system

Abstract

Provide a system. 【Solution means】 Means for obtaining position information data, traffic information data, weather information data, and event information data, Means for integrating the obtained data and storing it in an information set, Means for predicting the flow of people using a machine learning algorithm, Means for generating the prediction result as visualization data, Means for transmitting the generated visualization data to the user's device, Means for overlay-displaying the visualization data on the user's display device, A device that supports the user to select an optimal movement route A system including.

Description

Technical Field

[0004] , ,

[0005] , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Although people generally avoid congestion in public places and events and hope for efficient movement, currently there are limited means to obtain real-time and highly accurate people flow information. Conventional people flow data services mainly aim at marketing and commercial use and are not provided in a form that can be easily used by general users. In addition, there is a lack of a system that integrates various data such as location information, traffic information, weather information, and event information and provides accurate people flow prediction in real time. For this reason, situations occur where users are involved in unexpected congestion or waste time and energy.

Means for Solving the Problems

[0005] This invention provides means for acquiring location data, traffic data, weather data, and event data, and means for integrating the acquired data and storing it in a database. Furthermore, it includes means for using this data to predict pedestrian flow using a machine learning model, and means for generating the prediction results as visualization data. By combining this with means for distributing the generated visualization data to user terminals, users can easily utilize highly accurate pedestrian flow information in real time. This system enables users to avoid congestion, act efficiently, reduce wasted time and energy consumption, and realize an environmentally friendly lifestyle.

[0006] "Location data" refers to information that indicates the geographical location of a specific object or individual, and is obtained in the form of area, latitude, and longitude.

[0007] "Traffic information data" refers to information related to the flow and condition of traffic on roads and public transportation, and includes data on congestion, operating status, and delays.

[0008] "Weather information data" refers to information about the weather conditions of a designated area, and includes data such as temperature, humidity, precipitation, and wind speed.

[0009] "Event information data" refers to information about events and activities held at a specific date, time, and location, including data showing planned events, the number of participants, and their impact.

[0010] A "database" is a collection of information structured according to a specific method, and is a system that enables efficient data storage, retrieval, and processing.

[0011] A "machine learning model" is a collection of algorithms that learn patterns and relationships from large amounts of data and use them to make predictions and decisions about new data.

[0012] "Visualized data" refers to a graphical display format that visually represents information and data, making it easier to understand and analyze.

[0013] A "user terminal" is a device that an individual uses to directly operate and receive information, and includes smartphones, tablets, and personal computers. [Brief explanation of the drawing]

[0014] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

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

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

[0017] 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.

[0018] 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.

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

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system for collecting and integrating information on pedestrian flow from multiple data sources in real time and providing highly accurate pedestrian flow predictions using a predictive model. In a specific embodiment, the server first continuously acquires location information, traffic information, weather information, and event information. This allows the server to grasp the dynamics of pedestrian flow in various situations.

[0036] Next, the server preprocesses the acquired data and integrates it into a database. During the preprocessing process, incomplete data and noise are removed, and the data is normalized. This allows the server to build a clean dataset suitable for analysis.

[0037] Next, the server uses a machine learning model to predict pedestrian flow. It combines historical and real-time data to train a model for highly accurate pedestrian flow prediction. This prediction model responds instantly to the influx of new data, providing the best possible flow forecast at the present moment.

[0038] Furthermore, the server visualizes the prediction results. Specifically, it generates prediction data in visual formats such as heatmaps and flow maps, providing it in a way that users can intuitively understand.

[0039] Finally, the server delivers the generated visualization data to the user's terminal. The user can then open the application on their terminal and plan their movements and actions while visually viewing the real-time heatmap.

[0040] For example, when a user visits the city center on a weekend, the app provides a congestion forecast and suggests the most efficient travel route and visit time. This system allows users to avoid congestion, create a comfortable itinerary, and reduce wasted time and energy.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server retrieves data in real time from APIs of location providers, transportation systems, weather stations, and event calendars. In particular, location information is obtained directly from mobile devices and fixed sensors, and transportation data includes traffic congestion information and public transport service status.

[0044] Step 2:

[0045] The server preprocesses the collected raw data. It detects and corrects or removes missing or outlier values. It normalizes the data and converts it into a unified format, making it suitable for analysis.

[0046] Step 3:

[0047] The server stores the pre-processed data in a database. The database creates an index using geographic coordinates based on location information and organizes the data as a time series using timestamps.

[0048] Step 4:

[0049] The server uses machine learning algorithms to train a pedestrian flow prediction model. By combining historical pedestrian flow data with real-time data, it improves prediction accuracy.

[0050] Step 5:

[0051] The server performs short-term and medium-term pedestrian flow forecasts based on predictive models. This makes it possible to predict detailed pedestrian traffic for specific areas and time periods.

[0052] Step 6:

[0053] The server generates heatmaps and flow maps to visualize the prediction results. Visual data, shown with different colors and lines, allows users to see the level of congestion at a glance.

[0054] Step 7:

[0055] The server sends the generated visualization data to the user's device. The user receives this data through a mobile app and adjusts their travel plans and actions based on that information.

[0056] Step 8:

[0057] Users can view predictive data within the app to avoid congestion and choose the optimal travel route. They can also make real-time decisions based on the information and provide feedback on their choices within the app.

[0058] (Example 1)

[0059] 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."

[0060] In modern society, accurate predictions of human flow based on diverse information are required to support the smooth movement and optimization of people's action plans. However, conventional systems have difficulty integrating diverse data in real time and making accurate predictions, requiring a great deal of time and computing resources. Furthermore, they have the problem of not being able to provide information in a way that users can intuitively understand, and thus not being able to adequately contribute to users' action plans.

[0061] 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.

[0062] In this invention, the server includes information gathering means for acquiring location information data, traffic information data, weather information data, and event information data; data cleansing and integration means for preprocessing the acquired data and integrating it into a database; and prediction means for predicting pedestrian flow using machine learning algorithms. This makes it possible to efficiently process information obtained from diverse data sources and provide users with intuitive and real-time useful pedestrian flow prediction information.

[0063] "Information gathering means" refers to a device or system equipped with the function of acquiring location information data, traffic information data, weather information data, and event information data in real time.

[0064] "Data cleansing and integration means" refers to a device or system equipped with the function of preprocessing acquired data, removing incomplete data and noise, and performing processing to integrate it into a database in an appropriate form.

[0065] A "prediction tool" is a device or system equipped with the function of performing calculations to accurately predict the trends of human movement using machine learning algorithms.

[0066] "Visualization means" refers to a device or system equipped with the function of graphically displaying predicted results as a heat map or flow map.

[0067] "Data distribution means" refers to a device or system equipped with the function of quickly and efficiently transmitting generated visualization data to a user's electronic device.

[0068] This invention is implemented by constructing a server-centered system to collect and integrate information on human movement from multiple data sources in real time. The server functions as an information collection means, acquiring location information, traffic information, weather information, and event information using their respective APIs. Specifically, for location information, general geographic information systems and the GPS function of smartphones are used to import data into the server in real time according to the requirements.

[0069] As a data cleansing and integration method, a process is implemented on the server using a programming language such as Python to filter out outliers and missing values ​​in the data and normalize it. This allows for efficient storage and access of the organized data using a relational database system (RDBMS) for database management.

[0070] As a prediction method, the server utilizes frameworks for executing machine learning algorithms. For example, it uses libraries such as TENSORFLOW® and scikit-learn to build neural network models and other learning models, and performs highly accurate pedestrian flow predictions based on input datasets.

[0071] In visualization, the server generates visual data to communicate prediction results to the user. Data visualization libraries such as D3.js and Plotly are used to create heatmaps and flow maps, allowing users to intuitively understand the information.

[0072] Finally, as a data distribution method, the server delivers the generated visual data to the client's terminal. By using the WebSocket protocol, the user's terminal can receive updated information in real time, enabling efficient travel planning. Users can launch and operate the application through their electronic devices, inputting prompts such as "Please predict the congestion level in the city center on the weekend." This allows users to avoid congestion and travel more efficiently.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server retrieves location data, traffic data, weather data, and event data from their respective APIs. Using API keys and request parameters for each data source as input, the server sends requests. As output, the server aggregates the returned data in different formats. This process collects diverse real-time data on pedestrian flow.

[0076] Step 2:

[0077] The server preprocesses and cleanses the collected data. It receives a raw dataset as input and uses scripts such as Python to standardize the data, impart incomplete data, and denoise it. The output is a clean, consistent dataset, which is then integrated into the database. This preprocessing improves the data quality and makes it suitable for analysis.

[0078] Step 3:

[0079] The server runs a machine learning model using a clean dataset to predict pedestrian flow. Preprocessed data is provided as input, and the server runs a predictive model using machine learning libraries such as TensorFlow. The output generates predictive data showing future pedestrian flow trends. This process allows the server to obtain advanced analytical results, enabling efficient pedestrian flow prediction.

[0080] Step 4:

[0081] The server visualizes predicted pedestrian flow data. Receiving predicted data as input, the server uses visualization libraries such as D3.js to generate heatmaps and flow maps. The output is graphical data that users can intuitively understand. This process allows users to quickly grasp the situation based on visual information.

[0082] Step 5:

[0083] The server sends the visualized data to the user's terminal. Receiving the generated visualization data as input, the server delivers the data in real time using WebSocket. As output, the visualization data is displayed on the user's terminal and becomes accessible to the user. This step allows the user to receive immediate feedback in response to their prompts.

[0084] Step 6:

[0085] Users create action plans based on the visual information they receive. Through the application, users can check real-time pedestrian flow information and input prompts such as, "Please predict the congestion level in the city center on weekends." This allows users to avoid congestion and develop efficient action plans.

[0086] (Application Example 1)

[0087] 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."

[0088] In modern cities, people's movement is becoming increasingly complex, making it difficult to avoid congestion and travel efficiently. This can lead to wasted time, increased stress, and a decline in people's quality of life. Therefore, a system is needed that accurately predicts pedestrian flow in real time and supports users in making optimal travel decisions.

[0089] 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.

[0090] In this invention, the server includes means for acquiring location data, traffic data, weather data, and event data; means for integrating the acquired data and storing it in an information set; and means for predicting pedestrian flow using a machine learning algorithm. This allows users to visually confirm real-time pedestrian flow predictions and select travel routes that avoid congestion.

[0091] "Location data" refers to digital information that indicates the geographical location of an object, and is acquired using technologies such as GPS.

[0092] "Traffic information data" refers to information that shows the status of roads and public transportation, such as delays, congestion, and accidents.

[0093] "Weather information data" refers to information that shows local weather conditions, such as temperature, precipitation, and wind speed.

[0094] "Event information data" refers to information that provides details about events or gatherings held at a specific location and time.

[0095] A "device" is a mechanical or electronic component designed to perform a specific function.

[0096] An "information set" is a collection of data that aggregates and organizes a series of related data elements.

[0097] A "machine learning algorithm" is a computational method that learns patterns based on data and makes predictions and judgments based on new information.

[0098] "Visualized data" refers to data that has been converted into visual representations such as diagrams and graphs, including numerical values ​​and information.

[0099] "User's device" refers to the user's electronic device used to receive the service.

[0100] "Overlay display" is a method of displaying other information on top of a background image or information.

[0101] A "travel route" is a path used to move from one point to another.

[0102] The invention will now be described in terms of embodiments for carrying out the invention. This invention provides a system that predicts pedestrian flow in real time and assists users in making optimal movements. It has a mechanism that integrates various data to make predictions and provides the results to the user visually.

[0103] The server uses devices to acquire location data, traffic data, weather data, and event data, collecting this data in real time. This allows the server to understand the dynamics of human movement, taking various factors into account.

[0104] The collected data is integrated on a server and managed as an information set. During integration, data stream processing technologies such as Apache® Kafka are used to ensure data integrity and normalization. Next, based on the integrated dataset, machine learning algorithms (such as TensorFlow) are used to predict pedestrian flow. This algorithm analyzes historical and real-time data, and responds immediately to new data.

[0105] The prediction results are generated as visualized data using visualization tools (such as D3.js). This visualized data is then formatted as a heatmap or flow map and delivered to the user's device. If the user is using a display device such as smart glasses, this visualization data is overlaid, allowing the user to easily understand their travel route.

[0106] As a concrete example, when a user visits a busy area, they can efficiently move to a shopping mall while avoiding crowded intersections. Based on visualized pedestrian flow information, the user can select the optimal route, reducing the stress of travel.

