system

Abstract

We provide the system. [Solution] Means for obtaining nationwide mobility data, A means for anonymizing and processing missing values ​​in the acquired movement data, A means for analyzing pre-processed movement data and generating statistical information, A means of generating graphs and charts to visualize the generated statistical information, A means of automatically generating policy proposals based on analyzed statistical information, A means of presenting proposed measures to users and receiving feedback from them, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When dealing with nationwide movement data, advanced expertise and complex procedures are required, and there is a problem that many users cannot fully utilize this data. As a result, the potential value of the data cannot be extracted, and it is difficult to formulate effective measures. Furthermore, there is a lack of a mechanism that simultaneously satisfies privacy protection, data analysis efficiency, and user-friendly operability.

Means for Solving the Problems

[0005] This invention provides a system for efficiently collecting, anonymizing, and preprocessing nationwide mobility data. Furthermore, it utilizes artificial intelligence to analyze the preprocessed data and automatically generates statistical information. The generated information is visually represented and presented in a format that users can intuitively understand. In addition, it has a function to automatically generate policy proposals based on the analysis results, and continuously optimizes analysis by sequentially improving the analysis algorithm based on user feedback. This creates an environment where even users without expertise in data analysis can obtain useful insights.

[0006] "Mobility data" refers to data that shows people's geographical movement patterns and stay information during specific time periods.

[0007] "Anonymization" is a procedure that protects privacy by removing or transforming personally identifiable information during data processing.

[0008] "Preprocessing" refers to the process of preparing raw data to be analyzable, such as imputing missing values ​​and correcting outliers.

[0009] "Analysis" is the process of processing data using statistical or computational means, with the aim of understanding, interpreting, and evaluating the data.

[0010] Artificial intelligence is a technology that enables computer systems to perform intellectual tasks similar to those of humans, and is used for data analysis and pattern recognition.

[0011] "Statistical information" refers to probabilistic or quantitative information obtained by aggregating and analyzing data, and is a numerical value that shows a particular trend or characteristic.

[0012] "Visualization" refers to representing data and its analysis results in a visual form, such as graphs and charts, to make them easier to understand.

[0013] A "proposal" refers to a specific action plan or strategic proposal based on the analysis results.

[0014] "Feedback" refers to the process by which users provide opinions about the system's functions and results, and the system is improved based on that feedback.

[0015] "Sequential improvement" means continuously monitoring systems and processes and incorporating feedback to gradually improve performance. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention provides a data analysis system that effectively utilizes nationwide mobility data. The system processes data through automated processes at each stage, ultimately providing insights for the user. Its specific form is described below.

[0038] Data collection

[0039] The server periodically collects movement data for the target area. This data includes the number of visitors to each area, their length of stay, and their movement patterns.

[0040] Data preprocessing

[0041] The server anonymizes the collected data to ensure the protection of personal information. Furthermore, it automatically handles the imputation of missing values ​​and the identification and correction of outliers, thereby improving data consistency and reliability.

[0042] Data Analysis

[0043] The server sends the pre-processed dataset to the artificial intelligence for statistical analysis. This involves trend analysis of movement patterns and modeling fluctuations in visitor numbers related to specific factors.

[0044] visualization

[0045] Based on statistical information generated by the server, the system automatically generates graphs and charts that are easy to understand visually. These visuals can, for example, show fluctuations in past visitor numbers using line graphs, or indicate the popularity of specific regions using heatmaps.

[0046] Proposal and User Interaction

[0047] The device provides users with generated graphs and charts as dashboards. Through interactive operations, users can explore the data in depth and access detailed analysis results based on specific conditions.

[0048] The generating AI automatically proposes policy options based on the analysis results and presents them to the user via the device. Users can evaluate these policy options and provide feedback, thereby contributing to improving the accuracy of the analysis.

[0049] Specific example

[0050] Tourism businesses can use this system to visualize seasonal visitor trends in their area. For example, if visitor numbers are increasing in the spring, the artificial intelligence will analyze the cause and identify that an increase in spring events is a contributing factor. Based on this, it will suggest a new spring campaign. Users can review the suggestions and decide whether to incorporate them into their marketing strategy.

[0051] Thus, this invention provides a comprehensive system that enables users to effectively utilize data and support decision-making, even without specialized knowledge.

[0052] The following describes the processing flow.

[0053] Step 1:

[0054] The server connects to a nationwide mobility database to retrieve the latest mobility data. This data includes attributes such as location, time, number of visitors, and length of stay.

[0055] Step 2:

[0056] The server anonymizes the acquired data. It removes personally identifiable identifiers and transforms the data to meet data security standards.

[0057] Step 3:

[0058] The server performs data preprocessing. If there are missing values, it uses a specific algorithm to impute them, and if outliers are detected, it corrects or removes them to prepare a clean dataset.

[0059] Step 4:

[0060] The server sends clean data to an artificial intelligence module, which then begins data analysis. Here, statistical models are applied to analyze, for example, movement patterns by time of day or region.

[0061] Step 5:

[0062] Generative AI generates statistical information based on analysis results, identifying correlations and trends in the data. For example, it can find a tendency for the number of visitors to increase during a certain period when a specific event is occurring.

[0063] Step 6:

[0064] The server generates graphs and charts to visualize the analysis results. These include line graphs, bar graphs, and heatmaps.

[0065] Step 7:

[0066] The device displays generated graphs and charts on the dashboard, allowing users to interactively explore the data. Users can use this to view data details and delve deeper into areas of interest.

[0067] Step 8:

[0068] The AI ​​generates policy proposals automatically based on the analysis results and presents them to the user via the device. For example, it may suggest the timing of promotions for specific products or plan new events.

[0069] Step 9:

[0070] Users review the proposed measures and provide feedback, including their opinions and evaluations. This feedback is recorded by the server and used to improve the analysis algorithms.

[0071] Step 10:

[0072] The server analyzes user feedback and incorporates it into subsequent analysis processes. This enables continuously improving data analysis accuracy.

[0073] (Example 1)

[0074] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0075] A major challenge is the lack of a data analysis system capable of effectively acquiring nationwide mobility information and analyzing it to provide actionable insights. Currently, anonymization of collected data, handling of missing values, multidimensional analysis of data, visualization, and proposal of policy based on analysis results are often performed manually, which is labor-intensive and time-consuming. Furthermore, there is no established method for quickly incorporating user feedback into the system, making it difficult to improve the accuracy of the analysis.

[0076] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0077] In this invention, the server includes means for acquiring movement information from a wide range of locations, means for anonymizing the acquired movement information and processing missing and outlier values, and means for analyzing the pre-processed movement information to generate statistical information. This enables the automation of advanced data analysis and provides practical insights quickly and efficiently.

[0078] "Mobility information" refers to data about the movement of people and goods within a geographical area, and typically includes visitor numbers, length of stay, and movement patterns.

[0079] "Anonymization" is a process that protects privacy by removing or concealing information that could identify a specific individual.

[0080] "Missing values" refer to a state in a dataset where data that should be present is absent, and processing is required to fill in these missing parts.

[0081] An "outlier" is a value that differs significantly from other data points within a dataset, and this can hinder the consistency and interpretation of the data.

[0082] "Statistical information" refers to numerical or graphical results obtained through data analysis, which indicate trends and characteristics of the data.

[0083] "Visualization" is a technique that represents analyzed data as diagrams or graphs to make it easier to understand visually.

[0084] A "draft plan" refers to action guidelines or proposals generated based on data analysis results, and may include specific implementation plans.

[0085] "Artificial intelligence" refers to systems and programs that mimic human cognitive functions, and particularly includes technologies such as machine learning and natural language processing.

[0086] "Arithmetic operations" refer to basic calculations performed on numerical data, including addition, subtraction, multiplication, division, and statistical calculations.

[0087] A "display device" is a device used to visually display data and images, and provides information through a user interface.

[0088] This invention is a data analysis system that effectively analyzes nationwide mobility information and provides practical insights. The following hardware and software are used in implementing this system.

[0089] Data acquisition and preprocessing

[0090] The server retrieves movement information from government agencies and the private sector via API calls over the internet. The database used is a relational database designed to efficiently store a wide range of geographic data. Data anonymization is performed by filtering out personally identifiable information, and the Python Pandas library is used to handle missing or outlier values.

[0091] Data Analysis

[0092] The server analyzes the preprocessed data through an artificial intelligence engine, such as TENSORFLOW® or scikit-learn. Machine learning algorithms perform statistical analysis to extract trends and factors from the dataset. This builds a model based on visitor behavior.

[0093] Visualization and proposal

[0094] The server generates graphs and charts using Matplotlib and Seaborn libraries based on the analysis results. This visual data is integrated into a dashboard accessible to the user via their device, allowing for interactive operation. The generated AI model formulates policy proposals from the analysis results and provides them to the user as prompts.

[0095] To give a concrete example, if a tourism business uses this system, they can visualize the seasonal trends in visitor numbers in a specific region. Based on these results, the generating AI model performs an analysis using a prompt message such as, "Analyze the increasing trend in visitor numbers during the spring season, and propose causes and countermeasures," and provides practical countermeasure proposals.

[0096] In this way, the system helps users gain valuable business insights even without specialized knowledge.

[0097] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0098] Step 1:

[0099] The server retrieves movement information from public institutions and private data providers via APIs. The data received as input includes visitor numbers, dwell time, and movement patterns. The server stores this data in a relational database and compiles it into aggregated movement information. This aggregated data forms the basis for the next processing steps.

[0100] Step 2:

[0101] The server performs anonymization on the movement information aggregated in Step 1. The input is the data stored in Step 1, and the output is anonymized data from which personally identifiable information has been removed. Specifically, this involves removing fields that identify individual visitors and reorganizing information into aggregate units. This ensures that a dataset suitable for analysis is obtained while protecting privacy.

[0102] Step 3:

[0103] The server processes missing and outlier values ​​in the anonymized data resulting from Step 2. It uses the anonymized data from Step 2 as input and outputs clean, consistent data. The server uses the Python Pandas library to impute missing values ​​with the mean or median and filters out outliers. This data cleansing allows for smoother execution of the next analysis step.

[0104] Step 4:

[0105] The server passes the clean data obtained in step 3 to the artificial intelligence engine for statistical analysis. The input is processed data, and the output is the analysis results. Here, a machine learning model is applied using scikit-learn to analyze trends and causal relationships in movement patterns. This analysis allows meaningful insights to be gained from the data.

[0106] Step 5:

[0107] Based on the analysis results generated in step 4, the server uses Matplotlib and Seaborn to create visually easy-to-understand charts. The input is the statistical analysis results, and the output is a visual representation such as a line graph or heatmap. This visualization allows the user to intuitively understand the analysis results.

[0108] Step 6:

[0109] The terminal displays the visual created in step 5 on the dashboard and provides it to the user. The input is the visual data sent from the server, and it functions as an output interface for the user to interactively explore the data. Specifically, the user can set filters on the dashboard and analyze the data under specific conditions.

[0110] Step 7:

[0111] The generation AI automatically generates policy proposals using the analysis results from step 4 and presents them to the user via the terminal. The input consists of the analysis results and existing policy data, and the output is new policy proposals. Users can review these proposals and provide feedback, thereby improving the accuracy of the analysis model. This feedback loop allows the system to continuously evolve.

[0112] (Application Example 1)

[0113] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0114] Traditional customer behavior analysis systems have made it difficult to grasp detailed situations in real time, which has often led to delays in immediate responses and the development of sales promotion strategies, especially in physical stores. Furthermore, the lack of visually intuitive feedback has made it difficult to implement effective measures. A new method is needed to solve these problems and effectively support store operations.

[0115] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0116] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, and, as an extension implementation means, means for displaying the analysis results on a visual device and presenting location-specific movement information based on the analysis results. This makes it possible to grasp real-time customer trends in physical stores and to formulate immediate sales promotion strategies.

[0117] "Mobility data" refers to information about the movement of people and goods within a specific area, including the number of visitors, length of stay, and movement patterns.

[0118] "Anonymization" refers to the process of removing or transforming personally identifiable information from collected data, thereby protecting personal information.

[0119] "Handling missing values" refers to techniques used to fill in missing information in a dataset, thereby maintaining data consistency and reliability.

[0120] "Statistical information" refers to information that shows various numerical values, patterns, and trends obtained through data analysis.

[0121] "Visual devices" refer to equipment used to display digital information in a visually tangible form, and include smart glasses and similar devices.

[0122] "Movement flow information" refers to information about how people and objects move within a specific area, and this allows for the visualization of behavioral patterns.

[0123] The system for realizing this invention mainly consists of a server, a visual device, and a user terminal. The server collects movement data from across the country and performs a series of data processing operations. The server anonymizes the data using Python and handles missing values. It also performs trend analysis on the collected data using an artificial intelligence model (using TensorFlow) and generates statistical information. As the visual device, smart glasses (e.g., smart wearable device) are used, and the analysis results are displayed intuitively using Unity or other lightweight visualization software.

[0124] Specifically, users can view real-time information about foot traffic within the store via a visual device. Based on the server's analysis, the visual device displays the number of visitors and their dwell time in areas where specific products are located as a heatmap, providing store managers with intuitive and useful data. This allows store managers to immediately make decisions such as changing product placement or implementing special sales campaigns.

[0125] An example of a prompt is, "Analyze the behavioral patterns regarding the placement of this product and suggest the optimal placement." This prompt allows users to leverage data-driven insights and translate them into concrete actions.

[0126] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0127] Step 1:

[0128] The server collects movement data from the target area. This data includes the number of people visiting the area around the store, their length of stay, and their movement patterns, and is transmitted to the server via a communication module. The input is raw data collected in real time, and the output is this dataset.

