The server determines the data analysis flow based on the analysis results and the output of the emotion engine. In doing so, it takes into account the characteristics of existing data analysis tools and constructs an appropriate flow tailored to the user's emotional state. For example, if the system detects that the user is tired, it can generate a simpler and more intuitive flow.

[0330] The generated analysis flow is produced as a visual image using a visualization engine. This image is presented to the user with a color scheme and format that matches the user's emotional state. Furthermore, the server creates descriptive text related to the generated image and provides emotion-sensitive feedback. This feedback explains the purpose and role of each step in the analysis flow, helping the user to efficiently understand its content.

[0331] For example, if a user inputs "I want to calculate the average sales by region using sales data" and expresses concern, the server will generate an interface that is as clear and reassuring as possible, providing instructions in simple steps. In this way, even users without specialized knowledge can perform efficient data analysis by utilizing an analysis flow that is tailored to their emotional state.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] Users enter their analysis requests in natural language via the terminal's chat interface.

[0335] Step 2:

[0336] The terminal receives user input and sends it to the server.

[0337] Step 3:

[0338] The server passes the received input data to the generating AI and begins the analysis.

[0339] Step 4:

[0340] The AI ​​within the server analyzes the input language and extracts the key elements and context of the analysis request.

[0341] Step 5:

[0342] In parallel, the server uses an emotion engine to analyze and identify the user's emotional state from the text input.

[0343] Step 6:

[0344] The server combines the requirements and emotional states obtained from the analysis to design the data analysis flow. In this process, the characteristics of existing data analysis tools and adjustments based on user emotions are taken into consideration.

[0345] Step 7:

[0346] The server launches a visualization engine to generate the designed data analysis flow as a visual image.

[0347] Step 8:

[0348] The server creates text descriptions related to the generated flow images and adds feedback tailored to the user's emotional state.

[0349] Step 9:

[0350] The server sends the flow image and explanatory text as a package to the terminal.

[0351] Step 10:

[0352] The device displays the received package and presents it to the user in an appropriate format. This allows the user to receive an analysis flow that takes their emotional state into consideration and prepares them to proceed to the next step.

[0353] (Example 2)

[0354] 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".

[0355] In the field of data analysis, there is a problem in that it is difficult for users without specialized knowledge to intuitively analyze data. Furthermore, depending on the user's emotional state, the analysis process can become stressful. To solve these problems, it is necessary to provide personalized analysis flows that take user emotions into consideration.

[0356] 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.

[0357] In this invention, the server includes means for receiving analysis requests entered by the user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, and means for recognizing the user's emotions and understanding their emotional state. This makes it possible to execute an optimal data analysis flow based on the user's requests and emotions and present it in a visually easy-to-understand format.

[0358] A "user" refers to a person who uses the system to make data analysis requests in natural language.

[0359] "Natural language" refers to the forms of language that humans use in everyday life, and is a free-form text that is not structured.

[0360] An "analysis request" refers to a user's wish or instruction to request specific data analysis through the system.

[0361] "Means" refers to a specific function or the specific methods and processes used to achieve that function.

[0362] "Analysis" refers to the act of examining received data and requests to identify their meaning and importance.

[0363] "Identifying requirements" refers to clarifying the necessary procedures and conditions based on user requests and inputs.

[0364] "Recognizing emotions" refers to the process of understanding a user's mental state and feelings from their written statements and behavior.

[0365] "Emotional state" refers to the psychological or emotional situation or condition that a user is experiencing.

[0366] A "data processing flow" refers to a series of steps and processes for performing data analysis, and is built based on defined requirements.

[0367] "Visual format" refers to a format in which information is represented using visual elements such as shapes and images.

[0368] "Color tone" refers to the way in which visual elements are expressed in terms of color, and is used to convey specific emotions or impressions.

[0369] "Format" refers to the structured form or shape of data or information.

[0370] "Feedback" refers to the results and opinions that a system provides to a user, and may include information for improvement.

[0371] This system is implemented by combining multiple technologies to facilitate users making data analysis requests in natural language. The system mainly consists of terminals and servers, which work together to perform their functions.

[0372] Users access the chat interface through their device and input using natural language. For example, a user can enter an analytical request such as, "I want to forecast sales for the next quarter." This input is then sent to the server by the device.

[0373] The server is equipped with a generative AI model and an emotion engine. After receiving an analysis request, this software analyzes the request. The generative AI model extracts key elements from the input text and identifies the requirements for the analysis flow. This clarifies the analysis procedure best suited to the user's needs.

[0374] In parallel, the emotion engine recognizes emotions from the user's input text and monitors their emotional state. This process allows the server to understand the user's psychological state and build emotion-based data analysis flows.

[0375] In designing analytical flows, the server takes into account the characteristics of existing data analysis software. For example, common tools for visually analyzing data, such as Tableau or Power BI, may be used. This allows for the design of flows that leverage standardized data processing methods while being optimized for the individual emotional state of the user.

[0376] The designed analysis flow is generated as a visual image using a visualization engine. This image is presented to the user via their device, with a color scheme and format tailored to the user's emotional state. This allows the user to intuitively grasp the overall picture of the analysis.

[0377] Furthermore, the server generates descriptive text related to the generated images and provides sentiment-based feedback. This feedback helps users efficiently understand the purpose and process of each step in the analysis flow.

[0378] As a concrete example, prompt statements are used as follows:

[0379] "I want to make sales forecasts for the next quarter, but I don't know which data to use. I need help."

[0380] This system allows even users without specialized knowledge to intuitively perform complex data analysis processes.

[0381] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0382] Step 1:

[0383] The user accesses a chat interface through their device and enters an analysis request in natural language. This request indicates the purpose of the data analysis the user wishes to achieve. The input data is in natural language text format. This input is received by the device and sent to the server.

[0384] Step 2:

[0385] The server passes text data sent from the terminal to a generative AI model for analysis. The generative AI model processes the natural language analysis request and extracts keywords and important elements. This extraction process allows the server to identify the requirements for the analysis flow. The input is text data, and the output is structured data containing the extracted requirements.

[0386] Step 3:

[0387] The server simultaneously uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions from text to understand the user's emotional state. This process is performed using NLP techniques, and metadata related to emotions is output. The input is text data, and the output is data indicating the emotional state.

[0388] Step 4:

[0389] The server designs a data analysis flow based on the analyzed requests and emotional states. This design takes into account generative AI models and existing data analysis techniques. For example, an intuitively operable flow is constructed. The inputs are structured data and emotional state data, and the output is a visualized analysis flow.

[0390] Step 5:

[0391] The server constructs the analysis flow generated using the visualization engine as a visual image. This image is expressed in emotionally appropriate colors and formats and sent to the terminal. The input is the designed analysis flow, and the output is the visualized image.

[0392] Step 6:

[0393] The server generates descriptive text related to the generated images and sends it to the user. The descriptive text clarifies the purpose and intent of each step. The input is the visualized flow and emotional state data, and the output is the descriptive text for the user.

[0394] This series of steps allows users to intuitively understand and perform data analysis.

[0395] (Application Example 2)

[0396] 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 will be referred to as the "terminal."

[0397] In e-commerce, personalized recommendations based on user preferences and emotions are crucial for improving the user's purchasing experience. However, conventional systems lack sufficient means to present visual information and recommend products in a way that takes user emotions into account. Therefore, there is a need for a system that provides purchasing support that reflects the user's emotional state in real time.

