System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing traffic information in real time using generated AI and providing optimal departure time and routes to drivers; means for collecting traffic information; means for pre-processing the collected information; means for notifying drivers based on the pre-processed information; means for accumulating long-term traffic information and generating improvement suggestions for chronic traffic jams; and means for transmitting the generated improvement suggestions to a traffic management organization.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Traffic congestion is a common problem in many cities and causes significant stress for drivers. Conventional traffic information systems simply provide information, making it difficult to respond to individual driver needs in real time. Furthermore, they do not provide enough information to take effective measures to improve chronic congestion areas. This invention solves these problems by providing drivers with optimized traffic information in real time, and by providing traffic management organizations with improvement proposals for chronic congestion areas, aiming for comprehensive traffic improvement that even takes legal reform into consideration. [Means for solving the problem]

[0005] This invention is a system that uses generative AI to analyze traffic data in real time and provide drivers with optimal departure times and routes. Specifically, the above-mentioned problems are solved by providing a system that includes the following means: First, a means for collecting traffic information is provided, collecting the latest traffic information from various sources, such as road traffic cameras, GPS data, traffic sensors, and user reports. Second, a means for preprocessing the collected data is provided, removing noise and errors. Third, a means for analyzing the data using generative AI is provided, predicting traffic flow and congestion based on the preprocessed data. Furthermore, a means for notifying drivers of optimal departure times and routes based on the preprocessed data and analysis results is provided. Furthermore, a means for accumulating long-term traffic data, identifying chronic congestion areas, and generating improvement proposals, as well as a means for transmitting the generated improvement proposals to a traffic management organization, is provided. This allows the system to resolve chronic congestion areas and even propose legal reforms, thereby comprehensively improving traffic conditions.

[0006] "Generative AI" is artificial intelligence that uses machine learning techniques to analyze large amounts of data and make predictions and optimizations.

[0007] "Real-time" means processing, analyzing, and providing current events and data in the moment they occur.

[0008] "Traffic data" refers to various information related to road traffic, such as the flow of vehicles on roads, speeds, congestion conditions, traffic accidents, and road construction.

[0009] A "driver" is a person who operates a vehicle and drives it to a destination.

[0010] "Departure time" is the time when the driver starts the vehicle towards the destination.

[0011] A "route" is a travel path from a starting point to a destination.

[0012] A "means" is a method, technique, or device for achieving a specific purpose or function.

[0013] "Traffic information" refers to information related to current traffic conditions, congestion, and road conditions.

[0014] "Preprocessing" is the process of filtering and cleansing data to remove noise and errors before analyzing it.

[0015] A "notification" is a method or action of informing a user of important information.

[0016] "Storage" means collecting and storing data or information over a long period of time.

[0017] "Improvement proposal" means proposing an effective solution to a specific problem.

[0018] "traffic management organization" means a public or private organization responsible for the management and operation of road traffic;

[0019] "Legal reform" means reviewing, changing, or enacting new laws and regulations. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[0042] A natural language description of the program's processing

[0043] 1. Collecting traffic data

[0044] The server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, to provide up-to-date information on traffic conditions.

[0045] 2. Data Preprocessing

[0046] The server preprocesses the collected traffic data to remove noise and errors, preparing a clean dataset suitable for analysis.

[0047] 3. Data analysis using generative AI

[0048] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, and based on this, calculates the optimal departure time and route for each driver.

[0049] 4. Notification function

[0050] Based on the analysis results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[0051] 5. Accumulation and analysis of long-term traffic data

[0052] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it clear which areas are experiencing problems.

[0053] 6. Generate improvement suggestions

[0054] The server generates improvement proposals for identified chronic congestion points and sends them to the traffic management organization, and also proposes legal changes if necessary.

[0055] Specific examples

[0056] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0057] 1. The user sets a destination

[0058] The user sets the destination in the navigation app on their smartphone, and this information is sent to the server.

[0059] 2. The server collects traffic data

[0060] The server collects the latest traffic data for routes to the destination from various sensors and cameras.

[0061] 3. Data Preprocessing

[0062] The server filters the collected data to remove noise and errors.

[0063] 4. Analysis by generative AI

[0064] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[0065] 5. Notification function

[0066] The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[0067] 6. Long-term congestion analysis

[0068] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0069] 7. Generate improvement suggestions

[0070] Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to traffic management organizations.

[0071] In this way, the system according to the present invention provides drivers with optimal information in real time, contributing to the improvement of chronic traffic congestion.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The server collects traffic data in real time from data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[0075] Step 2:

[0076] The server filters the collected data, removing noise and errors to create a clean dataset suitable for analysis.

[0077] Step 3:

[0078] The server uses the generated AI to analyze the filtered data, predict traffic flow and congestion, and calculate the optimal departure time and route based on that.

[0079] Step 4:

[0080] The server sends the analysis results to the device, which then notifies the user's smartphone or car navigation system of the optimal departure time and route.

[0081] Step 5:

[0082] The user receives a notification and adjusts their departure plans according to the suggested departure time and route displayed on the device.

[0083] Step 6:

[0084] The server stores long-term traffic data. Data collected from traffic sensors and GPS devices is stored for long periods of time and analyzed to identify chronic congestion areas.

[0085] Step 7:

[0086] The server generates improvement proposals for the identified chronic congestion points and presents specific measures to the traffic management organization.

[0087] Step 8:

[0088] The server sends improvement proposals to traffic management organizations, such as adjusting traffic lights or adding lanes, to resolve congestion.

[0089] Example 1

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

[0091] Conventional traffic information systems have difficulty providing optimal departure times and routes in real time, and are not sufficient for long-term congestion analysis or improvement proposals. As a result, drivers are unable to obtain accurate information to avoid congestion and often end up stuck in it. There is also a lack of a means to make effective improvement proposals to traffic management organizations.

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

[0093] In this invention, the server includes means for collecting traffic data in real time from multiple data sources, means for preprocessing the collected traffic data and removing noise and errors, means for analyzing the preprocessed data using a generative AI model to predict traffic flow and congestion, means for notifying the driver of the optimal departure time and route based on the analysis results, means for accumulating long-term traffic data and identifying chronic congestion points, and means for generating improvement proposals for chronic congestion points and transmitting them to a traffic management organization. This allows drivers to obtain optimal traffic information in real time and make effective improvement proposals to the traffic management organization.

[0094] "Data Source" refers to any device or method by which traffic data can be collected, such as road traffic cameras, GPS devices, traffic sensors, or user reports.

[0095] "Preprocessing" refers to the process of removing noise and errors from collected data and preparing a clean dataset suitable for analysis.

[0096] A "generative AI model" refers to an algorithm or program that uses machine learning to learn from past traffic data and predict traffic flow and congestion based on current conditions.

[0097] "Analysis results" are the data obtained after analysis by the generative AI model, which includes information on optimal departure times and routes.

[0098] "Notification" is a means of transmitting information to the driver based on the analysis results, and is done using devices such as smartphones and car navigation systems.

[0099] "Chronic congestion spots" refer to specific locations or areas where congestion occurs frequently over the long term.

[0100] "Improvement proposals" refer to proposals that outline specific measures and countermeasures to resolve chronic congestion.

[0101] "Transportation Management Organization" means a public or private organization that supervises and manages transportation.

[0102] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. The system collects traffic data from data sources, preprocesses it, analyzes it using a generative AI model, and notifies the driver of the results. It also accumulates long-term traffic data and makes improvement suggestions for chronic congestion areas.