[0129] Step 2:

[0130] The server anonymizes and imputes missing values ​​in the collected movement data. Anonymization protects personal information, and missing values ​​are imputed using machine learning algorithms. The input is raw data, and the output is a consistent and reliable dataset. Specifically, data formatting is performed using Python data processing libraries.

[0131] Step 3:

[0132] The server feeds pre-processed data into a generating AI model (using TensorFlow) to perform trend analysis and movement pattern analysis. Here, the AI ​​model predicts fluctuations in the number of visitors and their length of stay in a specific area. The input is a pre-processed dataset, and the output is analyzed statistical information.

[0133] Step 4:

[0134] The server generates visualization information based on the analysis results. Specifically, it uses Unity to create heatmaps and line graphs, and prepares the data to be sent to the visual device. The input is statistical information, and the output is concrete visualization data.

[0135] Step 5:

[0136] The user's visual devices receive visualization information from the server and display it on the user interface. At this stage, the user can analyze their movement within the store and take immediate action based on the visual information. The input is visualization data, and the output is specific movement information that the user can clearly see.

[0137] Step 6:

[0138] The terminal has the function of sending user feedback to the server, and user interaction contributes to improving the accuracy of the analysis algorithm. The input is user feedback, and the output is data related to improvements to the analysis algorithm.

[0139] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0140] This invention provides a data analysis system that utilizes nationwide mobility data and combines it with an emotion engine based on user feedback. The system processes, analyzes, and optimizes suggestions through multiple processes.

[0141] Data acquisition and preprocessing

[0142] The server connects to an external mobility database to retrieve geographical movement information of people. This dataset is anonymized and missing values ​​are removed to prepare it as clean data for analysis.

[0143] Data analysis and visualization

[0144] The server sends pre-processed data to an artificial intelligence module for statistical analysis. Specific analysis includes correlations between movement patterns and seasonal trends.

[0145] The server creates interactive graphs and charts based on the analysis results and sends them to the terminal. This makes it easier for the user to visually understand the data.

[0146] Suggestion generation and sentiment recognition

[0147] The generation AI automatically generates policy proposals based on the analysis results. Before presenting the proposals, it analyzes the user's emotions using an emotion engine based on user feedback.

[0148] The device receives user feedback and uses an emotion engine to identify the user's emotions along with the content of the feedback. This allows for more precise adjustments to be reflected in proposed policies.

[0149] Application examples

[0150] For example, in the case of a tourism business, the generative AI predicts an increase in the number of visitors to a particular city and proposes a new tourism campaign. This proposal is presented to the tourism business's users through a device, and the AI ​​reads the feedback provided by the users, such as their expectations and concerns about the campaign.

[0151] The emotion engine detects user anxieties from the feedback and adjusts the proposed solutions based on this. Specifically, it reviews the timing of campaigns and the target age group. This process ensures that measures that better meet user needs are implemented.

[0152] Thus, the present invention provides a system that enables more user-friendly and effective data utilization by adaptively adjusting the proposed content while taking into account user emotions as part of data analysis.

[0153] The following describes the processing flow.

[0154] Step 1:

[0155] The server retrieves the latest travel data from a nationwide travel database. This data includes information such as visited locations, times, number of visitors, and length of stay. The retrieved data is not only stored but is also immediately prepared for subsequent processing.

[0156] Step 2:

[0157] Upon receiving data, the server immediately begins the anonymization process. It removes or transforms personally identifiable information from the dataset to ensure privacy. Furthermore, it uses inference algorithms to fill in any missing data, preparing it for analysis.

[0158] Step 3:

[0159] The server passes pre-processed data to an artificial intelligence (AI) engine, which then analyzes movement patterns. The AI ​​uses time-series analysis and clustering techniques to identify regional trends and correlations. For example, the AI ​​can identify increases or decreases in visitors due to specific events.

[0160] Step 4:

[0161] The server generates line graphs, heatmaps, and other visualizations using visualization tools based on the AI ​​analysis results. These visuals are dynamically configured to provide different analytical perspectives. The generated visuals are then compiled into a dashboard.

[0162] Step 5:

[0163] The device launches the dashboard and displays generated graphs and charts to the user. The user can click on these interactive visuals to view details or zoom in on specific datasets.

[0164] Step 6:

[0165] The AI ​​generates proposals automatically based on the analysis results and presents them to the user via their device. These proposals include specific marketing strategies and event implementation guidelines.

[0166] Step 7:

[0167] Users evaluate the presented suggestions and provide feedback. This feedback includes specific opinions and impressions, and emotional responses are also recorded.

[0168] Step 8:

[0169] The device sends the input feedback to an emotion engine, which analyzes the user's emotions. For example, it extracts satisfaction levels and concerns regarding a suggestion through text analysis.

[0170] Step 9:

[0171] The server adjusts the proposed measures based on the analysis results of the emotion engine. It modifies the measures in response to emotional feedback and re-presents the optimized proposals to the user.

[0172] Step 10:

[0173] Further feedback from users will be used to improve the analysis and suggestion process in the future. The server will analyze this data to help improve the overall accuracy of the system.

[0174] (Example 2)

[0175] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0176] Modern data analysis systems struggle to generate plans that adequately reflect user emotions and feedback, thus requiring flexible responses tailored to user needs. However, in conventional systems, data collection, analysis, and proposal generation are performed independently in each process, making it challenging to incorporate emotion-based feedback from users.

[0177] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0178] In this invention, the server includes means for acquiring geographical information, means for anonymizing and processing missing values ​​from the acquired information, and means for generating statistical information. This enables the automatic generation and adjustment of suggestions that take user sentiment into consideration.

[0179] "Geographic information" refers to data about the location or movement of individuals or groups, and includes spatial information related to a specific region.

[0180] "Anonymization" is a process that removes or transforms elements that could identify an individual from data in order to protect privacy.

[0181] "Handling missing values" is a method used to impart missing values ​​to a dataset, and is performed to maintain data integrity.

[0182] "Statistical information" is a collection of numerical and conceptual data characteristics obtained by analyzing data.

[0183] "Charts and diagrams" are visual representations of data, including graphs and charts, and are a means of making information easier to understand intuitively.

[0184] A "plan" is a proposal outlining specific actions and measures generated based on analyzed data and statistical information.

[0185] An "intelligent processing device" is a system or program capable of performing complex data processing, and is usually realized using artificial intelligence technology.

[0186] This invention is a data analysis system that utilizes geographical information and aims to incorporate user emotional feedback. The system collects large amounts of movement data, cleans it up through anonymization and missing value handling, and analyzes it as statistical information. The server makes API requests to an external database to collect initial data. In this process, geographical information is anonymized using anonymization techniques and missing value imputation algorithms to protect privacy. Data organization and processing are performed using Python's Pandas and NumPy.

[0187] Next, the server performs statistical analysis using an artificial intelligence module to understand the correlations and seasonal trends in movement patterns. During this process, the intelligent processing unit demonstrates high computational power and generates relevant statistical information. After analysis, the server visualizes the data as graphs and charts and sends them to the terminal. Here, specialized visualization libraries such as Matplotlib and D3.js are used.

[0188] In the generative AI model, the server automatically generates a plan based on statistical information. In this process, the generative AI constructs the optimal measures based on prompt statements. For example, a prompt such as "Propose a campaign if the number of visitors increases in a specific region" might be used.

[0189] Ultimately, the device receives user feedback, analyzes emotions using an emotion recognition engine, and incorporates the user's emotional feedback into the plan. This entire process allows for flexible measures tailored to user needs, enabling more refined and personalized suggestions.

[0190] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0191] Step 1:

[0192] The server accesses an external database to retrieve movement data. The input is raw data obtained via an API request. This data includes an individual's location information and movement history. The output is the raw geographical information retrieved. This raw data is retained for subsequent processing.

[0193] Step 2:

[0194] The server performs anonymization and missing value handling on the acquired raw data. The input is the raw data acquired in step 1. Anonymization removes elements that can identify individuals, and missing value handling uses methods such as mean imputation and mode imputation to fill in the incomplete parts of the data. The output is clean, analyzable geographical information.

[0195] Step 3:

[0196] The server sends clean data to the artificial intelligence module for statistical analysis. The input is the clean data, which is the output of step 2. The AI ​​module recognizes patterns in the data and analyzes correlations between movement patterns, seasonal factors, and so on. The output is the relevant statistical information.

[0197] Step 4:

[0198] The server generates interactive graphs and charts based on the analysis results. The input is the statistical information obtained in step 3. For visualization, visualization libraries such as Matplotlib and D3.js are used to transform the data into a visually easy-to-understand format. The output is a data visualization.

[0199] Step 5:

[0200] The terminal displays the generated graphs and charts to the user. The input is the data visualization from step 4. Based on this information, the user can understand the proposed future plan. The output leads to user understanding and feedback.

[0201] Step 6:

[0202] The generation AI automatically generates a plan based on statistical information. The input is the statistical information from step 3. The generated plan can be flexibly modified using prompts. For example, a prompt such as "Propose a campaign to coincide with the increase in the number of visitors to a specific region" is used. The output is the plan.

[0203] Step 7:

[0204] The device receives feedback from the user and analyzes emotions using an emotion recognition engine. The input consists of the proposed plan generated in step 6 and the user's feedback. Emotion analysis assigns emotion labels such as positive, negative, and neutral. The output is the analyzed emotion information.

[0205] Step 8:

[0206] The server adjusts the proposed plan based on the emotion analysis results. The input is the emotion information analyzed in step 7. If negative emotions such as anxiety are detected, the timing and target audience of the proposed plan are re-evaluated. The output is the proposed plan adjusted based on user feedback.

[0207] (Application Example 2)

[0208] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0209] In recent years, there has been a growing demand for services that meet the diverse needs of individual users. However, conventional systems have faced challenges in providing optimal suggestions that take into account users' emotions and past behavioral patterns. Furthermore, it has been difficult to provide more refined and personalized services by effectively analyzing dynamic user behavior data and adapting to emotions.

[0210] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0211] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, means for generating graphs and charts to visualize the generated statistical information, means for automatically generating policy proposals based on the analyzed statistical information, means for presenting the proposed policy proposals to the user and receiving feedback, means for selecting recommended services based on the user's past behavior history and location information data, and means for analyzing user emotions using an emotion engine based on the feedback and adjusting the proposed content. This makes it possible to make optimal proposals that take into account the individual emotions and actions of each user.

[0212] "Movement data" refers to location information and movement history of people acquired on a nationwide scale.

[0213] "Anonymization" refers to the process of removing or masking personally identifiable information from individual data.

[0214] "Missing value handling" refers to the process of filling in missing elements in a dataset.

[0215] "Statistical information" refers to numerical information that shows patterns and trends obtained by analyzing collected data.

[0216] "Graphs and charts" refer to graphical representations used to visually show trends and relationships in data.

[0217] A "proposal" refers to a plan of actions or strategies proposed to users.

[0218] "Feedback" refers to reaction information such as opinions, evaluations, and emotions provided by users.

[0219] An "emotion engine" refers to an algorithm that analyzes a user's emotions from their words and actions and reflects the results in the system.

[0220] "Behavioral history" refers to a record of actions a user has taken in the past.

[0221] "Location information" refers to data that indicates a user's current and past geographical location.

[0222] The system that realizes this invention consists of a server, a terminal, and a user. The server acquires nationwide movement data, anonymizes the collected data and handles missing values, and then performs data analysis. In the analysis process, movement patterns and statistical information are generated using Python's Pandas and Scikit-learn. The server visualizes these analysis results, generates interactive graphs and charts, and sends them to the terminal.

[0223] On the device, results are presented to the user through an interface built with React Native. Users can provide feedback based on this information. User feedback is analyzed using an emotion engine, and the user's emotions are identified using Anaconda and NLP libraries. Based on the acquired user emotion information, the server adjusts proposed measures using a generative AI model and further suggests appropriate services and products.

[0224] As a concrete example, in the case of a food delivery service, the server generates food delivery recommendations based on the user's past order history and current location information. If the user provides feedback such as "I want to eat something spicy today," sentiment analysis is used to select and suggest restaurants that serve spicy food.

[0225] An example of a prompt message is, "Based on past order history and current location, suggest a healthy lunch that can be enjoyed safely and quickly." This forms the basis for generating suggestions tailored to the user's needs.

[0226] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0227] Step 1:

[0228] The server retrieves nationwide mobility data from an external database. It takes people's location information and movement history as input, anonymizes it, and handles missing values. The output is clean, analyzable data.

[0229] Step 2:

[0230] The server analyzes preprocessed data using Python's Pandas and Scikit-learn libraries. It receives clean movement data as input and performs data calculations to generate movement patterns and statistics. The output provides statistical information showing the trends and correlations of movement patterns.

[0231] Step 3:

[0232] The server generates graphs and charts to visualize the analyzed statistical information. It receives statistical information as input and performs data processing to generate interactive charts and graphs. The output consists of visually easy-to-understand graphs and charts.

[0233] Step 4:

[0234] The terminal displays suggestions to the user based on graphs and charts sent from the server. It receives visualized information as input and displays it on the screen. As output, it obtains an interface that the user can view.

[0235] Step 5:

[0236] The user provides feedback based on the information presented. The input involves considering the proposal and entering feedback into the terminal. The output provides information about the user's expectations and concerns.

[0237] Step 6:

[0238] The terminal receives feedback from the user and sends it to the server. As input, it receives user feedback and passes it to the server. As output, the feedback information is transmitted to the server.

[0239] Step 7:

[0240] The server analyzes the user's emotions using an emotion engine. It takes feedback information as input and performs emotion analysis. The output is data indicating the user's emotions.

[0241] Step 8:

[0242] The server automatically generates adjusted policy proposals using a generative AI model. It receives sentiment analysis results and past behavioral data as input and performs the generation process. The output is a specific, adjusted service proposal.