[0398] 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.

[0399] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, means for determining a data analysis flow based on the identified requirements and generating it as a visual representation, means for recognizing the user's emotional state based on the generated visual representation and providing personalized recommended items, and means for presenting the generated visual representation to the user. This enables personalized purchase support that takes the user's emotions into consideration.

[0400] "Natural language" refers to the language that humans use on a daily basis, and is a text data format that can be processed by computers.

[0401] An "analysis request" is a request that indicates the type of analysis and results that the user wants to perform on the data.

[0402] An "analysis flow" refers to a series of steps and processes used to carry out data analysis.

[0403] "Visual representation" refers to a format for presenting data and information visually, including graphs and charts.

[0404] "Emotional state" refers to the emotional state a user is experiencing at a particular point in time, and includes feelings such as joy, sadness, and fatigue.

[0405] "Personalized recommendations" refer to recommendations for products and services selected based on the user's individual preferences and emotional state.

[0406] The system for implementing this invention is realized using a user's device (e.g., a smartphone or smart glasses) and a powerful server. First, the user inputs their analysis request in natural language using the device. This input is transmitted to the server via an interface installed on the terminal.

[0407] On the server, a generative AI model is used to analyze the received natural language input. During the analysis process, the server extracts user requests and identifies an analysis flow based on those requests. Furthermore, it prepares the corresponding data analysis flow using the provided database and external data sources. To take user emotions into consideration, an emotion recognition engine recognizes the emotional state from the user's facial expressions and voice. Based on this information, the server generates optimized visual representations and personalized recommendations.

[0408] For example, if a user enters "I'm looking for a Mother's Day gift, but there are too many options and I'm worried about not being able to choose. Please recommend something simple and nice," the server will analyze this request and, taking into account the user's anxiety, provide a reassuring and intuitive interface. Based on the generated visual representation, appropriate gift suggestions will be made.

[0409] This system allows users to have a personalized shopping experience that takes their emotions into consideration. These processes performed by the server enable users to make efficient and satisfying purchases.

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] Users input analysis requests in natural language through the interface of their smart devices. This input is sent from the device to the server as text data. The input includes specific wishes and emotional expressions.

[0413] Step 2:

[0414] The server analyzes the received text data. Here, it utilizes a generative AI model to extract important elements from the input. For example, it analyzes requests such as "I'm looking for a Mother's Day gift." It also identifies the user's emotional state from their expressions.

[0415] Step 3:

[0416] The emotion recognition engine analyzes user input and additional emotional data (such as facial expressions and tone of voice) to evaluate the user's emotional state. This evaluation is output as emotional labels such as feeling safe or anxious.

[0417] Step 4:

[0418] The server identifies the data analysis flow based on the extracted elements and emotional state, and generates an appropriate visual representation. In this process, if the user is seeking a sense of security, a brightly colored interface will be generated.

[0419] Step 5:

[0420] Based on the generated visual representation, the server determines personalized recommended items. In this process, it retrieves appropriate product information from the database and outputs a list of products that correspond to the user's emotions.

[0421] Step 6:

[0422] Finally, personalized recommended items, along with the generated visual representation, are sent to the device and presented to the user. This allows the user to receive choices that are relevant to their emotions.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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".

[0439] This invention relates to a system that easily generates and assists users in understanding the workflows necessary for data analysis. This system automatically constructs an appropriate data analysis workflow based on natural language analysis requests entered by the user and presents it visually to the user, thereby streamlining the analysis process.

[0440] First, the user enters their analysis request in natural language through the terminal's chat interface. The terminal receives this input and sends the data to the server. The server is equipped with generative AI, which analyzes the input text to understand the analysis request. Specifically, the text analysis engine extracts important keywords and context from the natural language to identify the requirements.

[0441] The server constructs a data analysis flow based on the analysis results. This includes an algorithm that considers the characteristics of existing data analysis tools and determines a process that meets the user's needs. The determined flow is then generated as an image by a visualization engine. The generated flow image is presented in a visually easy-to-understand format, making it easily accessible to the user.

[0442] Furthermore, the server generates explanatory text accompanying the images. This text explains the purpose and role of each step in the analysis flow, supporting users in efficiently understanding the content. The system also optimizes itself according to the characteristics of the tools as needed, flexibly responding to diverse user requirements.

[0443] For example, if a user inputs "I want to calculate the average sales by region using sales data," the server uses its analysis engine to extract elements such as "sales data," "region," and "average sales," and builds a workflow that includes steps such as data import, filtering, grouping, and aggregation. The generated image and explanation are presented to the user, allowing them to easily understand and execute the workflow for data analysis that suits their needs. In this way, this system enables even users without specialized knowledge to perform data analysis quickly.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The user enters their data analysis requests in natural language into the device's chat interface.

[0447] Step 2:

[0448] The terminal receives user input and sends that data to the server.

[0449] Step 3:

[0450] The server activates the generative AI to analyze the received input data.

[0451] Step 4:

[0452] The AI ​​within the server analyzes the input natural language and identifies the necessary elements of the analysis request. At this stage, important keywords and phrases are extracted from the text.

[0453] Step 5:

[0454] The server designs each step of the analysis flow based on the identified elements, taking into account the characteristics of existing data analysis tools.

[0455] Step 6:

[0456] The server runs a visualization engine to generate the designed analysis flow as a visual image.

[0457] Step 7:

[0458] The server combines the generated flow image with descriptive text about its contents to create a package for presentation to the user.

[0459] Step 8:

[0460] The terminal displays the flow image and explanatory text sent from the server to the user.

[0461] Step 9:

[0462] Based on the information provided, the user understands and executes the steps for the next analysis.

[0463] (Example 1)

[0464] 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."

[0465] When users perform information analysis, it is difficult for them to construct and understand appropriate data processing procedures. In particular, for users without specialized knowledge, visually understanding and grasping data analysis procedures is a significant challenge.

[0466] 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.

[0467] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying requirements based on the requests, and means for determining data processing procedures based on the identified requirements and generating them as visual representations. This makes it possible for users to easily understand and execute data analysis procedures even without specialized knowledge.

[0468] A "user" is an entity that uses an information system to input or request data.

[0469] "Natural language" refers to the forms of language that humans use on a daily basis, and is used to express requests for analysis, etc.

[0470] An "analysis request" is a request that specifies the purpose and conditions that a user seeks when analyzing information.

[0471] "Means" refer to the specific methods or functions used to achieve a particular objective.

[0472] "Analysis" is the process of interpreting given information and extracting useful information from it.

[0473] A "requirement" is a condition or standard that is necessary to achieve a specific objective.

[0474] A "data processing procedure" is a set of steps for properly organizing and analyzing information to obtain results that align with the objective.

[0475] "Visual representation" refers to methods of making information easier to understand by visualizing it using diagrams and images.

[0476] This invention aims to lower the barriers to information analysis for users and provide a system that allows for easy analysis. The system begins with the user inputting data-related requests in natural language. Users can input specific analysis requests using a chat interface on their device. These inputs can take the form of, for example, "I would like to know the average sales by region using last year's sales data."

[0477] The device sends the natural language analysis request received from the user to the server. The server uses a generative AI model to analyze the received text and identify requirements based on the user's request. In this analysis process, the text analysis engine works to extract important keywords and understand the context.

