System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting human flow data; means for cleansing and normalizing the collected data; means for performing natural language analysis and analyzing a user's request; means for performing data analysis and graph generation using a generated prompt; means for generating a measure proposal based on an analysis result; and means for providing the user with the analysis result and the measure proposal obtained by the respective means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Statistical services that utilize nationwide people flow data require special know-how for data analysis, and customers often feel they are not confident in their ability to use the tools, which leads to no orders. While there is a demand for tools that allow anyone to easily perform data analysis and plan measures based on the results, the lack of such tools is a real obstacle. Another problem is that existing data analysis tools are not intuitive and are difficult for general users without specialized knowledge to operate. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system including means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for performing data analysis and graph generation using the generated prompts, means for generating policy proposals based on the analysis results, and means for providing users with the analysis results and policy proposals obtained by each of the above means.

[0006] This system allows users without specialized know-how to easily analyze data and develop measures. Furthermore, the interactive interface allows users to operate the system intuitively and obtain analysis results tailored to their needs. This lowers the barrier to data utilization for users and supports strategic decision-making based on data.

[0007] "People flow data" is data that includes information on people's movements and stays.

[0008] "Cleansing" is the process of detecting missing or outliers in data and completing or removing them.

[0009] "Normalization" is the process of standardizing the format and units of data and preparing it in a form suitable for analysis.

[0010] "Natural language analysis" is a technology that uses computers to understand and analyze the natural language that people use on a daily basis.

[0011] A "prompt" is a specific instruction that the generative AI gives when analyzing data or generating graphs.

[0012] "Policy proposals" involve presenting specific action plans and improvement proposals based on the results of data analysis.

[0013] An "interactive interface" is an interface that allows a user to interact with a system through inputted text, selection boxes, buttons, etc. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0028] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[0036] Program processing and explanation

[0037] Data collection and preprocessing

[0038] Server: When collecting people flow data, it uses APIs from multiple data sources to obtain data. Specifically, it obtains people flow information for a specified date, time, and area, and stores it in a database. Next, it cleanses and normalizes the data. In other words, it detects missing values ​​and outliers, and properly complements or removes them, and standardizes the data format and units. This prepares the data in a form suitable for analysis.

[0039] User Interface Generation

[0040] Terminal: A display of a web application that can be accessed directly by the user. It provides UI components such as text input fields, selection boxes, and buttons, and is designed to allow users to easily input requests. This interface supports intuitive user interaction.

[0041] Natural Language Analysis and Prompt Generation

[0042] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0043] Terminal: Sends text data entered by the user to the server.

[0044] Server: Analyzes the received text data using a natural language processing (NLP) model, understanding the user's intent and generating appropriate prompts that identify specific analysis methods and required datasets.

[0045] Data analysis and graph generation

[0046] Server: Based on the prompts, generative AI models are used to analyze the data, for example, using time series analysis and clustering to measure changes in foot traffic before and after the event date. The results are then transformed into dynamic graphs and charts.

[0047] Terminal: The analysis results and graphs received from the server are displayed in an easy-to-understand manner to the user. For example, this includes line graphs showing increases and decreases in foot traffic, and heat maps showing the effectiveness of attracting customers.

[0048] Measure proposals

[0049] Server: Based on the analysis results, specific measures for the next event are generated. For example, recommendations include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. Measure suggestions are written in natural language and presented to users in a format that they can intuitively understand.

[0050] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[0051] Specific examples

[0052] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. In this case, the user obtains information through the following operations:

[0053] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0054] 2. Terminal: Sends the input request to the server.

[0055] 3. Server: Performs natural language analysis, identifies appropriate data and analytical methods, and generates prompts.

[0056] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[0057] 5. Terminal: Displays the analysis results and action proposals to the user.

[0058] 6. User: Use the information provided to plan your next event.

[0059] In this way, this system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective implementation of measures.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends requests to API endpoints and receives data in JSON format. Temporarily stores the received data.

[0063] Step 2:

[0064] Server: Cleanses the collected data. Specifically, it complements missing values, removes outliers, and corrects values. For example, it detects null values ​​and extremely outlying values ​​and replaces them with appropriate values. It also performs normalization to unify data formats and units.

[0065] Step 3:

[0066] Server: Stores the cleansed data in a database so that it can be efficiently accessed for subsequent analysis steps.

[0067] Step 4:

[0068] Terminal: Provides web applications that present an intuitive interface to users, including UI components such as text input fields, selection boxes, and buttons.

[0069] Step 5:

[0070] User: Enters a specific request into the interface. For example, the user enters a request such as, "I would like you to analyze the changes in the flow of people on the day of last year's tourist event and provide suggestions for planning the next one" into the text input field.

[0071] Step 6:

[0072] Terminal: Sends the request entered by the user to the server. The text data is included in the request payload and sent to the server.

[0073] Step 7:

[0074] Server: Analyzes the user request using a natural language processing (NLP) model, tokenizes the request text, understands the user's intent, generates appropriate prompts, and identifies the required dataset and analysis techniques.

[0075] Step 8:

[0076] Server: Using the generated prompts, the server begins analyzing the people flow data. Specifically, it performs time series analysis to detect changes in people flow before and after the event. It also uses clustering techniques to classify people flow patterns.

[0077] Step 9:

[0078] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[0079] Step 10:

[0080] Terminal: Displays the analysis results and graphs received from the server to the user, presenting the results in a format that is easy for the user to understand and allowing them to interpret the data visually.

[0081] Step 11:

[0082] Server: Based on the analysis results, the server generates specific action plans for the next event. These plans include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The generated proposals are written in natural language.

[0083] Step 12:

[0084] Terminal: The generated policy proposals are displayed to the user, who can then review the proposals and use them as a reference for formulating an implementation plan.

[0085] Step 13:

[0086] Users: Give feedback on the information and suggestions provided by filling out and submitting a form in the interface.

[0087] Step 14:

[0088] Server: Receives user feedback and reflects it in improvements to the AI ​​model and UI, thereby continuously improving the accuracy and usability of the system.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] With conventional technology, there was no consistent system that could efficiently collect nationwide people flow data, cleanse and normalize it, and then perform specific data analysis and policy proposals according to the user's intentions.Therefore, there is a need for a system that can perform everything from data collection to analysis and policy proposals all at once, through an interface that even non-experts can use easily.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating prompts using a generative AI model, and means for integrating the processing results of each means and providing an interactive interface that can be intuitively operated by users. This enables users without specialized knowledge to easily perform tasks from data collection to analysis and policy proposals through intuitive operations.

[0094] "People flow data" is information about the movements and gatherings of people in specific areas and at specific times.

[0095] "Cleansing" is the process of detecting missing or outliers in data and then filling or removing them appropriately.

[0096] "Normalization" is the process of standardizing and making consistent the format and units of data.

[0097] "Natural language analysis" is a technology that analyzes text written in human language into a form that can be understood by machines, and extracts intent and meaning.

[0098] "Prompt" refers to specific instructions or questions for data analysis or graph generation.

[0099] An "interactive interface" is a user interface that allows a user to intuitively interact with a system, and typically includes UI components such as text input fields, selection boxes, and buttons.

[0100] A "generative AI model" is an algorithm or computational model that leverages artificial intelligence techniques to automate specific tasks (e.g., natural language processing, data analysis).

[0101] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[0102] Data collection and preprocessing

[0103] Server: When collecting people flow data, APIs from multiple data sources are used to obtain data. Specifically, external data sources such as Google Maps API and social media APIs are used. The collected data is stored in a database. Next, during the data cleansing process, missing values ​​and outliers are detected and appropriate processing is performed, such as filling in the average value. The data is then normalized to unify the format and units.

[0104] User Interface Generation

[0105] Terminal: A web application is provided that can be accessed directly by the user. This application works with data provided by the server and displays UI components such as text input fields, selection boxes, and buttons. It is designed to be intuitive for the user, allowing them to easily input requests.

[0106] Natural Language Analysis and Prompt Generation

[0107] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0108] Terminal: Sends text data entered by the user to the server.

[0109] Server: Analyzes the received text data using a natural language processing model. Specifically, it uses generative AI models such as BERT and GPT-3 to understand the user's intent and generate appropriate prompts. The prompts are instructions that specify the specific analysis method and required dataset.

[0110] Data analysis and graph generation

[0111] Server: Based on generated prompts, data for a specified time period and region is filtered from the database. Generative AI models are then used to analyze the data. For example, time series analysis is used to measure changes in foot traffic before and after an event, and clustering techniques are used to find specific patterns and trends. The results of the analysis are then converted into dynamic graphs and charts using tools such as Python's Matplotlib and D3.js.

[0112] Measure proposals

[0113] Server: Based on the results of the data analysis, the server generates specific measures for the next event. For example, it proposes measures such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. These measures are written in natural language and presented to users in a format that they can intuitively understand.

[0114] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[0115] Specific examples

[0116] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. The information can be obtained through the following operations:

[0117] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0118] 2. Terminal: Sends the input request to the server.

[0119] 3. Server: Performs natural language analysis, identifies the required data and analysis methods, and generates prompts.

[0120] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[0121] 5. Terminal: Displays the analysis results and action proposals to the user.

[0122] 6. User: Use the information provided to plan your next event.

[0123] This system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective measures.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] Data collection

[0127] Server: Uses APIs to collect people flow data for specified dates, times, and regions from multiple data sources. Specifically, it uses Google Maps API and social media APIs to obtain real-time people flow data.

[0128] Input: Specified date and time, region, and API connection information.

[0129] Data processing and calculation: Data from multiple sources is integrated, converted into a single format, and stored in a database.

[0130] Output: Integrated people flow data.

[0131] Step 2:

[0132] Data Cleansing and Normalization

[0133] Server: Cleanses the collected data. Specifically, it detects and fills in missing values ​​and removes outliers. For example, if there are many missing values, it fills in the average value, and if there are clearly abnormal values, it removes them. After that, it standardizes the data format and units.

[0134] Input: Integrated people flow data.

[0135] Data processing and calculation: Completion of missing values, removal of outliers, and standardization of data format and units are carried out.

[0136] Output: Cleansed and normalized people flow data.

[0137] Step 3:

[0138] User Interface Generation

[0139] Terminal: Provides a web application that users can access, including UI components such as text inputs, select boxes, and buttons that allow users to intuitively input requests.

[0140] Input: UI design information, cleansed and normalized data.

[0141] Data processing and computation: Web page and UI component generation.

[0142] Output: A web application where users can enter their requests.

[0143] Step 4:

[0144] Receiving requests from users

[0145] User: Enter a request such as, "I would like you to analyze the changes in the flow of people on the days when tourist events were held last year and make suggestions for planning the next one."

[0146] Input: Text request.

[0147] Data processing and calculation: Sending the text request content to the server.

[0148] Output: The request data.

[0149] Step 5:

[0150] Natural Language Analysis and Prompt Generation

[0151] Server: Analyzes the received text data using a natural language processing model to understand the user's intent. Specifically, it uses BERT or GPT-3 to extract appropriate keywords and actions. Next, it generates a prompt based on the analysis results.

[0152] Input: Request data.

[0153] Data processing and calculation: text analysis, keyword extraction, prompt generation.

[0154] Output: The generated prompt.

[0155] Step 6:

[0156] Data analysis and graph generation

[0157] Server: Filters data from the database for the specified time period and region based on generated prompts, then performs time series analysis and clustering using generative AI models, and converts the analysis results into dynamic graphs and charts using Python's Matplotlib and D3.js.

[0158] Input: Generated prompts, cleansed and normalized data.

[0159] Data processing and calculations: data filtering, time series analysis, clustering, graph generation.

[0160] Output: Graphs and charts of the analysis results.

[0161] Step 7:

[0162] Generate policy proposals

[0163] Server: Based on the analysis results, the server generates specific measures for the next event, such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposed measures are written in natural language and presented to users in a format that is easy to understand.

[0164] Input: Graphs and charts of analytical results.

[0165] Data processing and calculation: Generation of policy proposals and descriptions in natural language.

[0166] Output: Policy proposal document.

[0167] Step 8:

[0168] Display of results and action recommendations

[0169] Terminal: The analysis results and action proposals received from the server are displayed to the user, who can then use them to plan their next event.

[0170] Input: Policy proposal documents, graphs and charts of analysis results.

[0171] Data processing and calculation: Web display of results and policy proposals.

[0172] Output: Provides information to the user.

[0173] (Application example 1)

[0174] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0175] In modern society, there is a need to effectively analyze large amounts of people flow data and quickly propose strategic measures based on that data. However, conventional systems have difficulty preprocessing and analyzing data, and making specific proposals based on user requests. This makes it difficult to develop efficient advertising strategies, particularly in the advertising field. To address this issue, there is a need for a system that can consistently perform data collection, analysis, and proposals, and visualize them in an easy-to-understand manner.

[0176] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0177] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating information to optimize advertising policies based on the collected data, means for visualizing people flow data for a specified period and providing it to the user, and means for providing specific proposals based on prompt sentences using a generative AI model. This makes it possible to efficiently analyze large amounts of people flow data and optimize advertising policies and propose specific strategies.

[0178] "People flow data" is data that records information on people's movements and stays in specific areas and periods of time.

[0179] "Cleansing" refers to the process of detecting missing or outliers in data and then filling or removing them.

[0180] "Normalization" refers to the process of standardizing the format and units of data and preparing it in a form suitable for analysis.

[0181] "Natural language analysis" is a technology that analyzes text data entered by a user and understands its intent and meaning.

[0182] A "prompt" is an input that generates a specific instruction or question and analyzes data accordingly.

[0183] A "generative AI model" is a model that uses artificial intelligence technology to generate appropriate responses or results for specific inputs.

[0184] "Data analysis" is the process of analyzing collected data using statistical or computational methods.

[0185] "Graph generation" refers to the process of creating graphs or charts to visually represent analytical results.

[0186] "Policy proposal" refers to proposing specific strategies and measures to be implemented next time based on the results of data analysis.

[0187] "Visualization" refers to a method of displaying data or information visually in an easy-to-understand manner.

[0188] In this invention, three parties are involved in realizing a system for advertising optimization: a server, a terminal, and a user. How this system works will be explained in detail below.

[0189] 1. Server Role

[0190] The server is responsible for the following processes:

[0191] Collection of people flow data: People flow data for specific regions and periods is obtained through APIs and stored in a database. The use of APIs is important for collecting data from various data sources.

[0192] Data cleansing and normalization: Detecting missing or outliers from collected data, and then filling or removing them, as well as standardizing the data format and units.

[0193] Natural Language Analysis: Receives the request text from the user and analyzes it using natural language processing technology to understand the user's intent and generate appropriate prompts.

[0194] Prompt generation and data analysis: Based on the generated prompts, a generative AI model is used to perform data analysis, including time series analysis and clustering.

[0195] Graph generation and action recommendations: Convert analysis results into dynamic graphs and charts and automatically generate action recommendations.

[0196] 2. Role of the terminal

[0197] The terminal is responsible for the following processes:

[0198] Providing a user interface: Provide a web application where users can enter requests. The interface includes UI components such as text input fields, select boxes, and buttons.

[0199] Request transmission and data display: The request entered by the user is sent to the server, and the analysis results and action proposals returned by the server are displayed. Display formats include line graphs and heat maps.

[0200] 3. User Roles

[0201] The user performs the following process:

[0202] Text input: For example, a request such as "Please suggest our next advertising strategy based on the foot traffic data from last year's campaign period" is entered into the device interface.

[0203] Reviewing the results and making decisions: Review the data analysis results and action proposals provided by the server, and plan the next advertising strategy based on them.

[0204] Hardware and software used

[0205] Hardware: User's smartphone and cloud server

[0206] Software: Python, open-source libraries (Pandas, Requests, Matplotlib), generative AI models (e.g., GPT-3)

[0207] Specific examples

[0208] When an advertising officer at a local government analyzes changes in foot traffic on the day of a specific event and plans the next advertising strategy based on that analysis, he or she uses the system in the following steps.

[0209] 1. User: Opens the smartphone app and enters a request: "Please suggest my next advertising strategy based on foot traffic data from last year's campaign period."

[0210] 2. Terminal: Sends the input request to the server.

[0211] 3. Server: Collects people flow data using APIs, cleansing and normalizing it, then performs natural language analysis to generate appropriate prompts.

[0212] 4. Server: Based on the generated prompts, a generative AI model is used to analyze the data and visualize the results, for example generating line graphs or heat maps.

[0213] 5. Server: Based on the results of the data analysis, generate proposals for the next advertising campaign and describe them in natural language.

[0214] 6. Terminal: Displays the generated analysis results and action proposals to the user.

[0215] 7. User: Plan your next advertising strategy based on the information displayed.

[0216] Prompt Sentence Examples

[0217] "I would like you to propose our next advertising strategy based on the foot traffic data from last year's campaign period."

[0218] In this way, by using the system of the present invention, advertising personnel can receive effective data analysis and strategic measures proposals.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The server uses API to collect people flow data for a specific area and period. The input is a request specifying the area and period, and the output is people flow data based on the specified conditions. The collected data is stored in a database.

[0222] Step 2:

[0223] The server cleanses and normalizes the collected people flow data. The input is the collected people flow data, and the output is the cleansed and normalized data. Specifically, it detects and completes missing and outlier values, and standardizes data formats and units.

[0224] Step 3:

[0225] The server receives the request text entered by the user on the terminal and performs natural language analysis. The input is the request text entered by the user, and the output is the analyzed user's intent. Specifically, NLP technology is used to understand the meaning and intent of the request text.

[0226] Step 4:

[0227] The server generates a prompt based on the natural language analysis results. The input is the analysis results including the user's intent, and the output is the generated prompt. The prompt is a specific instruction for data analysis.

[0228] Step 5:

[0229] The server performs data analysis based on the generated prompts. The input is the cleansed and normalized people flow data and the prompts, and the output is the analysis results. Specifically, it uses techniques such as time series analysis and clustering to analyze changes and patterns in people flow.

[0230] Step 6:

[0231] The server generates graphs and charts based on the results of the data analysis. The input is the data analysis results, and the output is visualized graphs and charts. Specifically, it uses tools such as Matplotlib to create line graphs, heat maps, and so on.

[0232] Step 7:

[0233] The server generates policy proposals based on the analysis results. The input is the data analysis results, including visualized graphs and charts, and the output is policy proposals. Specifically, a generative AI model is used to generate specific policy proposals in natural language.

[0234] Step 8:

[0235] The terminal displays the analysis results and proposed measures received from the server to the user. The input is the analysis results and proposed measures from the server, and the output is a visual display to the user. The user plans their next advertising strategy based on the displayed information.