[0243] Step 9:

[0244] The terminal then presents the adjusted policy proposal to the user again. It receives the optimized proposal as input and displays it on the user's screen. As output, it obtains an interface for the user to finalize the proposal.

[0245] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0246] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0247] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0248] [Second Embodiment]

[0249] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0250] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0251] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0252] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0253] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0254] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0255] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0256] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0257] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0258] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0259] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0260] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0261] This invention provides a data analysis system that effectively utilizes nationwide mobility data. The system processes data through automated processes at each stage, ultimately providing insights for the user. Its specific form is described below.

[0262] Data collection

[0263] The server periodically collects movement data for the target area. This data includes the number of visitors to each area, their length of stay, and their movement patterns.

[0264] Data preprocessing

[0265] The server anonymizes the collected data to ensure the protection of personal information. Furthermore, it automatically handles the imputation of missing values ​​and the identification and correction of outliers, thereby improving data consistency and reliability.

[0266] Data Analysis

[0267] The server sends the pre-processed dataset to the artificial intelligence for statistical analysis. This involves trend analysis of movement patterns and modeling fluctuations in visitor numbers related to specific factors.

[0268] visualization

[0269] Based on statistical information generated by the server, the system automatically generates graphs and charts that are easy to understand visually. These visuals can, for example, show fluctuations in past visitor numbers using line graphs, or indicate the popularity of specific regions using heatmaps.

[0270] Proposal and User Interaction

[0271] The device provides users with generated graphs and charts as dashboards. Through interactive operations, users can explore the data in depth and access detailed analysis results based on specific conditions.

[0272] The generating AI automatically proposes policy options based on the analysis results and presents them to the user via the device. Users can evaluate these policy options and provide feedback, thereby contributing to improving the accuracy of the analysis.

[0273] Specific example

[0274] When users in the tourism industry utilize this system, they can visualize the trends in the number of visitors by season in their own areas. For example, if the number of visitors in spring is on the rise, the artificial intelligence analyzes the cause and identifies that the increase in spring events has an impact. Based on this, it proposes implementing a new spring campaign. The user can review the proposed content and decide whether to incorporate it into their company's marketing strategy.

[0275] In this way, this invention provides a comprehensive system for users to effectively utilize data and support decision-making without the need for specialized knowledge.

[0276] The following explains the processing flow.

[0277] Step 1:

[0278] The server connects to the national mobility database and acquires the latest mobility data. This data includes attributes such as location, time, number of visitors, and stay time.

[0279] Step 2:

[0280] The server anonymizes the acquired data. It removes identifiers that can identify individuals and converts it into a form that meets the data security standards.

[0281] Step 3:

[0282] The server performs data preprocessing. If there are missing values, it uses a specific algorithm to complete them. If outliers are detected, it corrects or removes them to prepare a clean dataset.

[0283] Step 4:

[0284] The server sends the clean data to the artificial intelligence module and starts data analysis. Here, for example, a statistical model for analyzing mobility patterns by time period or region is applied.

[0285] Step 5:

[0286] The generative AI generates statistical information based on the analysis results to identify data correlations and trends. For example, it can find that the number of visitors tends to increase during a certain period with a specific event.

[0287] Step 6:

[0288] The server generates graphs and charts for visualizing the analysis results. This includes line graphs, bar graphs, heatmaps, etc.

[0289] Step 7:

[0290] The terminal displays the generated graphs and charts on the dashboard, enabling users to interactively explore the data. Users can use this to check the details of the data and further delve into items of interest.

[0291] Step 8:

[0292] The generative AI automatically creates a policy plan based on the analysis results and presents it to the user through the terminal. For example, proposals such as the promotion timing of a specific product or the planning of a new event are made.

[0293] Step 9:

[0294] The user checks the provided policy plan and inputs opinions and evaluations as feedback. This feedback is recorded by the server and utilized to improve the analysis algorithm.

[0295] Step 10:

[0296] The server analyzes the user's feedback and reflects it in subsequent analysis processes. This enables continuously improved data analysis with higher accuracy.

[0297] (Example 1)

[0298] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0299] A major challenge is the lack of a data analysis system capable of effectively acquiring nationwide mobility information and analyzing it to provide actionable insights. Currently, anonymization of collected data, handling of missing values, multidimensional analysis of data, visualization, and proposal of policy based on analysis results are often performed manually, which is labor-intensive and time-consuming. Furthermore, there is no established method for quickly incorporating user feedback into the system, making it difficult to improve the accuracy of the analysis.

[0300] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0301] In this invention, the server includes means for acquiring movement information from a wide range of locations, means for anonymizing the acquired movement information and processing missing and outlier values, and means for analyzing the pre-processed movement information to generate statistical information. This enables the automation of advanced data analysis and provides practical insights quickly and efficiently.

[0302] "Mobility information" refers to data about the movement of people and goods within a geographical area, and typically includes visitor numbers, length of stay, and movement patterns.

[0303] "Anonymization" is a process that protects privacy by removing or concealing information that could identify a specific individual.

[0304] "Missing values" refer to a state in a dataset where data that should be present is absent, and processing is required to fill in these missing parts.

[0305] An "outlier" is a value that is significantly different from other data points within a dataset, which may interfere with the consistency and interpretation of the data.

[0306] "Statistical information" refers to numerical or graphical results obtained through data analysis, which indicate the trends and characteristics of the data.

[0307] "Visualization" is a method of presenting analyzed data as charts or graphs to make it easier to understand visually.

[0308] A "plan" refers to action guidelines or proposals generated based on data analysis results, and may include specific implementation plans in some cases.

[0309] "Artificial intelligence" refers to systems or programs that mimic human cognitive functions, and particularly includes technologies such as machine learning and natural language processing.

[0310] "Arithmetic operation" refers to basic computational processing on numerical data, including addition, subtraction, multiplication, division, and statistical calculations.

[0311] A "display device" is a device for visually displaying data and images, and is a device that provides information through a user interface.

[0312] This invention is a data analysis system that effectively analyzes national movement information and provides practical insights. In the implementation of this system, the following hardware and software are used.

[0313] Data collection and preprocessing

[0314] The server retrieves movement information from government agencies and the private sector via API calls over the internet. The database used is a relational database designed to efficiently store a wide range of geographic data. Data anonymization is performed by filtering out personally identifiable information, and the Python Pandas library is used to handle missing or outlier values.

[0315] Data Analysis

[0316] The server analyzes the preprocessed data through an artificial intelligence engine, such as TensorFlow or scikit-learn. Machine learning algorithms perform statistical analysis to extract trends and factors from the dataset. This builds a model based on visitor behavior.

[0317] Visualization and proposal

[0318] The server generates graphs and charts using Matplotlib and Seaborn libraries based on the analysis results. This visual data is integrated into a dashboard accessible to the user via their device, allowing for interactive operation. The generated AI model formulates policy proposals from the analysis results and provides them to the user as prompts.

[0319] To give a concrete example, if a tourism business uses this system, they can visualize the seasonal trends in visitor numbers in a specific region. Based on these results, the generating AI model performs an analysis using a prompt message such as, "Analyze the increasing trend in visitor numbers during the spring season, and propose causes and countermeasures," and provides practical countermeasure proposals.

[0320] In this way, the system helps users gain valuable business insights even without specialized knowledge.

[0321] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0322] Step 1:

[0323] The server retrieves movement information from public institutions and private data providers via APIs. The data received as input includes visitor numbers, dwell time, and movement patterns. The server stores this data in a relational database and compiles it into aggregated movement information. This aggregated data forms the basis for the next processing steps.

[0324] Step 2:

[0325] The server performs anonymization on the movement information aggregated in Step 1. The input is the data stored in Step 1, and the output is anonymized data from which personally identifiable information has been removed. Specifically, this involves removing fields that identify individual visitors and reorganizing information into aggregate units. This ensures that a dataset suitable for analysis is obtained while protecting privacy.

[0326] Step 3:

[0327] The server processes missing and outlier values ​​in the anonymized data resulting from Step 2. It uses the anonymized data from Step 2 as input and outputs clean, consistent data. The server uses the Python Pandas library to impute missing values ​​with the mean or median and filters out outliers. This data cleansing allows for smoother execution of the next analysis step.

[0328] Step 4:

[0329] The server passes the clean data obtained in step 3 to the artificial intelligence engine for statistical analysis. The input is processed data, and the output is the analysis results. Here, a machine learning model is applied using scikit-learn to analyze trends and causal relationships in movement patterns. This analysis allows meaningful insights to be gained from the data.

[0330] Step 5:

[0331] Based on the analysis results generated in step 4, the server uses Matplotlib and Seaborn to create visually easy-to-understand charts. The input is the statistical analysis results, and the output is a visual representation such as a line graph or heatmap. This visualization allows the user to intuitively understand the analysis results.

[0332] Step 6:

[0333] The terminal displays the visual created in step 5 on the dashboard and provides it to the user. The input is the visual data sent from the server, and it functions as an output interface for the user to interactively explore the data. Specifically, the user can set filters on the dashboard and analyze the data under specific conditions.

[0334] Step 7:

[0335] The generation AI automatically generates policy proposals using the analysis results from step 4 and presents them to the user via the terminal. The input consists of the analysis results and existing policy data, and the output is new policy proposals. Users can review these proposals and provide feedback, thereby improving the accuracy of the analysis model. This feedback loop allows the system to continuously evolve.

[0336] (Application Example 1)

[0337] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0338] Traditional customer behavior analysis systems have made it difficult to grasp detailed situations in real time, which has often led to delays in immediate responses and the development of sales promotion strategies, especially in physical stores. Furthermore, the lack of visually intuitive feedback has made it difficult to implement effective measures. A new method is needed to solve these problems and effectively support store operations.

[0339] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0340] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, and, as an extension implementation means, means for displaying the analysis results on a visual device and presenting location-specific movement information based on the analysis results. This makes it possible to grasp real-time customer trends in physical stores and to formulate immediate sales promotion strategies.

[0341] "Mobility data" refers to information about the movement of people and goods within a specific area, including the number of visitors, length of stay, and movement patterns.

[0342] "Anonymization" refers to the process of removing or transforming personally identifiable information from collected data, thereby protecting personal information.

[0343] "Handling missing values" refers to techniques used to fill in missing information in a dataset, thereby maintaining data consistency and reliability.

[0344] "Statistical information" refers to information that shows various numerical values, patterns, and trends obtained through data analysis.

[0345] "Visual devices" refer to equipment used to display digital information in a visually tangible form, and include smart glasses and similar devices.

[0346] "Movement flow information" refers to information about how people and objects move within a specific area, and this allows for the visualization of behavioral patterns.

[0347] The system for realizing this invention mainly consists of a server, a visual device, and a user terminal. The server collects movement data from across the country and performs a series of data processing operations. The server anonymizes the data using Python and handles missing values. It also performs trend analysis on the collected data using an artificial intelligence model (using TensorFlow) and generates statistical information. As the visual device, smart glasses (e.g., smart wearable device) are used, and the analysis results are displayed intuitively using Unity or other lightweight visualization software.

[0348] Specifically, users can view real-time information about foot traffic within the store via a visual device. Based on the server's analysis, the visual device displays the number of visitors and their dwell time in areas where specific products are located as a heatmap, providing store managers with intuitive and useful data. This allows store managers to immediately make decisions such as changing product placement or implementing special sales campaigns.

[0349] An example of a prompt is, "Analyze the behavioral patterns regarding the placement of this product and suggest the optimal placement." This prompt allows users to leverage data-driven insights and translate them into concrete actions.

[0350] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0351] Step 1:

[0352] The server collects movement data from the target area. This data includes the number of people visiting the area around the store, their length of stay, and their movement patterns, and is transmitted to the server via a communication module. The input is raw data collected in real time, and the output is this dataset.

[0353] Step 2:

[0354] The server anonymizes and imputes missing values ​​in the collected movement data. Anonymization protects personal information, and missing values ​​are imputed using machine learning algorithms. The input is raw data, and the output is a consistent and reliable dataset. Specifically, data formatting is performed using Python data processing libraries.

[0355] Step 3:

[0356] The server feeds pre-processed data into a generating AI model (using TensorFlow) to perform trend analysis and movement pattern analysis. Here, the AI ​​model predicts fluctuations in the number of visitors and their length of stay in a specific area. The input is a pre-processed dataset, and the output is analyzed statistical information.

[0357] Step 4:

[0358] The server generates visualization information based on the analysis results. Specifically, it uses Unity to create heatmaps and line graphs, and prepares the data to be sent to the visual device. The input is statistical information, and the output is concrete visualization data.

[0359] Step 5:

[0360] The user's visual devices receive visualization information from the server and display it on the user interface. At this stage, the user can analyze their movement within the store and take immediate action based on the visual information. The input is visualization data, and the output is specific movement information that the user can clearly see.

[0361] Step 6:

[0362] The terminal has the function of sending user feedback to the server, and user interaction contributes to improving the accuracy of the analysis algorithm. The input is user feedback, and the output is data related to improvements to the analysis algorithm.

[0363] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0364] This invention provides a data analysis system that utilizes nationwide mobility data and combines it with an emotion engine based on user feedback. The system processes, analyzes, and optimizes suggestions through multiple processes.

[0365] Data acquisition and preprocessing

[0366] The server connects to an external mobility database to retrieve geographical movement information of people. This dataset is anonymized and missing values ​​are removed to prepare it as clean data for analysis.

[0367] Data analysis and visualization

[0368] The server sends pre-processed data to an artificial intelligence module for statistical analysis. Specific analysis includes correlations between movement patterns and seasonal trends.

[0369] The server creates interactive graphs and charts based on the analysis results and sends them to the terminal. This makes it easier for the user to visually understand the data.

