system

Abstract

We provide the system. [Solution] A means for selecting relevant data based on information entered by the user, A means of formatting and visualizing the selected data, A means of analyzing visualized data and generating policy advice, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Policy-making in local governments often relies on the experience and intuition of staff, and there is a problem that the basis based on data is insufficient. As a result, it is difficult to say that the cost-effectiveness of policies is fully exerted and the contribution to resident services and local communities is maximized. In addition, a large amount of data held by local governments is not fully utilized, and evidence essential for policy-making is lacking.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, and means for analyzing the visualized data and generating policy advice. This system makes it possible for users to easily make data-driven, evidence-based policy proposals. Furthermore, by providing means for selecting the optimal visualization format according to the theme specified by the user and means for providing multiple policy scenarios proposed based on the analysis results, the efficiency and effectiveness of policy formulation can be greatly improved.

[0006] A "user" refers to a person who operates the system and inputs information in order to formulate policies.

[0007] "Information" refers to data related to the themes and objectives of policies that users provide to the system.

[0008] "Data" refers to a collection of numerical data and facts in various forms that contain information necessary for policy making.

[0009] "Selection" refers to the process of extracting relevant data and identifying what is needed.

[0010] "Formatting" refers to the process of converting acquired data into a standard format.

[0011] "Visualization" refers to the process of representing data visually using graphs, charts, and other visual tools.

[0012] "Analysis" refers to the process of interpreting data and deriving useful information and conclusions from it.

[0013] "Policy" refers to official guidelines and action plans formulated by local governments.

[0014] "Advice" refers to actionable improvement measures or policies proposed based on the analysis results.

[0015] "Means" refers to various functions and methods included in a system to achieve a specific purpose.

[0016] "System" refers to a set of integrated programs designed to support a specific policy-making process.

Brief Description of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which 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 Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiment for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

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

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0032] 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.

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

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] The system of the present invention is designed to support data-driven decision-making in policy formulation by local governments. This system includes user-operated terminals, a server, and communication means for linking them together.

[0039] Users input policy-making objectives and themes using a terminal. The terminal sends this information to a server, which then collects relevant data from the local government's internal databases and external data providers. The server then processes the acquired data, such as removing duplicates and converting formats, to prepare it for analysis.

[0040] The formatted data is then visualized on the server. Specifically, a generating AI automatically selects a visualization format suitable for the data's characteristics and purpose, and generates it as graphs and charts. This visualized data is then presented to the user via their device.

[0041] Next, the server performs data analysis based on the visualized data. It applies machine learning algorithms to extract patterns and trends from past data and attempts to predict policy effects. Based on the analysis results, the server generates policy proposals and sends various policy scenarios to the terminal.

[0042] Users can proceed with considering specific policies based on the advice and policy scenarios displayed on their devices. For example, when considering tourism promotion policies, users can review visualized data on human flow and trends in tourist numbers, and receive support in determining the timing and target audience for effective tourism campaigns.

[0043] In this way, this system enables users to formulate objective and efficient policies based on data. As a result, local government policies become more effective, and high-quality services can be provided to residents.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user operates the terminal to input information about the objectives and themes of policy formulation. Once input is complete, the terminal sends this information to the server.

[0047] Step 2:

[0048] Based on themes received from users, the server accesses internal databases and external data sources to collect relevant data. The server then checks the retrieved data for duplicates and missing data, and organizes the data.

[0049] Step 3:

[0050] The server passes the formatted data to the visualization engine, where the generating AI selects the appropriate visualization format (e.g., graph, chart). The visualized data is then generated.

[0051] Step 4:

[0052] The terminal displays the visualized data sent from the server on the user interface. The user reviews this data and visually understands its trends and characteristics.

[0053] Step 5:

[0054] The server begins data analysis based on the visualized data. Using machine learning algorithms, it extracts patterns and trends from past data and predicts future policy effects.

[0055] Step 6:

[0056] The server generates policy proposals based on the analysis results and develops multiple most effective policy scenarios.

[0057] Step 7:

[0058] The device presents the user with generated advice and policy scenarios. Based on the information provided, the user can then consider and decide on specific policy directions.

[0059] (Example 1)

[0060] 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."

[0061] In policymaking by local governments, there is a need to efficiently and accurately predict policy effects and create objective policy proposals while utilizing vast amounts of data. Conventional systems have the problem of requiring a lot of manual work in the process of data collection, formatting, and analysis, which is time-consuming and labor-intensive, and also relies heavily on subjective judgment.

[0062] 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.

[0063] In this invention, the server includes means for collecting relevant information based on the purpose or theme of a plan entered by the user; means for removing duplicates from the collected information and formatting it into a unified format; means for visually displaying the formatted information in an optimal format using a generative AI model; means for extracting regularities or trends from past data based on the visualized information; means for predicting the effectiveness of the plan based on the extracted regularities or trends; and means for generating plan proposals using the generative AI model from the prediction results of the plan's effectiveness. This makes it possible to accurately process vast amounts of data and efficiently make objective policy proposals.

[0064] A "user" refers to someone who operates the system and inputs policy objectives and themes.

[0065] "Plan objectives or themes" refer to information that indicates specific goals and policies in policymaking.

[0066] "Relevant information" refers to information including data from internal databases and external data providers that are collected based on the objectives or themes of the plan.

[0067] "Means of collection" refers to methods and processes for automatically gathering necessary information based on a given theme.

[0068] "Deduplication" refers to the process of removing duplicate data from collected information.

[0069] "Methods for formatting into a unified format" refers to methods of processing collected information by converting it into a consistent format that facilitates analysis and visualization.

[0070] A "generative AI model" refers to an artificial intelligence model that automatically generates appropriate visual formats based on large amounts of data.

[0071] "Means of visual display" refers to methods of presenting formatted information in an easy-to-understand format for users, such as graphs and charts.

[0072] "Regularity or trend" refers to a consistent pattern or trend revealed through the analysis of past data.

[0073] "Means of predicting the effectiveness of a plan" refers to methods of predicting the degree to which a plan will be successful, using data-driven regularities or trends.

[0074] "Means for generating plan proposals" refers to methods for deriving proposals that support the formulation of optimal policies based on predictions and analysis results.

[0075] Embodiments of the present invention are shown below.

[0076] The system primarily consists of servers, terminals, and communication means to link them together. Users input policy-making objectives or themes via terminals, and the server operates based on this input.

[0077] The server collects relevant information from internal databases and external data providers based on the received policy theme. It uses database management systems such as SQL queries to access the internal database and REST APIs to retrieve external data.

[0078] The collected data undergoes formatting on the server, including deduplication and standardization. This formatting is performed using the Python Pandas library. The formatted data is then prepared for analysis and visualization.

[0079] Next, the formatted data is presented to the user in the most optimal visual format using a generative AI model. Python's Matplotlib and Seaborn libraries are used for visualization, automatically generating graphs and charts tailored to the nature and purpose of the data.

[0080] Furthermore, the server analyzes historical data from the visualized data to extract patterns and trends. This analysis utilizes the Scikit-learn library, particularly through regression analysis and clustering to reveal data patterns.

[0081] Based on the analysis results, the server utilizes a generative AI model to automatically generate various policy proposals. In this process, the generated proposals are presented as multiple different scenarios and displayed to the user on their device.

[0082] For example, in a case focused on promoting tourism, a user could input a prompt such as, "Based on tourist data from the past five years and current traffic data, please suggest the optimal timing and target customer base for a tourism campaign within the next six months." Based on this prompt, the AI ​​model would perform appropriate data analysis and generate specific advice. This would then enable the user to develop data-driven, effective policies.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user enters the policy objective or theme into the terminal. This input information is sent to the server as basic data for the server to search for relevant information. An example is entering the theme "How to promote regional economic revitalization" as a prompt. The entered theme serves as the starting point for processing on the server.

[0086] Step 2:

[0087] The server collects relevant information from local government internal databases and external data providers based on the received theme. This collection process uses SQL queries to extract data from databases and REST APIs to retrieve information from online data. The input is the theme, and the output is the collected dataset.

[0088] Step 3:

[0089] The server performs deduplication and formatting on the collected data. Specifically, it uses the Python Pandas library to eliminate duplicates within the dataset and standardize the format. This process results in structured and analyzable data.

[0090] Step 4:

[0091] The server generates formatted data and visualizes it using an AI model. It uses specific algorithms and libraries (such as Matplotlib and Seaborn) to generate visual representations tailored to the data's characteristics. The input is formatted data, and the output is visualized graphs and charts.

[0092] Step 5:

[0093] The server analyzes the visualized data and applies machine learning to reveal patterns and trends. Using the Scikit-learn library, it performs regression analysis, clustering, and other operations to extract regularities from past data. The input is the visualized data, and the output is the analyzed trends and patterns.

[0094] Step 6:

[0095] Based on the analysis results obtained, the server generates policy proposals using a generative AI model. The generated proposals are presented to the user as multiple policy scenarios. The input is the analysis results, and the output is a set of policy proposal scenarios.

[0096] Step 7:

[0097] The terminal displays policy proposals sent from the server to the user. The user can then use this to develop specific policies. For example, they might receive detailed advice on the timing and target audience of a tourism campaign. The input is the policy proposal, and the output is the specific advice the user sees.

[0098] (Application Example 1)

[0099] 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."

[0100] While data-driven decision-making is crucial in general policymaking and commercial activities, efficiently collecting, formatting, and analyzing relevant data, and then generating concrete proposals based on that data, remains a challenging task. Especially in situations requiring real-time analysis of real-world activity trends and behavioral patterns, and demanding immediate and optimal decision-making, existing systems may not be able to provide rapid and effective solutions.

[0101] 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.

[0102] In this invention, the server includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, means for analyzing the visualized data and generating policy advice, and means for analyzing trends and behavioral patterns of real-world activities and optimizing decision-making. This enables the user to make objective and efficient data-driven decisions in real time.

[0103] A "user" is someone who uses a system to input information and receives data to support decision-making.

[0104] "Information" refers to the purposes and themes related to policy-making and commercial activities that users input.

[0105] "Data" refers to a collection of numerical values, records, and other information related to the information being collected.

[0106] "Selection method" refers to the process of identifying and extracting necessary data related to the information entered by the user.

[0107] "Formatting" refers to the process of removing duplicates and converting the format of collected data to make it suitable for analysis and visualization.

[0108] "Methods of visualization" refer to the process of visually representing formatted data in the form of graphs, charts, and other visual media.

[0109] "Methods of analysis" refer to the process of extracting patterns and trends using machine learning algorithms and statistical methods with visualized data.

[0110] "Means of generating advice" refers to the process of creating specific improvement proposals for policies and commercial activities based on analysis results.

[0111] "Trends and behavioral patterns in real-world activities" refers to information about changes and trends in the real world related to commercial activities and social movements.

[0112] "Methods for optimizing decision-making" refer to the process of identifying and proposing the most advantageous option for the user using insights gained from analysis results.

[0113] This system begins with the user inputting the objectives and themes of policy planning or commercial activities using a terminal. The terminal sends this user input information to a server. Based on the information entered by the user, the server collects relevant data from internal and external databases. The data undergoes deduplicating and format conversion on the server side, and the formatted data is further processed into a format suitable for analysis.

[0114] Next, the server uses AI generation to automatically select a visualization format suitable for the data's characteristics and purpose, based on the formatted data, and generates it as graphs or charts. This visualized data is then presented to the user via their device.

[0115] Next, the server uses the visualized data to perform data analysis using machine learning algorithms and statistical methods. This analysis extracts past patterns and trends. Based on these results, the server generates specific advice regarding policies and commercial activities and proposes options for countermeasures.

[0116] In this system, specific hardware includes user terminals (PCs, smartphones, tablets, etc.), server computers, and APIs for data collection. Software includes scripting languages ​​for data collection and formatting (e.g., Python), libraries for data visualization (e.g., Matplotlib, Seaborn), and machine learning frameworks (e.g., Scikit-learn, TENSORFLOW®).

[0117] For example, a retail store might use this system to determine the timing of its next sale. The user inputs their marketing theme on a terminal, and the server analyzes past sales data to suggest the optimal promotion period.

[0118] An example of a prompt message is: "Analyze sales data from the past year, predict sales trends for the next three months, and generate suggested scenarios."

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] Users input the objectives and themes of policy planning and commercial activities using a terminal. This input information is transmitted to the server via the terminal. The input includes text information and numerical data. The output is the input information transferred to the server.