[0103] First, the server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. Specific data sources include road traffic cameras (high-resolution cameras), GPS devices (location information acquisition devices), and traffic sensors (traffic condition sensors).

[0104] The server then pre-processes the collected traffic data using data cleaning tools (e.g., "data processing software") to remove noise and errors, preparing a clean dataset suitable for analysis.

[0105] The pre-processed data is then analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms (e.g., a "machine learning engine") to predict traffic flow and congestion. The model learns from past data and calculates optimal departure times and routes for each driver based on current conditions.

[0106] The server then notifies the driver's device (e.g., a mobile information terminal or a car navigation system) of the optimal departure time and route based on the analysis results. This notification can be made using a push notification API (e.g., a messaging service).

[0107] The server also accumulates long-term traffic data and uses it to identify chronic congestion points. For this purpose, it stores the long-term data in a time-series database (e.g., a "data storage system") and periodically feeds this data into a machine learning model to analyze congestion trends at specific points.

[0108] Finally, the server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The improvement proposals are automatically generated using a generative AI model and then sent to the traffic management organization via email or API, allowing the traffic management organization to take appropriate measures.

[0109] For example, if a user is using a navigation app on their smartphone, the system works as follows:

[0110] 1. The user sets a destination in the navigation app on their smartphone. This information is sent to the server.

[0111] 2. The server collects the latest traffic data for the route to the destination from various sensors and cameras.

[0112] 3. The server filters the collected data to remove noise and errors.

[0113] 4. The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[0114] 5. The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[0115] 6. The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0116] 7. Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to the traffic management organization.

[0117] Example prompt sentence:

[0118] "My current location is in XX municipality in Tokyo, and my destination is in △△ municipality in Tokyo. Please tell me the best route and departure time, taking traffic congestion into consideration."

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] The server collects real-time traffic data from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. The server retrieves data from these sources through APIs and stores it as an initial dataset, providing up-to-date traffic information.

[0122] Step 2:

[0123] The server preprocesses the collected traffic data. The input is the initial dataset collected in step 1, and here noise and errors are removed. Specifically, data cleaning tools (e.g., data processing software) are used to impute missing values ​​and remove outliers. The output is a clean dataset, suitable for analysis.

[0124] Step 3:

[0125] The server's generative AI model analyzes the pre-processed data. The input is the clean dataset generated in step 2. Here, a generative AI model (e.g., a machine learning engine) is used to learn from past data and predict traffic flow and congestion based on current conditions. The output is the optimal departure time and route for each driver.

[0126] Step 4:

[0127] The server notifies the driver's device of the optimal departure time and route based on the analysis results. The input is the departure time and route information calculated in step 3. The server sends a message to the driver's device (smartphone, car navigation system, etc.) via a push notification API (e.g., messaging service). The output is a notification sent to the driver, suggesting the optimal action to avoid congestion.

[0128] Step 5:

[0129] The server accumulates long-term traffic data and identifies chronic congestion locations. The input is continuously collected traffic data. Specifically, the data is stored in a time-series database (e.g., a data storage system) and periodically input into a machine learning model to analyze congestion trends. The output is congestion trend data at specific locations.

[0130] Step 6:

[0131] The server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The input is the congestion trend data obtained in step 5. Specific improvement proposals are automatically generated using the generative AI model and sent to the traffic management organization via email or API. The output is the specific improvement proposals received by the traffic management organization.

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] In modern society, traffic congestion and traffic accidents have become commonplace problems, requiring efficient traffic management for drivers and traffic managers. However, current traffic management systems lack sufficient real-time traffic data analysis and proposals for optimal routes and departure times, and improvements are needed. Furthermore, long-term measures for chronic congestion in specific areas are insufficient, necessitating the development of efficient guidance for drivers and optimization of traffic flow. Furthermore, as autonomous vehicles become more widespread, the vehicles themselves will need to be equipped with advanced traffic analysis capabilities.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes: a means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; a means for collecting traffic information; a means for preprocessing the collected data; a means for notifying the driver based on the preprocessed data; a means for accumulating long-term traffic data and generating improvement proposals for chronic congestion points; a means for transmitting the generated improvement proposals to a traffic management organization; a means for collecting traffic information from sensors installed in the vehicle and external data sources; a means for performing data analysis using an in-vehicle edge AI computing unit; a means for notifying the vehicle's infotainment system of the calculated optimal route information; and a means for notifying the driver using voice guidance. This enables autonomous vehicles to obtain optimal traffic information in real time and provide efficient guidance to the driver. Furthermore, long-term data accumulation contributes to overall improvements in traffic management.

[0137] "Generative AI" refers to artificial intelligence technology that uses machine learning algorithms to analyze data and generate new information and predictions.

[0138] "Traffic data" refers to all information related to traffic, such as the flow of vehicles on roads, speed, location, traffic volume, and accident information.

[0139] "Driver" means a person who operates a motor vehicle or other means of transportation to travel to a destination.

[0140] "Departure time" means the time at which a driver begins traveling to a particular destination.

[0141] "Route" refers to the path from the starting point to the destination.

[0142] "Means" refers to methods, devices, techniques, etc. used to achieve a specific purpose.

[0143] "Traffic information" refers to information related to driving, such as current road conditions, congestion information, accident information, and road construction information.

[0144] "Collection" refers to the act or process of gathering the necessary data.

[0145] "Preprocessing" refers to processes that remove noise, clean, or transform raw data to make it easier to analyze.

[0146] "Notification" refers to the act of communicating important information to relevant parties.

[0147] "Storage" means collecting and storing data or information over a long period of time.

[0148] "Improvement proposal" refers to the act of presenting a specific plan to solve current problems.

[0149] "Traffic management organization" refers to a public agency or private organization that manages and supervises traffic flow and safety.

[0150] A "sensor" refers to a device that detects physical phenomena and outputs that information as an electrical signal.

[0151] An "external data source" is an information source that provides data obtained from outside the system.

[0152] An "edge AI computing unit" refers to a computing device that performs AI processing near the device without relying on the cloud.

[0153] "Infotainment system" refers to a system installed in a vehicle that provides information and entertainment functions.

[0154] "Voice guidance" refers to a function that conveys information to the driver using voice.

[0155] This invention is a system for autonomous vehicles that uses generative AI to analyze real-time traffic information and provide the driver with the optimal departure time and route. The system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[0156] 1. Collecting traffic data

[0157] The server collects real-time traffic information from sensors installed in vehicles and external data sources (public transportation databases, user-provided data, etc.), making it possible to instantly grasp the latest traffic conditions.

[0158] Sensors include LiDAR, cameras, and radar, while external data sources include V2X communication.

[0159] 2. Data Preprocessing

[0160] The server preprocesses the collected traffic data to remove noise and outliers, preparing a clean dataset suitable for analysis by generative AI.

[0161] In the pre-processing process, data processors such as NVIDIA's Jetson and Qualcomm's Snapdragon Automotive are used.

[0162] 3. Data analysis using generative AI

[0163] The server's edge AI computing unit uses pre-processed data to predict traffic flow and congestion, using a generative AI model such as GPT-4 or a custom version of it.

[0164] The generative AI model analyzes prompts given to it to calculate the optimal departure time and route for the driver. An example of a prompt is, "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..."

[0165] 4. Notification function

[0166] Based on the analysis results, the server notifies the driver's device (infotainment system, smartphone, etc.) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[0167] The vehicle's infotainment system includes visual displays and voice guidance, such as "Turn right at the next traffic light."

[0168] 5. Accumulation and analysis of long-term traffic data

[0169] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it possible to solve traffic problems in specific areas based on the data.