[0236] As a concrete example, if a user inputs, "Please suggest my next advertising campaign based on the foot traffic data from last year's campaign period," the server will analyze this request, collect and analyze foot traffic data for the specified period, generate specific advertising campaign proposals based on that data, and provide them to the user via their device.

[0237] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0238] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[0239] Program processing and explanation

[0240] Data collection and preprocessing

[0241] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends API requests and temporarily stores the retrieved data in JSON format. Next, cleanses and normalizes the data, properly handles missing values ​​and outliers, and standardizes the data format and units.

[0242] User Interface Generation

[0243] Terminal: Displays a web application that provides an intuitive interface to the user, including UI components such as text input fields, selection boxes, and buttons, designed to allow the user to easily input requests.

[0244] Natural Language Analysis and Emotion Recognition

[0245] User: For example, enter a request such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one" in the text input field.

[0246] Terminal: Sends user input to the server.

[0247] Server: Analyzes the received text data using a natural language processing (NLP) model to understand the user's intent. At the same time, it uses an emotion engine to analyze the emotions from the user's input. Based on the results of this emotion analysis, it generates more appropriate prompts.

[0248] Data analysis and graph generation

[0249] Server: Performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in pedestrian flow before and after the event. It creates dynamic graphs and charts based on the generated analysis results.

[0250] Terminal: Visually displays the analysis results and graphs received from the server, including line graphs showing increases and decreases in foot traffic and heat maps visualizing the effectiveness of attracting customers.

[0251] Policy proposals and emotional responses

[0252] Server: Generates specific action proposals based on the analysis results. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. They are customized based on the user's emotional state. For example, if the user shows signs of anxiety, they will receive more reassuring proposals.

[0253] Device: Displays customized action proposals to users, who can then review the proposals and make decisions, such as planning their next event.

[0254] Specific examples

[0255] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day of a specific event and plan for the next event. In this case, the following operations are performed.

[0256] 1. User: Opens the web application and enters a request to "analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0257] 2. Terminal: Sends the input request to the server.

[0258] 3. Server: Performs natural language analysis to understand the intent of the user's request. In parallel, it uses an emotion engine to analyze emotions from the user's input.

[0259] 4. Server: Generates appropriate prompts and starts analyzing people flow data, cleansing and normalizing the data, and generating graphs and charts based on the analysis results.

[0260] 5. Terminal: Displays the generated analysis results and graphs to the user.

[0261] 6. Server: Generates specific action proposals based on the analysis results and adjusts the proposals according to the user's emotions.

[0262] 7. Terminal: The customized action proposal is displayed to the user, who can then accept the proposal and plan their next event.

[0263] In this way, this system easily supports data analysis and policy planning while taking into account the user's emotions, allowing users to make more effective strategic decisions.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Specifically, it sends a request to the API endpoint and obtains people flow data for the required area and period in JSON format. The obtained data is temporarily stored in a database.

[0267] Step 2:

[0268] Server: Cleanses the collected data by imputing missing values ​​and filtering or correcting outliers. For example, it detects null values ​​and inappropriate data and replaces them with appropriate values ​​using imputation algorithms. It also normalizes the data format and units to make them consistent.

[0269] Step 3:

[0270] Server: The cleansed and normalized data is restored to a database in an optimal format for fast and efficient searching and analysis.

[0271] Step 4:

[0272] Terminal: Launches a web application that displays a user interface, which includes UI components such as text input fields, selection boxes, and buttons.

[0273] Step 5:

[0274] User: In the text input field, enter "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan," and press the send button.

[0275] Step 6:

[0276] Terminal: Collects user input and sends it to the server as an HTTP request, with the payload containing text data containing the user's request.

[0277] Step 7:

[0278] Server: Analyzes the received text data using a natural language processing (NLP) model, tokenizes the text data, analyzes the meaning of the sentences, and generates prompts to understand the user's request.

[0279] Step 8:

[0280] Server: At the same time, it uses an emotion engine to analyze the emotion from the user's input. The emotion engine analyzes the context of the input text and identifies the type of emotion (happiness, surprise, anxiety, etc.).

[0281] Step 9:

[0282] Server: Taking into account the results of sentiment analysis, adjust prompts according to the user's emotions. For example, if the user expresses anxiety, add additional reassuring information.

[0283] Step 10:

[0284] Server: Based on the prompt, the server begins analyzing the people flow data. It uses time series analysis and clustering techniques to measure changes in people flow before and after the event.

[0285] Step 11:

[0286] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[0287] Step 12:

[0288] Terminal: Displays the analysis results and graphs received from the server to the user, presenting data in a visually easy-to-understand format.

[0289] Step 13:

[0290] Server: Based on the analysis results, the server generates specific action proposals for the next event. These proposals include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The server also takes into account the results of sentiment analysis and customizes the proposals.

[0291] Step 14:

[0292] Device: The generated action proposals are displayed to the user, who can review the proposals and use them as reference for planning the next event.

[0293] Step 15:

[0294] Users: Provide feedback on the information and suggestions provided. Feedback is entered and submitted via the interface.

[0295] Step 16:

[0296] Server: Receives user feedback and reflects it in improving the AI ​​model and UI, thereby improving the accuracy and usability of the system.

[0297] Example 2

[0298] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0299] Conventional data analysis systems have had difficulty efficiently collecting and analyzing people flow data and providing specific policy proposals to users. They also were unable to provide policy proposals that took user emotions into account. This resulted in a decrease in the accuracy of the analysis results and proposals users received, and insufficient support for decision-making.

[0300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0301] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for analyzing user emotions using a sentiment analysis engine, means for performing time series analysis and clustering using the generated prompts, means for generating dynamic graphs and charts based on the analysis results, means for providing the generated analysis results and diagrams to the user, means for generating policy proposals based on the analysis results and customizing the proposal content based on the user's emotions, and means for providing the policy proposals obtained by the above means to the user. This enables efficient collection and analysis of people flow data as well as specific and accurate policy proposals that take user emotions into consideration.

[0302] "People flow data" is statistical data on the movement and gathering of people in a certain area.

[0303] "Cleansing" is a process of removing noise and missing values ​​from collected data to improve the quality of the data.

[0304] "Normalization" is the process of converting data into a consistent format and units to facilitate comparison and analysis.

[0305] "Natural language analysis" is the process of analyzing text data using machine learning and artificial intelligence techniques to understand grammar and meaning.

[0306] An "emotion analysis engine" is a software component for analyzing and classifying a user's emotional state from text data.

[0307] A "prompt" is an analytical instruction or command that is generated based on user input.

[0308] "Time series analysis" is a method for analyzing fluctuations in data over time to make predictions and recognize patterns.

[0309] "Clustering" is a technique for classifying data into groups with high similarity and finding patterns and structures.

[0310] "Dynamic graphs and charts" are dynamic diagrams for displaying interactive visualizations of data.

[0311] "Policy proposals" involve presenting specific action plans and improvement measures based on the results of data analysis.

[0312] An "interactive interface" is an interface that includes input and output items that can be intuitively operated by a user.

[0313] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[0314] Data collection and preprocessing

[0315] Server: This system collects people flow data from the National Movement Statistics Data API and other external data sources. It uses the Python requests library for collection. The acquired JSON-formatted data is temporarily stored, and the Pandas library is used to cleanse and normalize the data. Missing values ​​and outliers are handled appropriately, and the data format and units are standardized.

[0316] User Interface Generation

[0317] Terminal: A web application is displayed that provides the user with an intuitive interface. This interface is built using the JavaScript React.js framework. The user can easily enter requests using text input fields, select boxes, and buttons.

[0318] Natural Language Analysis and Emotion Recognition

[0319] User: For example, enter a request in the text input field, such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0320] Terminal: User input is sent to the server in real time using AJAX requests.

[0321] Server: Analyzes the received text data using Python's natural language processing (NLP) libraries, such as NLTK and SpaCy. Extracts entities and verbs to understand the user's intent. At the same time, analyzes the sentiment of the user's input using a sentiment analysis engine, such as IBM Watson Tone Analyzer. Based on the results of the sentiment analysis, generates more appropriate prompts.

[0322] Data analysis and graph generation

[0323] Server: Based on the generated prompts, the people flow data is analyzed using Python time series analysis libraries (e.g., Prophet) and clustering algorithms (e.g., k-means). Based on the analysis results, dynamic graphs and charts are generated using libraries such as Matplotlib and Seaborn.

[0324] Policy proposals and emotional responses

[0325] Server: Based on the information obtained from the analysis, the server generates specific action proposals. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposals are also customized based on the user's emotional state. For example, if the user shows signs of anxiety, the server will make suggestions that will reassure them.

[0326] Terminal: Displays the action proposals received from the server to the user. The analysis results and action proposals are presented in a visually easy-to-understand format.

[0327] Specific examples

[0328] For example, suppose a local government official (user) wants to analyze changes in foot traffic on the day of a specific event and make plans for the next one. In this case, the user opens a web application and enters a request: "Analyze changes in foot traffic on the day of last year's tourism event and make suggestions for the next plan." The device sends this request to the server, which performs natural language analysis and sentiment analysis. The server then begins data analysis based on the generated prompts and generates the results as graphs and charts. Finally, it customizes appropriate policy proposals and provides them to the user. This allows the user to make more effective strategic decisions.

[0329] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0330] Step 1: Data collection and preprocessing

[0331] Server: Sends an HTTP request to the National Movement Statistics Data API to obtain people flow data. The input is the API request URL, and the output is JSON-formatted data. Specifically, the API request is sent using the requests library. The server temporarily stores the obtained JSON data, and then cleanses and normalizes the data using the Pandas library. Specific data processing involves imputing missing values ​​using an appropriate method, removing outliers, and standardizing data formats and units. The output is a cleansed and normalized data frame.

[0332] Step 2: Generate the user interface

[0333] Terminal: Uses the JavaScript React.js framework to generate a web application for the user. The input is the elements necessary for the user interface, and the output is a web page that the user can operate intuitively. Specific operations include creating UI components such as text input fields, selection boxes, and buttons, and arranging them on the screen. The terminal adds event listeners to receive and send user input in real time.

[0334] Step 3: Natural Language Analysis and Emotion Recognition

[0335] User: For example, a user enters a request in the text input field, such as "I want you to analyze the changes in people flow on the day of last year's tourist event and make suggestions for the next plan." The input is the user's text request, and the output is a request to send to the server.

[0336] Terminal: Sends the input text request to the server using an AJAX request. The input is the user's text data, and the output is an HTTP request.

[0337] Server: The received text data is analyzed using Python's natural language processing (NLP) libraries, NLTK and SpaCy. The input is the user's text request, and the output is the analysis results (a list of entities and verbs). Specifically, the text data is tokenized and entities and verbs are extracted. At the same time, the IBM Watson Tone Analyzer is used to analyze the user's emotions. The input is the user's text, and the output is the emotion analysis results. This allows the user's emotional state to be determined and more appropriate prompts to be generated.

[0338] Step 4: Data analysis and graph generation

[0339] Server: Based on the generated prompts, data analysis is performed using Python's time series analysis library (Prophet) and clustering algorithm (k-means). The input is a cleansed and normalized data frame, and the output is the analysis results. Specific operations include predicting trends in time series data and identifying data patterns through clustering. Based on the analysis results, dynamic graphs and charts are generated using the Matplotlib and Seaborn libraries. The output is visualized graphs and charts.

[0340] Step 5: Propose measures and respond to emotions

[0341] Server: Generates specific action proposals based on the analysis results. The inputs are the analysis results and the results of user sentiment analysis, and the output is specific action proposals. Specific operations include evaluating the data analysis results and creating proposals such as revising advertising strategies and identifying areas to attract customers. The proposals are customized according to the user's emotional state.

[0342] Terminal: Visually displays the policy proposals received from the server to the user. The input is the proposal content and graphs from the server, and the output is a screen display that the user can check. Specifically, it displays the analysis results and proposal content in an easy-to-understand manner, helping the user to plan the next action.

[0343] (Application example 2)

[0344] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0345] Conventional analysis systems based on people flow data make uniform policy proposals without considering user emotions, which means they are unable to provide appropriate proposals that address the user's psychological state or specific needs. Furthermore, collected data often contains missing values ​​and outliers, requiring appropriate data cleansing and normalization. Furthermore, there is a lack of systems that can intuitively accept user requests through a conversational interface.

[0346] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis including an emotion engine that analyzes user emotions, means for performing data analysis and graph generation using the generated prompts, and means for generating policy proposals based on the analysis results, providing the generated graphs and policy proposals to the user, and customizing the proposal content based on the user's psychological state. This enables appropriate data analysis and policy proposals according to the user's emotional state.

[0347] "People flow data" is data that shows patterns of people's movements and gatherings in specific areas and time periods.

[0348] "Data cleansing" refers to detecting missing or outliers from collected data and applying appropriate processing.

[0349] "Normalization methods" are methods for converting data with different data formats, units, etc. into a unified format.

[0350] "Natural language analysis" is a technology that analyzes text data entered by users and understands their intent and content.

[0351] The "emotion engine" is a system that analyzes emotions from the text entered by the user and grasps their psychological state.

[0352] A "prompt" is text containing a series of instructions or questions to guide user input or system action.

[0353] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning techniques to derive useful information.

[0354] "Graph generation" refers to the creation of graphs and charts to visually represent the results of data analysis.

[0355] "Policy proposals" involve proposing specific actions and strategies based on the results of the analysis.

[0356] "Customization" means tailoring what is delivered and how it is delivered to the user's specific needs and emotional state.

[0357] An "interactive interface" is an interface in which the system provides appropriate responses and suggestions based on information entered by the user.

[0358] The system of this invention analyzes user requests based on people flow data and combines it with sentiment analysis to enable more appropriate data analysis and policy proposals. Below, we will explain the details of each component of this system and how it works.

[0359] The server collects nationwide people flow data via API. Specifically, it sends API requests from external data sources and temporarily stores the retrieved data in JSON format. It also cleanses and normalizes the data to handle missing values ​​and outliers. This process is performed using the Python pandas library.

[0360] The terminal accepts user requests through a conversational interface. The user enters specific requests into text input fields, which are then sent to the server. The terminal is presented as a web application with UI components such as selection boxes and buttons.

[0361] The server uses a natural language processing model to analyze the user's input text and understand its intent. At the same time, an emotion engine analyzes the emotions from the user's input. Based on the results of this emotion analysis, appropriate prompts are generated and the basis for data analysis is established. NLP technologies used include the TextBlob library.

[0362] The server performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in foot traffic during tourism events and specific campaigns. To visually represent the analysis results, it uses the matplotlib library to generate dynamic graphs and charts.

[0363] The device visually displays the analysis results and generated graphs to the user, allowing the user to understand at a glance the increase or decrease in foot traffic and the effectiveness of attracting customers. Furthermore, the server generates specific action proposals based on the analysis results. These action proposals are customized according to the user's emotional state. For example, if the user shows signs of anxiety, the server will make more reassuring suggestions.

[0364] As a concrete example, the following operation takes place: A local government official inputs a request to "analyze changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan." The system performs data analysis based on this request and visually displays the results. It then makes specific suggestions based on the results, such as "run discount promotions during specific times" or "consider increasing transportation options."

[0365] Examples of prompts include:

[0366] "Please tell us the peak traffic times for last year's Christmas event and use that data to suggest improvements for the next event."

[0367] In this way, the system of the present invention can propose more effective measures by conducting a combined analysis of user emotions and people flow data.

[0368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0369] Step 1:

[0370] The server collects people flow data from across the country via API. It sends API requests from external data sources and temporarily stores the retrieved data in JSON format. The input is the API endpoint URL, and the output is people flow data in JSON format. Specifically, it sends requests using the Python requests library and receives responses in JSON format.

[0371] Step 2:

[0372] The server cleanses and normalizes the collected data. The input is the JSON data obtained in step 1, and the output is a cleansed and normalized data frame. Specifically, the pandas library is used to detect missing values ​​and outliers and handle them appropriately. In this step, the data format and units are unified.

[0373] Step 3:

[0374] The terminal accepts user requests through a conversational interface. Input is a request that the user types into a text input field, and output is an HTTP request to a server to which the request is sent. Specifically, this includes the user entering a prompt through a UI component in a web application and clicking a button to submit.

[0375] Step 4:

[0376] The server analyzes the user's input text using a natural language processing model. The input is the text data received in step 3, and the output is a command statement containing the analyzed intent and meaning. It also analyzes emotions from the input text using an emotion engine. Specifically, it performs emotion analysis of the text using the TextBlob library and outputs a result that is either positive, negative, or neutral.

[0377] Step 5:

[0378] The server performs data analysis using the generated prompts. The input is the analysis results and cleansed data generated in step 4, and the output is a dataset and graphs containing the analysis results. Specifically, the data is analyzed using KMeans clustering and time series analysis methods, and graphs are created using the matplotlib library.

[0379] Step 6:

[0380] The terminal visually provides the analysis results sent from the server and the generated graphs. The input is the analysis results and graph images generated in Step 5, and the output is visualized data displayed on the user's browser. Specifically, graphs and charts are displayed on the user interface and presented in an intuitive format.

[0381] Step 7:

[0382] The server generates specific policy proposals based on the analysis results. The inputs are the analysis results obtained in step 5 and the emotion data analyzed in step 4, and the output is a customized policy proposal. Specifically, the server generates proposal content that takes into account the user's psychological state based on the emotion analysis results and sends it to the terminal in JSON format.

[0383] Step 8:

[0384] The terminal displays customized action proposals to the user. The input is the action proposal text generated in step 7, and the output is the proposal content displayed on the user's browser. Specifically, the action proposals are displayed in an easy-to-understand format, helping the user plan their next event and make strategic decisions more easily.

[0385] This processing step effectively enables appropriate data analysis and policy proposals based on the user's emotional state.

[0386] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0387] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0388] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0389] [Second embodiment]

[0390] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0391] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0392] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0393] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0394] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0395] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0396] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0397] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0398] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0399] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0400] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0401] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0402] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[0403] Program processing and explanation

[0404] Data collection and preprocessing

[0405] Server: When collecting people flow data, it uses APIs from multiple data sources to obtain data. Specifically, it obtains people flow information for a specified date, time, and area, and stores it in a database. Next, it cleanses and normalizes the data. In other words, it detects missing values ​​and outliers, and properly complements or removes them, and standardizes the data format and units. This prepares the data in a form suitable for analysis.

[0406] User Interface Generation

[0407] Terminal: A display of a web application that can be accessed directly by the user. It provides UI components such as text input fields, selection boxes, and buttons, and is designed to allow users to easily input requests. This interface supports intuitive user interaction.