[0107] An example of a prompt to a generative AI model is, "Tell me the best route when walking through a busy downtown area on the weekend. Display real-time visual information on my smart glasses to help me avoid crowded areas." This prompt allows the system to provide optimal pedestrian flow prediction information tailored to the user's needs.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server acquires location data, traffic data, weather data, and event data in real time. It uses sensors and APIs for data collection and aggregates information from each data source. Input is raw data acquired from each data source, and output is a set of this raw data. The collected data is temporarily stored for subsequent processing.

[0111] Step 2:

[0112] The server integrates the acquired raw data and organizes it as an information set. Apache Kafka is used to process the data stream, normalizing it while maintaining data integrity. The input is the set of raw data obtained in step 1, and the output is a denoised and normalized dataset. This dataset is stored in a database and used for analysis by machine learning models.

[0113] Step 3:

[0114] The server uses machine learning algorithms to predict pedestrian flow. TensorFlow is used to analyze the dataset and apply a model that predicts future pedestrian flow based on past and present data. The input is the normalized dataset obtained in step 2, and the output is the predicted pedestrian flow data. During this process, the model is also updated to enable the generative AI model to respond quickly to new prompts.

[0115] Step 4:

[0116] The server generates prediction results as visualization data. D3.js is used to convert this data into visual formats such as heatmaps and flow maps. The input is the predicted pedestrian flow data obtained in step 3, and the output is the visualization data. The visualized data is then processed in a way that is easy for the user to understand.

[0117] Step 5:

[0118] The server delivers the generated visualization data to the user's device. It sends the data to the user's terminal using a data transfer protocol. The input is the visualization data obtained in step 4, and the output is the data delivery to the user's device. This process includes prompts to avoid difficult situations.

[0119] Step 6:

[0120] The user overlays the received visualization data on the device and selects the optimal travel route. The visualization data is displayed overlaid on the smart glasses' display. The input is the visualization data delivered to the terminal in step 5, and the output is the user's action plan and travel route selection. As a concrete example, it becomes possible to choose a route that avoids congestion.

[0121] 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.

[0122] This invention combines a system that aggregates various information data to perform highly accurate pedestrian flow predictions with an emotion engine that recognizes user emotions. By acquiring various data and enabling multidimensional predictions that also consider the user's emotional state, it provides information that is more tailored to each individual.

[0123] First, the server is equipped with means to acquire location information, traffic information, weather information, and event information. This information is obtained in real time from external APIs, fixed sensors, and mobile devices. The server also has an emotion engine to recognize user emotions, and collects emotion data from the user's device using camera and audio data. This emotion data may vary depending on the user's actions and environment.

[0124] Next, the server integrates the diverse data it has acquired and stores it in a database. Data is efficiently managed through indexing of both time-series and spatial data. Emotional data from the emotion engine is also stored in the database and used to improve the user experience.

[0125] Next, the server uses a machine learning model to predict pedestrian traffic. In addition to conventional models, it incorporates emotional data as feedback to improve prediction accuracy. For example, suggested actions and movements are optimized based on emotions reflected in the popularity of restaurants from other regions and the expected waiting times.

[0126] Furthermore, the server generates prediction results as visualization data. This visualization is customized according to the user's emotional state, with adjustments made to the color scheme and details of the displayed content. If the user is feeling stressed, the presentation will be clearer and more focused.

[0127] Finally, the generated visualization data is delivered to the user's device. The user can view the information in real time through their device and adjust their travel plans and actions based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route.

[0128] Thus, the present invention, which incorporates an emotion engine, is a system that enables advanced data analysis and prediction that takes into account the user's emotional state, and provides a highly personalized user experience.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server collects various data in real time through APIs from location providers, transportation systems, weather data sources, and event platforms. This provides a foundation for understanding the latest human movement and environmental conditions.

[0132] Step 2:

[0133] The device uses the user's camera and microphone to collect emotional data via an emotion engine, which then transmits it to a server. It uses facial recognition and voice tone analysis to determine the user's emotional state and sends this data to the server as numerical values.

[0134] Step 3:

[0135] The server stores collected location information, traffic information, weather information, event information, and sentiment data in a database. Time-series and spatial data are used for indexing, enabling efficient data management.

[0136] Step 4:

[0137] The server uses stored data to train machine learning models and predict pedestrian flow. Predictions that incorporate emotional data, in particular, suggest optimal routes and actions that take into account user behavioral intentions and stress avoidance.

[0138] Step 5:

[0139] The server converts the prediction results into visualization data. This data is then customized in its display based on the user's current emotional state. For example, if the user is feeling stressed, softer colors are used, and an overload of information is avoided.

[0140] Step 6:

[0141] The server delivers the generated visualization data to the user's terminal. Here, the user can consider action plans in real time based on the displayed information.

[0142] Step 7:

[0143] Users review the visualizations they receive on their devices and select suggested routes and actions. If additional feedback data is generated based on the user's choices, it is sent back to the server to help refine the predictive models and sentiment engine.

[0144] (Example 2)

[0145] 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 will be referred to as the "terminal."

[0146] In modern society, accurately predicting people's movement patterns is a crucial challenge in urban planning, event management, and improving transportation efficiency. However, traditional prediction methods fail to consider subjective factors such as the emotional state of individual users, resulting in inaccurate predictions and making it difficult to provide personalized information and action suggestions.

[0147] 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.

[0148] In this invention, the server includes a configuration means for accumulating location information data, traffic information data, weather information data, and event information data; a configuration means for acquiring user emotion data from a user terminal using a camera and audio device; and a configuration means for integrating the acquired diverse data and storing it in a database resource. This enables highly accurate pedestrian flow prediction that takes user emotions into account, and allows for the optimization of personalized suggestions and action plans.

[0149] "Location data" refers to data that indicates the geographical coordinates of a specific point in time.

[0150] "Traffic information data" refers to data that shows information about traffic flow and operating conditions.

[0151] "Weather information data" refers to data that includes information about weather conditions such as temperature, humidity, and precipitation.

[0152] "Event information data" refers to data that shows information about events and gatherings in a specific region or time.

[0153] "Emotional data" refers to data that indicates a user's emotional state and includes information obtained from facial expressions and voice.

[0154] A "database resource" is a record and management system for integrating and storing information.

[0155] "Machine learning techniques" are methods that allow computers to learn from experience or data and perform inferences and predictions.

[0156] "Visualized data" refers to data that has been processed to provide a visual representation of information.

[0157] "Feedback" is the process of reacting to a prediction or result and using that information as input again.

[0158] This invention is a system that performs highly accurate pedestrian flow predictions tailored to individual users and provides information based on those predictions. Specific embodiments are described below.

[0159] The server collects location data, traffic data, weather data, and event data using external APIs, fixed sensors, mobile devices, etc. The collected data is integrated and stored in database resources. This allows the data to be efficiently indexed as time-series and spatial data.

[0160] Furthermore, the server acquires emotional data from the user's device through its camera and audio equipment. The emotion engine determines the user's emotional state from their facial expressions and voice, and collects this data. This allows for real-time monitoring of the user's current emotions and stress levels.

[0161] Using machine learning techniques, the server predicts human movement and flow patterns. In addition to traditional pedestrian flow data, emotional data is fed back to improve prediction accuracy. The prediction results are generated as visualization data and visualized by the server. These visualizations are adjusted to the user's emotional state, employing color schemes and presentations designed to reduce stress.

[0162] The generated visualization data is delivered to the user's device in real time. Based on the information provided through the device, users can plan their travel and activities. For example, a user wanting to visit a popular shopping mall on a holiday might receive suggestions for the optimal visit time and route to avoid crowds.

[0163] An example of a prompt message is, "I want to go to a shopping mall on my day off, but please tell me the best time and route to avoid crowds." In this way, users can receive optimal suggestions that take their individual emotional state into consideration.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server collects location data, traffic data, weather data, and event data. Real-time data from external APIs, fixed sensors, and mobile devices is used as input. This data is integrated to generate a dataset with time-series and spatial structure as output.

[0167] Step 2:

[0168] The server collects emotional data from the user's device using the camera and microphone. The input consists of the user's facial expressions and voice, which the emotion engine analyzes. The output is data indicating the user's stress level and emotional state. Specifically, it operates in the background while the user is using the app, continuously acquiring emotional data.

[0169] Step 3:

[0170] The server stores the integrated data in a database. This database supports indexing of time-series and spatial data. The datasets generated in steps 1 and 2 are used as input. The output is an indexed database, which also includes user-specific sentiment data.

[0171] Step 4:

[0172] The server uses machine learning techniques to predict pedestrian flow patterns. Inputs include integrated data stored in a database and user sentiment data. Outputs are predicted pedestrian flow data, enabling highly accurate predictions based on historical and current data. Specifically, the prediction model is periodically updated, allowing for real-time predictions.

[0173] Step 5:

[0174] The server generates prediction results as visualization data. This visualization data is customized according to the user's stress and emotional state. The inputs used are the prediction data obtained in step 4 and data on the user's emotional state. The output is a customized visualization. Specifically, the color scheme and diagram format are automatically adjusted to the user's needs.

[0175] Step 6:

[0176] The server delivers the generated visualization data to the user's device. The input is the customized visualization data generated in step 5. The output is displayed on the user's device, allowing for real-time information verification. Specifically, the user can create a travel plan based on their emotions and circumstances via their device.

[0177] (Application Example 2)

[0178] 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".

[0179] In modern urban environments, for residents to move comfortably and efficiently, it is necessary to integrate various real-time, fluctuating information and propose travel routes and actions that match their individual emotional states. However, conventional systems have struggled to perform fine-tuned optimization that takes emotional states into account, resulting in a failure to improve the user experience.

[0180] 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.

[0181] In this invention, the server includes means for acquiring location information data, traffic information data, weather information data, and event information data; means for integrating the acquired data and storing it in an information storage device; and means for recognizing the user's emotional state and collecting emotional data. This enables highly accurate pedestrian flow prediction and customized suggestions that take emotions into account.

[0182] "Location data" refers to data that provides geographical information related to a specific place or location.

[0183] "Traffic information data" refers to information that shows trends regarding the usage and congestion levels of roads and public transportation.

[0184] "Weather information data" refers to information about meteorological conditions such as weather, temperature, and humidity.

[0185] "Event information data" refers to information about events and activities held in specific regions or locations.

[0186] An "information storage device" is a system or device for accumulating and efficiently managing diverse data.

[0187] "Emotional data" refers to information about a user's emotional state, including indicators such as stress and happiness.

[0188] "Visualization data" refers to data generated to visually represent information and facilitate understanding.

[0189] "User terminal" refers to communication equipment or devices used by individuals to receive information.

[0190] "Feedback" refers to information such as opinions and impressions obtained from users, which is used to improve the system.

[0191] To implement this invention, a system is constructed that combines a server, a user terminal, and a communication device. The server acquires location data, traffic data, weather data, and event data in real time from external APIs, fixed sensors, and mobile devices. This information is stored in an information storage device for data integration and is efficiently managed by indexing time-series data and spatial data.

[0192] The server also features an emotion recognition engine that uses camera and audio data to recognize the user's emotional state, and this emotion data is also stored in an information storage device. The emotion recognition engine uses Google's TensorFlow, and the machine learning model uses the Python Scikit-learn library to improve the accuracy of pedestrian flow prediction.

[0193] The prediction results are generated as visualization data, with the color scheme and content customized according to the user's emotional state. This visualization is delivered to the user's device in real time, allowing the user to adjust their travel plan based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route on their device.

[0194] An example of a prompt message would be: "Suggest the optimal route for an event in the city. Use sentiment data. Current location: Shinjuku, route to Shinjuku Station West Exit Shopping Mall."

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server acquires location data, traffic data, weather data, and event data from external APIs and sensors. This process involves collecting information from each data source, converting it to its respective data format, and performing data format conversion for unified handling. Data input is from external data sources, and output is integrated information data.

[0198] Step 2:

[0199] The server stores the acquired data in an information storage device. In this step, the time-series and spatial data are indexed to organize and store the data in a way that allows for efficient subsequent processing. The input is integrated information data, and the output is an indexed database.

[0200] Step 3:

[0201] The server acquires camera and audio data from the user's terminal and collects the user's emotional data using an emotion recognition engine. At this stage, real-time emotion recognition processing is performed, and the emotional state is quantified and output. The input is camera and audio data, and the output is quantified emotional data.

[0202] Step 4:

[0203] The server inputs integrated data and sentiment data into a machine learning model to predict pedestrian flow. Here, data normalization and feature selection are performed, and a predictive model is built using a machine learning algorithm. The input is an indexed database and sentiment data, and the output is the predicted pedestrian flow pattern.