[0170] The accumulated data is stored in the cloud and organized in a way that is easy for traffic managers to access.

[0171] 6. Generate improvement suggestions

[0172] The server automatically generates and sends improvement proposals to traffic management organizations for identified chronic congestion points, and also proposes legal reforms if necessary.

[0173] For example, suggestions include "re-adjust the timing of the traffic lights at this intersection."

[0174] In this way, the system can provide drivers with optimal information in real time and improve overall traffic efficiency in the long term.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The server collects real-time traffic information from vehicle-mounted sensors (LiDAR, cameras, radar) and external data sources (V2X communication, public transport databases, user-provided data). The input includes real-time traffic data from each data source, and the output is the collected raw traffic data.

[0178] Step 2:

[0179] The server preprocesses the collected raw traffic data, which includes removing noise and outliers. The input is the raw data collected in step 1, and the output is clean traffic data with noise removed. Specifically, the data is filtered using a processor such as NVIDIA's Jetson or Qualcomm's Snapdragon Automotive.

[0180] Step 3:

[0181] The server's edge AI computing unit analyzes the preprocessed, cleaned traffic data using a generative AI model (e.g., GPT-4 or a custom version). The input is the cleaned data from step 2, and the prompt is "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..." The output is the optimal departure time and route.

[0182] Step 4:

[0183] The server notifies the driver's device (vehicle infotainment system, smartphone, etc.) based on the analysis results obtained from the generation AI. The input is the analysis results obtained in step 3, and the output is the optimal departure time and route information displayed on the driver's device. This includes visual displays and audio guidance.

[0184] Step 5:

[0185] The server stores long-term traffic data, including the real-time data acquired in steps 1 to 4. The input contains all traffic data collected over time, and the output is the accumulated historical traffic database.

[0186] Step 6:

[0187] The server identifies chronic congestion points based on the accumulated long-term traffic data and generates improvement proposals for the traffic management organization. The input is the historical traffic data accumulated in Step 5, and the output is the identified congestion points and their improvement proposals. A specific example is "Re-adjust the timing of the traffic lights at this intersection."

[0188] Step 7:

[0189] The server sends the generated improvement proposals to the traffic management organization via email or a dedicated management system. The input is the improvement proposal data obtained in step 6, and the output is the traffic management organization that received the improvement proposals.

[0190] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0191] This invention relates to a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[0192] A natural language description of the program's processing

[0193] 1. Collecting traffic data

[0194] The server collects real-time traffic information from various data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, allowing users to obtain the latest information on traffic conditions at all times.

[0195] 2. Data Preprocessing

[0196] The server preprocesses the collected traffic data to remove noise and errors, resulting in a clean dataset that improves the accuracy of the analysis.

[0197] 3. Data analysis using generative AI

[0198] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, allowing it to calculate optimal departure times and routes for drivers and provide customized information taking into account the individual needs of the driver.

[0199] 4. Emotion Recognition by Emotion Engine

[0200] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[0201] 5. Notification function

[0202] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[0203] 6. Accumulation and analysis of long-term traffic data

[0204] The server accumulates traffic data over time and identifies chronic congestion points, allowing for a clear understanding of problem areas.

[0205] 7. Generate improvement suggestions

[0206] The server generates improvement proposals for chronic congestion points based on the accumulated data and sends them to the traffic management organization. These proposals include specific measures.

[0207] 8. Proposals for legal reform

[0208] If necessary, the server will propose new legislative changes regarding the identified issues, which will also be sent to the traffic management organization.

[0209] Specific examples

[0210] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0211] 1. The user sets a destination

[0212] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[0213] 2. The server collects traffic data

[0214] The server collects the latest traffic data around the destination from various sensors and cameras.

[0215] 3. Data Preprocessing

[0216] The server filters the collected data to remove noise and errors.

[0217] 4. Analysis by generative AI

[0218] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[0219] 5. Emotion Recognition by Emotion Engine

[0220] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[0221] 6. Notification function

[0222] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[0223] 7. Long-term congestion analysis

[0224] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0225] 8. Generate improvement suggestions

[0226] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[0227] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[0228] The processing flow will be explained below.

[0229] Step 1:

[0230] The server collects traffic data from multiple data sources, including road traffic cameras, GPS devices, traffic sensors, and real-time reports from users, and accumulates up-to-date information on traffic conditions.

[0231] Step 2:

[0232] The server preprocesses the collected traffic data, filtering out noise and errors in the data to prepare a clean dataset suitable for analysis.

[0233] Step 3:

[0234] The server uses the generated AI to analyze the pre-processed data in real time, predicting traffic flow and congestion and calculating the optimal departure time and route for each driver.

[0235] Step 4:

[0236] The server uses an emotion engine to analyze the driver's emotional state based on data acquired from the user's smartphone and in-car camera. It analyzes facial expressions and voice data to evaluate stress levels and fatigue levels.

[0237] Step 5:

[0238] The server generates notifications based on the analysis results and data from the emotion engine, providing optimal departure times and routes, as well as messages and advice based on the driver's emotional state.

[0239] Step 6:

[0240] The server generates a notification and sends it to the user's device (smartphone or car navigation system). For example, it may say, "Delaying your departure time by 15 minutes will help you avoid traffic jams. Please relax and drive safely."

[0241] Step 7:

[0242] The user receives a notification, sees the departure time and route notification displayed on the device, and adjusts departure plans accordingly.

[0243] Step 8:

[0244] The server accumulates long-term traffic data and identifies chronic congestion points. Recurring congestion points are extracted from the data, and problem areas are clarified.

[0245] Step 9:

[0246] The server generates improvement proposals for identified chronic congestion areas, such as "re-adjusting traffic light timing" or "widening specific road sections."

[0247] Step 10:

[0248] The server generates and sends improvement proposals to the traffic management organization. The proposals are specific, actionable, and aimed at reducing traffic congestion, and may also include proposals for legal reform, if necessary.

[0249] Example 2

[0250] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0251] Traffic congestion and traffic accidents are serious issues in modern society. In particular, there is a need for real-time traffic information and appropriate route suggestions tailored to the needs of individual drivers. It is also important to provide information tailored to the emotional state of the driver and to improve chronic congestion areas through long-term data accumulation. However, there is currently no system that can solve these issues in one go.

[0252] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with an optimal departure time and route; means for collecting traffic information; means for preprocessing the collected traffic data; means for notifying the driver based on the preprocessed data; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; means for transmitting the generated improvement proposals to a traffic management organization; and means for providing information based on individual needs using an emotion engine that recognizes the driver's emotional state. This enables the server to propose optimal routes in real time, provide information according to the driver's emotional state, and propose long-term traffic improvements.

[0253] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and make predictions and generate results.

[0254] "Traffic data" refers to information relating to road traffic conditions such as vehicle speed, location information, traffic volume, and accident information.

[0255] A "driver" is a person who operates a vehicle and uses the system to travel to a destination.

[0256] The "departure time" is the optimum time for the driver to depart for the specified destination.

[0257] A "route" is the optimal path a driver takes to reach a destination.

[0258] "Traffic information" is information that includes data and events related to current traffic conditions.

[0259] "Preprocessing" is a data processing step to remove noise and errors from collected data and make it ready for analysis.

[0260] "Notification" is the process in which the server sends the analysis results to the user's terminal and displays them.

[0261] "Long-term traffic data" refers to data on traffic conditions that is accumulated over a certain period of time.

[0262] A "chronic congestion spot" is a traffic congestion spot that occurs repeatedly in a specific location.

[0263] An "improvement proposal" is a specific measure generated by the server to improve the traffic situation.