[0122] Step 2:

[0123] The server collects relevant data from internal databases and external data providers based on the input information received from the user. The input is the user's input information, and the output is a collection of relevant data. This step involves accessing external databases via APIs.

[0124] Step 3:

[0125] The server formats the collected data, specifically performing duplicate removal and format conversion. The input is a collection of related data, and the output is the formatted data. The formatting process includes data cleaning using a Python script.

[0126] Step 4:

[0127] The server uses a generative AI to select the optimal visualization format for the formatted data. The input is formatted data, and the output is in the form of graphs or charts. The visualization is generated using Python's Matplotlib or Seaborn.

[0128] Step 5:

[0129] The server analyzes the visualized data. At this stage, machine learning algorithms are used to extract patterns and trends from historical data. The input is the visualized data, and the output is a numerical model or graph as a result of the analysis. Model training and prediction are performed using Scikit-learn or TensorFlow.

[0130] Step 6:

[0131] The server generates advice on policies and commercial activities based on the analysis results. The input is the analysis results, and the output is the proposed policy and activity scenarios. This includes a natural language generation process using a generative AI model.

[0132] Step 7:

[0133] The terminal displays advice and suggested scenarios sent from the server, enabling the user to make optimal decisions. The input is the suggested scenarios from the server, and the output is the information displayed on the terminal's screen. This information is displayed via a GUI on the terminal.

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

[0135] This invention is a system that supports policy-making by local governments, and by combining it with an emotion engine, it provides data-driven policy proposals that take into account the user's emotions. The system consists of a terminal operated by the user, a server that operates in the background, and communication means that connect them.

[0136] The user inputs the objectives and themes of policy formulation through a terminal. The terminal sends this information to a server, which then collects relevant data from its internal database and external data providers. The server uses an emotion engine to evaluate the user's emotions based on their input patterns and operation speed. For example, if the input is smooth, the user is likely to be judged as calm.

[0137] The server formats the collected data, selects an appropriate visualization format, and visualizes the data. The visualization format chosen here also takes user emotions into consideration, presenting the data in a way that suits the user's state. For example, if a user is feeling stressed, a simple and easy-to-understand graph might be selected.

[0138] Based on the visualized data, the server performs data analysis. The emotion engine evaluates the user's emotional state, and based on the results, the server generates policy recommendations. If the user is judged to be calm, it presents more complex scenarios; if the user is anxious, it proposes simpler solutions, and so on.

[0139] The device presents the user with generated advice and policy scenarios. The content of the presentation reflects the user's emotions, allowing the user to receive suggestions in a way that suits their feelings. For example, when dealing with data on transportation policy, if the user appears to be seeking a quick solution, the device will concisely provide relevant information such as specific transportation improvement measures and cost-effectiveness.

[0140] In this way, this system enables users to formulate data-driven policies while taking emotions into consideration, thereby supporting more appropriate and effective decision-making.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The user inputs the objectives and themes of policy formulation through their device. The device then sends this information to the server.

[0144] Step 2:

[0145] The server collects relevant data from internal and external databases based on the theme received from the user. The server verifies the integrity of the data and performs any necessary formatting.

[0146] Step 3:

[0147] The server uses an emotion engine to evaluate the user's emotional state by analyzing the user's input patterns and operation speed. For example, if the user is typing hastily, the server infers that the user is feeling anxious.

[0148] Step 4:

[0149] The server selects an appropriate graph format to visualize the formatted data. It also makes adjustments based on the user's emotional state, prioritizing formats that are easy to understand.

[0150] Step 5:

[0151] The terminal displays the visualized data sent from the server through a user interface. The user visually reviews this data to understand trends and patterns.

[0152] Step 6:

[0153] The server performs further detailed data analysis based on the visualized data. The generated policy recommendations are optimized to match the user's sentiment.

[0154] Step 7:

[0155] The terminal presents the user with advice and multiple policy scenarios generated by the server. For example, if the user is feeling stressed, simple and direct suggestions will be offered.

[0156] Step 8:

[0157] Users consider and decide on policy proposals based on the advice provided. This allows for effective and appropriate policy-making that takes emotions into account.

[0158] (Example 2)

[0159] 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".

[0160] In policymaking, data analysis and proposals are often made without considering users' emotions and psychological states, which has posed challenges to effective policy decision-making. Proposals that ignore the uncertainty and stress that users experience lack feasibility and credibility, making it difficult to arrive at optimal policies.

[0161] 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.

[0162] In this invention, the server includes means for collecting relevant data based on information input by the user, means for performing an emotion evaluation and analyzing the user's psychological state, and means for formatting the selected data and visualizing it in an optimal format according to the user's emotions. This makes it possible to propose effective and practical policies that take into account the user's emotional state.

[0163] A "user" refers to a person who uses the system to input information for policy formulation and receive suggestions.

[0164] "Means of data collection" refers to the process of obtaining relevant information from internal or external sources based on user input.

[0165] "Methods for performing emotional evaluation" refers to technologies that analyze the user's input speed and patterns to evaluate the user's psychological state.

[0166] "Psychological state" refers to the user's mental state, including their emotions, motivation, and stress levels, and is a factor considered when analyzing data and making recommendations.

[0167] "Methods for formatting data" refers to the process of converting collected information into a format that is easy to analyze.

[0168] "Means of visualization" refers to methods for visually representing formatted data and presenting it in an easily understandable way to the user.

[0169] "Means of generating policy advice" refers to the process of creating proposals and advice for policy formulation based on analyzed data.

[0170] The embodiment of the invention consists of a system that enables data-driven proposals that take user sentiment into account in policymaking. This system includes a user-operated terminal, a server that processes data, and communication means that connect them.

[0171] First, the user operates a terminal to input the objectives and themes of the policy-making process. The terminal used here is a typical computer or digital device that receives input from the user and transmits that information to a server.

[0172] The server receives user input and then collects data based on it. This collection process involves accessing internal databases and external information providers to retrieve relevant data. A standard data management system is used for the internal database, while API-based communication is used to retrieve external information. To efficiently process and analyze the collected data, the server has programming languages ​​such as Python and Java (registered trademark) installed.

[0173] Next, an emotion engine is installed on the server to evaluate emotions based on data such as user input speed and patterns. This evaluation uses analysis methods that leverage natural language processing technology, with the Python TextBlob library being particularly applicable.

[0174] Furthermore, the server is responsible for formatting the collected data and visualizing it in a format appropriate to the user's emotional state. The Pandas library is used for data formatting, and the Matplotlib library is used for visualization. For example, by simplifying the data, bar graphs or pie charts are provided to users who are experiencing stress.

[0175] Finally, based on the visualized data, the server performs analysis and generates policy proposals. The SciPy library is used for the analysis. By utilizing a generative AI model to create a document about the policy proposals and providing prompts such as "Please describe in detail specific proposals for easing local traffic congestion," the system presents the user with appropriate policy scenarios.

[0176] This system allows users to receive emotion-sensitive data analysis and policy recommendations, enabling more appropriate and actionable policy-making.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] Users input policy-making objectives and themes using a terminal. This input is in text format and is done through an input interface built into the terminal. The terminal converts the input information into structured data and sends it to the server using a secure communication protocol.

[0180] Step 2:

[0181] The server analyzes the data received from the terminal and collects additional data from relevant external and internal sources. This collection process is carried out through external information retrieval via APIs and internal database queries. Since the collected data may be in different formats, the server unifies it and converts it into a format that is easy to analyze.

[0182] Step 3:

[0183] The server uses user text input and collected data to evaluate the user's emotional state using an emotion engine. Patterns such as input speed, selected words, and sentence structure are analyzed. The emotion engine uses natural language processing techniques to identify the user's emotions (e.g., calm, stressed, anxious) and outputs the evaluation results as a data structure.

[0184] Step 4:

[0185] The server selects an appropriate data visualization format based on the sentiment assessment results and formats the collected data. A data analysis library is used for data formatting, and a graphing library is used for visualization. If a user is assessed as experiencing stress, a simple, easy-to-understand graph format is selected. The formatted data is output as an image file or interactive graph.

[0186] Step 5:

[0187] The server analyzes standardized and formatted data and uses a generative AI model to create policy proposals. Statistical analysis libraries are utilized for data analysis, and the generated proposals are output in the form of detailed policy documents. The prompt, "Please describe in detail specific proposals for mitigating local traffic congestion," is used, and the AI ​​model generates proposals based on this.

[0188] Step 6:

[0189] The terminal displays visualization data and policy proposals received from the server to the user. The display is in the form of interactive dashboards and reports, allowing the user to consider more appropriate policy formulation based on the presented information.

[0190] (Application Example 2)

[0191] 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".

[0192] In modern society, local governments are required to make decisions that take into account the feelings and circumstances of residents when choosing from a variety of policies. However, conventional policy-making systems are based on quantitative data, and there is a challenge in that they have difficulty adequately considering the emotional state of users. Therefore, there is a need to develop a system that can make flexible policy proposals according to the situation.

[0193] 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.

[0194] In this invention, the server includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, means for analyzing the visualized data and generating policy proposals, means for sentiment analysis to measure the user's emotional state, and means for adjusting the data visualization format and proposal content based on the user's emotional state. This enables appropriate data visualization and policy proposals while taking the user's emotional state into consideration.

[0195] A "user" is an individual or group that uses the system and is the entity that receives selections and suggestions for relevant data based on the information it inputs.

[0196] "Data" refers to numerical and textual information collected and analyzed based on user input, and serves as the basis for policy proposals.

[0197] "Emotion analysis methods" refer to technologies that measure a user's emotional state based on their input methods, gaze, voice, etc., and reflect this in data processing and suggested content.

[0198] "Visualization methods" refer to technologies for formatting selected data into an easy-to-understand format and providing it to users in the form of graphs, charts, and other visual aids.

[0199] A "policy proposal" is a solution or guideline generated based on user input and related data, and is provided to the user while taking their emotional state into consideration.

[0200] A "system" is a collection of mechanisms and devices that comprehensively process data selection, visualization, analysis, measurement and adjustment of user sentiment, and ultimately propose policies.

[0201] This system primarily consists of a user-operated terminal and a server running in the background. The terminal receives policy-making information from the user and transmits it to the server. Based on this, the server collects relevant data from internal databases and external data providers and evaluates the user's emotional state using sentiment analysis tools.

[0202] Specifically, the emotion analysis system detects emotions from, for example, user input patterns, operation speed, and data from external sensors. The server formats the collected data and visualizes it in an appropriate format using visualization tools. In this process, a more easily understandable graph or visualization method suitable for the subject is selected according to the user's emotional state.

[0203] By utilizing a generative AI model to analyze data, policy proposals are generated based on the sentiment analysis results. For example, if a user is judged to be highly stressed, specific and concise proposals are provided. In this way, the system provides the user with the most suitable policy proposals and realizes an interactive policy-making process that takes their emotional state into consideration.

[0204] The hardware used includes wearable devices such as smart glasses, and the software includes an emotion analysis engine and a visualization module for visualizing collected data. By utilizing generative AI models, it is possible to generate scenario suggestions based on the user's emotions and data.

[0205] As a concrete example, when a user is walking in an urban area, smart glasses can sense their stress level in real time and display nearby safety information and evacuation routes. Another example of a prompt message is, "Explain what should be done to detect a user's stress level in a public place and provide a sense of security."

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] Users input information related to policy formulation using a terminal. This information includes themes and objectives, and is sent from the terminal to the server. This prepares the server to begin the process of collecting data related to the theme.

[0209] Step 2:

[0210] The server collects relevant data from internal databases and external data providers based on themes and objectives received from users. In this step, generative AI models are used to analyze historical data, predict trends, and prepare useful datasets. The collected data forms the basis for the next process.

[0211] Step 3:

[0212] The server evaluates the user's emotional state using emotion analysis tools. It quantifies the emotional state by utilizing data obtained from the user's input patterns, operation speed, and other sensors. Based on the data analysis results, it determines whether the user is stressed, calm, or otherwise unsettled.

[0213] Step 4:

[0214] The server processes and visualizes the data. Sentiment analysis results are incorporated, and the optimal visualization format is selected based on the user's state. For example, a user experiencing stress is presented with a simple and easy-to-understand graph. The visualized data is then output as information for the user.