[0408] Natural Language Analysis and Prompt Generation

[0409] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0410] Terminal: Sends text data entered by the user to the server.

[0411] Server: Analyzes the received text data using a natural language processing (NLP) model, understanding the user's intent and generating appropriate prompts that identify specific analysis methods and required datasets.

[0412] Data analysis and graph generation

[0413] Server: Based on the prompts, generative AI models are used to analyze the data, for example, using time series analysis and clustering to measure changes in foot traffic before and after the event date. The results are then transformed into dynamic graphs and charts.

[0414] Terminal: The analysis results and graphs received from the server are displayed in an easy-to-understand manner to the user. For example, this includes line graphs showing increases and decreases in foot traffic, and heat maps showing the effectiveness of attracting customers.

[0415] Measure proposals

[0416] Server: Based on the analysis results, specific measures for the next event are generated. For example, recommendations include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. Measure suggestions are written in natural language and presented to users in a format that they can intuitively understand.

[0417] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[0418] Specific examples

[0419] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. In this case, the user obtains information through the following operations:

[0420] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0421] 2. Terminal: Sends the input request to the server.

[0422] 3. Server: Performs natural language analysis, identifies appropriate data and analytical methods, and generates prompts.

[0423] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[0424] 5. Terminal: Displays the analysis results and action proposals to the user.

[0425] 6. User: Use the information provided to plan your next event.

[0426] In this way, this system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective implementation of measures.

[0427] The processing flow will be explained below.

[0428] Step 1:

[0429] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends requests to API endpoints and receives data in JSON format. Temporarily stores the received data.

[0430] Step 2:

[0431] Server: Cleanses the collected data. Specifically, it complements missing values, removes outliers, and corrects values. For example, it detects null values ​​and extremely outlying values ​​and replaces them with appropriate values. It also performs normalization to unify data formats and units.

[0432] Step 3:

[0433] Server: Stores the cleansed data in a database so that it can be efficiently accessed for subsequent analysis steps.

[0434] Step 4:

[0435] Terminal: Provides web applications that present an intuitive interface to users, including UI components such as text input fields, selection boxes, and buttons.

[0436] Step 5:

[0437] User: Enters a specific request into the interface. For example, the user enters a request such as, "I would like you to analyze the changes in the flow of people on the day of last year's tourist event and provide suggestions for planning the next one" into the text input field.

[0438] Step 6:

[0439] Terminal: Sends the request entered by the user to the server. The text data is included in the request payload and sent to the server.

[0440] Step 7:

[0441] Server: Analyzes the user request using a natural language processing (NLP) model, tokenizes the request text, understands the user's intent, generates appropriate prompts, and identifies the required dataset and analysis techniques.

[0442] Step 8:

[0443] Server: Using the generated prompts, the server begins analyzing the people flow data. Specifically, it performs time series analysis to detect changes in people flow before and after the event. It also uses clustering techniques to classify people flow patterns.

[0444] Step 9:

[0445] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[0446] Step 10:

[0447] Terminal: Displays the analysis results and graphs received from the server to the user, presenting the results in a format that is easy for the user to understand and allowing them to interpret the data visually.

[0448] Step 11:

[0449] Server: Based on the analysis results, the server generates specific action plans for the next event. These plans include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The generated proposals are written in natural language.

[0450] Step 12:

[0451] Terminal: The generated policy proposals are displayed to the user, who can then review the proposals and use them as a reference for formulating an implementation plan.

[0452] Step 13:

[0453] Users: Give feedback on the information and suggestions provided by filling out and submitting a form in the interface.

[0454] Step 14:

[0455] Server: Receives user feedback and reflects it in improvements to the AI ​​model and UI, thereby continuously improving the accuracy and usability of the system.

[0456] Example 1

[0457] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0458] With conventional technology, there was no consistent system that could efficiently collect nationwide people flow data, cleanse and normalize it, and then perform specific data analysis and policy proposals according to the user's intentions.Therefore, there is a need for a system that can perform everything from data collection to analysis and policy proposals all at once, through an interface that even non-experts can use easily.

[0459] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0460] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating prompts using a generative AI model, and means for integrating the processing results of each means and providing an interactive interface that can be intuitively operated by users. This enables users without specialized knowledge to easily perform tasks from data collection to analysis and policy proposals through intuitive operations.

[0461] "People flow data" is information about the movements and gatherings of people in specific areas and at specific times.

[0462] "Cleansing" is the process of detecting missing or outliers in data and then filling or removing them appropriately.

[0463] "Normalization" is the process of standardizing and making consistent the format and units of data.

[0464] "Natural language analysis" is a technology that analyzes text written in human language into a form that can be understood by machines, and extracts intent and meaning.

[0465] "Prompt" refers to specific instructions or questions for data analysis or graph generation.

[0466] An "interactive interface" is a user interface that allows a user to intuitively interact with a system, and typically includes UI components such as text input fields, selection boxes, and buttons.

[0467] A "generative AI model" is an algorithm or computational model that leverages artificial intelligence techniques to automate specific tasks (e.g., natural language processing, data analysis).

[0468] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[0469] Data collection and preprocessing

[0470] Server: When collecting people flow data, APIs from multiple data sources are used to obtain data. Specifically, external data sources such as Google Maps API and social media APIs are used. The collected data is stored in a database. Next, during the data cleansing process, missing values ​​and outliers are detected and appropriate processing is performed, such as filling in the average value. The data is then normalized to unify the format and units.

[0471] User Interface Generation

[0472] Terminal: A web application is provided that can be accessed directly by the user. This application works with data provided by the server and displays UI components such as text input fields, selection boxes, and buttons. It is designed to be intuitive for the user, allowing them to easily input requests.

[0473] Natural Language Analysis and Prompt Generation

[0474] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0475] Terminal: Sends text data entered by the user to the server.

[0476] Server: Analyzes the received text data using a natural language processing model. Specifically, it uses generative AI models such as BERT and GPT-3 to understand the user's intent and generate appropriate prompts. The prompts are instructions that specify the specific analysis method and required dataset.

[0477] Data analysis and graph generation

[0478] Server: Based on generated prompts, data for a specified time period and region is filtered from the database. Generative AI models are then used to analyze the data. For example, time series analysis is used to measure changes in foot traffic before and after an event, and clustering techniques are used to find specific patterns and trends. The results of the analysis are then converted into dynamic graphs and charts using tools such as Python's Matplotlib and D3.js.

[0479] Measure proposals

[0480] Server: Based on the results of the data analysis, the server generates specific measures for the next event. For example, it proposes measures such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. These measures are written in natural language and presented to users in a format that they can intuitively understand.

[0481] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[0482] Specific examples

[0483] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. The information can be obtained through the following operations:

[0484] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0485] 2. Terminal: Sends the input request to the server.

[0486] 3. Server: Performs natural language analysis, identifies the required data and analysis methods, and generates prompts.

[0487] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[0488] 5. Terminal: Displays the analysis results and action proposals to the user.

[0489] 6. User: Use the information provided to plan your next event.

[0490] This system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective measures.

[0491] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0492] Step 1:

[0493] Data collection

[0494] Server: Uses APIs to collect people flow data for specified dates, times, and regions from multiple data sources. Specifically, it uses Google Maps API and social media APIs to obtain real-time people flow data.

[0495] Input: Specified date and time, region, and API connection information.

[0496] Data processing and calculation: Data from multiple sources is integrated, converted into a single format, and stored in a database.

[0497] Output: Integrated people flow data.

[0498] Step 2:

[0499] Data Cleansing and Normalization

[0500] Server: Cleanses the collected data. Specifically, it detects and fills in missing values ​​and removes outliers. For example, if there are many missing values, it fills in the average value, and if there are clearly abnormal values, it removes them. After that, it standardizes the data format and units.

[0501] Input: Integrated people flow data.

[0502] Data processing and calculation: Completion of missing values, removal of outliers, and standardization of data format and units are carried out.

[0503] Output: Cleansed and normalized people flow data.

[0504] Step 3:

[0505] User Interface Generation

[0506] Terminal: Provides a web application that users can access, including UI components such as text inputs, select boxes, and buttons that allow users to intuitively input requests.

[0507] Input: UI design information, cleansed and normalized data.

[0508] Data processing and computation: Web page and UI component generation.

[0509] Output: A web application where users can enter their requests.

[0510] Step 4:

[0511] Receiving requests from users

[0512] User: Enter a request such as, "I would like you to analyze the changes in the flow of people on the days when tourist events were held last year and make suggestions for planning the next one."

[0513] Input: Text request.

[0514] Data processing and calculation: Sending the text request content to the server.

[0515] Output: The request data.

[0516] Step 5:

[0517] Natural Language Analysis and Prompt Generation

[0518] Server: Analyzes the received text data using a natural language processing model to understand the user's intent. Specifically, it uses BERT or GPT-3 to extract appropriate keywords and actions. Next, it generates a prompt based on the analysis results.

[0519] Input: Request data.

[0520] Data processing and calculation: text analysis, keyword extraction, prompt generation.

[0521] Output: The generated prompt.

[0522] Step 6:

[0523] Data analysis and graph generation

[0524] Server: Filters data from the database for the specified time period and region based on generated prompts, then performs time series analysis and clustering using generative AI models, and converts the analysis results into dynamic graphs and charts using Python's Matplotlib and D3.js.

[0525] Input: Generated prompts, cleansed and normalized data.

[0526] Data processing and calculations: data filtering, time series analysis, clustering, graph generation.

[0527] Output: Graphs and charts of the analysis results.

[0528] Step 7:

[0529] Generate policy proposals

[0530] Server: Based on the analysis results, the server generates specific measures for the next event, such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposed measures are written in natural language and presented to users in a format that is easy to understand.

[0531] Input: Graphs and charts of analytical results.

[0532] Data processing and calculation: Generation of policy proposals and descriptions in natural language.

[0533] Output: Policy proposal document.

[0534] Step 8:

[0535] Display of results and action recommendations

[0536] Terminal: The analysis results and action proposals received from the server are displayed to the user, who can then use them to plan their next event.

[0537] Input: Policy proposal documents, graphs and charts of analysis results.

[0538] Data processing and calculation: Web display of results and policy proposals.

[0539] Output: Provides information to the user.

[0540] (Application example 1)

[0541] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0542] In modern society, there is a need to effectively analyze large amounts of people flow data and quickly propose strategic measures based on that data. However, conventional systems have difficulty preprocessing and analyzing data, and making specific proposals based on user requests. This makes it difficult to develop efficient advertising strategies, particularly in the advertising field. To address this issue, there is a need for a system that can consistently perform data collection, analysis, and proposals, and visualize them in an easy-to-understand manner.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0544] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating information to optimize advertising policies based on the collected data, means for visualizing people flow data for a specified period and providing it to the user, and means for providing specific proposals based on prompt sentences using a generative AI model. This makes it possible to efficiently analyze large amounts of people flow data and optimize advertising policies and propose specific strategies.

[0545] "People flow data" is data that records information on people's movements and stays in specific areas and periods of time.

[0546] "Cleansing" refers to the process of detecting missing or outliers in data and then filling or removing them.

[0547] "Normalization" refers to the process of standardizing the format and units of data and preparing it in a form suitable for analysis.

[0548] "Natural language analysis" is a technology that analyzes text data entered by a user and understands its intent and meaning.

[0549] A "prompt" is an input that generates a specific instruction or question and analyzes data accordingly.

[0550] A "generative AI model" is a model that uses artificial intelligence technology to generate appropriate responses or results for specific inputs.

[0551] "Data analysis" is the process of analyzing collected data using statistical or computational methods.

[0552] "Graph generation" refers to the process of creating graphs or charts to visually represent analytical results.

[0553] "Policy proposal" refers to proposing specific strategies and measures to be implemented next time based on the results of data analysis.

[0554] "Visualization" refers to a method of displaying data or information visually in an easy-to-understand manner.

[0555] In this invention, three parties are involved in realizing a system for advertising optimization: a server, a terminal, and a user. How this system works will be explained in detail below.

[0556] 1. Server Role

[0557] The server is responsible for the following processes:

[0558] Collection of people flow data: People flow data for specific regions and periods is obtained through APIs and stored in a database. The use of APIs is important for collecting data from various data sources.

[0559] Data cleansing and normalization: Detecting missing or outliers from collected data, and then filling or removing them, as well as standardizing the data format and units.

[0560] Natural Language Analysis: Receives the request text from the user and analyzes it using natural language processing technology to understand the user's intent and generate appropriate prompts.

[0561] Prompt generation and data analysis: Based on the generated prompts, a generative AI model is used to perform data analysis, including time series analysis and clustering.

[0562] Graph generation and action recommendations: Convert analysis results into dynamic graphs and charts and automatically generate action recommendations.

[0563] 2. Role of the terminal

[0564] The terminal is responsible for the following processes:

[0565] Providing a user interface: Provide a web application where users can enter requests. The interface includes UI components such as text input fields, select boxes, and buttons.

[0566] Request transmission and data display: The request entered by the user is sent to the server, and the analysis results and action proposals returned by the server are displayed. Display formats include line graphs and heat maps.

[0567] 3. User Roles

[0568] The user performs the following process:

[0569] Text input: For example, a request such as "Please suggest our next advertising strategy based on the foot traffic data from last year's campaign period" is entered into the device interface.

[0570] Reviewing the results and making decisions: Review the data analysis results and action proposals provided by the server, and plan the next advertising strategy based on them.

[0571] Hardware and software used

[0572] Hardware: User's smartphone and cloud server

[0573] Software: Python, open-source libraries (Pandas, Requests, Matplotlib), generative AI models (e.g., GPT-3)

[0574] Specific examples

[0575] When an advertising officer at a local government analyzes changes in foot traffic on the day of a specific event and plans the next advertising strategy based on that analysis, he or she uses the system in the following steps.

[0576] 1. User: Opens the smartphone app and enters a request: "Please suggest my next advertising strategy based on foot traffic data from last year's campaign period."

[0577] 2. Terminal: Sends the input request to the server.

[0578] 3. Server: Collects people flow data using APIs, cleansing and normalizing it, then performs natural language analysis to generate appropriate prompts.

[0579] 4. Server: Based on the generated prompts, a generative AI model is used to analyze the data and visualize the results, for example generating line graphs or heat maps.

[0580] 5. Server: Based on the results of the data analysis, generate proposals for the next advertising campaign and describe them in natural language.

[0581] 6. Terminal: Displays the generated analysis results and action proposals to the user.

[0582] 7. User: Plan your next advertising strategy based on the information displayed.

[0583] Prompt Sentence Examples

[0584] "I would like you to propose our next advertising strategy based on the foot traffic data from last year's campaign period."

[0585] In this way, by using the system of the present invention, advertising personnel can receive effective data analysis and strategic measures proposals.

[0586] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0587] Step 1:

[0588] The server uses API to collect people flow data for a specific area and period. The input is a request specifying the area and period, and the output is people flow data based on the specified conditions. The collected data is stored in a database.

[0589] Step 2:

[0590] The server cleanses and normalizes the collected people flow data. The input is the collected people flow data, and the output is the cleansed and normalized data. Specifically, it detects and completes missing and outlier values, and standardizes data formats and units.

[0591] Step 3:

[0592] The server receives the request text entered by the user on the terminal and performs natural language analysis. The input is the request text entered by the user, and the output is the analyzed user's intent. Specifically, NLP technology is used to understand the meaning and intent of the request text.

[0593] Step 4:

[0594] The server generates a prompt based on the natural language analysis results. The input is the analysis results including the user's intent, and the output is the generated prompt. The prompt is a specific instruction for data analysis.

[0595] Step 5:

[0596] The server performs data analysis based on the generated prompts. The input is the cleansed and normalized people flow data and the prompts, and the output is the analysis results. Specifically, it uses techniques such as time series analysis and clustering to analyze changes and patterns in people flow.

[0597] Step 6:

[0598] The server generates graphs and charts based on the results of the data analysis. The input is the data analysis results, and the output is visualized graphs and charts. Specifically, it uses tools such as Matplotlib to create line graphs, heat maps, and so on.

[0599] Step 7:

[0600] The server generates policy proposals based on the analysis results. The input is the data analysis results, including visualized graphs and charts, and the output is policy proposals. Specifically, a generative AI model is used to generate specific policy proposals in natural language.

[0601] Step 8:

[0602] The terminal displays the analysis results and proposed measures received from the server to the user. The input is the analysis results and proposed measures from the server, and the output is a visual display to the user. The user plans their next advertising strategy based on the displayed information.

[0603] As a concrete example, if a user inputs, "Please suggest my next advertising campaign based on the foot traffic data from last year's campaign period," the server will analyze this request, collect and analyze foot traffic data for the specified period, generate specific advertising campaign proposals based on that data, and provide them to the user via their device.

[0604] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0605] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[0606] Program processing and explanation

[0607] Data collection and preprocessing

[0608] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends API requests and temporarily stores the retrieved data in JSON format. Next, cleanses and normalizes the data, properly handles missing values ​​and outliers, and standardizes the data format and units.

[0609] User Interface Generation

[0610] Terminal: Displays a web application that provides an intuitive interface to the user, including UI components such as text input fields, selection boxes, and buttons, designed to allow the user to easily input requests.

[0611] Natural Language Analysis and Emotion Recognition

[0612] User: For example, enter a request such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one" in the text input field.

[0613] Terminal: Sends user input to the server.

[0614] Server: Analyzes the received text data using a natural language processing (NLP) model to understand the user's intent. At the same time, it uses an emotion engine to analyze the emotions from the user's input. Based on the results of this emotion analysis, it generates more appropriate prompts.

[0615] Data analysis and graph generation

[0616] Server: Performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in pedestrian flow before and after the event. It creates dynamic graphs and charts based on the generated analysis results.

[0617] Terminal: Visually displays the analysis results and graphs received from the server, including line graphs showing increases and decreases in foot traffic and heat maps visualizing the effectiveness of attracting customers.

[0618] Policy proposals and emotional responses

[0619] Server: Generates specific action proposals based on the analysis results. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. They are customized based on the user's emotional state. For example, if the user shows signs of anxiety, they will receive more reassuring proposals.

[0620] Device: Displays customized action proposals to users, who can then review the proposals and make decisions, such as planning their next event.

[0621] Specific examples

[0622] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day of a specific event and plan for the next event. In this case, the following operations are performed.

[0623] 1. User: Opens the web application and enters a request to "analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0624] 2. Terminal: Sends the input request to the server.