[0478] The server automatically determines the data processing procedure based on the analysis results. Here, it assembles the optimal analysis flow, taking into account the characteristics of existing data processing tools and methods. This determined flow is then converted into a visual representation by a visualization engine. This representation is sent to the terminal in a format that is easy for the user to understand.

[0479] The terminal displays visual representations and explanatory text sent from the server to the user. By referring to this, the user can easily understand how to process the data. Furthermore, if necessary, the server provides detailed explanations in text related to the generated analysis flow. These explanations clearly describe the purpose and role of each step, allowing the user to proceed with the specific analysis while reading them.

[0480] For example, if a user inputs "I want to calculate the average sales by region using sales data," the server uses its analysis engine to extract elements such as "sales data," "region," and "average sales," and then builds a workflow that incorporates processes such as data import, filtering, grouping, and aggregation. Ultimately, the user can understand the presented workflow and easily execute the specific steps necessary to achieve excellent data analysis.

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] The user operates the terminal and enters an analysis request in natural language into the chat interface. An example of this input is, "I want to calculate the average sales by region using sales data." The purpose here is to capture the user's needs as concrete text. Once this request is entered, the terminal prepares to send it to the server.

[0484] Step 2:

[0485] The terminal sends input text data from the user to the server. This transmission process uses an appropriate communication protocol to ensure the input data is transmitted securely and quickly. The output is the text of the analysis request that reaches the server.

[0486] Step 3:

[0487] The server passes the text of the received analysis request to a generating AI model for natural language processing. This analysis utilizes a text analysis engine to extract key keywords (e.g., sales data, region, average sales) from the input text. The input is the user's analysis request, and the output is a list of extracted keywords and requirements.

[0488] Step 4:

[0489] The server constructs a data processing procedure based on the analyzed keywords and requirements. This procedure includes steps such as importing, filtering, grouping, and aggregating the necessary data. The server optimizes this procedure and prepares it for visualization. The output is a visualized data processing flow that meets the user's requirements.

[0490] Step 5:

[0491] The server passes the constructed data processing flow to the visualization engine, which converts it into a visually easy-to-understand format. The output of this process is an image or diagram that the user can intuitively understand.

[0492] Step 6:

[0493] The server generates explanatory text for each step, along with the generated visual representation, and sends it to the terminal. The explanatory text details the purpose and role of each step, aiding user understanding. The output is a visual data processing flow and its explanatory text.

[0494] Step 7:

[0495] The terminal presents the user with visual representations and explanatory text received from the server. This allows the user to decide how to proceed with data analysis using the presented information. At this stage, the output is the information and instructions received by the user.

[0496] (Application Example 1)

[0497] 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."

[0498] In logistics centers and similar facilities, it is difficult for workers without specialized data analysis knowledge to perform real-time analysis of inventory and delivery patterns. Furthermore, current systems lack an intuitive interface for understanding efficient analysis flow data after voice input. To address this situation and improve work efficiency, it is necessary to provide effective solutions.

[0499] 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.

[0500] In this invention, the server includes means for acquiring user voice input and converting the acquired voice into text, means for acquiring data analysis processes based on the converted text, and means for displaying the acquired data analysis processes on a visual display device. This makes it possible for workers without specialized knowledge of data analysis to intuitively understand inventory management and delivery pattern analysis in a logistics center in real time, thereby improving work efficiency.

[0501] A "user" is an individual or legal entity that makes data analysis requests to the system through natural language or voice.

[0502] "Natural language" refers to written and spoken text expressed in the language that humans use on a daily basis, and is the format in which users input it into a system.

[0503] "Analysis request" refers to the wishes or instructions that a user communicates to the system for the purpose of analyzing data.

[0504] "Analysis" is the process by which a system understands the data it receives and extracts each element and meaning.

[0505] The "analysis process" refers to a series of procedures and steps involved in data analysis, which are automatically generated by the system.

[0506] "Visual representation" refers to showing the analysis process in an intuitive and easy-to-understand way using images and diagrams.

[0507] A "visual display device" is a device used to present visual representations to a user, and includes smart glasses and monitors.

[0508] The system for implementing this invention begins with a user using a visual display device such as smart glasses to make a data analysis request via voice. The server converts the user's voice input into text data using speech recognition software. The Python speech_recognition library is used for this conversion.

[0509] The server, equipped with a generative AI model, analyzes text data received from users. This analysis process uses natural language processing techniques to extract important keywords and context from the analyzed text. Based on the analysis results, the server automatically constructs data analysis processes. These processes can address tasks such as inventory optimization and delivery route analysis.

[0510] Users can view the generated visual representation through the visual display of their smart glasses. The display shows the analysis process in a visually easy-to-understand format, along with explanatory text about the purpose and role of each step.

[0511] For example, if a worker at a logistics center inputs via voice, "I want to analyze monthly shipping data and create a demand forecast for the next three months," the server will recognize elements such as "monthly," "shipping," and "demand forecast," and generate a corresponding analysis flow.

[0512] In this way, the system allows users to efficiently analyze data in real time and improve their operations, even without specialized knowledge.

[0513] An example of a prompt for a generating AI model is one that instructs it to visualize the data analysis flow when the input is, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0514] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0515] Step 1:

[0516] The user inputs data analysis requests by voice through the microphone of smart glasses, which are a visual display device. The voice input might be something like, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0517] Step 2:

[0518] The device uses speech recognition software to convert the input speech into text data. In this process, the audio signal is converted into a digital format, and a string of text is generated. The output is the text, "I would like to analyze monthly shipment data to create a demand forecast for the next three months."

[0519] Step 3:

[0520] The server analyzes text data using a generative AI model. Keywords and important contextual information from the input text are extracted using natural language processing techniques. During this analysis stage, key elements such as "monthly," "shipments," and "demand forecast" are identified. These analyzed elements serve as the basis for constructing the data analysis process.

[0521] Step 4:

[0522] The server automatically constructs the data analysis process based on the extracted elements. This is done according to a pre-configured algorithm. The analysis flow best suited to the user's requirements is calculated, and the order of processes is determined accordingly. Specific data processing and calculations are then designed.

[0523] Step 5:

[0524] The server generates a visual representation of the constructed data analysis process and sends it to smart glasses. At this time, a generating AI model is used to shape the flow of each process as a visual diagram or chart. By displaying this on a visual display device, the user can intuitively understand the overall flow.

[0525] Step 6:

[0526] The server also generates and provides explanatory text related to the visual representation to the user. The generated text explains the purpose and role of each analysis step in detail, allowing the user to understand each point in the flow in detail. This explanation appears on the screen of the visual display device.

[0527] 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.

[0528] This invention relates to a system that integrates data analysis with user sentiment recognition to generate and present a more personalized analysis flow. This system assists the user in performing data analysis by easily generating the necessary steps and presenting them in an optimal format based on the user's sentiment.

[0529] The user enters analysis requests in natural language using a chat interface via their device. The device receives the user's text input and sends the data to the server. The server, which is equipped with a generative AI and an emotion engine, analyzes the entered analysis requests. The generative AI module extracts key elements from the analyzed text and identifies the requirements for the analysis flow. Simultaneously, the emotion engine recognizes the user's emotions and understands their emotional state.