[0204] Step 5:

[0205] The server generates visualization data based on prediction results and adjusts the color scheme and layout according to the user's emotional state. The visualization algorithm designs a visually intuitive interface. The input is the predicted pedestrian flow pattern, and the output is customized visualization data.

[0206] Step 6:

[0207] The terminal receives visualization data generated from the server, displays it to the user in real time, and provides optimized action suggestions. The terminal analyzes the data received by the communication module and presents the information on the user interface via the display module. The input is customized visualization data, and the output is the information displayed on the user interface.

[0208] 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.

[0209] 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 those described above. 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 shown 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.

[0210] 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.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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".

[0224] This invention is a system for collecting and integrating information on pedestrian flow from multiple data sources in real time and providing highly accurate pedestrian flow predictions using a predictive model. In a specific embodiment, the server first continuously acquires location information, traffic information, weather information, and event information. This allows the server to grasp the dynamics of pedestrian flow in various situations.

[0225] Next, the server preprocesses the acquired data and integrates it into a database. During the preprocessing process, incomplete data and noise are removed, and the data is normalized. This allows the server to build a clean dataset suitable for analysis.

[0226] Next, the server uses a machine learning model to predict pedestrian flow. It combines historical and real-time data to train a model for highly accurate pedestrian flow prediction. This prediction model responds instantly to the influx of new data, providing the best possible flow forecast at the present moment.

[0227] Furthermore, the server visualizes the prediction results. Specifically, it generates prediction data in visual formats such as heatmaps and flow maps, providing it in a way that users can intuitively understand.

[0228] Finally, the server delivers the generated visualization data to the user's terminal. The user can then open the application on their terminal and plan their movements and actions while visually viewing the real-time heatmap.

[0229] For example, when a user visits the city center on a weekend, the app provides a congestion forecast and suggests the most efficient travel route and visit time. This system allows users to avoid congestion, create a comfortable itinerary, and reduce wasted time and energy.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server retrieves data in real time from APIs of location providers, transportation systems, weather stations, and event calendars. In particular, location information is obtained directly from mobile devices and fixed sensors, and transportation data includes traffic congestion information and public transport service status.

[0233] Step 2:

[0234] The server preprocesses the collected raw data. It detects and corrects or removes missing or outlier values. It normalizes the data and converts it into a unified format, making it suitable for analysis.

[0235] Step 3:

[0236] The server stores the pre-processed data in a database. The database creates an index using geographic coordinates based on location information and organizes the data as a time series using timestamps.

[0237] Step 4:

[0238] The server uses machine learning algorithms to train a pedestrian flow prediction model. By combining historical pedestrian flow data with real-time data, it improves prediction accuracy.

[0239] Step 5:

[0240] The server performs short-term and medium-term pedestrian flow forecasts based on predictive models. This makes it possible to predict detailed pedestrian traffic for specific areas and time periods.

[0241] Step 6:

[0242] The server generates heatmaps and flow maps to visualize the prediction results. Visual data, shown with different colors and lines, allows users to see the level of congestion at a glance.

[0243] Step 7:

[0244] The server sends the generated visualization data to the user's device. The user receives this data through a mobile app and adjusts their travel plans and actions based on that information.

[0245] Step 8:

[0246] Users can view predictive data within the app to avoid congestion and choose the optimal travel route. They can also make real-time decisions based on the information and provide feedback on their choices within the app.

[0247] (Example 1)

[0248] 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."

[0249] In modern society, accurate predictions of human flow based on diverse information are required to support the smooth movement and optimization of people's action plans. However, conventional systems have difficulty integrating diverse data in real time and making accurate predictions, requiring a great deal of time and computing resources. Furthermore, they have the problem of not being able to provide information in a way that users can intuitively understand, and thus not being able to adequately contribute to users' action plans.

[0250] 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.

[0251] In this invention, the server includes information gathering means for acquiring location information data, traffic information data, weather information data, and event information data; data cleansing and integration means for preprocessing the acquired data and integrating it into a database; and prediction means for predicting pedestrian flow using machine learning algorithms. This makes it possible to efficiently process information obtained from diverse data sources and provide users with intuitive and real-time useful pedestrian flow prediction information.

[0252] "Information gathering means" refers to a device or system equipped with the function of acquiring location information data, traffic information data, weather information data, and event information data in real time.

[0253] "Data cleansing and integration means" refers to a device or system equipped with the function of preprocessing acquired data, removing incomplete data and noise, and performing processing to integrate it into a database in an appropriate form.

[0254] A "prediction tool" is a device or system equipped with the function of performing calculations to accurately predict the trends of human movement using machine learning algorithms.

[0255] "Visualization means" refers to a device or system equipped with the function of graphically displaying predicted results as a heat map or flow map.

[0256] "Data distribution means" refers to a device or system equipped with the function of quickly and efficiently transmitting generated visualization data to a user's electronic device.

[0257] This invention is implemented by constructing a server-centered system to collect and integrate information on human movement from multiple data sources in real time. The server functions as an information collection means, acquiring location information, traffic information, weather information, and event information using their respective APIs. Specifically, for location information, general geographic information systems and the GPS function of smartphones are used to import data into the server in real time according to the requirements.

[0258] As a data cleansing and integration method, a process is implemented on the server using a programming language such as Python to filter out outliers and missing values ​​in the data and normalize it. This allows for efficient storage and access of the organized data using a relational database system (RDBMS) for database management.

[0259] As a prediction method, the server utilizes frameworks for executing machine learning algorithms. For example, it uses libraries such as TensorFlow and scikit-learn to build neural network models and other learning models, and performs highly accurate pedestrian flow predictions based on input datasets.

[0260] In visualization, the server generates visual data to communicate prediction results to the user. Data visualization libraries such as D3.js and Plotly are used to create heatmaps and flow maps, allowing users to intuitively understand the information.

[0261] Finally, as a data distribution method, the server delivers the generated visual data to the client's terminal. By using the WebSocket protocol, the user's terminal can receive updated information in real time, enabling efficient travel planning. Users can launch and operate the application through their electronic devices, inputting prompts such as "Please predict the congestion level in the city center on the weekend." This allows users to avoid congestion and travel more efficiently.

[0262] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0263] Step 1:

[0264] The server retrieves location data, traffic data, weather data, and event data from their respective APIs. Using API keys and request parameters for each data source as input, the server sends requests. As output, the server aggregates the returned data in different formats. This process collects diverse real-time data on pedestrian flow.

[0265] Step 2:

[0266] The server preprocesses and cleanses the collected data. It receives a raw dataset as input and uses scripts such as Python to standardize the data, impart incomplete data, and denoise it. The output is a clean, consistent dataset, which is then integrated into the database. This preprocessing improves the data quality and makes it suitable for analysis.

[0267] Step 3:

[0268] The server runs a machine learning model using a clean dataset to predict pedestrian flow. Preprocessed data is provided as input, and the server runs a predictive model using machine learning libraries such as TensorFlow. The output generates predictive data showing future pedestrian flow trends. This process allows the server to obtain advanced analytical results, enabling efficient pedestrian flow prediction.

[0269] Step 4:

[0270] The server visualizes predicted pedestrian flow data. Receiving predicted data as input, the server uses visualization libraries such as D3.js to generate heatmaps and flow maps. The output is graphical data that users can intuitively understand. This process allows users to quickly grasp the situation based on visual information.

[0271] Step 5:

[0272] The server sends the visualized data to the user's terminal. Receiving the generated visualization data as input, the server delivers the data in real time using WebSocket. As output, the visualization data is displayed on the user's terminal and becomes accessible to the user. This step allows the user to receive immediate feedback in response to their prompts.

[0273] Step 6:

[0274] Users create action plans based on the visual information they receive. Through the application, users can check real-time pedestrian flow information and input prompts such as, "Please predict the congestion level in the city center on weekends." This allows users to avoid congestion and develop efficient action plans.

[0275] (Application Example 1)

[0276] 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."

[0277] In modern cities, people's movement is becoming increasingly complex, making it difficult to avoid congestion and travel efficiently. This can lead to wasted time, increased stress, and a decline in people's quality of life. Therefore, a system is needed that accurately predicts pedestrian flow in real time and supports users in making optimal travel decisions.

[0278] 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.

[0279] In this invention, the server includes means for acquiring location data, traffic data, weather data, and event data; means for integrating the acquired data and storing it in an information set; and means for predicting pedestrian flow using a machine learning algorithm. This allows users to visually confirm real-time pedestrian flow predictions and select travel routes that avoid congestion.

[0280] "Location data" refers to digital information that indicates the geographical location of an object, and is acquired using technologies such as GPS.

[0281] "Traffic information data" refers to information that shows the status of roads and public transportation, such as delays, congestion, and accidents.

[0282] "Meteorological information data" refers to information indicating meteorological conditions such as regional weather conditions, temperature, precipitation, wind speed, etc.

[0283] "Event information data" refers to information indicating details of events and happenings at specific locations and times.

[0284] "Device" refers to mechanical or electronic components designed to perform specific functions.

[0285] "Information set" refers to a collection of data that aggregates and organizes a series of related data elements.

[0286] "Machine learning algorithm" refers to a computational method for learning patterns based on data and making predictions or judgments from new information.

[0287] "Visualization data" refers to data that converts numerical values and information into visual representations such as diagrams and graphs.

[0288] "User's device" refers to the user's electronic device used to receive services.

[0289] "Overlay display" refers to a method of displaying additional information over a background image or information.

[0290] "Movement route" refers to the path for moving from one point to another.

[0291] The mode for implementing the invention will be described. This invention provides a system that predicts the flow of people in real time and supports users in making optimal movements. It has a mechanism for integrating various data for prediction and visually providing the results to users.

[0292] The server uses devices to acquire location data, traffic data, weather data, and event data, collecting this data in real time. This allows the server to understand the dynamics of human movement, taking various factors into account.

[0293] The collected data is integrated on a server and managed as an information set. Data stream processing technologies such as Apache Kafka are used for integration to ensure data integrity and normalization. Next, based on the integrated dataset, machine learning algorithms (such as TensorFlow) are used to predict pedestrian flow. This algorithm analyzes historical and real-time data, and responds immediately to new data.

[0294] The prediction results are generated as visualized data using visualization tools (such as D3.js). This visualized data is then formatted as a heatmap or flow map and delivered to the user's device. If the user is using a display device such as smart glasses, this visualization data is overlaid, allowing the user to easily understand their travel route.

[0295] As a concrete example, when a user visits a busy area, they can efficiently move to a shopping mall while avoiding crowded intersections. Based on visualized pedestrian flow information, the user can select the optimal route, reducing the stress of travel.

[0296] An example of a prompt to a generative AI model is, "Tell me the best route when walking through a busy downtown area on the weekend. Display real-time visual information on my smart glasses to help me avoid crowded areas." This prompt allows the system to provide optimal pedestrian flow prediction information tailored to the user's needs.

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] The server acquires location data, traffic data, weather data, and event data in real time. It uses sensors and APIs for data collection and aggregates information from each data source. Input is raw data acquired from each data source, and output is a set of this raw data. The collected data is temporarily stored for subsequent processing.

[0300] Step 2:

[0301] The server integrates the acquired raw data and organizes it as an information set. Apache Kafka is used to process the data stream, normalizing it while maintaining data integrity. The input is the set of raw data obtained in step 1, and the output is a denoised and normalized dataset. This dataset is stored in a database and used for analysis by machine learning models.

[0302] Step 3:

[0303] The server uses machine learning algorithms to predict pedestrian flow. TensorFlow is used to analyze the dataset and apply a model that predicts future pedestrian flow based on past and present data. The input is the normalized dataset obtained in step 2, and the output is the predicted pedestrian flow data. During this process, the model is also updated to enable the generative AI model to respond quickly to new prompts.

[0304] Step 4:

[0305] The server generates prediction results as visualization data. D3.js is used to convert this data into visual formats such as heatmaps and flow maps. The input is the predicted pedestrian flow data obtained in step 3, and the output is the visualization data. The visualized data is then processed in a way that is easy for the user to understand.

[0306] Step 5:

[0307] The server distributes the generated visualization data to the user's device. Using a data transfer protocol, it sends the data to the user's terminal. The input is the visualization data obtained in step 4, and the output is the data distribution to the user's device. At this time, a prompt sentence for avoiding difficult situations is included.

[0308] Step 6:

[0309] The user overlays and displays the received visualization data on the device and selects an optimal movement route. The visualization data is superimposed and displayed on the display of the smart glasses. The input is the visualization data distributed to the terminal in step 5, and the output is the user's action plan and the selection of a movement route. As a specific example, it is possible to select a route to avoid congestion.