[0625] 3. Server: Performs natural language analysis to understand the intent of the user's request. In parallel, it uses an emotion engine to analyze emotions from the user's input.

[0626] 4. Server: Generates appropriate prompts and starts analyzing people flow data, cleansing and normalizing the data, and generating graphs and charts based on the analysis results.

[0627] 5. Terminal: Displays the generated analysis results and graphs to the user.

[0628] 6. Server: Generates specific action proposals based on the analysis results and adjusts the proposals according to the user's emotions.

[0629] 7. Terminal: The customized action proposal is displayed to the user, who can then accept the proposal and plan their next event.

[0630] In this way, this system easily supports data analysis and policy planning while taking into account the user's emotions, allowing users to make more effective strategic decisions.

[0631] The processing flow will be explained below.

[0632] Step 1:

[0633] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Specifically, it sends a request to the API endpoint and obtains people flow data for the required area and period in JSON format. The obtained data is temporarily stored in a database.

[0634] Step 2:

[0635] Server: Cleanses the collected data by imputing missing values ​​and filtering or correcting outliers. For example, it detects null values ​​and inappropriate data and replaces them with appropriate values ​​using imputation algorithms. It also normalizes the data format and units to make them consistent.

[0636] Step 3:

[0637] Server: The cleansed and normalized data is restored to a database in an optimal format for fast and efficient searching and analysis.

[0638] Step 4:

[0639] Terminal: Launches a web application that displays a user interface, which includes UI components such as text input fields, selection boxes, and buttons.

[0640] Step 5:

[0641] User: In the text input field, enter "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan," and press the send button.

[0642] Step 6:

[0643] Terminal: Collects user input and sends it to the server as an HTTP request, with the payload containing text data containing the user's request.

[0644] Step 7:

[0645] Server: Analyzes the received text data using a natural language processing (NLP) model, tokenizes the text data, analyzes the meaning of the sentences, and generates prompts to understand the user's request.

[0646] Step 8:

[0647] Server: At the same time, it uses an emotion engine to analyze the emotion from the user's input. The emotion engine analyzes the context of the input text and identifies the type of emotion (happiness, surprise, anxiety, etc.).

[0648] Step 9:

[0649] Server: Taking into account the results of sentiment analysis, adjust prompts according to the user's emotions. For example, if the user expresses anxiety, add additional reassuring information.

[0650] Step 10:

[0651] Server: Based on the prompt, the server begins analyzing the people flow data. It uses time series analysis and clustering techniques to measure changes in people flow before and after the event.

[0652] Step 11:

[0653] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[0654] Step 12:

[0655] Terminal: Displays the analysis results and graphs received from the server to the user, presenting data in a visually easy-to-understand format.

[0656] Step 13:

[0657] Server: Based on the analysis results, the server generates specific action proposals for the next event. These proposals include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The server also takes into account the results of sentiment analysis and customizes the proposals.

[0658] Step 14:

[0659] Device: The generated action proposals are displayed to the user, who can review the proposals and use them as reference for planning the next event.

[0660] Step 15:

[0661] Users: Provide feedback on the information and suggestions provided. Feedback is entered and submitted via the interface.

[0662] Step 16:

[0663] Server: Receives user feedback and reflects it in improving the AI ​​model and UI, thereby improving the accuracy and usability of the system.

[0664] Example 2

[0665] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0666] Conventional data analysis systems have had difficulty efficiently collecting and analyzing people flow data and providing specific policy proposals to users. They also were unable to provide policy proposals that took user emotions into account. This resulted in a decrease in the accuracy of the analysis results and proposals users received, and insufficient support for decision-making.

[0667] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0668] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for analyzing user emotions using a sentiment analysis engine, means for performing time series analysis and clustering using the generated prompts, means for generating dynamic graphs and charts based on the analysis results, means for providing the generated analysis results and diagrams to the user, means for generating policy proposals based on the analysis results and customizing the proposal content based on the user's emotions, and means for providing the policy proposals obtained by the above means to the user. This enables efficient collection and analysis of people flow data as well as specific and accurate policy proposals that take user emotions into consideration.

[0669] "People flow data" is statistical data on the movement and gathering of people in a certain area.

[0670] "Cleansing" is a process of removing noise and missing values ​​from collected data to improve the quality of the data.

[0671] "Normalization" is the process of converting data into a consistent format and units to facilitate comparison and analysis.

[0672] "Natural language analysis" is the process of analyzing text data using machine learning and artificial intelligence techniques to understand grammar and meaning.

[0673] An "emotion analysis engine" is a software component for analyzing and classifying a user's emotional state from text data.

[0674] A "prompt" is an analytical instruction or command that is generated based on user input.

[0675] "Time series analysis" is a method for analyzing fluctuations in data over time to make predictions and recognize patterns.

[0676] "Clustering" is a technique for classifying data into groups with high similarity and finding patterns and structures.

[0677] "Dynamic graphs and charts" are dynamic diagrams for displaying interactive visualizations of data.

[0678] "Policy proposals" involve presenting specific action plans and improvement measures based on the results of data analysis.

[0679] An "interactive interface" is an interface that includes input and output items that can be intuitively operated by a user.

[0680] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[0681] Data collection and preprocessing

[0682] Server: This system collects people flow data from the National Movement Statistics Data API and other external data sources. It uses the Python requests library for collection. The acquired JSON-formatted data is temporarily stored, and the Pandas library is used to cleanse and normalize the data. Missing values ​​and outliers are handled appropriately, and the data format and units are standardized.

[0683] User Interface Generation

[0684] Terminal: A web application is displayed that provides the user with an intuitive interface. This interface is built using the JavaScript React.js framework. The user can easily enter requests using text input fields, select boxes, and buttons.

[0685] Natural Language Analysis and Emotion Recognition

[0686] User: For example, enter a request in the text input field, such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0687] Terminal: User input is sent to the server in real time using AJAX requests.

[0688] Server: Analyzes the received text data using Python's natural language processing (NLP) libraries, such as NLTK and SpaCy. Extracts entities and verbs to understand the user's intent. At the same time, analyzes the sentiment of the user's input using a sentiment analysis engine, such as IBM Watson Tone Analyzer. Based on the results of the sentiment analysis, generates more appropriate prompts.

[0689] Data analysis and graph generation

[0690] Server: Based on the generated prompts, the people flow data is analyzed using Python time series analysis libraries (e.g., Prophet) and clustering algorithms (e.g., k-means). Based on the analysis results, dynamic graphs and charts are generated using libraries such as Matplotlib and Seaborn.

[0691] Policy proposals and emotional responses

[0692] Server: Based on the information obtained from the analysis, the server generates specific action proposals. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposals are also customized based on the user's emotional state. For example, if the user shows signs of anxiety, the server will make suggestions that will reassure them.

[0693] Terminal: Displays the action proposals received from the server to the user. The analysis results and action proposals are presented in a visually easy-to-understand format.

[0694] Specific examples

[0695] For example, suppose a local government official (user) wants to analyze changes in foot traffic on the day of a specific event and make plans for the next one. In this case, the user opens a web application and enters a request: "Analyze changes in foot traffic on the day of last year's tourism event and make suggestions for the next plan." The device sends this request to the server, which performs natural language analysis and sentiment analysis. The server then begins data analysis based on the generated prompts and generates the results as graphs and charts. Finally, it customizes appropriate policy proposals and provides them to the user. This allows the user to make more effective strategic decisions.

[0696] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0697] Step 1: Data collection and preprocessing

[0698] Server: Sends an HTTP request to the National Movement Statistics Data API to obtain people flow data. The input is the API request URL, and the output is JSON-formatted data. Specifically, the API request is sent using the requests library. The server temporarily stores the obtained JSON data, and then cleanses and normalizes the data using the Pandas library. Specific data processing involves imputing missing values ​​using an appropriate method, removing outliers, and standardizing data formats and units. The output is a cleansed and normalized data frame.

[0699] Step 2: Generate the user interface

[0700] Terminal: Uses the JavaScript React.js framework to generate a web application for the user. The input is the elements necessary for the user interface, and the output is a web page that the user can operate intuitively. Specific operations include creating UI components such as text input fields, selection boxes, and buttons, and arranging them on the screen. The terminal adds event listeners to receive and send user input in real time.

[0701] Step 3: Natural Language Analysis and Emotion Recognition

[0702] User: For example, a user enters a request in the text input field, such as "I want you to analyze the changes in people flow on the day of last year's tourist event and make suggestions for the next plan." The input is the user's text request, and the output is a request to send to the server.

[0703] Terminal: Sends the input text request to the server using an AJAX request. The input is the user's text data, and the output is an HTTP request.

[0704] Server: The received text data is analyzed using Python's natural language processing (NLP) libraries, NLTK and SpaCy. The input is the user's text request, and the output is the analysis results (a list of entities and verbs). Specifically, the text data is tokenized and entities and verbs are extracted. At the same time, the IBM Watson Tone Analyzer is used to analyze the user's emotions. The input is the user's text, and the output is the emotion analysis results. This allows the user's emotional state to be determined and more appropriate prompts to be generated.

[0705] Step 4: Data analysis and graph generation

[0706] Server: Based on the generated prompts, data analysis is performed using Python's time series analysis library (Prophet) and clustering algorithm (k-means). The input is a cleansed and normalized data frame, and the output is the analysis results. Specific operations include predicting trends in time series data and identifying data patterns through clustering. Based on the analysis results, dynamic graphs and charts are generated using the Matplotlib and Seaborn libraries. The output is visualized graphs and charts.

[0707] Step 5: Propose measures and respond to emotions

[0708] Server: Generates specific action proposals based on the analysis results. The inputs are the analysis results and the results of user sentiment analysis, and the output is specific action proposals. Specific operations include evaluating the data analysis results and creating proposals such as revising advertising strategies and identifying areas to attract customers. The proposals are customized according to the user's emotional state.

[0709] Terminal: Visually displays the policy proposals received from the server to the user. The input is the proposal content and graphs from the server, and the output is a screen display that the user can check. Specifically, it displays the analysis results and proposal content in an easy-to-understand manner, helping the user to plan the next action.

[0710] (Application example 2)

[0711] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0712] Conventional analysis systems based on people flow data make uniform policy proposals without considering user emotions, which means they are unable to provide appropriate proposals that address the user's psychological state or specific needs. Furthermore, collected data often contains missing values ​​and outliers, requiring appropriate data cleansing and normalization. Furthermore, there is a lack of systems that can intuitively accept user requests through a conversational interface.

[0713] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis including an emotion engine that analyzes user emotions, means for performing data analysis and graph generation using the generated prompts, and means for generating policy proposals based on the analysis results, providing the generated graphs and policy proposals to the user, and customizing the proposal content based on the user's psychological state. This enables appropriate data analysis and policy proposals according to the user's emotional state.

[0714] "People flow data" is data that shows patterns of people's movements and gatherings in specific areas and time periods.

[0715] "Data cleansing" refers to detecting missing or outliers from collected data and applying appropriate processing.

[0716] "Normalization methods" are methods for converting data with different data formats, units, etc. into a unified format.

[0717] "Natural language analysis" is a technology that analyzes text data entered by users and understands their intent and content.

[0718] The "emotion engine" is a system that analyzes emotions from the text entered by the user and grasps their psychological state.

[0719] A "prompt" is text containing a series of instructions or questions to guide user input or system action.

[0720] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning techniques to derive useful information.

[0721] "Graph generation" refers to the creation of graphs and charts to visually represent the results of data analysis.

[0722] "Policy proposals" involve proposing specific actions and strategies based on the results of the analysis.

[0723] "Customization" means tailoring what is delivered and how it is delivered to the user's specific needs and emotional state.

[0724] An "interactive interface" is an interface in which the system provides appropriate responses and suggestions based on information entered by the user.

[0725] The system of this invention analyzes user requests based on people flow data and combines it with sentiment analysis to enable more appropriate data analysis and policy proposals. Below, we will explain the details of each component of this system and how it works.

[0726] The server collects nationwide people flow data via API. Specifically, it sends API requests from external data sources and temporarily stores the retrieved data in JSON format. It also cleanses and normalizes the data to handle missing values ​​and outliers. This process is performed using the Python pandas library.

[0727] The terminal accepts user requests through a conversational interface. The user enters specific requests into text input fields, which are then sent to the server. The terminal is presented as a web application with UI components such as selection boxes and buttons.

[0728] The server uses a natural language processing model to analyze the user's input text and understand its intent. At the same time, an emotion engine analyzes the emotions from the user's input. Based on the results of this emotion analysis, appropriate prompts are generated and the basis for data analysis is established. NLP technologies used include the TextBlob library.

[0729] The server performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in foot traffic during tourism events and specific campaigns. To visually represent the analysis results, it uses the matplotlib library to generate dynamic graphs and charts.

[0730] The device visually displays the analysis results and generated graphs to the user, allowing the user to understand at a glance the increase or decrease in foot traffic and the effectiveness of attracting customers. Furthermore, the server generates specific action proposals based on the analysis results. These action proposals are customized according to the user's emotional state. For example, if the user shows signs of anxiety, the server will make more reassuring suggestions.

[0731] As a concrete example, the following operation takes place: A local government official inputs a request to "analyze changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan." The system performs data analysis based on this request and visually displays the results. It then makes specific suggestions based on the results, such as "run discount promotions during specific times" or "consider increasing transportation options."

[0732] Examples of prompts include:

[0733] "Please tell us the peak traffic times for last year's Christmas event and use that data to suggest improvements for the next event."

[0734] In this way, the system of the present invention can propose more effective measures by conducting a combined analysis of user emotions and people flow data.

[0735] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0736] Step 1:

[0737] The server collects people flow data from across the country via API. It sends API requests from external data sources and temporarily stores the retrieved data in JSON format. The input is the API endpoint URL, and the output is people flow data in JSON format. Specifically, it sends requests using the Python requests library and receives responses in JSON format.

[0738] Step 2:

[0739] The server cleanses and normalizes the collected data. The input is the JSON data obtained in step 1, and the output is a cleansed and normalized data frame. Specifically, the pandas library is used to detect missing values ​​and outliers and handle them appropriately. In this step, the data format and units are unified.

[0740] Step 3:

[0741] The terminal accepts user requests through a conversational interface. Input is a request that the user types into a text input field, and output is an HTTP request to a server to which the request is sent. Specifically, this includes the user entering a prompt through a UI component in a web application and clicking a button to submit.

[0742] Step 4:

[0743] The server analyzes the user's input text using a natural language processing model. The input is the text data received in step 3, and the output is a command statement containing the analyzed intent and meaning. It also analyzes emotions from the input text using an emotion engine. Specifically, it performs emotion analysis of the text using the TextBlob library and outputs a result that is either positive, negative, or neutral.

[0744] Step 5:

[0745] The server performs data analysis using the generated prompts. The input is the analysis results and cleansed data generated in step 4, and the output is a dataset and graphs containing the analysis results. Specifically, the data is analyzed using KMeans clustering and time series analysis methods, and graphs are created using the matplotlib library.

[0746] Step 6:

[0747] The terminal visually provides the analysis results sent from the server and the generated graphs. The input is the analysis results and graph images generated in Step 5, and the output is visualized data displayed on the user's browser. Specifically, graphs and charts are displayed on the user interface and presented in an intuitive format.

[0748] Step 7:

[0749] The server generates specific policy proposals based on the analysis results. The inputs are the analysis results obtained in step 5 and the emotion data analyzed in step 4, and the output is a customized policy proposal. Specifically, the server generates proposal content that takes into account the user's psychological state based on the emotion analysis results and sends it to the terminal in JSON format.

[0750] Step 8:

[0751] The terminal displays customized action proposals to the user. The input is the action proposal text generated in step 7, and the output is the proposal content displayed on the user's browser. Specifically, the action proposals are displayed in an easy-to-understand format, helping the user plan their next event and make strategic decisions more easily.

[0752] This processing step effectively enables appropriate data analysis and policy proposals based on the user's emotional state.

[0753] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0754] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0755] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0756] [Third embodiment]

[0757] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0758] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0759] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0760] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0761] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0762] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0763] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0764] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0765] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0766] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0767] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0768] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0769] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[0770] Program processing and explanation

[0771] Data collection and preprocessing

[0772] Server: When collecting people flow data, it uses APIs from multiple data sources to obtain data. Specifically, it obtains people flow information for a specified date, time, and area, and stores it in a database. Next, it cleanses and normalizes the data. In other words, it detects missing values ​​and outliers, and properly complements or removes them, and standardizes the data format and units. This prepares the data in a form suitable for analysis.

[0773] User Interface Generation

[0774] Terminal: A display of a web application that can be accessed directly by the user. It provides UI components such as text input fields, selection boxes, and buttons, and is designed to allow users to easily input requests. This interface supports intuitive user interaction.

[0775] Natural Language Analysis and Prompt Generation

[0776] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0777] Terminal: Sends text data entered by the user to the server.

[0778] Server: Analyzes the received text data using a natural language processing (NLP) model, understanding the user's intent and generating appropriate prompts that identify specific analysis methods and required datasets.

[0779] Data analysis and graph generation

[0780] Server: Based on the prompts, generative AI models are used to analyze the data, for example, using time series analysis and clustering to measure changes in foot traffic before and after the event date. The results are then transformed into dynamic graphs and charts.

[0781] Terminal: The analysis results and graphs received from the server are displayed in an easy-to-understand manner to the user. For example, this includes line graphs showing increases and decreases in foot traffic, and heat maps showing the effectiveness of attracting customers.

[0782] Measure proposals

[0783] Server: Based on the analysis results, specific measures for the next event are generated. For example, recommendations include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. Measure suggestions are written in natural language and presented to users in a format that they can intuitively understand.

[0784] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[0785] Specific examples

[0786] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. In this case, the user obtains information through the following operations:

[0787] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0788] 2. Terminal: Sends the input request to the server.

[0789] 3. Server: Performs natural language analysis, identifies appropriate data and analytical methods, and generates prompts.

[0790] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[0791] 5. Terminal: Displays the analysis results and action proposals to the user.

[0792] 6. User: Use the information provided to plan your next event.

[0793] In this way, this system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective implementation of measures.

[0794] The processing flow will be explained below.

[0795] Step 1:

[0796] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends requests to API endpoints and receives data in JSON format. Temporarily stores the received data.

[0797] Step 2:

[0798] Server: Cleanses the collected data. Specifically, it complements missing values, removes outliers, and corrects values. For example, it detects null values ​​and extremely outlying values ​​and replaces them with appropriate values. It also performs normalization to unify data formats and units.

[0799] Step 3:

[0800] Server: Stores the cleansed data in a database so that it can be efficiently accessed for subsequent analysis steps.

