system

Abstract

We provide the system. [Solution] Means for acquiring pedestrian flow data, Means of obtaining event information, A method for predicting congestion by analyzing acquired pedestrian flow data and event information, A means for generating congestion avoidance information based on the aforementioned prediction, A means of visualizing congestion avoidance information on a map, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, smooth movement avoiding congestion is an important issue for many people. However, it has been difficult to predict congestion in real time and accurately and provide countermeasures by conventional means. In particular, it has been required to quickly respond to changes in traffic conditions during event holding or unexpected situations, but there has been no efficient system for realizing this.

Means for Solving the Problems

[0005] This invention predicts congestion by acquiring pedestrian flow data and event information from multiple data sources and analyzing them with an AI agent. Furthermore, it provides a system that allows users to easily select the optimal route by generating congestion avoidance information based on the prediction results and visualizing it on a map. It also includes means for improving prediction accuracy by collecting user feedback and retraining the prediction model.

[0006] "Human flow data" refers to information about the movement and density of people in a specific region or at a specific point in time.

[0007] "Event information" refers to detailed information about events or activities that will be held at a specific date, time, and location.

[0008] "Analysis" refers to the process of scrutinizing collected data and deriving meaningful insights and predictions from it.

[0009] "Congestion forecasting" is the process of predicting the future concentration of people in a specific area or time period based on past data and real-time information.

[0010] "Congestion avoidance information" refers to information about alternative routes and guidelines provided to avoid anticipated congestion.

[0011] "Visualizing on a map" means displaying analysis results and information on a map in a way that is easy to understand visually.

[0012] "Suggesting the optimal route" means considering the user's current location and destination, and presenting the most efficient means of transportation that avoids congestion and obstacles.

[0013] "Feedback" refers to opinions and impressions regarding the user experience and areas for improvement provided by system users.

[0014] "Retraining" refers to the process of adding new information to past training data in order to improve the accuracy and performance of a learning model. [Brief explanation of the drawing]

[0015] [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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a storage with a reference number 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a congestion prediction system that enables users to travel efficiently and comfortably. The system consists of a server, terminals, and an AI agent.

[0037] First, the server acquires pedestrian flow data and event information from multiple data sources. This information is collected from sources such as traffic sensors, social media posts, location services, and public event schedules. Next, the server cleans this data, converts it into a standardized format, and sends it to an AI agent. The AI ​​agent performs congestion predictions by comparing it with historical data and detecting anomalies in real time. This makes it possible to predict congestion in specific areas and time periods in the future.

[0038] Predicted congestion information is retrieved by a server and visualized on a map. This visualization data is then sent to the terminal. Based on the user's current location and destination, the terminal suggests the optimal route that reflects the predicted information. For example, if a user searches for a route from home to the office during the morning commute, the system can indicate that the usual route is congested and suggest an alternative route.

[0039] After moving, users provide feedback via their devices regarding the effectiveness of congestion avoidance and their satisfaction level. This feedback is collected on a server and used by an AI agent to retrain the predictive model. Through this process, the system continuously improves its predictive accuracy over time.

[0040] By implementing this invention, users can enjoy mobility services based on real-time and sophisticated congestion information, enabling a stress-free travel experience.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server accesses APIs from social media posts, location services, and traffic sensors to collect pedestrian flow data in real time. Furthermore, it obtains event information using APIs provided by public institutions and event organizers.

[0044] Step 2:

[0045] The server cleanses the collected data, which includes removing duplicates, handling missing values, and detecting outliers. Next, it standardizes the data and converts it into a format that the AI ​​agent can process.

[0046] Step 3:

[0047] The server sends the cleansed data to the AI ​​agent. The AI ​​agent combines this data with historical datasets to perform analysis for congestion prediction. This includes temporal and spatial data analysis.

[0048] Step 4:

[0049] The AI ​​agent applies real-time anomaly detection algorithms to identify congestion patterns that deviate from normal patterns. It then returns the identified congestion information to the server.

[0050] Step 5:

[0051] The server prepares the congestion prediction data received from the AI ​​agent to be visualized on a map, and then sends this information to the terminal.

[0052] Step 6:

[0053] The terminal displays map information received from the server, informs the user of congestion status, and calculates and suggests the optimal route from the user's current location to their destination.

[0054] Step 7:

[0055] The user selects the optimal travel route based on the information displayed on the device and moves according to the instructed path.

[0056] Step 8:

[0057] Users who have completed their journey provide feedback via their device regarding the effectiveness of congestion avoidance and their overall satisfaction. This feedback is collected by the server.

[0058] Step 9:

[0059] The server records user feedback in a database and sends it to the AI ​​agent for retraining the predictive model. This improves the system's predictive accuracy.

[0060] (Example 1)

[0061] 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."

[0062] In modern society, congestion is a source of wasted time and stress, significantly reducing the efficiency of travel. In particular, congestion during commutes and events causes unexpected travel delays, negatively impacting economic activity and personal lives. To address these challenges, there is a growing need for systems that provide real-time travel avoidance information.

[0063] 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.

[0064] In this invention, the server includes means for acquiring movement data, means for acquiring event information, means for processing the acquired movement data and event information to detect anomalies, means for predicting congestion by comparing it with past data, means for generating movement avoidance information based on the prediction, and means for visually displaying the movement avoidance information. This makes it possible to provide users with real-time information to support efficient and stress-free movement.

[0065] "Mobility data" refers to information about the movement of people and goods, such as location information and traffic volume.

[0066] "Event information" refers to information related to events that occur on a specific day or in a specific area, such as public events or accidents.

[0067] "Detecting anomalies" refers to the process of recognizing and identifying behavior that deviates from normal data patterns.

[0068] "Predicting congestion" refers to using past and present data to estimate future pedestrian and traffic congestion.

[0069] "Travel avoidance information" refers to information that includes routes and instructions to avoid congestion in specific locations and times.

[0070] "Visually displaying information" refers to providing information to users using visual means such as maps and graphs.

[0071] An "efficient route" refers to the optimal travel route that minimizes travel time and distance to the destination and meets the user's requirements.

[0072] "Gathering opinions" refers to the process of obtaining feedback and evaluations from users.

[0073] "Improving a predictive model" refers to the process of improving the accuracy and effectiveness of predictions based on collected data.

[0074] This invention relates to a congestion prediction system for improving travel efficiency. The system consists of a server, terminals, and an AI agent.

[0075] The server collects movement and event information from various data sources. This information is gathered from sources such as traffic sensors, social media posts, location services, and public event schedules. For example, it includes road traffic volume data obtained using traffic sensors and posts containing keywords such as "congestion" and "traffic jam" extracted from social media. The server cleanses this data and converts it into a consistent format.

[0076] The AI ​​agent uses standardized data to detect anomalies by comparing them with historical data, and uses a generative AI model to predict future congestion. This prediction allows for the generation of congestion avoidance information for specific locations and time periods.

[0077] The server generates a map visually representing the predicted congestion information and sends it to the terminal. The terminal considers the user's current location and destination and suggests the optimal route. For example, if the route the user normally uses is predicted to be congested, an alternative route can be suggested.

[0078] After the journey is complete, the user provides feedback through their device. This feedback is collected by the server and used by an AI agent to improve the predictive model. This allows the system to continuously improve its prediction accuracy, enabling users to have a faster and less stressful travel experience.

[0079] An example of a prompt message is, "Based on data obtained from social media and traffic sensors, please provide a congestion forecast for the area around major train stations next week."

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects movement and event information from multiple data sources, including traffic sensors, social media posts, location services, and public event schedules. In this step, information is retrieved from each data source via APIs. The input is raw data in various formats, and the output is an integrated raw data stream. Specifically, traffic volume data from traffic sensors, keyword posts from social media, and location data are retrieved.

[0083] Step 2:

[0084] The server cleanses the collected raw data and converts it into a standardized format. This step involves removing missing data, eliminating duplicates, and unifying the data format. The input is an integrated raw data stream, and the output is standardized data that can be processed by the AI ​​agent. Specific operations include normalization using a database.

[0085] Step 3:

[0086] The server sends standardized data to the AI ​​agent, which uses a generative AI model to compare it with historical data and detect anomalies. Standardized data is given as input, and the output is a report of the detected anomalies. Specifically, it uses a machine learning algorithm to classify anomaly patterns.

[0087] Step 4:

[0088] The AI ​​agent predicts congestion using a generative AI model based on the results of anomaly detection. In this step, anomaly reports are used as input, and the output is congestion prediction data for a specific area or time period. The specific operation involves running a time-series prediction model.

[0089] Step 5:

[0090] The server retrieves predicted congestion data and displays it on a map in a visually effective format. In this step, the input is congestion prediction data, and the output is visualization data that can be provided to the user. Specific operations include map generation using mapping software.

[0091] Step 6:

[0092] The terminal suggests the optimal route for the user based on the displayed visual data. In this step, the input consists of the visualized data and the user's current location and destination information. The output is the optimal route presented to the user. Specifically, route calculation is performed using a navigation algorithm.

[0093] Step 7:

[0094] Users provide feedback after their movement via their device. This feedback is collected on a server. The input is user feedback, and the output is training data used by the AI ​​agent. Specific actions include information collection using a feedback form.

[0095] Step 8:

[0096] The server sends the collected feedback to the AI ​​agent, which then retrains the predictive model based on that feedback. The input is user feedback data, and the output is the improved predictive model. As a concrete example, model updates are performed using batch learning.

[0097] (Application Example 1)

[0098] 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."

[0099] In modern cities, the complex flow of people and the impact of events make it difficult to predict congestion and provide users with the optimal travel routes. This challenge reduces the efficiency of travel and contributes to stress and wasted time. Furthermore, there is a lack of mechanisms to improve prediction accuracy by utilizing real-time feedback, highlighting the need to support more efficient and comfortable travel.

[0100] 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.

[0101] In this invention, the server includes means for acquiring movement information, means for acquiring event information, and means for analyzing the acquired movement information and event information to predict congestion. This enables the system to propose the optimal travel route to the user in real time, allowing for efficient and comfortable travel. Furthermore, by collecting user feedback and optimizing the prediction model, the prediction accuracy can be improved over time.

[0102] "Means for acquiring movement information" refers to methods for collecting data related to a user's location and travel route.

[0103] "Means of obtaining event information" refers to methods for gathering information related to events and activities taking place within a local area.

[0104] "Methods for predicting congestion" refer to methods for analyzing collected data to predict the degree of human concentration at different times and locations.

[0105] "Means for generating congestion avoidance information" refers to methods for formulating the optimal routes and means available to users based on predicted congestion information.

[0106] "Means for displaying congestion avoidance information" refers to methods for visualizing the generated congestion avoidance information in a way that is easy for users to understand.

[0107] "Means for presenting the optimal route to a user's electronic device" refers to a method of providing optimal route information to a user's mobile device in order to support their travel.

[0108] "Methods for receiving feedback and optimizing predictive models" refer to methods for collecting evaluations obtained from users' usage experiences and using that information to improve prediction accuracy.

[0109] "Means of utilizing diverse information sources" refers to methods for obtaining abundant information from various data sources within a region and using it within a system.

[0110] The system that realizes this invention consists of a server, a terminal, and a user. The server is connected to various data sources necessary for acquiring movement information and event information. Movement information is collected through general location information services and traffic data provision services, and event information is collected from public institution event schedules and local information provision sites, etc.

[0111] The server cleanses this data into a unified format and inputs it into an AI model for predictive analytics. This AI model performs pattern recognition based on historical data and anomaly detection in real time to predict future congestion levels. Machine learning frameworks such as TENSORFLOW® are used as examples of AI models.

[0112] The terminal receives congestion avoidance information transmitted from the server and provides an interface to assist the user's movement. For example, by using a map application on a smartphone or tablet, the system can present the user with the optimal route based on the latest congestion status. Google® Maps API is often used for map display.

[0113] Users can provide feedback on the routes provided by the system while moving through their devices. This feedback is sent to a server and added to the AI ​​model's training data, contributing to improved prediction accuracy.

[0114] As a concrete example, let's assume a user participates in a marathon event held in a city on the weekend. The app receives real-time predictions of public transport congestion for that day and suggests alternative routes if the usual route is congested. The feedback obtained during this process also contributes to improving accuracy for future events.

[0115] An example of a prompt would be, "Please tell me the best route from the city center to my destination next Friday at 3 PM. Please take into account public transport and congestion forecasts."

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server acquires movement information from location services and traffic data providers. It receives location data and traffic data from APIs as input and cleanses them into a standardized format. The output is the cleansed movement information data. Specifically, it standardizes the data format and handles duplicates and missing values.

[0119] Step 2:

[0120] The server retrieves event information from public institution event schedules and local information websites. It receives event-related data as input and organizes it into a format necessary for congestion prediction. The output is the organized event information data. Specifically, it extracts attributes such as event time, location, and scale, and stores them in a database.

[0121] Step 3:

[0122] The server inputs cleansed movement data and organized event data into an AI model to predict congestion. It accepts both movement and event data as input. The output is a congestion prediction for a specific time and location. Specifically, it runs the model and analyzes the data using a machine learning framework such as TensorFlow.

[0123] Step 4:

[0124] The server generates congestion avoidance information based on congestion prediction results. It takes congestion prediction results as input and calculates available alternative routes and less busy times. The output is congestion avoidance information provided to the user. Specifically, it evaluates multiple route options and selects the most efficient path.