[0264] A "traffic management organization" is a public agency or organization that promotes road safety and traffic flow.

[0265] The "emotion engine" is a technology that recognizes the driver's emotional state by analyzing their facial expressions and voice data.

[0266] "Individual needs" are the unique conditions that correspond to each driver's particular requirements and expectations.

[0267] This invention is a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[0268] Specifically, the system is implemented in the following manner.

[0269] 1. Collecting traffic data

[0270] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports. For example, the server periodically calls an API to retrieve data from each data source. Data from GPS devices can be received in JSON format.

[0271] 2. Data Preprocessing

[0272] The server preprocesses the collected traffic data to remove noise and errors, including imputing missing values ​​and normalizing the data. Specifically, it uses Python libraries (e.g., pandas and NumPy) to clean up the collected data, excluding noisy data points and filtering out abnormal sensor data.

[0273] 3. Data analysis using generative AI

[0274] The server's generation AI analyzes the preprocessed data and predicts traffic flow and congestion, calculating the optimal departure time and route for the driver. For example, the generation AI trains a model using frameworks such as TensorFlow and PyTorch to predict the next day's traffic conditions based on past traffic patterns.

[0275] 4. Emotion Recognition by Emotion Engine

[0276] The server's emotion engine recognizes each driver's emotional state in real time. For example, it uses cameras and sensor devices to analyze the driver's facial expressions and voice data to assess their stress level and fatigue. This is achieved by using OpenCV and deep learning models for facial recognition and emotion analysis. For voice data, it uses speech recognition tools (e.g., Google Cloud Speech-to-Text API).

[0277] 5. Notification function

[0278] Based on the analysis results and the emotion recognition results of the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state. For example, a push notification service such as Firebase Cloud Messaging could be used to send a message to the smartphone such as "Please leave 10 minutes earlier as traffic congestion is expected."

[0279] 6. Accumulation and analysis of long-term traffic data

[0280] The server accumulates traffic data over the long term and identifies chronic congestion areas, allowing for a clear understanding of traffic problem areas. Specifically, a time-series database (e.g., InfluxDB) is used to store data from each sensor over the long term.

[0281] 7. Generate improvement suggestions

[0282] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization. For example, it automatically generates a proposal to "adjust traffic light timing" and sends it to the traffic management organization via API.

[0283] 8. Proposals for legal reform

[0284] If necessary, the server will propose new legal changes regarding the identified issues, which will also be included in the automatically generated report and communicated to the traffic management organization via email or a dedicated portal.

[0285] Specific examples

[0286] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0287] 1. The user sets a destination

[0288] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[0289] 2. The server collects traffic data

[0290] The server collects the latest traffic data around the destination from various sensors and cameras.

[0291] 3. Data Preprocessing

[0292] The server filters the collected data to remove noise and errors.

[0293] 4. Analysis by generative AI

[0294] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[0295] 5. Emotion Recognition by Emotion Engine

[0296] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[0297] 6. Notification function

[0298] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[0299] 7. Long-term congestion analysis

[0300] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0301] 8. Generate improvement suggestions

[0302] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[0303] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[0304] Example prompt sentence:

[0305] "Due to traffic congestion, please leave 10 minutes earlier."

[0306] "Take a deep breath and relax."

[0307] This allows drivers to travel more comfortably and efficiently.

[0308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0309] Step 1:

[0310] Traffic data collection

[0311] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[0312] Input: Video data from road traffic cameras, location information from GPS devices, traffic sensor data, and traffic reports from users.

[0313] Output: Raw data (raw traffic information).

[0314] How it works: The server periodically calls the API to retrieve data from each data source. For example, data from a GPS device is received in JSON format, and video from a road traffic camera is received as stream data.

[0315] Step 2:

[0316] Data Preprocessing

[0317] The server preprocesses the collected traffic data to remove noise and errors, as well as impute missing values ​​and normalize the data.

[0318] Input: Raw data (raw traffic information).

[0319] Output: Clean data (data with noise and errors removed).

[0320] What it does: The server uses Python libraries (e.g., pandas, NumPy) to clean up the collected data. It filters out noisy data points and outliers from sensors. For example, it defines outliers as data outside a certain range and filters them out.

[0321] Step 3:

[0322] Data analysis with generative AI

[0323] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion.

[0324] Input: Clean data (data with noise and errors removed).

[0325] Output: Analysis results (optimal departure time and route, etc.).

[0326] How it works: Generative AI uses frameworks like TensorFlow and PyTorch to train models to predict the next day's traffic conditions based on past traffic patterns. The predictive models use neural networks and other machine learning algorithms.

[0327] Step 4:

[0328] Emotion recognition by emotion engine

[0329] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[0330] Input: Driver's facial expression data, voice data.

[0331] Output: Emotion recognition results (such as stress level and fatigue level).

[0332] How it works: The server uses OpenCV and deep learning models to perform facial recognition and emotion analysis. For voice data, it uses a speech recognition tool (e.g., Google Cloud Speech-to-Text API) to analyze it. For example, if a driver is tired, their emotional state is recognized as "fatigue."

[0333] Step 5:

[0334] Notification function

[0335] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[0336] Input: Analysis results (optimal departure time and route, etc.), emotion recognition results (stress level, fatigue level, etc.).

[0337] Output: Informational message.

[0338] What it does: The server uses a push notification service such as Firebase Cloud Messaging to send notifications to the smartphone. For example, a message saying, "Please leave 10 minutes early due to expected traffic congestion" is sent. If the driver is feeling stressed, advice such as "Take a deep breath and relax" is also sent.

[0339] Step 6:

[0340] Accumulation and analysis of long-term traffic data

[0341] The server accumulates traffic data over the long term and identifies areas with chronic congestion.

[0342] Input: Long-term traffic data.

[0343] Output: Traffic congestion analysis results.

[0344] How it works: The server uses a time-series database (e.g., InfluxDB) to store data from each sensor over time. It then runs queries to identify chronic congestion points. For example, if traffic volume at a particular intersection is high over a period of time, that point is considered a chronic congestion point.

[0345] Step 7:

[0346] Generate improvement suggestions

[0347] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization.

[0348] Input: Traffic congestion analysis results.

[0349] Output: Improvement proposals (specific measures).

[0350] How it works: The server uses the generation AI to automatically generate improvement proposals, such as adjusting traffic light timing. The proposals are automatically generated as a PDF report and sent to the traffic management organization via API.

[0351] Step 8:

[0352] Proposal for legal reform

[0353] The server will propose new legislative changes regarding identified issues, if necessary.

[0354] Input: Traffic congestion analysis results, improvement proposals.

[0355] Output: Proposed law change.

[0356] What it does: The server automatically generates reports containing proposed legal changes and notifies traffic management organizations via email or a dedicated portal, including proposals for new traffic regulations or infrastructure improvements.

[0357] (Application example 2)

[0358] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0359] Conventional traffic information systems have limited functionality in effectively analyzing real-time traffic data and providing drivers with optimal departure times and routes. Furthermore, they lacked the means to recognize the driver's emotional state and provide appropriate advice, which meant that they were unable to adequately reduce driver stress or support safe driving. Furthermore, they were unable to effectively propose and implement improvements to chronically congested areas through the accumulation and analysis of long-term traffic data. It is desirable to solve these problems and realize a more effective traffic information system.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; means for collecting traffic information; means for preprocessing the collected data; means for notifying the driver based on the preprocessed data; emotion recognition means for recognizing the driver's emotional state and adjusting the content of the notification; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; and means for transmitting the generated improvement proposals to a traffic management organization. This not only enables the provision of real-time traffic information but also support according to the driver's emotional state, making it possible to effectively analyze long-term traffic problems and propose improvements.