[0310] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0311] This invention combines an emotion engine that recognizes the user's emotion with a system that aggregates various information data and performs highly accurate crowd flow prediction. By acquiring various data and enabling multi-dimensional prediction considering the user's emotional state, it provides information more suitable for individuals.

[0312] First, the server has means for acquiring location information, traffic information, weather information, and event information. These information are acquired in real time from external APIs, fixed sensors, and mobile devices. Also, the server has an emotion engine for recognizing the user's emotion and collects emotion data using a camera and voice data from the user's terminal. This emotion data may vary depending on the user's operations and environment.

[0313] Next, the server integrates the diverse data it has acquired and stores it in a database. Data is efficiently managed through indexing of both time-series and spatial data. Emotional data from the emotion engine is also stored in the database and used to improve the user experience.

[0314] Next, the server uses a machine learning model to predict pedestrian traffic. In addition to conventional models, it incorporates emotional data as feedback to improve prediction accuracy. For example, suggested actions and movements are optimized based on emotions reflected in the popularity of restaurants from other regions and the expected waiting times.

[0315] Furthermore, the server generates prediction results as visualization data. This visualization is customized according to the user's emotional state, with adjustments made to the color scheme and details of the displayed content. If the user is feeling stressed, the presentation will be clearer and more focused.

[0316] Finally, the generated visualization data is delivered to the user's device. The user can view the information in real time through their device and adjust their travel plans and actions based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route.

[0317] Thus, the present invention, which incorporates an emotion engine, is a system that enables advanced data analysis and prediction that takes into account the user's emotional state, and provides a highly personalized user experience.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The server collects various types of data in real time through APIs from location providers, transportation systems, weather data sources, and event platforms. This provides a foundation for understanding the latest human movement and environmental conditions.

[0321] Step 2:

[0322] The device uses the user's camera and microphone to collect emotional data via an emotion engine, which then transmits it to a server. It uses facial recognition and voice tone analysis to determine the user's emotional state and sends this data to the server as numerical values.

[0323] Step 3:

[0324] The server stores collected location information, traffic information, weather information, event information, and sentiment data in a database. Time-series and spatial data are used for indexing, enabling efficient data management.

[0325] Step 4:

[0326] The server uses stored data to train machine learning models and predict pedestrian flow. Predictions that incorporate emotional data, in particular, suggest optimal routes and actions that take into account user behavioral intentions and stress avoidance.

[0327] Step 5:

[0328] The server converts the prediction results into visualization data. This data is then customized in its display based on the user's current emotional state. For example, if the user is feeling stressed, softer colors are used, and an overload of information is avoided.

[0329] Step 6:

[0330] The server delivers the generated visualization data to the user's terminal. Here, the user can consider action plans in real time based on the displayed information.

[0331] Step 7:

[0332] Users review the visualizations they receive on their devices and select suggested routes and actions. If additional feedback data is generated based on the user's choices, it is sent back to the server to help refine the predictive models and sentiment engine.

[0333] (Example 2)

[0334] 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".

[0335] In modern society, accurately predicting people's movement patterns is a crucial challenge in urban planning, event management, and improving transportation efficiency. However, traditional prediction methods fail to consider subjective factors such as the emotional state of individual users, resulting in inaccurate predictions and making it difficult to provide personalized information and action suggestions.

[0336] 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.

[0337] In this invention, the server includes a configuration means for accumulating location information data, traffic information data, weather information data, and event information data; a configuration means for acquiring user emotion data from a user terminal using a camera and audio device; and a configuration means for integrating the acquired diverse data and storing it in a database resource. This enables highly accurate pedestrian flow prediction that takes user emotions into account, and allows for the optimization of personalized suggestions and action plans.

[0338] "Location data" refers to data that indicates geographical coordinate information for a specific point in time.

[0339] "Traffic information data" refers to data that shows information about traffic flow and operating conditions.

[0340] "Weather information data" refers to data that includes information about weather conditions such as temperature, humidity, and precipitation.

[0341] "Event information data" refers to data that shows information about events and gatherings in a specific region or time.

[0342] "Emotional data" refers to data that indicates a user's emotional state and includes information obtained from facial expressions and voice.

[0343] A "database resource" is a record and management system for integrating and storing information.

[0344] "Machine learning techniques" are methods that allow computers to learn from experience or data and perform inferences and predictions.

[0345] "Visualized data" refers to data that has been processed to provide a visual representation of information.

[0346] "Feedback" is the process of reacting to a prediction or result and using that information as input again.

[0347] This invention is a system that performs highly accurate pedestrian flow predictions tailored to individual users and provides information based on those predictions. Specific embodiments are described below.

[0348] The server collects location data, traffic data, weather data, and event data using external APIs, fixed sensors, mobile devices, etc. The collected data is integrated and stored in database resources. This allows the data to be efficiently indexed as time-series and spatial data.

[0349] Furthermore, the server acquires emotional data from the user's device through its camera and audio equipment. The emotion engine determines the user's emotional state from their facial expressions and voice, and collects this data. This allows for real-time monitoring of the user's current emotions and stress levels.

[0350] Using machine learning techniques, the server predicts human movement and flow patterns. In addition to traditional pedestrian flow data, emotional data is fed back to improve prediction accuracy. The prediction results are generated as visualization data and visualized by the server. These visualizations are adjusted to the user's emotional state, employing color schemes and presentations designed to reduce stress.

[0351] The generated visualization data is delivered to the user's device in real time. Based on the information provided through the device, users can plan their travel and activities. For example, a user wanting to visit a popular shopping mall on a holiday might receive suggestions for the optimal visit time and route to avoid crowds.

[0352] An example of a prompt message is, "I want to go to a shopping mall on my day off, but please tell me the best time and route to avoid crowds." In this way, users can receive optimal suggestions that take their individual emotional state into consideration.

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] The server collects location data, traffic data, weather data, and event data. Real-time data from external APIs, fixed sensors, and mobile devices is used as input. This data is integrated to generate a dataset with time-series and spatial structure as output.

[0356] Step 2:

[0357] The server collects emotional data from the user's device using the camera and microphone. The input consists of the user's facial expressions and voice, which the emotion engine analyzes. The output is data indicating the user's stress level and emotional state. Specifically, it operates in the background while the user is using the app, continuously acquiring emotional data.

[0358] Step 3:

[0359] The server stores the integrated data in a database. This database supports indexing of time-series and spatial data. The datasets generated in steps 1 and 2 are used as input. The output is an indexed database, which also includes user-specific sentiment data.

[0360] Step 4:

[0361] The server uses machine learning techniques to predict pedestrian flow patterns. Inputs include integrated data stored in a database and user sentiment data. Outputs are predicted pedestrian flow data, enabling highly accurate predictions based on historical and current data. Specifically, the prediction model is periodically updated, allowing for real-time predictions.

[0362] Step 5:

[0363] The server generates prediction results as visualization data. This visualization data is customized according to the user's stress and emotional state. The inputs used are the prediction data obtained in step 4 and data on the user's emotional state. The output is a customized visualization. Specifically, the color scheme and diagram format are automatically adjusted to the user's needs.

[0364] Step 6:

[0365] The server delivers the generated visualization data to the user's device. The input is the customized visualization data generated in step 5. The output is displayed on the user's device, allowing for real-time information verification. Specifically, the user can create a travel plan based on their emotions and circumstances via their device.

[0366] (Application Example 2)

[0367] 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."

[0368] In modern urban environments, for residents to move comfortably and efficiently, it is necessary to integrate various real-time, fluctuating information and propose travel routes and actions that match their individual emotional states. However, conventional systems have struggled to perform fine-tuned optimization that takes emotional states into account, resulting in a failure to improve the user experience.

[0369] 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.

[0370] In this invention, the server includes means for acquiring location information data, traffic information data, weather information data, and event information data; means for integrating the acquired data and storing it in an information storage device; and means for recognizing the user's emotional state and collecting emotional data. This enables highly accurate pedestrian flow prediction and customized suggestions that take emotions into account.

[0371] "Location data" refers to data that provides geographical information related to a specific place or location.

[0372] "Traffic information data" refers to information that shows trends regarding the usage and congestion levels of roads and public transportation.

[0373] "Weather information data" refers to information about meteorological conditions such as weather, temperature, and humidity.

[0374] "Event information data" refers to information about events and activities held in specific regions or locations.

[0375] An "information storage device" is a system or device for accumulating and efficiently managing diverse data.

[0376] "Emotional data" refers to information about a user's emotional state, including indicators such as stress and happiness.

[0377] "Visualization data" refers to data generated to visually represent information and facilitate understanding.

[0378] "User terminal" refers to communication equipment or devices used by individuals to receive information.

[0379] "Feedback" refers to information such as opinions and impressions obtained from users, which is used to improve the system.

[0380] To implement this invention, a system is constructed that combines a server, a user terminal, and a communication device. The server acquires location data, traffic data, weather data, and event data in real time from external APIs, fixed sensors, and mobile devices. This information is stored in an information storage device for data integration and is efficiently managed by indexing time-series data and spatial data.

[0381] The server also features an emotion recognition engine that uses camera and audio data to recognize the user's emotional state, and this emotion data is also stored in an information storage device. Google's TensorFlow is used for the emotion recognition engine, and the Scikit-learn library in Python is used for the machine learning model to improve the accuracy of pedestrian flow prediction.

[0382] The prediction results are generated as visualization data, with the color scheme and content customized according to the user's emotional state. This visualization is delivered to the user's device in real time, allowing the user to adjust their travel plan based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route on their device.

[0383] An example of a prompt message would be: "Suggest the optimal route for an event in the city. Use sentiment data. Current location: Shinjuku, route to Shinjuku Station West Exit Shopping Mall."

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server acquires location data, traffic data, weather data, and event data from external APIs and sensors. This process involves collecting information from each data source, converting it to its respective data format, and performing data format conversion for unified handling. Data input is from external data sources, and output is integrated information data.

[0387] Step 2:

[0388] The server stores the acquired data in an information storage device. In this step, the time-series and spatial data are indexed to organize and store the data in a way that allows for efficient subsequent processing. The input is integrated information data, and the output is an indexed database.

[0389] Step 3:

[0390] The server acquires camera and audio data from the user's terminal and collects the user's emotional data using an emotion recognition engine. At this stage, real-time emotion recognition processing is performed, and the emotional state is quantified and output. The input is camera and audio data, and the output is quantified emotional data.

[0391] Step 4:

[0392] The server inputs integrated data and sentiment data into a machine learning model to predict pedestrian flow. Here, data normalization and feature selection are performed, and a predictive model is built using a machine learning algorithm. The input is an indexed database and sentiment data, and the output is the predicted pedestrian flow pattern.

[0393] Step 5:

[0394] The server generates visualization data based on prediction results and adjusts the color scheme and layout according to the user's emotional state. The visualization algorithm designs a visually intuitive interface. The input is the predicted pedestrian flow pattern, and the output is customized visualization data.

[0395] Step 6:

[0396] The terminal receives visualization data generated from the server, displays it to the user in real time, and provides optimized action suggestions. The terminal analyzes the data received by the communication module and presents the information on the user interface via the display module. The input is customized visualization data, and the output is the information displayed on the user interface.

[0397] 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.

[0398] 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 those described above. 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 shown 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.

[0399] 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.

[0400] [Third Embodiment]

[0401] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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".

[0413] This invention is a system for collecting and integrating information on pedestrian flow from multiple data sources in real time and providing highly accurate pedestrian flow predictions using a predictive model. In a specific embodiment, the server first continuously acquires location information, traffic information, weather information, and event information. This allows the server to grasp the dynamics of pedestrian flow in various situations.

[0414] Next, the server preprocesses the acquired data and integrates it into a database. During the preprocessing process, incomplete data and noise are removed, and the data is normalized. This allows the server to build a clean dataset suitable for analysis.

[0415] Next, the server uses a machine learning model to predict pedestrian flow. It combines historical and real-time data to train a model for highly accurate pedestrian flow prediction. This prediction model responds instantly to the influx of new data, providing the best possible flow forecast at the present moment.

[0416] Furthermore, the server visualizes the prediction results. Specifically, it generates prediction data in visual formats such as heatmaps and flow maps, providing it in a way that users can intuitively understand.

[0417] Finally, the server delivers the generated visualization data to the user's terminal. The user can then open the application on their terminal and plan their movements and actions while visually viewing the real-time heatmap.