[0125] Step 5:

[0126] The terminal receives congestion avoidance information from the server and displays it on the map through the user interface. It accepts congestion avoidance information as input and converts it into a display format. The output is a visual route guide that the user can review. Specifically, it uses the Google Maps API to overlay the information onto the map.

[0127] Step 6:

[0128] The user travels based on route information provided via their device and provides feedback based on their travel experience. The input is the user's experience, and the output is the feedback sent to the system. Specifically, the user inputs their satisfaction level and areas for improvement through a form.

[0129] Step 7:

[0130] The server collects user feedback and uses it to retrain the AI ​​model. It receives feedback data as input and analyzes it to improve the model. The output is an enhanced predictive model. Specifically, it analyzes the feedback and adds it to the model as new data points.

[0131] 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.

[0132] This invention provides a system that helps users avoid congestion and travel comfortably, and further provides more personalized services by taking user emotions into consideration. The system consists of a server, a terminal, an AI agent, and an emotion engine.

[0133] First, the server acquires pedestrian flow data and event information using standard procedures. This includes traffic sensor data, location services, and information from public service APIs. The acquired data is standardized by the server and sent to the AI ​​agent.

[0134] The AI ​​agent uses the received data to analyze pedestrian flow patterns and predict congestion. These predictions are transmitted to the terminal via a server and visualized on a map.

[0135] One feature of this invention is the introduction of an emotion engine. The terminal is equipped with a device for recognizing the user's emotions, and acquires emotion data from, for example, the user's facial expressions, tone of voice, and touch strength. The terminal sends this emotion data to a server, which uses the emotion engine to analyze the user's emotional state.

[0136] The emotion engine analyzes the user's emotional state. Based on this, the AI ​​agent generates congestion avoidance information tailored to the user's emotions. For example, if the user is feeling stressed, it can suggest a quieter route.

[0137] Ultimately, the device presents the user with personalized, emotion-based suggestions, and the user follows those suggestions. After moving, the user provides feedback on their actual travel experience through the device, which is collected by a server and used to further improve the AI ​​agent and emotion engine.

[0138] This allows users not only to avoid congestion but also to enjoy an optimal travel experience tailored to their mood at the time.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server uses various APIs to collect real-time pedestrian flow and event information. This data includes location services, traffic sensors, and posts from social media.

[0142] Step 2:

[0143] The server cleanses the acquired data, removing missing and outlier values. During this process, it also standardizes the data and converts it into a format suitable for analysis by the AI ​​agent.

[0144] Step 3:

[0145] The cleansed data is sent from the server to the AI ​​agent. The AI ​​agent compares it with past data, analyzes temporal and spatial patterns, and makes congestion predictions.

[0146] Step 4:

[0147] The prediction results are sent back to the server, where visualization data is prepared on the map. The server then sends this information to the terminal.

[0148] Step 5:

[0149] The terminal displays congestion prediction information received from the server on a map. Simultaneously, the emotion engine is activated and collects emotion data based on the user's terminal operations and sensor information.

[0150] Step 6:

[0151] The user's facial expressions and voice are recorded through the camera and microphone. Sensors also detect the strength and speed of the user's device operations as emotional data.

[0152] Step 7:

[0153] The device sends emotional data to the server, and the server analyzes the user's emotional state using an emotion engine.

[0154] Step 8:

[0155] The server generates personalized congestion avoidance information based on the user's emotional state and provides optimized travel routes.

[0156] Step 9:

[0157] The user reviews the submitted information, taking emotions into consideration, selects the optimal route displayed on their device, and begins their journey.

[0158] Step 10:

[0159] After completing their journey, users enter feedback about their journey experience on a device. This feedback is sent to a server and used to further improve the AI ​​agent and emotion engine.

[0160] (Example 2)

[0161] 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."

[0162] In modern urban environments, traffic congestion is a daily problem, and there is a demand for efficient and stress-free travel. Furthermore, mobility support that takes into account the emotional state of users has not been sufficiently achieved, and providing services tailored to the individual circumstances of each user remains a challenge.

[0163] 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.

[0164] In this invention, the server includes means for collecting pedestrian flow information, means for collecting location information, means for analyzing the collected pedestrian flow information and location information to predict congestion, means for using an emotion engine to acquire and analyze the emotional state of users, means for generating congestion avoidance information according to the emotional state of users, and means for displaying the congestion avoidance information on a visual display device. This makes it possible to provide an optimal travel route according to the emotional state of each user and to avoid congestion.

[0165] "Human flow information" refers to information about the movement and distribution of people traveling within a specific region or space.

[0166] "Location information" refers to geographical data used to identify the location of a specific object or person.

[0167] "Analysis" refers to the process of thoroughly examining collected data and information to obtain conclusions and insights that are relevant to a specific purpose.

[0168] "Congestion" refers to a state in which an excessive number of people or objects gather in a particular space, making normal actions and movement difficult.

[0169] An "emotion engine" refers to technologies and systems used to recognize and analyze a user's emotional state.

[0170] A "visual display device" refers to equipment or devices used to visually present digital data to a user.

[0171] "Opinions" refers to feedback information collected from users, including subjective evaluations, satisfaction levels, and suggestions for improvement.

[0172] A "predictive model" refers to a computational model built to estimate future events and trends based on data.

[0173] This invention is a system designed to assist users in traveling comfortably and provides personalized services that take into account the user's emotional state.

[0174] The server first collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. This data is standardized and sent to an artificial intelligence agent. Standardization includes transforming location coordinates and unifying data formats, which allows for consistent processing of information obtained from various data sources.

[0175] The device incorporates user facial recognition and voice analysis capabilities. It acquires emotional data through the user's facial expressions and voice tone, and sends this data to a server. The server uses an emotion engine to analyze this data and identify the user's current emotional state.

[0176] The AI ​​agent uses a model to predict future congestion based on standardized data and sentiment data provided by the server. This model is built using Python machine learning libraries, such as scikit-learn. Based on the congestion prediction results and the user's sentiment state, optimal routes and suggested spots are generated.

[0177] The generated suggestions are provided to the user via a terminal. After the user moves, they enter feedback into the terminal. This feedback is collected by the server and used to further improve the congestion prediction model.

[0178] For example, if a user is walking through a busy area, this system could suggest a quieter route. If the system determines that the user's emotional state is "anxious," it would also suggest relaxing spots such as a calm cafe or a quiet park.

[0179] An example of a prompt for the generating AI model would be, "I'd like to visit popular tourist spots in Paris, but please suggest a route that avoids crowds and allows me to relax. Also, please suggest convenient places to rest when I feel stressed." This would then provide the user with customized travel suggestions. This allows the user to enjoy an optimal travel experience tailored to their emotional state.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The server collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. It requests data from each information source's API as input, processes the received data quickly, corrects duplicates and inconsistencies, and standardizes it. As output, it generates a unified dataset and sends it to the AI ​​agent.

[0183] Step 2:

[0184] The device acquires emotional data from the user. It takes raw data from the camera and microphone as input and analyzes the user's emotional state using facial recognition and voice analysis. Specifically, it extracts facial expression features and inputs voice tone into an emotion classification model. The acquired emotional data is then sent to a server as output.

[0185] Step 3:

[0186] The server receives emotion data and analyzes it using an emotion engine. It uses user emotion data received from the terminal as input and processes it to quantify the emotional state. As output, it generates the quantified user emotional state and provides it to the AI ​​agent.

[0187] Step 4:

[0188] The AI ​​agent predicts congestion based on pedestrian flow information, location information, and sentiment data received from the server. Using these datasets as input, it analyzes them with a machine learning model while comparing them with historical data. Specifically, it performs pattern recognition and regression analysis to predict future congestion levels. The predicted congestion information is then sent to the terminal as output.

[0189] Step 5:

[0190] The terminal receives congestion avoidance information generated by the AI ​​agent and presents it to the user as a visual display on the map application. It receives information from the AI ​​agent as input and reflects it on the map in a way that considers usability on the user interface. As output, it provides route suggestions in a visually easy-to-understand format for the user.

[0191] Step 6:

[0192] Users navigate based on information obtained through their devices and input feedback into the devices after their journey. The input consists of filling out a feedback form with their impressions of their travel experience and suggestions for improvement, which the device then sends to the server. The output is the feedback data stored on the server, which is used for subsequent model improvements.

[0193] (Application Example 2)

[0194] 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 device 14 will be referred to as the "terminal."

[0195] In today's society, where users are expected to avoid congestion and travel comfortably, it is crucial not only to provide congestion information but also to offer a personalized travel experience that responds to the user's emotional state. However, current systems are unable to suggest routes that are individually adapted to the user's emotions, and therefore fail to provide the optimal travel experience for users.

[0196] 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.

[0197] In this invention, the server includes means for acquiring pedestrian flow information, means for acquiring activity information, means for analyzing the acquired pedestrian flow information and activity information to predict congestion, means for analyzing the user's emotional state, and means for generating personalized route suggestions based on the emotional state. This makes it possible to provide optimal congestion avoidance guidelines and a travel experience that takes the user's emotions into consideration.

[0198] "Population flow information" refers to data that shows the patterns and density of people's movement in a specific area.

[0199] "Activity information" refers to data that indicates events or activities taking place at specific locations and times.

[0200] A "means for predicting congestion" refers to a device or program that predicts crowds based on acquired pedestrian flow and activity information.

[0201] "Guidelines for avoiding congestion" refer to information about alternative routes and times suggested to avoid congestion.

[0202] "Means of visualizing on a display" refers to devices or software that visually represent and present the generated congestion avoidance guidelines to the user.

[0203] "Means for analyzing emotional states" refers to technologies or devices for recognizing and evaluating a user's emotions.

[0204] "Personalized suggestions" refer to travel routes and plans that are specially tailored based on the individual user's needs and feelings.

[0205] "Current location" refers to information that indicates the geographical location where the user is at a specific time.

[0206] A "destination" is information that indicates the geographical location that a user wants to reach at a specific time.

[0207] "Means of collecting opinions" refer to devices and methods for aggregating user experiences and feedback.

[0208] "Means for retraining predictive models" refers to a mechanism or program that improves existing predictive algorithms based on collected data.

[0209] A system for implementing this invention consists of a server, a terminal, an AI agent, and an emotion engine.

[0210] The server acquires pedestrian flow and activity information from traffic sensor data, location services, and public service APIs. This information is standardized and sent to an AI agent. The AI ​​agent analyzes the received information, predicts congestion, and generates congestion avoidance guidelines. These guidelines are sent to the user's device and visualized on a map.

[0211] The device is equipped with a mechanism to understand the user's emotional state. It acquires emotional data from the user's facial expressions, tone of voice, or touch intensity and sends it to a server. On the server, an emotion engine analyzes this data and evaluates the emotional state. Based on this information, the AI ​​agent generates emotion-based, personalized route suggestions.

[0212] This allows users to not only avoid congestion but also have a better travel experience by being presented with routes that are optimal for their emotional state. For example, if a user is feeling stressed during their morning commute, the server can suggest a quieter route that avoids congestion.

[0213] An example of a prompt message is: "Based on the user's emotional data, consider how to suggest the optimal route. If the user is feeling stressed, explain how to choose a quieter route."

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server acquires pedestrian flow and activity information through traffic sensor data, location services, and public institution APIs. This information is standardized and converted into a format that is easy to analyze. The input is raw data from various data sources, and the output is standardized pedestrian flow and activity information.

[0217] Step 2:

[0218] The server sends standardized pedestrian flow and activity information to the AI ​​agent. The input is the information output by the server, and the output is ready for the AI ​​agent to receive. At this point, data format conversion and error handling take place.

[0219] Step 3:

[0220] The AI ​​agent analyzes pedestrian flow and predicts congestion based on the information it receives. The input consists of standardized pedestrian flow and activity data, while the output is a predicted congestion guideline. The AI ​​agent uses machine learning algorithms to analyze and predict this data.

[0221] Step 4:

[0222] The generated congestion guidelines are sent to the terminal via the server. The input is the prediction result of the AI ​​agent, and the output is data for visualization. The server uses a communication protocol to ensure reliable data transmission.

[0223] Step 5:

[0224] The terminal visualizes the received congestion guidelines on a map. The input is data sent from the server, and the output is map information that the user can visually confirm. In this process, the terminal generates visual elements using map software.

[0225] Step 6:

[0226] The device uses devices that sense facial expressions, voice tone, or touch intensity to understand the user's emotional state and collect emotional data. The input is user behavior data, and the output is emotional state data. The device analyzes the data using emotion recognition technology.

[0227] Step 7:

[0228] The device sends collected emotional state data to the server. The input is the user's emotional state, and the output is the data format the server can receive. The system also checks for any abnormal data.

[0229] Step 8:

[0230] The server uses an emotion engine to evaluate the user's emotional state. The input is the user's emotional state data, and the output is a quantified emotional evaluation. The emotion engine uses artificial intelligence to analyze the emotional state.

[0231] Step 9:

[0232] The AI ​​agent generates personalized route suggestions that are optimal for the user based on the evaluated emotional state. The input is the evaluation result from the emotion engine, and the output is the proposed route guidance. In this process, an optimization is performed according to the emotion using a generative AI model.