[0370] Suggestion generation and sentiment recognition

[0371] The generation AI automatically generates policy proposals based on the analysis results. Before presenting the proposals, it analyzes the user's emotions using an emotion engine based on user feedback.

[0372] The device receives user feedback and uses an emotion engine to identify the user's emotions along with the content of the feedback. This allows for more precise adjustments to be reflected in proposed policies.

[0373] Application examples

[0374] For example, in the case of a tourism business, the generative AI predicts an increase in the number of visitors to a particular city and proposes a new tourism campaign. This proposal is presented to the tourism business's users through a device, and the AI ​​reads the feedback provided by the users, such as their expectations and concerns about the campaign.

[0375] The emotion engine detects user anxieties from the feedback and adjusts the proposed solutions based on this. Specifically, it reviews the timing of campaigns and the target age group. This process ensures that measures that better meet user needs are implemented.

[0376] Thus, the present invention provides a system that enables more user-friendly and effective data utilization by adaptively adjusting the proposed content while taking into account user emotions as part of data analysis.

[0377] The following describes the processing flow.

[0378] Step 1:

[0379] The server retrieves the latest travel data from a nationwide travel database. This data includes information such as visited locations, times, number of visitors, and length of stay. The retrieved data is not only stored but is also immediately prepared for subsequent processing.

[0380] Step 2:

[0381] Upon receiving data, the server immediately begins the anonymization process. It removes or transforms personally identifiable information from the dataset to ensure privacy. Furthermore, it uses inference algorithms to fill in any missing data, preparing it for analysis.

[0382] Step 3:

[0383] The server passes pre-processed data to an artificial intelligence (AI) engine, which then analyzes movement patterns. The AI ​​uses time-series analysis and clustering techniques to identify regional trends and correlations. For example, the AI ​​can identify increases or decreases in visitors due to specific events.

[0384] Step 4:

[0385] The server generates line graphs, heatmaps, and other visualizations using visualization tools based on the AI ​​analysis results. These visuals are dynamically configured to provide different analytical perspectives. The generated visuals are then compiled into a dashboard.

[0386] Step 5:

[0387] The device launches the dashboard and displays generated graphs and charts to the user. The user can click on these interactive visuals to view details or zoom in on specific datasets.

[0388] Step 6:

[0389] The AI ​​generates proposals automatically based on the analysis results and presents them to the user via their device. These proposals include specific marketing strategies and event implementation guidelines.

[0390] Step 7:

[0391] Users evaluate the presented suggestions and provide feedback. This feedback includes specific opinions and impressions, and emotional responses are also recorded.

[0392] Step 8:

[0393] The device sends the input feedback to an emotion engine, which analyzes the user's emotions. For example, it extracts satisfaction levels and concerns regarding a suggestion through text analysis.

[0394] Step 9:

[0395] The server adjusts the proposed measures based on the analysis results of the emotion engine. It modifies the measures in response to emotional feedback and re-presents the optimized proposals to the user.

[0396] Step 10:

[0397] Further feedback from users will be used to improve the analysis and suggestion process in the future. The server will analyze this data to help improve the overall accuracy of the system.

[0398] (Example 2)

[0399] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0400] Modern data analysis systems struggle to generate plans that adequately reflect user emotions and feedback, thus requiring flexible responses tailored to user needs. However, in conventional systems, data collection, analysis, and proposal generation are performed independently in each process, making it challenging to incorporate emotion-based feedback from users.

[0401] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0402] In this invention, the server includes means for acquiring geographical information, means for anonymizing and processing missing values ​​from the acquired information, and means for generating statistical information. This enables the automatic generation and adjustment of suggestions that take user sentiment into consideration.

[0403] "Geographic information" refers to data about the location or movement of individuals or groups, and includes spatial information related to a specific region.

[0404] "Anonymization" is a process that removes or transforms elements that could identify an individual from data in order to protect privacy.

[0405] "Handling missing values" is a method used to impart missing values ​​to a dataset, and is performed to maintain data integrity.

[0406] "Statistical information" is a collection of numerical and conceptual data characteristics obtained by analyzing data.

[0407] "Charts and diagrams" are visual representations of data, including graphs and charts, and are a means of making information easier to understand intuitively.

[0408] A "plan" is a proposal outlining specific actions and measures generated based on analyzed data and statistical information.

[0409] An "intelligent processing device" is a system or program capable of performing complex data processing, and is usually realized using artificial intelligence technology.

[0410] This invention is a data analysis system that utilizes geographical information and aims to incorporate user emotional feedback. The system collects large amounts of movement data, cleans it up through anonymization and missing value handling, and analyzes it as statistical information. The server makes API requests to an external database to collect initial data. In this process, geographical information is anonymized using anonymization techniques and missing value imputation algorithms to protect privacy. Data organization and processing are performed using Python's Pandas and NumPy.

[0411] Next, the server performs statistical analysis using an artificial intelligence module to understand the correlations and seasonal trends in movement patterns. During this process, the intelligent processing unit demonstrates high computational power and generates relevant statistical information. After analysis, the server visualizes the data as graphs and charts and sends them to the terminal. Here, specialized visualization libraries such as Matplotlib and D3.js are used.

[0412] In the generative AI model, the server automatically generates a plan based on statistical information. In this process, the generative AI constructs the optimal measures based on prompt statements. For example, a prompt such as "Propose a campaign if the number of visitors increases in a specific region" might be used.

[0413] Ultimately, the device receives user feedback, analyzes emotions using an emotion recognition engine, and incorporates the user's emotional feedback into the plan. This entire process allows for flexible measures tailored to user needs, enabling more refined and personalized suggestions.

[0414] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0415] Step 1:

[0416] The server accesses an external database to retrieve movement data. The input is raw data obtained via an API request. This data includes an individual's location information and movement history. The output is the raw geographical information retrieved. This raw data is retained for subsequent processing.

[0417] Step 2:

[0418] The server performs anonymization and missing value handling on the acquired raw data. The input is the raw data acquired in step 1. Anonymization removes elements that can identify individuals, and missing value handling uses methods such as mean imputation and mode imputation to fill in the incomplete parts of the data. The output is clean, analyzable geographical information.

[0419] Step 3:

[0420] The server sends clean data to the artificial intelligence module for statistical analysis. The input is the clean data, which is the output of step 2. The AI ​​module recognizes patterns in the data and analyzes correlations between movement patterns, seasonal factors, and so on. The output is the relevant statistical information.

[0421] Step 4:

[0422] The server generates interactive graphs and charts based on the analysis results. The input is the statistical information obtained in step 3. For visualization, visualization libraries such as Matplotlib and D3.js are used to transform the data into a visually easy-to-understand format. The output is a data visualization.

[0423] Step 5:

[0424] The terminal displays the generated graphs and charts to the user. The input is the data visualization from step 4. Based on this information, the user can understand the proposed future plan. The output leads to user understanding and feedback.

[0425] Step 6:

[0426] The generation AI automatically generates a plan based on statistical information. The input is the statistical information from step 3. The generated plan can be flexibly modified using prompts. For example, a prompt such as "Propose a campaign to coincide with the increase in the number of visitors to a specific region" is used. The output is the plan.

[0427] Step 7:

[0428] The device receives feedback from the user and analyzes emotions using an emotion recognition engine. The input consists of the proposed plan generated in step 6 and the user's feedback. Emotion analysis assigns emotion labels such as positive, negative, and neutral. The output is the analyzed emotion information.

[0429] Step 8:

[0430] The server adjusts the proposed plan based on the emotion analysis results. The input is the emotion information analyzed in step 7. If negative emotions such as anxiety are detected, the timing and target audience of the proposed plan are re-evaluated. The output is the proposed plan adjusted based on user feedback.

[0431] (Application Example 2)

[0432] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0433] In recent years, there has been a growing demand for services that meet the diverse needs of individual users. However, conventional systems have faced challenges in providing optimal suggestions that take into account users' emotions and past behavioral patterns. Furthermore, it has been difficult to provide more refined and personalized services by effectively analyzing dynamic user behavior data and adapting to emotions.

[0434] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0435] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, means for generating graphs and charts to visualize the generated statistical information, means for automatically generating policy proposals based on the analyzed statistical information, means for presenting the proposed policy proposals to the user and receiving feedback, means for selecting recommended services based on the user's past behavior history and location information data, and means for analyzing user emotions using an emotion engine based on the feedback and adjusting the proposed content. This makes it possible to make optimal proposals that take into account the individual emotions and actions of each user.

[0436] "Movement data" refers to location information and movement history of people acquired on a nationwide scale.

[0437] "Anonymization" refers to the process of removing or masking personally identifiable information from individual data.

[0438] "Missing value handling" refers to the process of filling in missing elements in a dataset.

[0439] "Statistical information" refers to numerical information that shows patterns and trends obtained by analyzing collected data.

[0440] "Graphs and charts" refer to graphical representations used to visually show trends and relationships in data.

[0441] A "proposal" refers to a plan of actions or strategies proposed to users.

[0442] "Feedback" refers to reaction information such as opinions, evaluations, and emotions provided by users.

[0443] An "emotion engine" refers to an algorithm that analyzes a user's emotions from their words and actions and reflects the results in the system.

[0444] "Behavioral history" refers to a record of actions a user has taken in the past.

[0445] "Location information" refers to data that indicates a user's current and past geographical location.

[0446] The system that realizes this invention consists of a server, a terminal, and a user. The server acquires nationwide movement data, anonymizes the collected data and handles missing values, and then performs data analysis. In the analysis process, movement patterns and statistical information are generated using Python's Pandas and Scikit-learn. The server visualizes these analysis results, generates interactive graphs and charts, and sends them to the terminal.

[0447] On the device, results are presented to the user through an interface built with React Native. Users can provide feedback based on this information. User feedback is analyzed using an emotion engine, and the user's emotions are identified using Anaconda and NLP libraries. Based on the acquired user emotion information, the server adjusts proposed measures using a generative AI model and further suggests appropriate services and products.

[0448] As a concrete example, in the case of a food delivery service, the server generates food delivery recommendations based on the user's past order history and current location information. If the user provides feedback such as "I want to eat something spicy today," sentiment analysis is used to select and suggest restaurants that serve spicy food.

[0449] An example of a prompt message is, "Based on past order history and current location, suggest a healthy lunch that can be enjoyed safely and quickly." This forms the basis for generating suggestions tailored to the user's needs.

[0450] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0451] Step 1:

[0452] The server retrieves nationwide mobility data from an external database. It takes people's location information and movement history as input, anonymizes it, and handles missing values. The output is clean, analyzable data.

[0453] Step 2:

[0454] The server analyzes preprocessed data using Python's Pandas and Scikit-learn libraries. It receives clean movement data as input and performs data calculations to generate movement patterns and statistics. The output provides statistical information showing the trends and correlations of movement patterns.

[0455] Step 3:

[0456] The server generates graphs and charts to visualize the analyzed statistical information. It receives statistical information as input and performs data processing to generate interactive charts and graphs. The output consists of visually easy-to-understand graphs and charts.

[0457] Step 4:

[0458] The terminal displays suggestions to the user based on graphs and charts sent from the server. It receives visualized information as input and displays it on the screen. As output, it obtains an interface that the user can view.

[0459] Step 5:

[0460] The user provides feedback based on the information presented. The input involves considering the proposal and entering feedback into the terminal. The output provides information about the user's expectations and concerns.

[0461] Step 6:

[0462] The terminal receives feedback from the user and sends it to the server. As input, it receives user feedback and passes it to the server. As output, the feedback information is transmitted to the server.

[0463] Step 7:

[0464] The server analyzes the user's emotions using an emotion engine. It takes feedback information as input and performs emotion analysis. The output is data indicating the user's emotions.

[0465] Step 8:

[0466] The server automatically generates adjusted policy proposals using a generative AI model. It receives sentiment analysis results and past behavioral data as input and performs the generation process. The output is a specific, adjusted service proposal.

[0467] Step 9:

[0468] The terminal then presents the adjusted policy proposal to the user again. It receives the optimized proposal as input and displays it on the user's screen. As output, it obtains an interface for the user to finalize the proposal.

[0469] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0470] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0471] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0472] [Third Embodiment]

[0473] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0474] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0475] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0476] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0477] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0478] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0479] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0480] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0481] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0482] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0483] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0484] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0485] This invention provides a data analysis system that effectively utilizes nationwide mobility data. The system processes data through automated processes at each stage, ultimately providing insights for the user. Its specific form is described below.

[0486] Data collection

[0487] The server periodically collects movement data for the target area. This data includes the number of visitors to each area, their length of stay, and their movement patterns.

[0488] Data preprocessing

[0489] The server anonymizes the collected data to ensure the protection of personal information. Furthermore, it automatically handles the imputation of missing values ​​and the identification and correction of outliers, thereby improving data consistency and reliability.

[0490] Data Analysis

[0491] The server sends the pre-processed dataset to the artificial intelligence for statistical analysis. This involves trend analysis of movement patterns and modeling fluctuations in visitor numbers related to specific factors.

[0492] visualization

[0493] Based on statistical information generated by the server, the system automatically generates graphs and charts that are easy to understand visually. These visuals can, for example, show fluctuations in past visitor numbers using line graphs, or indicate the popularity of specific regions using heatmaps.

[0494] Proposal and User Interaction

[0495] The device provides users with generated graphs and charts as dashboards. Through interactive operations, users can explore the data in depth and access detailed analysis results based on specific conditions.

[0496] The generating AI automatically proposes policy options based on the analysis results and presents them to the user via the device. Users can evaluate these policy options and provide feedback, thereby contributing to improving the accuracy of the analysis.