[0530] The server determines the data analysis flow based on the analysis results and the output of the emotion engine. In doing so, it takes into account the characteristics of existing data analysis tools and constructs an appropriate flow tailored to the user's emotional state. For example, if the system detects that the user is tired, it can generate a simpler and more intuitive flow.

[0531] The generated analysis flow is produced as a visual image using a visualization engine. This image is presented to the user with a color scheme and format that matches the user's emotional state. Furthermore, the server creates descriptive text related to the generated image and provides emotion-sensitive feedback. This feedback explains the purpose and role of each step in the analysis flow, helping the user to efficiently understand its content.

[0532] For example, if a user inputs "I want to calculate the average sales by region using sales data" and expresses concern, the server will generate an interface that is as clear and reassuring as possible, providing instructions in simple steps. In this way, even users without specialized knowledge can perform efficient data analysis by utilizing an analysis flow that is tailored to their emotional state.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] Users enter their analysis requests in natural language via the terminal's chat interface.

[0536] Step 2:

[0537] The terminal receives user input and sends it to the server.

[0538] Step 3:

[0539] The server passes the received input data to the generating AI and begins the analysis.

[0540] Step 4:

[0541] The AI ​​within the server analyzes the input language and extracts the key elements and context of the analysis request.

[0542] Step 5:

[0543] In parallel, the server uses an emotion engine to analyze and identify the user's emotional state from the text input.

[0544] Step 6:

[0545] The server combines the requirements and emotional states obtained from the analysis to design the data analysis flow. In this process, the characteristics of existing data analysis tools and adjustments based on user emotions are taken into consideration.

[0546] Step 7:

[0547] The server launches a visualization engine to generate the designed data analysis flow as a visual image.

[0548] Step 8:

[0549] The server creates text descriptions related to the generated flow images and adds feedback tailored to the user's emotional state.

[0550] Step 9:

[0551] The server sends the flow image and explanatory text as a package to the terminal.

[0552] Step 10:

[0553] The device displays the received package and presents it to the user in an appropriate format. This allows the user to receive an analysis flow that takes their emotional state into consideration and prepares them to proceed to the next step.

[0554] (Example 2)

[0555] 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."

[0556] In the field of data analysis, there is a problem in that it is difficult for users without specialized knowledge to intuitively analyze data. Furthermore, depending on the user's emotional state, the analysis process can become stressful. To solve these problems, it is necessary to provide personalized analysis flows that take user emotions into consideration.

[0557] 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.

[0558] In this invention, the server includes means for receiving analysis requests entered by the user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, and means for recognizing the user's emotions and understanding their emotional state. This makes it possible to execute an optimal data analysis flow based on the user's requests and emotions and present it in a visually easy-to-understand format.

[0559] A "user" refers to a person who uses the system to make data analysis requests in natural language.

[0560] "Natural language" refers to the forms of language that humans use in everyday life, and is a free-form text that is not structured.

[0561] An "analysis request" refers to a user's wish or instruction to request specific data analysis through the system.

[0562] "Means" refers to a specific function or the specific methods and processes used to achieve that function.

[0563] "Analysis" refers to the act of examining received data and requests to identify their meaning and importance.

[0564] "Identifying requirements" refers to clarifying the necessary procedures and conditions based on user requests and inputs.

[0565] "Recognizing emotions" refers to the process of understanding a user's mental state and feelings from their written statements and behavior.

[0566] "Emotional state" refers to the psychological or emotional situation or condition that a user is experiencing.

[0567] A "data processing flow" refers to a series of steps and processes for performing data analysis, and is built based on defined requirements.

[0568] "Visual format" refers to a format in which information is represented using visual elements such as shapes and images.

[0569] "Color tone" refers to the way in which visual elements are expressed in terms of color, and is used to convey specific emotions or impressions.

[0570] "Format" refers to the structured form or shape of data or information.

[0571] "Feedback" refers to the results and opinions that a system provides to a user, and may include information for improvement.

[0572] This system is implemented by combining multiple technologies to facilitate users making data analysis requests in natural language. The system mainly consists of terminals and servers, which work together to perform their functions.

[0573] Users access the chat interface through their device and input using natural language. For example, a user can enter an analytical request such as, "I want to forecast sales for the next quarter." This input is then sent to the server by the device.

[0574] The server is equipped with a generative AI model and an emotion engine. After receiving an analysis request, this software analyzes the request. The generative AI model extracts key elements from the input text and identifies the requirements for the analysis flow. This clarifies the analysis procedure best suited to the user's needs.

[0575] In parallel, the emotion engine recognizes emotions from the user's input text and monitors their emotional state. This process allows the server to understand the user's psychological state and build emotion-based data analysis flows.

[0576] In designing analytical flows, the server takes into account the characteristics of existing data analysis software. For example, common tools for visually analyzing data, such as Tableau or Power BI, may be used. This allows for the design of flows that leverage standardized data processing methods while being optimized for the individual emotional state of the user.

[0577] The designed analysis flow is generated as a visual image using a visualization engine. This image is presented to the user via their device, with a color scheme and format tailored to the user's emotional state. This allows the user to intuitively grasp the overall picture of the analysis.

[0578] Furthermore, the server generates descriptive text related to the generated images and provides sentiment-based feedback. This feedback helps users efficiently understand the purpose and process of each step in the analysis flow.

[0579] As a concrete example, prompt statements are used as follows:

[0580] "I want to make sales forecasts for the next quarter, but I don't know which data to use. I need help."

[0581] This system allows even users without specialized knowledge to intuitively perform complex data analysis processes.

[0582] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0583] Step 1:

[0584] The user accesses a chat interface through their device and enters an analysis request in natural language. This request indicates the purpose of the data analysis the user wishes to achieve. The input data is in natural language text format. This input is received by the device and sent to the server.

[0585] Step 2:

[0586] The server passes text data sent from the terminal to a generative AI model for analysis. The generative AI model processes the natural language analysis request and extracts keywords and important elements. This extraction process allows the server to identify the requirements for the analysis flow. The input is text data, and the output is structured data containing the extracted requirements.

[0587] Step 3:

[0588] The server simultaneously uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions from text to understand the user's emotional state. This process is performed using NLP techniques, and metadata related to emotions is output. The input is text data, and the output is data indicating the emotional state.

[0589] Step 4:

[0590] The server designs a data analysis flow based on the analyzed requests and emotional states. This design takes into account generative AI models and existing data analysis techniques. For example, an intuitively operable flow is constructed. The inputs are structured data and emotional state data, and the output is a visualized analysis flow.

[0591] Step 5:

[0592] The server constructs the analysis flow generated using the visualization engine as a visual image. This image is expressed in emotionally appropriate colors and formats and sent to the terminal. The input is the designed analysis flow, and the output is the visualized image.

[0593] Step 6:

[0594] The server generates descriptive text related to the generated images and sends it to the user. The descriptive text clarifies the purpose and intent of each step. The input is the visualized flow and emotional state data, and the output is the descriptive text for the user.

[0595] This series of steps allows users to intuitively understand and perform data analysis.

[0596] (Application Example 2)

[0597] 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."

[0598] In e-commerce, personalized recommendations based on user preferences and emotions are crucial for improving the user's purchasing experience. However, conventional systems lack sufficient means to present visual information and recommend products in a way that takes user emotions into account. Therefore, there is a need for a system that provides purchasing support that reflects the user's emotional state in real time.

[0599] 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.

