system

Abstract

Provide a system. 【Solution means】 Means for obtaining data from an external information source, Means for converting the obtained data into an internal format, Means for storing the converted data in a database, Means for performing differential analysis on specific indicators based on the stored data, Means for analyzing annual changes using past data and generating a trend line, Means for automatically creating a report based on the analysis results, Means for comparing other data with its own data and identifying characteristic differences, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In local governments, due to the effects of a declining birthrate, aging population, and labor shortages, there is an increasing need to efficiently and quickly analyze regional data and make appropriate policy decisions. However, many local governments lack the specialized knowledge and resources necessary for data analysis and are unable to fully utilize the vast amounts of data provided by the country or region. As a result, it has become difficult to identify region-specific issues and compare with other regions. In view of such a situation, it is necessary to provide a method for efficiently collecting and analyzing data and supporting strategic decision-making related to one's own region.

Means for Solving the Problems

[0005] This invention provides a system that automatically collects data from external sources, converts it to an internal format, and stores it in a database. This system includes a function to perform difference analysis on specific indicators based on the stored data. It can also generate trend lines using historical data to predict long-term trends. Furthermore, it supports decision-making by using AI models to identify factors influencing data fluctuations and automatically generating reports based on the analysis results. It also includes a function to compare its own data with other data and identify characteristic differences, thereby clarifying region-specific issues. These means enable local governments to efficiently utilize data and provide information useful for understanding the current situation in their regions and for policy formulation.

[0006] "Data" refers to a collection of facts and concepts expressed in various forms, such as numbers and strings, obtained from information sources.

[0007] "External information sources" refer to data providers that are not directly managed by the system, such as local government or national statistical departments.

[0008] "To acquire" refers to the act of taking data from an external source and making it usable within the system.

[0009] "Converting" refers to the process of transforming acquired data into a format suitable for processing within the system.

[0010] A "database" is a system for systematically storing large amounts of data and managing it in a way that allows for efficient searching and updating.

[0011] "To save" refers to the act of storing data in a form that can be maintained for a long period of time, such as in a database or other storage device.

[0012] An "indicator" refers to a numerical value or standard that indicates a specific attribute or characteristic of data.

[0013] "Difference analysis" is an analytical method that reveals numerical differences and changes between data from one's own municipality and standard data.

[0014] A "trend line" refers to a mathematical line or curve that shows the pattern of data fluctuations based on past data.

[0015] An "AI model" is a software model that uses machine learning algorithms to learn patterns in data and enables inference and prediction.

[0016] A "report" is a document that organizes the results of an analysis and presents them clearly in visual or written form.

[0017] "Comparing" refers to the act of analyzing data to identify similarities and differences between different datasets.

[0018] "Characteristic differences" refer to particularly noticeable differences or characteristics between the datasets being compared. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] 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 a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of 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 an 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 an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] 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).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] This invention provides a system that enables local governments to efficiently utilize data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a specific role.

[0041] First, the server retrieves data from external sources. By regularly collecting statistical data from local governments and the national government using APIs, it is possible to quickly incorporate the latest information into the system. The retrieved data is automatically converted into the necessary format and stored in a database. This stored data forms the basis for subsequent analysis.

[0042] Next, the server performs analysis based on the stored data. Using the difference analysis function, it can compare the differences between the local statistical data and the national statistical data. Furthermore, longitudinal analysis makes it possible to understand past trends and predict future trends. By using AI models, important factors can be identified from the data, and detailed factor analysis can be performed.

[0043] The analysis results are automatically generated as a report by the server. This report consists of visual graphs and text, presenting information in an easy-to-understand format for the user. Furthermore, it allows for comparison with data from other municipalities with similar functionality, helping to identify challenges specific to one's own region.

[0044] The terminal provides users with generated reports and analysis results through a user interface. Users can access the system via this terminal and request further in-depth data analysis or the generation of additional reports as needed.

[0045] By utilizing the above functions, users can make important decisions in local government administration quickly and rationally. For example, by quickly grasping changes in the financial situation and taking necessary measures in advance, they can improve the quality of services to local residents. In this way, the present invention streamlines local government operations and supports the formation of excellent data-driven policies.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server accesses APIs from external information sources to periodically retrieve the latest statistical data. A schedule is set to manage this process, ensuring that data collection is performed automatically.

[0049] Step 2:

[0050] The server converts the acquired data into a format that can be used internally. For example, it might convert JSON data to CSV format so that it can be used efficiently in subsequent processing.

[0051] Step 3:

[0052] The server saves the converted data to a database. The data is saved in an easily accessible format by setting keys such as regional ID and year.

[0053] Step 4:

[0054] The server performs a difference analysis on specific indicators based on the information stored in the database. This reveals and displays the numerical differences between the target municipality and the national average.

[0055] Step 5:

[0056] The server performs a year-on-year analysis based on historical data and generates trend lines. During this process, it graphs the year-to-year changes in numerical values, visually illustrating long-term trends.

[0057] Step 6:

[0058] The server uses an AI model to analyze the factors behind data fluctuations. The AI ​​detects specific patterns and anomalies within the data and identifies the underlying causes based on these findings.

[0059] Step 7:

[0060] The server aggregates the analysis results and automatically generates a report. The report is structured in an easy-to-understand format, including a summary of the analyzed data and graphs illustrating the results.

[0061] Step 8:

[0062] The server compares the data with that of other municipalities of similar size to identify distinctive differences. This highlights the unique challenges specific to the target municipality.

[0063] Step 9:

[0064] The terminal provides the user with the generated report through its user interface. Based on this information, the user can quickly identify the issues they need to address.

[0065] Step 10:

[0066] Users can request more in-depth information about specific data analyses through their devices. This request is immediately transmitted to the server.

[0067] Step 11:

[0068] Based on user requests, the server performs additional data analysis and generates a new report. This provides more detailed information to support decision-making.

[0069] (Example 1)

[0070] 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."

[0071] Local governments are required to efficiently utilize the latest data to solve regional issues and support administrative decision-making. Existing systems often manage each stage of data collection, transformation, storage, analysis, and reporting individually, making integrated and timely information provision difficult. Furthermore, comparing various data and predicting trends is time-consuming, hindering the efficient use of time and resources.

[0072] 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.

[0073] In this invention, the server includes means for acquiring data from public information sources, means for converting the acquired data into a standard format, and means for storing the converted data in a storage device. This enables efficient data collection, storage, and utilization.

[0074] "Data" is a collection of information that is collected, processed, and stored by a computer.

[0075] "Public information sources" refer to official information provided by local governments, national agencies, and other similar organizations.

[0076] A "standard format" is a format established to ensure data compatibility and readability.

[0077] A "storage device" is a piece of hardware or software used to store information for the long term.

[0078] "Differences in metrics" refers to differences in characteristics and trends across different datasets.

[0079] "Daily variation" refers to changes in data observed at specific time intervals.

[0080] A "prediction curve" is a graph used to estimate future trends based on past data.

[0081] A "report" is an informational document that presents analysis results and conclusions in a documented format.

[0082] A "user interface" is a visual interface that allows users to interact with the system and obtain information.

[0083] A "machine learning model" is an algorithm that automatically learns patterns from data to perform predictions and classifications.

[0084] This invention is a system for local governments to effectively utilize various types of data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a different role.

[0085] The server retrieves data from external public information sources via APIs. The retrieved data is converted to a standard format using libraries such as Python's Pandas library and stored in a database system, such as PostgreSQL. Based on the stored data, the server performs data analysis using machine learning models. This analysis includes techniques using TENSORFLOW® and PyTorch to evaluate differences in metrics and daily fluctuations, and to generate forecast curves necessary for future predictions. The analysis results are visualized using Matplotlib and D3.js and automatically formatted into reports.

[0086] The terminal provides a user interface that allows users to access and view generated reports and analysis results. This interface is implemented using React.js and Vue.js, enabling interactive user operation.

[0087] Users obtain system information via their terminals and request more detailed analysis or the generation of additional reports. For example, if a user wants to know about trends in financial data, they would enter the following as a prompt:

[0088] "Based on the fiscal balance data for the past three years, analyze the trends in increases and decreases for each expenditure item and assess their impact on next year's budget plan."

[0089] This system enables local governments to formulate data-driven, logical, and rapid policies, contributing to improved quality of services for residents.

[0090] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0091] Step 1:

[0092] The server retrieves data from external public information sources. In this process, the server uses an API to connect to the database in real time and retrieve the necessary datasets. The input is raw data from the external information source, and the output is unprocessed data stored within the server.

[0093] Step 2:

[0094] The server converts the acquired raw data into a standard format. This conversion uses the Python Pandas library to format the data and impute missing values. The input is the raw data, and the output is the data converted to the standard format.

[0095] Step 3:

[0096] The server stores the transformed data in a relational database. PostgreSQL is used here to efficiently store the organized data and prepare it for later analysis. The input is data in a standard format, and the output is data managed within the database.

[0097] Step 4:

[0098] The server performs analysis based on stored data. It uses machine learning models to analyze differences in metrics between data points and daily fluctuations. This process utilizes TensorFlow and PyTorch to perform trend analysis and prediction. The input is data retrieved from the database, and the output is the analysis results.

[0099] Step 5:

[0100] The server visualizes the analysis results and automatically generates reports. It uses Matplotlib and D3.js to create graphs and generates reports containing text information in PDF or HTML format. The input is the analysis results, and the output is the report provided to the user.

[0101] Step 6:

[0102] The terminal presents the generated reports and analysis results to the user. It provides a graphical user interface using React.js and Vue.js, allowing users to view and further manipulate the visualized information. The input is the generated report, and the output is the screen display accessible to the user.

[0103] Step 7:

[0104] Users access the system to request detailed analysis or the generation of additional reports. For example, they might request a detailed trend analysis based on historical financial data using a prompt. The input is the user's request or prompt, and the output is the newly generated analysis or report.

[0105] (Application Example 1)

[0106] 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."

[0107] In modern society, security risks are increasing, and real-time information gathering and rapid risk assessment are required. However, current systems have limited means of efficiently acquiring and analyzing the latest security information, making it particularly difficult for individuals and small organizations to respond quickly to risks.

[0108] 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.

[0109] In this invention, the server includes means for acquiring data from external information sources, means for evaluating security risks and providing the results visually to the user, and means for comparing its own data with other data and identifying characteristic differences. This enables real-time identification of security risks and rapid response.

[0110] "Means of obtaining data from external sources" refers to functions for collecting necessary information through external databases or APIs.

[0111] "Means of converting to an internal format" refers to a function that converts acquired data into a format that is easy for the system to process.

[0112] "Means of saving to a database" refers to the function of storing converted data in order to effectively manage it.

[0113] "Methods for performing difference analysis on specific indicators" refer to methods that calculate the differences in numerical values ​​between different datasets and use the results to find specific trends or patterns.

[0114] "A method for analyzing year-to-year changes using historical data and generating trend lines" refers to a function that analyzes data fluctuations over time and draws lines to predict future trends.

[0115] "Methods for automatically generating reports" refers to functions that generate documents based on analysis results and compile information.

[0116] "Means for identifying distinctive differences" refers to methods for finding particularly noteworthy differences among data points being compared.

[0117] "A means of assessing security risks and providing the results to users visually" refers to a function that analyzes potential threats and communicates that information to users in a graphical format.

[0118] In this embodiment of the invention, the server functions as follows: The server retrieves information from an external security database using an API and converts the data into an internally specific format. It also efficiently stores the converted data in the database. This allows for rapid access while maintaining data integrity. The server then performs differential analysis based on the stored data to assess security risks. Using an AI model, it is possible to analyze the factors causing data fluctuations in detail and automatically generate a report based on the analysis results. This report is displayed to the user through a user interface, allowing them to understand the security situation in real time.

[0119] In terms of hardware, a server with a high-performance processor and sufficient data storage capacity is required. In terms of software, a data processing program using Python and an AI model implementation using TensorFlow will be necessary.

[0120] As a concrete example, this system could be used by small organizations that want to strengthen their defenses against specific cyberattacks in their daily operations. The server can analyze information obtained from external data and send a request to a generating AI model using a prompt message such as, "Predict security risks based on recent cyberattack trends and propose specific countermeasures." This makes it possible to quickly implement practical defensive measures based on the provided data.

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

[0122] Step 1:

[0123] The server accesses an external security database via an API to retrieve the latest security-related data. Because this input data has an external format and structure, it needs to be in a standardized format. For example, it accepts data in CSV or JSON format.

[0124] Step 2:

[0125] The server converts the acquired data into an internal format. Specifically, it analyzes the data structure and extracts the necessary fields to format it for analysis. This process involves removing unnecessary data and standardizing data types. The output is a well-organized dataset.

[0126] Step 3:

[0127] The server saves the converted data to the database. Transactional processing is performed during this saving process to maintain data consistency and integrity. The saved data is then ready for use in subsequent analysis.