[0497] Specific example

[0498] Tourism businesses can use this system to visualize seasonal visitor trends in their area. For example, if visitor numbers are increasing in the spring, the artificial intelligence will analyze the cause and identify that an increase in spring events is a contributing factor. Based on this, it will suggest a new spring campaign. Users can review the suggestions and decide whether to incorporate them into their marketing strategy.

[0499] Thus, this invention provides a comprehensive system that enables users to effectively utilize data and support decision-making, even without specialized knowledge.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The server connects to a nationwide mobility database to retrieve the latest mobility data. This data includes attributes such as location, time, number of visitors, and length of stay.

[0503] Step 2:

[0504] The server anonymizes the acquired data. It removes personally identifiable identifiers and transforms the data to meet data security standards.

[0505] Step 3:

[0506] The server performs data preprocessing. If there are missing values, it uses a specific algorithm to impute them, and if outliers are detected, it corrects or removes them to prepare a clean dataset.

[0507] Step 4:

[0508] The server sends clean data to an artificial intelligence module, which then begins data analysis. Here, statistical models are applied to analyze, for example, movement patterns by time of day or region.

[0509] Step 5:

[0510] Generative AI generates statistical information based on analysis results, identifying correlations and trends in the data. For example, it can find a tendency for the number of visitors to increase during a certain period when a specific event is occurring.

[0511] Step 6:

[0512] The server generates graphs and charts to visualize the analysis results. These include line graphs, bar graphs, and heatmaps.

[0513] Step 7:

[0514] The device displays generated graphs and charts on the dashboard, allowing users to interactively explore the data. Users can use this to view data details and delve deeper into areas of interest.

[0515] Step 8:

[0516] The AI ​​generates policy proposals automatically based on the analysis results and presents them to the user via the device. For example, it may suggest the timing of promotions for specific products or plan new events.

[0517] Step 9:

[0518] Users review the proposed measures and provide feedback, including their opinions and evaluations. This feedback is recorded by the server and used to improve the analysis algorithms.

[0519] Step 10:

[0520] The server analyzes user feedback and incorporates it into subsequent analysis processes. This enables continuously improving data analysis accuracy.

[0521] (Example 1)

[0522] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0523] A major challenge is the lack of a data analysis system capable of effectively acquiring nationwide mobility information and analyzing it to provide actionable insights. Currently, anonymization of collected data, handling of missing values, multidimensional analysis of data, visualization, and proposal of policy based on analysis results are often performed manually, which is labor-intensive and time-consuming. Furthermore, there is no established method for quickly incorporating user feedback into the system, making it difficult to improve the accuracy of the analysis.

[0524] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0525] In this invention, the server includes means for acquiring movement information from a wide range of locations, means for anonymizing the acquired movement information and processing missing and outlier values, and means for analyzing the pre-processed movement information to generate statistical information. This enables the automation of advanced data analysis and provides practical insights quickly and efficiently.

[0526] "Mobility information" refers to data about the movement of people and goods within a geographical area, and typically includes visitor numbers, length of stay, and movement patterns.

[0527] "Anonymization" is a process that protects privacy by removing or concealing information that could identify a specific individual.

[0528] "Missing values" refer to a state in a dataset where data that should be present is absent, and processing is required to fill in these missing parts.

[0529] An "outlier" is a value that differs significantly from other data points within a dataset, and this can hinder the consistency and interpretation of the data.

[0530] "Statistical information" refers to numerical or graphical results obtained through data analysis, which indicate trends and characteristics of the data.

[0531] "Visualization" is a technique that represents analyzed data as diagrams or graphs to make it easier to understand visually.

[0532] A "draft plan" refers to action guidelines or proposals generated based on data analysis results, and may include specific implementation plans.

[0533] "Artificial intelligence" refers to systems and programs that mimic human cognitive functions, and particularly includes technologies such as machine learning and natural language processing.

[0534] "Arithmetic operations" refer to basic calculations performed on numerical data, including addition, subtraction, multiplication, division, and statistical calculations.

[0535] A "display device" is a device used to visually display data and images, and provides information through a user interface.

[0536] This invention is a data analysis system that effectively analyzes nationwide mobility information and provides practical insights. The following hardware and software are used in implementing this system.

[0537] Data acquisition and preprocessing

[0538] The server retrieves movement information from government agencies and the private sector via API calls over the internet. The database used is a relational database designed to efficiently store a wide range of geographic data. Data anonymization is performed by filtering out personally identifiable information, and the Python Pandas library is used to handle missing or outlier values.

[0539] Data Analysis

[0540] The server analyzes the preprocessed data through an artificial intelligence engine, such as TensorFlow or scikit-learn. Machine learning algorithms perform statistical analysis to extract trends and factors from the dataset. This builds a model based on visitor behavior.

[0541] Visualization and proposal

[0542] The server generates graphs and charts using Matplotlib and Seaborn libraries based on the analysis results. This visual data is integrated into a dashboard accessible to the user via their device, allowing for interactive operation. The generated AI model formulates policy proposals from the analysis results and provides them to the user as prompts.

[0543] To give a concrete example, if a tourism business uses this system, they can visualize the seasonal trends in visitor numbers in a specific region. Based on these results, the generating AI model performs an analysis using a prompt message such as, "Analyze the increasing trend in visitor numbers during the spring season, and propose causes and countermeasures," and provides practical countermeasure proposals.

[0544] In this way, the system helps users gain valuable business insights even without specialized knowledge.

[0545] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0546] Step 1:

[0547] The server retrieves movement information from public institutions and private data providers via APIs. The data received as input includes visitor numbers, dwell time, and movement patterns. The server stores this data in a relational database and compiles it into aggregated movement information. This aggregated data forms the basis for the next processing steps.

[0548] Step 2:

[0549] The server performs anonymization on the movement information aggregated in Step 1. The input is the data stored in Step 1, and the output is anonymized data from which personally identifiable information has been removed. Specifically, this involves removing fields that identify individual visitors and reorganizing information into aggregate units. This ensures that a dataset suitable for analysis is obtained while protecting privacy.

[0550] Step 3:

[0551] The server processes missing and outlier values ​​in the anonymized data resulting from Step 2. It uses the anonymized data from Step 2 as input and outputs clean, consistent data. The server uses the Python Pandas library to impute missing values ​​with the mean or median and filters out outliers. This data cleansing allows for smoother execution of the next analysis step.

[0552] Step 4:

[0553] The server passes the clean data obtained in step 3 to the artificial intelligence engine for statistical analysis. The input is processed data, and the output is the analysis results. Here, a machine learning model is applied using scikit-learn to analyze trends and causal relationships in movement patterns. This analysis allows meaningful insights to be gained from the data.

[0554] Step 5:

[0555] Based on the analysis results generated in step 4, the server uses Matplotlib and Seaborn to create visually easy-to-understand charts. The input is the statistical analysis results, and the output is a visual representation such as a line graph or heatmap. This visualization allows the user to intuitively understand the analysis results.

[0556] Step 6:

[0557] The terminal displays the visual created in step 5 on the dashboard and provides it to the user. The input is the visual data sent from the server, and it functions as an output interface for the user to interactively explore the data. Specifically, the user can set filters on the dashboard and analyze the data under specific conditions.

[0558] Step 7:

[0559] The generation AI automatically generates policy proposals using the analysis results from step 4 and presents them to the user via the terminal. The input consists of the analysis results and existing policy data, and the output is new policy proposals. Users can review these proposals and provide feedback, thereby improving the accuracy of the analysis model. This feedback loop allows the system to continuously evolve.

[0560] (Application Example 1)

[0561] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0562] Traditional customer behavior analysis systems have made it difficult to grasp detailed situations in real time, which has often led to delays in immediate responses and the development of sales promotion strategies, especially in physical stores. Furthermore, the lack of visually intuitive feedback has made it difficult to implement effective measures. A new method is needed to solve these problems and effectively support store operations.

[0563] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0564] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, and, as an extension implementation means, means for displaying the analysis results on a visual device and presenting location-specific movement information based on the analysis results. This makes it possible to grasp real-time customer trends in physical stores and to formulate immediate sales promotion strategies.

[0565] "Mobility data" refers to information about the movement of people and goods within a specific area, including the number of visitors, length of stay, and movement patterns.

[0566] "Anonymization" refers to the process of removing or transforming personally identifiable information from collected data, thereby protecting personal information.

[0567] "Handling missing values" refers to techniques used to fill in missing information in a dataset, thereby maintaining data consistency and reliability.

[0568] "Statistical information" refers to information that shows various numerical values, patterns, and trends obtained through data analysis.

[0569] "Visual devices" refer to equipment used to display digital information in a visually tangible form, and include smart glasses and similar devices.

[0570] "Movement flow information" refers to information about how people and objects move within a specific area, and this allows for the visualization of behavioral patterns.

[0571] The system for realizing this invention mainly consists of a server, a visual device, and a user terminal. The server collects movement data from across the country and performs a series of data processing operations. The server anonymizes the data using Python and handles missing values. It also performs trend analysis on the collected data using an artificial intelligence model (using TensorFlow) and generates statistical information. As the visual device, smart glasses (e.g., smart wearable device) are used, and the analysis results are displayed intuitively using Unity or other lightweight visualization software.

[0572] Specifically, users can view real-time information about foot traffic within the store via a visual device. Based on the server's analysis, the visual device displays the number of visitors and their dwell time in areas where specific products are located as a heatmap, providing store managers with intuitive and useful data. This allows store managers to immediately make decisions such as changing product placement or implementing special sales campaigns.

[0573] An example of a prompt is, "Analyze the behavioral patterns regarding the placement of this product and suggest the optimal placement." This prompt allows users to leverage insights gained from data and translate them into concrete actions.

[0574] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0575] Step 1:

[0576] The server collects movement data from the target area. This data includes the number of people visiting the area around the store, their length of stay, and their movement patterns, and is transmitted to the server via a communication module. The input is raw data collected in real time, and the output is this dataset.

[0577] Step 2:

[0578] The server anonymizes and imputes missing values ​​in the collected movement data. Anonymization protects personal information, and missing values ​​are imputed using machine learning algorithms. The input is raw data, and the output is a consistent and reliable dataset. Specifically, data formatting is performed using Python data processing libraries.

[0579] Step 3:

[0580] The server feeds pre-processed data into a generating AI model (using TensorFlow) to perform trend analysis and movement pattern analysis. Here, the AI ​​model predicts fluctuations in the number of visitors and their length of stay in a specific area. The input is a pre-processed dataset, and the output is analyzed statistical information.

[0581] Step 4:

[0582] The server generates visualization information based on the analysis results. Specifically, it uses Unity to create heatmaps and line graphs, and prepares the data to be sent to the visual device. The input is statistical information, and the output is concrete visualization data.

[0583] Step 5:

[0584] The user's visual devices receive visualization information from the server and display it on the user interface. At this stage, the user can analyze their movement within the store and take immediate action based on the visual information. The input is visualization data, and the output is specific movement information that the user can clearly see.

[0585] Step 6:

[0586] The terminal has the function of sending user feedback to the server, and user interaction contributes to improving the accuracy of the analysis algorithm. The input is user feedback, and the output is data related to improvements to the analysis algorithm.

[0587] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0588] This invention provides a data analysis system that utilizes nationwide mobility data and combines it with an emotion engine based on user feedback. The system processes, analyzes, and optimizes suggestions through multiple processes.

[0589] Data acquisition and preprocessing

[0590] The server connects to an external mobility database to retrieve geographical movement information of people. This dataset is anonymized and missing values ​​are removed to prepare it as clean data for analysis.

[0591] Data analysis and visualization

[0592] The server sends pre-processed data to an artificial intelligence module for statistical analysis. Specific analysis includes correlations between movement patterns and seasonal trends.

[0593] The server creates interactive graphs and charts based on the analysis results and sends them to the terminal. This makes it easier for the user to visually understand the data.

[0594] Suggestion generation and sentiment recognition

[0595] The generation AI automatically generates policy proposals based on the analysis results. Before presenting the proposals, it analyzes the user's emotions using an emotion engine based on user feedback.

[0596] The device receives user feedback and uses an emotion engine to identify the user's emotions along with the content of the feedback. This allows for more precise adjustments to be reflected in proposed policies.

[0597] Application examples

[0598] For example, in the case of a tourism business, the generative AI predicts an increase in the number of visitors to a particular city and proposes a new tourism campaign. This proposal is presented to the tourism business's users through a device, and the AI ​​reads the feedback provided by the users, such as their expectations and concerns about the campaign.

[0599] The emotion engine detects user anxieties from the feedback and adjusts the proposed solutions based on this. Specifically, it reviews the timing of campaigns and the target age group. This process ensures that measures that better meet user needs are implemented.

[0600] Thus, the present invention provides a system that enables more user-friendly and effective data utilization by adaptively adjusting the proposed content while taking into account user emotions as part of data analysis.

[0601] The following describes the processing flow.

[0602] Step 1:

[0603] The server retrieves the latest travel data from a nationwide travel database. This data includes information such as visited locations, times, number of visitors, and length of stay. The retrieved data is not only stored but is also immediately prepared for subsequent processing.

[0604] Step 2:

[0605] Upon receiving data, the server immediately begins the anonymization process. It removes or transforms personally identifiable information from the dataset to ensure privacy. Furthermore, it uses inference algorithms to fill in any missing data, preparing it for analysis.

[0606] Step 3:

[0607] The server passes pre-processed data to an artificial intelligence (AI) engine, which then analyzes movement patterns. The AI ​​uses time-series analysis and clustering techniques to identify regional trends and correlations. For example, the AI ​​can identify increases or decreases in visitors due to specific events.

[0608] Step 4:

[0609] The server generates line graphs, heatmaps, and other visualizations using visualization tools based on the AI ​​analysis results. These visuals are dynamically configured to provide different analytical perspectives. The generated visuals are then compiled into a dashboard.