[0600] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, means for determining a data analysis flow based on the identified requirements and generating it as a visual representation, means for recognizing the user's emotional state based on the generated visual representation and providing personalized recommended items, and means for presenting the generated visual representation to the user. This enables personalized purchase support that takes the user's emotions into consideration.

[0601] "Natural language" refers to the language that humans use on a daily basis, and is a text data format that can be processed by computers.

[0602] An "analysis request" is a request that indicates the type of analysis and results that the user wants to perform on the data.

[0603] An "analysis flow" refers to a series of steps and processes used to carry out data analysis.

[0604] "Visual representation" refers to a format for presenting data and information visually, including graphs and charts.

[0605] "Emotional state" refers to the emotional state a user is experiencing at a particular point in time, and includes feelings such as joy, sadness, and fatigue.

[0606] "Personalized recommendations" refer to recommendations for products and services selected based on the user's individual preferences and emotional state.

[0607] The system for implementing this invention is realized using a user's device (e.g., a smartphone or smart glasses) and a powerful server. First, the user inputs their analysis request in natural language using the device. This input is transmitted to the server via an interface installed on the terminal.

[0608] On the server, a generative AI model is used to analyze the received natural language input. During the analysis process, the server extracts user requests and identifies an analysis flow based on those requests. Furthermore, it prepares the corresponding data analysis flow using the provided database and external data sources. To take user emotions into consideration, an emotion recognition engine recognizes the emotional state from the user's facial expressions and voice. Based on this information, the server generates optimized visual representations and personalized recommendations.

[0609] For example, if a user enters "I'm looking for a Mother's Day gift, but there are too many options and I'm worried about not being able to choose. Please recommend something simple and nice," the server will analyze this request and, taking into account the user's anxiety, provide a reassuring and intuitive interface. Based on the generated visual representation, appropriate gift suggestions will be made.

[0610] This system allows users to have a personalized shopping experience that takes their emotions into consideration. These processes performed by the server enable users to make efficient and satisfying purchases.

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] Users input analysis requests in natural language through the interface of their smart devices. This input is sent from the device to the server as text data. The input includes specific wishes and emotional expressions.

[0614] Step 2:

[0615] The server analyzes the received text data. Here, it utilizes a generative AI model to extract important elements from the input. For example, it analyzes requests such as "I'm looking for a Mother's Day gift." It also identifies the user's emotional state from their expressions.

[0616] Step 3:

[0617] The emotion recognition engine analyzes user input and additional emotional data (such as facial expressions and tone of voice) to evaluate the user's emotional state. This evaluation is output as emotional labels such as feeling safe or anxious.

[0618] Step 4:

[0619] The server identifies the data analysis flow based on the extracted elements and emotional state, and generates an appropriate visual representation. In this process, if the user is seeking a sense of security, a brightly colored interface will be generated.

[0620] Step 5:

[0621] Based on the generated visual representation, the server determines personalized recommended items. In this process, it retrieves appropriate product information from the database and outputs a list of products that correspond to the user's emotions.

[0622] Step 6:

[0623] Finally, personalized recommended items, along with the generated visual representation, are sent to the device and presented to the user. This allows the user to receive choices that are relevant to their emotions.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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".

[0641] This invention relates to a system that easily generates and assists users in understanding the workflows necessary for data analysis. This system automatically constructs an appropriate data analysis workflow based on natural language analysis requests entered by the user and presents it visually to the user, thereby streamlining the analysis process.

[0642] First, the user enters their analysis request in natural language through the terminal's chat interface. The terminal receives this input and sends the data to the server. The server is equipped with generative AI, which analyzes the input text to understand the analysis request. Specifically, the text analysis engine extracts important keywords and context from the natural language to identify the requirements.

[0643] The server constructs a data analysis flow based on the analysis results. This includes an algorithm that considers the characteristics of existing data analysis tools and determines a process that meets the user's needs. The determined flow is then generated as an image by a visualization engine. The generated flow image is presented in a visually easy-to-understand format, making it easily accessible to the user.

[0644] Furthermore, the server generates explanatory text accompanying the images. This text explains the purpose and role of each step in the analysis flow, supporting users in efficiently understanding the content. The system also optimizes itself according to the characteristics of the tools as needed, flexibly responding to diverse user requirements.

[0645] For example, if a user inputs "I want to calculate the average sales by region using sales data," the server uses its analysis engine to extract elements such as "sales data," "region," and "average sales," and builds a workflow that includes steps such as data import, filtering, grouping, and aggregation. The generated image and explanation are presented to the user, allowing them to easily understand and execute the workflow for data analysis that suits their needs. In this way, this system enables even users without specialized knowledge to perform data analysis quickly.

[0646] The following describes the processing flow.

[0647] Step 1:

[0648] The user enters their data analysis requests in natural language into the device's chat interface.

[0649] Step 2:

[0650] The terminal receives user input and sends that data to the server.

[0651] Step 3:

[0652] The server activates the generative AI to analyze the received input data.

[0653] Step 4:

[0654] The AI ​​within the server analyzes the input natural language and identifies the necessary elements of the analysis request. At this stage, important keywords and phrases are extracted from the text.

[0655] Step 5:

[0656] The server designs each step of the analysis flow based on the identified elements, taking into account the characteristics of existing data analysis tools.

[0657] Step 6:

[0658] The server runs a visualization engine to generate the designed analysis flow as a visual image.

[0659] Step 7:

[0660] The server combines the generated flow image with descriptive text about its contents to create a package for presentation to the user.

[0661] Step 8:

[0662] The terminal displays the flow image and explanatory text sent from the server to the user.

[0663] Step 9:

[0664] Based on the information provided, the user understands and executes the steps for the next analysis.

[0665] (Example 1)

[0666] 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".

[0667] When users perform information analysis, it is difficult for them to construct and understand appropriate data processing procedures. In particular, for users without specialized knowledge, visually understanding and grasping data analysis procedures is a significant challenge.

[0668] 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.

[0669] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying requirements based on the requests, and means for determining data processing procedures based on the identified requirements and generating them as visual representations. This makes it possible for users to easily understand and execute data analysis procedures even without specialized knowledge.

[0670] A "user" is an entity that uses an information system to input or request data.

[0671] "Natural language" refers to the forms of language that humans use on a daily basis, and is used to express requests for analysis, etc.

[0672] An "analysis request" is a request that specifies the purpose and conditions that a user seeks when analyzing information.

[0673] "Means" refer to the specific methods or functions used to achieve a particular objective.

[0674] "Analysis" is the process of interpreting given information and extracting useful information from it.

[0675] A "requirement" is a condition or standard that is necessary to achieve a specific objective.

[0676] A "data processing procedure" is a set of steps for properly organizing and analyzing information to obtain results that align with the objective.

[0677] "Visual representation" refers to methods of making information easier to understand by visualizing it using diagrams and images.

[0678] This invention aims to lower the barriers to information analysis for users and provide a system that allows for easy analysis. The system begins with the user inputting data-related requests in natural language. Users can input specific analysis requests using a chat interface on their device. These inputs can take the form of, for example, "I would like to know the average sales by region using last year's sales data."

[0679] The device sends the natural language analysis request received from the user to the server. The server uses a generative AI model to analyze the received text and identify requirements based on the user's request. In this analysis process, the text analysis engine works to extract important keywords and understand the context.