[0233] Step 10:

[0234] The device presents the user with optimal route guidance. Input is output from an AI agent, and the output is guidance via a visual display or voice assistant. This allows the user to have an emotionally-based, optimal travel experience.

[0235] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0236] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0237] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0238] [Second Embodiment]

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

[0240] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0241] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0242] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0243] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0244] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0245] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0246] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0247] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0248] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0249] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0250] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0251] This invention is a congestion prediction system that enables users to travel efficiently and comfortably. The system consists of a server, terminals, and an AI agent.

[0252] First, the server acquires pedestrian flow data and event information from multiple data sources. This information is collected from sources such as traffic sensors, social media posts, location services, and public event schedules. Next, the server cleans this data, converts it into a standardized format, and sends it to an AI agent. The AI ​​agent performs congestion predictions by comparing it with historical data and detecting anomalies in real time. This makes it possible to predict congestion in specific areas and time periods in the future.

[0253] Predicted congestion information is retrieved by a server and visualized on a map. This visualization data is then sent to the terminal. Based on the user's current location and destination, the terminal suggests the optimal route that reflects the predicted information. For example, if a user searches for a route from home to the office during the morning commute, the system can indicate that the usual route is congested and suggest an alternative route.

[0254] After moving, users provide feedback via their devices regarding the effectiveness of congestion avoidance and their satisfaction level. This feedback is collected on a server and used by an AI agent to retrain the predictive model. Through this process, the system continuously improves its predictive accuracy over time.

[0255] By implementing this invention, users can enjoy mobility services based on real-time and sophisticated congestion information, enabling a stress-free travel experience.

[0256] The following describes the processing flow.

[0257] Step 1:

[0258] The server accesses APIs from social media posts, location services, and traffic sensors to collect pedestrian flow data in real time. Furthermore, it obtains event information using APIs provided by public institutions and event organizers.

[0259] Step 2:

[0260] The server cleanses the collected data, which includes removing duplicates, handling missing values, and detecting outliers. Next, it standardizes the data and converts it into a format that the AI ​​agent can process.

[0261] Step 3:

[0262] The server sends the cleansed data to the AI ​​agent. The AI ​​agent combines this data with historical datasets to perform analysis for congestion prediction. This includes temporal and spatial data analysis.

[0263] Step 4:

[0264] The AI ​​agent applies real-time anomaly detection algorithms to identify congestion patterns that deviate from normal patterns. It then returns the identified congestion information to the server.

[0265] Step 5:

[0266] The server prepares the congestion prediction data received from the AI ​​agent to be visualized on a map, and then sends this information to the terminal.

[0267] Step 6:

[0268] The terminal displays map information received from the server, informs the user of congestion status, and calculates and suggests the optimal route from the user's current location to their destination.

[0269] Step 7:

[0270] The user selects the optimal travel route based on the information displayed on the device and moves according to the instructed path.

[0271] Step 8:

[0272] Users who have completed their journey provide feedback via their device regarding the effectiveness of congestion avoidance and their overall satisfaction. This feedback is collected by the server.

[0273] Step 9:

[0274] The server records user feedback in a database and sends it to the AI ​​agent for retraining the predictive model. This improves the system's predictive accuracy.

[0275] (Example 1)

[0276] 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."

[0277] In modern society, congestion is a source of wasted time and stress, significantly reducing the efficiency of travel. In particular, congestion during commutes and events causes unexpected travel delays, negatively impacting economic activity and personal lives. To address these challenges, there is a growing need for systems that provide real-time travel avoidance information.

[0278] 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.

[0279] In this invention, the server includes means for acquiring movement data, means for acquiring event information, means for processing the acquired movement data and event information to detect anomalies, means for predicting congestion by comparing it with past data, means for generating movement avoidance information based on the prediction, and means for visually displaying the movement avoidance information. This makes it possible to provide users with real-time information to support efficient and stress-free movement.

[0280] "Mobility data" refers to information about the movement of people and goods, such as location information and traffic volume.

[0281] "Event information" refers to information related to events that occur on a specific day or in a specific area, such as public events or accidents.

[0282] "Detecting anomalies" refers to the process of recognizing and identifying behaviors that deviate from normal data patterns.

[0283] "Predicting congestion" refers to estimating future crowd flow and traffic congestion using past and current data.

[0284] "Movement avoidance information" refers to information including routes and instructions for avoiding congestion at specific locations and times.

[0285] "Visually displaying" refers to providing information to users using visual means such as maps and graphs.

[0286] "Efficient route" refers to the optimal movement route that minimizes the travel time and distance to the destination and meets the user's requirements.

[0287] "Collecting opinions" refers to the process of obtaining feedback and evaluations from users.

[0288] "Improving the prediction model" refers to the process of improving the accuracy and effectiveness of predictions based on the collected data.

[0289] The present invention is a congestion prediction system for improving movement efficiency. This system is composed of a server, a terminal, and an AI agent.

[0290] The server collects movement and event information from various data sources. This information is gathered from sources such as traffic sensors, social media posts, location services, and public event schedules. For example, it includes road traffic volume data obtained using traffic sensors and posts containing keywords such as "congestion" and "traffic jam" extracted from social media. The server cleanses this data and converts it into a consistent format.

[0291] The AI ​​agent uses standardized data to detect anomalies by comparing them with historical data, and uses a generative AI model to predict future congestion. This prediction allows for the generation of congestion avoidance information for specific locations and time periods.

[0292] The server generates a map visually representing the predicted congestion information and sends it to the terminal. The terminal considers the user's current location and destination and suggests the optimal route. For example, if the route the user normally uses is predicted to be congested, an alternative route can be suggested.

[0293] After the journey is complete, the user provides feedback through their device. This feedback is collected by the server and used by an AI agent to improve the predictive model. This allows the system to continuously improve its prediction accuracy, enabling users to have a faster and less stressful travel experience.

[0294] An example of a prompt message is, "Based on data obtained from social media and traffic sensors, please provide a congestion forecast for the area around major train stations next week."

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The server collects movement and event information from multiple data sources, including traffic sensors, social media posts, location services, and public event schedules. In this step, information is retrieved from each data source via APIs. The input is raw data in various formats, and the output is an integrated raw data stream. Specifically, traffic volume data from traffic sensors, keyword posts from social media, and location data are retrieved.

[0298] Step 2:

[0299] The server cleanses the collected raw data and converts it into a standardized format. This step involves removing missing data, eliminating duplicates, and unifying the data format. The input is an integrated raw data stream, and the output is standardized data that can be processed by the AI ​​agent. Specific operations include normalization using a database.

[0300] Step 3:

[0301] The server sends standardized data to the AI ​​agent, which uses a generative AI model to compare it with historical data and detect anomalies. Standardized data is given as input, and the output is a report of the detected anomalies. Specifically, it uses a machine learning algorithm to classify anomaly patterns.

[0302] Step 4:

[0303] The AI ​​agent predicts congestion using a generative AI model based on the results of anomaly detection. In this step, anomaly reports are used as input, and the output is congestion prediction data for a specific area or time period. The specific operation involves running a time-series prediction model.

[0304] Step 5:

[0305] The server acquires the predicted congestion data and displays it on a map in a visually effective form. In this step, the input is the congestion prediction data, and the output is the visualization data that can be provided to the user. Specific operations include map generation using mapping software.

[0306] Step 6:

[0307] Based on the displayed visual data, the terminal proposes an optimal route for the user. In this step, the input is the visualization data and the user's current location and destination information. The output is the optimal route presented to the user. As a specific example, route calculation is performed using a navigation algorithm.

[0308] Step 7:

[0309] The user provides feedback after movement through the terminal. This feedback is collected by the server. The input is the feedback from the user, and the output is the learning data used by the AI agent. Specific operations include information collection using a feedback form.

[0310] Step 8:

[0311] The server sends the feedback collected by the AI agent and retrains the prediction model based on it. The input is the user feedback data, and the output is a prediction model with improved accuracy. As a specific example, model update using batch learning is performed.

[0312] (Application Example 1)

[0313] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0314] In modern cities, the complex flow of people and the impact of events make it difficult to predict congestion and provide users with the optimal travel routes. This challenge reduces the efficiency of travel and contributes to stress and wasted time. Furthermore, there is a lack of mechanisms to improve prediction accuracy by utilizing real-time feedback, highlighting the need to support more efficient and comfortable travel.

[0315] 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.

[0316] In this invention, the server includes means for acquiring movement information, means for acquiring event information, and means for analyzing the acquired movement information and event information to predict congestion. This enables the system to propose the optimal travel route to the user in real time, allowing for efficient and comfortable travel. Furthermore, by collecting user feedback and optimizing the prediction model, the prediction accuracy can be improved over time.

[0317] "Means for acquiring movement information" refers to methods for collecting data related to a user's location and travel route.

[0318] "Means of obtaining event information" refers to methods for gathering information related to events and activities taking place within a local area.

[0319] "Methods for predicting congestion" refer to methods for analyzing collected data to predict the degree of human concentration at different times and locations.

[0320] "Means for generating congestion avoidance information" refers to methods for formulating the optimal routes and means available to users based on predicted congestion information.

[0321] "Means for displaying congestion avoidance information" refers to methods for visualizing the generated congestion avoidance information in a way that is easy for users to understand.

[0322] "Means for presenting the optimal route to a user's electronic device" refers to a method of providing optimal route information to a user's mobile device in order to support their travel.

[0323] "Methods for receiving feedback and optimizing predictive models" refer to methods for collecting evaluations obtained from users' usage experiences and using that information to improve prediction accuracy.

[0324] "Means of utilizing diverse information sources" refers to methods for obtaining abundant information from various data sources within a region and using it within a system.

[0325] The system that realizes this invention consists of a server, a terminal, and a user. The server is connected to various data sources necessary for acquiring movement information and event information. Movement information is collected through general location information services and traffic data provision services, and event information is collected from public institution event schedules and local information provision sites, etc.

[0326] The server cleanses this data into a unified format and inputs it into an AI model for predictive analytics. This AI model performs pattern recognition based on historical data and real-time anomaly detection to predict future congestion levels. Machine learning frameworks such as TensorFlow are used as examples of AI models.

[0327] The terminal receives congestion avoidance information transmitted from the server and provides an interface to assist the user's movement. For example, by using a map application on a smartphone or tablet, the system can present the user with the optimal route based on the latest congestion status. Google Maps API and similar services are often used for map display.

[0328] Users can provide feedback on the routes provided by the system while moving through their devices. This feedback is sent to a server and added to the AI ​​model's training data, contributing to improved prediction accuracy.

[0329] As a concrete example, let's assume a user participates in a marathon event held in a city on the weekend. The app receives real-time predictions of public transport congestion for that day and suggests alternative routes if the usual route is congested. The feedback obtained during this process also contributes to improving accuracy for future events.

[0330] An example of a prompt would be, "Please tell me the best route from the city center to my destination next Friday at 3 PM. Please take into account public transport and congestion forecasts."

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The server acquires movement information from location services and traffic data providers. It receives location data and traffic data from APIs as input and cleanses them into a standardized format. The output is the cleansed movement information data. Specifically, it standardizes the data format and handles duplicates and missing values.

[0334] Step 2:

[0335] The server retrieves event information from public institution event schedules and local information websites. It receives event-related data as input and organizes it into a format necessary for congestion prediction. The output is the organized event information data. Specifically, it extracts attributes such as event time, location, and scale, and stores them in a database.

[0336] Step 3:

[0337] The server inputs cleansed movement data and organized event data into an AI model to predict congestion. It accepts both movement and event data as input. The output is a congestion prediction for a specific time and location. Specifically, it runs the model and analyzes the data using a machine learning framework such as TensorFlow.

[0338] Step 4:

[0339] The server generates congestion avoidance information based on congestion prediction results. It takes congestion prediction results as input and calculates available alternative routes and less busy times. The output is congestion avoidance information provided to the user. Specifically, it evaluates multiple route options and selects the most efficient path.

[0340] Step 5:

[0341] The terminal receives congestion avoidance information from the server and displays it on the map through the user interface. It accepts congestion avoidance information as input and converts it into a display format. The output is a visual route guide that the user can review. Specifically, it uses the Google Maps API to overlay the information onto the map.

[0342] Step 6:

[0343] The user travels based on route information provided via their device and provides feedback based on their travel experience. The input is the user's experience, and the output is the feedback sent to the system. Specifically, the user inputs their satisfaction level and areas for improvement through a form.

[0344] Step 7:

[0345] The server collects user feedback and uses it to retrain the AI ​​model. It receives feedback data as input and analyzes it to improve the model. The output is an enhanced predictive model. Specifically, it analyzes the feedback and adds it to the model as new data points.

[0346] 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.

[0347] This invention provides a system that helps users avoid congestion and travel comfortably, and further provides more personalized services by taking user emotions into consideration. The system consists of a server, a terminal, an AI agent, and an emotion engine.

[0348] First, the server acquires pedestrian flow data and event information using standard procedures. This includes traffic sensor data, location services, and information from public service APIs. The acquired data is standardized by the server and sent to the AI ​​agent.

[0349] The AI ​​agent uses the received data to analyze pedestrian flow patterns and predict congestion. These predictions are transmitted to the terminal via a server and visualized on a map.

[0350] One feature of this invention is the introduction of an emotion engine. The terminal is equipped with a device for recognizing the user's emotions, and acquires emotion data from, for example, the user's facial expressions, tone of voice, and touch strength. The terminal sends this emotion data to a server, which uses the emotion engine to analyze the user's emotional state.