[0128] Step 4:

[0129] The server performs differential analysis using the stored data. Specifically, it compares past data with current data to detect statistically significant changes. The output obtained from this analysis is an indicator showing the trend of increasing or decreasing risk.

[0130] Step 5:

[0131] The server utilizes an AI model to identify factors influencing data fluctuations and conduct a detailed risk analysis. The AI ​​model compares past data patterns with current data to predict potential risk factors. The output is a risk factor analysis report.

[0132] Step 6:

[0133] The server automatically generates a report based on the analysis results and sends it to the terminal. This report includes visual graphs and text information and is converted into a format that is easy for the user to understand. The output is a report that can be viewed in the user interface.

[0134] Step 7:

[0135] The terminal displays a visually generated report to the user through its user interface. Based on this information, the user can make specific decisions regarding security measures. The report's output is used as a countermeasure against security risks.

[0136] 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.

[0137] This invention provides an advanced data analysis system incorporating an emotion engine to enable local governments to efficiently utilize data and support the resolution of regional issues and administrative decision-making. This system is composed of a server, terminals, users, and the emotion engine as its core components.

[0138] The server periodically retrieves the latest statistical data using APIs from external information sources. The data is automatically converted to an internal format and stored in a database. Based on the stored data, differential analysis, longitudinal analysis, trend analysis, etc., are performed, and AI models are used to identify the factors causing data fluctuations.

[0139] The server then automatically generates reports based on the analysis results. The generated reports are visually easy to understand, allowing users to quickly grasp the information. These reports also include comparisons with other municipalities, highlighting the unique challenges and characteristics of the target municipality.

[0140] The terminal serves to provide reports to the user through its user interface. This interface incorporates an emotion engine that understands the user's emotional state. The emotion engine recognizes emotions using user input data, operational actions, and even speech recognition.

[0141] If a user's emotional state is detected, such as anxiety or frustration, the amount of information presented will be reduced, or the user interface will be adjusted with softer colors and messages. Conversely, if the emotion indicates active engagement, the information presented will be made more detailed, or other adjustments will be made to match the user's state.

[0142] Users can operate this system to streamline data-driven decision-making. For example, in financial planning, using the emotion engine displays appropriate information to support favorable policy decisions. This reduces the emotional burden associated with decision-making, enabling users to make more logical and faster judgments.

[0143] Thus, by combining emotion recognition technology, the present invention provides not only a tool for conventional data analysis systems, but also flexible, interactive support functions that respond to the user's emotional state.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The server accesses APIs from external information sources to retrieve the latest municipal statistics data. At this point, an automated scheduling function ensures that data collection is performed periodically.

[0147] Step 2:

[0148] The server analyzes the acquired data and converts it into an internal format suitable for the system. The format conversion is optimized to maintain data integrity while ensuring smooth subsequent processing.

[0149] Step 3:

[0150] The server stores the data, converted to an internal format, in the database. During this process, indexes such as regional ID and year are set to improve data retrieval efficiency.

[0151] Step 4:

[0152] The server utilizes the stored data to perform differential analysis based on indicators. This allows for the identification of numerical differences between the local government and the national average or other benchmarks.

[0153] Step 5:

[0154] The server analyzes the data's changes over time and generates trend lines. Here, data from the past to the present is referenced and graphed to predict long-term trends.

[0155] Step 6:

[0156] The server uses an AI model to perform an analysis of the factors behind data fluctuations. The AI ​​identifies key patterns within the dataset and derives the contributing factors from them.

[0157] Step 7:

[0158] The server automatically generates a report based on these analysis results. The report includes an analysis summary, graphs, and recommendations.

[0159] Step 8:

[0160] The terminal provides the generated report to the user through the user interface. During this process, the emotion engine analyzes the user's actions and input data to estimate their emotional state.

[0161] Step 9:

[0162] The emotion engine adjusts how report content is presented based on the user's emotions. For example, if a user is feeling stressed, it adjusts the interface's color scheme and the amount of information displayed to provide a comfortable user experience.

[0163] Step 10:

[0164] Users view reports on their devices and make decisions tailored to their needs. By providing information that resonates with their emotions, users can utilize the analysis results more effectively.

[0165] Step 11:

[0166] If users require additional information, they can request further analysis from the server via their terminal. This request is processed immediately, and the results are presented quickly.

[0167] (Example 2)

[0168] 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".

[0169] Modern local governments must efficiently utilize vast amounts of data to solve complex social problems in their communities. However, they often lack sufficient support for understanding the results of data analysis and making quick and appropriate decisions based on them, and users may experience emotional burdens during the process. Therefore, a system is needed that not only effectively analyzes data and provides the analysis results in an easily understandable format, but also adapts to the emotional state of the user.

[0170] 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.

[0171] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for storing the converted data in a data set. This makes it possible to efficiently analyze data on complex social issues faced by local governments and present it appropriately based on the user's emotional state, thereby supporting policy decisions and streamlining decision-making.

[0172] "Data" refers to a collection of information obtained from an information source and subjected to processing such as analysis and storage within a system.

[0173] "External information sources" refer to information infrastructure and data provision services that exist outside the system for supplying data.

[0174] "Internal format" refers to the data format that a system uses to convert data obtained from external sources into a format that can be processed.

[0175] A "data collection" refers to a storage or database in which processed data is organized according to certain rules.

[0176] A "server" refers to a computer system that performs roles such as processing, storing, and supplying data over a network.

[0177] A "report" is a document automatically generated based on the results of data analysis, and it includes information presented in a visually easy-to-understand manner.

[0178] "User interface" refers to the screens and operating systems that users directly interact with to view information.

[0179] "Emotional state" refers to the user's psychological and emotional state and reactions, which the system detects through voice tone and input behavior.

[0180] A "generative AI model" refers to a program platform that uses machine learning and artificial intelligence techniques to extract data features and generate insights in processes such as data analysis.

[0181] The system of this invention provides advanced data analysis functions that work collaboratively between servers, terminals, and users to support local government decision-making and problem-solving through data utilization.

[0182] The server first collects the necessary data from external sources using APIs. Specifically, it obtains information related to economic indicators and demographics from publicly available government APIs. The server receives this data in JSON format and applies a data conversion algorithm to automatically convert it to an internal format. The converted data is then stored in a data collection such as an SQL database. This ensures that the data is stored in a format suitable for analysis.

[0183] Furthermore, the server uses the stored data to perform differential and trend analysis. This involves using a generative AI model to identify the factors and trends influencing data fluctuations. The AI ​​model is built on machine learning techniques and extracts meaningful patterns from the accumulated data. Based on the analysis results obtained in this process, the server generates highly visible reports. These reports include graphs and charts and are designed to allow users to easily understand the information.

[0184] The device functions as a connection point to the user and incorporates an emotion engine. The device monitors user input and behavior, analyzing their emotional state. If the user is feeling anxious, it reduces the burden by providing a visually calming user interface and adjusting the amount of information presented. Conversely, if the user shows active engagement, the device dynamically responds by providing more detailed information.

[0185] Users can utilize the information and emotional adaptation features provided through this system to act more logically and quickly in situations such as policy making. For example, in urban planning, the emotional engine improves the quality of decision-making by considering the user's psychological state and presenting optimal data.

[0186] An example of a prompt message is: "Conduct an analysis of the current state of elderly welfare policies in local governments and create a report that includes comparisons with other local governments. The report should also include suggestions based on the user's emotional state using an emotion engine." Based on this prompt, the system will perform the necessary processing and generate an output that meets the objective.

[0187] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0188] Step 1:

[0189] The server retrieves data from external sources. This process involves establishing a secure connection using API keys to obtain data such as economic indicators and population data from publicly available government APIs. The input is raw JSON data obtained from the API, and the output is the retrieved raw data. The server then prepares this data for formatting into its internal format.

[0190] Step 2:

[0191] The server converts the acquired data into an internal format. It applies a conversion algorithm, organizing data, for example, from JSON format into a table format for storage in an SQL database. The input is JSON data, and the output is formatted data in SQL format. This ensures the data is stored in a format suitable for later analysis.

[0192] Step 3:

[0193] The server performs data analysis based on the stored data. It uses generative AI models to identify factors and trends in data fluctuations through differential analysis and trend analysis. For example, it performs regression analysis to identify factors influencing increases and decreases in crime rates. The input is organized data in a SQL database, and the output is the insights gained from the analysis.

[0194] Step 4:

[0195] The server automatically generates a report based on the analysis results. The report is created in a visual format, including graphs and charts, to make it easy for the user to understand. The input is the analysis results, and the output is a visually organized report. This report is saved in PDF or web format and can be used later on the device.

[0196] Step 5:

[0197] The terminal receives reports from the server and displays them through the user interface. During this process, an emotion engine operates, receiving the user's emotional state as input. For example, it determines whether the user is experiencing stress based on click patterns during operation and voice input. The output is an interface adjusted according to the user's emotional state.

[0198] Step 6:

[0199] The device adjusts its display content and interface based on the user's emotions. If the user is showing signs of anxiety, it controls the amount of information displayed and uses calmer colors. The input is the result of the emotion engine's analysis, and the output is the modified interface. This allows the user to receive information without feeling burdened.

[0200] Step 7:

[0201] Users make concrete decisions based on information provided through their devices. Their ability to leverage necessary data and insights to make logical judgments, such as in financial planning, improves. The input is information received through a refined interface, and the output is improved decision-making.

[0202] (Application Example 2)

[0203] 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".

[0204] In local communities and commercial facilities, there is a growing need to understand users' emotional states and provide information adaptively based on those states to reduce the burden of decision-making and provide more satisfying experiences. Conventional systems have struggled to provide dynamic information that responds to users' emotions, and have faced challenges such as user stress and information overload due to the provision of fixed information.

[0205] 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.

[0206] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for understanding the emotional state based on the stored data and adapting the presentation of information accordingly. This makes it possible to provide information that is tailored to the emotional state of the user.

[0207] "Data" refers to a collection of information that a server acquires from external sources, converts to an internal format, and stores.

[0208] An "external information source" is an information source that serves as an external source of data for obtaining data.

[0209] An "internal format" is a format used to organize acquired data and convert it into a format usable within the system.

[0210] "Information structure" refers to databases and storage systems used to systematically store converted data.

[0211] "Difference analysis" is a method for evaluating changes or differences in a specific indicator based on stored data.

[0212] A "trend line" is a straight or curved line used to visually represent year-to-year changes based on historical data.

[0213] An "instruction manual" is a document that is automatically generated based on the analysis results and provides information to the user.

[0214] A "distinctive difference" refers to a unique change or characteristic observed in specific data compared to other data.

[0215] "Device" refers to a hardware or software system equipped with a user interface that understands the user's emotional state and adjusts the presentation of information accordingly.

[0216] "Emotional state" refers to the psychological or sensory state exhibited by the user, and is an important factor to consider when providing information.

[0217] This invention provides a system that improves the customer experience in local communities and commercial facilities by providing information tailored to the customer's emotional state.

[0218] The server has the function of acquiring data from external sources, converting it to an internal format, and storing it in an information structure. This includes connections via APIs to periodically acquire information from external data sources, and software to convert the data into a format that can be processed within the system. The converted data is then stored in a database as an information structure.

[0219] The device will provide information through its user interface and utilize an emotion engine to understand the user's emotional state. Specifically, it will implement an emotion recognition system that combines eye-tracking and voice recognition technologies using user devices such as smart glasses and head-mounted displays. This system will evaluate the user's emotions, such as joy, confusion, and interest, in real time and optimize the information presentation.

[0220] By wearing smart glasses and walking around a store, users can receive new product information and services based on their emotions. For example, if they show interest, detailed information and best practices for the corresponding product will be displayed on the glasses' screen. On the other hand, if confusion is detected, the amount of information will be reduced and the interface will switch to a more reassuring color scheme.

[0221] As a concrete example, when a customer visits the electronics section, the system detects their "interest" from their facial expression and displays the latest reviews and usage instructions for that product on their glasses. Furthermore, it utilizes "generating AI models and prompt sentences" to generate prompts and provide information, such as: "We want to improve user interaction based on emotion recognition in our smart glasses app for physical stores. Please tell us how to build a system that detects interest and confusion and displays appropriate product information and suggestions."

[0222] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0223] Step 1:

[0224] The server retrieves data from an external source using an API. The API endpoint of the external source is required as input, and the output contains the retrieved raw data. This data is passed to the server in JSON or XML format.

[0225] Step 2:

[0226] The server converts the acquired data into an internal format. The input is the raw data obtained in step 1, and the output is in a format that can be processed internally. The conversion process uses a JSON parser and custom scripts to extract the necessary items and organize them into a data frame.

[0227] Step 3:

[0228] The server stores the converted data in an information structure. The input is internally formatted data, and the output is the state in which it is stored in the database. Here, SQL queries or database APIs are used to write to the database.