[0215] Step 5:

[0216] The server utilizes a generative AI model to generate policy proposals based on visualized data and sentiment analysis results. The complexity and detail of the proposals are adjusted according to the user's emotional state. Calm users are offered more detailed scenarios, while stressed users are offered simpler solutions.

[0217] Step 6:

[0218] The terminal presents the generated policy proposals to the user. In doing so, appropriate information is displayed in a way that reflects the user's emotional state. For example, when making urban policy proposals to the user, if a quick response is required, this includes promptly presenting specific measures and cost information.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] The system of the present invention is designed to support data-driven decision-making in policy formulation by local governments. This system includes user-operated terminals, a server, and communication means for linking them together.

[0236] Users input policy-making objectives and themes using a terminal. The terminal sends this information to a server, which then collects relevant data from the local government's internal databases and external data providers. The server then processes the acquired data, such as removing duplicates and converting formats, to prepare it for analysis.

[0237] The formatted data is then visualized on the server. Specifically, a generating AI automatically selects a visualization format suitable for the data's characteristics and purpose, and generates it as graphs and charts. This visualized data is then presented to the user via their device.

[0238] Next, the server performs data analysis based on the visualized data. It applies machine learning algorithms to extract patterns and trends from past data and attempts to predict policy effects. Based on the analysis results, the server generates policy proposals and sends various policy scenarios to the terminal.

[0239] Users can proceed with considering specific policies based on the advice and policy scenarios displayed on their devices. For example, when considering tourism promotion policies, users can review visualized data on human flow and trends in tourist numbers, and receive support in determining the timing and target audience for effective tourism campaigns.

[0240] In this way, this system enables users to formulate objective and efficient policies based on data. As a result, local government policies become more effective, and high-quality services can be provided to residents.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The user operates the terminal to input information about the objectives and themes of policy formulation. Once input is complete, the terminal sends this information to the server.

[0244] Step 2:

[0245] Based on themes received from users, the server accesses internal databases and external data sources to collect relevant data. The server then checks the retrieved data for duplicates and missing data, and organizes the data.

[0246] Step 3:

[0247] The server passes the formatted data to the visualization engine, where the generating AI selects the appropriate visualization format (e.g., graph, chart). The visualized data is then generated.

[0248] Step 4:

[0249] The terminal displays the visualized data sent from the server on the user interface. The user reviews this data and visually understands its trends and characteristics.

[0250] Step 5:

[0251] The server begins data analysis based on the visualized data. Using machine learning algorithms, it extracts patterns and trends from past data and predicts future policy effects.

[0252] Step 6:

[0253] The server generates policy proposals based on the analysis results and develops multiple most effective policy scenarios.

[0254] Step 7:

[0255] The device presents the user with generated advice and policy scenarios. Based on the information provided, the user can then consider and decide on specific policy directions.

[0256] (Example 1)

[0257] 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."

[0258] In policymaking by local governments, there is a need to efficiently and accurately predict policy effects and create objective policy proposals while utilizing vast amounts of data. Conventional systems have the problem of requiring a lot of manual work in the process of data collection, formatting, and analysis, which is time-consuming and labor-intensive, and also relies heavily on subjective judgment.

[0259] 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.

[0260] In this invention, the server includes means for collecting relevant information based on the purpose or theme of a plan entered by the user; means for removing duplicates from the collected information and formatting it into a unified format; means for visually displaying the formatted information in an optimal format using a generative AI model; means for extracting regularities or trends from past data based on the visualized information; means for predicting the effectiveness of the plan based on the extracted regularities or trends; and means for generating plan proposals using the generative AI model from the prediction results of the plan's effectiveness. This makes it possible to accurately process vast amounts of data and efficiently make objective policy proposals.

[0261] A "user" refers to someone who operates the system and inputs policy objectives and themes.

[0262] "Plan objectives or themes" refer to information that indicates specific goals and policies in policymaking.

[0263] "Relevant information" refers to information including data from internal databases and external data providers that are collected based on the objectives or themes of the plan.

[0264] "Means of collection" refers to methods and processes for automatically gathering necessary information based on a given theme.

[0265] "Deduplication" refers to the process of removing duplicate data from collected information.

[0266] "Methods for formatting into a unified format" refers to methods of processing collected information by converting it into a consistent format that facilitates analysis and visualization.

[0267] A "generative AI model" refers to an artificial intelligence model that automatically generates appropriate visual formats based on large amounts of data.

[0268] "Means of visual display" refers to methods of presenting formatted information in an easy-to-understand format for users, such as graphs and charts.

[0269] "Regularity or trend" refers to a consistent pattern or trend revealed through the analysis of past data.

[0270] "Means of predicting the effectiveness of a plan" refers to methods of predicting the degree to which a plan will be successful, using data-driven regularities or trends.

[0271] "Means for generating plan proposals" refers to methods for deriving proposals that support the formulation of optimal policies based on predictions and analysis results.

[0272] Embodiments of the present invention are shown below.

[0273] The system primarily consists of servers, terminals, and communication means to link them together. Users input policy-making objectives or themes via terminals, and the server operates based on this input.

[0274] The server collects relevant information from internal databases and external data providers based on the received policy theme. It uses database management systems such as SQL queries to access the internal database and REST APIs to retrieve external data.

[0275] The collected data undergoes formatting on the server, including deduplication and standardization. This formatting is performed using the Python Pandas library. The formatted data is then prepared for analysis and visualization.

[0276] Next, the formatted data is presented to the user in the most optimal visual format using a generative AI model. Python's Matplotlib and Seaborn libraries are used for visualization, automatically generating graphs and charts tailored to the nature and purpose of the data.

[0277] Furthermore, the server analyzes historical data from the visualized data to extract patterns and trends. This analysis utilizes the Scikit-learn library, particularly through regression analysis and clustering to reveal data patterns.

[0278] Based on the analysis results, the server utilizes a generative AI model to automatically generate various policy proposals. In this process, the generated proposals are presented as multiple different scenarios and displayed to the user on their device.

[0279] For example, in a case focused on promoting tourism, a user could input a prompt such as, "Based on tourist data from the past five years and current traffic data, please suggest the optimal timing and target customer base for a tourism campaign within the next six months." Based on this prompt, the AI ​​model would perform appropriate data analysis and generate specific advice. This would then enable the user to develop data-driven, effective policies.

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The user inputs the purpose or theme of the policy into the terminal. This input information is sent to the server as basic data for the server to search for relevant information. For example, the theme "How to promote the activation of the regional economy" is input as a prompt. The input theme becomes the starting point for processing by the server.

[0283] Step 2:

[0284] Based on the received theme, the server collects relevant information from the internal database of local governments and external data providers. In this collection process, data is extracted from the database using SQL queries, and information is obtained from online data using REST APIs. The input is the theme, and the output is the collected dataset.

[0285] Step 3:

[0286] The server performs duplicate removal and format unification on the collected data. Specifically, the Pandas library in Python is used to eliminate duplicates within the dataset and unify the format. Through this process, structured and analyzable data is output.

[0287] Step 4:

[0288] The server visualizes the formatted data using a generative AI model. Specific algorithms and libraries (such as Matplotlib and Seaborn) are used to generate visual representations according to the characteristics of the data. The input is the formatted data, and the output is visualized graphs and charts.

[0289] Step 5:

[0290] The server analyzes the visualized data and applies machine learning to reveal patterns and trends. Using the Scikit-learn library, it performs regression analysis, clustering, and other operations to extract regularities from past data. The input is the visualized data, and the output is the analyzed trends and patterns.

[0291] Step 6:

[0292] Based on the analysis results obtained, the server generates policy proposals using a generative AI model. The generated proposals are presented to the user as multiple policy scenarios. The input is the analysis results, and the output is a set of policy proposal scenarios.

[0293] Step 7:

[0294] The terminal displays policy proposals sent from the server to the user. The user can then use this to develop specific policies. For example, they might receive detailed advice on the timing and target audience of a tourism campaign. The input is the policy proposal, and the output is the specific advice the user sees.

[0295] (Application Example 1)

[0296] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0297] While data-driven decision-making is crucial in general policymaking and commercial activities, efficiently collecting, formatting, and analyzing relevant data, and then generating concrete proposals based on that data, remains a challenging task. Especially in situations requiring real-time analysis of real-world activity trends and behavioral patterns, and demanding immediate and optimal decision-making, existing systems may not be able to provide rapid and effective solutions.

[0298] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0299] In this invention, the server includes means for selecting relevant data based on information input by the user, means for shaping and visualizing the selected data, means for analyzing the visualized data and generating advice on policies, and means for analyzing trends and behavior patterns in activities in the real world and optimizing decision-making. Thereby, the user can make objective and efficient decisions based on data in real time.

[0300] A "user" is a person who inputs information using the system and receives data to assist in decision-making.

[0301] "Information" refers to the purposes and themes related to policy-making and business activities input by the user.

[0302] "Data" is a collection of numerical values, records, etc. related to the information collected.

[0303] The "means for selecting" is a process of identifying and extracting the necessary data related to the information input from the user.

[0304] The "means for shaping" is a process of performing duplicate removal and format conversion on the collected data and processing it into a form suitable for analysis and visualization.

[0305] The "means for visualizing" is a process of visually representing the shaped data in the form of graphs, charts, etc.

[0306] The "means for analyzing" is a process of extracting patterns and trends from the visualized data using machine learning algorithms and statistical methods.

[0307] The "means for generating advice" is a process of creating specific improvement proposals for policies and business activities based on the analysis results.

[0308] "Trends and behavioral patterns in real-world activities" refers to information about changes and trends in the real world related to commercial activities and social movements.

[0309] "Methods for optimizing decision-making" refer to the process of identifying and proposing the most advantageous option for the user using insights gained from analysis results.

[0310] This system begins with the user inputting the objectives and themes of policy planning or commercial activities using a terminal. The terminal sends this user input information to a server. Based on the information entered by the user, the server collects relevant data from internal and external databases. The data undergoes deduplicating and format conversion on the server side, and the formatted data is further processed into a format suitable for analysis.

[0311] Next, the server uses AI generation to automatically select a visualization format suitable for the data's characteristics and purpose, based on the formatted data, and generates it as graphs or charts. This visualized data is then presented to the user via their device.

[0312] Next, the server uses the visualized data to perform data analysis using machine learning algorithms and statistical methods. This analysis extracts past patterns and trends. Based on these results, the server generates specific advice regarding policies and commercial activities and proposes options for countermeasures.

[0313] In this system, specific hardware includes user terminals (PCs, smartphones, tablets, etc.), server computers, and APIs for data collection. Software includes scripting languages ​​for data collection and formatting (e.g., Python), libraries for data visualization (e.g., Matplotlib, Seaborn), and machine learning frameworks (e.g., Scikit-learn, TensorFlow).

[0314] For example, a retail store might use this system to determine the timing of its next sale. The user inputs their marketing theme on a terminal, and the server analyzes past sales data to suggest the optimal promotion period.

[0315] An example of a prompt message is: "Analyze sales data from the past year, predict sales trends for the next three months, and generate suggested scenarios."

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] Users input the objectives and themes of policy planning and commercial activities using a terminal. This input information is transmitted to the server via the terminal. The input includes text information and numerical data. The output is the input information transferred to the server.

[0319] Step 2:

[0320] The server collects relevant data from internal databases and external data providers based on the input information received from the user. The input is the user's input information, and the output is a collection of relevant data. This step involves accessing external databases via APIs.

[0321] Step 3:

[0322] The server formats the collected data, specifically performing duplicate removal and format conversion. The input is a collection of related data, and the output is the formatted data. The formatting process includes data cleaning using a Python script.

[0323] Step 4:

[0324] The server uses a generative AI to select the optimal visualization format for the formatted data. The input is formatted data, and the output is in the form of graphs or charts. The visualization is generated using Python's Matplotlib or Seaborn.

[0325] Step 5:

[0326] The server analyzes the visualized data. At this stage, machine learning algorithms are used to extract patterns and trends from historical data. The input is the visualized data, and the output is a numerical model or graph as a result of the analysis. Model training and prediction are performed using Scikit-learn or TensorFlow.

[0327] Step 6:

[0328] The server generates advice on policies and commercial activities based on the analysis results. The input is the analysis results, and the output is the proposed policy and activity scenarios. This includes a natural language generation process using a generative AI model.

[0329] Step 7:

[0330] The terminal displays advice and suggested scenarios sent from the server, enabling the user to make optimal decisions. The input is the suggested scenarios from the server, and the output is the information displayed on the terminal's screen. This information is displayed via a GUI on the terminal.