[0801] Step 4:

[0802] Terminal: Provides web applications that present an intuitive interface to users, including UI components such as text input fields, selection boxes, and buttons.

[0803] Step 5:

[0804] User: Enters a specific request into the interface. For example, the user enters a request such as, "I would like you to analyze the changes in the flow of people on the day of last year's tourist event and provide suggestions for planning the next one" into the text input field.

[0805] Step 6:

[0806] Terminal: Sends the request entered by the user to the server. The text data is included in the request payload and sent to the server.

[0807] Step 7:

[0808] Server: Analyzes the user request using a natural language processing (NLP) model, tokenizes the request text, understands the user's intent, generates appropriate prompts, and identifies the required dataset and analysis techniques.

[0809] Step 8:

[0810] Server: Using the generated prompts, the server begins analyzing the people flow data. Specifically, it performs time series analysis to detect changes in people flow before and after the event. It also uses clustering techniques to classify people flow patterns.

[0811] Step 9:

[0812] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[0813] Step 10:

[0814] Terminal: Displays the analysis results and graphs received from the server to the user, presenting the results in a format that is easy for the user to understand and allowing them to interpret the data visually.

[0815] Step 11:

[0816] Server: Based on the analysis results, the server generates specific action plans for the next event. These plans include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The generated proposals are written in natural language.

[0817] Step 12:

[0818] Terminal: The generated policy proposals are displayed to the user, who can then review the proposals and use them as a reference for formulating an implementation plan.

[0819] Step 13:

[0820] Users: Give feedback on the information and suggestions provided by filling out and submitting a form in the interface.

[0821] Step 14:

[0822] Server: Receives user feedback and reflects it in improvements to the AI ​​model and UI, thereby continuously improving the accuracy and usability of the system.

[0823] Example 1

[0824] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0825] With conventional technology, there was no consistent system that could efficiently collect nationwide people flow data, cleanse and normalize it, and then perform specific data analysis and policy proposals according to the user's intentions.Therefore, there is a need for a system that can perform everything from data collection to analysis and policy proposals all at once, through an interface that even non-experts can use easily.

[0826] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0827] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating prompts using a generative AI model, and means for integrating the processing results of each means and providing an interactive interface that can be intuitively operated by users. This enables users without specialized knowledge to easily perform tasks from data collection to analysis and policy proposals through intuitive operations.

[0828] "People flow data" is information about the movements and gatherings of people in specific areas and at specific times.

[0829] "Cleansing" is the process of detecting missing or outliers in data and then filling or removing them appropriately.

[0830] "Normalization" is the process of standardizing and making consistent the format and units of data.

[0831] "Natural language analysis" is a technology that analyzes text written in human language into a form that can be understood by machines, and extracts intent and meaning.

[0832] "Prompt" refers to specific instructions or questions for data analysis or graph generation.

[0833] An "interactive interface" is a user interface that allows a user to intuitively interact with a system, and typically includes UI components such as text input fields, selection boxes, and buttons.

[0834] A "generative AI model" is an algorithm or computational model that leverages artificial intelligence techniques to automate specific tasks (e.g., natural language processing, data analysis).

[0835] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[0836] Data collection and preprocessing

[0837] Server: When collecting people flow data, APIs from multiple data sources are used to obtain data. Specifically, external data sources such as Google Maps API and social media APIs are used. The collected data is stored in a database. Next, during the data cleansing process, missing values ​​and outliers are detected and appropriate processing is performed, such as filling in the average value. The data is then normalized to unify the format and units.

[0838] User Interface Generation

[0839] Terminal: A web application is provided that can be accessed directly by the user. This application works with data provided by the server and displays UI components such as text input fields, selection boxes, and buttons. It is designed to be intuitive for the user, allowing them to easily input requests.

[0840] Natural Language Analysis and Prompt Generation

[0841] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0842] Terminal: Sends text data entered by the user to the server.

[0843] Server: Analyzes the received text data using a natural language processing model. Specifically, it uses generative AI models such as BERT and GPT-3 to understand the user's intent and generate appropriate prompts. The prompts are instructions that specify the specific analysis method and required dataset.

[0844] Data analysis and graph generation

[0845] Server: Based on generated prompts, data for a specified time period and region is filtered from the database. Generative AI models are then used to analyze the data. For example, time series analysis is used to measure changes in foot traffic before and after an event, and clustering techniques are used to find specific patterns and trends. The results of the analysis are then converted into dynamic graphs and charts using tools such as Python's Matplotlib and D3.js.

[0846] Measure proposals

[0847] Server: Based on the results of the data analysis, the server generates specific measures for the next event. For example, it proposes measures such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. These measures are written in natural language and presented to users in a format that they can intuitively understand.

[0848] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[0849] Specific examples

[0850] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. The information can be obtained through the following operations:

[0851] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0852] 2. Terminal: Sends the input request to the server.

[0853] 3. Server: Performs natural language analysis, identifies the required data and analysis methods, and generates prompts.

[0854] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[0855] 5. Terminal: Displays the analysis results and action proposals to the user.

[0856] 6. User: Use the information provided to plan your next event.

[0857] This system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective measures.

[0858] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0859] Step 1:

[0860] Data collection

[0861] Server: Uses APIs to collect people flow data for specified dates, times, and regions from multiple data sources. Specifically, it uses Google Maps API and social media APIs to obtain real-time people flow data.

[0862] Input: Specified date and time, region, and API connection information.

[0863] Data processing and calculation: Data from multiple sources is integrated, converted into a single format, and stored in a database.

[0864] Output: Integrated people flow data.

[0865] Step 2:

[0866] Data Cleansing and Normalization

[0867] Server: Cleanses the collected data. Specifically, it detects and fills in missing values ​​and removes outliers. For example, if there are many missing values, it fills in the average value, and if there are clearly abnormal values, it removes them. After that, it standardizes the data format and units.

[0868] Input: Integrated people flow data.

[0869] Data processing and calculation: Completion of missing values, removal of outliers, and standardization of data format and units are carried out.

[0870] Output: Cleansed and normalized people flow data.

[0871] Step 3:

[0872] User Interface Generation

[0873] Terminal: Provides a web application that users can access, including UI components such as text inputs, select boxes, and buttons that allow users to intuitively input requests.

[0874] Input: UI design information, cleansed and normalized data.

[0875] Data processing and computation: Web page and UI component generation.

[0876] Output: A web application where users can enter their requests.

[0877] Step 4:

[0878] Receiving requests from users

[0879] User: Enter a request such as, "I would like you to analyze the changes in the flow of people on the days when tourist events were held last year and make suggestions for planning the next one."

[0880] Input: Text request.

[0881] Data processing and calculation: Sending the text request content to the server.

[0882] Output: The request data.

[0883] Step 5:

[0884] Natural Language Analysis and Prompt Generation

[0885] Server: Analyzes the received text data using a natural language processing model to understand the user's intent. Specifically, it uses BERT or GPT-3 to extract appropriate keywords and actions. Next, it generates a prompt based on the analysis results.

[0886] Input: Request data.

[0887] Data processing and calculation: text analysis, keyword extraction, prompt generation.

[0888] Output: The generated prompt.

[0889] Step 6:

[0890] Data analysis and graph generation

[0891] Server: Filters data from the database for the specified time period and region based on generated prompts, then performs time series analysis and clustering using generative AI models, and converts the analysis results into dynamic graphs and charts using Python's Matplotlib and D3.js.

[0892] Input: Generated prompts, cleansed and normalized data.

[0893] Data processing and calculations: data filtering, time series analysis, clustering, graph generation.

[0894] Output: Graphs and charts of the analysis results.

[0895] Step 7:

[0896] Generate policy proposals

[0897] Server: Based on the analysis results, the server generates specific measures for the next event, such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposed measures are written in natural language and presented to users in a format that is easy to understand.

[0898] Input: Graphs and charts of analytical results.

[0899] Data processing and calculation: Generation of policy proposals and descriptions in natural language.

[0900] Output: Policy proposal document.

[0901] Step 8:

[0902] Display of results and action recommendations

[0903] Terminal: The analysis results and action proposals received from the server are displayed to the user, who can then use them to plan their next event.

[0904] Input: Policy proposal documents, graphs and charts of analysis results.

[0905] Data processing and calculation: Web display of results and policy proposals.

[0906] Output: Provides information to the user.

[0907] (Application example 1)

[0908] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0909] In modern society, there is a need to effectively analyze large amounts of people flow data and quickly propose strategic measures based on that data. However, conventional systems have difficulty preprocessing and analyzing data, and making specific proposals based on user requests. This makes it difficult to develop efficient advertising strategies, particularly in the advertising field. To address this issue, there is a need for a system that can consistently perform data collection, analysis, and proposals, and visualize them in an easy-to-understand manner.

[0910] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0911] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating information to optimize advertising policies based on the collected data, means for visualizing people flow data for a specified period and providing it to the user, and means for providing specific proposals based on prompt sentences using a generative AI model. This makes it possible to efficiently analyze large amounts of people flow data and optimize advertising policies and propose specific strategies.

[0912] "People flow data" is data that records information on people's movements and stays in specific areas and periods of time.

[0913] "Cleansing" refers to the process of detecting missing or outliers in data and then filling or removing them.

[0914] "Normalization" refers to the process of standardizing the format and units of data and preparing it in a form suitable for analysis.

[0915] "Natural language analysis" is a technology that analyzes text data entered by a user and understands its intent and meaning.

[0916] A "prompt" is an input that generates a specific instruction or question and analyzes data accordingly.

[0917] A "generative AI model" is a model that uses artificial intelligence technology to generate appropriate responses or results for specific inputs.

[0918] "Data analysis" is the process of analyzing collected data using statistical or computational methods.

[0919] "Graph generation" refers to the process of creating graphs or charts to visually represent analytical results.

[0920] "Policy proposal" refers to proposing specific strategies and measures to be implemented next time based on the results of data analysis.

[0921] "Visualization" refers to a method of displaying data or information visually in an easy-to-understand manner.

[0922] In this invention, three parties are involved in realizing a system for advertising optimization: a server, a terminal, and a user. How this system works will be explained in detail below.

[0923] 1. Server Role

[0924] The server is responsible for the following processes:

[0925] Collection of people flow data: People flow data for specific regions and periods is obtained through APIs and stored in a database. The use of APIs is important for collecting data from various data sources.

[0926] Data cleansing and normalization: Detecting missing or outliers from collected data, and then filling or removing them, as well as standardizing the data format and units.

[0927] Natural Language Analysis: Receives the request text from the user and analyzes it using natural language processing technology to understand the user's intent and generate appropriate prompts.

[0928] Prompt generation and data analysis: Based on the generated prompts, a generative AI model is used to perform data analysis, including time series analysis and clustering.

[0929] Graph generation and action recommendations: Convert analysis results into dynamic graphs and charts and automatically generate action recommendations.

[0930] 2. Role of the terminal

[0931] The terminal is responsible for the following processes:

[0932] Providing a user interface: Provide a web application where users can enter requests. The interface includes UI components such as text input fields, select boxes, and buttons.

[0933] Request transmission and data display: The request entered by the user is sent to the server, and the analysis results and action proposals returned by the server are displayed. Display formats include line graphs and heat maps.

[0934] 3. User Roles

[0935] The user performs the following process:

[0936] Text input: For example, a request such as "Please suggest our next advertising strategy based on the foot traffic data from last year's campaign period" is entered into the device interface.

[0937] Reviewing the results and making decisions: Review the data analysis results and action proposals provided by the server, and plan the next advertising strategy based on them.

[0938] Hardware and software used

[0939] Hardware: User's smartphone and cloud server

[0940] Software: Python, open-source libraries (Pandas, Requests, Matplotlib), generative AI models (e.g., GPT-3)

[0941] Specific examples

[0942] When an advertising officer at a local government analyzes changes in foot traffic on the day of a specific event and plans the next advertising strategy based on that analysis, he or she uses the system in the following steps.

[0943] 1. User: Opens the smartphone app and enters a request: "Please suggest my next advertising strategy based on foot traffic data from last year's campaign period."

[0944] 2. Terminal: Sends the input request to the server.

[0945] 3. Server: Collects people flow data using APIs, cleansing and normalizing it, then performs natural language analysis to generate appropriate prompts.

[0946] 4. Server: Based on the generated prompts, a generative AI model is used to analyze the data and visualize the results, for example generating line graphs or heat maps.

[0947] 5. Server: Based on the results of the data analysis, generate proposals for the next advertising campaign and describe them in natural language.

[0948] 6. Terminal: Displays the generated analysis results and action proposals to the user.

[0949] 7. User: Plan your next advertising strategy based on the information displayed.

[0950] Prompt Sentence Examples

[0951] "I would like you to propose our next advertising strategy based on the foot traffic data from last year's campaign period."

[0952] In this way, by using the system of the present invention, advertising personnel can receive effective data analysis and strategic measures proposals.

[0953] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0954] Step 1:

[0955] The server uses API to collect people flow data for a specific area and period. The input is a request specifying the area and period, and the output is people flow data based on the specified conditions. The collected data is stored in a database.

[0956] Step 2:

[0957] The server cleanses and normalizes the collected people flow data. The input is the collected people flow data, and the output is the cleansed and normalized data. Specifically, it detects and completes missing and outlier values, and standardizes data formats and units.

[0958] Step 3:

[0959] The server receives the request text entered by the user on the terminal and performs natural language analysis. The input is the request text entered by the user, and the output is the analyzed user's intent. Specifically, NLP technology is used to understand the meaning and intent of the request text.

[0960] Step 4:

[0961] The server generates a prompt based on the natural language analysis results. The input is the analysis results including the user's intent, and the output is the generated prompt. The prompt is a specific instruction for data analysis.

[0962] Step 5:

[0963] The server performs data analysis based on the generated prompts. The input is the cleansed and normalized people flow data and the prompts, and the output is the analysis results. Specifically, it uses techniques such as time series analysis and clustering to analyze changes and patterns in people flow.

[0964] Step 6:

[0965] The server generates graphs and charts based on the results of the data analysis. The input is the data analysis results, and the output is visualized graphs and charts. Specifically, it uses tools such as Matplotlib to create line graphs, heat maps, and so on.

[0966] Step 7:

[0967] The server generates policy proposals based on the analysis results. The input is the data analysis results, including visualized graphs and charts, and the output is policy proposals. Specifically, a generative AI model is used to generate specific policy proposals in natural language.

[0968] Step 8:

[0969] The terminal displays the analysis results and proposed measures received from the server to the user. The input is the analysis results and proposed measures from the server, and the output is a visual display to the user. The user plans their next advertising strategy based on the displayed information.

[0970] As a concrete example, if a user inputs, "Please suggest my next advertising campaign based on the foot traffic data from last year's campaign period," the server will analyze this request, collect and analyze foot traffic data for the specified period, generate specific advertising campaign proposals based on that data, and provide them to the user via their device.

[0971] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0972] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[0973] Program processing and explanation

[0974] Data collection and preprocessing

[0975] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends API requests and temporarily stores the retrieved data in JSON format. Next, cleanses and normalizes the data, properly handles missing values ​​and outliers, and standardizes the data format and units.

[0976] User Interface Generation

[0977] Terminal: Displays a web application that provides an intuitive interface to the user, including UI components such as text input fields, selection boxes, and buttons, designed to allow the user to easily input requests.

[0978] Natural Language Analysis and Emotion Recognition

[0979] User: For example, enter a request such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one" in the text input field.

[0980] Terminal: Sends user input to the server.

[0981] Server: Analyzes the received text data using a natural language processing (NLP) model to understand the user's intent. At the same time, it uses an emotion engine to analyze the emotions from the user's input. Based on the results of this emotion analysis, it generates more appropriate prompts.

[0982] Data analysis and graph generation

[0983] Server: Performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in pedestrian flow before and after the event. It creates dynamic graphs and charts based on the generated analysis results.

[0984] Terminal: Visually displays the analysis results and graphs received from the server, including line graphs showing increases and decreases in foot traffic and heat maps visualizing the effectiveness of attracting customers.

[0985] Policy proposals and emotional responses

[0986] Server: Generates specific action proposals based on the analysis results. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. They are customized based on the user's emotional state. For example, if the user shows signs of anxiety, they will receive more reassuring proposals.

[0987] Device: Displays customized action proposals to users, who can then review the proposals and make decisions, such as planning their next event.

[0988] Specific examples

[0989] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day of a specific event and plan for the next event. In this case, the following operations are performed.

[0990] 1. User: Opens the web application and enters a request to "analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[0991] 2. Terminal: Sends the input request to the server.

[0992] 3. Server: Performs natural language analysis to understand the intent of the user's request. In parallel, it uses an emotion engine to analyze emotions from the user's input.

[0993] 4. Server: Generates appropriate prompts and starts analyzing people flow data, cleansing and normalizing the data, and generating graphs and charts based on the analysis results.

[0994] 5. Terminal: Displays the generated analysis results and graphs to the user.

[0995] 6. Server: Generates specific action proposals based on the analysis results and adjusts the proposals according to the user's emotions.

[0996] 7. Terminal: The customized action proposal is displayed to the user, who can then accept the proposal and plan their next event.

[0997] In this way, this system easily supports data analysis and policy planning while taking into account the user's emotions, allowing users to make more effective strategic decisions.

[0998] The processing flow will be explained below.

[0999] Step 1:

[1000] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Specifically, it sends a request to the API endpoint and obtains people flow data for the required area and period in JSON format. The obtained data is temporarily stored in a database.

[1001] Step 2:

[1002] Server: Cleanses the collected data by imputing missing values ​​and filtering or correcting outliers. For example, it detects null values ​​and inappropriate data and replaces them with appropriate values ​​using imputation algorithms. It also normalizes the data format and units to make them consistent.

[1003] Step 3:

[1004] Server: The cleansed and normalized data is restored to a database in an optimal format for fast and efficient searching and analysis.

[1005] Step 4:

[1006] Terminal: Launches a web application that displays a user interface, which includes UI components such as text input fields, selection boxes, and buttons.

[1007] Step 5:

[1008] User: In the text input field, enter "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan," and press the send button.

[1009] Step 6:

[1010] Terminal: Collects user input and sends it to the server as an HTTP request, with the payload containing text data containing the user's request.

[1011] Step 7:

[1012] Server: Analyzes the received text data using a natural language processing (NLP) model, tokenizes the text data, analyzes the meaning of the sentences, and generates prompts to understand the user's request.

[1013] Step 8:

[1014] Server: At the same time, it uses an emotion engine to analyze the emotion from the user's input. The emotion engine analyzes the context of the input text and identifies the type of emotion (happiness, surprise, anxiety, etc.).