[0361] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate new information from data and perform specific tasks.

[0362] "Traffic data" refers to information that indicates traffic conditions such as road congestion, vehicle flow, and traffic light timing.

[0363] "Driver" means a person who drives a motor vehicle.

[0364] "Departure time" refers to the time when you start driving to your destination.

[0365] A "route" is a path from a starting point to a destination.

[0366] "Traffic information" refers to data that indicates current and predicted road conditions and congestion levels.

[0367] "Data preprocessing" refers to the process of converting collected raw data into a form suitable for analysis.

[0368] "Notification" refers to the action of the system providing information to the driver.

[0369] "Emotional state" refers to the driver's psychological and physiological state, such as stress level and fatigue level.

[0370] "Emotion recognition means" refers to technology that analyzes the driver's facial expressions and voice to identify their emotional state.

[0371] "Chronic congestion spots" are specific roads or intersections where congestion frequently occurs.

[0372] "Improvement proposals" are specific measures or proposed changes to improve traffic conditions.

[0373] "Traffic management organization" means a public or private organization that manages road traffic and helps it operate smoothly.

[0374] This invention is a system that uses generative AI and an emotion engine to analyze traffic data in real time and provide drivers with optimal departure times and routes. This system includes traffic data collection, data preprocessing, data analysis using generative AI, emotion recognition, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions.

[0375] The server first collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, user reports, etc. Cloud infrastructure (e.g., Google Cloud Platform or Amazon Web Services) is used at this stage.

[0376] The server then pre-processes the collected traffic data to remove noise and errors, improving the accuracy of the analysis. This pre-processing includes data filtering techniques and generating a clean dataset.

[0377] The pre-processed data is then analyzed through a generative AI model (e.g., GPT-4), which predicts traffic flow and congestion, calculates optimal departure times and routes for drivers, and provides customized information that takes into account the individual needs of the driver.

[0378] The emotion engine uses the driver's camera and sensor devices to recognize the driver's emotional state in real time. For example, deep learning frameworks (e.g., TensorFlow and OpenCV) are used for facial recognition and voice analysis. Notification content is then tailored based on this emotional state.

[0379] Based on the analysis and emotion recognition results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is even more effective because it is adjusted taking into account the driver's emotional state. For example, if the driver is feeling stressed, the notification will include a message saying, "Take a deep breath and relax."

[0380] Long-term traffic data is stored on a server and used to identify chronic congestion points. Based on this data, concrete improvement proposals can be generated for traffic management organizations, and even legal reforms can be proposed if necessary.

[0381] A concrete example would be a scenario where a user sets a destination and if their current stress level is high, the prompt "Relax" is displayed. For example, if a driver sets Tokyo Station as their destination in a smartphone navigation app, the following prompt sentence is used:

[0382] gps_data = GPSSensor().get_data(destination="Tokyo Station")

[0383] In this way, the system of the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] The server collects traffic data. The input is real-time data from road traffic cameras, GPS devices, traffic sensors, and user reports. The output is a set of collected raw data. This step includes, for example, obtaining location information from GPS devices and image data from cameras.

[0387] Step 2:

[0388] The server preprocesses the collected data. The input is the raw data collected in step 1. The output is a cleaned dataset with noise and errors removed. In this step, data cleansing such as data filtering and outlier removal is performed. Specifically, image processing algorithms are applied to image data, and location information is corrected for GPS data.

[0389] Step 3:

[0390] The server inputs the preprocessed data into a generative AI to analyze the optimal departure time and route. The input is cleaned traffic data. The output is optimal departure time and route information to provide to the driver. In this step, for example, a generative AI model (GPT-4) is used to analyze multiple data points to perform congestion prediction and time route optimization. The generative AI model analyzes traffic patterns and congestion trends and generates predictions.

[0391] Step 4:

[0392] The server uses an emotion engine to recognize the driver's emotional state. The input is the driver's camera and audio data. The output is the driver's emotional state (e.g., stress level and fatigue level). In this step, a deep learning framework (TensorFlow or OpenCV) is used to perform facial recognition and audio analysis to identify the driver's emotional state. Specifically, the server determines the driver's emotion by detecting changes in facial expression from the driver's facial image and analyzing the tone and speed of voice from the audio.

[0393] Step 5:

[0394] Based on the analysis results and emotion recognition results, the server notifies the driver of the optimal departure time and route, as well as advice based on the driver's emotional state. The input is the optimized departure time, route, and the driver's emotional state. The output is a notification message to be displayed on the driver's smartphone or car navigation system. In this step, the notification system is used to send advice based on the calculated information and emotions to the driver's device. For example, messages such as "The optimal departure time is 8:30. There is no traffic jam at the moment" or "Relax. The next rest stop is 20 km away" are displayed.

[0395] Step 6:

[0396] The server accumulates and analyzes long-term traffic data. The input is traffic data collected daily. The output is the analysis results on chronic congestion points. In this step, the collected past data is stored in a database and statistical analysis is performed. For example, it identifies which days of the week and at what times of day a particular road is prone to congestion.

[0397] Step 7:

[0398] The server generates improvement proposals based on the accumulated data and sends them to the traffic management organization. The input is the long-term traffic analysis results. The output is a specific improvement proposal. In this step, improvement proposals are generated, including, for example, signal timing adjustments and road widening proposals, and are sent to the traffic management organization via email or a dedicated management system.

[0399] This will not only provide real-time traffic information, but also support tailored to the driver's emotional state, as well as analyze and propose improvements to long-term traffic problems.

[0400] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0401] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0402] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0406] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0407] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0408] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0409] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0410] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0411] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0412] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0413] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0414] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0415] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0416] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[0417] A natural language description of the program's processing

[0418] 1. Collecting traffic data

[0419] The server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, to provide up-to-date information on traffic conditions.

[0420] 2. Data Preprocessing

[0421] The server preprocesses the collected traffic data to remove noise and errors, preparing a clean dataset suitable for analysis.

[0422] 3. Data analysis using generative AI

[0423] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, and based on this, calculates the optimal departure time and route for each driver.

[0424] 4. Notification function

[0425] Based on the analysis results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[0426] 5. Accumulation and analysis of long-term traffic data

[0427] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it clear which areas are experiencing problems.

[0428] 6. Generate improvement suggestions

[0429] The server generates improvement proposals for identified chronic congestion points and sends them to the traffic management organization, and also proposes legal changes if necessary.

[0430] Specific examples

[0431] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0432] 1. The user sets a destination

[0433] The user sets the destination in the navigation app on their smartphone, and this information is sent to the server.

[0434] 2. The server collects traffic data

[0435] The server collects the latest traffic data for routes to the destination from various sensors and cameras.

[0436] 3. Data Preprocessing

[0437] The server filters the collected data to remove noise and errors.

[0438] 4. Analysis by generative AI

[0439] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[0440] 5. Notification function

[0441] The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[0442] 6. Long-term congestion analysis

[0443] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0444] 7. Generate improvement suggestions

[0445] Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to traffic management organizations.

[0446] In this way, the system according to the present invention provides drivers with optimal information in real time, contributing to the improvement of chronic traffic congestion.

[0447] The processing flow will be explained below.

[0448] Step 1:

[0449] The server collects traffic data in real time from data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[0450] Step 2:

[0451] The server filters the collected data, removing noise and errors to create a clean dataset suitable for analysis.