[0331] 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.

[0332] This invention is a system that supports policy-making by local governments, and by combining it with an emotion engine, it provides data-driven policy proposals that take into account the user's emotions. The system consists of a terminal operated by the user, a server that operates in the background, and communication means that connect them.

[0333] The user inputs the objectives and themes of policy formulation through a terminal. The terminal sends this information to a server, which then collects relevant data from its internal database and external data providers. The server uses an emotion engine to evaluate the user's emotions based on their input patterns and operation speed. For example, if the input is smooth, the user is likely to be judged as calm.

[0334] The server formats the collected data, selects an appropriate visualization format, and visualizes the data. The visualization format chosen here also takes user emotions into consideration, presenting the data in a way that suits the user's state. For example, if a user is feeling stressed, a simple and easy-to-understand graph might be selected.

[0335] Based on the visualized data, the server performs data analysis. The emotion engine evaluates the user's emotional state, and based on the results, the server generates policy recommendations. If the user is judged to be calm, it presents more complex scenarios; if the user is anxious, it proposes simpler solutions, and so on.

[0336] The device presents the user with generated advice and policy scenarios. The content of the presentation reflects the user's emotions, allowing the user to receive suggestions in a way that suits their feelings. For example, when dealing with data on transportation policy, if the user appears to be seeking a quick solution, the device will concisely provide relevant information such as specific transportation improvement measures and cost-effectiveness.

[0337] In this way, this system enables users to formulate data-driven policies while taking emotions into consideration, thereby supporting more appropriate and effective decision-making.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The user inputs the objectives and themes of policy formulation through their device. The device then sends this information to the server.

[0341] Step 2:

[0342] The server collects relevant data from internal and external databases based on the theme received from the user. The server verifies the integrity of the data and performs any necessary formatting.

[0343] Step 3:

[0344] The server uses an emotion engine to evaluate the user's emotional state by analyzing the user's input patterns and operation speed. For example, if the user is typing hastily, the server infers that the user is feeling anxious.

[0345] Step 4:

[0346] The server selects an appropriate graph format to visualize the formatted data. It also makes adjustments based on the user's emotional state, prioritizing formats that are easy to understand.

[0347] Step 5:

[0348] The terminal displays the visualized data sent from the server through a user interface. The user visually reviews this data to understand trends and patterns.

[0349] Step 6:

[0350] The server performs further detailed data analysis based on the visualized data. The generated policy recommendations are optimized to match the user's sentiment.

[0351] Step 7:

[0352] The terminal presents the user with advice and multiple policy scenarios generated by the server. For example, if the user is feeling stressed, simple and direct suggestions will be offered.

[0353] Step 8:

[0354] Users consider and decide on policy proposals based on the advice provided. This allows for effective and appropriate policy-making that takes emotions into account.

[0355] (Example 2)

[0356] 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".

[0357] In policymaking, data analysis and proposals are often made without considering users' emotions and psychological states, which has posed challenges to effective policy decision-making. Proposals that ignore the uncertainty and stress that users experience lack feasibility and credibility, making it difficult to arrive at optimal policies.

[0358] 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.

[0359] In this invention, the server includes means for collecting relevant data based on information input by the user, means for performing an emotion evaluation and analyzing the user's psychological state, and means for formatting the selected data and visualizing it in an optimal format according to the user's emotions. This makes it possible to propose effective and practical policies that take into account the user's emotional state.

[0360] A "user" refers to a person who uses the system to input information for policy formulation and receive suggestions.

[0361] "Means of data collection" refers to the process of obtaining relevant information from internal or external sources based on user input.

[0362] "Methods for performing emotional evaluation" refers to technologies that analyze the user's input speed and patterns to evaluate the user's psychological state.

[0363] "Psychological state" refers to the user's mental state, including their emotions, motivation, and stress levels, and is a factor considered when analyzing data and making recommendations.

[0364] "Methods for formatting data" refers to the process of converting collected information into a format that is easy to analyze.

[0365] "Means of visualization" refers to methods for visually representing formatted data and presenting it in an easily understandable way to the user.

[0366] "Means of generating policy advice" refers to the process of creating proposals and advice for policy formulation based on analyzed data.

[0367] The embodiment of the invention consists of a system that enables data-driven proposals that take user sentiment into account in policymaking. This system includes a user-operated terminal, a server that processes data, and communication means that connect them.

[0368] First, the user operates a terminal to input the objectives and themes of the policy-making process. The terminal used here is a typical computer or digital device that receives input from the user and transmits that information to a server.

[0369] The server receives user input and then collects data based on it. This collection process involves accessing internal databases and external information providers to retrieve relevant data. A common data management system is used for the internal database, while API-based communication is used to retrieve external information. To efficiently process and analyze the collected data, the server has programming languages ​​such as Python and Java installed.

[0370] Next, an emotion engine is installed on the server to evaluate emotions based on data such as user input speed and patterns. This evaluation uses analysis methods that leverage natural language processing technology, with the Python TextBlob library being particularly applicable.

[0371] Furthermore, the server is responsible for formatting the collected data and visualizing it in a format appropriate to the user's emotional state. The Pandas library is used for data formatting, and the Matplotlib library is used for visualization. For example, by simplifying the data, bar graphs or pie charts are provided to users who are experiencing stress.

[0372] Finally, based on the visualized data, the server performs analysis and generates policy proposals. The SciPy library is used for the analysis. By utilizing a generative AI model to create a document about the policy proposals and providing prompts such as "Please describe in detail specific proposals for easing local traffic congestion," the system presents the user with appropriate policy scenarios.

[0373] This system allows users to receive emotion-sensitive data analysis and policy recommendations, enabling more appropriate and actionable policy-making.

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1:

[0376] Users input policy-making objectives and themes using a terminal. This input is in text format and is done through an input interface built into the terminal. The terminal converts the input information into structured data and sends it to the server using a secure communication protocol.

[0377] Step 2:

[0378] The server analyzes the data received from the terminal and collects additional data from relevant external and internal sources. This collection process is carried out through external information retrieval via APIs and internal database queries. Since the collected data may be in different formats, the server unifies it and converts it into a format that is easy to analyze.

[0379] Step 3:

[0380] The server uses user text input and collected data to evaluate the user's emotional state using an emotion engine. Patterns such as input speed, selected words, and sentence structure are analyzed. The emotion engine uses natural language processing techniques to identify the user's emotions (e.g., calm, stressed, anxious) and outputs the evaluation results as a data structure.

[0381] Step 4:

[0382] The server selects an appropriate data visualization format based on the sentiment assessment results and formats the collected data. A data analysis library is used for data formatting, and a graphing library is used for visualization. If a user is assessed as experiencing stress, a simple, easy-to-understand graph format is selected. The formatted data is output as an image file or interactive graph.

[0383] Step 5:

[0384] The server analyzes standardized and formatted data and uses a generative AI model to create policy proposals. Statistical analysis libraries are utilized for data analysis, and the generated proposals are output in the form of detailed policy documents. The prompt, "Please describe in detail specific proposals for mitigating local traffic congestion," is used, and the AI ​​model generates proposals based on this.

[0385] Step 6:

[0386] The terminal displays visualization data and policy proposals received from the server to the user. The display is in the form of interactive dashboards and reports, allowing the user to consider more appropriate policy formulation based on the presented information.

[0387] (Application Example 2)

[0388] 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."

[0389] In modern society, local governments are required to make decisions that take into account the feelings and circumstances of residents when choosing from a variety of policies. However, conventional policy-making systems are based on quantitative data, and there is a challenge in that they have difficulty adequately considering the emotional state of users. Therefore, there is a need to develop a system that can make flexible policy proposals according to the situation.

[0390] 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.

[0391] In this invention, the server includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, means for analyzing the visualized data and generating policy proposals, means for sentiment analysis to measure the user's emotional state, and means for adjusting the data visualization format and proposal content based on the user's emotional state. This enables appropriate data visualization and policy proposals while taking the user's emotional state into consideration.

[0392] A "user" is an individual or group that uses the system and is the entity that receives selections and suggestions for relevant data based on the information it inputs.

[0393] "Data" refers to numerical and textual information collected and analyzed based on user input, and serves as the basis for policy proposals.

[0394] "Emotion analysis methods" refer to technologies that measure a user's emotional state based on their input methods, gaze, voice, etc., and reflect this in data processing and suggested content.

[0395] "Visualization methods" refer to technologies for formatting selected data into an easy-to-understand format and providing it to users in the form of graphs, charts, and other visual aids.

[0396] A "policy proposal" is a solution or guideline generated based on user input and related data, and is provided to the user while taking their emotional state into consideration.

[0397] A "system" is a collection of mechanisms and devices that comprehensively process data selection, visualization, analysis, measurement and adjustment of user sentiment, and ultimately propose policies.

[0398] This system primarily consists of a user-operated terminal and a server running in the background. The terminal receives policy-making information from the user and transmits it to the server. Based on this, the server collects relevant data from internal databases and external data providers and evaluates the user's emotional state using sentiment analysis tools.

[0399] Specifically, the emotion analysis system detects emotions from, for example, user input patterns, operation speed, and data from external sensors. The server formats the collected data and visualizes it in an appropriate format using visualization tools. In this process, a more easily understandable graph or visualization method suitable for the subject is selected according to the user's emotional state.

[0400] By utilizing a generative AI model to analyze data, policy proposals are generated based on the sentiment analysis results. For example, if a user is judged to be highly stressed, specific and concise proposals are provided. In this way, the system provides the user with the most suitable policy proposals and realizes an interactive policy-making process that takes their emotional state into consideration.

[0401] The hardware used includes wearable devices such as smart glasses, and the software includes an emotion analysis engine and a visualization module for visualizing collected data. By utilizing generative AI models, it is possible to generate scenario suggestions based on the user's emotions and data.

[0402] As a concrete example, when a user is walking in an urban area, smart glasses can sense their stress level in real time and display nearby safety information and evacuation routes. Another example of a prompt message is, "Explain what should be done to detect a user's stress level in a public place and provide a sense of security."

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] Users input information related to policy formulation using a terminal. This information includes themes and objectives, and is sent from the terminal to the server. This prepares the server to begin the process of collecting data related to the theme.

[0406] Step 2:

[0407] The server collects relevant data from internal databases and external data providers based on themes and objectives received from users. In this step, generative AI models are used to analyze historical data, predict trends, and prepare useful datasets. The collected data forms the basis for the next process.

[0408] Step 3:

[0409] The server evaluates the user's emotional state using emotion analysis tools. It quantifies the emotional state by utilizing data obtained from the user's input patterns, operation speed, and other sensors. Based on the data analysis results, it determines whether the user is stressed, calm, or otherwise unsettled.

[0410] Step 4:

[0411] The server processes and visualizes the data. Sentiment analysis results are incorporated, and the optimal visualization format is selected based on the user's state. For example, a user experiencing stress is presented with a simple and easy-to-understand graph. The visualized data is then output as information for the user.

[0412] Step 5:

[0413] The server utilizes a generative AI model to generate policy proposals based on visualized data and sentiment analysis results. The complexity and detail of the proposals are adjusted according to the user's emotional state. Calm users are offered more detailed scenarios, while stressed users are offered simpler solutions.

[0414] Step 6:

[0415] The terminal presents the generated policy proposals to the user. In doing so, appropriate information is displayed in a way that reflects the user's emotional state. For example, when making urban policy proposals to the user, if a quick response is required, this includes promptly presenting specific measures and cost information.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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".

[0432] The system of the present invention is designed to support data-driven decision-making in policy formulation by local governments. This system includes user-operated terminals, a server, and communication means for linking them together.

[0433] Users input policy-making objectives and themes using a terminal. The terminal sends this information to a server, which then collects relevant data from the local government's internal databases and external data providers. The server then processes the acquired data, such as removing duplicates and converting formats, to prepare it for analysis.

[0434] The formatted data is then visualized on the server. Specifically, a generating AI automatically selects a visualization format suitable for the data's characteristics and purpose, and generates it as graphs and charts. This visualized data is then presented to the user via their device.

[0435] Next, the server performs data analysis based on the visualized data. It applies machine learning algorithms to extract patterns and trends from past data and attempts to predict policy effects. Based on the analysis results, the server generates policy proposals and sends various policy scenarios to the terminal.