[0229] Step 4:

[0230] The device uses sensors in smart glasses to detect the user's emotional state in real time. Inputs are camera images and audio data, and output is data representing the emotion recognition results. The emotion engine uses a facial recognition algorithm and an audio analysis model to evaluate the user's emotions.

[0231] Step 5:

[0232] The terminal displays appropriate information on the user interface according to the emotional state. The input is the emotion recognition result from step 4 and product information obtained from the server, and the output is a visualized information display. For example, if "interest" is detected, detailed product information will be displayed on the screen.

[0233] Step 6:

[0234] The user makes decisions based on information presented by the smart glasses. The input is the information displayed by the device, and the output is the purchase decision or the choice of the next action. The user's actions are fed back into step 4 as data for the next emotional evaluation. This loop continues until the user leaves the store.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] [Second Embodiment]

[0239] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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).

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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".

[0251] This invention provides a system that enables local governments to efficiently utilize data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a specific role.

[0252] First, the server retrieves data from external sources. By regularly collecting statistical data from local governments and the national government using APIs, it is possible to quickly incorporate the latest information into the system. The retrieved data is automatically converted into the necessary format and stored in a database. This stored data forms the basis for subsequent analysis.

[0253] Next, the server performs analysis based on the stored data. Using the difference analysis function, it can compare the differences between the local statistical data and the national statistical data. Furthermore, longitudinal analysis makes it possible to understand past trends and predict future trends. By using AI models, important factors can be identified from the data, and detailed factor analysis can be performed.

[0254] The analysis results are automatically generated as a report by the server. This report consists of visual graphs and text, presenting information in an easy-to-understand format for the user. Furthermore, it allows for comparison with data from other municipalities with similar functionality, helping to identify challenges specific to one's own region.

[0255] The terminal provides users with generated reports and analysis results through a user interface. Users can access the system via this terminal and request further in-depth data analysis or the generation of additional reports as needed.

[0256] By utilizing the above functions, users can make important decisions in local government administration quickly and rationally. For example, by quickly grasping changes in the financial situation and taking necessary measures in advance, they can improve the quality of services to local residents. In this way, the present invention streamlines local government operations and supports the formation of excellent data-driven policies.

[0257] The following describes the processing flow.

[0258] Step 1:

[0259] The server accesses APIs from external information sources to periodically retrieve the latest statistical data. A schedule is set to manage this process, ensuring that data collection is performed automatically.

[0260] Step 2:

[0261] The server converts the acquired data into a format that can be used internally. For example, it might convert JSON data to CSV format so that it can be used efficiently in subsequent processing.

[0262] Step 3:

[0263] The server saves the converted data to a database. The data is saved in an easily accessible format by setting keys such as regional ID and year.

[0264] Step 4:

[0265] The server performs a difference analysis on specific indicators based on the information stored in the database. This reveals and displays the numerical differences between the target municipality and the national average.

[0266] Step 5:

[0267] The server performs a year-on-year analysis based on historical data and generates trend lines. During this process, it graphs the year-to-year changes in numerical values, visually illustrating long-term trends.

[0268] Step 6:

[0269] The server uses an AI model to analyze the factors behind data fluctuations. The AI ​​detects specific patterns and anomalies within the data and identifies the underlying causes based on these findings.

[0270] Step 7:

[0271] The server aggregates the analysis results and automatically generates a report. The report is structured in an easy-to-understand format, including a summary of the analyzed data and graphs illustrating the results.

[0272] Step 8:

[0273] The server compares the data with that of other municipalities of similar size to identify distinctive differences. This highlights the unique challenges specific to the target municipality.

[0274] Step 9:

[0275] The terminal provides the user with the generated report through its user interface. Based on this information, the user can quickly identify the issues they need to address.

[0276] Step 10:

[0277] Users can request more in-depth information about specific data analyses through their devices. This request is immediately transmitted to the server.

[0278] Step 11:

[0279] Based on user requests, the server performs additional data analysis and generates a new report. This provides more detailed information to support decision-making.

[0280] (Example 1)

[0281] 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."

[0282] Local governments are required to efficiently utilize the latest data to solve regional issues and support administrative decision-making. Existing systems often manage each stage of data collection, transformation, storage, analysis, and reporting individually, making integrated and timely information provision difficult. Furthermore, comparing various data and predicting trends is time-consuming, hindering the efficient use of time and resources.

[0283] 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.

[0284] In this invention, the server includes means for acquiring data from an information source of a public institution, means for converting the acquired data into a standard format, and means for storing the converted data in a storage device. As a result, efficient data collection, storage, and utilization become possible.

[0285] "Data" is a collection of information and is what is collected, processed, and stored by a computer.

[0286] "Information source of a public institution" refers to official information provided by local governments, national agencies, etc.

[0287] "Standard format" is a format defined to ensure data compatibility and readability.

[0288] "Storage device" is a part of hardware or software for long-term storage of information.

[0289] "Difference in indicators" refers to the differences in characteristics and trends in different data sets.

[0290] "Variation by date and time" refers to the changes in data observed at specific time intervals.

[0291] "Prediction curve" is a graph for estimating future trends based on past data.

[0292] "Report" is an information document presenting analysis results and conclusions in a documented form.

[0293] "User operation screen" is a visual interface for a user to interact with the system and obtain information.

[0294] "Machine learning model" is an algorithm for automatically learning patterns from data and performing prediction and classification.

[0295] This invention is a system for local governments to effectively utilize various types of data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a different role.

[0296] The server retrieves data from external public information sources via APIs. The retrieved data is converted to a standard format using libraries such as Python's Pandas library and stored in a database system, such as PostgreSQL. Based on the stored data, the server performs data analysis using machine learning models. This analysis includes techniques using TensorFlow and PyTorch to evaluate differences in metrics and daily fluctuations, and to generate prediction curves necessary for future forecasting. The analysis results are visualized using Matplotlib and D3.js and automatically formatted into a report.

[0297] The terminal provides a user interface that allows users to access and view generated reports and analysis results. This interface is implemented using React.js and Vue.js, enabling interactive user operation.

[0298] Users obtain system information via their terminals and request more detailed analysis or the generation of additional reports. For example, if a user wants to know about trends in financial data, they would enter the following as a prompt:

[0299] "Based on the fiscal balance data for the past three years, analyze the trends in increases and decreases for each expenditure item and assess their impact on next year's budget plan."

[0300] This system enables local governments to formulate data-driven, logical, and rapid policies, contributing to improved quality of services for residents.

[0301] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0302] Step 1:

[0303] The server retrieves data from an external public institution information source. At this time, the server uses an API to connect to the database in real time and extracts the necessary dataset. The input is raw data from the external information source, and the output is the unprocessed data stored in the server.

[0304] Step 2:

[0305] The server converts the retrieved raw data into a standard format. For this conversion, the Pandas library of Python is used to format the data and complete missing values. The input is the unprocessed data, and the output is the data converted into the standard format.

[0306] Step 3:

[0307] The server saves the converted data into a relational database. Here, PostgreSQL is used to efficiently store the organized data in preparation for later analysis. The input is the data in the standard format, and the output is the data managed within the database.

[0308] Step 4:

[0309] The server performs analysis based on the saved data. Using a machine learning model, it analyzes the differences in metrics between data and the variations over time. TensorFlow or PyTorch is utilized in this process to conduct trend analysis and prediction. The input is the data retrieved from the database, and the output is the analysis result.

[0310] Step 5:

[0311] The server visualizes the analysis result and automatically generates a report. Matplotlib or D3.js is used to create graphs, and a report containing text information is created in PDF or HTML format. The input is the analysis result, and the output is the report provided to the user.

[0312] Step 6:

[0313] The terminal presents the generated reports and analysis results to the user. It provides a graphical user interface using React.js and Vue.js, allowing users to view and further manipulate the visualized information. The input is the generated report, and the output is the screen display accessible to the user.

[0314] Step 7:

[0315] Users access the system to request detailed analysis or the generation of additional reports. For example, they might request a detailed trend analysis based on historical financial data using a prompt. The input is the user's request or prompt, and the output is the newly generated analysis or report.

[0316] (Application Example 1)

[0317] 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."

[0318] In modern society, security risks are increasing, and real-time information gathering and rapid risk assessment are required. However, current systems have limited means of efficiently acquiring and analyzing the latest security information, making it particularly difficult for individuals and small organizations to respond quickly to risks.

[0319] 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.

[0320] In this invention, the server includes means for acquiring data from external information sources, means for evaluating security risks and providing the results visually to the user, and means for comparing its own data with other data and identifying characteristic differences. This enables real-time identification of security risks and rapid response.

[0321] "Means of obtaining data from external sources" refers to functions for collecting necessary information through external databases or APIs.

[0322] "Means of converting to an internal format" refers to a function that converts acquired data into a format that is easy for the system to process.

[0323] "Means of saving to a database" refers to the function of storing converted data in order to effectively manage it.

[0324] "Methods for performing difference analysis on specific indicators" refer to methods that calculate the differences in numerical values ​​between different datasets and use the results to find specific trends or patterns.

[0325] "A method for analyzing year-to-year changes using historical data and generating trend lines" refers to a function that analyzes data fluctuations over time and draws lines to predict future trends.

[0326] "Methods for automatically generating reports" refers to functions that generate documents based on analysis results and compile information.

[0327] "Means for identifying distinctive differences" refers to methods for finding particularly noteworthy differences among data points being compared.

[0328] "A means of assessing security risks and providing the results to users visually" refers to a function that analyzes potential threats and communicates that information to users in a graphical format.

[0329] In this embodiment of the invention, the server functions as follows: The server retrieves information from an external security database using an API and converts the data into an internally specific format. It also efficiently stores the converted data in the database. This allows for rapid access while maintaining data integrity. The server then performs differential analysis based on the stored data to assess security risks. Using an AI model, it is possible to analyze the factors causing data fluctuations in detail and automatically generate a report based on the analysis results. This report is displayed to the user through a user interface, allowing them to understand the security situation in real time.

[0330] In terms of hardware, a server with a high-performance processor and sufficient data storage capacity is required. In terms of software, a data processing program using Python and an AI model implementation using TensorFlow will be necessary.

[0331] As a concrete example, this system could be used by small organizations that want to strengthen their defenses against specific cyberattacks in their daily operations. The server can analyze information obtained from external data and send a request to a generating AI model using a prompt message such as, "Predict security risks based on recent cyberattack trends and propose specific countermeasures." This makes it possible to quickly implement practical defensive measures based on the provided data.

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

[0333] Step 1:

[0334] The server accesses an external security database via an API to retrieve the latest security-related data. Because this input data has an external format and structure, it needs to be in a standardized format. For example, it accepts data in CSV or JSON format.

[0335] Step 2:

[0336] The server converts the acquired data into an internal format. Specifically, it analyzes the data structure and extracts the necessary fields to format it for analysis. This process involves removing unnecessary data and standardizing data types. The output is a well-organized dataset.

[0337] Step 3:

[0338] The server saves the converted data to the database. Transactional processing is performed during this saving process to maintain data consistency and integrity. The saved data is then ready for use in subsequent analysis.

[0339] Step 4:

[0340] The server performs differential analysis using the stored data. Specifically, it compares past data with current data to detect statistically significant changes. The output obtained from this analysis is an indicator showing the trend of increasing or decreasing risk.

[0341] Step 5:

[0342] The server utilizes an AI model to identify factors influencing data fluctuations and conduct a detailed risk analysis. The AI ​​model compares past data patterns with current data to predict potential risk factors. The output is a risk factor analysis report.

[0343] Step 6:

[0344] The server automatically generates a report based on the analysis results and sends it to the terminal. This report includes visual graphs and text information and is converted into a format that is easy for the user to understand. The output is a report that can be viewed in the user interface.

[0345] Step 7:

[0346] The terminal displays a visually generated report to the user through its user interface. Based on this information, the user can make specific decisions regarding security measures. The report's output is used as a countermeasure against security risks.

[0347] 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.

[0348] This invention provides an advanced data analysis system incorporating an emotion engine to enable local governments to efficiently utilize data and support the resolution of regional issues and administrative decision-making. This system is composed of a server, terminals, users, and the emotion engine as its core components.

[0349] The server periodically retrieves the latest statistical data using APIs from external information sources. The data is automatically converted to an internal format and stored in a database. Based on the stored data, differential analysis, longitudinal analysis, trend analysis, etc., are performed, and AI models are used to identify the factors causing data fluctuations.

[0350] The server then automatically generates reports based on the analysis results. The generated reports are visually easy to understand, allowing users to quickly grasp the information. These reports also include comparisons with other municipalities, highlighting the unique challenges and characteristics of the target municipality.

[0351] The terminal serves to provide reports to the user through its user interface. This interface incorporates an emotion engine that understands the user's emotional state. The emotion engine recognizes emotions using user input data, operational actions, and even speech recognition.