[0418] For example, when a user visits the city center on a weekend, the app provides a congestion forecast and suggests the most efficient travel route and visit time. This system allows users to avoid congestion, create a comfortable itinerary, and reduce wasted time and energy.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] The server retrieves data in real time from APIs of location providers, transportation systems, weather stations, and event calendars. In particular, location information is obtained directly from mobile devices and fixed sensors, and transportation data includes traffic congestion information and public transport service status.

[0422] Step 2:

[0423] The server preprocesses the collected raw data. It detects and corrects or removes missing or outlier values. It normalizes the data and converts it into a unified format, making it suitable for analysis.

[0424] Step 3:

[0425] The server stores the pre-processed data in a database. The database creates an index using geographic coordinates based on location information and organizes the data as a time series using timestamps.

[0426] Step 4:

[0427] The server uses machine learning algorithms to train a pedestrian flow prediction model. By combining historical pedestrian flow data with real-time data, it improves prediction accuracy.

[0428] Step 5:

[0429] The server performs short-term and medium-term pedestrian flow forecasts based on predictive models. This makes it possible to predict detailed pedestrian traffic for specific areas and time periods.

[0430] Step 6:

[0431] The server generates heatmaps and flow maps to visualize the prediction results. Visual data, shown with different colors and lines, allows users to see the level of congestion at a glance.

[0432] Step 7:

[0433] The server sends the generated visualization data to the user's device. The user receives this data through a mobile app and adjusts their travel plans and actions based on that information.

[0434] Step 8:

[0435] Users can view predictive data within the app to avoid congestion and choose the optimal travel route. They can also make real-time decisions based on the information and provide feedback on their choices within the app.

[0436] (Example 1)

[0437] 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."

[0438] In modern society, accurate predictions of human flow based on diverse information are required to support the smooth movement and optimization of people's action plans. However, conventional systems have difficulty integrating diverse data in real time and making accurate predictions, requiring a great deal of time and computing resources. Furthermore, they have the problem of not being able to provide information in a way that users can intuitively understand, and thus not being able to adequately contribute to users' action plans.

[0439] 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.

[0440] In this invention, the server includes information gathering means for acquiring location information data, traffic information data, weather information data, and event information data; data cleansing and integration means for preprocessing the acquired data and integrating it into a database; and prediction means for predicting pedestrian flow using machine learning algorithms. This makes it possible to efficiently process information obtained from diverse data sources and provide users with intuitive and real-time useful pedestrian flow prediction information.

[0441] "Information gathering means" refers to a device or system equipped with the function of acquiring location information data, traffic information data, weather information data, and event information data in real time.

[0442] "Data cleansing and integration means" refers to a device or system equipped with the function of preprocessing acquired data, removing incomplete data and noise, and performing processing to integrate it into a database in an appropriate form.

[0443] A "prediction tool" is a device or system equipped with the function of performing calculations to accurately predict the trends of human movement using machine learning algorithms.

[0444] "Visualization means" refers to a device or system equipped with the function of graphically displaying predicted results as a heat map or flow map.

[0445] "Data distribution means" refers to a device or system equipped with the function of quickly and efficiently transmitting generated visualization data to a user's electronic device.

[0446] This invention is implemented by constructing a server-centered system to collect and integrate information on human movement from multiple data sources in real time. The server functions as an information collection means, acquiring location information, traffic information, weather information, and event information using their respective APIs. Specifically, for location information, general geographic information systems and the GPS function of smartphones are used to import data into the server in real time according to the requirements.

[0447] As a data cleansing and integration method, a process is implemented on the server using a programming language such as Python to filter out outliers and missing values ​​in the data and normalize it. This allows for efficient storage and access of the organized data using a relational database system (RDBMS) for database management.

[0448] As a prediction method, the server utilizes frameworks for executing machine learning algorithms. For example, it uses libraries such as TensorFlow and scikit-learn to build neural network models and other learning models, and performs highly accurate pedestrian flow predictions based on input datasets.

[0449] In visualization, the server generates visual data to communicate prediction results to the user. Data visualization libraries such as D3.js and Plotly are used to create heatmaps and flow maps, allowing users to intuitively understand the information.

[0450] Finally, as a data distribution method, the server delivers the generated visual data to the client's terminal. By using the WebSocket protocol, the user's terminal can receive updated information in real time, enabling efficient travel planning. Users can launch and operate the application through their electronic devices, inputting prompts such as "Please predict the congestion level in the city center on the weekend." This allows users to avoid congestion and travel more efficiently.

[0451] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0452] Step 1:

[0453] The server retrieves location data, traffic data, weather data, and event data from their respective APIs. Using API keys and request parameters for each data source as input, the server sends requests. As output, the server aggregates the returned data in different formats. This process collects diverse real-time data on pedestrian flow.

[0454] Step 2:

[0455] The server preprocesses and cleanses the collected data. It receives a raw dataset as input and uses scripts such as Python to standardize the data, impart incomplete data, and denoise it. The output is a clean, consistent dataset, which is then integrated into the database. This preprocessing improves the data quality and makes it suitable for analysis.

[0456] Step 3:

[0457] The server runs a machine learning model using a clean dataset to predict pedestrian flow. Preprocessed data is provided as input, and the server runs a predictive model using machine learning libraries such as TensorFlow. The output generates predictive data showing future pedestrian flow trends. This process allows the server to obtain advanced analytical results, enabling efficient pedestrian flow prediction.

[0458] Step 4:

[0459] The server visualizes predicted pedestrian flow data. Receiving predicted data as input, the server uses visualization libraries such as D3.js to generate heatmaps and flow maps. The output is graphical data that users can intuitively understand. This process allows users to quickly grasp the situation based on visual information.

[0460] Step 5:

[0461] The server sends the visualized data to the user's terminal. Receiving the generated visualization data as input, the server delivers the data in real time using WebSocket. As output, the visualization data is displayed on the user's terminal and becomes accessible to the user. This step allows the user to receive immediate feedback in response to their prompts.

[0462] Step 6:

[0463] Users create action plans based on the visual information they receive. Through the application, users can check real-time pedestrian flow information and input prompts such as, "Please predict the congestion level in the city center on weekends." This allows users to avoid congestion and develop efficient action plans.

[0464] (Application Example 1)

[0465] 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."

[0466] In modern cities, people's movement is becoming increasingly complex, making it difficult to avoid congestion and travel efficiently. This can lead to wasted time, increased stress, and a decline in people's quality of life. Therefore, a system is needed that accurately predicts pedestrian flow in real time and supports users in making optimal travel decisions.

[0467] 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.

[0468] In this invention, the server includes means for acquiring location data, traffic data, weather data, and event data; means for integrating the acquired data and storing it in an information set; and means for predicting pedestrian flow using a machine learning algorithm. This allows users to visually confirm real-time pedestrian flow predictions and select travel routes that avoid congestion.

[0469] "Location data" refers to digital information that indicates the geographical location of an object, and is acquired using technologies such as GPS.

[0470] "Traffic information data" refers to information that shows the status of roads and public transportation, such as delays, congestion, and accidents.

[0471] "Weather information data" refers to information that shows local weather conditions, such as temperature, precipitation, and wind speed.

[0472] "Event information data" refers to information that provides details about events or gatherings held at a specific location and time.

[0473] A "device" is a mechanical or electronic component designed to perform a specific function.

[0474] An "information set" is a collection of data that aggregates and organizes a series of related data elements.

[0475] A "machine learning algorithm" is a computational method that learns patterns based on data and makes predictions and judgments based on new information.

[0476] "Visualized data" refers to data that has been converted into visual representations such as diagrams and graphs, including numerical values ​​and information.

[0477] "User's device" refers to the user's electronic device used to receive the service.

[0478] "Overlay display" is a method of displaying other information on top of a background image or information.

[0479] A "travel route" is a path used to move from one point to another.

[0480] The invention will now be described in terms of embodiments for carrying out the invention. This invention provides a system that predicts pedestrian flow in real time and assists users in making optimal movements. It has a mechanism that integrates various data to make predictions and provides the results to the user visually.

[0481] The server uses devices to acquire location data, traffic data, weather data, and event data, collecting this data in real time. This allows the server to understand the dynamics of human movement, taking various factors into account.

[0482] The collected data is integrated on a server and managed as an information set. Data stream processing technologies such as Apache Kafka are used for integration to ensure data integrity and normalization. Next, based on the integrated dataset, machine learning algorithms (such as TensorFlow) are used to predict pedestrian flow. This algorithm analyzes historical and real-time data, and responds immediately to new data.

[0483] The prediction results are generated as visualized data using visualization tools (such as D3.js). This visualized data is then formatted as a heatmap or flow map and delivered to the user's device. If the user is using a display device such as smart glasses, this visualization data is overlaid, allowing the user to easily understand their travel route.

[0484] As a concrete example, when a user visits a busy area, they can efficiently move to a shopping mall while avoiding crowded intersections. Based on visualized pedestrian flow information, the user can select the optimal route, reducing the stress of travel.

[0485] An example of a prompt to a generative AI model is, "Tell me the best route when walking through a busy downtown area on the weekend. Display real-time visual information on my smart glasses to help me avoid crowded areas." This prompt allows the system to provide optimal pedestrian flow prediction information tailored to the user's needs.

[0486] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0487] Step 1:

[0488] The server acquires location data, traffic data, weather data, and event data in real time. It uses sensors and APIs for data collection and aggregates information from each data source. Input is raw data acquired from each data source, and output is a set of this raw data. The collected data is temporarily stored for subsequent processing.

[0489] Step 2:

[0490] The server integrates the acquired raw data and organizes it as an information set. Apache Kafka is used to process the data stream, normalizing it while maintaining data integrity. The input is the set of raw data obtained in step 1, and the output is a denoised and normalized dataset. This dataset is stored in a database and used for analysis by machine learning models.

[0491] Step 3:

[0492] The server uses machine learning algorithms to predict pedestrian flow. TensorFlow is used to analyze the dataset and apply a model that predicts future pedestrian flow based on past and present data. The input is the normalized dataset obtained in step 2, and the output is the predicted pedestrian flow data. During this process, the model is also updated to enable the generative AI model to respond quickly to new prompts.

[0493] Step 4:

[0494] The server generates prediction results as visualization data. D3.js is used to convert this data into visual formats such as heatmaps and flow maps. The input is the predicted pedestrian flow data obtained in step 3, and the output is the visualization data. The visualized data is then processed in a way that is easy for the user to understand.

[0495] Step 5:

[0496] The server delivers the generated visualization data to the user's device. It sends the data to the user's terminal using a data transfer protocol. The input is the visualization data obtained in step 4, and the output is the data delivery to the user's device. This process includes prompts to avoid difficult situations.

[0497] Step 6:

[0498] The user overlays the received visualization data on the device and selects the optimal travel route. The visualization data is displayed overlaid on the smart glasses' display. The input is the visualization data delivered to the terminal in step 5, and the output is the user's action plan and travel route selection. As a concrete example, it becomes possible to choose a route that avoids congestion.

[0499] 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.

[0500] This invention combines a system that aggregates various information data to perform highly accurate pedestrian flow predictions with an emotion engine that recognizes user emotions. By acquiring various data and enabling multidimensional predictions that also consider the user's emotional state, it provides information that is more tailored to each individual.

[0501] First, the server is equipped with means to acquire location information, traffic information, weather information, and event information. This information is obtained in real time from external APIs, fixed sensors, and mobile devices. The server also has an emotion engine to recognize user emotions, and collects emotion data from the user's device using camera and audio data. This emotion data may vary depending on the user's actions and environment.

[0502] Next, the server integrates the diverse data it has acquired and stores it in a database. Data is efficiently managed through indexing of both time-series and spatial data. Emotional data from the emotion engine is also stored in the database and used to improve the user experience.

[0503] Next, the server uses a machine learning model to predict pedestrian traffic. In addition to conventional models, it incorporates emotional data as feedback to improve prediction accuracy. For example, suggested actions and movements are optimized based on emotions reflected in the popularity of restaurants from other regions and the expected waiting times.

[0504] Furthermore, the server generates prediction results as visualization data. This visualization is customized according to the user's emotional state, with adjustments made to the color scheme and details of the displayed content. If the user is feeling stressed, the presentation will be clearer and more focused.

[0505] Finally, the generated visualization data is delivered to the user's device. The user can view the information in real time through their device and adjust their travel plans and actions based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route.

[0506] Thus, the present invention, which incorporates an emotion engine, is a system that enables advanced data analysis and prediction that takes into account the user's emotional state, and provides a highly personalized user experience.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] The server collects various types of data in real time through APIs from location providers, transportation systems, weather data sources, and event platforms. This provides a foundation for understanding the latest human movement and environmental conditions.