[0436] Users can proceed with considering specific policies based on the advice and policy scenarios displayed on their devices. For example, when considering tourism promotion policies, users can review visualized data on human flow and trends in tourist numbers, and receive support in determining the timing and target audience for effective tourism campaigns.

[0437] In this way, this system enables users to formulate objective and efficient policies based on data. As a result, local government policies become more effective, and high-quality services can be provided to residents.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The user operates the terminal to input information about the objectives and themes of policy formulation. Once input is complete, the terminal sends this information to the server.

[0441] Step 2:

[0442] Based on themes received from users, the server accesses internal databases and external data sources to collect relevant data. The server then checks the retrieved data for duplicates and missing data, and organizes the data.

[0443] Step 3:

[0444] The server passes the formatted data to the visualization engine, where the generating AI selects the appropriate visualization format (e.g., graph, chart). The visualized data is then generated.

[0445] Step 4:

[0446] The terminal displays the visualized data sent from the server on the user interface. The user reviews this data and visually understands its trends and characteristics.

[0447] Step 5:

[0448] The server begins data analysis based on the visualized data. Using machine learning algorithms, it extracts patterns and trends from past data and predicts future policy effects.

[0449] Step 6:

[0450] The server generates policy proposals based on the analysis results and develops multiple most effective policy scenarios.

[0451] Step 7:

[0452] The device presents the user with generated advice and policy scenarios. Based on the information provided, the user can then consider and decide on specific policy directions.

[0453] (Example 1)

[0454] 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."

[0455] In policymaking by local governments, there is a need to efficiently and accurately predict policy effects and create objective policy proposals while utilizing vast amounts of data. Conventional systems have the problem of requiring a lot of manual work in the process of data collection, formatting, and analysis, which is time-consuming and labor-intensive, and also relies heavily on subjective judgment.

[0456] 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.

[0457] In this invention, the server includes means for collecting relevant information based on the purpose or theme of a plan entered by the user; means for removing duplicates from the collected information and formatting it into a unified format; means for visually displaying the formatted information in an optimal format using a generative AI model; means for extracting regularities or trends from past data based on the visualized information; means for predicting the effectiveness of the plan based on the extracted regularities or trends; and means for generating plan proposals using the generative AI model from the prediction results of the plan's effectiveness. This makes it possible to accurately process vast amounts of data and efficiently make objective policy proposals.

[0458] A "user" refers to someone who operates the system and inputs policy objectives and themes.

[0459] "Plan objectives or themes" refer to information that indicates specific goals and policies in policymaking.

[0460] "Relevant information" refers to information including data from internal databases and external data providers that are collected based on the objectives or themes of the plan.

[0461] "Means of collection" refers to methods and processes for automatically gathering necessary information based on a given theme.

[0462] "Deduplication" refers to the process of removing duplicate data from collected information.

[0463] "Methods for formatting into a unified format" refers to methods of processing collected information by converting it into a consistent format that facilitates analysis and visualization.

[0464] A "generative AI model" refers to an artificial intelligence model that automatically generates appropriate visual formats based on large amounts of data.

[0465] "Means of visual display" refers to methods of presenting formatted information in an easy-to-understand format for users, such as graphs and charts.

[0466] "Regularity or trend" refers to a consistent pattern or trend revealed through the analysis of past data.

[0467] "Means of predicting the effectiveness of a plan" refers to methods of predicting the degree to which a plan will be successful, using data-driven regularities or trends.

[0468] "Means for generating plan proposals" refers to methods for deriving proposals that support the formulation of optimal policies based on predictions and analysis results.

[0469] Embodiments of the present invention are shown below.

[0470] The system primarily consists of servers, terminals, and communication means to link them together. Users input policy-making objectives or themes via terminals, and the server operates based on this input.

[0471] The server collects relevant information from internal databases and external data providers based on the received policy theme. It uses database management systems such as SQL queries to access the internal database and REST APIs to retrieve external data.

[0472] The collected data undergoes formatting on the server, including deduplication and standardization. This formatting is performed using the Python Pandas library. The formatted data is then prepared for analysis and visualization.

[0473] Next, the formatted data is presented to the user in the most optimal visual format using a generative AI model. Python's Matplotlib and Seaborn libraries are used for visualization, automatically generating graphs and charts tailored to the nature and purpose of the data.

[0474] Furthermore, the server analyzes historical data from the visualized data to extract patterns and trends. This analysis utilizes the Scikit-learn library, particularly through regression analysis and clustering to reveal data patterns.

[0475] Based on the analysis results, the server utilizes a generative AI model to automatically generate various policy proposals. In this process, the generated proposals are presented as multiple different scenarios and displayed to the user on their device.

[0476] For example, in a case focused on promoting tourism, a user could input a prompt such as, "Based on tourist data from the past five years and current traffic data, please suggest the optimal timing and target customer base for a tourism campaign within the next six months." Based on this prompt, the AI ​​model would perform appropriate data analysis and generate specific advice. This would then enable the user to develop data-driven, effective policies.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The user enters the policy objective or theme into the terminal. This input information is sent to the server as basic data for the server to search for relevant information. An example is entering the theme "How to promote regional economic revitalization" as a prompt. The entered theme serves as the starting point for processing on the server.

[0480] Step 2:

[0481] The server collects relevant information from local government internal databases and external data providers based on the received theme. This collection process uses SQL queries to extract data from databases and REST APIs to retrieve information from online data. The input is the theme, and the output is the collected dataset.

[0482] Step 3:

[0483] The server performs deduplication and formatting on the collected data. Specifically, it uses the Python Pandas library to eliminate duplicates within the dataset and standardize the format. This process results in structured and analyzable data.

[0484] Step 4:

[0485] The server generates formatted data and visualizes it using an AI model. It uses specific algorithms and libraries (such as Matplotlib and Seaborn) to generate visual representations tailored to the data's characteristics. The input is formatted data, and the output is visualized graphs and charts.

[0486] Step 5:

[0487] The server analyzes the visualized data and applies machine learning to reveal patterns and trends. Using the Scikit-learn library, it performs regression analysis, clustering, and other operations to extract regularities from past data. The input is the visualized data, and the output is the analyzed trends and patterns.

[0488] Step 6:

[0489] Based on the analysis results obtained, the server generates policy proposals using a generative AI model. The generated proposals are presented to the user as multiple policy scenarios. The input is the analysis results, and the output is a set of policy proposal scenarios.

[0490] Step 7:

[0491] The terminal displays policy proposals sent from the server to the user. The user can then use this to develop specific policies. For example, they might receive detailed advice on the timing and target audience of a tourism campaign. The input is the policy proposal, and the output is the specific advice the user sees.

[0492] (Application Example 1)

[0493] 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."

[0494] While data-driven decision-making is crucial in general policymaking and commercial activities, efficiently collecting, formatting, and analyzing relevant data, and then generating concrete proposals based on that data, remains a challenging task. Especially in situations requiring real-time analysis of real-world activity trends and behavioral patterns, and demanding immediate and optimal decision-making, existing systems may not be able to provide rapid and effective solutions.

[0495] 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.

[0496] In this invention, the server includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, means for analyzing the visualized data and generating policy advice, and means for analyzing trends and behavioral patterns of real-world activities and optimizing decision-making. This enables the user to make objective and efficient data-driven decisions in real time.

[0497] A "user" is someone who uses a system to input information and receives data to support decision-making.

[0498] "Information" refers to the purposes and themes related to policy-making and commercial activities that users input.

[0499] "Data" refers to a collection of numerical values, records, and other information related to the information being collected.

[0500] "Selection method" refers to the process of identifying and extracting necessary data related to the information entered by the user.

[0501] "Formatting" refers to the process of removing duplicates and converting the format of collected data to make it suitable for analysis and visualization.

[0502] "Methods of visualization" refer to the process of visually representing formatted data in the form of graphs, charts, and other visual media.

[0503] "Methods of analysis" refer to the process of extracting patterns and trends using machine learning algorithms and statistical methods with visualized data.

[0504] "Means of generating advice" refers to the process of creating specific improvement proposals for policies and commercial activities based on analysis results.

[0505] "Trends and behavioral patterns in real-world activities" refers to information about changes and trends in the real world related to commercial activities and social movements.

[0506] "Methods for optimizing decision-making" refer to the process of identifying and proposing the most advantageous option for the user using insights gained from analysis results.

[0507] This system begins with the user inputting the objectives and themes of policy planning or commercial activities using a terminal. The terminal sends this user input information to a server. Based on the information entered by the user, the server collects relevant data from internal and external databases. The data undergoes deduplicating and format conversion on the server side, and the formatted data is further processed into a format suitable for analysis.

[0508] Next, the server uses AI generation to automatically select a visualization format suitable for the data's characteristics and purpose, based on the formatted data, and generates it as graphs or charts. This visualized data is then presented to the user via their device.

[0509] Next, the server uses the visualized data to perform data analysis using machine learning algorithms and statistical methods. This analysis extracts past patterns and trends. Based on these results, the server generates specific advice regarding policies and commercial activities and proposes options for countermeasures.

[0510] In this system, specific hardware includes user terminals (PCs, smartphones, tablets, etc.), server computers, and APIs for data collection. Software includes scripting languages ​​for data collection and formatting (e.g., Python), libraries for data visualization (e.g., Matplotlib, Seaborn), and machine learning frameworks (e.g., Scikit-learn, TensorFlow).

[0511] For example, a retail store might use this system to determine the timing of its next sale. The user inputs their marketing theme on a terminal, and the server analyzes past sales data to suggest the optimal promotion period.

[0512] An example of a prompt message is: "Analyze sales data from the past year, predict sales trends for the next three months, and generate suggested scenarios."

[0513] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0514] Step 1:

[0515] Users input the objectives and themes of policy planning and commercial activities using a terminal. This input information is transmitted to the server via the terminal. The input includes text information and numerical data. The output is the input information transferred to the server.

[0516] Step 2:

[0517] The server collects relevant data from internal databases and external data providers based on the input information received from the user. The input is the user's input information, and the output is a collection of relevant data. This step involves accessing external databases via APIs.

[0518] Step 3:

[0519] The server formats the collected data, specifically performing duplicate removal and format conversion. The input is a collection of related data, and the output is the formatted data. The formatting process includes data cleaning using a Python script.

[0520] Step 4:

[0521] The server uses a generative AI to select the optimal visualization format for the formatted data. The input is formatted data, and the output is in the form of graphs or charts. The visualization is generated using Python's Matplotlib or Seaborn.

[0522] Step 5:

[0523] The server analyzes the visualized data. At this stage, machine learning algorithms are used to extract patterns and trends from historical data. The input is the visualized data, and the output is a numerical model or graph as a result of the analysis. Model training and prediction are performed using Scikit-learn or TensorFlow.

[0524] Step 6:

[0525] The server generates advice on policies and commercial activities based on the analysis results. The input is the analysis results, and the output is the proposed policy and activity scenarios. This includes a natural language generation process using a generative AI model.

[0526] Step 7:

[0527] The terminal displays advice and suggested scenarios sent from the server, enabling the user to make optimal decisions. The input is the suggested scenarios from the server, and the output is the information displayed on the terminal's screen. This information is displayed via a GUI on the terminal.

[0528] 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.

[0529] This invention is a system that supports policy-making by local governments, and by combining it with an emotion engine, it provides data-driven policy proposals that take into account the user's emotions. The system consists of a terminal operated by the user, a server that operates in the background, and communication means that connect them.

[0530] The user inputs the objectives and themes of policy formulation through a terminal. The terminal sends this information to a server, which then collects relevant data from its internal database and external data providers. The server uses an emotion engine to evaluate the user's emotions based on their input patterns and operation speed. For example, if the input is smooth, the user is likely to be judged as calm.

[0531] The server formats the collected data, selects an appropriate visualization format, and visualizes the data. The visualization format chosen here also takes user emotions into consideration, presenting the data in a way that suits the user's state. For example, if a user is feeling stressed, a simple and easy-to-understand graph might be selected.

[0532] Based on the visualized data, the server performs data analysis. The emotion engine evaluates the user's emotional state, and based on the results, the server generates policy recommendations. If the user is judged to be calm, it presents more complex scenarios; if the user is anxious, it proposes simpler solutions, and so on.

[0533] The device presents the user with generated advice and policy scenarios. The content of the presentation reflects the user's emotions, allowing the user to receive suggestions in a way that suits their feelings. For example, when dealing with data on transportation policy, if the user appears to be seeking a quick solution, the device will concisely provide relevant information such as specific transportation improvement measures and cost-effectiveness.