[0352] If a user's emotional state is detected, such as anxiety or frustration, the amount of information presented will be reduced, or the user interface will be adjusted with softer colors and messages. Conversely, if the emotion indicates active engagement, the information presented will be made more detailed, or other adjustments will be made to match the user's state.

[0353] Users can operate this system to streamline data-driven decision-making. For example, in financial planning, using the emotion engine displays appropriate information to support favorable policy decisions. This reduces the emotional burden associated with decision-making, enabling users to make more logical and faster judgments.

[0354] Thus, by combining emotion recognition technology, the present invention provides not only a tool for conventional data analysis systems, but also flexible, interactive support functions that respond to the user's emotional state.

[0355] The following describes the processing flow.

[0356] Step 1:

[0357] The server accesses APIs from external information sources to retrieve the latest municipal statistics data. At this point, an automated scheduling function ensures that data collection is performed periodically.

[0358] Step 2:

[0359] The server analyzes the acquired data and converts it into an internal format suitable for the system. The format conversion is optimized to maintain data integrity while ensuring smooth subsequent processing.

[0360] Step 3:

[0361] The server stores the data, converted to an internal format, in the database. During this process, indexes such as regional ID and year are set to improve data retrieval efficiency.

[0362] Step 4:

[0363] The server utilizes the stored data to perform differential analysis based on indicators. This allows for the identification of numerical differences between the local government and the national average or other benchmarks.

[0364] Step 5:

[0365] The server analyzes the data's changes over time and generates trend lines. Here, data from the past to the present is referenced and graphed to predict long-term trends.

[0366] Step 6:

[0367] The server uses an AI model to perform an analysis of the factors behind data fluctuations. The AI ​​identifies key patterns within the dataset and derives the contributing factors from them.

[0368] Step 7:

[0369] The server automatically generates a report based on these analysis results. The report includes an analysis summary, graphs, and recommendations.

[0370] Step 8:

[0371] The terminal provides the generated report to the user through the user interface. During this process, the emotion engine analyzes the user's actions and input data to estimate their emotional state.

[0372] Step 9:

[0373] The emotion engine adjusts how report content is presented based on the user's emotions. For example, if a user is feeling stressed, it adjusts the interface's color scheme and the amount of information displayed to provide a comfortable user experience.

[0374] Step 10:

[0375] Users view reports on their devices and make decisions tailored to their needs. By providing information that resonates with their emotions, users can utilize the analysis results more effectively.

[0376] Step 11:

[0377] If users require additional information, they can request further analysis from the server via their terminal. This request is processed immediately, and the results are presented quickly.

[0378] (Example 2)

[0379] 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".

[0380] Modern local governments must efficiently utilize vast amounts of data to solve complex social problems in their communities. However, they often lack sufficient support for understanding the results of data analysis and making quick and appropriate decisions based on them, and users may experience emotional burdens during the process. Therefore, a system is needed that not only effectively analyzes data and provides the analysis results in an easily understandable format, but also adapts to the emotional state of the user.

[0381] 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.

[0382] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for storing the converted data in a data set. This makes it possible to efficiently analyze data on complex social issues faced by local governments and present it appropriately based on the user's emotional state, thereby supporting policy decisions and streamlining decision-making.

[0383] "Data" refers to a collection of information obtained from an information source and subjected to processing such as analysis and storage within a system.

[0384] "External information sources" refer to information infrastructure and data provision services that exist outside the system for supplying data.

[0385] "Internal format" refers to the data format that a system uses to convert data obtained from external sources into a format that can be processed.

[0386] A "data collection" refers to a storage or database in which processed data is organized according to certain rules.

[0387] A "server" refers to a computer system that performs roles such as processing, storing, and supplying data over a network.

[0388] A "report" is a document automatically generated based on the results of data analysis, and it includes information presented in a visually easy-to-understand manner.

[0389] "User interface" refers to the screens and operating systems that users directly interact with to view information.

[0390] "Emotional state" refers to the user's psychological and emotional state and reactions, which the system detects through voice tone and input behavior.

[0391] A "generative AI model" refers to a program platform that uses machine learning and artificial intelligence techniques to extract data features and generate insights in processes such as data analysis.

[0392] The system of this invention provides advanced data analysis functions that work collaboratively between servers, terminals, and users to support local government decision-making and problem-solving through data utilization.

[0393] The server first collects the necessary data from external sources using APIs. Specifically, it obtains information related to economic indicators and demographics from publicly available government APIs. The server receives this data in JSON format and applies a data conversion algorithm to automatically convert it to an internal format. The converted data is then stored in a data collection such as an SQL database. This ensures that the data is stored in a format suitable for analysis.

[0394] Furthermore, the server uses the stored data to perform differential and trend analysis. This involves using a generative AI model to identify the factors and trends influencing data fluctuations. The AI ​​model is built on machine learning techniques and extracts meaningful patterns from the accumulated data. Based on the analysis results obtained in this process, the server generates highly visible reports. These reports include graphs and charts and are designed to allow users to easily understand the information.

[0395] The device functions as a connection point to the user and incorporates an emotion engine. The device monitors user input and behavior, analyzing their emotional state. If the user is feeling anxious, it reduces the burden by providing a visually calming user interface and adjusting the amount of information presented. Conversely, if the user shows active engagement, the device dynamically responds by providing more detailed information.

[0396] Users can utilize the information and emotional adaptation features provided through this system to act more logically and quickly in situations such as policy making. For example, in urban planning, the emotional engine improves the quality of decision-making by considering the user's psychological state and presenting optimal data.

[0397] An example of a prompt message is: "Conduct an analysis of the current state of elderly welfare policies in local governments and create a report that includes comparisons with other local governments. The report should also include suggestions based on the user's emotional state using an emotion engine." Based on this prompt, the system will perform the necessary processing and generate an output that meets the objective.

[0398] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0399] Step 1:

[0400] The server retrieves data from external sources. This process involves establishing a secure connection using API keys to obtain data such as economic indicators and population data from publicly available government APIs. The input is raw JSON data obtained from the API, and the output is the retrieved raw data. The server then prepares this data for formatting into its internal format.

[0401] Step 2:

[0402] The server converts the acquired data into an internal format. It applies a conversion algorithm, organizing data, for example, from JSON format into a table format for storage in an SQL database. The input is JSON data, and the output is formatted data in SQL format. This ensures the data is stored in a format suitable for later analysis.

[0403] Step 3:

[0404] The server performs data analysis based on the stored data. It uses generative AI models to identify factors and trends in data fluctuations through differential analysis and trend analysis. For example, it performs regression analysis to identify factors influencing increases and decreases in crime rates. The input is organized data in a SQL database, and the output is the insights gained from the analysis.

[0405] Step 4:

[0406] The server automatically generates a report based on the analysis results. The report is created in a visual format, including graphs and charts, to make it easy for the user to understand. The input is the analysis results, and the output is a visually organized report. This report is saved in PDF or web format and can be used later on the device.

[0407] Step 5:

[0408] The terminal receives reports from the server and displays them through the user interface. During this process, an emotion engine operates, receiving the user's emotional state as input. For example, it determines whether the user is experiencing stress based on click patterns during operation and voice input. The output is an interface adjusted according to the user's emotional state.

[0409] Step 6:

[0410] The device adjusts its display content and interface based on the user's emotions. If the user is showing signs of anxiety, it controls the amount of information displayed and uses calmer colors. The input is the result of the emotion engine's analysis, and the output is the modified interface. This allows the user to receive information without feeling burdened.

[0411] Step 7:

[0412] Users make concrete decisions based on information provided through their devices. Their ability to leverage necessary data and insights to make logical judgments, such as in financial planning, improves. The input is information received through a refined interface, and the output is improved decision-making.

[0413] (Application Example 2)

[0414] 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."

[0415] In local communities and commercial facilities, there is a growing need to understand users' emotional states and provide information adaptively based on those states to reduce the burden of decision-making and provide more satisfying experiences. Conventional systems have struggled to provide dynamic information that responds to users' emotions, and have faced challenges such as user stress and information overload due to the provision of fixed information.

[0416] 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.

[0417] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for understanding the emotional state based on the stored data and adapting the presentation of information accordingly. This makes it possible to provide information that is tailored to the emotional state of the user.

[0418] "Data" refers to a collection of information that a server acquires from external sources, converts to an internal format, and stores.

[0419] An "external information source" is an information source that serves as an external source of data for obtaining data.

[0420] An "internal format" is a format used to organize acquired data and convert it into a format usable within the system.

[0421] "Information structure" refers to databases and storage systems used to systematically store converted data.

[0422] "Difference analysis" is a method for evaluating changes or differences in a specific indicator based on stored data.

[0423] A "trend line" is a straight or curved line used to visually represent year-to-year changes based on historical data.

[0424] An "instruction manual" is a document that is automatically generated based on the analysis results and provides information to the user.

[0425] A "distinctive difference" refers to a unique change or characteristic observed in specific data compared to other data.

[0426] "Device" refers to a hardware or software system equipped with a user interface that understands the user's emotional state and adjusts the presentation of information accordingly.

[0427] "Emotional state" refers to the psychological or sensory state exhibited by the user, and is an important factor to consider when providing information.

[0428] This invention provides a system that improves the customer experience in local communities and commercial facilities by providing information tailored to the customer's emotional state.

[0429] The server has the function of acquiring data from external sources, converting it to an internal format, and storing it in an information structure. This includes connections via APIs to periodically acquire information from external data sources, and software to convert the data into a format that can be processed within the system. The converted data is then stored in a database as an information structure.

[0430] The device will provide information through its user interface and utilize an emotion engine to understand the user's emotional state. Specifically, it will implement an emotion recognition system that combines eye-tracking and voice recognition technologies using user devices such as smart glasses and head-mounted displays. This system will evaluate the user's emotions, such as joy, confusion, and interest, in real time and optimize the information presentation.

[0431] By wearing smart glasses and walking around a store, users can receive new product information and services based on their emotions. For example, if they show interest, detailed information and best practices for the corresponding product will be displayed on the glasses' screen. On the other hand, if confusion is detected, the amount of information will be reduced and the interface will switch to a more reassuring color scheme.

[0432] As a concrete example, when a customer visits the electronics section, the system detects their "interest" from their facial expression and displays the latest reviews and usage instructions for that product on their glasses. Furthermore, it utilizes "generating AI models and prompt sentences" to generate prompts and provide information, such as: "We want to improve user interaction based on emotion recognition in our smart glasses app for physical stores. Please tell us how to build a system that detects interest and confusion and displays appropriate product information and suggestions."

[0433] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0434] Step 1:

[0435] The server retrieves data from an external source using an API. The API endpoint of the external source is required as input, and the output contains the retrieved raw data. This data is passed to the server in JSON or XML format.

[0436] Step 2:

[0437] The server converts the acquired data into an internal format. The input is the raw data obtained in step 1, and the output is in a format that can be processed internally. The conversion process uses a JSON parser and custom scripts to extract the necessary items and organize them into a data frame.

[0438] Step 3:

[0439] The server stores the converted data in an information structure. The input is internally formatted data, and the output is the state in which it is stored in the database. Here, SQL queries or database APIs are used to write to the database.

[0440] Step 4:

[0441] The device uses sensors in smart glasses to detect the user's emotional state in real time. Inputs are camera images and audio data, and output is data representing the emotion recognition results. The emotion engine uses a facial recognition algorithm and an audio analysis model to evaluate the user's emotions.

[0442] Step 5:

[0443] The terminal displays appropriate information on the user interface according to the emotional state. The input is the emotion recognition result from step 4 and product information obtained from the server, and the output is a visualized information display. For example, if "interest" is detected, detailed product information will be displayed on the screen.

[0444] Step 6:

[0445] The user makes decisions based on information presented by the smart glasses. The input is the information displayed by the device, and the output is the purchase decision or the choice of the next action. The user's actions are fed back into step 4 as data for the next emotional evaluation. This loop continues until the user leaves the store.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] [Third Embodiment]

[0450] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0451] 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.

[0452] 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).

[0453] 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.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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".

[0462] This invention provides a system that enables local governments to efficiently utilize data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a specific role.

[0463] First, the server retrieves data from external sources. By regularly collecting statistical data from local governments and the national government using APIs, it is possible to quickly incorporate the latest information into the system. The retrieved data is automatically converted into the necessary format and stored in a database. This stored data forms the basis for subsequent analysis.

[0464] Next, the server performs analysis based on the stored data. Using the difference analysis function, it can compare the differences between the local statistical data and the national statistical data. Furthermore, longitudinal analysis makes it possible to understand past trends and predict future trends. By using AI models, important factors can be identified from the data, and detailed factor analysis can be performed.

[0465] The analysis results are automatically generated as a report by the server. This report consists of visual graphs and text, presenting information in an easy-to-understand format for the user. Furthermore, it allows for comparison with data from other municipalities with similar functionality, helping to identify challenges specific to one's own region.