[0610] Step 5:

[0611] The device launches the dashboard and displays generated graphs and charts to the user. The user can click on these interactive visuals to view details or zoom in on specific datasets.

[0612] Step 6:

[0613] The AI ​​generates proposals automatically based on the analysis results and presents them to the user via their device. These proposals include specific marketing strategies and event implementation guidelines.

[0614] Step 7:

[0615] Users evaluate the presented suggestions and provide feedback. This feedback includes specific opinions and impressions, and emotional responses are also recorded.

[0616] Step 8:

[0617] The device sends the input feedback to an emotion engine, which analyzes the user's emotions. For example, it extracts satisfaction levels and concerns regarding a suggestion through text analysis.

[0618] Step 9:

[0619] The server adjusts the proposed measures based on the analysis results of the emotion engine. It modifies the measures in response to emotional feedback and re-presents the optimized proposals to the user.

[0620] Step 10:

[0621] Further feedback from users will be used to improve the analysis and suggestion process in the future. The server will analyze this data to help improve the overall accuracy of the system.

[0622] (Example 2)

[0623] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0624] Modern data analysis systems struggle to generate plans that adequately reflect user emotions and feedback, thus requiring flexible responses tailored to user needs. However, in conventional systems, data collection, analysis, and proposal generation are performed independently in each process, making it challenging to incorporate emotion-based feedback from users.

[0625] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0626] In this invention, the server includes means for acquiring geographical information, means for anonymizing and processing missing values ​​from the acquired information, and means for generating statistical information. This enables the automatic generation and adjustment of suggestions that take user sentiment into consideration.

[0627] "Geographic information" refers to data about the location or movement of individuals or groups, and includes spatial information related to a specific region.

[0628] "Anonymization" is a process that removes or transforms elements that could identify an individual from data in order to protect privacy.

[0629] "Handling missing values" is a method used to impart missing values ​​to a dataset, and is performed to maintain data integrity.

[0630] "Statistical information" is a collection of numerical and conceptual data characteristics obtained by analyzing data.

[0631] "Charts and diagrams" are visual representations of data, including graphs and charts, and are a means of making information easier to understand intuitively.

[0632] A "plan" is a proposal outlining specific actions and measures generated based on analyzed data and statistical information.

[0633] An "intelligent processing device" is a system or program capable of performing complex data processing, and is usually realized using artificial intelligence technology.

[0634] This invention is a data analysis system that utilizes geographical information and aims to incorporate user emotional feedback. The system collects large amounts of movement data, cleans it up through anonymization and missing value handling, and analyzes it as statistical information. The server makes API requests to an external database to collect initial data. In this process, geographical information is anonymized using anonymization techniques and missing value imputation algorithms to protect privacy. Data organization and processing are performed using Python's Pandas and NumPy.

[0635] Next, the server performs statistical analysis using an artificial intelligence module to understand the correlations and seasonal trends in movement patterns. During this process, the intelligent processing unit demonstrates high computational power and generates relevant statistical information. After analysis, the server visualizes the data as graphs and charts and sends them to the terminal. Here, specialized visualization libraries such as Matplotlib and D3.js are used.

[0636] In the generative AI model, the server automatically generates a plan based on statistical information. In this process, the generative AI constructs the optimal measures based on prompt statements. For example, a prompt such as "Propose a campaign if the number of visitors increases in a specific region" might be used.

[0637] Ultimately, the device receives user feedback, analyzes emotions using an emotion recognition engine, and incorporates the user's emotional feedback into the plan. This entire process allows for flexible measures tailored to user needs, enabling more refined and personalized suggestions.

[0638] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0639] Step 1:

[0640] The server accesses an external database to retrieve movement data. The input is raw data obtained via an API request. This data includes an individual's location information and movement history. The output is the raw geographical information retrieved. This raw data is retained for subsequent processing.

[0641] Step 2:

[0642] The server performs anonymization and missing value handling on the acquired raw data. The input is the raw data acquired in step 1. Anonymization removes elements that can identify individuals, and missing value handling uses methods such as mean imputation and mode imputation to fill in the incomplete parts of the data. The output is clean, analyzable geographical information.

[0643] Step 3:

[0644] The server sends clean data to the artificial intelligence module for statistical analysis. The input is the clean data, which is the output of step 2. The AI ​​module recognizes patterns in the data and analyzes correlations between movement patterns, seasonal factors, and so on. The output is the relevant statistical information.

[0645] Step 4:

[0646] The server generates interactive graphs and charts based on the analysis results. The input is the statistical information obtained in step 3. For visualization, visualization libraries such as Matplotlib and D3.js are used to transform the data into a visually easy-to-understand format. The output is a data visualization.

[0647] Step 5:

[0648] The terminal displays the generated graphs and charts to the user. The input is the data visualization from step 4. Based on this information, the user can understand the proposed future plan. The output leads to user understanding and feedback.

[0649] Step 6:

[0650] The generation AI automatically generates a plan based on statistical information. The input is the statistical information from step 3. The generated plan can be flexibly modified using prompts. For example, a prompt such as "Propose a campaign to coincide with the increase in the number of visitors to a specific region" is used. The output is the plan.

[0651] Step 7:

[0652] The device receives feedback from the user and analyzes emotions using an emotion recognition engine. The input consists of the proposed plan generated in step 6 and the user's feedback. Emotion analysis assigns emotion labels such as positive, negative, and neutral. The output is the analyzed emotion information.

[0653] Step 8:

[0654] The server adjusts the proposed plan based on the emotion analysis results. The input is the emotion information analyzed in step 7. If negative emotions such as anxiety are detected, the timing and target audience of the proposed plan are re-evaluated. The output is the proposed plan adjusted based on user feedback.

[0655] (Application Example 2)

[0656] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0657] In recent years, there has been a growing demand for services that meet the diverse needs of individual users. However, conventional systems have faced challenges in providing optimal suggestions that take into account users' emotions and past behavioral patterns. Furthermore, it has been difficult to provide more refined and personalized services by effectively analyzing dynamic user behavior data and adapting to emotions.

[0658] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0659] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, means for generating graphs and charts to visualize the generated statistical information, means for automatically generating policy proposals based on the analyzed statistical information, means for presenting the proposed policy proposals to the user and receiving feedback, means for selecting recommended services based on the user's past behavior history and location information data, and means for analyzing user emotions using an emotion engine based on the feedback and adjusting the proposed content. This makes it possible to make optimal proposals that take into account the individual emotions and actions of each user.

[0660] "Movement data" refers to location information and movement history of people acquired on a nationwide scale.

[0661] "Anonymization" refers to the process of removing or masking personally identifiable information from individual data.

[0662] "Missing value handling" refers to the process of filling in missing elements in a dataset.

[0663] "Statistical information" refers to numerical information that shows patterns and trends obtained by analyzing collected data.

[0664] "Graphs and charts" refer to graphical representations used to visually show trends and relationships in data.

[0665] A "proposal" refers to a plan of actions or strategies proposed to users.

[0666] "Feedback" refers to reaction information such as opinions, evaluations, and emotions provided by users.

[0667] An "emotion engine" refers to an algorithm that analyzes a user's emotions from their words and actions and reflects the results in the system.

[0668] "Behavioral history" refers to a record of actions a user has taken in the past.

[0669] "Location information" refers to data that indicates a user's current and past geographical location.

[0670] The system that realizes this invention consists of a server, a terminal, and a user. The server acquires nationwide movement data, anonymizes the collected data and handles missing values, and then performs data analysis. In the analysis process, movement patterns and statistical information are generated using Python's Pandas and Scikit-learn. The server visualizes these analysis results, generates interactive graphs and charts, and sends them to the terminal.

[0671] On the device, results are presented to the user through an interface built with React Native. Users can provide feedback based on this information. User feedback is analyzed using an emotion engine, and the user's emotions are identified using Anaconda and NLP libraries. Based on the acquired user emotion information, the server adjusts proposed measures using a generative AI model and further suggests appropriate services and products.

[0672] As a concrete example, in the case of a food delivery service, the server generates food delivery recommendations based on the user's past order history and current location information. If the user provides feedback such as "I want to eat something spicy today," sentiment analysis is used to select and suggest restaurants that serve spicy food.

[0673] An example of a prompt message is, "Based on past order history and current location, suggest a healthy lunch that can be enjoyed safely and quickly." This forms the basis for generating suggestions tailored to the user's needs.

[0674] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0675] Step 1:

[0676] The server retrieves nationwide mobility data from an external database. It takes people's location information and movement history as input, anonymizes it, and handles missing values. The output is clean, analyzable data.

[0677] Step 2:

[0678] The server analyzes preprocessed data using Python's Pandas and Scikit-learn libraries. It receives clean movement data as input and performs data calculations to generate movement patterns and statistics. The output provides statistical information showing the trends and correlations of movement patterns.

[0679] Step 3:

[0680] The server generates graphs and charts to visualize the analyzed statistical information. It receives statistical information as input and performs data processing to generate interactive charts and graphs. The output consists of visually easy-to-understand graphs and charts.

[0681] Step 4:

[0682] The terminal displays suggestions to the user based on graphs and charts sent from the server. It receives visualized information as input and displays it on the screen. As output, it obtains an interface that the user can view.

[0683] Step 5:

[0684] The user provides feedback based on the information presented. The input involves considering the proposal and entering feedback into the terminal. The output provides information about the user's expectations and concerns.

[0685] Step 6:

[0686] The terminal receives feedback from the user and sends it to the server. As input, it receives user feedback and passes it to the server. As output, the feedback information is transmitted to the server.

[0687] Step 7:

[0688] The server analyzes the user's emotions using an emotion engine. It takes feedback information as input and performs emotion analysis. The output is data indicating the user's emotions.

[0689] Step 8:

[0690] The server automatically generates adjusted policy proposals using a generative AI model. It receives sentiment analysis results and past behavioral data as input and performs the generation process. The output is a specific, adjusted service proposal.

[0691] Step 9:

[0692] The terminal then presents the adjusted policy proposal to the user again. It receives the optimized proposal as input and displays it on the user's screen. As output, it obtains an interface for the user to finalize the proposal.

[0693] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0694] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0695] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0696] [Fourth Embodiment]

[0697] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0698] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0699] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0700] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0701] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0702] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0703] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0704] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0705] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0706] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0707] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0708] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0709] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0710] This invention provides a data analysis system that effectively utilizes nationwide mobility data. The system processes data through automated processes at each stage, ultimately providing insights for the user. Its specific form is described below.

[0711] Data collection

[0712] The server periodically collects movement data for the target area. This data includes the number of visitors to each area, their length of stay, and their movement patterns.

[0713] Data preprocessing

[0714] The server anonymizes the collected data to ensure the protection of personal information. Furthermore, it automatically handles the imputation of missing values ​​and the identification and correction of outliers, thereby improving data consistency and reliability.

[0715] Data Analysis

[0716] The server sends the pre-processed dataset to the artificial intelligence for statistical analysis. This involves trend analysis of movement patterns and modeling fluctuations in visitor numbers related to specific factors.

[0717] visualization

[0718] Based on statistical information generated by the server, the system automatically generates graphs and charts that are easy to understand visually. These visuals can, for example, show fluctuations in past visitor numbers using line graphs, or indicate the popularity of specific regions using heatmaps.

[0719] Proposal and User Interaction

[0720] The device provides users with generated graphs and charts as dashboards. Through interactive operations, users can explore the data in depth and access detailed analysis results based on specific conditions.

[0721] The generating AI automatically proposes policy options based on the analysis results and presents them to the user via the device. Users can evaluate these policy options and provide feedback, thereby contributing to improving the accuracy of the analysis.

[0722] Specific example

[0723] Tourism businesses can use this system to visualize seasonal visitor trends in their area. For example, if visitor numbers are increasing in the spring, the artificial intelligence will analyze the cause and identify that an increase in spring events is a contributing factor. Based on this, it will suggest a new spring campaign. Users can review the suggestions and decide whether to incorporate them into their marketing strategy.

[0724] Thus, this invention provides a comprehensive system that enables users to effectively utilize data and support decision-making, even without specialized knowledge.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] The server connects to a nationwide mobility database to retrieve the latest mobility data. This data includes attributes such as location, time, number of visitors, and length of stay.

[0728] Step 2:

[0729] The server anonymizes the acquired data. It removes personally identifiable identifiers and transforms the data to meet data security standards.

[0730] Step 3:

[0731] The server performs data preprocessing. If there are missing values, it uses a specific algorithm to impute them, and if outliers are detected, it corrects or removes them to prepare a clean dataset.

[0732] Step 4:

[0733] The server sends clean data to an artificial intelligence module, which then begins data analysis. Here, statistical models are applied to analyze, for example, movement patterns by time of day or region.

[0734] Step 5:

[0735] Generative AI generates statistical information based on analysis results, identifying correlations and trends in the data. For example, it can find a tendency for the number of visitors to increase during a certain period when a specific event is occurring.

[0736] Step 6:

[0737] The server generates graphs and charts to visualize the analysis results. These include line graphs, bar graphs, and heatmaps.

[0738] Step 7:

[0739] The device displays generated graphs and charts on the dashboard, allowing users to interactively explore the data. Users can use this to view data details and delve deeper into areas of interest.

[0740] Step 8:

[0741] The AI ​​generates policy proposals automatically based on the analysis results and presents them to the user via the device. For example, it may suggest the timing of promotions for specific products or plan new events.

[0742] Step 9:

[0743] Users review the proposed measures and provide feedback, including their opinions and evaluations. This feedback is recorded by the server and used to improve the analysis algorithms.

[0744] Step 10:

[0745] The server analyzes user feedback and incorporates it into subsequent analysis processes. This enables continuously improving data analysis accuracy.