[0534] In this way, this system enables users to formulate data-driven policies while taking emotions into consideration, thereby supporting more appropriate and effective decision-making.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The user inputs the objectives and themes of policy formulation through their device. The device then sends this information to the server.

[0538] Step 2:

[0539] The server collects relevant data from internal and external databases based on the theme received from the user. The server verifies the integrity of the data and performs any necessary formatting.

[0540] Step 3:

[0541] The server uses an emotion engine to evaluate the user's emotional state by analyzing the user's input patterns and operation speed. For example, if the user is typing hastily, the server infers that the user is feeling anxious.

[0542] Step 4:

[0543] The server selects an appropriate graph format to visualize the formatted data. It also makes adjustments based on the user's emotional state, prioritizing formats that are easy to understand.

[0544] Step 5:

[0545] The terminal displays the visualized data sent from the server through a user interface. The user visually reviews this data to understand trends and patterns.

[0546] Step 6:

[0547] The server performs further detailed data analysis based on the visualized data. The generated policy recommendations are optimized to match the user's sentiment.

[0548] Step 7:

[0549] The terminal presents the user with advice and multiple policy scenarios generated by the server. For example, if the user is feeling stressed, simple and direct suggestions will be offered.

[0550] Step 8:

[0551] Users consider and decide on policy proposals based on the advice provided. This allows for effective and appropriate policy-making that takes emotions into account.

[0552] (Example 2)

[0553] 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."

[0554] In policymaking, data analysis and proposals are often made without considering users' emotions and psychological states, which has posed challenges to effective policy decision-making. Proposals that ignore the uncertainty and stress that users experience lack feasibility and credibility, making it difficult to arrive at optimal policies.

[0555] 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.

[0556] In this invention, the server includes means for collecting relevant data based on information input by the user, means for performing an emotion evaluation and analyzing the user's psychological state, and means for formatting the selected data and visualizing it in an optimal format according to the user's emotions. This makes it possible to propose effective and practical policies that take into account the user's emotional state.

[0557] A "user" refers to a person who uses the system to input information for policy formulation and receive suggestions.

[0558] "Means of data collection" refers to the process of obtaining relevant information from internal or external sources based on user input.

[0559] "Methods for performing emotional evaluation" refers to technologies that analyze the user's input speed and patterns to evaluate the user's psychological state.

[0560] "Psychological state" refers to the user's mental state, including their emotions, motivation, and stress levels, and is a factor considered when analyzing data and making recommendations.

[0561] "Methods for formatting data" refers to the process of converting collected information into a format that is easy to analyze.

[0562] "Means of visualization" refers to methods for visually representing formatted data and presenting it in an easily understandable way to the user.

[0563] "Means of generating policy advice" refers to the process of creating proposals and advice for policy formulation based on analyzed data.

[0564] The embodiment of the invention consists of a system that enables data-driven proposals that take user sentiment into account in policymaking. This system includes a user-operated terminal, a server that processes data, and communication means that connect them.

[0565] First, the user operates a terminal to input the objectives and themes of the policy-making process. The terminal used here is a typical computer or digital device that receives input from the user and transmits that information to a server.

[0566] The server receives user input and then collects data based on it. This collection process involves accessing internal databases and external information providers to retrieve relevant data. A common data management system is used for the internal database, while API-based communication is used to retrieve external information. To efficiently process and analyze the collected data, the server has programming languages ​​such as Python and Java installed.

[0567] Next, an emotion engine is installed on the server to evaluate emotions based on data such as user input speed and patterns. This evaluation uses analysis methods that leverage natural language processing technology, with the Python TextBlob library being particularly applicable.

[0568] Furthermore, the server is responsible for formatting the collected data and visualizing it in a format appropriate to the user's emotional state. The Pandas library is used for data formatting, and the Matplotlib library is used for visualization. For example, by simplifying the data, bar graphs or pie charts are provided to users who are experiencing stress.

[0569] Finally, based on the visualized data, the server performs analysis and generates policy proposals. The SciPy library is used for the analysis. By utilizing a generative AI model to create a document about the policy proposals and providing prompts such as "Please describe in detail specific proposals for easing local traffic congestion," the system presents the user with appropriate policy scenarios.

[0570] This system allows users to receive emotion-sensitive data analysis and policy recommendations, enabling more appropriate and actionable policy-making.

[0571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0572] Step 1:

[0573] Users input policy-making objectives and themes using a terminal. This input is in text format and is done through an input interface built into the terminal. The terminal converts the input information into structured data and sends it to the server using a secure communication protocol.

[0574] Step 2:

[0575] The server analyzes the data received from the terminal and collects additional data from relevant external and internal sources. This collection process is carried out through external information retrieval via APIs and internal database queries. Since the collected data may be in different formats, the server unifies it and converts it into a format that is easy to analyze.

[0576] Step 3:

[0577] The server uses user text input and collected data to evaluate the user's emotional state using an emotion engine. Patterns such as input speed, selected words, and sentence structure are analyzed. The emotion engine uses natural language processing techniques to identify the user's emotions (e.g., calm, stressed, anxious) and outputs the evaluation results as a data structure.

[0578] Step 4:

[0579] The server selects an appropriate data visualization format based on the sentiment assessment results and formats the collected data. A data analysis library is used for data formatting, and a graphing library is used for visualization. If a user is assessed as experiencing stress, a simple, easy-to-understand graph format is selected. The formatted data is output as an image file or interactive graph.

[0580] Step 5:

[0581] The server analyzes standardized and formatted data and uses a generative AI model to create policy proposals. Statistical analysis libraries are utilized for data analysis, and the generated proposals are output in the form of detailed policy documents. The prompt, "Please describe in detail specific proposals for mitigating local traffic congestion," is used, and the AI ​​model generates proposals based on this.

[0582] Step 6:

[0583] The terminal displays visualization data and policy proposals received from the server to the user. The display is in the form of interactive dashboards and reports, allowing the user to consider more appropriate policy formulation based on the presented information.

[0584] (Application Example 2)

[0585] 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."

[0586] In modern society, local governments are required to make decisions that take into account the feelings and circumstances of residents when choosing from a variety of policies. However, conventional policy-making systems are based on quantitative data, and there is a challenge in that they have difficulty adequately considering the emotional state of users. Therefore, there is a need to develop a system that can make flexible policy proposals according to the situation.

[0587] 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.

[0588] In this invention, the server includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, means for analyzing the visualized data and generating policy proposals, means for sentiment analysis to measure the user's emotional state, and means for adjusting the data visualization format and proposal content based on the user's emotional state. This enables appropriate data visualization and policy proposals while taking the user's emotional state into consideration.

[0589] A "user" is an individual or group that uses the system and is the entity that receives selections and suggestions for relevant data based on the information it inputs.

[0590] "Data" refers to numerical and textual information collected and analyzed based on user input, and serves as the basis for policy proposals.

[0591] "Emotion analysis methods" refer to technologies that measure a user's emotional state based on their input methods, gaze, voice, etc., and reflect this in data processing and suggested content.

[0592] "Visualization methods" refer to technologies for formatting selected data into an easy-to-understand format and providing it to users in the form of graphs, charts, and other visual aids.

[0593] A "policy proposal" is a solution or guideline generated based on user input and related data, and is provided to the user while taking their emotional state into consideration.

[0594] A "system" is a collection of mechanisms and devices that comprehensively process data selection, visualization, analysis, measurement and adjustment of user sentiment, and ultimately propose policies.

[0595] This system primarily consists of a user-operated terminal and a server running in the background. The terminal receives policy-making information from the user and transmits it to the server. Based on this, the server collects relevant data from internal databases and external data providers and evaluates the user's emotional state using sentiment analysis tools.

[0596] Specifically, the emotion analysis system detects emotions from, for example, user input patterns, operation speed, and data from external sensors. The server formats the collected data and visualizes it in an appropriate format using visualization tools. In this process, a more easily understandable graph or visualization method suitable for the subject is selected according to the user's emotional state.

[0597] By utilizing a generative AI model to analyze data, policy proposals are generated based on the sentiment analysis results. For example, if a user is judged to be highly stressed, specific and concise proposals are provided. In this way, the system provides the user with the most suitable policy proposals and realizes an interactive policy-making process that takes their emotional state into consideration.

[0598] The hardware used includes wearable devices such as smart glasses, and the software includes an emotion analysis engine and a visualization module for visualizing collected data. By utilizing generative AI models, it is possible to generate scenario suggestions based on the user's emotions and data.

[0599] As a concrete example, when a user is walking in an urban area, smart glasses can sense their stress level in real time and display nearby safety information and evacuation routes. Another example of a prompt message is, "Explain what should be done to detect a user's stress level in a public place and provide a sense of security."

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] Users input information related to policy formulation using a terminal. This information includes themes and objectives, and is sent from the terminal to the server. This prepares the server to begin the process of collecting data related to the theme.

[0603] Step 2:

[0604] The server collects relevant data from internal databases and external data providers based on themes and objectives received from users. In this step, generative AI models are used to analyze historical data, predict trends, and prepare useful datasets. The collected data forms the basis for the next process.

[0605] Step 3:

[0606] The server evaluates the user's emotional state using emotion analysis tools. It quantifies the emotional state by utilizing data obtained from the user's input patterns, operation speed, and other sensors. Based on the data analysis results, it determines whether the user is stressed, calm, or otherwise unsettled.

[0607] Step 4:

[0608] The server processes and visualizes the data. Sentiment analysis results are incorporated, and the optimal visualization format is selected based on the user's state. For example, a user experiencing stress is presented with a simple and easy-to-understand graph. The visualized data is then output as information for the user.

[0609] Step 5:

[0610] The server utilizes a generative AI model to generate policy proposals based on visualized data and sentiment analysis results. The complexity and detail of the proposals are adjusted according to the user's emotional state. Calm users are offered more detailed scenarios, while stressed users are offered simpler solutions.

[0611] Step 6:

[0612] The terminal presents the generated policy proposals to the user. In doing so, appropriate information is displayed in a way that reflects the user's emotional state. For example, when making urban policy proposals to the user, if a quick response is required, this includes promptly presenting specific measures and cost information.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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).

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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".

[0630] The system of the present invention is designed to support data-driven decision-making in policy formulation by local governments. This system includes user-operated terminals, a server, and communication means for linking them together.

[0631] Users input policy-making objectives and themes using a terminal. The terminal sends this information to a server, which then collects relevant data from the local government's internal databases and external data providers. The server then processes the acquired data, such as removing duplicates and converting formats, to prepare it for analysis.

[0632] The formatted data is then visualized on the server. Specifically, a generating AI automatically selects a visualization format suitable for the data's characteristics and purpose, and generates it as graphs and charts. This visualized data is then presented to the user via their device.

[0633] Next, the server performs data analysis based on the visualized data. It applies machine learning algorithms to extract patterns and trends from past data and attempts to predict policy effects. Based on the analysis results, the server generates policy proposals and sends various policy scenarios to the terminal.

[0634] Users can proceed with considering specific policies based on the advice and policy scenarios displayed on their devices. For example, when considering tourism promotion policies, users can review visualized data on human flow and trends in tourist numbers, and receive support in determining the timing and target audience for effective tourism campaigns.

[0635] In this way, this system enables users to formulate objective and efficient policies based on data. As a result, local government policies become more effective, and high-quality services can be provided to residents.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] The user operates the terminal to input information about the objectives and themes of policy formulation. Once input is complete, the terminal sends this information to the server.

[0639] Step 2:

[0640] Based on themes received from users, the server accesses internal databases and external data sources to collect relevant data. The server then checks the retrieved data for duplicates and missing data, and organizes the data.

[0641] Step 3:

[0642] The server passes the formatted data to the visualization engine, where the generating AI selects the appropriate visualization format (e.g., graph, chart). The visualized data is then generated.

[0643] Step 4:

[0644] The terminal displays the visualized data sent from the server on the user interface. The user reviews this data and visually understands its trends and characteristics.

[0645] Step 5:

[0646] The server begins data analysis based on the visualized data. Using machine learning algorithms, it extracts patterns and trends from past data and predicts future policy effects.

[0647] Step 6:

[0648] The server generates policy proposals based on the analysis results and develops multiple most effective policy scenarios.

[0649] Step 7:

[0650] The device presents the user with generated advice and policy scenarios. Based on the information provided, the user can then consider and decide on specific policy directions.