[0680] The server automatically determines the data processing procedure based on the analysis results. Here, it assembles the optimal analysis flow, taking into account the characteristics of existing data processing tools and methods. This determined flow is then converted into a visual representation by a visualization engine. This representation is sent to the terminal in a format that is easy for the user to understand.

[0681] The terminal displays visual representations and explanatory text sent from the server to the user. By referring to this, the user can easily understand how to process the data. Furthermore, if necessary, the server provides detailed explanations in text related to the generated analysis flow. These explanations clearly describe the purpose and role of each step, allowing the user to proceed with the specific analysis while reading them.

[0682] For example, if a user inputs "I want to calculate the average sales by region using sales data," the server uses its analysis engine to extract elements such as "sales data," "region," and "average sales," and then builds a workflow that incorporates processes such as data import, filtering, grouping, and aggregation. Ultimately, the user can understand the presented workflow and easily execute the specific steps necessary to achieve excellent data analysis.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The user operates the terminal and enters an analysis request in natural language into the chat interface. An example of this input is, "I want to calculate the average sales by region using sales data." The purpose here is to capture the user's needs as concrete text. Once this request is entered, the terminal prepares to send it to the server.

[0686] Step 2:

[0687] The terminal sends input text data from the user to the server. This transmission process uses an appropriate communication protocol to ensure the input data is transmitted securely and quickly. The output is the text of the analysis request that reaches the server.

[0688] Step 3:

[0689] The server passes the text of the received analysis request to a generating AI model for natural language processing. This analysis utilizes a text analysis engine to extract key keywords (e.g., sales data, region, average sales) from the input text. The input is the user's analysis request, and the output is a list of extracted keywords and requirements.

[0690] Step 4:

[0691] The server constructs a data processing procedure based on the analyzed keywords and requirements. This procedure includes steps such as importing, filtering, grouping, and aggregating the necessary data. The server optimizes this procedure and prepares it for visualization. The output is a visualized data processing flow that meets the user's requirements.

[0692] Step 5:

[0693] The server passes the constructed data processing flow to the visualization engine, which converts it into a visually easy-to-understand format. The output of this process is an image or diagram that the user can intuitively understand.

[0694] Step 6:

[0695] The server generates explanatory text for each step, along with the generated visual representation, and sends it to the terminal. The explanatory text details the purpose and role of each step, aiding user understanding. The output is a visual data processing flow and its explanatory text.

[0696] Step 7:

[0697] The terminal presents the user with visual representations and explanatory text received from the server. This allows the user to decide how to proceed with data analysis using the presented information. At this stage, the output is the information and instructions received by the user.

[0698] (Application Example 1)

[0699] 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".

[0700] In logistics centers and similar facilities, it is difficult for workers without specialized data analysis knowledge to perform real-time analysis of inventory and delivery patterns. Furthermore, current systems lack an intuitive interface for understanding efficient analysis flow data after voice input. To address this situation and improve work efficiency, it is necessary to provide effective solutions.

[0701] 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.

[0702] In this invention, the server includes means for acquiring user voice input and converting the acquired voice into text, means for acquiring data analysis processes based on the converted text, and means for displaying the acquired data analysis processes on a visual display device. This makes it possible for workers without specialized knowledge of data analysis to intuitively understand inventory management and delivery pattern analysis in a logistics center in real time, thereby improving work efficiency.

[0703] A "user" is an individual or legal entity that makes data analysis requests to the system through natural language or voice.

[0704] "Natural language" refers to written and spoken text expressed in the language that humans use on a daily basis, and is the format in which users input it into a system.

[0705] "Analysis request" refers to the wishes or instructions that a user communicates to the system for the purpose of analyzing data.

[0706] "Analysis" is the process by which a system understands the data it receives and extracts each element and meaning.

[0707] The "analysis process" refers to a series of procedures and steps involved in data analysis, which are automatically generated by the system.

[0708] "Visual representation" refers to showing the analysis process in an intuitive and easy-to-understand way using images and diagrams.

[0709] A "visual display device" is a device used to present visual representations to a user, and includes smart glasses and monitors.

[0710] The system for implementing this invention begins with a user using a visual display device such as smart glasses to make a data analysis request via voice. The server converts the user's voice input into text data using speech recognition software. The Python speech_recognition library is used for this conversion.

[0711] The server, equipped with a generative AI model, analyzes text data received from users. This analysis process uses natural language processing techniques to extract important keywords and context from the analyzed text. Based on the analysis results, the server automatically constructs data analysis processes. These processes can address tasks such as inventory optimization and delivery route analysis.

[0712] Users can view the generated visual representation through the visual display of their smart glasses. The display shows the analysis process in a visually easy-to-understand format, along with explanatory text about the purpose and role of each step.

[0713] For example, if a worker at a logistics center inputs via voice, "I want to analyze monthly shipping data and create a demand forecast for the next three months," the server will recognize elements such as "monthly," "shipping," and "demand forecast," and generate a corresponding analysis flow.

[0714] In this way, the system allows users to efficiently analyze data in real time and improve their operations, even without specialized knowledge.

[0715] An example of a prompt for a generating AI model is one that instructs it to visualize the data analysis flow when the input is, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0716] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0717] Step 1:

[0718] The user inputs data analysis requests by voice through the microphone of smart glasses, which are a visual display device. The voice input might be something like, "I want to analyze monthly shipment data and create a demand forecast for the next three months."

[0719] Step 2:

[0720] The device uses speech recognition software to convert the input speech into text data. In this process, the audio signal is converted into a digital format, and a string of text is generated. The output is the text, "I would like to analyze monthly shipment data to create a demand forecast for the next three months."

[0721] Step 3:

[0722] The server analyzes text data using a generative AI model. Keywords and important contextual information from the input text are extracted using natural language processing techniques. During this analysis stage, key elements such as "monthly," "shipments," and "demand forecast" are identified. These analyzed elements serve as the basis for constructing the data analysis process.

[0723] Step 4:

[0724] The server automatically constructs the data analysis process based on the extracted elements. This is done according to a pre-configured algorithm. The analysis flow best suited to the user's requirements is calculated, and the order of processes is determined accordingly. Specific data processing and calculations are then designed.

[0725] Step 5:

[0726] The server generates a visual representation of the constructed data analysis process and sends it to smart glasses. At this time, a generating AI model is used to shape the flow of each process as a visual diagram or chart. By displaying this on a visual display device, the user can intuitively understand the overall flow.

[0727] Step 6:

[0728] The server also generates and provides explanatory text related to the visual representation to the user. The generated text explains the purpose and role of each analysis step in detail, allowing the user to understand each point in the flow in detail. This explanation appears on the screen of the visual display device.

[0729] 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.

[0730] This invention relates to a system that integrates data analysis with user sentiment recognition to generate and present a more personalized analysis flow. This system assists the user in performing data analysis by easily generating the necessary steps and presenting them in an optimal format based on the user's sentiment.

[0731] The user enters analysis requests in natural language using a chat interface via their device. The device receives the user's text input and sends the data to the server. The server, which is equipped with a generative AI and an emotion engine, analyzes the entered analysis requests. The generative AI module extracts key elements from the analyzed text and identifies the requirements for the analysis flow. Simultaneously, the emotion engine recognizes the user's emotions and understands their emotional state.