[0746] (Example 1)

[0747] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0748] A major challenge is the lack of a data analysis system capable of effectively acquiring nationwide mobility information and analyzing it to provide actionable insights. Currently, anonymization of collected data, handling of missing values, multidimensional analysis of data, visualization, and proposal of policy based on analysis results are often performed manually, which is labor-intensive and time-consuming. Furthermore, there is no established method for quickly incorporating user feedback into the system, making it difficult to improve the accuracy of the analysis.

[0749] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0750] In this invention, the server includes means for acquiring movement information from a wide range of locations, means for anonymizing the acquired movement information and processing missing and outlier values, and means for analyzing the pre-processed movement information to generate statistical information. This enables the automation of advanced data analysis and provides practical insights quickly and efficiently.

[0751] "Mobility information" refers to data about the movement of people and goods within a geographical area, and typically includes visitor numbers, length of stay, and movement patterns.

[0752] "Anonymization" is a process that protects privacy by removing or concealing information that could identify a specific individual.

[0753] "Missing values" refer to a state in a dataset where data that should be present is absent, and processing is required to fill in these missing parts.

[0754] An "outlier" is a value that differs significantly from other data points within a dataset, and this can hinder the consistency and interpretation of the data.

[0755] "Statistical information" refers to numerical or graphical results obtained through data analysis, which indicate trends and characteristics of the data.

[0756] "Visualization" is a technique that represents analyzed data as diagrams or graphs to make it easier to understand visually.

[0757] A "draft plan" refers to action guidelines or proposals generated based on data analysis results, and may include specific implementation plans.

[0758] "Artificial intelligence" refers to systems and programs that mimic human cognitive functions, and particularly includes technologies such as machine learning and natural language processing.

[0759] "Arithmetic operations" refer to basic calculations performed on numerical data, including addition, subtraction, multiplication, division, and statistical calculations.

[0760] A "display device" is a device used to visually display data and images, and provides information through a user interface.

[0761] This invention is a data analysis system that effectively analyzes nationwide mobility information and provides practical insights. The following hardware and software are used in implementing this system.

[0762] Data acquisition and preprocessing

[0763] The server retrieves movement information from government agencies and the private sector via API calls over the internet. The database used is a relational database designed to efficiently store a wide range of geographic data. Data anonymization is performed by filtering out personally identifiable information, and the Python Pandas library is used to handle missing or outlier values.

[0764] Data Analysis

[0765] The server analyzes the preprocessed data through an artificial intelligence engine, such as TensorFlow or scikit-learn. Machine learning algorithms perform statistical analysis to extract trends and factors from the dataset. This builds a model based on visitor behavior.

[0766] Visualization and proposal

[0767] The server generates graphs and charts using Matplotlib and Seaborn libraries based on the analysis results. This visual data is integrated into a dashboard accessible to the user via their device, allowing for interactive operation. The generated AI model formulates policy proposals from the analysis results and provides them to the user as prompts.

[0768] To give a concrete example, if a tourism business uses this system, they can visualize the seasonal trends in visitor numbers in a specific region. Based on these results, the generating AI model performs an analysis using a prompt message such as, "Analyze the increasing trend in visitor numbers during the spring season, and propose causes and countermeasures," and provides practical countermeasure proposals.

[0769] In this way, the system helps users gain valuable business insights even without specialized knowledge.

[0770] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0771] Step 1:

[0772] The server retrieves movement information from public institutions and private data providers via APIs. The data received as input includes visitor numbers, dwell time, and movement patterns. The server stores this data in a relational database and compiles it into aggregated movement information. This aggregated data forms the basis for the next processing steps.

[0773] Step 2:

[0774] The server performs anonymization on the movement information aggregated in Step 1. The input is the data stored in Step 1, and the output is anonymized data from which personally identifiable information has been removed. Specifically, this involves removing fields that identify individual visitors and reorganizing information into aggregate units. This ensures that a dataset suitable for analysis is obtained while protecting privacy.

[0775] Step 3:

[0776] The server processes missing and outlier values ​​in the anonymized data resulting from Step 2. It uses the anonymized data from Step 2 as input and outputs clean, consistent data. The server uses the Python Pandas library to impute missing values ​​with the mean or median and filters out outliers. This data cleansing allows for smoother execution of the next analysis step.

[0777] Step 4:

[0778] The server passes the clean data obtained in step 3 to the artificial intelligence engine for statistical analysis. The input is processed data, and the output is the analysis results. Here, a machine learning model is applied using scikit-learn to analyze trends and causal relationships in movement patterns. This analysis allows meaningful insights to be gained from the data.

[0779] Step 5:

[0780] Based on the analysis results generated in step 4, the server uses Matplotlib and Seaborn to create visually easy-to-understand charts. The input is the statistical analysis results, and the output is a visual representation such as a line graph or heatmap. This visualization allows the user to intuitively understand the analysis results.

[0781] Step 6:

[0782] The terminal displays the visual created in step 5 on the dashboard and provides it to the user. The input is the visual data sent from the server, and it functions as an output interface for the user to interactively explore the data. Specifically, the user can set filters on the dashboard and analyze the data under specific conditions.

[0783] Step 7:

[0784] The generation AI automatically generates policy proposals using the analysis results from step 4 and presents them to the user via the terminal. The input consists of the analysis results and existing policy data, and the output is new policy proposals. Users can review these proposals and provide feedback, thereby improving the accuracy of the analysis model. This feedback loop allows the system to continuously evolve.

[0785] (Application Example 1)

[0786] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] Traditional customer behavior analysis systems have made it difficult to grasp detailed situations in real time, which has often led to delays in immediate responses and the development of sales promotion strategies, especially in physical stores. Furthermore, the lack of visually intuitive feedback has made it difficult to implement effective measures. A new method is needed to solve these problems and effectively support store operations.

[0788] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0789] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, and, as an extension implementation means, means for displaying the analysis results on a visual device and presenting location-specific movement information based on the analysis results. This makes it possible to grasp real-time customer trends in physical stores and to formulate immediate sales promotion strategies.

[0790] "Mobility data" refers to information about the movement of people and goods within a specific area, including the number of visitors, length of stay, and movement patterns.

[0791] "Anonymization" refers to the process of removing or transforming personally identifiable information from collected data, thereby protecting personal information.

[0792] "Handling missing values" refers to techniques used to fill in missing information in a dataset, thereby maintaining data consistency and reliability.

[0793] "Statistical information" refers to information that shows various numerical values, patterns, and trends obtained through data analysis.

[0794] "Visual devices" refer to equipment used to display digital information in a visually tangible form, and include smart glasses and similar devices.

[0795] "Movement flow information" refers to information about how people and objects move within a specific area, and this allows for the visualization of behavioral patterns.

[0796] The system for realizing this invention mainly consists of a server, a visual device, and a user terminal. The server collects movement data from across the country and performs a series of data processing operations. The server anonymizes the data using Python and handles missing values. It also performs trend analysis on the collected data using an artificial intelligence model (using TensorFlow) and generates statistical information. As the visual device, smart glasses (e.g., smart wearable device) are used, and the analysis results are displayed intuitively using Unity or other lightweight visualization software.

[0797] Specifically, users can view real-time information about foot traffic within the store via a visual device. Based on the server's analysis, the visual device displays the number of visitors and their dwell time in areas where specific products are located as a heatmap, providing store managers with intuitive and useful data. This allows store managers to immediately make decisions such as changing product placement or implementing special sales campaigns.

[0798] An example of a prompt is, "Analyze the behavioral patterns regarding the placement of this product and suggest the optimal placement." This prompt allows users to leverage insights gained from data and translate them into concrete actions.

[0799] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0800] Step 1:

[0801] The server collects movement data from the target area. This data includes the number of people visiting the area around the store, their length of stay, and their movement patterns, and is transmitted to the server via a communication module. The input is raw data collected in real time, and the output is this dataset.

[0802] Step 2:

[0803] The server anonymizes and imputes missing values ​​in the collected movement data. Anonymization protects personal information, and missing values ​​are imputed using machine learning algorithms. The input is raw data, and the output is a consistent and reliable dataset. Specifically, data formatting is performed using Python data processing libraries.

[0804] Step 3:

[0805] The server feeds pre-processed data into a generating AI model (using TensorFlow) to perform trend analysis and movement pattern analysis. Here, the AI ​​model predicts fluctuations in the number of visitors and their length of stay in a specific area. The input is a pre-processed dataset, and the output is analyzed statistical information.

[0806] Step 4:

[0807] The server generates visualization information based on the analysis results. Specifically, it uses Unity to create heatmaps and line graphs, and prepares the data to be sent to the visual device. The input is statistical information, and the output is concrete visualization data.

[0808] Step 5:

[0809] The user's visual devices receive visualization information from the server and display it on the user interface. At this stage, the user can analyze their movement within the store and take immediate action based on the visual information. The input is visualization data, and the output is specific movement information that the user can clearly see.

[0810] Step 6:

[0811] The terminal has the function of sending user feedback to the server, and user interaction contributes to improving the accuracy of the analysis algorithm. The input is user feedback, and the output is data related to improvements to the analysis algorithm.

[0812] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0813] This invention provides a data analysis system that utilizes nationwide mobility data and combines it with an emotion engine based on user feedback. The system processes, analyzes, and optimizes suggestions through multiple processes.

[0814] Data acquisition and preprocessing

[0815] The server connects to an external mobility database to retrieve geographical movement information of people. This dataset is anonymized and missing values ​​are removed to prepare it as clean data for analysis.

[0816] Data analysis and visualization

[0817] The server sends pre-processed data to an artificial intelligence module for statistical analysis. Specific analysis includes correlations between movement patterns and seasonal trends.

[0818] The server creates interactive graphs and charts based on the analysis results and sends them to the terminal. This makes it easier for the user to visually understand the data.

[0819] Suggestion generation and sentiment recognition

[0820] The generation AI automatically generates policy proposals based on the analysis results. Before presenting the proposals, it analyzes the user's emotions using an emotion engine based on user feedback.

[0821] The device receives user feedback and uses an emotion engine to identify the user's emotions along with the content of the feedback. This allows for more precise adjustments to be reflected in proposed policies.

[0822] Application examples

[0823] For example, in the case of a tourism business, the generative AI predicts an increase in the number of visitors to a particular city and proposes a new tourism campaign. This proposal is presented to the tourism business's users through a device, and the AI ​​reads the feedback provided by the users, such as their expectations and concerns about the campaign.

[0824] The emotion engine detects user anxieties from the feedback and adjusts the proposed solutions based on this. Specifically, it reviews the timing of campaigns and the target age group. This process ensures that measures that better meet user needs are implemented.

[0825] Thus, the present invention provides a system that enables more user-friendly and effective data utilization by adaptively adjusting the proposed content while taking into account user emotions as part of data analysis.

[0826] The following describes the processing flow.

[0827] Step 1:

[0828] The server retrieves the latest travel data from a nationwide travel database. This data includes information such as visited locations, times, number of visitors, and length of stay. The retrieved data is not only stored but is also immediately prepared for subsequent processing.

[0829] Step 2:

[0830] Upon receiving data, the server immediately begins the anonymization process. It removes or transforms personally identifiable information from the dataset to ensure privacy. Furthermore, it uses inference algorithms to fill in any missing data, preparing it for analysis.

[0831] Step 3:

[0832] The server passes pre-processed data to an artificial intelligence (AI) engine, which then analyzes movement patterns. The AI ​​uses time-series analysis and clustering techniques to identify regional trends and correlations. For example, the AI ​​can identify increases or decreases in visitors due to specific events.

[0833] Step 4:

[0834] The server generates line graphs, heatmaps, and other visualizations using visualization tools based on the AI ​​analysis results. These visuals are dynamically configured to provide different analytical perspectives. The generated visuals are then compiled into a dashboard.

[0835] Step 5:

[0836] The device launches the dashboard and displays generated graphs and charts to the user. The user can click on these interactive visuals to view details or zoom in on specific datasets.

[0837] Step 6:

[0838] The AI ​​generates proposals automatically based on the analysis results and presents them to the user via their device. These proposals include specific marketing strategies and event implementation guidelines.

[0839] Step 7:

[0840] Users evaluate the presented suggestions and provide feedback. This feedback includes specific opinions and impressions, and emotional responses are also recorded.

[0841] Step 8:

[0842] The device sends the input feedback to an emotion engine, which analyzes the user's emotions. For example, it extracts satisfaction levels and concerns regarding a suggestion through text analysis.

[0843] Step 9:

[0844] The server adjusts the proposed measures based on the analysis results of the emotion engine. It modifies the measures in response to emotional feedback and re-presents the optimized proposals to the user.

[0845] Step 10:

[0846] Further feedback from users will be used to improve the analysis and suggestion process in the future. The server will analyze this data to help improve the overall accuracy of the system.

[0847] (Example 2)

[0848] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0849] Modern data analysis systems struggle to generate plans that adequately reflect user emotions and feedback, thus requiring flexible responses tailored to user needs. However, in conventional systems, data collection, analysis, and proposal generation are performed independently in each process, making it challenging to incorporate emotion-based feedback from users.

[0850] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0851] In this invention, the server includes means for acquiring geographical information, means for anonymizing and processing missing values ​​from the acquired information, and means for generating statistical information. This enables the automatic generation and adjustment of suggestions that take user sentiment into consideration.

[0852] "Geographic information" refers to data about the location or movement of individuals or groups, and includes spatial information related to a specific region.

[0853] "Anonymization" is a process that removes or transforms elements that could identify an individual from data in order to protect privacy.

[0854] "Handling missing values" is a method used to impart missing values ​​to a dataset, and is performed to maintain data integrity.

[0855] "Statistical information" is a collection of numerical and conceptual data characteristics obtained by analyzing data.