[0510] Step 2:

[0511] The device uses the user's camera and microphone to collect emotional data via an emotion engine, which then transmits it to a server. It uses facial recognition and voice tone analysis to determine the user's emotional state and sends this data to the server as numerical values.

[0512] Step 3:

[0513] The server stores collected location information, traffic information, weather information, event information, and sentiment data in a database. Time-series and spatial data are used for indexing, enabling efficient data management.

[0514] Step 4:

[0515] The server uses stored data to train machine learning models and predict pedestrian flow. Predictions that incorporate emotional data, in particular, suggest optimal routes and actions that take into account user behavioral intentions and stress avoidance.

[0516] Step 5:

[0517] The server converts the prediction results into visualization data. This data is then customized in its display based on the user's current emotional state. For example, if the user is feeling stressed, softer colors are used, and an overload of information is avoided.

[0518] Step 6:

[0519] The server delivers the generated visualization data to the user's terminal. Here, the user can consider action plans in real time based on the displayed information.

[0520] Step 7:

[0521] Users review the visualizations they receive on their devices and select suggested routes and actions. If additional feedback data is generated based on the user's choices, it is sent back to the server to help refine the predictive models and sentiment engine.

[0522] (Example 2)

[0523] 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."

[0524] In modern society, accurately predicting people's movement patterns is a crucial challenge in urban planning, event management, and improving transportation efficiency. However, traditional prediction methods fail to consider subjective factors such as the emotional state of individual users, resulting in inaccurate predictions and making it difficult to provide personalized information and action suggestions.

[0525] 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.

[0526] In this invention, the server includes a configuration means for accumulating location information data, traffic information data, weather information data, and event information data; a configuration means for acquiring user emotion data from a user terminal using a camera and audio device; and a configuration means for integrating the acquired diverse data and storing it in a database resource. This enables highly accurate pedestrian flow prediction that takes user emotions into account, and allows for the optimization of personalized suggestions and action plans.

[0527] "Location data" refers to data that indicates geographical coordinate information for a specific point in time.

[0528] "Traffic information data" refers to data that shows information about traffic flow and operating conditions.

[0529] "Weather information data" refers to data that includes information about weather conditions such as temperature, humidity, and precipitation.

[0530] "Event information data" refers to data that shows information about events and gatherings in a specific region or time.

[0531] "Emotional data" refers to data that indicates a user's emotional state and includes information obtained from facial expressions and voice.

[0532] A "database resource" is a record and management system for integrating and storing information.

[0533] "Machine learning techniques" are methods that allow computers to learn from experience or data and perform inferences and predictions.

[0534] "Visualized data" refers to data that has been processed to provide a visual representation of information.

[0535] "Feedback" is the process of reacting to a prediction or result and using that information as input again.

[0536] This invention is a system that performs highly accurate pedestrian flow predictions tailored to individual users and provides information based on those predictions. Specific embodiments are described below.

[0537] The server collects location data, traffic data, weather data, and event data using external APIs, fixed sensors, mobile devices, etc. The collected data is integrated and stored in database resources. This allows the data to be efficiently indexed as time-series and spatial data.

[0538] Furthermore, the server acquires emotional data from the user's device through its camera and audio equipment. The emotion engine determines the user's emotional state from their facial expressions and voice, and collects this data. This allows for real-time monitoring of the user's current emotions and stress levels.

[0539] Using machine learning techniques, the server predicts human movement and flow patterns. In addition to traditional pedestrian flow data, emotional data is fed back to improve prediction accuracy. The prediction results are generated as visualization data and visualized by the server. These visualizations are adjusted to the user's emotional state, employing color schemes and presentations designed to reduce stress.

[0540] The generated visualization data is delivered to the user's device in real time. Based on the information provided through the device, users can plan their travel and activities. For example, a user wanting to visit a popular shopping mall on a holiday might receive suggestions for the optimal visit time and route to avoid crowds.

[0541] An example of a prompt message is, "I want to go to a shopping mall on my day off, but please tell me the best time and route to avoid crowds." In this way, users can receive optimal suggestions that take their individual emotional state into consideration.

[0542] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0543] Step 1:

[0544] The server collects location data, traffic data, weather data, and event data. Real-time data from external APIs, fixed sensors, and mobile devices is used as input. This data is integrated to generate a dataset with time-series and spatial structure as output.

[0545] Step 2:

[0546] The server collects emotional data from the user's device using the camera and microphone. The input consists of the user's facial expressions and voice, which the emotion engine analyzes. The output is data indicating the user's stress level and emotional state. Specifically, it operates in the background while the user is using the app, continuously acquiring emotional data.

[0547] Step 3:

[0548] The server stores the integrated data in a database. This database supports indexing of time-series and spatial data. The datasets generated in steps 1 and 2 are used as input. The output is an indexed database, which also includes user-specific sentiment data.

[0549] Step 4:

[0550] The server uses machine learning techniques to predict pedestrian flow patterns. Inputs include integrated data stored in a database and user sentiment data. Outputs are predicted pedestrian flow data, enabling highly accurate predictions based on historical and current data. Specifically, the prediction model is periodically updated, allowing for real-time predictions.

[0551] Step 5:

[0552] The server generates prediction results as visualization data. This visualization data is customized according to the user's stress and emotional state. The inputs used are the prediction data obtained in step 4 and data on the user's emotional state. The output is a customized visualization. Specifically, the color scheme and diagram format are automatically adjusted to the user's needs.

[0553] Step 6:

[0554] The server delivers the generated visualization data to the user's device. The input is the customized visualization data generated in step 5. The output is displayed on the user's device, allowing for real-time information verification. Specifically, the user can create a travel plan based on their emotions and circumstances via their device.

[0555] (Application Example 2)

[0556] 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."

[0557] In modern urban environments, for residents to move comfortably and efficiently, it is necessary to integrate various real-time, fluctuating information and propose travel routes and actions that match their individual emotional states. However, conventional systems have struggled to perform fine-tuned optimization that takes emotional states into account, resulting in a failure to improve the user experience.

[0558] 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.

[0559] In this invention, the server includes means for acquiring location information data, traffic information data, weather information data, and event information data; means for integrating the acquired data and storing it in an information storage device; and means for recognizing the user's emotional state and collecting emotional data. This enables highly accurate pedestrian flow prediction and customized suggestions that take emotions into account.

[0560] "Location data" refers to data that provides geographical information related to a specific place or location.

[0561] "Traffic information data" refers to information that shows trends regarding the usage and congestion levels of roads and public transportation.

[0562] "Weather information data" refers to information about meteorological conditions such as weather, temperature, and humidity.

[0563] "Event information data" refers to information about events and activities held in specific regions or locations.

[0564] An "information storage device" is a system or device for accumulating and efficiently managing diverse data.

[0565] "Emotional data" refers to information about a user's emotional state, including indicators such as stress and happiness.

[0566] "Visualization data" refers to data generated to visually represent information and facilitate understanding.

[0567] "User terminal" refers to communication equipment or devices used by individuals to receive information.

[0568] "Feedback" refers to information such as opinions and impressions obtained from users, which is used to improve the system.

[0569] To implement this invention, a system is constructed that combines a server, a user terminal, and a communication device. The server acquires location data, traffic data, weather data, and event data in real time from external APIs, fixed sensors, and mobile devices. This information is stored in an information storage device for data integration and is efficiently managed by indexing time-series data and spatial data.

[0570] The server also features an emotion recognition engine that uses camera and audio data to recognize the user's emotional state, and this emotion data is also stored in an information storage device. Google's TensorFlow is used for the emotion recognition engine, and the Scikit-learn library in Python is used for the machine learning model to improve the accuracy of pedestrian flow prediction.

[0571] The prediction results are generated as visualization data, with the color scheme and content customized according to the user's emotional state. This visualization is delivered to the user's device in real time, allowing the user to adjust their travel plan based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route on their device.

[0572] An example of a prompt message would be: "Suggest the optimal route for an event in the city. Use sentiment data. Current location: Shinjuku, route to Shinjuku Station West Exit Shopping Mall."

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The server acquires location data, traffic data, weather data, and event data from external APIs and sensors. This process involves collecting information from each data source, converting it to its respective data format, and performing data format conversion for unified handling. Data input is from external data sources, and output is integrated information data.

[0576] Step 2:

[0577] The server stores the acquired data in an information storage device. In this step, the time-series and spatial data are indexed to organize and store the data in a way that allows for efficient subsequent processing. The input is integrated information data, and the output is an indexed database.

[0578] Step 3:

[0579] The server acquires camera and audio data from the user's terminal and collects the user's emotional data using an emotion recognition engine. At this stage, real-time emotion recognition processing is performed, and the emotional state is quantified and output. The input is camera and audio data, and the output is quantified emotional data.

[0580] Step 4:

[0581] The server inputs integrated data and sentiment data into a machine learning model to predict pedestrian flow. Here, data normalization and feature selection are performed, and a predictive model is built using a machine learning algorithm. The input is an indexed database and sentiment data, and the output is the predicted pedestrian flow pattern.

[0582] Step 5:

[0583] The server generates visualization data based on prediction results and adjusts the color scheme and layout according to the user's emotional state. The visualization algorithm designs a visually intuitive interface. The input is the predicted pedestrian flow pattern, and the output is customized visualization data.

[0584] Step 6:

[0585] The terminal receives visualization data generated from the server, displays it to the user in real time, and provides optimized action suggestions. The terminal analyzes the data received by the communication module and presents the information on the user interface via the display module. The input is customized visualization data, and the output is the information displayed on the user interface.

[0586] 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.

[0587] 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 those described above. 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 shown 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.

[0588] 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.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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".

[0603] This invention is a system for collecting and integrating information on pedestrian flow from multiple data sources in real time and providing highly accurate pedestrian flow predictions using a predictive model. In a specific embodiment, the server first continuously acquires location information, traffic information, weather information, and event information. This allows the server to grasp the dynamics of pedestrian flow in various situations.

[0604] Next, the server preprocesses the acquired data and integrates it into a database. During the preprocessing process, incomplete data and noise are removed, and the data is normalized. This allows the server to build a clean dataset suitable for analysis.

[0605] Next, the server uses a machine learning model to predict pedestrian flow. It combines historical and real-time data to train a model for highly accurate pedestrian flow prediction. This prediction model responds instantly to the influx of new data, providing the best possible flow forecast at the present moment.

[0606] Furthermore, the server visualizes the prediction results. Specifically, it generates prediction data in visual formats such as heatmaps and flow maps, providing it in a way that users can intuitively understand.

[0607] Finally, the server delivers the generated visualization data to the user's terminal. The user can then open the application on their terminal and plan their movements and actions while visually viewing the real-time heatmap.

[0608] For example, when a user visits the city center on a weekend, the app provides a congestion forecast and suggests the most efficient travel route and visit time. This system allows users to avoid congestion, create a comfortable itinerary, and reduce wasted time and energy.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] The server retrieves data in real time from APIs of location providers, transportation systems, weather stations, and event calendars. In particular, location information is obtained directly from mobile devices and fixed sensors, and transportation data includes traffic congestion information and public transport service status.

[0612] Step 2:

[0613] The server preprocesses the collected raw data. It detects and corrects or removes missing or outlier values. It normalizes the data and converts it into a unified format, making it suitable for analysis.

[0614] Step 3:

[0615] The server stores the pre-processed data in a database. The database creates an index using geographic coordinates based on location information and organizes the data as a time series using timestamps.

[0616] Step 4:

[0617] The server uses machine learning algorithms to train a pedestrian flow prediction model. By combining historical pedestrian flow data with real-time data, it improves prediction accuracy.

[0618] Step 5:

[0619] The server performs short-term and medium-term pedestrian flow forecasts based on predictive models. This makes it possible to predict detailed pedestrian traffic for specific areas and time periods.

[0620] Step 6:

[0621] The server generates heatmaps and flow maps to visualize the prediction results. Visual data, shown with different colors and lines, allows users to see the level of congestion at a glance.

[0622] Step 7:

[0623] The server sends the generated visualization data to the user's device. The user receives this data through a mobile app and adjusts their travel plans and actions based on that information.

[0624] Step 8:

[0625] Users can view predictive data within the app to avoid congestion and choose the optimal travel route. They can also make real-time decisions based on the information and provide feedback on their choices within the app.

[0626] (Example 1)

[0627] 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".