[0651] (Example 1)

[0652] 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".

[0653] In policymaking by local governments, there is a need to efficiently and accurately predict policy effects and create objective policy proposals while utilizing vast amounts of data. Conventional systems have the problem of requiring a lot of manual work in the process of data collection, formatting, and analysis, which is time-consuming and labor-intensive, and also relies heavily on subjective judgment.

[0654] 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.

[0655] In this invention, the server includes means for collecting relevant information based on the purpose or theme of a plan entered by the user; means for removing duplicates from the collected information and formatting it into a unified format; means for visually displaying the formatted information in an optimal format using a generative AI model; means for extracting regularities or trends from past data based on the visualized information; means for predicting the effectiveness of the plan based on the extracted regularities or trends; and means for generating plan proposals using the generative AI model from the prediction results of the plan's effectiveness. This makes it possible to accurately process vast amounts of data and efficiently make objective policy proposals.

[0656] A "user" refers to someone who operates the system and inputs policy objectives and themes.

[0657] "Plan objectives or themes" refer to information that indicates specific goals and policies in policymaking.

[0658] "Relevant information" refers to information including data from internal databases and external data providers that are collected based on the objectives or themes of the plan.

[0659] "Means of collection" refers to methods and processes for automatically gathering necessary information based on a given theme.

[0660] "Deduplication" refers to the process of removing duplicate data from collected information.

[0661] "Methods for formatting into a unified format" refers to methods of processing collected information by converting it into a consistent format that facilitates analysis and visualization.

[0662] A "generative AI model" refers to an artificial intelligence model that automatically generates appropriate visual formats based on large amounts of data.

[0663] "Means of visual display" refers to methods of presenting formatted information in an easy-to-understand format for users, such as graphs and charts.

[0664] "Regularity or trend" refers to a consistent pattern or trend revealed through the analysis of past data.

[0665] "Means of predicting the effectiveness of a plan" refers to methods of predicting the degree to which a plan will be successful, using data-driven regularities or trends.

[0666] "Means for generating plan proposals" refers to methods for deriving proposals that support the formulation of optimal policies based on predictions and analysis results.

[0667] Embodiments of the present invention are shown below.

[0668] The system primarily consists of servers, terminals, and communication means to link them together. Users input policy-making objectives or themes via terminals, and the server operates based on this input.

[0669] The server collects relevant information from internal databases and external data providers based on the received policy theme. It uses database management systems such as SQL queries to access the internal database and REST APIs to retrieve external data.

[0670] The collected data undergoes formatting on the server, including deduplication and standardization. This formatting is performed using the Python Pandas library. The formatted data is then prepared for analysis and visualization.

[0671] Next, the formatted data is presented to the user in the most optimal visual format using a generative AI model. Python's Matplotlib and Seaborn libraries are used for visualization, automatically generating graphs and charts tailored to the nature and purpose of the data.

[0672] Furthermore, the server analyzes historical data from the visualized data to extract patterns and trends. This analysis utilizes the Scikit-learn library, particularly through regression analysis and clustering to reveal data patterns.

[0673] Based on the analysis results, the server utilizes a generative AI model to automatically generate various policy proposals. In this process, the generated proposals are presented as multiple different scenarios and displayed to the user on their device.

[0674] For example, in a case focused on promoting tourism, a user could input a prompt such as, "Based on tourist data from the past five years and current traffic data, please suggest the optimal timing and target customer base for a tourism campaign within the next six months." Based on this prompt, the AI ​​model would perform appropriate data analysis and generate specific advice. This would then enable the user to develop data-driven, effective policies.

[0675] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0676] Step 1:

[0677] The user enters the policy objective or theme into the terminal. This input information is sent to the server as basic data for the server to search for relevant information. An example is entering the theme "How to promote regional economic revitalization" as a prompt. The entered theme serves as the starting point for processing on the server.

[0678] Step 2:

[0679] The server collects relevant information from local government internal databases and external data providers based on the received theme. This collection process uses SQL queries to extract data from databases and REST APIs to retrieve information from online data. The input is the theme, and the output is the collected dataset.

[0680] Step 3:

[0681] The server performs deduplication and formatting on the collected data. Specifically, it uses the Python Pandas library to eliminate duplicates within the dataset and standardize the format. This process results in structured and analyzable data.

[0682] Step 4:

[0683] The server generates formatted data and visualizes it using an AI model. It uses specific algorithms and libraries (such as Matplotlib and Seaborn) to generate visual representations tailored to the data's characteristics. The input is formatted data, and the output is visualized graphs and charts.

[0684] Step 5:

[0685] The server analyzes the visualized data and applies machine learning to reveal patterns and trends. Using the Scikit-learn library, it performs regression analysis, clustering, and other operations to extract regularities from past data. The input is the visualized data, and the output is the analyzed trends and patterns.

[0686] Step 6:

[0687] Based on the analysis results obtained, the server generates policy proposals using a generative AI model. The generated proposals are presented to the user as multiple policy scenarios. The input is the analysis results, and the output is a set of policy proposal scenarios.

[0688] Step 7:

[0689] The terminal displays policy proposals sent from the server to the user. The user can then use this to develop specific policies. For example, they might receive detailed advice on the timing and target audience of a tourism campaign. The input is the policy proposal, and the output is the specific advice the user sees.

[0690] (Application Example 1)

[0691] 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".

[0692] While data-driven decision-making is crucial in general policymaking and commercial activities, efficiently collecting, formatting, and analyzing relevant data, and then generating concrete proposals based on that data, remains a challenging task. Especially in situations requiring real-time analysis of real-world activity trends and behavioral patterns, and demanding immediate and optimal decision-making, existing systems may not be able to provide rapid and effective solutions.

[0693] 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.

[0694] In this invention, the server includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, means for analyzing the visualized data and generating policy advice, and means for analyzing trends and behavioral patterns of real-world activities and optimizing decision-making. This enables the user to make objective and efficient data-driven decisions in real time.

[0695] A "user" is someone who uses a system to input information and receives data to support decision-making.

[0696] "Information" refers to the purposes and themes related to policy-making and commercial activities that users input.

[0697] "Data" refers to a collection of numerical values, records, and other information related to the information being collected.

[0698] "Selection method" refers to the process of identifying and extracting necessary data related to the information entered by the user.

[0699] "Formatting" refers to the process of removing duplicates and converting the format of collected data to make it suitable for analysis and visualization.

[0700] "Methods of visualization" refer to the process of visually representing formatted data in the form of graphs, charts, and other visual media.

[0701] "Methods of analysis" refer to the process of extracting patterns and trends using machine learning algorithms and statistical methods with visualized data.

[0702] "Means of generating advice" refers to the process of creating specific improvement proposals for policies and commercial activities based on analysis results.

[0703] "Trends and behavioral patterns in real-world activities" refers to information about changes and trends in the real world related to commercial activities and social movements.

[0704] "Methods for optimizing decision-making" refer to the process of identifying and proposing the most advantageous option for the user using insights gained from analysis results.

[0705] This system begins with the user inputting the objectives and themes of policy planning or commercial activities using a terminal. The terminal sends this user input information to a server. Based on the information entered by the user, the server collects relevant data from internal and external databases. The data undergoes deduplicating and format conversion on the server side, and the formatted data is further processed into a format suitable for analysis.

[0706] Next, the server uses generation AI to automatically select a visualization format suitable for the data's characteristics and purpose, based on the formatted data, and generates it as graphs or charts. This visualized data is then presented to the user via their device.

[0707] Next, the server uses the visualized data to perform data analysis using machine learning algorithms and statistical methods. This analysis extracts past patterns and trends. Based on these results, the server generates specific advice regarding policies and commercial activities and proposes options for countermeasures.

[0708] In this system, specific hardware includes user terminals (PCs, smartphones, tablets, etc.), server computers, and APIs for data collection. Software includes scripting languages ​​for data collection and formatting (e.g., Python), libraries for data visualization (e.g., Matplotlib, Seaborn), and machine learning frameworks (e.g., Scikit-learn, TensorFlow).

[0709] For example, a retail store might use this system to determine the timing of its next sale. The user inputs their marketing theme on a terminal, and the server analyzes past sales data to suggest the optimal promotion period.

[0710] An example of a prompt message is: "Analyze sales data from the past year, predict sales trends for the next three months, and generate suggested scenarios."

[0711] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0712] Step 1:

[0713] Users input the objectives and themes of policy planning and commercial activities using a terminal. This input information is transmitted to the server via the terminal. The input includes text information and numerical data. The output is the input information transferred to the server.

[0714] Step 2:

[0715] The server collects relevant data from internal databases and external data providers based on the input information received from the user. The input is the user's input information, and the output is a collection of relevant data. This step involves accessing external databases via APIs.

[0716] Step 3:

[0717] The server formats the collected data, specifically performing duplicate removal and format conversion. The input is a collection of related data, and the output is the formatted data. The formatting process includes data cleaning using a Python script.

[0718] Step 4:

[0719] The server uses a generative AI to select the optimal visualization format for the formatted data. The input is formatted data, and the output is in the form of graphs or charts. The visualization is generated using Python's Matplotlib or Seaborn.

[0720] Step 5:

[0721] The server analyzes the visualized data. At this stage, machine learning algorithms are used to extract patterns and trends from historical data. The input is the visualized data, and the output is a numerical model or graph as a result of the analysis. Model training and prediction are performed using Scikit-learn or TensorFlow.

[0722] Step 6:

[0723] The server generates advice on policies and commercial activities based on the analysis results. The input is the analysis results, and the output is the proposed policy and activity scenarios. This includes a natural language generation process using a generative AI model.

[0724] Step 7:

[0725] The terminal displays advice and suggested scenarios sent from the server, enabling the user to make optimal decisions. The input is the suggested scenarios from the server, and the output is the information displayed on the terminal's screen. This information is displayed via a GUI on the terminal.

[0726] 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.

[0727] This invention is a system that supports policy-making by local governments, and by combining it with an emotion engine, it provides data-driven policy proposals that take into account the user's emotions. The system consists of a terminal operated by the user, a server that operates in the background, and communication means that connect them.

[0728] The user inputs the objectives and themes of policy formulation through a terminal. The terminal sends this information to a server, which then collects relevant data from its internal database and external data providers. The server uses an emotion engine to evaluate the user's emotions based on their input patterns and operation speed. For example, if the input is smooth, the user is likely to be judged as calm.

[0729] The server formats the collected data, selects an appropriate visualization format, and visualizes the data. The visualization format chosen here also takes user emotions into consideration, presenting the data in a way that suits the user's state. For example, if a user is feeling stressed, a simple and easy-to-understand graph might be selected.

[0730] Based on the visualized data, the server performs data analysis. The emotion engine evaluates the user's emotional state, and based on the results, the server generates policy recommendations. If the user is judged to be calm, it presents more complex scenarios; if the user is anxious, it proposes simpler solutions, and so on.

[0731] The device presents the user with generated advice and policy scenarios. The content of the presentation reflects the user's emotions, allowing the user to receive suggestions in a way that suits their feelings. For example, when dealing with data on transportation policy, if the user appears to be seeking a quick solution, the device will concisely provide relevant information such as specific transportation improvement measures and cost-effectiveness.

[0732] In this way, this system enables users to formulate data-driven policies while taking emotions into consideration, thereby supporting more appropriate and effective decision-making.

[0733] The following describes the processing flow.

[0734] Step 1:

[0735] The user inputs the objectives and themes of policy formulation through their device. The device then sends this information to the server.

[0736] Step 2:

[0737] The server collects relevant data from internal and external databases based on the theme received from the user. The server verifies the integrity of the data and performs any necessary formatting.

[0738] Step 3:

[0739] The server uses an emotion engine to evaluate the user's emotional state by analyzing the user's input patterns and operation speed. For example, if the user is typing hastily, the server infers that the user is feeling anxious.

[0740] Step 4:

[0741] The server selects an appropriate graph format to visualize the formatted data. It also makes adjustments based on the user's emotional state, prioritizing formats that are easy to understand.

[0742] Step 5:

[0743] The terminal displays the visualized data sent from the server through a user interface. The user visually reviews this data to understand trends and patterns.

[0744] Step 6:

[0745] The server performs further detailed data analysis based on the visualized data. The generated policy recommendations are optimized to match the user's sentiment.

[0746] Step 7:

[0747] The terminal presents the user with advice and multiple policy scenarios generated by the server. For example, if the user is feeling stressed, simple and direct suggestions will be offered.