[1015] Step 9:

[1016] Server: Taking into account the results of sentiment analysis, adjust prompts according to the user's emotions. For example, if the user expresses anxiety, add additional reassuring information.

[1017] Step 10:

[1018] Server: Based on the prompt, the server begins analyzing the people flow data. It uses time series analysis and clustering techniques to measure changes in people flow before and after the event.

[1019] Step 11:

[1020] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[1021] Step 12:

[1022] Terminal: Displays the analysis results and graphs received from the server to the user, presenting data in a visually easy-to-understand format.

[1023] Step 13:

[1024] Server: Based on the analysis results, the server generates specific action proposals for the next event. These proposals include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The server also takes into account the results of sentiment analysis and customizes the proposals.

[1025] Step 14:

[1026] Device: The generated action proposals are displayed to the user, who can review the proposals and use them as reference for planning the next event.

[1027] Step 15:

[1028] Users: Provide feedback on the information and suggestions provided. Feedback is entered and submitted via the interface.

[1029] Step 16:

[1030] Server: Receives user feedback and reflects it in improving the AI ​​model and UI, thereby improving the accuracy and usability of the system.

[1031] Example 2

[1032] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1033] Conventional data analysis systems have had difficulty efficiently collecting and analyzing people flow data and providing specific policy proposals to users. They also were unable to provide policy proposals that took user emotions into account. This resulted in a decrease in the accuracy of the analysis results and proposals users received, and insufficient support for decision-making.

[1034] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1035] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for analyzing user emotions using a sentiment analysis engine, means for performing time series analysis and clustering using the generated prompts, means for generating dynamic graphs and charts based on the analysis results, means for providing the generated analysis results and diagrams to the user, means for generating policy proposals based on the analysis results and customizing the proposal content based on the user's emotions, and means for providing the policy proposals obtained by the above means to the user. This enables efficient collection and analysis of people flow data as well as specific and accurate policy proposals that take user emotions into consideration.

[1036] "People flow data" is statistical data on the movement and gathering of people in a certain area.

[1037] "Cleansing" is a process of removing noise and missing values ​​from collected data to improve the quality of the data.

[1038] "Normalization" is the process of converting data into a consistent format and units to facilitate comparison and analysis.

[1039] "Natural language analysis" is the process of analyzing text data using machine learning and artificial intelligence techniques to understand grammar and meaning.

[1040] An "emotion analysis engine" is a software component for analyzing and classifying a user's emotional state from text data.

[1041] A "prompt" is an analytical instruction or command that is generated based on user input.

[1042] "Time series analysis" is a method for analyzing fluctuations in data over time to make predictions and recognize patterns.

[1043] "Clustering" is a technique for classifying data into groups with high similarity and finding patterns and structures.

[1044] "Dynamic graphs and charts" are dynamic diagrams for displaying interactive visualizations of data.

[1045] "Policy proposals" involve presenting specific action plans and improvement measures based on the results of data analysis.

[1046] An "interactive interface" is an interface that includes input and output items that can be intuitively operated by a user.

[1047] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[1048] Data collection and preprocessing

[1049] Server: This system collects people flow data from the National Movement Statistics Data API and other external data sources. It uses the Python requests library for collection. The acquired JSON-formatted data is temporarily stored, and the Pandas library is used to cleanse and normalize the data. Missing values ​​and outliers are handled appropriately, and the data format and units are standardized.

[1050] User Interface Generation

[1051] Terminal: A web application is displayed that provides the user with an intuitive interface. This interface is built using the JavaScript React.js framework. The user can easily enter requests using text input fields, select boxes, and buttons.

[1052] Natural Language Analysis and Emotion Recognition

[1053] User: For example, enter a request in the text input field, such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[1054] Terminal: User input is sent to the server in real time using AJAX requests.

[1055] Server: Analyzes the received text data using Python's natural language processing (NLP) libraries, such as NLTK and SpaCy. Extracts entities and verbs to understand the user's intent. At the same time, analyzes the sentiment of the user's input using a sentiment analysis engine, such as IBM Watson Tone Analyzer. Based on the results of the sentiment analysis, generates more appropriate prompts.

[1056] Data analysis and graph generation

[1057] Server: Based on the generated prompts, the people flow data is analyzed using Python time series analysis libraries (e.g., Prophet) and clustering algorithms (e.g., k-means). Based on the analysis results, dynamic graphs and charts are generated using libraries such as Matplotlib and Seaborn.

[1058] Policy proposals and emotional responses

[1059] Server: Based on the information obtained from the analysis, the server generates specific action proposals. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposals are also customized based on the user's emotional state. For example, if the user shows signs of anxiety, the server will make suggestions that will reassure them.

[1060] Terminal: Displays the action proposals received from the server to the user. The analysis results and action proposals are presented in a visually easy-to-understand format.

[1061] Specific examples

[1062] For example, suppose a local government official (user) wants to analyze changes in foot traffic on the day of a specific event and make plans for the next one. In this case, the user opens a web application and enters a request: "Analyze changes in foot traffic on the day of last year's tourism event and make suggestions for the next plan." The device sends this request to the server, which performs natural language analysis and sentiment analysis. The server then begins data analysis based on the generated prompts and generates the results as graphs and charts. Finally, it customizes appropriate policy proposals and provides them to the user. This allows the user to make more effective strategic decisions.

[1063] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1064] Step 1: Data collection and preprocessing

[1065] Server: Sends an HTTP request to the National Movement Statistics Data API to obtain people flow data. The input is the API request URL, and the output is JSON-formatted data. Specifically, the API request is sent using the requests library. The server temporarily stores the obtained JSON data, and then cleanses and normalizes the data using the Pandas library. Specific data processing involves imputing missing values ​​using an appropriate method, removing outliers, and standardizing data formats and units. The output is a cleansed and normalized data frame.

[1066] Step 2: Generate the user interface

[1067] Terminal: Uses the JavaScript React.js framework to generate a web application for the user. The input is the elements necessary for the user interface, and the output is a web page that the user can operate intuitively. Specific operations include creating UI components such as text input fields, selection boxes, and buttons, and arranging them on the screen. The terminal adds event listeners to receive and send user input in real time.

[1068] Step 3: Natural Language Analysis and Emotion Recognition

[1069] User: For example, a user enters a request in the text input field, such as "I want you to analyze the changes in people flow on the day of last year's tourist event and make suggestions for the next plan." The input is the user's text request, and the output is a request to send to the server.

[1070] Terminal: Sends the input text request to the server using an AJAX request. The input is the user's text data, and the output is an HTTP request.

[1071] Server: The received text data is analyzed using Python's natural language processing (NLP) libraries, NLTK and SpaCy. The input is the user's text request, and the output is the analysis results (a list of entities and verbs). Specifically, the text data is tokenized and entities and verbs are extracted. At the same time, the IBM Watson Tone Analyzer is used to analyze the user's emotions. The input is the user's text, and the output is the emotion analysis results. This allows the user's emotional state to be determined and more appropriate prompts to be generated.

[1072] Step 4: Data analysis and graph generation

[1073] Server: Based on the generated prompts, data analysis is performed using Python's time series analysis library (Prophet) and clustering algorithm (k-means). The input is a cleansed and normalized data frame, and the output is the analysis results. Specific operations include predicting trends in time series data and identifying data patterns through clustering. Based on the analysis results, dynamic graphs and charts are generated using the Matplotlib and Seaborn libraries. The output is visualized graphs and charts.

[1074] Step 5: Propose measures and respond to emotions

[1075] Server: Generates specific action proposals based on the analysis results. The inputs are the analysis results and the results of user sentiment analysis, and the output is specific action proposals. Specific operations include evaluating the data analysis results and creating proposals such as revising advertising strategies and identifying areas to attract customers. The proposals are customized according to the user's emotional state.

[1076] Terminal: Visually displays the policy proposals received from the server to the user. The input is the proposal content and graphs from the server, and the output is a screen display that the user can check. Specifically, it displays the analysis results and proposal content in an easy-to-understand manner, helping the user to plan the next action.

[1077] (Application example 2)

[1078] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1079] Conventional analysis systems based on people flow data make uniform policy proposals without considering user emotions, which means they are unable to provide appropriate proposals that address the user's psychological state or specific needs. Furthermore, collected data often contains missing values ​​and outliers, requiring appropriate data cleansing and normalization. Furthermore, there is a lack of systems that can intuitively accept user requests through a conversational interface.

[1080] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis including an emotion engine that analyzes user emotions, means for performing data analysis and graph generation using the generated prompts, and means for generating policy proposals based on the analysis results, providing the generated graphs and policy proposals to the user, and customizing the proposal content based on the user's psychological state. This enables appropriate data analysis and policy proposals according to the user's emotional state.

[1081] "People flow data" is data that shows patterns of people's movements and gatherings in specific areas and time periods.

[1082] "Data cleansing" refers to detecting missing or outliers from collected data and applying appropriate processing.

[1083] "Normalization methods" are methods for converting data with different data formats, units, etc. into a unified format.

[1084] "Natural language analysis" is a technology that analyzes text data entered by users and understands their intent and content.

[1085] The "emotion engine" is a system that analyzes emotions from the text entered by the user and grasps their psychological state.

[1086] A "prompt" is text containing a series of instructions or questions to guide user input or system action.

[1087] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning techniques to derive useful information.

[1088] "Graph generation" refers to the creation of graphs and charts to visually represent the results of data analysis.

[1089] "Policy proposals" involve proposing specific actions and strategies based on the results of the analysis.

[1090] "Customization" means tailoring what is delivered and how it is delivered to the user's specific needs and emotional state.

[1091] An "interactive interface" is an interface in which the system provides appropriate responses and suggestions based on information entered by the user.

[1092] The system of this invention analyzes user requests based on people flow data and combines it with sentiment analysis to enable more appropriate data analysis and policy proposals. Below, we will explain the details of each component of this system and how it works.

[1093] The server collects nationwide people flow data via API. Specifically, it sends API requests from external data sources and temporarily stores the retrieved data in JSON format. It also cleanses and normalizes the data to handle missing values ​​and outliers. This process is performed using the Python pandas library.

[1094] The terminal accepts user requests through a conversational interface. The user enters specific requests into text input fields, which are then sent to the server. The terminal is presented as a web application with UI components such as selection boxes and buttons.

[1095] The server uses a natural language processing model to analyze the user's input text and understand its intent. At the same time, an emotion engine analyzes the emotions from the user's input. Based on the results of this emotion analysis, appropriate prompts are generated and the basis for data analysis is established. NLP technologies used include the TextBlob library.

[1096] The server performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in foot traffic during tourism events and specific campaigns. To visually represent the analysis results, it uses the matplotlib library to generate dynamic graphs and charts.

[1097] The device visually displays the analysis results and generated graphs to the user, allowing the user to understand at a glance the increase or decrease in foot traffic and the effectiveness of attracting customers. Furthermore, the server generates specific action proposals based on the analysis results. These action proposals are customized according to the user's emotional state. For example, if the user shows signs of anxiety, the server will make more reassuring suggestions.

[1098] As a concrete example, the following operation takes place: A local government official inputs a request to "analyze changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan." The system performs data analysis based on this request and visually displays the results. It then makes specific suggestions based on the results, such as "run discount promotions during specific times" or "consider increasing transportation options."

[1099] Examples of prompts include:

[1100] "Please tell us the peak traffic times for last year's Christmas event and use that data to suggest improvements for the next event."

[1101] In this way, the system of the present invention can propose more effective measures by conducting a combined analysis of user emotions and people flow data.

[1102] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1103] Step 1:

[1104] The server collects people flow data from across the country via API. It sends API requests from external data sources and temporarily stores the retrieved data in JSON format. The input is the API endpoint URL, and the output is people flow data in JSON format. Specifically, it sends requests using the Python requests library and receives responses in JSON format.

[1105] Step 2:

[1106] The server cleanses and normalizes the collected data. The input is the JSON data obtained in step 1, and the output is a cleansed and normalized data frame. Specifically, the pandas library is used to detect missing values ​​and outliers and handle them appropriately. In this step, the data format and units are unified.

[1107] Step 3:

[1108] The terminal accepts user requests through a conversational interface. Input is a request that the user types into a text input field, and output is an HTTP request to a server to which the request is sent. Specifically, this includes the user entering a prompt through a UI component in a web application and clicking a button to submit.

[1109] Step 4:

[1110] The server analyzes the user's input text using a natural language processing model. The input is the text data received in step 3, and the output is a command statement containing the analyzed intent and meaning. It also analyzes emotions from the input text using an emotion engine. Specifically, it performs emotion analysis of the text using the TextBlob library and outputs a result that is either positive, negative, or neutral.

[1111] Step 5:

[1112] The server performs data analysis using the generated prompts. The input is the analysis results and cleansed data generated in step 4, and the output is a dataset and graphs containing the analysis results. Specifically, the data is analyzed using KMeans clustering and time series analysis methods, and graphs are created using the matplotlib library.

[1113] Step 6:

[1114] The terminal visually provides the analysis results sent from the server and the generated graphs. The input is the analysis results and graph images generated in Step 5, and the output is visualized data displayed on the user's browser. Specifically, graphs and charts are displayed on the user interface and presented in an intuitive format.

[1115] Step 7:

[1116] The server generates specific policy proposals based on the analysis results. The inputs are the analysis results obtained in step 5 and the emotion data analyzed in step 4, and the output is a customized policy proposal. Specifically, the server generates proposal content that takes into account the user's psychological state based on the emotion analysis results and sends it to the terminal in JSON format.

[1117] Step 8:

[1118] The terminal displays customized action proposals to the user. The input is the action proposal text generated in step 7, and the output is the proposal content displayed on the user's browser. Specifically, the action proposals are displayed in an easy-to-understand format, helping the user plan their next event and make strategic decisions more easily.

[1119] This processing step effectively enables appropriate data analysis and policy proposals based on the user's emotional state.

[1120] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1121] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1122] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1123] [Fourth embodiment]

[1124] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1125] 7, a 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.

[1126] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1127] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1128] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1129] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1131] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1132] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1133] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1135] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1136] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1137] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[1138] Program processing and explanation

[1139] Data collection and preprocessing

[1140] Server: When collecting people flow data, it uses APIs from multiple data sources to obtain data. Specifically, it obtains people flow information for a specified date, time, and area, and stores it in a database. Next, it cleanses and normalizes the data. In other words, it detects missing values ​​and outliers, and properly complements or removes them, and standardizes the data format and units. This prepares the data in a form suitable for analysis.

[1141] User Interface Generation

[1142] Terminal: A display of a web application that can be accessed directly by the user. It provides UI components such as text input fields, selection boxes, and buttons, and is designed to allow users to easily input requests. This interface supports intuitive user interaction.

[1143] Natural Language Analysis and Prompt Generation

[1144] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[1145] Terminal: Sends text data entered by the user to the server.

[1146] Server: Analyzes the received text data using a natural language processing (NLP) model, understanding the user's intent and generating appropriate prompts that identify specific analysis methods and required datasets.

[1147] Data analysis and graph generation

[1148] Server: Based on the prompts, generative AI models are used to analyze the data, for example, using time series analysis and clustering to measure changes in foot traffic before and after the event date. The results are then transformed into dynamic graphs and charts.

[1149] Terminal: The analysis results and graphs received from the server are displayed in an easy-to-understand manner to the user. For example, this includes line graphs showing increases and decreases in foot traffic, and heat maps showing the effectiveness of attracting customers.

[1150] Measure proposals

[1151] Server: Based on the analysis results, specific measures for the next event are generated. For example, recommendations include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. Measure suggestions are written in natural language and presented to users in a format that they can intuitively understand.

[1152] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[1153] Specific examples

[1154] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. In this case, the user obtains information through the following operations:

[1155] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[1156] 2. Terminal: Sends the input request to the server.

[1157] 3. Server: Performs natural language analysis, identifies appropriate data and analytical methods, and generates prompts.

[1158] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[1159] 5. Terminal: Displays the analysis results and action proposals to the user.

[1160] 6. User: Use the information provided to plan your next event.

[1161] In this way, this system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective implementation of measures.

[1162] The processing flow will be explained below.

[1163] Step 1:

[1164] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends requests to API endpoints and receives data in JSON format. Temporarily stores the received data.

[1165] Step 2:

[1166] Server: Cleanses the collected data. Specifically, it complements missing values, removes outliers, and corrects values. For example, it detects null values ​​and extremely outlying values ​​and replaces them with appropriate values. It also performs normalization to unify data formats and units.

[1167] Step 3:

[1168] Server: Stores the cleansed data in a database so that it can be efficiently accessed for subsequent analysis steps.

[1169] Step 4:

[1170] Terminal: Provides web applications that present an intuitive interface to users, including UI components such as text input fields, selection boxes, and buttons.

[1171] Step 5:

[1172] User: Enters a specific request into the interface. For example, the user enters a request such as, "I would like you to analyze the changes in the flow of people on the day of last year's tourist event and provide suggestions for planning the next one" into the text input field.

[1173] Step 6:

[1174] Terminal: Sends the request entered by the user to the server. The text data is included in the request payload and sent to the server.

[1175] Step 7:

[1176] Server: Analyzes the user request using a natural language processing (NLP) model, tokenizes the request text, understands the user's intent, generates appropriate prompts, and identifies the required dataset and analysis techniques.

[1177] Step 8:

[1178] Server: Using the generated prompts, the server begins analyzing the people flow data. Specifically, it performs time series analysis to detect changes in people flow before and after the event. It also uses clustering techniques to classify people flow patterns.

[1179] Step 9:

[1180] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[1181] Step 10:

[1182] Terminal: Displays the analysis results and graphs received from the server to the user, presenting the results in a format that is easy for the user to understand and allowing them to interpret the data visually.

[1183] Step 11:

[1184] Server: Based on the analysis results, the server generates specific action plans for the next event. These plans include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The generated proposals are written in natural language.

[1185] Step 12:

[1186] Terminal: The generated policy proposals are displayed to the user, who can then review the proposals and use them as a reference for formulating an implementation plan.

[1187] Step 13:

[1188] Users: Give feedback on the information and suggestions provided by filling out and submitting a form in the interface.

[1189] Step 14:

[1190] Server: Receives user feedback and reflects it in improvements to the AI ​​model and UI, thereby continuously improving the accuracy and usability of the system.

[1191] Example 1

[1192] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1193] With conventional technology, there was no consistent system that could efficiently collect nationwide people flow data, cleanse and normalize it, and then perform specific data analysis and policy proposals according to the user's intentions.Therefore, there is a need for a system that can perform everything from data collection to analysis and policy proposals all at once, through an interface that even non-experts can use easily.