[0628] In modern society, accurate predictions of human flow based on diverse information are required to support the smooth movement and optimization of people's action plans. However, conventional systems have difficulty integrating diverse data in real time and making accurate predictions, requiring a great deal of time and computing resources. Furthermore, they have the problem of not being able to provide information in a way that users can intuitively understand, and thus not being able to adequately contribute to users' action plans.

[0629] 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.

[0630] In this invention, the server includes information gathering means for acquiring location information data, traffic information data, weather information data, and event information data; data cleansing and integration means for preprocessing the acquired data and integrating it into a database; and prediction means for predicting pedestrian flow using machine learning algorithms. This makes it possible to efficiently process information obtained from diverse data sources and provide users with intuitive and real-time useful pedestrian flow prediction information.

[0631] "Information gathering means" refers to a device or system equipped with the function of acquiring location information data, traffic information data, weather information data, and event information data in real time.

[0632] "Data cleansing and integration means" refers to a device or system equipped with the function of preprocessing acquired data, removing incomplete data and noise, and performing processing to integrate it into a database in an appropriate form.

[0633] A "prediction tool" is a device or system equipped with the function of performing calculations to accurately predict the trends of human movement using machine learning algorithms.

[0634] "Visualization means" refers to a device or system equipped with the function of graphically displaying predicted results as a heat map or flow map.

[0635] "Data distribution means" refers to a device or system equipped with the function of quickly and efficiently transmitting generated visualization data to a user's electronic device.

[0636] This invention is implemented by constructing a server-centered system to collect and integrate information on human movement from multiple data sources in real time. The server functions as an information collection means, acquiring location information, traffic information, weather information, and event information using their respective APIs. Specifically, for location information, general geographic information systems and the GPS function of smartphones are used to import data into the server in real time according to the requirements.

[0637] As a data cleansing and integration method, a process is implemented on the server using a programming language such as Python to filter out outliers and missing values ​​in the data and normalize it. This allows for efficient storage and access of the organized data using a relational database system (RDBMS) for database management.

[0638] As a prediction method, the server utilizes frameworks for executing machine learning algorithms. For example, it uses libraries such as TensorFlow and scikit-learn to build neural network models and other learning models, and performs highly accurate pedestrian flow predictions based on input datasets.

[0639] In visualization, the server generates visual data to communicate prediction results to the user. Data visualization libraries such as D3.js and Plotly are used to create heatmaps and flow maps, allowing users to intuitively understand the information.

[0640] Finally, as a data distribution method, the server delivers the generated visual data to the client's terminal. By using the WebSocket protocol, the user's terminal can receive updated information in real time, enabling efficient travel planning. Users can launch and operate the application through their electronic devices, inputting prompts such as "Please predict the congestion level in the city center on the weekend." This allows users to avoid congestion and travel more efficiently.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1:

[0643] The server retrieves location data, traffic data, weather data, and event data from their respective APIs. Using API keys and request parameters for each data source as input, the server sends requests. As output, the server aggregates the returned data in different formats. This process collects diverse real-time data on pedestrian flow.

[0644] Step 2:

[0645] The server preprocesses and cleanses the collected data. It receives a raw dataset as input and uses scripts such as Python to standardize the data, impart incomplete data, and denoise it. The output is a clean, consistent dataset, which is then integrated into the database. This preprocessing improves the data quality and makes it suitable for analysis.

[0646] Step 3:

[0647] The server runs a machine learning model using a clean dataset to predict pedestrian flow. Preprocessed data is provided as input, and the server runs a predictive model using machine learning libraries such as TensorFlow. The output generates predictive data showing future pedestrian flow trends. This process allows the server to obtain advanced analytical results, enabling efficient pedestrian flow prediction.

[0648] Step 4:

[0649] The server visualizes predicted pedestrian flow data. Receiving predicted data as input, the server uses visualization libraries such as D3.js to generate heatmaps and flow maps. The output is graphical data that users can intuitively understand. This process allows users to quickly grasp the situation based on visual information.

[0650] Step 5:

[0651] The server sends the visualized data to the user's terminal. Receiving the generated visualization data as input, the server delivers the data in real time using WebSocket. As output, the visualization data is displayed on the user's terminal and becomes accessible to the user. This step allows the user to receive immediate feedback in response to their prompts.

[0652] Step 6:

[0653] Users create action plans based on the visual information they receive. Through the application, users can check real-time pedestrian flow information and input prompts such as, "Please predict the congestion level in the city center on weekends." This allows users to avoid congestion and develop efficient action plans.

[0654] (Application Example 1)

[0655] 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".

[0656] In modern cities, people's movement is becoming increasingly complex, making it difficult to avoid congestion and travel efficiently. This can lead to wasted time, increased stress, and a decline in people's quality of life. Therefore, a system is needed that accurately predicts pedestrian flow in real time and supports users in making optimal travel decisions.

[0657] 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.

[0658] In this invention, the server includes means for acquiring location data, traffic data, weather data, and event data; means for integrating the acquired data and storing it in an information set; and means for predicting pedestrian flow using a machine learning algorithm. This allows users to visually confirm real-time pedestrian flow predictions and select travel routes that avoid congestion.

[0659] "Location data" refers to digital information that indicates the geographical location of an object, and is acquired using technologies such as GPS.

[0660] "Traffic information data" refers to information that shows the status of roads and public transportation, such as delays, congestion, and accidents.

[0661] "Weather information data" refers to information that shows local weather conditions, such as temperature, precipitation, and wind speed.

[0662] "Event information data" refers to information that provides details about events or gatherings held at a specific location and time.

[0663] A "device" is a mechanical or electronic component designed to perform a specific function.

[0664] An "information set" is a collection of data that aggregates and organizes a series of related data elements.

[0665] A "machine learning algorithm" is a computational method that learns patterns based on data and makes predictions and judgments based on new information.

[0666] "Visualized data" refers to data that has been converted into visual representations such as diagrams and graphs, including numerical values ​​and information.

[0667] "User's device" refers to the user's electronic device used to receive the service.

[0668] "Overlay display" is a method of displaying other information on top of a background image or information.

[0669] A "travel route" is a path used to move from one point to another.

[0670] The invention will now be described in terms of embodiments for carrying out the invention. This invention provides a system that predicts pedestrian flow in real time and assists users in making optimal movements. It has a mechanism that integrates various data to make predictions and provides the results to the user visually.

[0671] The server uses devices to acquire location data, traffic data, weather data, and event data, collecting this data in real time. This allows the server to understand the dynamics of human movement, taking various factors into account.

[0672] The collected data is integrated on a server and managed as an information set. Data stream processing technologies such as Apache Kafka are used for integration to ensure data integrity and normalization. Next, based on the integrated dataset, machine learning algorithms (such as TensorFlow) are used to predict pedestrian flow. This algorithm analyzes historical and real-time data, and responds immediately to new data.

[0673] The prediction results are generated as visualized data using visualization tools (such as D3.js). This visualized data is then formatted as a heatmap or flow map and delivered to the user's device. If the user is using a display device such as smart glasses, this visualization data is overlaid, allowing the user to easily understand their travel route.

[0674] As a concrete example, when a user visits a busy area, they can efficiently move to a shopping mall while avoiding crowded intersections. Based on visualized pedestrian flow information, the user can select the optimal route, reducing the stress of travel.

[0675] An example of a prompt to a generative AI model is, "Tell me the best route when walking through a busy downtown area on the weekend. Display real-time visual information on my smart glasses to help me avoid crowded areas." This prompt allows the system to provide optimal pedestrian flow prediction information tailored to the user's needs.

[0676] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0677] Step 1:

[0678] The server acquires location data, traffic data, weather data, and event data in real time. It uses sensors and APIs for data collection and aggregates information from each data source. Input is raw data acquired from each data source, and output is a set of this raw data. The collected data is temporarily stored for subsequent processing.

[0679] Step 2:

[0680] The server integrates the acquired raw data and organizes it as an information set. Apache Kafka is used to process the data stream, normalizing it while maintaining data integrity. The input is the set of raw data obtained in step 1, and the output is a denoised and normalized dataset. This dataset is stored in a database and used for analysis by machine learning models.

[0681] Step 3:

[0682] The server uses machine learning algorithms to predict pedestrian flow. TensorFlow is used to analyze the dataset and apply a model that predicts future pedestrian flow based on past and present data. The input is the normalized dataset obtained in step 2, and the output is the predicted pedestrian flow data. During this process, the model is also updated to enable the generative AI model to respond quickly to new prompts.

[0683] Step 4:

[0684] The server generates prediction results as visualization data. D3.js is used to convert this data into visual formats such as heatmaps and flow maps. The input is the predicted pedestrian flow data obtained in step 3, and the output is the visualization data. The visualized data is then processed in a way that is easy for the user to understand.

[0685] Step 5:

[0686] The server delivers the generated visualization data to the user's device. It sends the data to the user's terminal using a data transfer protocol. The input is the visualization data obtained in step 4, and the output is the data delivery to the user's device. This process includes prompts to avoid difficult situations.

[0687] Step 6:

[0688] The user overlays the received visualization data on the device and selects the optimal travel route. The visualization data is displayed overlaid on the smart glasses' display. The input is the visualization data delivered to the terminal in step 5, and the output is the user's action plan and travel route selection. As a concrete example, it becomes possible to choose a route that avoids congestion.

[0689] 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.

[0690] This invention combines a system that aggregates various information data to perform highly accurate pedestrian flow predictions with an emotion engine that recognizes user emotions. By acquiring various data and enabling multidimensional predictions that also consider the user's emotional state, it provides information that is more tailored to each individual.

[0691] First, the server is equipped with means to acquire location information, traffic information, weather information, and event information. This information is obtained in real time from external APIs, fixed sensors, and mobile devices. The server also has an emotion engine to recognize user emotions, and collects emotion data from the user's device using camera and audio data. This emotion data may vary depending on the user's actions and environment.

[0692] Next, the server integrates the diverse data it has acquired and stores it in a database. Data is efficiently managed through indexing of both time-series and spatial data. Emotional data from the emotion engine is also stored in the database and used to improve the user experience.

[0693] Next, the server uses a machine learning model to predict pedestrian traffic. In addition to conventional models, it incorporates emotional data as feedback to improve prediction accuracy. For example, suggested actions and movements are optimized based on emotions reflected in the popularity of restaurants from other regions and the expected waiting times.

[0694] Furthermore, the server generates prediction results as visualization data. This visualization is customized according to the user's emotional state, with adjustments made to the color scheme and details of the displayed content. If the user is feeling stressed, the presentation will be clearer and more focused.

[0695] Finally, the generated visualization data is delivered to the user's device. The user can view the information in real time through their device and adjust their travel plans and actions based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route.

[0696] Thus, the present invention, which incorporates an emotion engine, is a system that enables advanced data analysis and prediction that takes into account the user's emotional state, and provides a highly personalized user experience.

[0697] The following describes the processing flow.

[0698] Step 1:

[0699] The server collects various types of data in real time through APIs from location providers, transportation systems, weather data sources, and event platforms. This provides a foundation for understanding the latest human movement and environmental conditions.

[0700] Step 2:

[0701] The device uses the user's camera and microphone to collect emotional data via an emotion engine, which then transmits it to a server. It uses facial recognition and voice tone analysis to determine the user's emotional state and sends this data to the server as numerical values.

[0702] Step 3:

[0703] The server stores collected location information, traffic information, weather information, event information, and sentiment data in a database. Time-series and spatial data are used for indexing, enabling efficient data management.

[0704] Step 4:

[0705] The server uses stored data to train machine learning models and predict pedestrian flow. Predictions that incorporate emotional data, in particular, suggest optimal routes and actions that take into account user behavioral intentions and stress avoidance.

[0706] Step 5:

[0707] The server converts the prediction results into visualization data. This data is then customized in its display based on the user's current emotional state. For example, if the user is feeling stressed, softer colors are used, and an overload of information is avoided.

[0708] Step 6:

[0709] The server delivers the generated visualization data to the user's terminal. Here, the user can consider action plans in real time based on the displayed information.

[0710] Step 7:

[0711] Users review the visualizations they receive on their devices and select suggested routes and actions. If additional feedback data is generated based on the user's choices, it is sent back to the server to help refine the predictive models and sentiment engine.

[0712] (Example 2)

[0713] 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".

[0714] In modern society, accurately predicting people's movement patterns is a crucial challenge in urban planning, event management, and improving transportation efficiency. However, traditional prediction methods fail to consider subjective factors such as the emotional state of individual users, resulting in inaccurate predictions and making it difficult to provide personalized information and action suggestions.

[0715] 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.