[0452] Step 3:

[0453] The server uses the generated AI to analyze the filtered data, predict traffic flow and congestion, and calculate the optimal departure time and route based on that.

[0454] Step 4:

[0455] The server sends the analysis results to the device, which then notifies the user's smartphone or car navigation system of the optimal departure time and route.

[0456] Step 5:

[0457] The user receives a notification and adjusts their departure plans according to the suggested departure time and route displayed on the device.

[0458] Step 6:

[0459] The server stores long-term traffic data. Data collected from traffic sensors and GPS devices is stored for long periods of time and analyzed to identify chronic congestion areas.

[0460] Step 7:

[0461] The server generates improvement proposals for the identified chronic congestion points and presents specific measures to the traffic management organization.

[0462] Step 8:

[0463] The server sends improvement proposals to traffic management organizations, such as adjusting traffic lights or adding lanes, to resolve congestion.

[0464] Example 1

[0465] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0466] Conventional traffic information systems have difficulty providing optimal departure times and routes in real time, and are not sufficient for long-term congestion analysis or improvement proposals. As a result, drivers are unable to obtain accurate information to avoid congestion and often end up stuck in it. There is also a lack of a means to make effective improvement proposals to traffic management organizations.

[0467] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0468] In this invention, the server includes means for collecting traffic data in real time from multiple data sources, means for preprocessing the collected traffic data and removing noise and errors, means for analyzing the preprocessed data using a generative AI model to predict traffic flow and congestion, means for notifying the driver of the optimal departure time and route based on the analysis results, means for accumulating long-term traffic data and identifying chronic congestion points, and means for generating improvement proposals for chronic congestion points and transmitting them to a traffic management organization. This allows drivers to obtain optimal traffic information in real time and make effective improvement proposals to the traffic management organization.

[0469] "Data Source" refers to any device or method by which traffic data can be collected, such as road traffic cameras, GPS devices, traffic sensors, or user reports.

[0470] "Preprocessing" refers to the process of removing noise and errors from collected data and preparing a clean dataset suitable for analysis.

[0471] A "generative AI model" refers to an algorithm or program that uses machine learning to learn from past traffic data and predict traffic flow and congestion based on current conditions.

[0472] "Analysis results" are the data obtained after analysis by the generative AI model, which includes information on optimal departure times and routes.

[0473] "Notification" is a means of transmitting information to the driver based on the analysis results, and is done using devices such as smartphones and car navigation systems.

[0474] "Chronic congestion spots" refer to specific locations or areas where congestion occurs frequently over the long term.

[0475] "Improvement proposals" refer to proposals that outline specific measures and countermeasures to resolve chronic congestion.

[0476] "Transportation Management Organization" means a public or private organization that supervises and manages transportation.

[0477] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. The system collects traffic data from data sources, preprocesses it, analyzes it using a generative AI model, and notifies the driver of the results. It also accumulates long-term traffic data and makes improvement suggestions for chronic congestion areas.

[0478] First, the server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. Specific data sources include road traffic cameras (high-resolution cameras), GPS devices (location information acquisition devices), and traffic sensors (traffic condition sensors).

[0479] The server then pre-processes the collected traffic data using data cleaning tools (e.g., "data processing software") to remove noise and errors, preparing a clean dataset suitable for analysis.

[0480] The pre-processed data is then analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms (e.g., a "machine learning engine") to predict traffic flow and congestion. The model learns from past data and calculates optimal departure times and routes for each driver based on current conditions.

[0481] The server then notifies the driver's device (e.g., a mobile information terminal or a car navigation system) of the optimal departure time and route based on the analysis results. This notification can be made using a push notification API (e.g., a messaging service).

[0482] The server also accumulates long-term traffic data and uses it to identify chronic congestion points. For this purpose, it stores the long-term data in a time-series database (e.g., a "data storage system") and periodically feeds this data into a machine learning model to analyze congestion trends at specific points.

[0483] Finally, the server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The improvement proposals are automatically generated using a generative AI model and then sent to the traffic management organization via email or API, allowing the traffic management organization to take appropriate measures.

[0484] For example, if a user is using a navigation app on their smartphone, the system works as follows:

[0485] 1. The user sets a destination in the navigation app on their smartphone. This information is sent to the server.

[0486] 2. The server collects the latest traffic data for the route to the destination from various sensors and cameras.

[0487] 3. The server filters the collected data to remove noise and errors.

[0488] 4. The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[0489] 5. The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[0490] 6. The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0491] 7. Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to the traffic management organization.

[0492] Example prompt sentence:

[0493] "My current location is in XX municipality in Tokyo, and my destination is in △△ municipality in Tokyo. Please tell me the best route and departure time, taking traffic congestion into consideration."

[0494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0495] Step 1:

[0496] The server collects real-time traffic data from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. The server retrieves data from these sources through APIs and stores it as an initial dataset, providing up-to-date traffic information.

[0497] Step 2:

[0498] The server preprocesses the collected traffic data. The input is the initial dataset collected in step 1, and here noise and errors are removed. Specifically, data cleaning tools (e.g., data processing software) are used to impute missing values ​​and remove outliers. The output is a clean dataset, suitable for analysis.

[0499] Step 3:

[0500] The server's generative AI model analyzes the pre-processed data. The input is the clean dataset generated in step 2. Here, a generative AI model (e.g., a machine learning engine) is used to learn from past data and predict traffic flow and congestion based on current conditions. The output is the optimal departure time and route for each driver.

[0501] Step 4:

[0502] The server notifies the driver's device of the optimal departure time and route based on the analysis results. The input is the departure time and route information calculated in step 3. The server sends a message to the driver's device (smartphone, car navigation system, etc.) via a push notification API (e.g., messaging service). The output is a notification sent to the driver, suggesting the optimal action to avoid congestion.

[0503] Step 5:

[0504] The server accumulates long-term traffic data and identifies chronic congestion locations. The input is continuously collected traffic data. Specifically, the data is stored in a time-series database (e.g., a data storage system) and periodically input into a machine learning model to analyze congestion trends. The output is congestion trend data at specific locations.

[0505] Step 6:

[0506] The server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The input is the congestion trend data obtained in step 5. Specific improvement proposals are automatically generated using the generative AI model and sent to the traffic management organization via email or API. The output is the specific improvement proposals received by the traffic management organization.

[0507] (Application example 1)

[0508] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0509] In modern society, traffic congestion and traffic accidents have become commonplace problems, requiring efficient traffic management for drivers and traffic managers. However, current traffic management systems lack sufficient real-time traffic data analysis and proposals for optimal routes and departure times, and improvements are needed. Furthermore, long-term measures for chronic congestion in specific areas are insufficient, necessitating the development of efficient guidance for drivers and optimization of traffic flow. Furthermore, as autonomous vehicles become more widespread, the vehicles themselves will need to be equipped with advanced traffic analysis capabilities.

[0510] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0511] In this invention, the server includes: a means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; a means for collecting traffic information; a means for preprocessing the collected data; a means for notifying the driver based on the preprocessed data; a means for accumulating long-term traffic data and generating improvement proposals for chronic congestion points; a means for transmitting the generated improvement proposals to a traffic management organization; a means for collecting traffic information from sensors installed in the vehicle and external data sources; a means for performing data analysis using an in-vehicle edge AI computing unit; a means for notifying the vehicle's infotainment system of the calculated optimal route information; and a means for notifying the driver using voice guidance. This enables autonomous vehicles to obtain optimal traffic information in real time and provide efficient guidance to the driver. Furthermore, long-term data accumulation contributes to overall improvements in traffic management.