[0351] The emotion engine analyzes the user's emotional state. Based on this, the AI ​​agent generates congestion avoidance information tailored to the user's emotions. For example, if the user is feeling stressed, it can suggest a quieter route.

[0352] Ultimately, the device presents the user with personalized, emotion-based suggestions, and the user follows those suggestions. After moving, the user provides feedback on their actual travel experience through the device, which is collected by a server and used to further improve the AI ​​agent and emotion engine.

[0353] This allows users not only to avoid congestion but also to enjoy an optimal travel experience tailored to their mood at the time.

[0354] The following describes the processing flow.

[0355] Step 1:

[0356] The server uses various APIs to collect real-time pedestrian flow and event information. This data includes location services, traffic sensors, and posts from social media.

[0357] Step 2:

[0358] The server cleanses the acquired data, removing missing and outlier values. During this process, it also standardizes the data and converts it into a format suitable for analysis by the AI ​​agent.

[0359] Step 3:

[0360] The cleansed data is sent from the server to the AI ​​agent. The AI ​​agent compares it with past data, analyzes temporal and spatial patterns, and makes congestion predictions.

[0361] Step 4:

[0362] The prediction results are sent back to the server, where visualization data is prepared on the map. The server then sends this information to the terminal.

[0363] Step 5:

[0364] The terminal displays congestion prediction information received from the server on a map. Simultaneously, the emotion engine is activated and collects emotion data based on the user's terminal operations and sensor information.

[0365] Step 6:

[0366] The user's facial expressions and voice are recorded through the camera and microphone. Sensors also detect the strength and speed of the user's device operations as emotional data.

[0367] Step 7:

[0368] The device sends emotional data to the server, and the server analyzes the user's emotional state using an emotion engine.

[0369] Step 8:

[0370] The server generates personalized congestion avoidance information based on the user's emotional state and provides optimized travel routes.

[0371] Step 9:

[0372] The user reviews the submitted information, taking emotions into consideration, selects the optimal route displayed on their device, and begins their journey.

[0373] Step 10:

[0374] After completing their journey, users enter feedback about their journey experience on a device. This feedback is sent to a server and used to further improve the AI ​​agent and emotion engine.

[0375] (Example 2)

[0376] 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".

[0377] In modern urban environments, traffic congestion is a daily problem, and there is a demand for efficient and stress-free travel. Furthermore, mobility support that takes into account the emotional state of users has not been sufficiently achieved, and providing services tailored to the individual circumstances of each user remains a challenge.

[0378] 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.

[0379] In this invention, the server includes means for collecting pedestrian flow information, means for collecting location information, means for analyzing the collected pedestrian flow information and location information to predict congestion, means for using an emotion engine to acquire and analyze the emotional state of users, means for generating congestion avoidance information according to the emotional state of users, and means for displaying the congestion avoidance information on a visual display device. This makes it possible to provide an optimal travel route according to the emotional state of each user and to avoid congestion.

[0380] "Human flow information" refers to information about the movement and distribution of people traveling within a specific region or space.

[0381] "Location information" refers to geographical data used to identify the location of a specific object or person.

[0382] "Analysis" refers to the process of thoroughly examining collected data and information to obtain conclusions and insights that are relevant to a specific purpose.

[0383] "Congestion" refers to a state in which an excessive number of people or objects gather in a particular space, making normal actions and movement difficult.

[0384] An "emotion engine" refers to technologies and systems used to recognize and analyze a user's emotional state.

[0385] A "visual display device" refers to equipment or devices used to visually present digital data to a user.

[0386] "Opinions" refers to feedback information collected from users, including subjective evaluations, satisfaction levels, and suggestions for improvement.

[0387] A "predictive model" refers to a computational model built to estimate future events and trends based on data.

[0388] This invention is a system designed to assist users in traveling comfortably and provides personalized services that take into account the user's emotional state.

[0389] The server first collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. This data is standardized and sent to an artificial intelligence agent. Standardization includes transforming location coordinates and unifying data formats, which allows for consistent processing of information obtained from various data sources.

[0390] The device incorporates user facial recognition and voice analysis capabilities. It acquires emotional data through the user's facial expressions and voice tone, and sends this data to a server. The server uses an emotion engine to analyze this data and identify the user's current emotional state.

[0391] The AI ​​agent uses a model to predict future congestion based on standardized data and sentiment data provided by the server. This model is built using Python machine learning libraries, such as scikit-learn. Based on the congestion prediction results and the user's sentiment state, optimal routes and suggested spots are generated.

[0392] The generated suggestions are provided to the user via a terminal. After the user moves, they enter feedback into the terminal. This feedback is collected by the server and used to further improve the congestion prediction model.

[0393] For example, if a user is walking through a busy area, this system could suggest a quieter route. If the system determines that the user's emotional state is "anxious," it would also suggest relaxing spots such as a calm cafe or a quiet park.

[0394] An example of a prompt for the generating AI model would be, "I'd like to visit popular tourist spots in Paris, but please suggest a route that avoids crowds and allows me to relax. Also, please suggest convenient places to rest when I feel stressed." This would then provide the user with customized travel suggestions. This allows the user to enjoy an optimal travel experience tailored to their emotional state.

[0395] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0396] Step 1:

[0397] The server collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. It requests data from each information source's API as input, processes the received data quickly, corrects duplicates and inconsistencies, and standardizes it. As output, it generates a unified dataset and sends it to the AI ​​agent.

[0398] Step 2:

[0399] The device acquires emotional data from the user. It takes raw data from the camera and microphone as input and analyzes the user's emotional state using facial recognition and voice analysis. Specifically, it extracts facial expression features and inputs voice tone into an emotion classification model. The acquired emotional data is then sent to a server as output.

[0400] Step 3:

[0401] The server receives emotion data and analyzes it using an emotion engine. It uses user emotion data received from the terminal as input and processes it to quantify the emotional state. As output, it generates the quantified user emotional state and provides it to the AI ​​agent.

[0402] Step 4:

[0403] The AI ​​agent predicts congestion based on pedestrian flow information, location information, and sentiment data received from the server. Using these datasets as input, it analyzes them with a machine learning model while comparing them with historical data. Specifically, it performs pattern recognition and regression analysis to predict future congestion levels. The predicted congestion information is then sent to the terminal as output.

[0404] Step 5:

[0405] The terminal receives congestion avoidance information generated by the AI ​​agent and presents it to the user as a visual display on the map application. It receives information from the AI ​​agent as input and reflects it on the map in a way that considers usability on the user interface. As output, it provides route suggestions in a visually easy-to-understand format for the user.

[0406] Step 6:

[0407] Users navigate based on information obtained through their devices and input feedback into the devices after their journey. The input consists of filling out a feedback form with their impressions of their travel experience and suggestions for improvement, which the device then sends to the server. The output is the feedback data stored on the server, which is used for subsequent model improvements.

[0408] (Application Example 2)

[0409] 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."

[0410] In today's society, where users are expected to avoid congestion and travel comfortably, it is crucial not only to provide congestion information but also to offer a personalized travel experience that responds to the user's emotional state. However, current systems are unable to suggest routes that are individually adapted to the user's emotions, and therefore fail to provide the optimal travel experience for users.

[0411] 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.

[0412] In this invention, the server includes means for acquiring pedestrian flow information, means for acquiring activity information, means for analyzing the acquired pedestrian flow information and activity information to predict congestion, means for analyzing the user's emotional state, and means for generating personalized route suggestions based on the emotional state. This makes it possible to provide optimal congestion avoidance guidelines and a travel experience that takes the user's emotions into consideration.

[0413] "Population flow information" refers to data that shows the patterns and density of people's movement in a specific area.

[0414] "Activity information" refers to data that indicates events or activities taking place at specific locations and times.

[0415] A "means for predicting congestion" refers to a device or program that predicts crowds based on acquired pedestrian flow and activity information.

[0416] "Guidelines for avoiding congestion" refer to information about alternative routes and times suggested to avoid congestion.

[0417] "Means of visualizing on a display" refers to devices or software that visually represent and present the generated congestion avoidance guidelines to the user.

[0418] "Means for analyzing emotional states" refers to technologies or devices for recognizing and evaluating a user's emotions.

[0419] "Personalized suggestions" refer to travel routes and plans that are specially tailored based on the individual user's needs and feelings.

[0420] "Current location" refers to information that indicates the geographical location where the user is at a specific time.

[0421] A "destination" is information that indicates the geographical location that a user wants to reach at a specific time.

[0422] "Means of collecting opinions" refer to devices and methods for aggregating user experiences and feedback.

[0423] "Means for retraining predictive models" refers to a mechanism or program that improves existing predictive algorithms based on collected data.

[0424] A system for implementing this invention consists of a server, a terminal, an AI agent, and an emotion engine.

[0425] The server acquires pedestrian flow and activity information from traffic sensor data, location services, and public service APIs. This information is standardized and sent to an AI agent. The AI ​​agent analyzes the received information, predicts congestion, and generates congestion avoidance guidelines. These guidelines are sent to the user's device and visualized on a map.

[0426] The device is equipped with a mechanism to understand the user's emotional state. It acquires emotional data from the user's facial expressions, tone of voice, or touch intensity and sends it to a server. On the server, an emotion engine analyzes this data and evaluates the emotional state. Based on this information, the AI ​​agent generates emotion-based, personalized route suggestions.

[0427] This allows users to not only avoid congestion but also have a better travel experience by being presented with routes that are optimal for their emotional state. For example, if a user is feeling stressed during their morning commute, the server can suggest a quieter route that avoids congestion.

[0428] An example of a prompt message is: "Based on the user's emotional data, consider how to suggest the optimal route. If the user is feeling stressed, explain how to choose a quieter route."

[0429] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0430] Step 1:

[0431] The server acquires pedestrian flow and activity information through traffic sensor data, location services, and public institution APIs. This information is standardized and converted into a format that is easy to analyze. The input is raw data from various data sources, and the output is standardized pedestrian flow and activity information.

[0432] Step 2:

[0433] The server sends standardized pedestrian flow and activity information to the AI ​​agent. The input is the information output by the server, and the output is ready for the AI ​​agent to receive. At this point, data format conversion and error handling take place.

[0434] Step 3:

[0435] The AI ​​agent analyzes pedestrian flow and predicts congestion based on the information it receives. The input consists of standardized pedestrian flow and activity data, while the output is a predicted congestion guideline. The AI ​​agent uses machine learning algorithms to analyze and predict this data.

[0436] Step 4:

[0437] The generated congestion guidelines are sent to the terminal via the server. The input is the prediction result of the AI ​​agent, and the output is data for visualization. The server uses a communication protocol to ensure reliable data transmission.

[0438] Step 5:

[0439] The terminal visualizes the received congestion guidelines on a map. The input is data sent from the server, and the output is map information that the user can visually confirm. In this process, the terminal generates visual elements using map software.

[0440] Step 6:

[0441] The device uses devices that sense facial expressions, voice tone, or touch intensity to understand the user's emotional state and collect emotional data. The input is user behavior data, and the output is emotional state data. The device analyzes the data using emotion recognition technology.

[0442] Step 7:

[0443] The device sends collected emotional state data to the server. The input is the user's emotional state, and the output is the data format the server can receive. The system also checks for any abnormal data.

[0444] Step 8:

[0445] The server uses an emotion engine to evaluate the user's emotional state. The input is the user's emotional state data, and the output is a quantified emotional evaluation. The emotion engine uses artificial intelligence to analyze the emotional state.

[0446] Step 9:

[0447] The AI ​​agent generates personalized route suggestions that are optimal for the user based on the evaluated emotional state. The input is the evaluation result from the emotion engine, and the output is the proposed route guidance. In this process, an optimization is performed according to the emotion using a generative AI model.

[0448] Step 10:

[0449] The device presents the user with optimal route guidance. Input is output from an AI agent, and the output is guidance via a visual display or voice assistant. This allows the user to have an emotionally-based, optimal travel experience.

[0450] 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.

[0451] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0452] 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.

[0453] [Third Embodiment]

[0454] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0455] 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.

[0456] 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).

[0457] 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.

[0458] 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.

[0459] 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).

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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".

[0466] This invention is a congestion prediction system that enables users to travel efficiently and comfortably. The system consists of a server, terminals, and an AI agent.

[0467] First, the server acquires pedestrian flow data and event information from multiple data sources. This information is collected from sources such as traffic sensors, social media posts, location services, and public event schedules. Next, the server cleans this data, converts it into a standardized format, and sends it to an AI agent. The AI ​​agent performs congestion predictions by comparing it with historical data and detecting anomalies in real time. This makes it possible to predict congestion in specific areas and time periods in the future.

[0468] Predicted congestion information is retrieved by a server and visualized on a map. This visualization data is then sent to the terminal. Based on the user's current location and destination, the terminal suggests the optimal route that reflects the predicted information. For example, if a user searches for a route from home to the office during the morning commute, the system can indicate that the usual route is congested and suggest an alternative route.

[0469] After moving, users provide feedback via their devices regarding the effectiveness of congestion avoidance and their satisfaction level. This feedback is collected on a server and used by an AI agent to retrain the predictive model. Through this process, the system continuously improves its predictive accuracy over time.

[0470] By implementing this invention, users can enjoy mobility services based on real-time and sophisticated congestion information, enabling a stress-free travel experience.