[1194] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1195] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating prompts using a generative AI model, and means for integrating the processing results of each means and providing an interactive interface that can be intuitively operated by users. This enables users without specialized knowledge to easily perform tasks from data collection to analysis and policy proposals through intuitive operations.

[1196] "People flow data" is information about the movements and gatherings of people in specific areas and at specific times.

[1197] "Cleansing" is the process of detecting missing or outliers in data and then filling or removing them appropriately.

[1198] "Normalization" is the process of standardizing and making consistent the format and units of data.

[1199] "Natural language analysis" is a technology that analyzes text written in human language into a form that can be understood by machines, and extracts intent and meaning.

[1200] "Prompt" refers to specific instructions or questions for data analysis or graph generation.

[1201] An "interactive interface" is a user interface that allows a user to intuitively interact with a system, and typically includes UI components such as text input fields, selection boxes, and buttons.

[1202] A "generative AI model" is an algorithm or computational model that leverages artificial intelligence techniques to automate specific tasks (e.g., natural language processing, data analysis).

[1203] This invention is a system that performs everything from data analysis based on nationwide people flow data to policy proposals. It mainly involves three entities: "server," "terminal," and "user."

[1204] Data collection and preprocessing

[1205] Server: When collecting people flow data, APIs from multiple data sources are used to obtain data. Specifically, external data sources such as Google Maps API and social media APIs are used. The collected data is stored in a database. Next, during the data cleansing process, missing values ​​and outliers are detected and appropriate processing is performed, such as filling in the average value. The data is then normalized to unify the format and units.

[1206] User Interface Generation

[1207] Terminal: A web application is provided that can be accessed directly by the user. This application works with data provided by the server and displays UI components such as text input fields, selection boxes, and buttons. It is designed to be intuitive for the user, allowing them to easily input requests.

[1208] Natural Language Analysis and Prompt Generation

[1209] User: For example, enter text such as, "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[1210] Terminal: Sends text data entered by the user to the server.

[1211] Server: Analyzes the received text data using a natural language processing model. Specifically, it uses generative AI models such as BERT and GPT-3 to understand the user's intent and generate appropriate prompts. The prompts are instructions that specify the specific analysis method and required dataset.

[1212] Data analysis and graph generation

[1213] Server: Based on generated prompts, data for a specified time period and region is filtered from the database. Generative AI models are then used to analyze the data. For example, time series analysis is used to measure changes in foot traffic before and after an event, and clustering techniques are used to find specific patterns and trends. The results of the analysis are then converted into dynamic graphs and charts using tools such as Python's Matplotlib and D3.js.

[1214] Measure proposals

[1215] Server: Based on the results of the data analysis, the server generates specific measures for the next event. For example, it proposes measures such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. These measures are written in natural language and presented to users in a format that they can intuitively understand.

[1216] Terminal: The proposed measures are displayed to the user, who then checks the proposal and makes the necessary decisions.

[1217] Specific examples

[1218] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day a specific event is held. The information can be obtained through the following operations:

[1219] 1. User: Opens the web application and enters a request in the text input field: "I would like you to analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[1220] 2. Terminal: Sends the input request to the server.

[1221] 3. Server: Performs natural language analysis, identifies the required data and analysis methods, and generates prompts.

[1222] 4. Server: Analyzes data, generates graphs and charts based on the results, and creates policy proposals.

[1223] 5. Terminal: Displays the analysis results and action proposals to the user.

[1224] 6. User: Use the information provided to plan your next event.

[1225] This system allows users without specialized know-how to easily analyze data and plan measures, which is expected to enable strategic decision-making based on data and lead to more effective measures.

[1226] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1227] Step 1:

[1228] Data collection

[1229] Server: Uses APIs to collect people flow data for specified dates, times, and regions from multiple data sources. Specifically, it uses Google Maps API and social media APIs to obtain real-time people flow data.

[1230] Input: Specified date and time, region, and API connection information.

[1231] Data processing and calculation: Data from multiple sources is integrated, converted into a single format, and stored in a database.

[1232] Output: Integrated people flow data.

[1233] Step 2:

[1234] Data Cleansing and Normalization

[1235] Server: Cleanses the collected data. Specifically, it detects and fills in missing values ​​and removes outliers. For example, if there are many missing values, it fills in the average value, and if there are clearly abnormal values, it removes them. After that, it standardizes the data format and units.

[1236] Input: Integrated people flow data.

[1237] Data processing and calculation: Completion of missing values, removal of outliers, and standardization of data format and units are carried out.

[1238] Output: Cleansed and normalized people flow data.

[1239] Step 3:

[1240] User Interface Generation

[1241] Terminal: Provides a web application that users can access, including UI components such as text inputs, select boxes, and buttons that allow users to intuitively input requests.

[1242] Input: UI design information, cleansed and normalized data.

[1243] Data processing and computation: Web page and UI component generation.

[1244] Output: A web application where users can enter their requests.

[1245] Step 4:

[1246] Receiving requests from users

[1247] User: Enter a request such as, "I would like you to analyze the changes in the flow of people on the days when tourist events were held last year and make suggestions for planning the next one."

[1248] Input: Text request.

[1249] Data processing and calculation: Sending the text request content to the server.

[1250] Output: The request data.

[1251] Step 5:

[1252] Natural Language Analysis and Prompt Generation

[1253] Server: Analyzes the received text data using a natural language processing model to understand the user's intent. Specifically, it uses BERT or GPT-3 to extract appropriate keywords and actions. Next, it generates a prompt based on the analysis results.

[1254] Input: Request data.

[1255] Data processing and calculation: text analysis, keyword extraction, prompt generation.

[1256] Output: The generated prompt.

[1257] Step 6:

[1258] Data analysis and graph generation

[1259] Server: Filters data from the database for the specified time period and region based on generated prompts, then performs time series analysis and clustering using generative AI models, and converts the analysis results into dynamic graphs and charts using Python's Matplotlib and D3.js.

[1260] Input: Generated prompts, cleansed and normalized data.

[1261] Data processing and calculations: data filtering, time series analysis, clustering, graph generation.

[1262] Output: Graphs and charts of the analysis results.

[1263] Step 7:

[1264] Generate policy proposals

[1265] Server: Based on the analysis results, the server generates specific measures for the next event, such as reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposed measures are written in natural language and presented to users in a format that is easy to understand.

[1266] Input: Graphs and charts of analytical results.

[1267] Data processing and calculation: Generation of policy proposals and descriptions in natural language.

[1268] Output: Policy proposal document.

[1269] Step 8:

[1270] Display of results and action recommendations

[1271] Terminal: The analysis results and action proposals received from the server are displayed to the user, who can then use them to plan their next event.

[1272] Input: Policy proposal documents, graphs and charts of analysis results.

[1273] Data processing and calculation: Web display of results and policy proposals.

[1274] Output: Provides information to the user.

[1275] (Application example 1)

[1276] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1277] In modern society, there is a need to effectively analyze large amounts of people flow data and quickly propose strategic measures based on that data. However, conventional systems have difficulty preprocessing and analyzing data, and making specific proposals based on user requests. This makes it difficult to develop efficient advertising strategies, particularly in the advertising field. To address this issue, there is a need for a system that can consistently perform data collection, analysis, and proposals, and visualize them in an easy-to-understand manner.

[1278] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1279] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for performing data analysis and graph generation using generated prompts, means for generating policy proposals based on the analysis results, means for generating information to optimize advertising policies based on the collected data, means for visualizing people flow data for a specified period and providing it to the user, and means for providing specific proposals based on prompt sentences using a generative AI model. This makes it possible to efficiently analyze large amounts of people flow data and optimize advertising policies and propose specific strategies.

[1280] "People flow data" is data that records information on people's movements and stays in specific areas and periods of time.

[1281] "Cleansing" refers to the process of detecting missing or outliers in data and then filling or removing them.

[1282] "Normalization" refers to the process of standardizing the format and units of data and preparing it in a form suitable for analysis.

[1283] "Natural language analysis" is a technology that analyzes text data entered by a user and understands its intent and meaning.

[1284] A "prompt" is an input that generates a specific instruction or question and analyzes data accordingly.

[1285] A "generative AI model" is a model that uses artificial intelligence technology to generate appropriate responses or results for specific inputs.

[1286] "Data analysis" is the process of analyzing collected data using statistical or computational methods.

[1287] "Graph generation" refers to the process of creating graphs or charts to visually represent analytical results.

[1288] "Policy proposal" refers to proposing specific strategies and measures to be implemented next time based on the results of data analysis.

[1289] "Visualization" refers to a method of displaying data or information visually in an easy-to-understand manner.

[1290] In this invention, three parties are involved in realizing a system for advertising optimization: a server, a terminal, and a user. How this system works will be explained in detail below.

[1291] 1. Server Role

[1292] The server is responsible for the following processes:

[1293] Collection of people flow data: People flow data for specific regions and periods is obtained through APIs and stored in a database. The use of APIs is important for collecting data from various data sources.

[1294] Data cleansing and normalization: Detecting missing or outliers from collected data, and then filling or removing them, as well as standardizing the data format and units.

[1295] Natural Language Analysis: Receives the request text from the user and analyzes it using natural language processing technology to understand the user's intent and generate appropriate prompts.

[1296] Prompt generation and data analysis: Based on the generated prompts, a generative AI model is used to perform data analysis, including time series analysis and clustering.

[1297] Graph generation and action recommendations: Convert analysis results into dynamic graphs and charts and automatically generate action recommendations.

[1298] 2. Role of the terminal

[1299] The terminal is responsible for the following processes:

[1300] Providing a user interface: Provide a web application where users can enter requests. The interface includes UI components such as text input fields, select boxes, and buttons.

[1301] Request transmission and data display: The request entered by the user is sent to the server, and the analysis results and action proposals returned by the server are displayed. Display formats include line graphs and heat maps.

[1302] 3. User Roles

[1303] The user performs the following process:

[1304] Text input: For example, a request such as "Please suggest our next advertising strategy based on the foot traffic data from last year's campaign period" is entered into the device interface.

[1305] Reviewing the results and making decisions: Review the data analysis results and action proposals provided by the server, and plan the next advertising strategy based on them.

[1306] Hardware and software used

[1307] Hardware: User's smartphone and cloud server

[1308] Software: Python, open-source libraries (Pandas, Requests, Matplotlib), generative AI models (e.g., GPT-3)

[1309] Specific examples

[1310] When an advertising officer at a local government analyzes changes in foot traffic on the day of a specific event and plans the next advertising strategy based on that analysis, he or she uses the system in the following steps.

[1311] 1. User: Opens the smartphone app and enters a request: "Please suggest my next advertising strategy based on foot traffic data from last year's campaign period."

[1312] 2. Terminal: Sends the input request to the server.

[1313] 3. Server: Collects people flow data using APIs, cleansing and normalizing it, then performs natural language analysis to generate appropriate prompts.

[1314] 4. Server: Based on the generated prompts, a generative AI model is used to analyze the data and visualize the results, for example generating line graphs or heat maps.

[1315] 5. Server: Based on the results of the data analysis, generate proposals for the next advertising campaign and describe them in natural language.

[1316] 6. Terminal: Displays the generated analysis results and action proposals to the user.

[1317] 7. User: Plan your next advertising strategy based on the information displayed.

[1318] Prompt Sentence Examples

[1319] "I would like you to propose our next advertising strategy based on the foot traffic data from last year's campaign period."

[1320] In this way, by using the system of the present invention, advertising personnel can receive effective data analysis and strategic measures proposals.

[1321] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1322] Step 1:

[1323] The server uses API to collect people flow data for a specific area and period. The input is a request specifying the area and period, and the output is people flow data based on the specified conditions. The collected data is stored in a database.

[1324] Step 2:

[1325] The server cleanses and normalizes the collected people flow data. The input is the collected people flow data, and the output is the cleansed and normalized data. Specifically, it detects and completes missing and outlier values, and standardizes data formats and units.

[1326] Step 3:

[1327] The server receives the request text entered by the user on the terminal and performs natural language analysis. The input is the request text entered by the user, and the output is the analyzed user's intent. Specifically, NLP technology is used to understand the meaning and intent of the request text.

[1328] Step 4:

[1329] The server generates a prompt based on the natural language analysis results. The input is the analysis results including the user's intent, and the output is the generated prompt. The prompt is a specific instruction for data analysis.

[1330] Step 5:

[1331] The server performs data analysis based on the generated prompts. The input is the cleansed and normalized people flow data and the prompts, and the output is the analysis results. Specifically, it uses techniques such as time series analysis and clustering to analyze changes and patterns in people flow.

[1332] Step 6:

[1333] The server generates graphs and charts based on the results of the data analysis. The input is the data analysis results, and the output is visualized graphs and charts. Specifically, it uses tools such as Matplotlib to create line graphs, heat maps, and so on.

[1334] Step 7:

[1335] The server generates policy proposals based on the analysis results. The input is the data analysis results, including visualized graphs and charts, and the output is policy proposals. Specifically, a generative AI model is used to generate specific policy proposals in natural language.

[1336] Step 8:

[1337] The terminal displays the analysis results and proposed measures received from the server to the user. The input is the analysis results and proposed measures from the server, and the output is a visual display to the user. The user plans their next advertising strategy based on the displayed information.

[1338] As a concrete example, if a user inputs, "Please suggest my next advertising campaign based on the foot traffic data from last year's campaign period," the server will analyze this request, collect and analyze foot traffic data for the specified period, generate specific advertising campaign proposals based on that data, and provide them to the user via their device.

[1339] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1340] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[1341] Program processing and explanation

[1342] Data collection and preprocessing

[1343] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Sends API requests and temporarily stores the retrieved data in JSON format. Next, cleanses and normalizes the data, properly handles missing values ​​and outliers, and standardizes the data format and units.

[1344] User Interface Generation

[1345] Terminal: Displays a web application that provides an intuitive interface to the user, including UI components such as text input fields, selection boxes, and buttons, designed to allow the user to easily input requests.

[1346] Natural Language Analysis and Emotion Recognition

[1347] User: For example, enter a request such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one" in the text input field.

[1348] Terminal: Sends user input to the server.

[1349] Server: Analyzes the received text data using a natural language processing (NLP) model to understand the user's intent. At the same time, it uses an emotion engine to analyze the emotions from the user's input. Based on the results of this emotion analysis, it generates more appropriate prompts.

[1350] Data analysis and graph generation

[1351] Server: Performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in pedestrian flow before and after the event. It creates dynamic graphs and charts based on the generated analysis results.

[1352] Terminal: Visually displays the analysis results and graphs received from the server, including line graphs showing increases and decreases in foot traffic and heat maps visualizing the effectiveness of attracting customers.

[1353] Policy proposals and emotional responses

[1354] Server: Generates specific action proposals based on the analysis results. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. They are customized based on the user's emotional state. For example, if the user shows signs of anxiety, they will receive more reassuring proposals.

[1355] Device: Displays customized action proposals to users, who can then review the proposals and make decisions, such as planning their next event.

[1356] Specific examples

[1357] For example, suppose a local government official (user) wants to analyze changes in the flow of people on the day of a specific event and plan for the next event. In this case, the following operations are performed.

[1358] 1. User: Opens the web application and enters a request to "analyze changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[1359] 2. Terminal: Sends the input request to the server.

[1360] 3. Server: Performs natural language analysis to understand the intent of the user's request. In parallel, it uses an emotion engine to analyze emotions from the user's input.

[1361] 4. Server: Generates appropriate prompts and starts analyzing people flow data, cleansing and normalizing the data, and generating graphs and charts based on the analysis results.

[1362] 5. Terminal: Displays the generated analysis results and graphs to the user.

[1363] 6. Server: Generates specific action proposals based on the analysis results and adjusts the proposals according to the user's emotions.

[1364] 7. Terminal: The customized action proposal is displayed to the user, who can then accept the proposal and plan their next event.

[1365] In this way, this system easily supports data analysis and policy planning while taking into account the user's emotions, allowing users to make more effective strategic decisions.

[1366] The processing flow will be explained below.

[1367] Step 1:

[1368] Server: Collects people flow data from the National Movement Statistics Data API and other external data sources. Specifically, it sends a request to the API endpoint and obtains people flow data for the required area and period in JSON format. The obtained data is temporarily stored in a database.

[1369] Step 2:

[1370] Server: Cleanses the collected data by imputing missing values ​​and filtering or correcting outliers. For example, it detects null values ​​and inappropriate data and replaces them with appropriate values ​​using imputation algorithms. It also normalizes the data format and units to make them consistent.

[1371] Step 3:

[1372] Server: The cleansed and normalized data is restored to a database in an optimal format for fast and efficient searching and analysis.

[1373] Step 4:

[1374] Terminal: Launches a web application that displays a user interface, which includes UI components such as text input fields, selection boxes, and buttons.

[1375] Step 5:

[1376] User: In the text input field, enter "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan," and press the send button.

[1377] Step 6:

[1378] Terminal: Collects user input and sends it to the server as an HTTP request, with the payload containing text data containing the user's request.

[1379] Step 7:

[1380] Server: Analyzes the received text data using a natural language processing (NLP) model, tokenizes the text data, analyzes the meaning of the sentences, and generates prompts to understand the user's request.

[1381] Step 8:

[1382] Server: At the same time, it uses an emotion engine to analyze the emotion from the user's input. The emotion engine analyzes the context of the input text and identifies the type of emotion (happiness, surprise, anxiety, etc.).

[1383] Step 9:

[1384] Server: Taking into account the results of sentiment analysis, adjust prompts according to the user's emotions. For example, if the user expresses anxiety, add additional reassuring information.

[1385] Step 10:

[1386] Server: Based on the prompt, the server begins analyzing the people flow data. It uses time series analysis and clustering techniques to measure changes in people flow before and after the event.

[1387] Step 11:

[1388] Server: Generates dynamic graphs and charts based on the analysis results, such as line graphs showing increases and decreases in foot traffic, or heat maps that visualize the effectiveness of attracting visitors during an event.

[1389] Step 12:

[1390] Terminal: Displays the analysis results and graphs received from the server to the user, presenting data in a visually easy-to-understand format.

[1391] Step 13:

[1392] Server: Based on the analysis results, the server generates specific action proposals for the next event. These proposals include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The server also takes into account the results of sentiment analysis and customizes the proposals.

[1393] Step 14:

[1394] Device: The generated action proposals are displayed to the user, who can review the proposals and use them as reference for planning the next event.

[1395] Step 15:

[1396] Users: Provide feedback on the information and suggestions provided. Feedback is entered and submitted via the interface.