[0856] "Charts and diagrams" are visual representations of data, including graphs and charts, and are a means of making information easier to understand intuitively.

[0857] A "plan" is a proposal outlining specific actions and measures generated based on analyzed data and statistical information.

[0858] An "intelligent processing device" is a system or program capable of performing complex data processing, and is usually realized using artificial intelligence technology.

[0859] This invention is a data analysis system that utilizes geographical information and aims to incorporate user emotional feedback. The system collects large amounts of movement data, cleans it up through anonymization and missing value handling, and analyzes it as statistical information. The server makes API requests to an external database to collect initial data. In this process, geographical information is anonymized using anonymization techniques and missing value imputation algorithms to protect privacy. Data organization and processing are performed using Python's Pandas and NumPy.

[0860] Next, the server performs statistical analysis using an artificial intelligence module to understand the correlations and seasonal trends in movement patterns. During this process, the intelligent processing unit demonstrates high computational power and generates relevant statistical information. After analysis, the server visualizes the data as graphs and charts and sends them to the terminal. Here, specialized visualization libraries such as Matplotlib and D3.js are used.

[0861] In the generative AI model, the server automatically generates a plan based on statistical information. In this process, the generative AI constructs the optimal measures based on prompt statements. For example, a prompt such as "Propose a campaign if the number of visitors increases in a specific region" might be used.

[0862] Ultimately, the device receives user feedback, analyzes emotions using an emotion recognition engine, and incorporates the user's emotional feedback into the plan. This entire process allows for flexible measures tailored to user needs, enabling more refined and personalized suggestions.

[0863] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0864] Step 1:

[0865] The server accesses an external database to retrieve movement data. The input is raw data obtained via an API request. This data includes an individual's location information and movement history. The output is the raw geographical information retrieved. This raw data is retained for subsequent processing.

[0866] Step 2:

[0867] The server performs anonymization and missing value handling on the acquired raw data. The input is the raw data acquired in step 1. Anonymization removes elements that can identify individuals, and missing value handling uses methods such as mean imputation and mode imputation to fill in the incomplete parts of the data. The output is clean, analyzable geographical information.

[0868] Step 3:

[0869] The server sends clean data to the artificial intelligence module for statistical analysis. The input is the clean data, which is the output of step 2. The AI ​​module recognizes patterns in the data and analyzes correlations between movement patterns, seasonal factors, and so on. The output is the relevant statistical information.

[0870] Step 4:

[0871] The server generates interactive graphs and charts based on the analysis results. The input is the statistical information obtained in step 3. For visualization, visualization libraries such as Matplotlib and D3.js are used to transform the data into a visually easy-to-understand format. The output is a data visualization.

[0872] Step 5:

[0873] The terminal displays the generated graphs and charts to the user. The input is the data visualization from step 4. Based on this information, the user can understand the proposed future plan. The output leads to user understanding and feedback.

[0874] Step 6:

[0875] The generation AI automatically generates a plan based on statistical information. The input is the statistical information from step 3. The generated plan can be flexibly modified using prompts. For example, a prompt such as "Propose a campaign to coincide with the increase in the number of visitors to a specific region" is used. The output is the plan.

[0876] Step 7:

[0877] The device receives feedback from the user and analyzes emotions using an emotion recognition engine. The input consists of the proposed plan generated in step 6 and the user's feedback. Emotion analysis assigns emotion labels such as positive, negative, and neutral. The output is the analyzed emotion information.

[0878] Step 8:

[0879] The server adjusts the proposed plan based on the emotion analysis results. The input is the emotion information analyzed in step 7. If negative emotions such as anxiety are detected, the timing and target audience of the proposed plan are re-evaluated. The output is the proposed plan adjusted based on user feedback.

[0880] (Application Example 2)

[0881] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0882] In recent years, there has been a growing demand for services that meet the diverse needs of individual users. However, conventional systems have faced challenges in providing optimal suggestions that take into account users' emotions and past behavioral patterns. Furthermore, it has been difficult to provide more refined and personalized services by effectively analyzing dynamic user behavior data and adapting to emotions.

[0883] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0884] In this invention, the server includes means for acquiring nationwide movement data, means for anonymizing and processing missing values ​​in the acquired movement data, means for analyzing the pre-processed movement data and generating statistical information, means for generating graphs and charts to visualize the generated statistical information, means for automatically generating policy proposals based on the analyzed statistical information, means for presenting the proposed policy proposals to the user and receiving feedback, means for selecting recommended services based on the user's past behavior history and location information data, and means for analyzing user emotions using an emotion engine based on the feedback and adjusting the proposed content. This makes it possible to make optimal proposals that take into account the individual emotions and actions of each user.

[0885] "Movement data" refers to location information and movement history of people acquired on a nationwide scale.

[0886] "Anonymization" refers to the process of removing or masking personally identifiable information from individual data.

[0887] "Missing value handling" refers to the process of filling in missing elements in a dataset.

[0888] "Statistical information" refers to numerical information that shows patterns and trends obtained by analyzing collected data.

[0889] "Graphs and charts" refer to graphical representations used to visually show trends and relationships in data.

[0890] A "proposal" refers to a plan of actions or strategies proposed to users.

[0891] "Feedback" refers to reaction information such as opinions, evaluations, and emotions provided by users.

[0892] An "emotion engine" refers to an algorithm that analyzes a user's emotions from their words and actions and reflects the results in the system.

[0893] "Behavioral history" refers to a record of actions a user has taken in the past.

[0894] "Location information" refers to data that indicates a user's current and past geographical location.

[0895] The system that realizes this invention consists of a server, a terminal, and a user. The server acquires nationwide movement data, anonymizes the collected data and handles missing values, and then performs data analysis. In the analysis process, movement patterns and statistical information are generated using Python's Pandas and Scikit-learn. The server visualizes these analysis results, generates interactive graphs and charts, and sends them to the terminal.

[0896] On the device, results are presented to the user through an interface built with React Native. Users can provide feedback based on this information. User feedback is analyzed using an emotion engine, and the user's emotions are identified using Anaconda and NLP libraries. Based on the acquired user emotion information, the server adjusts proposed measures using a generative AI model and further suggests appropriate services and products.

[0897] As a concrete example, in the case of a food delivery service, the server generates food delivery recommendations based on the user's past order history and current location information. If the user provides feedback such as "I want to eat something spicy today," sentiment analysis is used to select and suggest restaurants that serve spicy food.

[0898] An example of a prompt message is, "Based on past order history and current location, suggest a healthy lunch that can be enjoyed safely and quickly." This forms the basis for generating suggestions tailored to the user's needs.

[0899] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0900] Step 1:

[0901] The server retrieves nationwide mobility data from an external database. It takes people's location information and movement history as input, anonymizes it, and handles missing values. The output is clean, analyzable data.

[0902] Step 2:

[0903] The server analyzes preprocessed data using Python's Pandas and Scikit-learn libraries. It receives clean movement data as input and performs data calculations to generate movement patterns and statistics. The output provides statistical information showing the trends and correlations of movement patterns.

[0904] Step 3:

[0905] The server generates graphs and charts to visualize the analyzed statistical information. It receives statistical information as input and performs data processing to generate interactive charts and graphs. The output consists of visually easy-to-understand graphs and charts.

[0906] Step 4:

[0907] The terminal displays suggestions to the user based on graphs and charts sent from the server. It receives visualized information as input and displays it on the screen. As output, it obtains an interface that the user can view.

[0908] Step 5:

[0909] The user provides feedback based on the information presented. The input involves considering the proposal and entering feedback into the terminal. The output provides information about the user's expectations and concerns.

[0910] Step 6:

[0911] The terminal receives feedback from the user and sends it to the server. As input, it receives user feedback and passes it to the server. As output, the feedback information is transmitted to the server.

[0912] Step 7:

[0913] The server analyzes the user's emotions using an emotion engine. It takes feedback information as input and performs emotion analysis. The output is data indicating the user's emotions.

[0914] Step 8:

[0915] The server automatically generates adjusted policy proposals using a generative AI model. It receives sentiment analysis results and past behavioral data as input and performs the generation process. The output is a specific, adjusted service proposal.

[0916] Step 9:

[0917] The terminal then presents the adjusted policy proposal to the user again. It receives the optimized proposal as input and displays it on the user's screen. As output, it obtains an interface for the user to finalize the proposal.

[0918] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0919] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0920] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0921] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0922] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0923] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0924] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0925] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0926] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0927] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0928] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0929] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0930] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0931] 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.

[0932] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0933] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0934] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0935] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0936] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0937] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0938] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0939] The following is further disclosed regarding the embodiments described above.

[0940] (Claim 1)

[0941] Means for obtaining nationwide mobility data,

[0942] A means for anonymizing and processing missing values ​​in the acquired movement data,

[0943] A means for analyzing pre-processed movement data and generating statistical information,

[0944] A means of generating graphs and charts to visualize the generated statistical information,

[0945] A means of automatically generating policy proposals based on analyzed statistical information,

[0946] A means of presenting proposed measures to users and receiving feedback from them,

[0947] A system that includes this.

[0948] (Claim 2)

[0949] The system according to claim 1, which utilizes artificial intelligence to perform a series of arithmetic operations in the analysis of movement data.

[0950] (Claim 3)

[0951] The system according to claim 1, comprising means for successively improving the analysis algorithm based on user feedback.

[0952] "Example 1"

[0953] (Claim 1)

[0954] Means for acquiring movement information from a wide area,

[0955] A means for anonymizing acquired movement information and processing missing and outlier values,

[0956] A means for analyzing pre-processed movement information to generate statistical information,

[0957] A means for generating figures and tables to visualize the generated statistical information,

[0958] A means for automatically generating a plan based on analyzed statistical information,

[0959] A means of presenting the proposed plan to users and receiving their feedback,

[0960] A means of performing arithmetic operations using artificial intelligence and analyzing trends in movement information,

[0961] A means for providing the generated figures and tables to a user-operable display device,

[0962] A system that includes this.

[0963] (Claim 2)

[0964] The system according to claim 1, comprising means for continuously improving the analysis procedure for subsequent times based on feedback from users.

[0965] (Claim 3)

[0966] The system according to claim 1, comprising means for generating a predictive model using machine learning based on statistical information.

[0967] "Application Example 1"

[0968] (Claim 1)

[0969] Means for obtaining nationwide mobility data,

[0970] A means for anonymizing and processing missing values ​​in the acquired movement data,

[0971] A means for analyzing pre-processed movement data and generating statistical information,

[0972] A means for generating graphical information to visualize the generated statistical information,

[0973] A means of automatically generating policy proposals based on analyzed statistical information,

[0974] A means of presenting proposed measures to users and receiving feedback from them,

[0975] As means for implementing the extension, the means includes displaying the analysis results on a visual device and presenting movement information for each location based on the analysis results,

[0976] A system that includes this.

[0977] (Claim 2)

[0978] The system according to claim 1, which uses artificial intelligence to analyze movement data and provides movement path information to a visual device.

[0979] (Claim 3)

[0980] The system according to claim 1, comprising means for improving the analysis method for subsequent analysis based on user feedback and for displaying trend analysis information through a visual device.

[0981] "Example 2 of combining an emotion engine"

[0982] (Claim 1)

[0983] Means for acquiring movement data including geographical information,

[0984] Means for anonymizing and handling missing values ​​of acquired geographical information,

[0985] A means for analyzing pre-processed geographical information and generating statistical information,

[0986] A means for generating charts and graphs to visualize the generated statistical information,

[0987] A means for automatically generating a draft plan based on analyzed statistical information,

[0988] A means to analyze user emotions based on the generated plan and adjust the plan accordingly.

[0989] A means of presenting the revised plan to the user and receiving feedback from the user, including their emotions,

[0990] A system that includes this.

[0991] (Claim 2)

[0992] The system according to claim 1, which utilizes an intelligent processing device for performing arithmetic operations.

[0993] (Claim 3)

[0994] The system according to claim 1, comprising means for successively improving the analysis method in subsequent analyses based on user feedback, including emotional feedback.

[0995] "Application example 2 when combining with an emotional engine"

[0996] (Claim 1)

[0997] Means for obtaining nationwide mobility data,

[0998] A means for anonymizing and processing missing values ​​in the acquired movement data,

[0999] A means for analyzing pre-processed movement data and generating statistical information,

[1000] A means of generating graphs and charts to visualize the generated statistical information,

[1001] A means of automatically generating policy proposals based on analyzed statistical information,

[1002] A means of presenting proposed measures to users and receiving feedback from them,

[1003] A method for selecting recommended services based on the user's past behavioral history and location data,

[1004] A means of analyzing user emotions using an emotion engine based on feedback and adjusting the suggested content,

[1005] A system that includes this.

[1006] (Claim 2)

[1007] The system according to claim 1, which uses artificial intelligence to perform a series of arithmetic operations in the analysis of movement data, and performs recommendations that combine past behavioral history and sentiment analysis.

[1008] (Claim 3)

[1009] The system according to claim 1, comprising means for successively improving the analysis algorithm based on user feedback to improve the accuracy of suggestions using sentiment analysis results. [Explanation of Symbols]

[1010] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for obtaining nationwide mobility data, A means for anonymizing and processing missing values ​​in the acquired movement data, A means for analyzing pre-processed movement data and generating statistical information, A means of generating graphs and charts to visualize the generated statistical information, A means of automatically generating policy proposals based on analyzed statistical information, A means of presenting proposed measures to users and receiving feedback from them, A system that includes this.

2. The system according to claim 1, which utilizes artificial intelligence to perform a series of arithmetic operations in the analysis of movement data.

3. The system according to claim 1, comprising means for successively improving the analysis algorithm for subsequent uses based on user feedback.

Images