[0471] The following describes the processing flow.

[0472] Step 1:

[0473] The server accesses APIs from social media posts, location services, and traffic sensors to collect pedestrian flow data in real time. Furthermore, it obtains event information using APIs provided by public institutions and event organizers.

[0474] Step 2:

[0475] The server cleanses the collected data, which includes removing duplicates, handling missing values, and detecting outliers. Next, it standardizes the data and converts it into a format that the AI ​​agent can process.

[0476] Step 3:

[0477] The server sends the cleansed data to the AI ​​agent. The AI ​​agent combines this data with historical datasets to perform analysis for congestion prediction. This includes temporal and spatial data analysis.

[0478] Step 4:

[0479] The AI ​​agent applies real-time anomaly detection algorithms to identify congestion patterns that deviate from normal patterns. It then returns the identified congestion information to the server.

[0480] Step 5:

[0481] The server prepares the congestion prediction data received from the AI ​​agent to be visualized on a map, and then sends this information to the terminal.

[0482] Step 6:

[0483] The terminal displays map information received from the server, informs the user of congestion status, and calculates and suggests the optimal route from the user's current location to their destination.

[0484] Step 7:

[0485] The user selects the optimal travel route based on the information displayed on the device and moves according to the instructed path.

[0486] Step 8:

[0487] Users who have completed their journey provide feedback via their device regarding the effectiveness of congestion avoidance and their overall satisfaction. This feedback is collected by the server.

[0488] Step 9:

[0489] The server records user feedback in a database and sends it to the AI ​​agent for retraining the predictive model. This improves the system's predictive accuracy.

[0490] (Example 1)

[0491] 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."

[0492] In modern society, congestion is a source of wasted time and stress, significantly reducing the efficiency of travel. In particular, congestion during commutes and events causes unexpected travel delays, negatively impacting economic activity and personal lives. To address these challenges, there is a growing need for systems that provide real-time travel avoidance information.

[0493] 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.

[0494] In this invention, the server includes means for acquiring movement data, means for acquiring event information, means for processing the acquired movement data and event information to detect anomalies, means for predicting congestion by comparing it with past data, means for generating movement avoidance information based on the prediction, and means for visually displaying the movement avoidance information. This makes it possible to provide users with real-time information to support efficient and stress-free movement.

[0495] "Mobility data" refers to information about the movement of people and goods, such as location information and traffic volume.

[0496] "Event information" refers to information related to events that occur on a specific day or in a specific area, such as public events or accidents.

[0497] "Detecting anomalies" refers to the process of recognizing and identifying behavior that deviates from normal data patterns.

[0498] "Predicting congestion" refers to using past and present data to estimate future pedestrian and traffic congestion.

[0499] "Travel avoidance information" refers to information that includes routes and instructions to avoid congestion in specific locations and times.

[0500] "Visually displaying information" refers to providing information to users using visual means such as maps and graphs.

[0501] An "efficient route" refers to the optimal travel route that minimizes travel time and distance to the destination and meets the user's requirements.

[0502] "Gathering opinions" refers to the process of obtaining feedback and evaluations from users.

[0503] "Improving a predictive model" refers to the process of improving the accuracy and effectiveness of predictions based on collected data.

[0504] This invention relates to a congestion prediction system for improving travel efficiency. The system consists of a server, terminals, and an AI agent.

[0505] The server collects movement and event information from various data sources. This information is gathered from sources such as traffic sensors, social media posts, location services, and public event schedules. For example, it includes road traffic volume data obtained using traffic sensors and posts containing keywords such as "congestion" and "traffic jam" extracted from social media. The server cleanses this data and converts it into a consistent format.

[0506] The AI ​​agent uses standardized data to detect anomalies by comparing them with historical data, and uses a generative AI model to predict future congestion. This prediction allows for the generation of congestion avoidance information for specific locations and time periods.

[0507] The server generates a map visually representing the predicted congestion information and sends it to the terminal. The terminal considers the user's current location and destination and suggests the optimal route. For example, if the route the user normally uses is predicted to be congested, an alternative route can be suggested.

[0508] After the journey is complete, the user provides feedback through their device. This feedback is collected by the server and used by an AI agent to improve the predictive model. This allows the system to continuously improve its prediction accuracy, enabling users to have a faster and less stressful travel experience.

[0509] An example of a prompt message is, "Based on data obtained from social media and traffic sensors, please provide a congestion forecast for the area around major train stations next week."

[0510] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0511] Step 1:

[0512] The server collects movement and event information from multiple data sources, including traffic sensors, social media posts, location services, and public event schedules. In this step, information is retrieved from each data source via APIs. The input is raw data in various formats, and the output is an integrated raw data stream. Specifically, traffic volume data from traffic sensors, keyword posts from social media, and location data are retrieved.

[0513] Step 2:

[0514] The server cleanses the collected raw data and converts it into a standardized format. This step involves removing missing data, eliminating duplicates, and unifying the data format. The input is an integrated raw data stream, and the output is standardized data that can be processed by the AI ​​agent. Specific operations include normalization using a database.

[0515] Step 3:

[0516] The server sends standardized data to the AI ​​agent, which uses a generative AI model to compare it with historical data and detect anomalies. Standardized data is given as input, and the output is a report of the detected anomalies. Specifically, it uses a machine learning algorithm to classify anomaly patterns.

[0517] Step 4:

[0518] The AI ​​agent predicts congestion using a generative AI model based on the results of anomaly detection. In this step, anomaly reports are used as input, and the output is congestion prediction data for a specific area or time period. The specific operation involves running a time-series prediction model.

[0519] Step 5:

[0520] The server retrieves predicted congestion data and displays it on a map in a visually effective format. In this step, the input is congestion prediction data, and the output is visualization data that can be provided to the user. Specific operations include map generation using mapping software.

[0521] Step 6:

[0522] The terminal suggests the optimal route for the user based on the displayed visual data. In this step, the input consists of the visualized data and the user's current location and destination information. The output is the optimal route presented to the user. Specifically, route calculation is performed using a navigation algorithm.

[0523] Step 7:

[0524] Users provide feedback after their movement via their device. This feedback is collected on a server. The input is user feedback, and the output is training data used by the AI ​​agent. Specific actions include information collection using a feedback form.

[0525] Step 8:

[0526] The server sends the collected feedback to the AI ​​agent, which then retrains the predictive model based on that feedback. The input is user feedback data, and the output is the improved predictive model. As a concrete example, model updates are performed using batch learning.

[0527] (Application Example 1)

[0528] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0529] In modern cities, the complex flow of people and the impact of events make it difficult to predict congestion and provide users with the optimal travel routes. This challenge reduces the efficiency of travel and contributes to stress and wasted time. Furthermore, there is a lack of mechanisms to improve prediction accuracy by utilizing real-time feedback, highlighting the need to support more efficient and comfortable travel.

[0530] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0531] In this invention, the server includes means for acquiring movement information, means for acquiring event information, and means for analyzing the acquired movement information and event information to predict congestion. This enables the system to propose the optimal travel route to the user in real time, allowing for efficient and comfortable travel. Furthermore, by collecting user feedback and optimizing the prediction model, the prediction accuracy can be improved over time.

[0532] "Means for acquiring movement information" refers to methods for collecting data related to a user's location and travel route.

[0533] "Means of obtaining event information" refers to methods for gathering information related to events and activities taking place within a local area.

[0534] "Methods for predicting congestion" refer to methods for analyzing collected data to predict the degree of human concentration at different times and locations.

[0535] "Means for generating congestion avoidance information" refers to methods for formulating the optimal routes and means available to users based on predicted congestion information.

[0536] "Means for displaying congestion avoidance information" refers to methods for visualizing the generated congestion avoidance information in a way that is easy for users to understand.

[0537] "Means for presenting the optimal route to a user's electronic device" refers to a method of providing optimal route information to a user's mobile device in order to support their travel.

[0538] "Methods for receiving feedback and optimizing predictive models" refer to methods for collecting evaluations obtained from users' usage experiences and using that information to improve prediction accuracy.

[0539] "Means of utilizing diverse information sources" refers to methods for obtaining abundant information from various data sources within a region and using it within a system.

[0540] The system that realizes this invention consists of a server, a terminal, and a user. The server is connected to various data sources necessary for acquiring movement information and event information. Movement information is collected through general location information services and traffic data provision services, and event information is collected from public institution event schedules and local information provision sites, etc.

[0541] The server cleanses this data into a unified format and inputs it into an AI model for predictive analytics. This AI model performs pattern recognition based on historical data and real-time anomaly detection to predict future congestion levels. Machine learning frameworks such as TensorFlow are used as examples of AI models.

[0542] The terminal receives congestion avoidance information transmitted from the server and provides an interface to assist the user's movement. For example, by using a map application on a smartphone or tablet, the system can present the user with the optimal route based on the latest congestion status. Google Maps API and similar services are often used for map display.

[0543] Users can provide feedback on the routes provided by the system while moving through their devices. This feedback is sent to a server and added to the AI ​​model's training data, contributing to improved prediction accuracy.

[0544] As a concrete example, let's assume a user participates in a marathon event held in a city on the weekend. The app receives real-time predictions of public transport congestion for that day and suggests alternative routes if the usual route is congested. The feedback obtained during this process also contributes to improving accuracy for future events.

[0545] An example of a prompt would be, "Please tell me the best route from the city center to my destination next Friday at 3 PM. Please take into account public transport and congestion forecasts."

[0546] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0547] Step 1:

[0548] The server acquires movement information from location services and traffic data providers. It receives location data and traffic data from APIs as input and cleanses them into a standardized format. The output is the cleansed movement information data. Specifically, it standardizes the data format and handles duplicates and missing values.

[0549] Step 2:

[0550] The server retrieves event information from public institution event schedules and local information websites. It receives event-related data as input and organizes it into a format necessary for congestion prediction. The output is the organized event information data. Specifically, it extracts attributes such as event time, location, and scale, and stores them in a database.

[0551] Step 3:

[0552] The server inputs cleansed movement data and organized event data into an AI model to predict congestion. It accepts both movement and event data as input. The output is a congestion prediction for a specific time and location. Specifically, it runs the model and analyzes the data using a machine learning framework such as TensorFlow.

[0553] Step 4:

[0554] The server generates congestion avoidance information based on congestion prediction results. It takes congestion prediction results as input and calculates available alternative routes and less busy times. The output is congestion avoidance information provided to the user. Specifically, it evaluates multiple route options and selects the most efficient path.

[0555] Step 5:

[0556] The terminal receives congestion avoidance information from the server and displays it on the map through the user interface. It accepts congestion avoidance information as input and converts it into a display format. The output is a visual route guide that the user can review. Specifically, it uses the Google Maps API to overlay the information onto the map.

[0557] Step 6:

[0558] The user travels based on route information provided via their device and provides feedback based on their travel experience. The input is the user's experience, and the output is the feedback sent to the system. Specifically, the user inputs their satisfaction level and areas for improvement through a form.

[0559] Step 7:

[0560] The server collects user feedback and uses it to retrain the AI ​​model. It receives feedback data as input and analyzes it to improve the model. The output is an enhanced predictive model. Specifically, it analyzes the feedback and adds it to the model as new data points.

[0561] 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.

[0562] This invention provides a system that helps users avoid congestion and travel comfortably, and further provides more personalized services by taking user emotions into consideration. The system consists of a server, a terminal, an AI agent, and an emotion engine.

[0563] First, the server acquires pedestrian flow data and event information using standard procedures. This includes traffic sensor data, location services, and information from public service APIs. The acquired data is standardized by the server and sent to the AI ​​agent.

[0564] The AI ​​agent uses the received data to analyze pedestrian flow patterns and predict congestion. These predictions are transmitted to the terminal via a server and visualized on a map.

[0565] One feature of this invention is the introduction of an emotion engine. The terminal is equipped with a device for recognizing the user's emotions, and acquires emotion data from, for example, the user's facial expressions, tone of voice, and touch strength. The terminal sends this emotion data to a server, which uses the emotion engine to analyze the user's emotional state.

[0566] The emotion engine analyzes the user's emotional state. Based on this, the AI ​​agent generates congestion avoidance information tailored to the user's emotions. For example, if the user is feeling stressed, it can suggest a quieter route.

[0567] Ultimately, the device presents the user with personalized, emotion-based suggestions, and the user follows those suggestions. After moving, the user provides feedback on their actual travel experience through the device, which is collected by a server and used to further improve the AI ​​agent and emotion engine.

[0568] This allows users not only to avoid congestion but also to enjoy an optimal travel experience tailored to their mood at the time.

[0569] The following describes the processing flow.

[0570] Step 1:

[0571] The server uses various APIs to collect real-time pedestrian flow and event information. This data includes location services, traffic sensors, and posts from social media.

[0572] Step 2:

[0573] The server cleanses the acquired data, removing missing and outlier values. During this process, it also standardizes the data and converts it into a format suitable for analysis by the AI ​​agent.

[0574] Step 3:

[0575] The cleansed data is sent from the server to the AI ​​agent. The AI ​​agent compares it with past data, analyzes temporal and spatial patterns, and makes congestion predictions.

[0576] Step 4:

[0577] The prediction results are sent back to the server, where visualization data is prepared on the map. The server then sends this information to the terminal.