[0716] In this invention, the server includes a configuration means for accumulating location information data, traffic information data, weather information data, and event information data; a configuration means for acquiring user emotion data from a user terminal using a camera and audio device; and a configuration means for integrating the acquired diverse data and storing it in a database resource. This enables highly accurate pedestrian flow prediction that takes user emotions into account, and allows for the optimization of personalized suggestions and action plans.

[0717] "Location data" refers to data that indicates geographical coordinate information for a specific point in time.

[0718] "Traffic information data" refers to data that shows information about traffic flow and operating conditions.

[0719] "Weather information data" refers to data that includes information about weather conditions such as temperature, humidity, and precipitation.

[0720] "Event information data" refers to data that shows information about events and gatherings in a specific region or time.

[0721] "Emotional data" refers to data that indicates a user's emotional state and includes information obtained from facial expressions and voice.

[0722] A "database resource" is a record and management system for integrating and storing information.

[0723] "Machine learning techniques" are methods that allow computers to learn from experience or data and perform inferences and predictions.

[0724] "Visualized data" refers to data that has been processed to provide a visual representation of information.

[0725] "Feedback" is the process of reacting to a prediction or result and using that information as input again.

[0726] This invention is a system that performs highly accurate pedestrian flow predictions tailored to individual users and provides information based on those predictions. Specific embodiments are described below.

[0727] The server collects location data, traffic data, weather data, and event data using external APIs, fixed sensors, mobile devices, etc. The collected data is integrated and stored in database resources. This allows the data to be efficiently indexed as time-series and spatial data.

[0728] Furthermore, the server acquires emotional data from the user's device through its camera and audio equipment. The emotion engine determines the user's emotional state from their facial expressions and voice, and collects this data. This allows for real-time monitoring of the user's current emotions and stress levels.

[0729] Using machine learning techniques, the server predicts human movement and flow patterns. In addition to traditional pedestrian flow data, emotional data is fed back to improve prediction accuracy. The prediction results are generated as visualization data and visualized by the server. These visualizations are adjusted to the user's emotional state, employing color schemes and presentations designed to reduce stress.

[0730] The generated visualization data is delivered to the user's device in real time. Based on the information provided through the device, users can plan their travel and activities. For example, a user wanting to visit a popular shopping mall on a holiday might receive suggestions for the optimal visit time and route to avoid crowds.

[0731] An example of a prompt message is, "I want to go to a shopping mall on my day off, but please tell me the best time and route to avoid crowds." In this way, users can receive optimal suggestions that take their individual emotional state into consideration.

[0732] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0733] Step 1:

[0734] The server collects location data, traffic data, weather data, and event data. Real-time data from external APIs, fixed sensors, and mobile devices is used as input. This data is integrated to generate a dataset with time-series and spatial structure as output.

[0735] Step 2:

[0736] The server collects emotional data from the user's device using the camera and microphone. The input consists of the user's facial expressions and voice, which the emotion engine analyzes. The output is data indicating the user's stress level and emotional state. Specifically, it operates in the background while the user is using the app, continuously acquiring emotional data.

[0737] Step 3:

[0738] The server stores the integrated data in a database. This database supports indexing of time-series and spatial data. The datasets generated in steps 1 and 2 are used as input. The output is an indexed database, which also includes user-specific sentiment data.

[0739] Step 4:

[0740] The server uses machine learning techniques to predict pedestrian flow patterns. Inputs include integrated data stored in a database and user sentiment data. Outputs are predicted pedestrian flow data, enabling highly accurate predictions based on historical and current data. Specifically, the prediction model is periodically updated, allowing for real-time predictions.

[0741] Step 5:

[0742] The server generates prediction results as visualization data. This visualization data is customized according to the user's stress and emotional state. The inputs used are the prediction data obtained in step 4 and data on the user's emotional state. The output is a customized visualization. Specifically, the color scheme and diagram format are automatically adjusted to the user's needs.

[0743] Step 6:

[0744] The server delivers the generated visualization data to the user's device. The input is the customized visualization data generated in step 5. The output is displayed on the user's device, allowing for real-time information verification. Specifically, the user can create a travel plan based on their emotions and circumstances via their device.

[0745] (Application Example 2)

[0746] 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".

[0747] In modern urban environments, for residents to move comfortably and efficiently, it is necessary to integrate various real-time, fluctuating information and propose travel routes and actions that match their individual emotional states. However, conventional systems have struggled to perform fine-tuned optimization that takes emotional states into account, resulting in a failure to improve the user experience.

[0748] 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.

[0749] In this invention, the server includes means for acquiring location information data, traffic information data, weather information data, and event information data; means for integrating the acquired data and storing it in an information storage device; and means for recognizing the user's emotional state and collecting emotional data. This enables highly accurate pedestrian flow prediction and customized suggestions that take emotions into account.

[0750] "Location data" refers to data that provides geographical information related to a specific place or location.

[0751] "Traffic information data" refers to information that shows trends regarding the usage and congestion levels of roads and public transportation.

[0752] "Weather information data" refers to information about meteorological conditions such as weather, temperature, and humidity.

[0753] "Event information data" refers to information about events and activities held in specific regions or locations.

[0754] An "information storage device" is a system or device for accumulating and efficiently managing diverse data.

[0755] "Emotional data" refers to information about a user's emotional state, including indicators such as stress and happiness.

[0756] "Visualization data" refers to data generated to visually represent information and facilitate understanding.

[0757] "User terminal" refers to communication equipment or devices used by individuals to receive information.

[0758] "Feedback" refers to information such as opinions and impressions obtained from users, which is used to improve the system.

[0759] To implement this invention, a system is constructed that combines a server, a user terminal, and a communication device. The server acquires location data, traffic data, weather data, and event data in real time from external APIs, fixed sensors, and mobile devices. This information is stored in an information storage device for data integration and is efficiently managed by indexing time-series data and spatial data.

[0760] The server also features an emotion recognition engine that uses camera and audio data to recognize the user's emotional state, and this emotion data is also stored in an information storage device. Google's TensorFlow is used for the emotion recognition engine, and the Scikit-learn library in Python is used for the machine learning model to improve the accuracy of pedestrian flow prediction.

[0761] The prediction results are generated as visualization data, with the color scheme and content customized according to the user's emotional state. This visualization is delivered to the user's device in real time, allowing the user to adjust their travel plan based on individually optimized suggestions. For example, a user who wants to avoid crowds on their way to a shopping area will be recommended the least stressful route on their device.

[0762] An example of a prompt message would be: "Suggest the optimal route for an event in the city. Use sentiment data. Current location: Shinjuku, route to Shinjuku Station West Exit Shopping Mall."

[0763] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0764] Step 1:

[0765] The server acquires location data, traffic data, weather data, and event data from external APIs and sensors. This process involves collecting information from each data source, converting it to its respective data format, and performing data format conversion for unified handling. Data input is from external data sources, and output is integrated information data.

[0766] Step 2:

[0767] The server stores the acquired data in an information storage device. In this step, the time-series and spatial data are indexed to organize and store the data in a way that allows for efficient subsequent processing. The input is integrated information data, and the output is an indexed database.

[0768] Step 3:

[0769] The server acquires camera and audio data from the user's terminal and collects the user's emotional data using an emotion recognition engine. At this stage, real-time emotion recognition processing is performed, and the emotional state is quantified and output. The input is camera and audio data, and the output is quantified emotional data.

[0770] Step 4:

[0771] The server inputs integrated data and sentiment data into a machine learning model to predict pedestrian flow. Here, data normalization and feature selection are performed, and a predictive model is built using a machine learning algorithm. The input is an indexed database and sentiment data, and the output is the predicted pedestrian flow pattern.

[0772] Step 5:

[0773] The server generates visualization data based on prediction results and adjusts the color scheme and layout according to the user's emotional state. The visualization algorithm designs a visually intuitive interface. The input is the predicted pedestrian flow pattern, and the output is customized visualization data.

[0774] Step 6:

[0775] The terminal receives visualization data generated from the server, displays it to the user in real time, and provides optimized action suggestions. The terminal analyzes the data received by the communication module and presents the information on the user interface via the display module. The input is customized visualization data, and the output is the information displayed on the user interface.

[0776] 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.

[0777] 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 those described above. 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 shown 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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."

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] The following is further disclosed regarding the embodiments described above.

[0798] (Claim 1)

[0799] Means for acquiring location data, traffic data, weather data, and event data,

[0800] A means of integrating the acquired data and storing it in a database,

[0801] A method for predicting pedestrian flow using machine learning models,

[0802] A means for generating prediction results as visualization data,

[0803] A system that includes means for distributing generated visualization data to user terminals.

[0804] (Claim 2)

[0805] The system according to claim 1, a means for indexing a database using time-series data and spatial data.

[0806] (Claim 3)

[0807] The system according to claim 1, comprising means for collecting user feedback and analyzing the feedback to improve the accuracy of a predictive model.

[0808] "Example 1"

[0809] (Claim 1)

[0810] Information gathering means for acquiring location data, traffic information data, weather information data, and event information data,

[0811] A data cleansing and integration means for preprocessing acquired data and integrating it into a database,

[0812] A prediction method for predicting pedestrian flow using machine learning algorithms,

[0813] A visualization means for generating prediction results as visualization data,

[0814] A system including data distribution means for distributing generated visualization data to a user's electronic device.

[0815] (Claim 2)

[0816] The system according to claim 1, an indexing means for indexing a database using time-series data and spatial data.

[0817] (Claim 3)

[0818] The system according to claim 1, comprising a feedback analysis means for collecting user feedback and analyzing that feedback to improve the accuracy of a prediction means.

[0819] "Application Example 1"

[0820] (Claim 1)

[0821] Means for acquiring location data, traffic data, weather data, and event data,

[0822] A means for integrating the acquired data and storing it in an information set,

[0823] A method for predicting pedestrian flow using machine learning algorithms,

[0824] A means for generating prediction results as visualization data,

[0825] A means for transmitting the generated visualization data to the user's device,

[0826] A means for overlaying visualization data on the user's display device,

[0827] A device that helps users select the optimal travel route.

[0828] A system that includes this.

[0829] (Claim 2)

[0830] A system according to claim 1, which is an apparatus for indexing an information set using time-series information and spatial information.

[0831] (Claim 3)

[0832] A system according to claim 1, which collects opinions from users and analyzes those opinions to improve the accuracy of a predictive model.

[0833] "Example 2 of combining an emotion engine"

[0834] (Claim 1)

[0835] A configuration means for accumulating location information data, traffic information data, weather information data, and event information data,

[0836] A configuration means for acquiring user emotion data from a user terminal using a camera and audio device,

[0837] A configuration means for integrating the diverse data acquired and storing it in a database resource,

[0838] A configuration means for efficiently managing data records through time-series and spatial identification,

[0839] A configuration that uses machine learning techniques to predict human movement,

[0840] A configuration means for providing feedback on emotional data to improve the accuracy of predictions,

[0841] A configuration means for generating prediction results as visualization data,

[0842] A system that includes a configuration for transmitting that visualization data to a user device.

[0843] (Claim 2)

[0844] The system according to claim 1, which adjusts the display's color tone and information details to adapt the visualization data to the user's emotional state.

[0845] (Claim 3)

[0846] The system according to claim 1, which analyzes user emotion data and modifies the content of suggestions in order to optimize action suggestions and travel plans.

[0847] "Application example 2 when combining with an emotional engine"

[0848] (Claim 1)

[0849] Means for acquiring location data, traffic data, weather data, and event data,

[0850] A means for integrating the acquired data and storing it in an information storage device,

[0851] A means of recognizing the user's emotional state and collecting emotional data,

[0852] A method for predicting pedestrian flow using machine learning models with data and sentiment data,

[0853] A means of generating prediction results as visualization data and customizing them according to emotional state,

[0854] A method for distributing generated visualization data to user terminals and providing personalized suggestions based on emotional state.

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, a means for indexing an information storage device using time-series data and spatial data.

[0858] (Claim 3)

[0859] The system according to claim 1, comprising means for collecting user feedback and analyzing the feedback to improve the accuracy of a predictive model. [Explanation of symbols]

[0860] 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 acquiring location data, traffic data, weather data, and event data, A means for integrating the acquired data and storing it in an information set, A method for predicting pedestrian flow using machine learning algorithms, A means for generating prediction results as visualization data, A means for transmitting the generated visualization data to the user's device, A means for overlaying visualization data on the user's display device, A means to support users in selecting the optimal travel route. A system that includes this.

2. The system according to claim 1, further comprising means for indexing an information set using time-series information and spatial information.

3. The system according to claim 1, further comprising means for collecting user feedback and analyzing that feedback to improve the accuracy of a predictive model.

Images