[0466] The terminal provides users with generated reports and analysis results through a user interface. Users can access the system via this terminal and request further in-depth data analysis or the generation of additional reports as needed.

[0467] By utilizing the above functions, users can make important decisions in local government administration quickly and rationally. For example, by quickly grasping changes in the financial situation and taking necessary measures in advance, they can improve the quality of services to local residents. In this way, the present invention streamlines local government operations and supports the formation of excellent data-driven policies.

[0468] The following describes the processing flow.

[0469] Step 1:

[0470] The server accesses APIs from external information sources to periodically retrieve the latest statistical data. A schedule is set to manage this process, ensuring that data collection is performed automatically.

[0471] Step 2:

[0472] The server converts the acquired data into a format that can be used internally. For example, it might convert JSON data to CSV format so that it can be used efficiently in subsequent processing.

[0473] Step 3:

[0474] The server saves the converted data to a database. The data is saved in an easily accessible format by setting keys such as regional ID and year.

[0475] Step 4:

[0476] The server performs a difference analysis on specific indicators based on the information stored in the database. This reveals and displays the numerical differences between the target municipality and the national average.

[0477] Step 5:

[0478] The server performs a year-on-year analysis based on historical data and generates trend lines. During this process, it graphs the year-to-year changes in numerical values, visually illustrating long-term trends.

[0479] Step 6:

[0480] The server uses an AI model to analyze the factors behind data fluctuations. The AI ​​detects specific patterns and anomalies within the data and identifies the underlying causes based on these findings.

[0481] Step 7:

[0482] The server aggregates the analysis results and automatically generates a report. The report is structured in an easy-to-understand format, including a summary of the analyzed data and graphs illustrating the results.

[0483] Step 8:

[0484] The server compares the data with that of other municipalities of similar size to identify distinctive differences. This highlights the unique challenges specific to the target municipality.

[0485] Step 9:

[0486] The terminal provides the user with the generated report through its user interface. Based on this information, the user can quickly identify the issues they need to address.

[0487] Step 10:

[0488] Users can request more in-depth information about specific data analyses through their devices. This request is immediately transmitted to the server.

[0489] Step 11:

[0490] Based on user requests, the server performs additional data analysis and generates a new report. This provides more detailed information to support decision-making.

[0491] (Example 1)

[0492] 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."

[0493] Local governments are required to efficiently utilize the latest data to solve regional issues and support administrative decision-making. Existing systems often manage each stage of data collection, transformation, storage, analysis, and reporting individually, making integrated and timely information provision difficult. Furthermore, comparing various data and predicting trends is time-consuming, hindering the efficient use of time and resources.

[0494] 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.

[0495] In this invention, the server includes means for acquiring data from public information sources, means for converting the acquired data into a standard format, and means for storing the converted data in a storage device. This enables efficient data collection, storage, and utilization.

[0496] "Data" is a collection of information that is collected, processed, and stored by a computer.

[0497] "Public information sources" refer to official information provided by local governments, national agencies, and other similar organizations.

[0498] A "standard format" is a format established to ensure data compatibility and readability.

[0499] A "storage device" is a piece of hardware or software used to store information for the long term.

[0500] "Differences in metrics" refers to differences in characteristics and trends across different datasets.

[0501] "Daily variation" refers to changes in data observed at specific time intervals.

[0502] A "prediction curve" is a graph used to estimate future trends based on past data.

[0503] A "report" is an informational document that presents analysis results and conclusions in a documented format.

[0504] A "user interface" is a visual interface that allows users to interact with the system and obtain information.

[0505] A "machine learning model" is an algorithm that automatically learns patterns from data to perform predictions and classifications.

[0506] This invention is a system for local governments to effectively utilize various types of data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a different role.

[0507] The server retrieves data from external public information sources via APIs. The retrieved data is converted to a standard format using libraries such as Python's Pandas library and stored in a database system, such as PostgreSQL. Based on the stored data, the server performs data analysis using machine learning models. This analysis includes techniques using TensorFlow and PyTorch to evaluate differences in metrics and daily fluctuations, and to generate prediction curves necessary for future forecasting. The analysis results are visualized using Matplotlib and D3.js and automatically formatted into a report.

[0508] The terminal provides a user interface that allows users to access and view generated reports and analysis results. This interface is implemented using React.js and Vue.js, enabling interactive user operation.

[0509] Users obtain system information via their terminals and request more detailed analysis or the generation of additional reports. For example, if a user wants to know about trends in financial data, they would enter the following as a prompt:

[0510] "Based on the fiscal balance data for the past three years, analyze the trends in increases and decreases for each expenditure item and assess their impact on next year's budget plan."

[0511] This system enables local governments to formulate data-driven, logical, and rapid policies, contributing to improved quality of services for residents.

[0512] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0513] Step 1:

[0514] The server retrieves data from external public information sources. In this process, the server uses an API to connect to the database in real time and retrieve the necessary datasets. The input is raw data from the external information source, and the output is unprocessed data stored within the server.

[0515] Step 2:

[0516] The server converts the acquired raw data into a standard format. This conversion uses the Python Pandas library to format the data and impute missing values. The input is the raw data, and the output is the data converted to the standard format.

[0517] Step 3:

[0518] The server stores the transformed data in a relational database. PostgreSQL is used here to efficiently store the organized data and prepare it for later analysis. The input is data in a standard format, and the output is data managed within the database.

[0519] Step 4:

[0520] The server performs analysis based on stored data. It uses machine learning models to analyze differences in metrics between data points and daily fluctuations. This process utilizes TensorFlow and PyTorch to perform trend analysis and prediction. The input is data retrieved from the database, and the output is the analysis results.

[0521] Step 5:

[0522] The server visualizes the analysis results and automatically generates reports. It uses Matplotlib and D3.js to create graphs and generates reports containing text information in PDF or HTML format. The input is the analysis results, and the output is the report provided to the user.

[0523] Step 6:

[0524] The terminal presents the generated reports and analysis results to the user. It provides a graphical user interface using React.js and Vue.js, allowing users to view and further manipulate the visualized information. The input is the generated report, and the output is the screen display accessible to the user.

[0525] Step 7:

[0526] Users access the system to request detailed analysis or the generation of additional reports. For example, they might request a detailed trend analysis based on historical financial data using a prompt. The input is the user's request or prompt, and the output is the newly generated analysis or report.

[0527] (Application Example 1)

[0528] 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."

[0529] In modern society, security risks are increasing, and real-time information gathering and rapid risk assessment are required. However, current systems have limited means of efficiently acquiring and analyzing the latest security information, making it particularly difficult for individuals and small organizations to respond quickly to risks.

[0530] 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.

[0531] In this invention, the server includes means for acquiring data from external information sources, means for evaluating security risks and providing the results visually to the user, and means for comparing its own data with other data and identifying characteristic differences. This enables real-time identification of security risks and rapid response.

[0532] "Means of obtaining data from external sources" refers to functions for collecting necessary information through external databases or APIs.

[0533] "Means of converting to an internal format" refers to a function that converts acquired data into a format that is easy for the system to process.

[0534] "Means of saving to a database" refers to the function of storing converted data in order to effectively manage it.

[0535] "Methods for performing difference analysis on specific indicators" refer to methods that calculate the differences in numerical values ​​between different datasets and use the results to find specific trends or patterns.

[0536] "A method for analyzing year-to-year changes using historical data and generating trend lines" refers to a function that analyzes data fluctuations over time and draws lines to predict future trends.

[0537] "Methods for automatically generating reports" refers to functions that generate documents based on analysis results and compile information.

[0538] "Means for identifying distinctive differences" refers to methods for finding particularly noteworthy differences among data points being compared.

[0539] "A means of assessing security risks and providing the results to users visually" refers to a function that analyzes potential threats and communicates that information to users in a graphical format.

[0540] In this embodiment of the invention, the server functions as follows: The server retrieves information from an external security database using an API and converts the data into an internally specific format. It also efficiently stores the converted data in the database. This allows for rapid access while maintaining data integrity. The server then performs differential analysis based on the stored data to assess security risks. Using an AI model, it is possible to analyze the factors causing data fluctuations in detail and automatically generate a report based on the analysis results. This report is displayed to the user through a user interface, allowing them to understand the security situation in real time.

[0541] In terms of hardware, a server with a high-performance processor and sufficient data storage capacity is required. In terms of software, a data processing program using Python and an AI model implementation using TensorFlow will be necessary.

[0542] As a concrete example, this system could be used by small organizations that want to strengthen their defenses against specific cyberattacks in their daily operations. The server can analyze information obtained from external data and send a request to a generating AI model using a prompt message such as, "Predict security risks based on recent cyberattack trends and propose specific countermeasures." This makes it possible to quickly implement practical defensive measures based on the provided data.

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

[0544] Step 1:

[0545] The server accesses an external security database via an API to retrieve the latest security-related data. Because this input data has an external format and structure, it needs to be in a standardized format. For example, it accepts data in CSV or JSON format.

[0546] Step 2:

[0547] The server converts the acquired data into an internal format. Specifically, it analyzes the data structure and extracts the necessary fields to format it for analysis. This process involves removing unnecessary data and standardizing data types. The output is a well-organized dataset.

[0548] Step 3:

[0549] The server saves the converted data to the database. Transactional processing is performed during this saving process to maintain data consistency and integrity. The saved data is then ready for use in subsequent analysis.

[0550] Step 4:

[0551] The server performs differential analysis using the stored data. Specifically, it compares past data with current data to detect statistically significant changes. The output obtained from this analysis is an indicator showing the trend of increasing or decreasing risk.

[0552] Step 5:

[0553] The server utilizes an AI model to identify factors influencing data fluctuations and conduct a detailed risk analysis. The AI ​​model compares past data patterns with current data to predict potential risk factors. The output is a risk factor analysis report.

[0554] Step 6:

[0555] The server automatically generates a report based on the analysis results and sends it to the terminal. This report includes visual graphs and text information and is converted into a format that is easy for the user to understand. The output is a report that can be viewed in the user interface.

[0556] Step 7:

[0557] The terminal displays a visually generated report to the user through its user interface. Based on this information, the user can make specific decisions regarding security measures. The report's output is used as a countermeasure against security risks.

[0558] 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.

[0559] This invention provides an advanced data analysis system incorporating an emotion engine to enable local governments to efficiently utilize data and support the resolution of regional issues and administrative decision-making. This system is composed of a server, terminals, users, and the emotion engine as its core components.

[0560] The server periodically retrieves the latest statistical data using APIs from external information sources. The data is automatically converted to an internal format and stored in a database. Based on the stored data, differential analysis, longitudinal analysis, trend analysis, etc., are performed, and AI models are used to identify the factors causing data fluctuations.

[0561] The server then automatically generates reports based on the analysis results. The generated reports are visually easy to understand, allowing users to quickly grasp the information. These reports also include comparisons with other municipalities, highlighting the unique challenges and characteristics of the target municipality.

[0562] The terminal serves to provide reports to the user through its user interface. This interface incorporates an emotion engine that understands the user's emotional state. The emotion engine recognizes emotions using user input data, operational actions, and even speech recognition.

[0563] If a user's emotional state is detected, such as anxiety or frustration, the amount of information presented will be reduced, or the user interface will be adjusted with softer colors and messages. Conversely, if the emotion indicates active engagement, the information presented will be made more detailed, or other adjustments will be made to match the user's state.

[0564] Users can operate this system to streamline data-driven decision-making. For example, in financial planning, using the emotion engine displays appropriate information to support favorable policy decisions. This reduces the emotional burden associated with decision-making, enabling users to make more logical and faster judgments.

[0565] Thus, by combining emotion recognition technology, the present invention provides not only a tool for conventional data analysis systems, but also flexible, interactive support functions that respond to the user's emotional state.

[0566] The following describes the processing flow.

[0567] Step 1:

[0568] The server accesses APIs from external information sources to retrieve the latest municipal statistics data. At this point, an automated scheduling function ensures that data collection is performed periodically.

[0569] Step 2:

[0570] The server analyzes the acquired data and converts it into an internal format suitable for the system. The format conversion is optimized to maintain data integrity while ensuring smooth subsequent processing.

[0571] Step 3:

[0572] The server stores the data, converted to an internal format, in the database. During this process, indexes such as regional ID and year are set to improve data retrieval efficiency.

[0573] Step 4:

[0574] The server utilizes the stored data to perform differential analysis based on indicators. This allows for the identification of numerical differences between the local government and the national average or other benchmarks.

[0575] Step 5:

[0576] The server analyzes the data's changes over time and generates trend lines. Here, data from the past to the present is referenced and graphed to predict long-term trends.

[0577] Step 6:

[0578] The server uses an AI model to perform an analysis of the factors behind data fluctuations. The AI ​​identifies key patterns within the dataset and derives the contributing factors from them.

[0579] Step 7:

[0580] The server automatically generates a report based on these analysis results. The report includes an analysis summary, graphs, and recommendations.