[0578] Step 5:

[0579] The terminal displays congestion prediction information received from the server on a map. Simultaneously, the emotion engine is activated and collects emotion data based on the user's terminal operations and sensor information.

[0580] Step 6:

[0581] The user's facial expressions and voice are recorded through the camera and microphone. Sensors also detect the strength and speed of the user's device operations as emotional data.

[0582] Step 7:

[0583] The device sends emotional data to the server, and the server analyzes the user's emotional state using an emotion engine.

[0584] Step 8:

[0585] The server generates personalized congestion avoidance information based on the user's emotional state and provides optimized travel routes.

[0586] Step 9:

[0587] The user reviews the submitted information, taking emotions into consideration, selects the optimal route displayed on their device, and begins their journey.

[0588] Step 10:

[0589] After completing their journey, users enter feedback about their journey experience on a device. This feedback is sent to a server and used to further improve the AI ​​agent and emotion engine.

[0590] (Example 2)

[0591] 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."

[0592] In modern urban environments, traffic congestion is a daily problem, and there is a demand for efficient and stress-free travel. Furthermore, mobility support that takes into account the emotional state of users has not been sufficiently achieved, and providing services tailored to the individual circumstances of each user remains a challenge.

[0593] 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.

[0594] In this invention, the server includes means for collecting pedestrian flow information, means for collecting location information, means for analyzing the collected pedestrian flow information and location information to predict congestion, means for using an emotion engine to acquire and analyze the emotional state of users, means for generating congestion avoidance information according to the emotional state of users, and means for displaying the congestion avoidance information on a visual display device. This makes it possible to provide an optimal travel route according to the emotional state of each user and to avoid congestion.

[0595] "Human flow information" refers to information about the movement and distribution of people traveling within a specific region or space.

[0596] "Location information" refers to geographical data used to identify the location of a specific object or person.

[0597] "Analysis" refers to the process of thoroughly examining collected data and information to obtain conclusions and insights that are relevant to a specific purpose.

[0598] "Congestion" refers to a state in which an excessive number of people or objects gather in a particular space, making normal actions and movement difficult.

[0599] An "emotion engine" refers to technologies and systems used to recognize and analyze a user's emotional state.

[0600] A "visual display device" refers to equipment or devices used to visually present digital data to a user.

[0601] "Opinions" refers to feedback information collected from users, including subjective evaluations, satisfaction levels, and suggestions for improvement.

[0602] A "predictive model" refers to a computational model built to estimate future events and trends based on data.

[0603] This invention is a system designed to assist users in traveling comfortably and provides personalized services that take into account the user's emotional state.

[0604] The server first collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. This data is standardized and sent to an artificial intelligence agent. Standardization includes transforming location coordinates and unifying data formats, which allows for consistent processing of information obtained from various data sources.

[0605] The device incorporates user facial recognition and voice analysis capabilities. It acquires emotional data through the user's facial expressions and voice tone, and sends this data to a server. The server uses an emotion engine to analyze this data and identify the user's current emotional state.

[0606] The AI ​​agent uses a model to predict future congestion based on standardized data and sentiment data provided by the server. This model is built using Python machine learning libraries, such as scikit-learn. Based on the congestion prediction results and the user's sentiment state, optimal routes and suggested spots are generated.

[0607] The generated suggestions are provided to the user via a terminal. After the user moves, they enter feedback into the terminal. This feedback is collected by the server and used to further improve the congestion prediction model.

[0608] For example, if a user is walking through a busy area, this system could suggest a quieter route. If the system determines that the user's emotional state is "anxious," it would also suggest relaxing spots such as a calm cafe or a quiet park.

[0609] An example of a prompt for the generating AI model would be, "I'd like to visit popular tourist spots in Paris, but please suggest a route that avoids crowds and allows me to relax. Also, please suggest convenient places to rest when I feel stressed." This would then provide the user with customized travel suggestions. This allows the user to enjoy an optimal travel experience tailored to their emotional state.

[0610] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0611] Step 1:

[0612] The server collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. It requests data from each information source's API as input, processes the received data quickly, corrects duplicates and inconsistencies, and standardizes it. As output, it generates a unified dataset and sends it to the AI ​​agent.

[0613] Step 2:

[0614] The device acquires emotional data from the user. It takes raw data from the camera and microphone as input and analyzes the user's emotional state using facial recognition and voice analysis. Specifically, it extracts facial expression features and inputs voice tone into an emotion classification model. The acquired emotional data is then sent to a server as output.

[0615] Step 3:

[0616] The server receives emotion data and analyzes it using an emotion engine. It uses user emotion data received from the terminal as input and processes it to quantify the emotional state. As output, it generates the quantified user emotional state and provides it to the AI ​​agent.

[0617] Step 4:

[0618] The AI ​​agent predicts congestion based on pedestrian flow information, location information, and sentiment data received from the server. Using these datasets as input, it analyzes them with a machine learning model while comparing them with historical data. Specifically, it performs pattern recognition and regression analysis to predict future congestion levels. The predicted congestion information is then sent to the terminal as output.

[0619] Step 5:

[0620] The terminal receives congestion avoidance information generated by the AI ​​agent and presents it to the user as a visual display on the map application. It receives information from the AI ​​agent as input and reflects it on the map in a way that considers usability on the user interface. As output, it provides route suggestions in a visually easy-to-understand format for the user.

[0621] Step 6:

[0622] Users navigate based on information obtained through their devices and input feedback into the devices after their journey. The input consists of filling out a feedback form with their impressions of their travel experience and suggestions for improvement, which the device then sends to the server. The output is the feedback data stored on the server, which is used for subsequent model improvements.

[0623] (Application Example 2)

[0624] 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."

[0625] In today's society, where users are expected to avoid congestion and travel comfortably, it is crucial not only to provide congestion information but also to offer a personalized travel experience that responds to the user's emotional state. However, current systems are unable to suggest routes that are individually adapted to the user's emotions, and therefore fail to provide the optimal travel experience for users.

[0626] 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.

[0627] In this invention, the server includes means for acquiring pedestrian flow information, means for acquiring activity information, means for analyzing the acquired pedestrian flow information and activity information to predict congestion, means for analyzing the user's emotional state, and means for generating personalized route suggestions based on the emotional state. This makes it possible to provide optimal congestion avoidance guidelines and a travel experience that takes the user's emotions into consideration.

[0628] "Population flow information" refers to data that shows the patterns and density of people's movement in a specific area.

[0629] "Activity information" refers to data that indicates events or activities taking place at specific locations and times.

[0630] A "means for predicting congestion" refers to a device or program that predicts crowds based on acquired pedestrian flow and activity information.

[0631] "Guidelines for avoiding congestion" refer to information about alternative routes and times suggested to avoid congestion.

[0632] "Means of visualizing on a display" refers to devices or software that visually represent and present the generated congestion avoidance guidelines to the user.

[0633] "Means for analyzing emotional states" refers to technologies or devices for recognizing and evaluating a user's emotions.

[0634] "Personalized suggestions" refer to travel routes and plans that are specially tailored based on the individual user's needs and feelings.

[0635] "Current location" refers to information that indicates the geographical location where the user is at a specific time.

[0636] A "destination" is information that indicates the geographical location that a user wants to reach at a specific time.

[0637] "Means of collecting opinions" refer to devices and methods for aggregating user experiences and feedback.

[0638] "Means for retraining predictive models" refers to a mechanism or program that improves existing predictive algorithms based on collected data.

[0639] A system for implementing this invention consists of a server, a terminal, an AI agent, and an emotion engine.

[0640] The server acquires pedestrian flow and activity information from traffic sensor data, location services, and public service APIs. This information is standardized and sent to an AI agent. The AI ​​agent analyzes the received information, predicts congestion, and generates congestion avoidance guidelines. These guidelines are sent to the user's device and visualized on a map.

[0641] The device is equipped with a mechanism to understand the user's emotional state. It acquires emotional data from the user's facial expressions, tone of voice, or touch intensity and sends it to a server. On the server, an emotion engine analyzes this data and evaluates the emotional state. Based on this information, the AI ​​agent generates emotion-based, personalized route suggestions.

[0642] This allows users to not only avoid congestion but also have a better travel experience by being presented with routes that are optimal for their emotional state. For example, if a user is feeling stressed during their morning commute, the server can suggest a quieter route that avoids congestion.

[0643] An example of a prompt message is: "Based on the user's emotional data, consider how to suggest the optimal route. If the user is feeling stressed, explain how to choose a quieter route."

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

[0645] Step 1:

[0646] The server acquires pedestrian flow and activity information through traffic sensor data, location services, and public institution APIs. This information is standardized and converted into a format that is easy to analyze. The input is raw data from various data sources, and the output is standardized pedestrian flow and activity information.

[0647] Step 2:

[0648] The server sends standardized pedestrian flow and activity information to the AI ​​agent. The input is the information output by the server, and the output is ready for the AI ​​agent to receive. At this point, data format conversion and error handling take place.

[0649] Step 3:

[0650] The AI ​​agent analyzes pedestrian flow and predicts congestion based on the information it receives. The input consists of standardized pedestrian flow and activity data, while the output is a predicted congestion guideline. The AI ​​agent uses machine learning algorithms to analyze and predict this data.

[0651] Step 4:

[0652] The generated congestion guidelines are sent to the terminal via the server. The input is the prediction result of the AI ​​agent, and the output is data for visualization. The server uses a communication protocol to ensure reliable data transmission.

[0653] Step 5:

[0654] The terminal visualizes the received congestion guidelines on a map. The input is data sent from the server, and the output is map information that the user can visually confirm. In this process, the terminal generates visual elements using map software.

[0655] Step 6:

[0656] The device uses devices that sense facial expressions, voice tone, or touch intensity to understand the user's emotional state and collect emotional data. The input is user behavior data, and the output is emotional state data. The device analyzes the data using emotion recognition technology.

[0657] Step 7:

[0658] The device sends collected emotional state data to the server. The input is the user's emotional state, and the output is the data format the server can receive. The system also checks for any abnormal data.

[0659] Step 8:

[0660] The server uses an emotion engine to evaluate the user's emotional state. The input is the user's emotional state data, and the output is a quantified emotional evaluation. The emotion engine uses artificial intelligence to analyze the emotional state.

[0661] Step 9:

[0662] The AI ​​agent generates personalized route suggestions that are optimal for the user based on the evaluated emotional state. The input is the evaluation result from the emotion engine, and the output is the proposed route guidance. In this process, an optimization is performed according to the emotion using a generative AI model.

[0663] Step 10:

[0664] The device presents the user with optimal route guidance. Input is output from an AI agent, and the output is guidance via a visual display or voice assistant. This allows the user to have an emotionally-based, optimal travel experience.

[0665] 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.

[0666] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0667] 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.

[0668] [Fourth Embodiment]

[0669] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0670] 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.

[0671] 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).

[0672] 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.

[0673] 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.

[0674] 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).

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] 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.

[0681] 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".

[0682] This invention is a congestion prediction system that enables users to travel efficiently and comfortably. The system consists of a server, terminals, and an AI agent.

[0683] First, the server acquires pedestrian flow data and event information from multiple data sources. This information is collected from sources such as traffic sensors, social media posts, location services, and public event schedules. Next, the server cleans this data, converts it into a standardized format, and sends it to an AI agent. The AI ​​agent performs congestion predictions by comparing it with historical data and detecting anomalies in real time. This makes it possible to predict congestion in specific areas and time periods in the future.

[0684] Predicted congestion information is retrieved by a server and visualized on a map. This visualization data is then sent to the terminal. Based on the user's current location and destination, the terminal suggests the optimal route that reflects the predicted information. For example, if a user searches for a route from home to the office during the morning commute, the system can indicate that the usual route is congested and suggest an alternative route.

[0685] After moving, users provide feedback via their devices regarding the effectiveness of congestion avoidance and their satisfaction level. This feedback is collected on a server and used by an AI agent to retrain the predictive model. Through this process, the system continuously improves its predictive accuracy over time.

[0686] By implementing this invention, users can enjoy mobility services based on real-time and sophisticated congestion information, enabling a stress-free travel experience.

[0687] The following describes the processing flow.

[0688] Step 1:

[0689] The server accesses APIs from social media posts, location services, and traffic sensors to collect pedestrian flow data in real time. Furthermore, it obtains event information using APIs provided by public institutions and event organizers.

[0690] Step 2:

[0691] The server cleanses the collected data, which includes removing duplicates, handling missing values, and detecting outliers. Next, it standardizes the data and converts it into a format that the AI ​​agent can process.

[0692] Step 3:

[0693] The server sends the cleansed data to the AI ​​agent. The AI ​​agent combines this data with historical datasets to perform analysis for congestion prediction. This includes temporal and spatial data analysis.

[0694] Step 4:

[0695] The AI ​​agent applies real-time anomaly detection algorithms to identify congestion patterns that deviate from normal patterns. It then returns the identified congestion information to the server.

[0696] Step 5:

[0697] The server prepares the congestion prediction data received from the AI ​​agent to be visualized on a map, and then sends this information to the terminal.

[0698] Step 6:

[0699] The terminal displays map information received from the server, informs the user of congestion status, and calculates and suggests the optimal route from the user's current location to their destination.

[0700] Step 7:

[0701] The user selects the optimal travel route based on the information displayed on the device and moves according to the instructed path.