[0512] "Generative AI" refers to artificial intelligence technology that uses machine learning algorithms to analyze data and generate new information and predictions.

[0513] "Traffic data" refers to all information related to traffic, such as the flow of vehicles on roads, speed, location, traffic volume, and accident information.

[0514] "Driver" means a person who operates a motor vehicle or other means of transportation to travel to a destination.

[0515] "Departure time" means the time at which a driver begins traveling to a particular destination.

[0516] "Route" refers to the path from the starting point to the destination.

[0517] "Means" refers to methods, devices, techniques, etc. used to achieve a specific purpose.

[0518] "Traffic information" refers to information related to driving, such as current road conditions, congestion information, accident information, and road construction information.

[0519] "Collection" refers to the act or process of gathering the necessary data.

[0520] "Preprocessing" refers to processes that remove noise, clean, or transform raw data to make it easier to analyze.

[0521] "Notification" refers to the act of communicating important information to relevant parties.

[0522] "Storage" means collecting and storing data or information over a long period of time.

[0523] "Improvement proposal" refers to the act of presenting a specific plan to solve current problems.

[0524] "Traffic management organization" refers to a public agency or private organization that manages and supervises traffic flow and safety.

[0525] A "sensor" refers to a device that detects physical phenomena and outputs that information as an electrical signal.

[0526] An "external data source" is an information source that provides data obtained from outside the system.

[0527] An "edge AI computing unit" refers to a computing device that performs AI processing near the device without relying on the cloud.

[0528] "Infotainment system" refers to a system installed in a vehicle that provides information and entertainment functions.

[0529] "Voice guidance" refers to a function that conveys information to the driver using voice.

[0530] This invention is a system for autonomous vehicles that uses generative AI to analyze real-time traffic information and provide the driver with the optimal departure time and route. The system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[0531] 1. Collecting traffic data

[0532] The server collects real-time traffic information from sensors installed in vehicles and external data sources (public transportation databases, user-provided data, etc.), making it possible to instantly grasp the latest traffic conditions.

[0533] Sensors include LiDAR, cameras, and radar, while external data sources include V2X communication.

[0534] 2. Data Preprocessing

[0535] The server preprocesses the collected traffic data to remove noise and outliers, preparing a clean dataset suitable for analysis by generative AI.

[0536] In the pre-processing process, data processors such as NVIDIA's Jetson and Qualcomm's Snapdragon Automotive are used.

[0537] 3. Data analysis using generative AI

[0538] The server's edge AI computing unit uses pre-processed data to predict traffic flow and congestion, using a generative AI model such as GPT-4 or a custom version of it.

[0539] The generative AI model analyzes prompts given to it to calculate the optimal departure time and route for the driver. An example of a prompt is, "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..."

[0540] 4. Notification function

[0541] Based on the analysis results, the server notifies the driver's device (infotainment system, smartphone, etc.) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[0542] The vehicle's infotainment system includes visual displays and voice guidance, such as "Turn right at the next traffic light."

[0543] 5. Accumulation and analysis of long-term traffic data

[0544] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it possible to solve traffic problems in specific areas based on the data.

[0545] The accumulated data is stored in the cloud and organized in a way that is easy for traffic managers to access.

[0546] 6. Generate improvement suggestions

[0547] The server automatically generates and sends improvement proposals to traffic management organizations for identified chronic congestion points, and also proposes legal reforms if necessary.

[0548] For example, suggestions include "re-adjust the timing of the traffic lights at this intersection."

[0549] In this way, the system can provide drivers with optimal information in real time and improve overall traffic efficiency in the long term.

[0550] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0551] Step 1:

[0552] The server collects real-time traffic information from vehicle-mounted sensors (LiDAR, cameras, radar) and external data sources (V2X communication, public transport databases, user-provided data). The input includes real-time traffic data from each data source, and the output is the collected raw traffic data.

[0553] Step 2:

[0554] The server preprocesses the collected raw traffic data, which includes removing noise and outliers. The input is the raw data collected in step 1, and the output is clean traffic data with noise removed. Specifically, the data is filtered using a processor such as NVIDIA's Jetson or Qualcomm's Snapdragon Automotive.

[0555] Step 3:

[0556] The server's edge AI computing unit analyzes the preprocessed, cleaned traffic data using a generative AI model (e.g., GPT-4 or a custom version). The input is the cleaned data from step 2, and the prompt is "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..." The output is the optimal departure time and route.

[0557] Step 4:

[0558] The server notifies the driver's device (vehicle infotainment system, smartphone, etc.) based on the analysis results obtained from the generation AI. The input is the analysis results obtained in step 3, and the output is the optimal departure time and route information displayed on the driver's device. This includes visual displays and audio guidance.

[0559] Step 5:

[0560] The server stores long-term traffic data, including the real-time data acquired in steps 1 to 4. The input contains all traffic data collected over time, and the output is the accumulated historical traffic database.

[0561] Step 6:

[0562] The server identifies chronic congestion points based on the accumulated long-term traffic data and generates improvement proposals for the traffic management organization. The input is the historical traffic data accumulated in Step 5, and the output is the identified congestion points and their improvement proposals. A specific example is "Re-adjust the timing of the traffic lights at this intersection."

[0563] Step 7:

[0564] The server sends the generated improvement proposals to the traffic management organization via email or a dedicated management system. The input is the improvement proposal data obtained in step 6, and the output is the traffic management organization that received the improvement proposals.

[0565] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0566] This invention relates to a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[0567] A natural language description of the program's processing

[0568] 1. Collecting traffic data

[0569] The server collects real-time traffic information from various data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, allowing users to obtain the latest information on traffic conditions at all times.

[0570] 2. Data Preprocessing

[0571] The server preprocesses the collected traffic data to remove noise and errors, resulting in a clean dataset that improves the accuracy of the analysis.

[0572] 3. Data analysis using generative AI

[0573] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, allowing it to calculate optimal departure times and routes for drivers and provide customized information taking into account the individual needs of the driver.

[0574] 4. Emotion Recognition by Emotion Engine

[0575] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[0576] 5. Notification function

[0577] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[0578] 6. Accumulation and analysis of long-term traffic data

[0579] The server accumulates traffic data over time and identifies chronic congestion points, allowing for a clear understanding of problem areas.

[0580] 7. Generate improvement suggestions

[0581] The server generates improvement proposals for chronic congestion points based on the accumulated data and sends them to the traffic management organization. These proposals include specific measures.

[0582] 8. Proposals for legal reform

[0583] If necessary, the server will propose new legislative changes regarding the identified issues, which will also be sent to the traffic management organization.

[0584] Specific examples

[0585] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0586] 1. The user sets a destination

[0587] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[0588] 2. The server collects traffic data

[0589] The server collects the latest traffic data around the destination from various sensors and cameras.

[0590] 3. Data Preprocessing

[0591] The server filters the collected data to remove noise and errors.

[0592] 4. Analysis by generative AI

[0593] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[0594] 5. Emotion Recognition by Emotion Engine

[0595] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[0596] 6. Notification function

[0597] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[0598] 7. Long-term congestion analysis

[0599] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0600] 8. Generate improvement suggestions

[0601] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[0602] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[0603] The processing flow will be explained below.

[0604] Step 1:

[0605] The server collects traffic data from multiple data sources, including road traffic cameras, GPS devices, traffic sensors, and real-time reports from users, and accumulates up-to-date information on traffic conditions.

[0606] Step 2:

[0607] The server preprocesses the collected traffic data, filtering out noise and errors in the data to prepare a clean dataset suitable for analysis.