[0732] The server determines the data analysis flow based on the analysis results and the output of the emotion engine. In doing so, it takes into account the characteristics of existing data analysis tools and constructs an appropriate flow tailored to the user's emotional state. For example, if the system detects that the user is tired, it can generate a simpler and more intuitive flow.

[0733] The generated analysis flow is produced as a visual image using a visualization engine. This image is presented to the user with a color scheme and format that matches the user's emotional state. Furthermore, the server creates descriptive text related to the generated image and provides emotion-sensitive feedback. This feedback explains the purpose and role of each step in the analysis flow, helping the user to efficiently understand its content.

[0734] For example, if a user inputs "I want to calculate the average sales by region using sales data" and expresses concern, the server will generate an interface that is as clear and reassuring as possible, providing instructions in simple steps. In this way, even users without specialized knowledge can perform efficient data analysis by utilizing an analysis flow that is tailored to their emotional state.

[0735] The following describes the processing flow.

[0736] Step 1:

[0737] Users enter their analysis requests in natural language via the terminal's chat interface.

[0738] Step 2:

[0739] The terminal receives user input and sends it to the server.

[0740] Step 3:

[0741] The server passes the received input data to the generating AI and begins the analysis.

[0742] Step 4:

[0743] The AI ​​within the server analyzes the input language and extracts the key elements and context of the analysis request.

[0744] Step 5:

[0745] In parallel, the server uses an emotion engine to analyze and identify the user's emotional state from the text input.

[0746] Step 6:

[0747] The server combines the requirements and emotional states obtained from the analysis to design the data analysis flow. In this process, the characteristics of existing data analysis tools and adjustments based on user emotions are taken into consideration.

[0748] Step 7:

[0749] The server launches a visualization engine to generate the designed data analysis flow as a visual image.

[0750] Step 8:

[0751] The server creates text descriptions related to the generated flow images and adds feedback tailored to the user's emotional state.

[0752] Step 9:

[0753] The server sends the flow image and explanatory text as a package to the terminal.

[0754] Step 10:

[0755] The device displays the received package and presents it to the user in an appropriate format. This allows the user to receive an analysis flow that takes their emotional state into consideration and prepares them to proceed to the next step.

[0756] (Example 2)

[0757] 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".

[0758] In the field of data analysis, there is a problem in that it is difficult for users without specialized knowledge to intuitively analyze data. Furthermore, depending on the user's emotional state, the analysis process can become stressful. To solve these problems, it is necessary to provide personalized analysis flows that take user emotions into consideration.

[0759] 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.

[0760] In this invention, the server includes means for receiving analysis requests entered by the user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, and means for recognizing the user's emotions and understanding their emotional state. This makes it possible to execute an optimal data analysis flow based on the user's requests and emotions and present it in a visually easy-to-understand format.

[0761] A "user" refers to a person who uses the system to make data analysis requests in natural language.

[0762] "Natural language" refers to the forms of language that humans use in everyday life, and is a free-form text that is not structured.

[0763] An "analysis request" refers to a user's wish or instruction to request specific data analysis through the system.

[0764] "Means" refers to a specific function or the specific methods and processes used to achieve that function.

[0765] "Analysis" refers to the act of examining received data and requests to identify their meaning and importance.

[0766] "Identifying requirements" refers to clarifying the necessary procedures and conditions based on user requests and inputs.

[0767] "Recognizing emotions" refers to the process of understanding a user's mental state and feelings from their written statements and behavior.

[0768] "Emotional state" refers to the psychological or emotional situation or condition that a user is experiencing.

[0769] A "data processing flow" refers to a series of steps and processes for performing data analysis, and is built based on defined requirements.

[0770] "Visual format" refers to a format in which information is represented using visual elements such as shapes and images.

[0771] "Color tone" refers to the way in which visual elements are expressed in terms of color, and is used to convey specific emotions or impressions.

[0772] "Format" refers to the structured form or shape of data or information.

[0773] "Feedback" refers to the results and opinions that a system provides to a user, and may include information for improvement.

[0774] This system is implemented by combining multiple technologies to facilitate users making data analysis requests in natural language. The system mainly consists of terminals and servers, which work together to perform their functions.

[0775] Users access the chat interface through their device and input using natural language. For example, a user can enter an analytical request such as, "I want to forecast sales for the next quarter." This input is then sent to the server by the device.

[0776] The server is equipped with a generative AI model and an emotion engine. After receiving an analysis request, this software analyzes the request. The generative AI model extracts key elements from the input text and identifies the requirements for the analysis flow. This clarifies the analysis procedure best suited to the user's needs.

[0777] In parallel, the emotion engine recognizes emotions from the user's input text and monitors their emotional state. This process allows the server to understand the user's psychological state and build emotion-based data analysis flows.

[0778] In designing analytical flows, the server takes into account the characteristics of existing data analysis software. For example, common tools for visually analyzing data, such as Tableau or Power BI, may be used. This allows for the design of flows that leverage standardized data processing methods while being optimized for the individual emotional state of the user.

[0779] The designed analysis flow is generated as a visual image using a visualization engine. This image is presented to the user via their device, with a color scheme and format tailored to the user's emotional state. This allows the user to intuitively grasp the overall picture of the analysis.

[0780] Furthermore, the server generates descriptive text related to the generated images and provides sentiment-based feedback. This feedback helps users efficiently understand the purpose and process of each step in the analysis flow.

[0781] As a concrete example, prompt statements are used as follows:

[0782] "I want to make sales forecasts for the next quarter, but I don't know which data to use. I need help."

[0783] This system allows even users without specialized knowledge to intuitively perform complex data analysis processes.

[0784] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0785] Step 1:

[0786] The user accesses a chat interface through their device and enters an analysis request in natural language. This request indicates the purpose of the data analysis the user wishes to achieve. The input data is in natural language text format. This input is received by the device and sent to the server.

[0787] Step 2:

[0788] The server passes text data sent from the terminal to a generative AI model for analysis. The generative AI model processes the natural language analysis request and extracts keywords and important elements. This extraction process allows the server to identify the requirements for the analysis flow. The input is text data, and the output is structured data containing the extracted requirements.

[0789] Step 3:

[0790] The server simultaneously uses an emotion engine to recognize the user's emotions. The emotion engine analyzes emotions from text to understand the user's emotional state. This process is performed using NLP techniques, and metadata related to emotions is output. The input is text data, and the output is data indicating the emotional state.

[0791] Step 4:

[0792] The server designs a data analysis flow based on the analyzed requests and emotional states. This design takes into account generative AI models and existing data analysis techniques. For example, an intuitively operable flow is constructed. The inputs are structured data and emotional state data, and the output is a visualized analysis flow.

[0793] Step 5:

[0794] The server constructs the analysis flow generated using the visualization engine as a visual image. This image is expressed in emotionally appropriate colors and formats and sent to the terminal. The input is the designed analysis flow, and the output is the visualized image.

[0795] Step 6:

[0796] The server generates descriptive text related to the generated images and sends it to the user. The descriptive text clarifies the purpose and intent of each step. The input is the visualized flow and emotional state data, and the output is the descriptive text for the user.

[0797] This series of steps allows users to intuitively understand and perform data analysis.

[0798] (Application Example 2)

[0799] 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".

[0800] In e-commerce, personalized recommendations based on user preferences and emotions are crucial for improving the user's purchasing experience. However, conventional systems lack sufficient means to present visual information and recommend products in a way that takes user emotions into account. Therefore, there is a need for a system that provides purchasing support that reflects the user's emotional state in real time.