[0702] Step 8:

[0703] Users who have completed their journey provide feedback via their device regarding the effectiveness of congestion avoidance and their overall satisfaction. This feedback is collected by the server.

[0704] Step 9:

[0705] The server records user feedback in a database and sends it to the AI ​​agent for retraining the predictive model. This improves the system's predictive accuracy.

[0706] (Example 1)

[0707] 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".

[0708] In modern society, congestion is a source of wasted time and stress, significantly reducing the efficiency of travel. In particular, congestion during commutes and events causes unexpected travel delays, negatively impacting economic activity and personal lives. To address these challenges, there is a growing need for systems that provide real-time travel avoidance information.

[0709] 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.

[0710] In this invention, the server includes means for acquiring movement data, means for acquiring event information, means for processing the acquired movement data and event information to detect anomalies, means for predicting congestion by comparing it with past data, means for generating movement avoidance information based on the prediction, and means for visually displaying the movement avoidance information. This makes it possible to provide users with real-time information to support efficient and stress-free movement.

[0711] "Mobility data" refers to information about the movement of people and goods, such as location information and traffic volume.

[0712] "Event information" refers to information related to events that occur on a specific day or in a specific area, such as public events or accidents.

[0713] "Detecting anomalies" refers to the process of recognizing and identifying behavior that deviates from normal data patterns.

[0714] "Predicting congestion" refers to using past and present data to estimate future pedestrian and traffic congestion.

[0715] "Travel avoidance information" refers to information that includes routes and instructions to avoid congestion in specific locations and times.

[0716] "Visually displaying information" refers to providing information to users using visual means such as maps and graphs.

[0717] An "efficient route" refers to the optimal travel route that minimizes travel time and distance to the destination and meets the user's requirements.

[0718] "Gathering opinions" refers to the process of obtaining feedback and evaluations from users.

[0719] "Improving a predictive model" refers to the process of improving the accuracy and effectiveness of predictions based on collected data.

[0720] This invention relates to a congestion prediction system for improving travel efficiency. The system consists of a server, terminals, and an AI agent.

[0721] The server collects movement and event information from various data sources. This information is gathered from sources such as traffic sensors, social media posts, location services, and public event schedules. For example, it includes road traffic volume data obtained using traffic sensors and posts containing keywords such as "congestion" and "traffic jam" extracted from social media. The server cleanses this data and converts it into a consistent format.

[0722] The AI ​​agent uses standardized data to detect anomalies by comparing them with historical data, and uses a generative AI model to predict future congestion. This prediction allows for the generation of congestion avoidance information for specific locations and time periods.

[0723] The server generates a map visually representing the predicted congestion information and sends it to the terminal. The terminal considers the user's current location and destination and suggests the optimal route. For example, if the route the user normally uses is predicted to be congested, an alternative route can be suggested.

[0724] After the journey is complete, the user provides feedback through their device. This feedback is collected by the server and used by an AI agent to improve the predictive model. This allows the system to continuously improve its prediction accuracy, enabling users to have a faster and less stressful travel experience.

[0725] An example of a prompt message is, "Based on data obtained from social media and traffic sensors, please provide a congestion forecast for the area around major train stations next week."

[0726] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0727] Step 1:

[0728] The server collects movement and event information from multiple data sources, including traffic sensors, social media posts, location services, and public event schedules. In this step, information is retrieved from each data source via APIs. The input is raw data in various formats, and the output is an integrated raw data stream. Specifically, traffic volume data from traffic sensors, keyword posts from social media, and location data are retrieved.

[0729] Step 2:

[0730] The server cleanses the collected raw data and converts it into a standardized format. This step involves removing missing data, eliminating duplicates, and unifying the data format. The input is an integrated raw data stream, and the output is standardized data that can be processed by the AI ​​agent. Specific operations include normalization using a database.

[0731] Step 3:

[0732] The server sends standardized data to the AI ​​agent, which uses a generative AI model to compare it with historical data and detect anomalies. Standardized data is given as input, and the output is a report of the detected anomalies. Specifically, it uses a machine learning algorithm to classify anomaly patterns.

[0733] Step 4:

[0734] The AI ​​agent predicts congestion using a generative AI model based on the results of anomaly detection. In this step, anomaly reports are used as input, and the output is congestion prediction data for a specific area or time period. The specific operation involves running a time-series prediction model.

[0735] Step 5:

[0736] The server retrieves predicted congestion data and displays it on a map in a visually effective format. In this step, the input is congestion prediction data, and the output is visualization data that can be provided to the user. Specific operations include map generation using mapping software.

[0737] Step 6:

[0738] The terminal suggests the optimal route for the user based on the displayed visual data. In this step, the input consists of the visualized data and the user's current location and destination information. The output is the optimal route presented to the user. Specifically, route calculation is performed using a navigation algorithm.

[0739] Step 7:

[0740] Users provide feedback after their movement via their device. This feedback is collected on a server. The input is user feedback, and the output is training data used by the AI ​​agent. Specific actions include information collection using a feedback form.

[0741] Step 8:

[0742] The server sends the collected feedback to the AI ​​agent, which then retrains the predictive model based on that feedback. The input is user feedback data, and the output is the improved predictive model. As a concrete example, model updates are performed using batch learning.

[0743] (Application Example 1)

[0744] 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".

[0745] In modern cities, the complex flow of people and the impact of events make it difficult to predict congestion and provide users with the optimal travel routes. This challenge reduces the efficiency of travel and contributes to stress and wasted time. Furthermore, there is a lack of mechanisms to improve prediction accuracy by utilizing real-time feedback, highlighting the need to support more efficient and comfortable travel.

[0746] 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.

[0747] In this invention, the server includes means for acquiring movement information, means for acquiring event information, and means for analyzing the acquired movement information and event information to predict congestion. This enables the system to propose the optimal travel route to the user in real time, allowing for efficient and comfortable travel. Furthermore, by collecting user feedback and optimizing the prediction model, the prediction accuracy can be improved over time.

[0748] "Means for acquiring movement information" refers to methods for collecting data related to a user's location and travel route.

[0749] "Means of obtaining event information" refers to methods for gathering information related to events and activities taking place within a local area.

[0750] "Methods for predicting congestion" refer to methods for analyzing collected data to predict the degree of human concentration at different times and locations.

[0751] "Means for generating congestion avoidance information" refers to methods for formulating the optimal routes and means available to users based on predicted congestion information.

[0752] "Means for displaying congestion avoidance information" refers to methods for visualizing the generated congestion avoidance information in a way that is easy for users to understand.

[0753] "Means for presenting the optimal route to a user's electronic device" refers to a method of providing optimal route information to a user's mobile device in order to support their travel.

[0754] "Methods for receiving feedback and optimizing predictive models" refer to methods for collecting evaluations obtained from users' usage experiences and using that information to improve prediction accuracy.

[0755] "Means of utilizing diverse information sources" refers to methods for obtaining abundant information from various data sources within a region and using it within a system.

[0756] The system that realizes this invention consists of a server, a terminal, and a user. The server is connected to various data sources necessary for acquiring movement information and event information. Movement information is collected through general location information services and traffic data provision services, and event information is collected from public institution event schedules and local information provision sites, etc.

[0757] The server cleanses this data into a unified format and inputs it into an AI model for predictive analytics. This AI model performs pattern recognition based on historical data and real-time anomaly detection to predict future congestion levels. Machine learning frameworks such as TensorFlow are used as examples of AI models.

[0758] The terminal receives congestion avoidance information transmitted from the server and provides an interface to assist the user's movement. For example, by using a map application on a smartphone or tablet, the system can present the user with the optimal route based on the latest congestion status. Google Maps API and similar services are often used for map display.

[0759] Users can provide feedback on the routes provided by the system while moving through their devices. This feedback is sent to a server and added to the AI ​​model's training data, contributing to improved prediction accuracy.

[0760] As a concrete example, let's assume a user participates in a marathon event held in a city on the weekend. The app receives real-time predictions of public transport congestion for that day and suggests alternative routes if the usual route is congested. The feedback obtained during this process also contributes to improving accuracy for future events.

[0761] An example of a prompt would be, "Please tell me the best route from the city center to my destination next Friday at 3 PM. Please take into account public transport and congestion forecasts."

[0762] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0763] Step 1:

[0764] The server acquires movement information from location services and traffic data providers. It receives location data and traffic data from APIs as input and cleanses them into a standardized format. The output is the cleansed movement information data. Specifically, it standardizes the data format and handles duplicates and missing values.

[0765] Step 2:

[0766] The server retrieves event information from public institution event schedules and local information websites. It receives event-related data as input and organizes it into a format necessary for congestion prediction. The output is the organized event information data. Specifically, it extracts attributes such as event time, location, and scale, and stores them in a database.

[0767] Step 3:

[0768] The server inputs cleansed movement data and organized event data into an AI model to predict congestion. It accepts both movement and event data as input. The output is a congestion prediction for a specific time and location. Specifically, it runs the model and analyzes the data using a machine learning framework such as TensorFlow.

[0769] Step 4:

[0770] The server generates congestion avoidance information based on congestion prediction results. It takes congestion prediction results as input and calculates available alternative routes and less busy times. The output is congestion avoidance information provided to the user. Specifically, it evaluates multiple route options and selects the most efficient path.

[0771] Step 5:

[0772] The terminal receives congestion avoidance information from the server and displays it on the map through the user interface. It accepts congestion avoidance information as input and converts it into a display format. The output is a visual route guide that the user can review. Specifically, it uses the Google Maps API to overlay the information onto the map.

[0773] Step 6:

[0774] The user travels based on route information provided via their device and provides feedback based on their travel experience. The input is the user's experience, and the output is the feedback sent to the system. Specifically, the user inputs their satisfaction level and areas for improvement through a form.

[0775] Step 7:

[0776] The server collects user feedback and uses it to retrain the AI ​​model. It receives feedback data as input and analyzes it to improve the model. The output is an enhanced predictive model. Specifically, it analyzes the feedback and adds it to the model as new data points.

[0777] 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.

[0778] This invention provides a system that helps users avoid congestion and travel comfortably, and further provides more personalized services by taking user emotions into consideration. The system consists of a server, a terminal, an AI agent, and an emotion engine.

[0779] First, the server acquires pedestrian flow data and event information using standard procedures. This includes traffic sensor data, location services, and information from public service APIs. The acquired data is standardized by the server and sent to the AI ​​agent.

[0780] The AI ​​agent uses the received data to analyze pedestrian flow patterns and predict congestion. These predictions are transmitted to the terminal via a server and visualized on a map.

[0781] One feature of this invention is the introduction of an emotion engine. The terminal is equipped with a device for recognizing the user's emotions, and acquires emotion data from, for example, the user's facial expressions, tone of voice, and touch strength. The terminal sends this emotion data to a server, which uses the emotion engine to analyze the user's emotional state.

[0782] The emotion engine analyzes the user's emotional state. Based on this, the AI ​​agent generates congestion avoidance information tailored to the user's emotions. For example, if the user is feeling stressed, it can suggest a quieter route.

[0783] Ultimately, the device presents the user with personalized, emotion-based suggestions, and the user follows those suggestions. After moving, the user provides feedback on their actual travel experience through the device, which is collected by a server and used to further improve the AI ​​agent and emotion engine.

[0784] This allows users not only to avoid congestion but also to enjoy an optimal travel experience tailored to their mood at the time.

[0785] The following describes the processing flow.

[0786] Step 1:

[0787] The server uses various APIs to collect real-time pedestrian flow and event information. This data includes location services, traffic sensors, and posts from social media.

[0788] Step 2:

[0789] The server cleanses the acquired data, removing missing and outlier values. During this process, it also standardizes the data and converts it into a format suitable for analysis by the AI ​​agent.

[0790] Step 3:

[0791] The cleansed data is sent from the server to the AI ​​agent. The AI ​​agent compares it with past data, analyzes temporal and spatial patterns, and makes congestion predictions.

[0792] Step 4:

[0793] The prediction results are sent back to the server, where visualization data is prepared on the map. The server then sends this information to the terminal.

[0794] Step 5:

[0795] The terminal displays congestion prediction information received from the server on a map. Simultaneously, the emotion engine is activated and collects emotion data based on the user's terminal operations and sensor information.

[0796] Step 6:

[0797] The user's facial expressions and voice are recorded through the camera and microphone. Sensors also detect the strength and speed of the user's device operations as emotional data.

[0798] Step 7:

[0799] The device sends emotional data to the server, and the server analyzes the user's emotional state using an emotion engine.

[0800] Step 8:

[0801] The server generates personalized congestion avoidance information based on the user's emotional state and provides optimized travel routes.

[0802] Step 9:

[0803] The user reviews the submitted information, taking emotions into consideration, selects the optimal route displayed on their device, and begins their journey.

[0804] Step 10:

[0805] After completing their journey, users enter feedback about their journey experience on a device. This feedback is sent to a server and used to further improve the AI ​​agent and emotion engine.

[0806] (Example 2)

[0807] 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".

[0808] In modern urban environments, traffic congestion is a daily problem, and there is a demand for efficient and stress-free travel. Furthermore, mobility support that takes into account the emotional state of users has not been sufficiently achieved, and providing services tailored to the individual circumstances of each user remains a challenge.

[0809] 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.