[0748] Step 8:

[0749] Users consider and decide on policy proposals based on the advice provided. This allows for effective and appropriate policy-making that takes emotions into account.

[0750] (Example 2)

[0751] 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".

[0752] In policymaking, data analysis and proposals are often made without considering users' emotions and psychological states, which has posed challenges to effective policy decision-making. Proposals that ignore the uncertainty and stress that users experience lack feasibility and credibility, making it difficult to arrive at optimal policies.

[0753] 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.

[0754] In this invention, the server includes means for collecting relevant data based on information input by the user, means for performing an emotion evaluation and analyzing the user's psychological state, and means for formatting the selected data and visualizing it in an optimal format according to the user's emotions. This makes it possible to propose effective and practical policies that take into account the user's emotional state.

[0755] A "user" refers to a person who uses the system to input information for policy formulation and receive suggestions.

[0756] "Means of data collection" refers to the process of obtaining relevant information from internal or external sources based on user input.

[0757] "Methods for performing emotional evaluation" refers to technologies that analyze the user's input speed and patterns to evaluate the user's psychological state.

[0758] "Psychological state" refers to the user's mental state, including their emotions, motivation, and stress levels, and is a factor considered when analyzing data and making recommendations.

[0759] "Methods for formatting data" refers to the process of converting collected information into a format that is easy to analyze.

[0760] "Means of visualization" refers to methods for visually representing formatted data and presenting it in an easily understandable way to the user.

[0761] "Means of generating policy advice" refers to the process of creating proposals and advice for policy formulation based on analyzed data.

[0762] The embodiment of the invention consists of a system that enables data-driven proposals that take user sentiment into account in policymaking. This system includes a user-operated terminal, a server that processes data, and communication means that connect them.

[0763] First, the user operates a terminal to input the objectives and themes of the policy-making process. The terminal used here is a typical computer or digital device that receives input from the user and transmits that information to a server.

[0764] The server receives user input and then collects data based on it. This collection process involves accessing internal databases and external information providers to retrieve relevant data. A common data management system is used for the internal database, while API-based communication is used to retrieve external information. To efficiently process and analyze the collected data, the server has programming languages ​​such as Python and Java installed.

[0765] Next, an emotion engine is installed on the server to evaluate emotions based on data such as user input speed and patterns. This evaluation uses analysis methods that leverage natural language processing technology, with the Python TextBlob library being particularly applicable.

[0766] Furthermore, the server is responsible for formatting the collected data and visualizing it in a format appropriate to the user's emotional state. The Pandas library is used for data formatting, and the Matplotlib library is used for visualization. For example, by simplifying the data, bar graphs or pie charts are provided to users who are experiencing stress.

[0767] Finally, based on the visualized data, the server performs analysis and generates policy proposals. The SciPy library is used for the analysis. By utilizing a generative AI model to create a document about the policy proposals and providing prompts such as "Please describe in detail specific proposals for easing local traffic congestion," the system presents the user with appropriate policy scenarios.

[0768] This system allows users to receive emotion-sensitive data analysis and policy recommendations, enabling more appropriate and actionable policy-making.

[0769] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0770] Step 1:

[0771] Users input policy-making objectives and themes using a terminal. This input is in text format and is done through an input interface built into the terminal. The terminal converts the input information into structured data and sends it to the server using a secure communication protocol.

[0772] Step 2:

[0773] The server analyzes the data received from the terminal and collects additional data from relevant external and internal sources. This collection process is carried out through external information retrieval via APIs and internal database queries. Since the collected data may be in different formats, the server unifies it and converts it into a format that is easy to analyze.

[0774] Step 3:

[0775] The server uses user text input and collected data to evaluate the user's emotional state using an emotion engine. Patterns such as input speed, selected words, and sentence structure are analyzed. The emotion engine uses natural language processing techniques to identify the user's emotions (e.g., calm, stressed, anxious) and outputs the evaluation results as a data structure.

[0776] Step 4:

[0777] The server selects an appropriate data visualization format based on the sentiment assessment results and formats the collected data. A data analysis library is used for data formatting, and a graphing library is used for visualization. If a user is assessed as experiencing stress, a simple, easy-to-understand graph format is selected. The formatted data is output as an image file or interactive graph.

[0778] Step 5:

[0779] The server analyzes standardized and formatted data and uses a generative AI model to create policy proposals. Statistical analysis libraries are utilized for data analysis, and the generated proposals are output in the form of detailed policy documents. The prompt, "Please describe in detail specific proposals for mitigating local traffic congestion," is used, and the AI ​​model generates proposals based on this.

[0780] Step 6:

[0781] The terminal displays visualization data and policy proposals received from the server to the user. The display is in the form of interactive dashboards and reports, allowing the user to consider more appropriate policy formulation based on the presented information.

[0782] (Application Example 2)

[0783] 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".

[0784] In modern society, local governments are required to make decisions that take into account the feelings and circumstances of residents when choosing from a variety of policies. However, conventional policy-making systems are based on quantitative data, and there is a challenge in that they have difficulty adequately considering the emotional state of users. Therefore, there is a need to develop a system that can make flexible policy proposals according to the situation.

[0785] 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.

[0786] In this invention, the server includes means for selecting relevant data based on information input by the user, means for formatting and visualizing the selected data, means for analyzing the visualized data and generating policy proposals, means for sentiment analysis to measure the user's emotional state, and means for adjusting the data visualization format and proposal content based on the user's emotional state. This enables appropriate data visualization and policy proposals while taking the user's emotional state into consideration.

[0787] A "user" is an individual or group that uses the system and is the entity that receives selections and suggestions for relevant data based on the information it inputs.

[0788] "Data" refers to numerical and textual information collected and analyzed based on user input, and serves as the basis for policy proposals.

[0789] "Emotion analysis methods" refer to technologies that measure a user's emotional state based on their input methods, gaze, voice, etc., and reflect this in data processing and suggested content.

[0790] "Visualization methods" refer to technologies for formatting selected data into an easy-to-understand format and providing it to users in the form of graphs, charts, and other visual aids.

[0791] A "policy proposal" is a solution or guideline generated based on user input and related data, and is provided to the user while taking their emotional state into consideration.

[0792] A "system" is a collection of mechanisms and devices that comprehensively process data selection, visualization, analysis, measurement and adjustment of user sentiment, and ultimately propose policies.

[0793] This system primarily consists of a user-operated terminal and a server running in the background. The terminal receives policy-making information from the user and transmits it to the server. Based on this, the server collects relevant data from internal databases and external data providers and evaluates the user's emotional state using sentiment analysis tools.

[0794] Specifically, the emotion analysis system detects emotions from, for example, user input patterns, operation speed, and data from external sensors. The server formats the collected data and visualizes it in an appropriate format using visualization tools. In this process, a more easily understandable graph or visualization method suitable for the subject is selected according to the user's emotional state.

[0795] By utilizing a generative AI model to analyze data, policy proposals are generated based on the sentiment analysis results. For example, if a user is judged to be highly stressed, specific and concise proposals are provided. In this way, the system provides the user with the most suitable policy proposals and realizes an interactive policy-making process that takes their emotional state into consideration.

[0796] The hardware used includes wearable devices such as smart glasses, and the software includes an emotion analysis engine and a visualization module for visualizing collected data. By utilizing generative AI models, it is possible to generate scenario suggestions based on the user's emotions and data.

[0797] As a concrete example, when a user is walking in an urban area, smart glasses can sense their stress level in real time and display nearby safety information and evacuation routes. Another example of a prompt message is, "Explain what should be done to detect a user's stress level in a public place and provide a sense of security."

[0798] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0799] Step 1:

[0800] Users input information related to policy formulation using a terminal. This information includes themes and objectives, and is sent from the terminal to the server. This prepares the server to begin the process of collecting data related to the theme.

[0801] Step 2:

[0802] The server collects relevant data from internal databases and external data providers based on themes and objectives received from users. In this step, generative AI models are used to analyze historical data, predict trends, and prepare useful datasets. The collected data forms the basis for the next process.

[0803] Step 3:

[0804] The server evaluates the user's emotional state using emotion analysis tools. It quantifies the emotional state by utilizing data obtained from the user's input patterns, operation speed, and other sensors. Based on the data analysis results, it determines whether the user is stressed, calm, or otherwise unsettled.

[0805] Step 4:

[0806] The server processes and visualizes the data. Sentiment analysis results are incorporated, and the optimal visualization format is selected based on the user's state. For example, a user experiencing stress is presented with a simple and easy-to-understand graph. The visualized data is then output as information for the user.

[0807] Step 5:

[0808] The server utilizes a generative AI model to generate policy proposals based on visualized data and sentiment analysis results. The complexity and detail of the proposals are adjusted according to the user's emotional state. Calm users are offered more detailed scenarios, while stressed users are offered simpler solutions.

[0809] Step 6:

[0810] The terminal presents the generated policy proposals to the user. In doing so, appropriate information is displayed in a way that reflects the user's emotional state. For example, when making urban policy proposals to the user, if a quick response is required, this includes promptly presenting specific measures and cost information.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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."

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] The following is further disclosed regarding the embodiments described above.

[0833] (Claim 1)

[0834] A means of selecting relevant data based on information entered by the user,

[0835] A means of formatting and visualizing the selected data,

[0836] A means of analyzing visualized data and generating policy advice,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, comprising means for selecting the optimal visualization format according to a theme specified by the user.

[0840] (Claim 3)

[0841] The system according to claim 1, comprising means for providing multiple policy scenarios proposed based on the analysis results.

[0842] "Example 1"

[0843] (Claim 1)

[0844] Means for collecting relevant information based on the purpose or theme of the plan entered by the user,

[0845] A means of removing duplicates from the collected information and formatting it into a unified format,

[0846] A means of visually displaying formatted information in the optimal format using a generation AI model,

[0847] A means of extracting regularities or trends from past data based on visualized information,

[0848] A means of predicting the effectiveness of the plan based on the extracted regularities or trends,

[0849] A means of generating plan proposals using a generation AI model based on prediction results of the plan's effectiveness,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, comprising means for automatically selecting a visualization format based on a specified theme.

[0853] (Claim 3)

[0854] The system according to claim 1, comprising means for providing multiple planning scenarios based on extracted regularities or proposed plans.

[0855] "Application Example 1"

[0856] (Claim 1)

[0857] A means of selecting relevant data based on information entered by the user,

[0858] A means of formatting and visualizing the selected data,

[0859] A means of analyzing visualized data and generating policy advice,

[0860] A means of analyzing trends and behavioral patterns in real-world activities to optimize decision-making,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, comprising means for selecting the optimal visualization format according to a theme specified by the user.

[0864] (Claim 3)

[0865] The system according to claim 1, comprising means for providing multiple policy scenarios proposed based on the analysis results.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] Means for collecting relevant data based on information entered by the user,

[0869] A means of performing emotional evaluations and analyzing the user's psychological state,

[0870] A method for formatting selected data and visualizing it in the most optimal format according to the user's emotions,

[0871] A means of analyzing visualized data and generating policy advice based on the generated data,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, comprising means for evaluating emotions based on the user's input speed and patterns, and selecting a visualization format that matches those emotions.

[0875] (Claim 3)

[0876] The system according to claim 1, comprising means for adjusting and providing multiple policy scenarios to be generated based on the results of an emotional evaluation, according to the user's psychological state.

[0877] "Application example 2 when combining with an emotional engine"

[0878] (Claim 1)

[0879] A means of selecting relevant data based on information entered by the user,

[0880] A means of formatting and visualizing the selected data,

[0881] A means of analyzing visualized data and generating policy proposals,

[0882] A means of analyzing the emotional state of a user,

[0883] A means of adjusting the data visualization format and suggested content based on the user's emotional state,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, comprising means for selecting the optimal visualization format according to a subject specified by the user, and means for monitoring the user's emotional state in real time.

[0887] (Claim 3)

[0888] The system according to claim 1, comprising means for providing multiple policy scenarios proposed based on analysis results, taking into account the user's emotional state. [Explanation of Symbols]

[0889] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of selecting relevant data based on information entered by the user, A means of formatting and visualizing the selected data, A means of analyzing visualized data and generating policy advice, A system that includes this.

2. The system according to claim 1, comprising means for selecting the optimal visualization format according to a theme specified by the user.

3. The system according to claim 1, comprising means for providing multiple policy scenarios proposed based on the analysis results.

Images