[0801] 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.

[0802] In this invention, the server includes means for receiving analysis requests entered by a user in natural language, means for analyzing the received analysis requests and identifying the requirements of the analysis flow, means for determining a data analysis flow based on the identified requirements and generating it as a visual representation, means for recognizing the user's emotional state based on the generated visual representation and providing personalized recommended items, and means for presenting the generated visual representation to the user. This enables personalized purchase support that takes the user's emotions into consideration.

[0803] "Natural language" refers to the language that humans use on a daily basis, and is a text data format that can be processed by computers.

[0804] An "analysis request" is a request that indicates the type of analysis and results that the user wants to perform on the data.

[0805] An "analysis flow" refers to a series of steps and processes used to carry out data analysis.

[0806] "Visual representation" refers to a format for presenting data and information visually, including graphs and charts.

[0807] "Emotional state" refers to the emotional state a user is experiencing at a particular point in time, and includes feelings such as joy, sadness, and fatigue.

[0808] "Personalized recommendations" refer to recommendations for products and services selected based on the user's individual preferences and emotional state.

[0809] The system for implementing this invention is realized using a user's device (e.g., a smartphone or smart glasses) and a powerful server. First, the user inputs their analysis request in natural language using the device. This input is transmitted to the server via an interface installed on the terminal.

[0810] On the server, a generative AI model is used to analyze the received natural language input. During the analysis process, the server extracts user requests and identifies an analysis flow based on those requests. Furthermore, it prepares the corresponding data analysis flow using the provided database and external data sources. To take user emotions into consideration, an emotion recognition engine recognizes the emotional state from the user's facial expressions and voice. Based on this information, the server generates optimized visual representations and personalized recommendations.

[0811] For example, if a user enters "I'm looking for a Mother's Day gift, but there are too many options and I'm worried about not being able to choose. Please recommend something simple and nice," the server will analyze this request and, taking into account the user's anxiety, provide a reassuring and intuitive interface. Based on the generated visual representation, appropriate gift suggestions will be made.

[0812] This system allows users to have a personalized shopping experience that takes their emotions into consideration. These processes performed by the server enable users to make efficient and satisfying purchases.

[0813] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0814] Step 1:

[0815] Users input analysis requests in natural language through the interface of their smart devices. This input is sent from the device to the server as text data. The input includes specific wishes and emotional expressions.

[0816] Step 2:

[0817] The server analyzes the received text data. Here, it utilizes a generative AI model to extract important elements from the input. For example, it analyzes requests such as "I'm looking for a Mother's Day gift." It also identifies the user's emotional state from their expressions.

[0818] Step 3:

[0819] The emotion recognition engine analyzes user input and additional emotional data (such as facial expressions and tone of voice) to evaluate the user's emotional state. This evaluation is output as emotional labels such as feeling safe or anxious.

[0820] Step 4:

[0821] The server identifies the data analysis flow based on the extracted elements and emotional state, and generates an appropriate visual representation. In this process, if the user is seeking a sense of security, a brightly colored interface will be generated.

[0822] Step 5:

[0823] Based on the generated visual representation, the server determines personalized recommended items. In this process, it retrieves appropriate product information from the database and outputs a list of products that correspond to the user's emotions.

[0824] Step 6:

[0825] Finally, personalized recommended items, along with the generated visual representation, are sent to the device and presented to the user. This allows the user to receive choices that are relevant to their emotions.

[0826] 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.

[0827] 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.

[0828] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0829] 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.

[0830] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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."

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] The following is further disclosed regarding the embodiments described above.

[0848] (Claim 1)

[0849] A means for receiving analysis requests entered by users in natural language,

[0850] A means of analyzing received analysis requests and identifying the requirements of the analysis flow,

[0851] A means of determining the data analysis flow based on identified requirements and generating it as an image,

[0852] A means of presenting the generated image to the user,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, further comprising means for considering the characteristics of known data analysis tools when determining the analysis flow.

[0856] (Claim 3)

[0857] The system according to claim 1, further comprising means for generating and providing to a user a text description related to the generated image.

[0858] "Example 1"

[0859] (Claim 1)

[0860] A means for receiving analysis requests entered by users in natural language,

[0861] A means for analyzing received analysis requests and identifying requirements based on those requests,

[0862] A means for determining data processing procedures based on identified requirements and generating them as a visual representation,

[0863] A means of presenting the generated visual representation to the user,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising means for considering the characteristics of known data processing functions when determining the analysis flow.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising means for generating and providing to the user an explanation related to the generated visual representation.

[0869] "Application Example 1"

[0870] (Claim 1)

[0871] A means for receiving analysis requests entered by users in natural language,

[0872] A means for analyzing received analysis requests and identifying the requirements of the analysis process,

[0873] A means for determining the data analysis process based on identified requirements and generating it as a visual representation,

[0874] A means of presenting the generated visual representation to the user,

[0875] A means for acquiring user voice input and converting the acquired voice into text,

[0876] A means of obtaining data analysis processes based on the converted text,

[0877] A means for displaying the acquired data analysis process on a visual display device,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, further comprising means for considering the characteristics of known data analysis tools when determining the analysis process.

[0881] (Claim 3)

[0882] The system according to claim 1, further comprising means for generating and providing to the user a textual description related to the generated visual representation.

[0883] "Example 2 of combining an emotion engine"

[0884] (Claim 1)

[0885] A means for receiving analysis requests entered by users in natural language,

[0886] A means of analyzing received analysis requests and identifying the requirements of the analysis flow,

[0887] A means of recognizing and understanding the user's emotions and emotional state,

[0888] A means to optimize the data analysis flow according to emotional state,

[0889] A means for determining and generating a data processing flow in a visual format based on identified requirements and emotional states,

[0890] A means of presenting the generated visual format to the user in a color scheme and format that responds to emotions,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, further comprising means for considering the characteristics of known data analysis techniques when determining the analysis flow.

[0894] (Claim 3)

[0895] The system according to claim 1, further comprising means for generating an explanatory text related to the generated visual format and providing it to the user along with emotion-responsive feedback.

[0896] "Application example 2 when combining with an emotional engine"

[0897] (Claim 1)

[0898] A means for receiving analysis requests entered by users in natural language,

[0899] A means of analyzing received analysis requests and identifying the requirements of the analysis flow,

[0900] A means of determining the data analysis flow based on identified requirements and generating it as a visual representation,

[0901] A means of recognizing the user's emotional state based on the generated visual representation and providing personalized recommended items,

[0902] A means of presenting the generated visual representation to the user,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising means for considering the characteristics of known data analysis techniques when determining the analysis flow.

[0906] (Claim 3)

[0907] The system according to claim 1, further comprising means for generating and providing to a user an explanatory text relating to the generated visual representation. [Explanation of Symbols]

[0908] 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 for receiving analysis requests entered by users in natural language, A means of analyzing received analysis requests and identifying the requirements of the analysis flow, A means of determining the data analysis flow based on identified requirements and generating it as an image, A means of presenting the generated image to the user, A system that includes this.

2. The system according to claim 1, further comprising means for considering the characteristics of known data analysis tools when determining the analysis flow.

3. The system according to claim 1, further comprising means for generating and providing to a user a text description related to the generated image.

Images