[0810] In this invention, the server includes means for collecting pedestrian flow information, means for collecting location information, means for analyzing the collected pedestrian flow information and location information to predict congestion, means for using an emotion engine to acquire and analyze the emotional state of users, means for generating congestion avoidance information according to the emotional state of users, and means for displaying the congestion avoidance information on a visual display device. This makes it possible to provide an optimal travel route according to the emotional state of each user and to avoid congestion.

[0811] "Human flow information" refers to information about the movement and distribution of people traveling within a specific region or space.

[0812] "Location information" refers to geographical data used to identify the location of a specific object or person.

[0813] "Analysis" refers to the process of thoroughly examining collected data and information to obtain conclusions and insights that are relevant to a specific purpose.

[0814] "Congestion" refers to a state in which an excessive number of people or objects gather in a particular space, making normal actions and movement difficult.

[0815] An "emotion engine" refers to technologies and systems used to recognize and analyze a user's emotional state.

[0816] A "visual display device" refers to equipment or devices used to visually present digital data to a user.

[0817] "Opinions" refers to feedback information collected from users, including subjective evaluations, satisfaction levels, and suggestions for improvement.

[0818] A "predictive model" refers to a computational model built to estimate future events and trends based on data.

[0819] This invention is a system designed to assist users in traveling comfortably and provides personalized services that take into account the user's emotional state.

[0820] The server first collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. This data is standardized and sent to an artificial intelligence agent. Standardization includes transforming location coordinates and unifying data formats, which allows for consistent processing of information obtained from various data sources.

[0821] The device incorporates user facial recognition and voice analysis capabilities. It acquires emotional data through the user's facial expressions and voice tone, and sends this data to a server. The server uses an emotion engine to analyze this data and identify the user's current emotional state.

[0822] The AI ​​agent uses a model to predict future congestion based on standardized data and sentiment data provided by the server. This model is built using Python machine learning libraries, such as scikit-learn. Based on the congestion prediction results and the user's sentiment state, optimal routes and suggested spots are generated.

[0823] The generated suggestions are provided to the user via a terminal. After the user moves, they enter feedback into the terminal. This feedback is collected by the server and used to further improve the congestion prediction model.

[0824] For example, if a user is walking through a busy area, this system could suggest a quieter route. If the system determines that the user's emotional state is "anxious," it would also suggest relaxing spots such as a calm cafe or a quiet park.

[0825] An example of a prompt for the generating AI model would be, "I'd like to visit popular tourist spots in Paris, but please suggest a route that avoids crowds and allows me to relax. Also, please suggest convenient places to rest when I feel stressed." This would then provide the user with customized travel suggestions. This allows the user to enjoy an optimal travel experience tailored to their emotional state.

[0826] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0827] Step 1:

[0828] The server collects pedestrian flow and location information from traffic sensor data, location services, and public institution APIs. It requests data from each information source's API as input, processes the received data quickly, corrects duplicates and inconsistencies, and standardizes it. As output, it generates a unified dataset and sends it to the AI ​​agent.

[0829] Step 2:

[0830] The device acquires emotional data from the user. It takes raw data from the camera and microphone as input and analyzes the user's emotional state using facial recognition and voice analysis. Specifically, it extracts facial expression features and inputs voice tone into an emotion classification model. The acquired emotional data is then sent to a server as output.

[0831] Step 3:

[0832] The server receives emotion data and analyzes it using an emotion engine. It uses user emotion data received from the terminal as input and processes it to quantify the emotional state. As output, it generates the quantified user emotional state and provides it to the AI ​​agent.

[0833] Step 4:

[0834] The AI ​​agent predicts congestion based on pedestrian flow information, location information, and sentiment data received from the server. Using these datasets as input, it analyzes them with a machine learning model while comparing them with historical data. Specifically, it performs pattern recognition and regression analysis to predict future congestion levels. The predicted congestion information is then sent to the terminal as output.

[0835] Step 5:

[0836] The terminal receives congestion avoidance information generated by the AI ​​agent and presents it to the user as a visual display on the map application. It receives information from the AI ​​agent as input and reflects it on the map in a way that considers usability on the user interface. As output, it provides route suggestions in a visually easy-to-understand format for the user.

[0837] Step 6:

[0838] Users navigate based on information obtained through their devices and input feedback into the devices after their journey. The input consists of filling out a feedback form with their impressions of their travel experience and suggestions for improvement, which the device then sends to the server. The output is the feedback data stored on the server, which is used for subsequent model improvements.

[0839] (Application Example 2)

[0840] 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".

[0841] In today's society, where users are expected to avoid congestion and travel comfortably, it is crucial not only to provide congestion information but also to offer a personalized travel experience that responds to the user's emotional state. However, current systems are unable to suggest routes that are individually adapted to the user's emotions, and therefore fail to provide the optimal travel experience for users.

[0842] 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.

[0843] In this invention, the server includes means for acquiring pedestrian flow information, means for acquiring activity information, means for analyzing the acquired pedestrian flow information and activity information to predict congestion, means for analyzing the user's emotional state, and means for generating personalized route suggestions based on the emotional state. This makes it possible to provide optimal congestion avoidance guidelines and a travel experience that takes the user's emotions into consideration.

[0844] "Population flow information" refers to data that shows the patterns and density of people's movement in a specific area.

[0845] "Activity information" refers to data that indicates events or activities taking place at specific locations and times.

[0846] A "means for predicting congestion" refers to a device or program that predicts crowds based on acquired pedestrian flow and activity information.

[0847] "Guidelines for avoiding congestion" refer to information about alternative routes and times suggested to avoid congestion.

[0848] "Means of visualizing on a display" refers to devices or software that visually represent and present the generated congestion avoidance guidelines to the user.

[0849] "Means for analyzing emotional states" refers to technologies or devices for recognizing and evaluating a user's emotions.

[0850] "Personalized suggestions" refer to travel routes and plans that are specially tailored based on the individual user's needs and feelings.

[0851] "Current location" refers to information that indicates the geographical location where the user is at a specific time.

[0852] A "destination" is information that indicates the geographical location that a user wants to reach at a specific time.

[0853] "Means of collecting opinions" refer to devices and methods for aggregating user experiences and feedback.

[0854] "Means for retraining predictive models" refers to a mechanism or program that improves existing predictive algorithms based on collected data.

[0855] A system for implementing this invention consists of a server, a terminal, an AI agent, and an emotion engine.

[0856] The server acquires pedestrian flow and activity information from traffic sensor data, location services, and public service APIs. This information is standardized and sent to an AI agent. The AI ​​agent analyzes the received information, predicts congestion, and generates congestion avoidance guidelines. These guidelines are sent to the user's device and visualized on a map.

[0857] The device is equipped with a mechanism to understand the user's emotional state. It acquires emotional data from the user's facial expressions, tone of voice, or touch intensity and sends it to a server. On the server, an emotion engine analyzes this data and evaluates the emotional state. Based on this information, the AI ​​agent generates emotion-based, personalized route suggestions.

[0858] This allows users to not only avoid congestion but also have a better travel experience by being presented with routes that are optimal for their emotional state. For example, if a user is feeling stressed during their morning commute, the server can suggest a quieter route that avoids congestion.

[0859] An example of a prompt message is: "Based on the user's emotional data, consider how to suggest the optimal route. If the user is feeling stressed, explain how to choose a quieter route."

[0860] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0861] Step 1:

[0862] The server acquires pedestrian flow and activity information through traffic sensor data, location services, and public institution APIs. This information is standardized and converted into a format that is easy to analyze. The input is raw data from various data sources, and the output is standardized pedestrian flow and activity information.

[0863] Step 2:

[0864] The server sends standardized pedestrian flow and activity information to the AI ​​agent. The input is the information output by the server, and the output is ready for the AI ​​agent to receive. At this point, data format conversion and error handling take place.

[0865] Step 3:

[0866] The AI ​​agent analyzes pedestrian flow and predicts congestion based on the information it receives. The input consists of standardized pedestrian flow and activity data, while the output is a predicted congestion guideline. The AI ​​agent uses machine learning algorithms to analyze and predict this data.

[0867] Step 4:

[0868] The generated congestion guidelines are sent to the terminal via the server. The input is the prediction result of the AI ​​agent, and the output is data for visualization. The server uses a communication protocol to ensure reliable data transmission.

[0869] Step 5:

[0870] The terminal visualizes the received congestion guidelines on a map. The input is data sent from the server, and the output is map information that the user can visually confirm. In this process, the terminal generates visual elements using map software.

[0871] Step 6:

[0872] The device uses devices that sense facial expressions, voice tone, or touch intensity to understand the user's emotional state and collect emotional data. The input is user behavior data, and the output is emotional state data. The device analyzes the data using emotion recognition technology.

[0873] Step 7:

[0874] The device sends collected emotional state data to the server. The input is the user's emotional state, and the output is the data format the server can receive. The system also checks for any abnormal data.

[0875] Step 8:

[0876] The server uses an emotion engine to evaluate the user's emotional state. The input is the user's emotional state data, and the output is a quantified emotional evaluation. The emotion engine uses artificial intelligence to analyze the emotional state.

[0877] Step 9:

[0878] The AI ​​agent generates personalized route suggestions that are optimal for the user based on the evaluated emotional state. The input is the evaluation result from the emotion engine, and the output is the proposed route guidance. In this process, an optimization is performed according to the emotion using a generative AI model.

[0879] Step 10:

[0880] The device presents the user with optimal route guidance. Input is output from an AI agent, and the output is guidance via a visual display or voice assistant. This allows the user to have an emotionally-based, optimal travel experience.

[0881] 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.

[0882] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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."

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] The following is further disclosed regarding the embodiments described above.

[0903] (Claim 1)

[0904] Means for acquiring pedestrian flow data,

[0905] Means of obtaining event information,

[0906] A method for predicting congestion by analyzing acquired pedestrian flow data and event information,

[0907] A means for generating congestion avoidance information based on the aforementioned prediction,

[0908] A means of visualizing congestion avoidance information on a map,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, further comprising means for suggesting an optimal route based on the user's current location and destination.

[0912] (Claim 3)

[0913] The system according to claim 1, further comprising means for collecting user feedback and retraining a predictive model based on that feedback.

[0914] "Example 1"

[0915] (Claim 1)

[0916] Means for acquiring movement data,

[0917] Means for acquiring event information,

[0918] A means for processing acquired movement data and event information to detect anomalies,

[0919] A method for predicting congestion by comparing it with past data,

[0920] Means for generating movement avoidance information based on the aforementioned prediction,

[0921] A means of visually displaying movement avoidance information,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, further comprising means for indicating an efficient route based on the user's location information and destination.

[0925] (Claim 3)

[0926] The system according to claim 1, further comprising means for collecting user feedback and thereby improving the predictive model.

[0927] "Application Example 1"

[0928] (Claim 1)

[0929] Means for obtaining movement information,

[0930] Means of obtaining event information,

[0931] A method for predicting congestion by analyzing acquired travel information and event information,

[0932] A means for generating congestion avoidance information based on the aforementioned prediction,

[0933] A means of displaying information to avoid congestion,

[0934] A means of presenting the optimal route for the user's electronic device,

[0935] A means of receiving feedback and optimizing the predictive model,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, further comprising means for suggesting the optimal mode of transportation based on the user's travel purpose and predictive information.

[0939] (Claim 3)

[0940] The system according to claim 1, further comprising means of utilizing diverse local information sources to provide support for more effective travel.

[0941] "Example 2 of combining an emotion engine"

[0942] (Claim 1)

[0943] Means for collecting information on human movement,

[0944] Means for collecting location information,

[0945] A method for predicting congestion by analyzing collected pedestrian flow and location information,

[0946] A method using an emotion engine to acquire and analyze the user's emotional state,

[0947] A means for generating congestion avoidance information according to the user's emotional state,

[0948] A means for displaying congestion avoidance information on a visual display device,

[0949] A system that includes this.

[0950] (Claim 2)

[0951] The system according to claim 1, further comprising means for proposing an optimal route based on destination information and current location information.

[0952] (Claim 3)

[0953] The system according to claim 1, further comprising means for collecting user feedback and reconstructing a predictive model based on that feedback.

[0954] "Application example 2 when combining with an emotional engine"

[0955] (Claim 1)

[0956] Means of acquiring information on human movement,

[0957] Means of obtaining activity information,

[0958] A method for predicting congestion by analyzing acquired pedestrian flow and activity information,

[0959] Means for generating congestion avoidance guidelines based on the aforementioned prediction,

[0960] A means of visualizing congestion avoidance guidelines on a display,

[0961] A means of analyzing the emotional state of users,

[0962] A means for generating personalized suggestions regarding routes based on emotional state,

[0963] A system that includes this.

[0964] (Claim 2)

[0965] The system according to claim 1, further comprising means for suggesting an optimal route based on the user's current location and destination.

[0966] (Claim 3)

[0967] The system according to claim 1, further comprising means for collecting user feedback and retraining a predictive model based on that feedback. [Explanation of Symbols]

[0968] 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 pedestrian flow data, Means of obtaining event information, A method for predicting congestion by analyzing acquired pedestrian flow data and event information, A means for generating congestion avoidance information based on the aforementioned prediction, A means of visualizing congestion avoidance information on a map, A system that includes this.

2. The system according to claim 1, further comprising means for suggesting an optimal route based on the user's current location and destination.

3. The system according to claim 1, further comprising means for collecting user feedback and retraining a predictive model based on that feedback.

Images