[0581] Step 8:

[0582] The terminal provides the generated report to the user through the user interface. During this process, the emotion engine analyzes the user's actions and input data to estimate their emotional state.

[0583] Step 9:

[0584] The emotion engine adjusts how report content is presented based on the user's emotions. For example, if a user is feeling stressed, it adjusts the interface's color scheme and the amount of information displayed to provide a comfortable user experience.

[0585] Step 10:

[0586] Users view reports on their devices and make decisions tailored to their needs. By providing information that resonates with their emotions, users can utilize the analysis results more effectively.

[0587] Step 11:

[0588] If users require additional information, they can request further analysis from the server via their terminal. This request is processed immediately, and the results are presented quickly.

[0589] (Example 2)

[0590] 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."

[0591] Modern local governments must efficiently utilize vast amounts of data to solve complex social problems in their communities. However, they often lack sufficient support for understanding the results of data analysis and making quick and appropriate decisions based on them, and users may experience emotional burdens during the process. Therefore, a system is needed that not only effectively analyzes data and provides the analysis results in an easily understandable format, but also adapts to the emotional state of the user.

[0592] 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.

[0593] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for storing the converted data in a data set. This makes it possible to efficiently analyze data on complex social issues faced by local governments and present it appropriately based on the user's emotional state, thereby supporting policy decisions and streamlining decision-making.

[0594] "Data" refers to a collection of information obtained from an information source and subjected to processing such as analysis and storage within a system.

[0595] "External information sources" refer to information infrastructure and data provision services that exist outside the system for supplying data.

[0596] "Internal format" refers to the data format that a system uses to convert data obtained from external sources into a format that can be processed.

[0597] A "data collection" refers to a storage or database in which processed data is organized according to certain rules.

[0598] A "server" refers to a computer system that performs roles such as processing, storing, and supplying data over a network.

[0599] A "report" is a document automatically generated based on the results of data analysis, and it includes information presented in a visually easy-to-understand manner.

[0600] "User interface" refers to the screens and operating systems that users directly interact with to view information.

[0601] "Emotional state" refers to the user's psychological and emotional state and reactions, which the system detects through voice tone and input behavior.

[0602] A "generative AI model" refers to a program platform that uses machine learning and artificial intelligence techniques to extract data features and generate insights in processes such as data analysis.

[0603] The system of this invention provides advanced data analysis functions that work collaboratively between servers, terminals, and users to support local government decision-making and problem-solving through data utilization.

[0604] The server first collects the necessary data from external sources using APIs. Specifically, it obtains information related to economic indicators and demographics from publicly available government APIs. The server receives this data in JSON format and applies a data conversion algorithm to automatically convert it to an internal format. The converted data is then stored in a data collection such as an SQL database. This ensures that the data is stored in a format suitable for analysis.

[0605] Furthermore, the server uses the stored data to perform differential and trend analysis. This involves using a generative AI model to identify the factors and trends influencing data fluctuations. The AI ​​model is built on machine learning techniques and extracts meaningful patterns from the accumulated data. Based on the analysis results obtained in this process, the server generates highly visible reports. These reports include graphs and charts and are designed to allow users to easily understand the information.

[0606] The device functions as a connection point to the user and incorporates an emotion engine. The device monitors user input and behavior, analyzing their emotional state. If the user is feeling anxious, it reduces the burden by providing a visually calming user interface and adjusting the amount of information presented. Conversely, if the user shows active engagement, the device dynamically responds by providing more detailed information.

[0607] Users can utilize the information and emotional adaptation features provided through this system to act more logically and quickly in situations such as policy making. For example, in urban planning, the emotional engine improves the quality of decision-making by considering the user's psychological state and presenting optimal data.

[0608] An example of a prompt message is: "Conduct an analysis of the current state of elderly welfare policies in local governments and create a report that includes comparisons with other local governments. The report should also include suggestions based on the user's emotional state using an emotion engine." Based on this prompt, the system will perform the necessary processing and generate an output that meets the objective.

[0609] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0610] Step 1:

[0611] The server retrieves data from external sources. This process involves establishing a secure connection using API keys to obtain data such as economic indicators and population data from publicly available government APIs. The input is raw JSON data obtained from the API, and the output is the retrieved raw data. The server then prepares this data for formatting into its internal format.

[0612] Step 2:

[0613] The server converts the acquired data into an internal format. It applies a conversion algorithm, organizing data, for example, from JSON format into a table format for storage in an SQL database. The input is JSON data, and the output is formatted data in SQL format. This ensures the data is stored in a format suitable for later analysis.

[0614] Step 3:

[0615] The server performs data analysis based on the stored data. It uses generative AI models to identify factors and trends in data fluctuations through differential analysis and trend analysis. For example, it performs regression analysis to identify factors influencing increases and decreases in crime rates. The input is organized data in a SQL database, and the output is the insights gained from the analysis.

[0616] Step 4:

[0617] The server automatically generates a report based on the analysis results. The report is created in a visual format, including graphs and charts, to make it easy for the user to understand. The input is the analysis results, and the output is a visually organized report. This report is saved in PDF or web format and can be used later on the device.

[0618] Step 5:

[0619] The terminal receives reports from the server and displays them through the user interface. During this process, an emotion engine operates, receiving the user's emotional state as input. For example, it determines whether the user is experiencing stress based on click patterns during operation and voice input. The output is an interface adjusted according to the user's emotional state.

[0620] Step 6:

[0621] The device adjusts its display content and interface based on the user's emotions. If the user is showing signs of anxiety, it controls the amount of information displayed and uses calmer colors. The input is the result of the emotion engine's analysis, and the output is the modified interface. This allows the user to receive information without feeling burdened.

[0622] Step 7:

[0623] Users make concrete decisions based on information provided through their devices. Their ability to leverage necessary data and insights to make logical judgments, such as in financial planning, improves. The input is information received through a refined interface, and the output is improved decision-making.

[0624] (Application Example 2)

[0625] 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."

[0626] In local communities and commercial facilities, there is a growing need to understand users' emotional states and provide information adaptively based on those states to reduce the burden of decision-making and provide more satisfying experiences. Conventional systems have struggled to provide dynamic information that responds to users' emotions, and have faced challenges such as user stress and information overload due to the provision of fixed information.

[0627] 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.

[0628] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for understanding the emotional state based on the stored data and adapting the presentation of information accordingly. This makes it possible to provide information that is tailored to the emotional state of the user.

[0629] "Data" refers to a collection of information that a server acquires from external sources, converts to an internal format, and stores.

[0630] An "external information source" is an information source that serves as an external source of data for obtaining data.

[0631] An "internal format" is a format used to organize acquired data and convert it into a format usable within the system.

[0632] "Information structure" refers to databases and storage systems used to systematically store converted data.

[0633] "Difference analysis" is a method for evaluating changes or differences in a specific indicator based on stored data.

[0634] A "trend line" is a straight or curved line used to visually represent year-to-year changes based on historical data.

[0635] An "instruction manual" is a document that is automatically generated based on the analysis results and provides information to the user.

[0636] A "distinctive difference" refers to a unique change or characteristic observed in specific data compared to other data.

[0637] "Device" refers to a hardware or software system equipped with a user interface that understands the user's emotional state and adjusts the presentation of information accordingly.

[0638] "Emotional state" refers to the psychological or sensory state exhibited by the user, and is an important factor to consider when providing information.

[0639] This invention provides a system that improves the customer experience in local communities and commercial facilities by providing information tailored to the customer's emotional state.

[0640] The server has the function of acquiring data from external sources, converting it to an internal format, and storing it in an information structure. This includes connections via APIs to periodically acquire information from external data sources, and software to convert the data into a format that can be processed within the system. The converted data is then stored in a database as an information structure.

[0641] The device will provide information through its user interface and utilize an emotion engine to understand the user's emotional state. Specifically, it will implement an emotion recognition system that combines eye-tracking and voice recognition technologies using user devices such as smart glasses and head-mounted displays. This system will evaluate the user's emotions, such as joy, confusion, and interest, in real time and optimize the information presentation.

[0642] By wearing smart glasses and walking around a store, users can receive new product information and services based on their emotions. For example, if they show interest, detailed information and best practices for the corresponding product will be displayed on the glasses' screen. On the other hand, if confusion is detected, the amount of information will be reduced and the interface will switch to a more reassuring color scheme.

[0643] As a concrete example, when a customer visits the electronics section, the system detects their "interest" from their facial expression and displays the latest reviews and usage instructions for that product on their glasses. Furthermore, it utilizes "generating AI models and prompt sentences" to generate prompts and provide information, such as: "We want to improve user interaction based on emotion recognition in our smart glasses app for physical stores. Please tell us how to build a system that detects interest and confusion and displays appropriate product information and suggestions."

[0644] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0645] Step 1:

[0646] The server retrieves data from an external source using an API. The API endpoint of the external source is required as input, and the output contains the retrieved raw data. This data is passed to the server in JSON or XML format.

[0647] Step 2:

[0648] The server converts the acquired data into an internal format. The input is the raw data obtained in step 1, and the output is in a format that can be processed internally. The conversion process uses a JSON parser and custom scripts to extract the necessary items and organize them into a data frame.

[0649] Step 3:

[0650] The server stores the converted data in an information structure. The input is internally formatted data, and the output is the state in which it is stored in the database. Here, SQL queries or database APIs are used to write to the database.

[0651] Step 4:

[0652] The device uses sensors in smart glasses to detect the user's emotional state in real time. Inputs are camera images and audio data, and output is data representing the emotion recognition results. The emotion engine uses a facial recognition algorithm and an audio analysis model to evaluate the user's emotions.

[0653] Step 5:

[0654] The terminal displays appropriate information on the user interface according to the emotional state. The input is the emotion recognition result from step 4 and product information obtained from the server, and the output is a visualized information display. For example, if "interest" is detected, detailed product information will be displayed on the screen.

[0655] Step 6:

[0656] The user makes decisions based on information presented by the smart glasses. The input is the information displayed by the device, and the output is the purchase decision or the choice of the next action. The user's actions are fed back into step 4 as data for the next emotional evaluation. This loop continues until the user leaves the store.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] [Fourth Embodiment]

[0661] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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).

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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".

[0674] This invention provides a system that enables local governments to efficiently utilize data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a specific role.

[0675] First, the server retrieves data from external sources. By regularly collecting statistical data from local governments and the national government using APIs, it is possible to quickly incorporate the latest information into the system. The retrieved data is automatically converted into the necessary format and stored in a database. This stored data forms the basis for subsequent analysis.

[0676] Next, the server performs analysis based on the stored data. Using the difference analysis function, it can compare the differences between the local statistical data and the national statistical data. Furthermore, longitudinal analysis makes it possible to understand past trends and predict future trends. By using AI models, important factors can be identified from the data, and detailed factor analysis can be performed.

[0677] The analysis results are automatically generated as a report by the server. This report consists of visual graphs and text, presenting information in an easy-to-understand format for the user. Furthermore, it allows for comparison with data from other municipalities with similar functionality, helping to identify challenges specific to one's own region.

[0678] The terminal provides users with generated reports and analysis results through a user interface. Users can access the system via this terminal and request further in-depth data analysis or the generation of additional reports as needed.

[0679] By utilizing the above functions, users can make important decisions in local government administration quickly and rationally. For example, by quickly grasping changes in the financial situation and taking necessary measures in advance, they can improve the quality of services to local residents. In this way, the present invention streamlines local government operations and supports the formation of excellent data-driven policies.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The server accesses APIs from external information sources to periodically retrieve the latest statistical data. A schedule is set to manage this process, ensuring that data collection is performed automatically.

[0683] Step 2:

[0684] The server converts the acquired data into a format that can be used internally. For example, it might convert JSON data to CSV format so that it can be used efficiently in subsequent processing.

[0685] Step 3:

[0686] The server saves the converted data to a database. The data is saved in an easily accessible format by setting keys such as regional ID and year.

[0687] Step 4:

[0688] The server performs a difference analysis on specific indicators based on the information stored in the database. This reveals and displays the numerical differences between the target municipality and the national average.

[0689] Step 5:

[0690] The server performs a year-on-year analysis based on historical data and generates trend lines. During this process, it graphs the year-to-year changes in numerical values, visually illustrating long-term trends.

[0691] Step 6:

[0692] The server uses an AI model to analyze the factors behind data fluctuations. The AI ​​detects specific patterns and anomalies within the data and identifies the underlying causes based on these findings.

[0693] Step 7:

[0694] The server aggregates the analysis results and automatically generates a report. The report is structured in an easy-to-understand format, including a summary of the analyzed data and graphs illustrating the results.

[0695] Step 8:

[0696] The server compares the data with that of other municipalities of similar size to identify distinctive differences. This highlights the unique challenges specific to the target municipality.

[0697] Step 9:

[0698] The terminal provides the user with the generated report through its user interface. Based on this information, the user can quickly identify the issues they need to address.