[1397] Step 16:

[1398] Server: Receives user feedback and reflects it in improving the AI ​​model and UI, thereby improving the accuracy and usability of the system.

[1399] Example 2

[1400] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1401] Conventional data analysis systems have had difficulty efficiently collecting and analyzing people flow data and providing specific policy proposals to users. They also were unable to provide policy proposals that took user emotions into account. This resulted in a decrease in the accuracy of the analysis results and proposals users received, and insufficient support for decision-making.

[1402] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1403] In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for performing natural language analysis to analyze user requests, means for analyzing user emotions using a sentiment analysis engine, means for performing time series analysis and clustering using the generated prompts, means for generating dynamic graphs and charts based on the analysis results, means for providing the generated analysis results and diagrams to the user, means for generating policy proposals based on the analysis results and customizing the proposal content based on the user's emotions, and means for providing the policy proposals obtained by the above means to the user. This enables efficient collection and analysis of people flow data as well as specific and accurate policy proposals that take user emotions into consideration.

[1404] "People flow data" is statistical data on the movement and gathering of people in a certain area.

[1405] "Cleansing" is a process of removing noise and missing values ​​from collected data to improve the quality of the data.

[1406] "Normalization" is the process of converting data into a consistent format and units to facilitate comparison and analysis.

[1407] "Natural language analysis" is the process of analyzing text data using machine learning and artificial intelligence techniques to understand grammar and meaning.

[1408] An "emotion analysis engine" is a software component for analyzing and classifying a user's emotional state from text data.

[1409] A "prompt" is an analytical instruction or command that is generated based on user input.

[1410] "Time series analysis" is a method for analyzing fluctuations in data over time to make predictions and recognize patterns.

[1411] "Clustering" is a technique for classifying data into groups with high similarity and finding patterns and structures.

[1412] "Dynamic graphs and charts" are dynamic diagrams for displaying interactive visualizations of data.

[1413] "Policy proposals" involve presenting specific action plans and improvement measures based on the results of data analysis.

[1414] An "interactive interface" is an interface that includes input and output items that can be intuitively operated by a user.

[1415] This invention combines a system that performs everything from data analysis based on nationwide people flow data to policy proposals with an emotion engine that recognizes user emotions. Three main entities are involved: the server, the terminal, and the user.

[1416] Data collection and preprocessing

[1417] Server: This system collects people flow data from the National Movement Statistics Data API and other external data sources. It uses the Python requests library for collection. The acquired JSON-formatted data is temporarily stored, and the Pandas library is used to cleanse and normalize the data. Missing values ​​and outliers are handled appropriately, and the data format and units are standardized.

[1418] User Interface Generation

[1419] Terminal: A web application is displayed that provides the user with an intuitive interface. This interface is built using the JavaScript React.js framework. The user can easily enter requests using text input fields, select boxes, and buttons.

[1420] Natural Language Analysis and Emotion Recognition

[1421] User: For example, enter a request in the text input field, such as "I would like you to analyze the changes in foot traffic on the days of last year's tourist event and provide suggestions for planning the next one."

[1422] Terminal: User input is sent to the server in real time using AJAX requests.

[1423] Server: Analyzes the received text data using Python's natural language processing (NLP) libraries, such as NLTK and SpaCy. Extracts entities and verbs to understand the user's intent. At the same time, analyzes the sentiment of the user's input using a sentiment analysis engine, such as IBM Watson Tone Analyzer. Based on the results of the sentiment analysis, generates more appropriate prompts.

[1424] Data analysis and graph generation

[1425] Server: Based on the generated prompts, the people flow data is analyzed using Python time series analysis libraries (e.g., Prophet) and clustering algorithms (e.g., k-means). Based on the analysis results, dynamic graphs and charts are generated using libraries such as Matplotlib and Seaborn.

[1426] Policy proposals and emotional responses

[1427] Server: Based on the information obtained from the analysis, the server generates specific action proposals. These proposals may include reviewing advertising strategies, increasing transportation options, and identifying areas to attract customers. The proposals are also customized based on the user's emotional state. For example, if the user shows signs of anxiety, the server will make suggestions that will reassure them.

[1428] Terminal: Displays the action proposals received from the server to the user. The analysis results and action proposals are presented in a visually easy-to-understand format.

[1429] Specific examples

[1430] For example, suppose a local government official (user) wants to analyze changes in foot traffic on the day of a specific event and make plans for the next one. In this case, the user opens a web application and enters a request: "Analyze changes in foot traffic on the day of last year's tourism event and make suggestions for the next plan." The device sends this request to the server, which performs natural language analysis and sentiment analysis. The server then begins data analysis based on the generated prompts and generates the results as graphs and charts. Finally, it customizes appropriate policy proposals and provides them to the user. This allows the user to make more effective strategic decisions.

[1431] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1432] Step 1: Data collection and preprocessing

[1433] Server: Sends an HTTP request to the National Movement Statistics Data API to obtain people flow data. The input is the API request URL, and the output is JSON-formatted data. Specifically, the API request is sent using the requests library. The server temporarily stores the obtained JSON data, and then cleanses and normalizes the data using the Pandas library. Specific data processing involves imputing missing values ​​using an appropriate method, removing outliers, and standardizing data formats and units. The output is a cleansed and normalized data frame.

[1434] Step 2: Generate the user interface

[1435] Terminal: Uses the JavaScript React.js framework to generate a web application for the user. The input is the elements necessary for the user interface, and the output is a web page that the user can operate intuitively. Specific operations include creating UI components such as text input fields, selection boxes, and buttons, and arranging them on the screen. The terminal adds event listeners to receive and send user input in real time.

[1436] Step 3: Natural Language Analysis and Emotion Recognition

[1437] User: For example, a user enters a request in the text input field, such as "I want you to analyze the changes in people flow on the day of last year's tourist event and make suggestions for the next plan." The input is the user's text request, and the output is a request to send to the server.

[1438] Terminal: Sends the input text request to the server using an AJAX request. The input is the user's text data, and the output is an HTTP request.

[1439] Server: The received text data is analyzed using Python's natural language processing (NLP) libraries, NLTK and SpaCy. The input is the user's text request, and the output is the analysis results (a list of entities and verbs). Specifically, the text data is tokenized and entities and verbs are extracted. At the same time, the IBM Watson Tone Analyzer is used to analyze the user's emotions. The input is the user's text, and the output is the emotion analysis results. This allows the user's emotional state to be determined and more appropriate prompts to be generated.

[1440] Step 4: Data analysis and graph generation

[1441] Server: Based on the generated prompts, data analysis is performed using Python's time series analysis library (Prophet) and clustering algorithm (k-means). The input is a cleansed and normalized data frame, and the output is the analysis results. Specific operations include predicting trends in time series data and identifying data patterns through clustering. Based on the analysis results, dynamic graphs and charts are generated using the Matplotlib and Seaborn libraries. The output is visualized graphs and charts.

[1442] Step 5: Propose measures and respond to emotions

[1443] Server: Generates specific action proposals based on the analysis results. The inputs are the analysis results and the results of user sentiment analysis, and the output is specific action proposals. Specific operations include evaluating the data analysis results and creating proposals such as revising advertising strategies and identifying areas to attract customers. The proposals are customized according to the user's emotional state.

[1444] Terminal: Visually displays the policy proposals received from the server to the user. The input is the proposal content and graphs from the server, and the output is a screen display that the user can check. Specifically, it displays the analysis results and proposal content in an easy-to-understand manner, helping the user to plan the next action.

[1445] (Application example 2)

[1446] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1447] Conventional analysis systems based on people flow data make uniform policy proposals without considering user emotions, which means they are unable to provide appropriate proposals that address the user's psychological state or specific needs. Furthermore, collected data often contains missing values ​​and outliers, requiring appropriate data cleansing and normalization. Furthermore, there is a lack of systems that can intuitively accept user requests through a conversational interface.

[1448] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting people flow data, means for cleansing and normalizing the collected data, means for analyzing user requests by performing natural language analysis including an emotion engine that analyzes user emotions, means for performing data analysis and graph generation using the generated prompts, and means for generating policy proposals based on the analysis results, providing the generated graphs and policy proposals to the user, and customizing the proposal content based on the user's psychological state. This enables appropriate data analysis and policy proposals according to the user's emotional state.

[1449] "People flow data" is data that shows patterns of people's movements and gatherings in specific areas and time periods.

[1450] "Data cleansing" refers to detecting missing or outliers from collected data and applying appropriate processing.

[1451] "Normalization methods" are methods for converting data with different data formats, units, etc. into a unified format.

[1452] "Natural language analysis" is a technology that analyzes text data entered by users and understands their intent and content.

[1453] The "emotion engine" is a system that analyzes emotions from the text entered by the user and grasps their psychological state.

[1454] A "prompt" is text containing a series of instructions or questions to guide user input or system action.

[1455] "Data analysis" is the process of analyzing collected data using statistical methods and machine learning techniques to derive useful information.

[1456] "Graph generation" refers to the creation of graphs and charts to visually represent the results of data analysis.

[1457] "Policy proposals" involve proposing specific actions and strategies based on the results of the analysis.

[1458] "Customization" means tailoring what is delivered and how it is delivered to the user's specific needs and emotional state.

[1459] An "interactive interface" is an interface in which the system provides appropriate responses and suggestions based on information entered by the user.

[1460] The system of this invention analyzes user requests based on people flow data and combines it with sentiment analysis to enable more appropriate data analysis and policy proposals. Below, we will explain the details of each component of this system and how it works.

[1461] The server collects nationwide people flow data via API. Specifically, it sends API requests from external data sources and temporarily stores the retrieved data in JSON format. It also cleanses and normalizes the data to handle missing values ​​and outliers. This process is performed using the Python pandas library.

[1462] The terminal accepts user requests through a conversational interface. The user enters specific requests into text input fields, which are then sent to the server. The terminal is presented as a web application with UI components such as selection boxes and buttons.

[1463] The server uses a natural language processing model to analyze the user's input text and understand its intent. At the same time, an emotion engine analyzes the emotions from the user's input. Based on the results of this emotion analysis, appropriate prompts are generated and the basis for data analysis is established. NLP technologies used include the TextBlob library.

[1464] The server performs data analysis based on the generated prompts. Specifically, it uses time series analysis and clustering techniques to measure changes in foot traffic during tourism events and specific campaigns. To visually represent the analysis results, it uses the matplotlib library to generate dynamic graphs and charts.

[1465] The device visually displays the analysis results and generated graphs to the user, allowing the user to understand at a glance the increase or decrease in foot traffic and the effectiveness of attracting customers. Furthermore, the server generates specific action proposals based on the analysis results. These action proposals are customized according to the user's emotional state. For example, if the user shows signs of anxiety, the server will make more reassuring suggestions.

[1466] As a concrete example, the following operation takes place: A local government official inputs a request to "analyze changes in foot traffic on the days of last year's tourist event and make suggestions for the next plan." The system performs data analysis based on this request and visually displays the results. It then makes specific suggestions based on the results, such as "run discount promotions during specific times" or "consider increasing transportation options."

[1467] Examples of prompts include:

[1468] "Please tell us the peak traffic times for last year's Christmas event and use that data to suggest improvements for the next event."

[1469] In this way, the system of the present invention can propose more effective measures by conducting a combined analysis of user emotions and people flow data.

[1470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1471] Step 1:

[1472] The server collects people flow data from across the country via API. It sends API requests from external data sources and temporarily stores the retrieved data in JSON format. The input is the API endpoint URL, and the output is people flow data in JSON format. Specifically, it sends requests using the Python requests library and receives responses in JSON format.

[1473] Step 2:

[1474] The server cleanses and normalizes the collected data. The input is the JSON data obtained in step 1, and the output is a cleansed and normalized data frame. Specifically, the pandas library is used to detect missing values ​​and outliers and handle them appropriately. In this step, the data format and units are unified.

[1475] Step 3:

[1476] The terminal accepts user requests through a conversational interface. Input is a request that the user types into a text input field, and output is an HTTP request to a server to which the request is sent. Specifically, this includes the user entering a prompt through a UI component in a web application and clicking a button to submit.

[1477] Step 4:

[1478] The server analyzes the user's input text using a natural language processing model. The input is the text data received in step 3, and the output is a command statement containing the analyzed intent and meaning. It also analyzes emotions from the input text using an emotion engine. Specifically, it performs emotion analysis of the text using the TextBlob library and outputs a result that is either positive, negative, or neutral.

[1479] Step 5:

[1480] The server performs data analysis using the generated prompts. The input is the analysis results and cleansed data generated in step 4, and the output is a dataset and graphs containing the analysis results. Specifically, the data is analyzed using KMeans clustering and time series analysis methods, and graphs are created using the matplotlib library.

[1481] Step 6:

[1482] The terminal visually provides the analysis results sent from the server and the generated graphs. The input is the analysis results and graph images generated in Step 5, and the output is visualized data displayed on the user's browser. Specifically, graphs and charts are displayed on the user interface and presented in an intuitive format.

[1483] Step 7:

[1484] The server generates specific policy proposals based on the analysis results. The inputs are the analysis results obtained in step 5 and the emotion data analyzed in step 4, and the output is a customized policy proposal. Specifically, the server generates proposal content that takes into account the user's psychological state based on the emotion analysis results and sends it to the terminal in JSON format.

[1485] Step 8:

[1486] The terminal displays customized action proposals to the user. The input is the action proposal text generated in step 7, and the output is the proposal content displayed on the user's browser. Specifically, the action proposals are displayed in an easy-to-understand format, helping the user plan their next event and make strategic decisions more easily.

[1487] This processing step effectively enables appropriate data analysis and policy proposals based on the user's emotional state.

[1488] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1489] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1490] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1491] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1492] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1493] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1494] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1495] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1496] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1497] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1498] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1499] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1500] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1501] 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.

[1502] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1503] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1504] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1505] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1506] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1507] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1508] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1509] The following is further disclosed regarding the above embodiment.

[1510] (Claim 1)

[1511] a means of collecting people flow data;

[1512] A means of cleansing and normalizing the collected data;

[1513] A means of analyzing user requests through natural language analysis;

[1514] a means for performing data analysis and graph generation using the generated prompts;

[1515] A means for generating policy proposals based on the analysis results;

[1516] A means for providing users with the analysis results and policy proposals obtained by the above means;

[1517] A system including:

[1518] (Claim 2)

[1519] 2. The system according to claim 1, further comprising means for detecting missing values ​​and outliers from the collected data and performing appropriate processing.

[1520] (Claim 3)

[1521] 10. The system of claim 1, further comprising means for accepting user requests through an interactive interface.

[1522] "Example 1"

[1523] (Claim 1)

[1524] a means of collecting people flow data;

[1525] A means of cleansing and normalizing the collected data;

[1526] A means of analyzing user requests through natural language analysis;

[1527] a means for performing data analysis and graph generation using the generated prompts;

[1528] A means for generating policy proposals based on the analysis results;

[1529] A means for providing users with the analysis results and policy proposals obtained by the above means;

[1530] means for generating prompts using a generative AI model;

[1531] A means for integrating the processing results of each means and providing an interactive interface that users can intuitively operate;

[1532] A system including:

[1533] (Claim 2)

[1534] 2. The system according to claim 1, further comprising means for detecting missing values ​​and outliers from the collected data and performing appropriate processing.

[1535] (Claim 3)

[1536] 10. The system of claim 1, further comprising means for accepting user requests through an interactive interface.

[1537] "Application Example 1"

[1538] (Claim 1)

[1539] a means of collecting people flow data;

[1540] A means of cleansing and normalizing the collected data;

[1541] A means of analyzing user requests through natural language analysis;

[1542] a means for performing data analysis and graph generation using the generated prompts;

[1543] A means for generating policy proposals based on the analysis results;

[1544] A means for providing users with the analysis results and policy proposals obtained by the above means;

[1545] A means for generating information that optimizes advertising measures based on collected data;

[1546] A means to visualize people flow data for a specified period and provide it to users,

[1547] a means for using a generative AI model to provide specific suggestions based on the prompt; and

[1548] A system including:

[1549] (Claim 2)

[1550] 2. The system according to claim 1, further comprising means for detecting missing values ​​and outliers from the collected data and performing appropriate processing.

[1551] (Claim 3)

[1552] 10. The system of claim 1, further comprising means for accepting user requests through an interactive interface.

[1553] "Example 2: Combining Emotion Engines"

[1554] (Claim 1)

[1555] a means of collecting people flow data;

[1556] A means of cleansing and normalizing the collected data;

[1557] A means of analyzing user requests through natural language analysis;

[1558] A means for analyzing user emotions using an emotion analysis engine;

[1559] A means of conducting time series analysis and clustering using the generated prompts;

[1560] A means to generate dynamic graphs and charts based on the analysis results,

[1561] a means for providing the generated analysis results and charts to the user;

[1562] A means for generating policy proposals based on the analysis results and customizing the proposals based on user sentiment;

[1563] A means for providing users with the policy proposals obtained by the above means;

[1564] A system including:

[1565] (Claim 2)

[1566] 2. The system according to claim 1, further comprising means for detecting missing values ​​and outliers from the collected data and performing appropriate processing.

[1567] (Claim 3)

[1568] 10. The system of claim 1, further comprising means for accepting user requests through an interactive interface.

[1569] "Application example 2 when combining emotion engines"

[1570] (Claim 1)

[1571] a means of collecting people flow data;

[1572] A means of cleansing and normalizing the collected data;

[1573] a means for analyzing a user's request by performing natural language analysis, including an emotion engine for analyzing the user's emotion;

[1574] means for performing data analysis and graph generation using the generated prompts;

[1575] A means for generating policy proposals based on the analysis results;

[1576] A means for providing the generated graphs and policy proposals to the user and customizing the proposals based on the user's psychological state;

[1577] A system including:

[1578] (Claim 2)

[1579] 2. The system according to claim 1, further comprising means for detecting missing values ​​and outliers from the collected data and performing appropriate processing.

[1580] (Claim 3)

[1581] 10. The system of claim 1, further comprising means for accepting user requests through an interactive interface. [Explanation of symbols]

[1582] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting people flow data; A means of cleansing and normalizing the collected data; A means of analyzing user requests through natural language analysis; a means for performing data analysis and graph generation using the generated prompts; A means for generating policy proposals based on the analysis results; A means for providing users with the analysis results and policy proposals obtained by the above means; A system including:

2. 2. The system according to claim 1, further comprising means for detecting missing values ​​and abnormal values ​​from the collected data and performing appropriate processing.

3. 10. The system of claim 1, further comprising means for accepting user requests through an interactive interface.

Images