[0699] Step 10:

[0700] Users can request more in-depth information about specific data analyses through their devices. This request is immediately transmitted to the server.

[0701] Step 11:

[0702] Based on user requests, the server performs additional data analysis and generates a new report. This provides more detailed information to support decision-making.

[0703] (Example 1)

[0704] 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".

[0705] Local governments are required to efficiently utilize the latest data to solve regional issues and support administrative decision-making. Existing systems often manage each stage of data collection, transformation, storage, analysis, and reporting individually, making integrated and timely information provision difficult. Furthermore, comparing various data and predicting trends is time-consuming, hindering the efficient use of time and resources.

[0706] 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.

[0707] In this invention, the server includes means for acquiring data from public information sources, means for converting the acquired data into a standard format, and means for storing the converted data in a storage device. This enables efficient data collection, storage, and utilization.

[0708] "Data" is a collection of information that is collected, processed, and stored by a computer.

[0709] "Public information sources" refer to official information provided by local governments, national agencies, and other similar organizations.

[0710] A "standard format" is a format established to ensure data compatibility and readability.

[0711] A "storage device" is a piece of hardware or software used to store information for the long term.

[0712] "Differences in metrics" refers to differences in characteristics and trends across different datasets.

[0713] "Daily variation" refers to changes in data observed at specific time intervals.

[0714] A "prediction curve" is a graph used to estimate future trends based on past data.

[0715] A "report" is an informational document that presents analysis results and conclusions in a documented format.

[0716] A "user interface" is a visual interface that allows users to interact with the system and obtain information.

[0717] A "machine learning model" is an algorithm that automatically learns patterns from data to perform predictions and classifications.

[0718] This invention is a system for local governments to effectively utilize various types of data to support the resolution of regional issues and administrative decision-making. This system consists of a server, terminals, and users, each playing a different role.

[0719] The server retrieves data from external public information sources via APIs. The retrieved data is converted to a standard format using libraries such as Python's Pandas library and stored in a database system, such as PostgreSQL. Based on the stored data, the server performs data analysis using machine learning models. This analysis includes techniques using TensorFlow and PyTorch to evaluate differences in metrics and daily fluctuations, and to generate prediction curves necessary for future forecasting. The analysis results are visualized using Matplotlib and D3.js and automatically formatted into a report.

[0720] The terminal provides a user interface that allows users to access and view generated reports and analysis results. This interface is implemented using React.js and Vue.js, enabling interactive user operation.

[0721] Users obtain system information via their terminals and request more detailed analysis or the generation of additional reports. For example, if a user wants to know about trends in financial data, they would enter the following as a prompt:

[0722] "Based on the fiscal balance data for the past three years, analyze the trends in increases and decreases for each expenditure item and assess their impact on next year's budget plan."

[0723] This system enables local governments to formulate data-driven, logical, and rapid policies, contributing to improved quality of services for residents.

[0724] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0725] Step 1:

[0726] The server retrieves data from external public information sources. In this process, the server uses an API to connect to the database in real time and retrieve the necessary datasets. The input is raw data from the external information source, and the output is unprocessed data stored within the server.

[0727] Step 2:

[0728] The server converts the acquired raw data into a standard format. This conversion uses the Python Pandas library to format the data and impute missing values. The input is the raw data, and the output is the data converted to the standard format.

[0729] Step 3:

[0730] The server stores the transformed data in a relational database. PostgreSQL is used here to efficiently store the organized data and prepare it for later analysis. The input is data in a standard format, and the output is data managed within the database.

[0731] Step 4:

[0732] The server performs analysis based on stored data. It uses machine learning models to analyze differences in metrics between data points and daily fluctuations. This process utilizes TensorFlow and PyTorch to perform trend analysis and prediction. The input is data retrieved from the database, and the output is the analysis results.

[0733] Step 5:

[0734] The server visualizes the analysis results and automatically generates reports. It uses Matplotlib and D3.js to create graphs and generates reports containing text information in PDF or HTML format. The input is the analysis results, and the output is the report provided to the user.

[0735] Step 6:

[0736] The terminal presents the generated reports and analysis results to the user. It provides a graphical user interface using React.js and Vue.js, allowing users to view and further manipulate the visualized information. The input is the generated report, and the output is the screen display accessible to the user.

[0737] Step 7:

[0738] Users access the system to request detailed analysis or the generation of additional reports. For example, they might request a detailed trend analysis based on historical financial data using a prompt. The input is the user's request or prompt, and the output is the newly generated analysis or report.

[0739] (Application Example 1)

[0740] 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".

[0741] In modern society, security risks are increasing, and real-time information gathering and rapid risk assessment are required. However, current systems have limited means of efficiently acquiring and analyzing the latest security information, making it particularly difficult for individuals and small organizations to respond quickly to risks.

[0742] 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.

[0743] In this invention, the server includes means for acquiring data from external information sources, means for evaluating security risks and providing the results visually to the user, and means for comparing its own data with other data and identifying characteristic differences. This enables real-time identification of security risks and rapid response.

[0744] "Means of obtaining data from external sources" refers to functions for collecting necessary information through external databases or APIs.

[0745] "Means of converting to an internal format" refers to a function that converts acquired data into a format that is easy for the system to process.

[0746] "Means of saving to a database" refers to the function of storing converted data in order to effectively manage it.

[0747] "Methods for performing difference analysis on specific indicators" refer to methods that calculate the differences in numerical values ​​between different datasets and use the results to find specific trends or patterns.

[0748] "A method for analyzing year-to-year changes using historical data and generating trend lines" refers to a function that analyzes data fluctuations over time and draws lines to predict future trends.

[0749] "Methods for automatically generating reports" refers to functions that generate documents based on analysis results and compile information.

[0750] "Means for identifying distinctive differences" refers to methods for finding particularly noteworthy differences among data points being compared.

[0751] "A means of assessing security risks and providing the results to users visually" refers to a function that analyzes potential threats and communicates that information to users in a graphical format.

[0752] In this embodiment of the invention, the server functions as follows: The server retrieves information from an external security database using an API and converts the data into an internally specific format. It also efficiently stores the converted data in the database. This allows for rapid access while maintaining data integrity. The server then performs differential analysis based on the stored data to assess security risks. Using an AI model, it is possible to analyze the factors causing data fluctuations in detail and automatically generate a report based on the analysis results. This report is displayed to the user through a user interface, allowing them to understand the security situation in real time.

[0753] In terms of hardware, a server with a high-performance processor and sufficient data storage capacity is required. In terms of software, a data processing program using Python and an AI model implementation using TensorFlow will be necessary.

[0754] As a concrete example, this system could be used by small organizations that want to strengthen their defenses against specific cyberattacks in their daily operations. The server can analyze information obtained from external data and send a request to a generating AI model using a prompt message such as, "Predict security risks based on recent cyberattack trends and propose specific countermeasures." This makes it possible to quickly implement practical defensive measures based on the provided data.

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

[0756] Step 1:

[0757] The server accesses an external security database via an API to retrieve the latest security-related data. Because this input data has an external format and structure, it needs to be in a standardized format. For example, it accepts data in CSV or JSON format.

[0758] Step 2:

[0759] The server converts the acquired data into an internal format. Specifically, it analyzes the data structure and extracts the necessary fields to format it for analysis. This process involves removing unnecessary data and standardizing data types. The output is a well-organized dataset.

[0760] Step 3:

[0761] The server saves the converted data to the database. Transactional processing is performed during this saving process to maintain data consistency and integrity. The saved data is then ready for use in subsequent analysis.

[0762] Step 4:

[0763] The server performs differential analysis using the stored data. Specifically, it compares past data with current data to detect statistically significant changes. The output obtained from this analysis is an indicator showing the trend of increasing or decreasing risk.

[0764] Step 5:

[0765] The server utilizes an AI model to identify factors influencing data fluctuations and conduct a detailed risk analysis. The AI ​​model compares past data patterns with current data to predict potential risk factors. The output is a risk factor analysis report.

[0766] Step 6:

[0767] The server automatically generates a report based on the analysis results and sends it to the terminal. This report includes visual graphs and text information and is converted into a format that is easy for the user to understand. The output is a report that can be viewed in the user interface.

[0768] Step 7:

[0769] The terminal displays a visually generated report to the user through its user interface. Based on this information, the user can make specific decisions regarding security measures. The report's output is used as a countermeasure against security risks.

[0770] 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.

[0771] This invention provides an advanced data analysis system incorporating an emotion engine to enable local governments to efficiently utilize data and support the resolution of regional issues and administrative decision-making. This system is composed of a server, terminals, users, and the emotion engine as its core components.

[0772] The server periodically retrieves the latest statistical data using APIs from external information sources. The data is automatically converted to an internal format and stored in a database. Based on the stored data, differential analysis, longitudinal analysis, trend analysis, etc., are performed, and AI models are used to identify the factors causing data fluctuations.

[0773] The server then automatically generates reports based on the analysis results. The generated reports are visually easy to understand, allowing users to quickly grasp the information. These reports also include comparisons with other municipalities, highlighting the unique challenges and characteristics of the target municipality.

[0774] The terminal serves to provide reports to the user through its user interface. This interface incorporates an emotion engine that understands the user's emotional state. The emotion engine recognizes emotions using user input data, operational actions, and even speech recognition.

[0775] If a user's emotional state is detected, such as anxiety or frustration, the amount of information presented will be reduced, or the user interface will be adjusted with softer colors and messages. Conversely, if the emotion indicates active engagement, the information presented will be made more detailed, or other adjustments will be made to match the user's state.

[0776] Users can operate this system to streamline data-driven decision-making. For example, in financial planning, using the emotion engine displays appropriate information to support favorable policy decisions. This reduces the emotional burden associated with decision-making, enabling users to make more logical and faster judgments.

[0777] Thus, by combining emotion recognition technology, the present invention provides not only a tool for conventional data analysis systems, but also flexible, interactive support functions that respond to the user's emotional state.

[0778] The following describes the processing flow.

[0779] Step 1:

[0780] The server accesses APIs from external information sources to retrieve the latest municipal statistics data. At this point, an automated scheduling function ensures that data collection is performed periodically.

[0781] Step 2:

[0782] The server analyzes the acquired data and converts it into an internal format suitable for the system. The format conversion is optimized to maintain data integrity while ensuring smooth subsequent processing.

[0783] Step 3:

[0784] The server stores the data, converted to an internal format, in the database. During this process, indexes such as regional ID and year are set to improve data retrieval efficiency.

[0785] Step 4:

[0786] The server utilizes the stored data to perform differential analysis based on indicators. This allows for the identification of numerical differences between the local government and the national average or other benchmarks.

[0787] Step 5:

[0788] The server analyzes the data's changes over time and generates trend lines. Here, data from the past to the present is referenced and graphed to predict long-term trends.

[0789] Step 6:

[0790] The server uses an AI model to perform an analysis of the factors behind data fluctuations. The AI ​​identifies key patterns within the dataset and derives the contributing factors from them.

[0791] Step 7:

[0792] The server automatically generates a report based on these analysis results. The report includes an analysis summary, graphs, and recommendations.

[0793] Step 8:

[0794] The terminal provides the generated report to the user through the user interface. During this process, the emotion engine analyzes the user's actions and input data to estimate their emotional state.

[0795] Step 9:

[0796] The emotion engine adjusts how report content is presented based on the user's emotions. For example, if a user is feeling stressed, it adjusts the interface's color scheme and the amount of information displayed to provide a comfortable user experience.

[0797] Step 10:

[0798] Users view reports on their devices and make decisions tailored to their needs. By providing information that resonates with their emotions, users can utilize the analysis results more effectively.

[0799] Step 11:

[0800] If users require additional information, they can request further analysis from the server via their terminal. This request is processed immediately, and the results are presented quickly.

[0801] (Example 2)

[0802] 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".

[0803] Modern local governments must efficiently utilize vast amounts of data to solve complex social problems in their communities. However, they often lack sufficient support for understanding the results of data analysis and making quick and appropriate decisions based on them, and users may experience emotional burdens during the process. Therefore, a system is needed that not only effectively analyzes data and provides the analysis results in an easily understandable format, but also adapts to the emotional state of the user.

[0804] 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.

[0805] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for storing the converted data in a data set. This makes it possible to efficiently analyze data on complex social issues faced by local governments and present it appropriately based on the user's emotional state, thereby supporting policy decisions and streamlining decision-making.

[0806] "Data" refers to a collection of information obtained from an information source and subjected to processing such as analysis and storage within a system.

[0807] "External information sources" refer to information infrastructure and data provision services that exist outside the system for supplying data.

[0808] "Internal format" refers to the data format that a system uses to convert data obtained from external sources into a format that can be processed.

[0809] A "data collection" refers to a storage or database in which processed data is organized according to certain rules.

[0810] A "server" refers to a computer system that performs roles such as processing, storing, and supplying data over a network.

[0811] A "report" is a document automatically generated based on the results of data analysis, and it includes information presented in a visually easy-to-understand manner.

[0812] "User interface" refers to the screens and operating systems that users directly interact with to view information.

[0813] "Emotional state" refers to the user's psychological and emotional state and reactions, which the system detects through voice tone and input behavior.

[0814] A "generative AI model" refers to a program platform that uses machine learning and artificial intelligence techniques to extract data features and generate insights in processes such as data analysis.

[0815] The system of this invention provides advanced data analysis functions that work collaboratively between servers, terminals, and users to support local government decision-making and problem-solving through data utilization.

[0816] The server first collects the necessary data from external sources using APIs. Specifically, it obtains information related to economic indicators and demographics from publicly available government APIs. The server receives this data in JSON format and applies a data conversion algorithm to automatically convert it to an internal format. The converted data is then stored in a data collection such as an SQL database. This ensures that the data is stored in a format suitable for analysis.

[0817] Furthermore, the server uses the stored data to perform differential and trend analysis. This involves using a generative AI model to identify the factors and trends influencing data fluctuations. The AI ​​model is built on machine learning techniques and extracts meaningful patterns from the accumulated data. Based on the analysis results obtained in this process, the server generates highly visible reports. These reports include graphs and charts and are designed to allow users to easily understand the information.

[0818] The device functions as a connection point to the user and incorporates an emotion engine. The device monitors user input and behavior, analyzing their emotional state. If the user is feeling anxious, it reduces the burden by providing a visually calming user interface and adjusting the amount of information presented. Conversely, if the user shows active engagement, the device dynamically responds by providing more detailed information.

[0819] Users can utilize the information and emotional adaptation features provided through this system to act more logically and quickly in situations such as policy making. For example, in urban planning, the emotional engine improves the quality of decision-making by considering the user's psychological state and presenting optimal data.

[0820] An example of a prompt message is: "Conduct an analysis of the current state of elderly welfare policies in local governments and create a report that includes comparisons with other local governments. The report should also include suggestions based on the user's emotional state using an emotion engine." Based on this prompt, the system will perform the necessary processing and generate an output that meets the objective.

[0821] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0822] Step 1:

[0823] The server retrieves data from external sources. This process involves establishing a secure connection using API keys to obtain data such as economic indicators and population data from publicly available government APIs. The input is raw JSON data obtained from the API, and the output is the retrieved raw data. The server then prepares this data for formatting into its internal format.

[0824] Step 2:

[0825] The server converts the acquired data into an internal format. It applies a conversion algorithm, organizing data, for example, from JSON format into a table format for storage in an SQL database. The input is JSON data, and the output is formatted data in SQL format. This ensures the data is stored in a format suitable for later analysis.

[0826] Step 3:

[0827] The server performs data analysis based on the stored data. It uses generative AI models to identify factors and trends in data fluctuations through differential analysis and trend analysis. For example, it performs regression analysis to identify factors influencing increases and decreases in crime rates. The input is organized data in a SQL database, and the output is the insights gained from the analysis.

[0828] Step 4:

[0829] The server automatically generates a report based on the analysis results. The report is created in a visual format, including graphs and charts, to make it easy for the user to understand. The input is the analysis results, and the output is a visually organized report. This report is saved in PDF or web format and can be used later on the device.

[0830] Step 5:

[0831] The terminal receives reports from the server and displays them through the user interface. During this process, an emotion engine operates, receiving the user's emotional state as input. For example, it determines whether the user is experiencing stress based on click patterns during operation and voice input. The output is an interface adjusted according to the user's emotional state.

[0832] Step 6:

[0833] The device adjusts its display content and interface based on the user's emotions. If the user is showing signs of anxiety, it controls the amount of information displayed and uses calmer colors. The input is the result of the emotion engine's analysis, and the output is the modified interface. This allows the user to receive information without feeling burdened.

[0834] Step 7:

[0835] Users make concrete decisions based on information provided through their devices. Their ability to leverage necessary data and insights to make logical judgments, such as in financial planning, improves. The input is information received through a refined interface, and the output is improved decision-making.

[0836] (Application Example 2)

[0837] 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".

[0838] In local communities and commercial facilities, there is a growing need to understand users' emotional states and provide information adaptively based on those states to reduce the burden of decision-making and provide more satisfying experiences. Conventional systems have struggled to provide dynamic information that responds to users' emotions, and have faced challenges such as user stress and information overload due to the provision of fixed information.

[0839] 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.

[0840] In this invention, the server includes means for acquiring data from an external information source, means for converting the acquired data into an internal format, and means for understanding the emotional state based on the stored data and adapting the presentation of information accordingly. This makes it possible to provide information that is tailored to the emotional state of the user.

[0841] "Data" refers to a collection of information that a server acquires from external sources, converts to an internal format, and stores.

[0842] An "external information source" is an information source that serves as an external source of data for obtaining data.

[0843] An "internal format" is a format used to organize acquired data and convert it into a format usable within the system.

[0844] "Information structure" refers to databases and storage systems used to systematically store converted data.

[0845] "Difference analysis" is a method for evaluating changes or differences in a specific indicator based on stored data.

[0846] A "trend line" is a straight or curved line used to visually represent year-to-year changes based on historical data.

[0847] An "instruction manual" is a document that is automatically generated based on the analysis results and provides information to the user.

[0848] A "distinctive difference" refers to a unique change or characteristic observed in specific data compared to other data.

[0849] "Device" refers to a hardware or software system equipped with a user interface that understands the user's emotional state and adjusts the presentation of information accordingly.

[0850] "Emotional state" refers to the psychological or sensory state exhibited by the user, and is an important factor to consider when providing information.

[0851] This invention provides a system that improves the customer experience in local communities and commercial facilities by providing information tailored to the customer's emotional state.

[0852] The server has the function of acquiring data from external sources, converting it to an internal format, and storing it in an information structure. This includes connections via APIs to periodically acquire information from external data sources, and software to convert the data into a format that can be processed within the system. The converted data is then stored in a database as an information structure.

[0853] The device will provide information through its user interface and utilize an emotion engine to understand the user's emotional state. Specifically, it will implement an emotion recognition system that combines eye-tracking and voice recognition technologies using user devices such as smart glasses and head-mounted displays. This system will evaluate the user's emotions, such as joy, confusion, and interest, in real time and optimize the information presentation.

[0854] By wearing smart glasses and walking around a store, users can receive new product information and services based on their emotions. For example, if they show interest, detailed information and best practices for the corresponding product will be displayed on the glasses' screen. On the other hand, if confusion is detected, the amount of information will be reduced and the interface will switch to a more reassuring color scheme.

[0855] As a concrete example, when a customer visits the electronics section, the system detects their "interest" from their facial expression and displays the latest reviews and usage instructions for that product on their glasses. Furthermore, it utilizes "generating AI models and prompt sentences" to generate prompts and provide information, such as: "We want to improve user interaction based on emotion recognition in our smart glasses app for physical stores. Please tell us how to build a system that detects interest and confusion and displays appropriate product information and suggestions."

[0856] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0857] Step 1:

[0858] The server retrieves data from an external source using an API. The API endpoint of the external source is required as input, and the output contains the retrieved raw data. This data is passed to the server in JSON or XML format.

[0859] Step 2:

[0860] The server converts the acquired data into an internal format. The input is the raw data obtained in step 1, and the output is in a format that can be processed internally. The conversion process uses a JSON parser and custom scripts to extract the necessary items and organize them into a data frame.

[0861] Step 3:

[0862] The server stores the converted data in an information structure. The input is internally formatted data, and the output is the state in which it is stored in the database. Here, SQL queries or database APIs are used to write to the database.

[0863] Step 4:

[0864] The device uses sensors in smart glasses to detect the user's emotional state in real time. Inputs are camera images and audio data, and output is data representing the emotion recognition results. The emotion engine uses a facial recognition algorithm and an audio analysis model to evaluate the user's emotions.

[0865] Step 5:

[0866] The terminal displays appropriate information on the user interface according to the emotional state. The input is the emotion recognition result from step 4 and product information obtained from the server, and the output is a visualized information display. For example, if "interest" is detected, detailed product information will be displayed on the screen.

[0867] Step 6:

[0868] The user makes decisions based on information presented by the smart glasses. The input is the information displayed by the device, and the output is the purchase decision or the choice of the next action. The user's actions are fed back into step 4 as data for the next emotional evaluation. This loop continues until the user leaves the store.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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."

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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 to be incorporated by reference.

[0890] The following is further disclosed regarding the embodiments described above.

[0891] (Claim 1)

[0892] Means of obtaining data from external sources,

[0893] A means of converting the acquired data into an internal format,

[0894] A means of saving the converted data to a database,

[0895] A means of performing difference analysis on a specific indicator based on stored data,

[0896] A method for analyzing year-to-year changes using historical data and generating trend lines,

[0897] A means of automatically generating reports based on analysis results,

[0898] A means of comparing our own data with other data and identifying characteristic differences,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, wherein the analysis means uses an AI model to identify the factors causing data fluctuations.

[0902] (Claim 3)

[0903] The system according to claim 1, wherein the report generation means provides a report in a format that can be displayed through a user interface.

[0904] "Example 1"

[0905] (Claim 1)

[0906] Means of obtaining data from public sources,

[0907] A means of converting the acquired data into a standard format,

[0908] A means for storing the converted data in a storage device,

[0909] A means of analyzing differences in indicators based on saved data,

[0910] A means of analyzing daily fluctuations using accumulated data and generating a prediction curve,

[0911] A means of automatically generating reports based on analysis results,

[0912] A means of comparing one's own data with other data and identifying unique differences,

[0913] A means for users to request detailed specific analysis or the generation of additional reports,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, wherein the analysis means uses a machine learning model to identify factors causing data fluctuations.

[0917] (Claim 3)

[0918] The system according to claim 1, wherein the report creation means provides a report in a format that can be displayed through a user operation screen.

[0919] "Application Example 1"

[0920] (Claim 1)

[0921] Means of obtaining data from external sources,

[0922] A means of converting the acquired data into an internal format,

[0923] A means of saving the converted data to a database,

[0924] A means of performing difference analysis on a specific indicator based on stored data,

[0925] A method for analyzing year-to-year changes using historical data and generating trend lines,

[0926] A means of automatically generating reports based on analysis results,

[0927] A means of comparing our own data with other data and identifying characteristic differences,

[0928] A means of assessing security risks and providing the results to users visually,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, wherein the analysis means uses an AI model to identify the factors causing data fluctuations.

[0932] (Claim 3)

[0933] The system according to claim 1, wherein the report generation means provides a report in a format that can be displayed through a user interface.

[0934] "Example 2 of combining an emotion engine"

[0935] (Claim 1)

[0936] Means of obtaining data from external sources,

[0937] A means of converting the acquired data into an internal format,

[0938] A means for storing the converted data in a data set,

[0939] A means of performing difference analysis on a specific indicator based on stored data,

[0940] A means for analyzing temporal trends using stored data and identifying trends,

[0941] A means of automatically generating a report based on the analysis results,

[0942] A means of comparing our own data with other data and identifying characteristic differences,

[0943] A means for detecting the user's emotional state and adjusting the interface,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, wherein the analysis means uses a generative AI model to identify the factors causing data fluctuations.

[0947] (Claim 3)

[0948] The system according to claim 1, wherein the report creation means provides a report in a format that corresponds to the user's emotional state through a user interface.

[0949] "Application example 2 of combining emotional engines"

[0950] (Claim 1)

[0951] Means of obtaining data from external sources,

[0952] A means of converting the acquired data into an internal format,

[0953] A means for storing the converted data in an information structure,

[0954] A means of performing difference analysis on a specific indicator based on stored data,

[0955] A method for analyzing year-to-year changes using historical data and generating trend lines,

[0956] A means of automatically generating instructions based on analysis results,

[0957] A means of comparing our own data with other data and identifying characteristic differences,

[0958] The device has a means of understanding the user's emotional state and adapting the presentation of information accordingly.

[0959] A system that includes this.

[0960] (Claim 2)

[0961] The system according to claim 1, wherein the analysis means uses an artificial intelligence model to identify the factors causing data fluctuations.

[0962] (Claim 3)

[0963] The system according to claim 1, wherein the instruction manual creation means provides an instruction manual in a format that can be displayed through a user interface, and the presented information is adjusted based on emotion recognition. [Explanation of symbols]

[0964] 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. Means of obtaining data from external sources, A means of converting the acquired data into an internal format, A means of saving the converted data to a database, A means of performing difference analysis on a specific indicator based on stored data, A method for analyzing year-to-year changes using historical data and generating trend lines, A means of automatically generating reports based on analysis results, A means of comparing our own data with other data and identifying characteristic differences, A system that includes this.

2. The system according to claim 1, wherein the analysis means uses an AI model to identify the factors causing data fluctuations.

3. The system according to claim 1, wherein the report generation means provides a report in a format that can be displayed through a user interface.

Images