[0608] Step 3:

[0609] The server uses the generated AI to analyze the pre-processed data in real time, predicting traffic flow and congestion and calculating the optimal departure time and route for each driver.

[0610] Step 4:

[0611] The server uses an emotion engine to analyze the driver's emotional state based on data acquired from the user's smartphone and in-car camera. It analyzes facial expressions and voice data to evaluate stress levels and fatigue levels.

[0612] Step 5:

[0613] The server generates notifications based on the analysis results and data from the emotion engine, providing optimal departure times and routes, as well as messages and advice based on the driver's emotional state.

[0614] Step 6:

[0615] The server generates a notification and sends it to the user's device (smartphone or car navigation system). For example, it may say, "Delaying your departure time by 15 minutes will help you avoid traffic jams. Please relax and drive safely."

[0616] Step 7:

[0617] The user receives a notification, sees the departure time and route notification displayed on the device, and adjusts departure plans accordingly.

[0618] Step 8:

[0619] The server accumulates long-term traffic data and identifies chronic congestion points. Recurring congestion points are extracted from the data, and problem areas are clarified.

[0620] Step 9:

[0621] The server generates improvement proposals for identified chronic congestion areas, such as "re-adjusting traffic light timing" or "widening specific road sections."

[0622] Step 10:

[0623] The server generates and sends improvement proposals to the traffic management organization. The proposals are specific, actionable, and aimed at reducing traffic congestion, and may also include proposals for legal reform, if necessary.

[0624] Example 2

[0625] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0626] Traffic congestion and traffic accidents are serious issues in modern society. In particular, there is a need for real-time traffic information and appropriate route suggestions tailored to the needs of individual drivers. It is also important to provide information tailored to the emotional state of the driver and to improve chronic congestion areas through long-term data accumulation. However, there is currently no system that can solve these issues in one go.

[0627] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with an optimal departure time and route; means for collecting traffic information; means for preprocessing the collected traffic data; means for notifying the driver based on the preprocessed data; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; means for transmitting the generated improvement proposals to a traffic management organization; and means for providing information based on individual needs using an emotion engine that recognizes the driver's emotional state. This enables the server to propose optimal routes in real time, provide information according to the driver's emotional state, and propose long-term traffic improvements.

[0628] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and make predictions and generate results.

[0629] "Traffic data" refers to information relating to road traffic conditions such as vehicle speed, location information, traffic volume, and accident information.

[0630] A "driver" is a person who operates a vehicle and uses the system to travel to a destination.

[0631] The "departure time" is the optimum time for the driver to depart for the specified destination.

[0632] A "route" is the optimal path a driver takes to reach a destination.

[0633] "Traffic information" is information that includes data and events related to current traffic conditions.

[0634] "Preprocessing" is a data processing step to remove noise and errors from collected data and make it ready for analysis.

[0635] "Notification" is the process in which the server sends the analysis results to the user's terminal and displays them.

[0636] "Long-term traffic data" refers to data on traffic conditions that is accumulated over a certain period of time.

[0637] A "chronic congestion spot" is a traffic congestion spot that occurs repeatedly in a specific location.

[0638] An "improvement proposal" is a specific measure generated by the server to improve the traffic situation.

[0639] A "traffic management organization" is a public agency or organization that promotes road safety and traffic flow.

[0640] The "emotion engine" is a technology that recognizes the driver's emotional state by analyzing their facial expressions and voice data.

[0641] "Individual needs" are the unique conditions that correspond to each driver's particular requirements and expectations.

[0642] This invention is a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[0643] Specifically, the system is implemented in the following manner.

[0644] 1. Collecting traffic data

[0645] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports. For example, the server periodically calls an API to retrieve data from each data source. Data from GPS devices can be received in JSON format.

[0646] 2. Data Preprocessing

[0647] The server preprocesses the collected traffic data to remove noise and errors, including imputing missing values ​​and normalizing the data. Specifically, it uses Python libraries (e.g., pandas and NumPy) to clean up the collected data, excluding noisy data points and filtering out abnormal sensor data.

[0648] 3. Data analysis using generative AI

[0649] The server's generation AI analyzes the preprocessed data and predicts traffic flow and congestion, calculating the optimal departure time and route for the driver. For example, the generation AI trains a model using frameworks such as TensorFlow and PyTorch to predict the next day's traffic conditions based on past traffic patterns.

[0650] 4. Emotion Recognition by Emotion Engine

[0651] The server's emotion engine recognizes each driver's emotional state in real time. For example, it uses cameras and sensor devices to analyze the driver's facial expressions and voice data to assess their stress level and fatigue. This is achieved by using OpenCV and deep learning models for facial recognition and emotion analysis. For voice data, it uses speech recognition tools (e.g., Google Cloud Speech-to-Text API).

[0652] 5. Notification function

[0653] Based on the analysis results and the emotion recognition results of the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state. For example, a push notification service such as Firebase Cloud Messaging could be used to send a message to the smartphone such as "Please leave 10 minutes earlier as traffic congestion is expected."

[0654] 6. Accumulation and analysis of long-term traffic data

[0655] The server accumulates traffic data over the long term and identifies chronic congestion areas, allowing for a clear understanding of traffic problem areas. Specifically, a time-series database (e.g., InfluxDB) is used to store data from each sensor over the long term.

[0656] 7. Generate improvement suggestions

[0657] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization. For example, it automatically generates a proposal to "adjust traffic light timing" and sends it to the traffic management organization via API.

[0658] 8. Proposals for legal reform

[0659] If necessary, the server will propose new legal changes regarding the identified issues, which will also be included in the automatically generated report and communicated to the traffic management organization via email or a dedicated portal.

[0660] Specific examples

[0661] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0662] 1. The user sets a destination

[0663] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[0664] 2. The server collects traffic data

[0665] The server collects the latest traffic data around the destination from various sensors and cameras.

[0666] 3. Data Preprocessing

[0667] The server filters the collected data to remove noise and errors.

[0668] 4. Analysis by generative AI

[0669] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[0670] 5. Emotion Recognition by Emotion Engine

[0671] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[0672] 6. Notification function

[0673] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[0674] 7. Long-term congestion analysis

[0675] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0676] 8. Generate improvement suggestions

[0677] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[0678] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[0679] Example prompt sentence:

[0680] "Due to traffic congestion, please leave 10 minutes earlier."

[0681] "Take a deep breath and relax."

[0682] This allows drivers to travel more comfortably and efficiently.

[0683] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0684] Step 1:

[0685] Traffic data collection

[0686] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[0687] Input: Video data from road traffic cameras, location information from GPS devices, traffic sensor data, and traffic reports from users.

[0688] Output: Raw data (raw traffic information).

[0689] How it works: The server periodically calls the API to retrieve data from each data source. For example, data from a GPS device is received in JSON format, and video from a road traffic camera is received as stream data.

[0690] Step 2:

[0691] Data Preprocessing

[0692] The server preprocesses the collected traffic data to remove noise and errors, as well as impute missing values ​​and normalize the data.

[0693] Input: Raw data (raw traffic information).

[0694] Output: Clean data (data with noise and errors removed).

[0695] What it does: The server uses Python libraries (e.g., pandas, NumPy) to clean up the collected data. It filters out noisy data points and outliers from sensors. For example, it defines outliers as data outside a certain range and filters them out.

[0696] Step 3:

[0697] Data analysis with generative AI

[0698] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion.

[0699] Input: Clean data (data with noise and errors removed).

[0700] Output: Analysis results (optimal departure time and route, etc.).

[0701] How it works: Generative AI uses frameworks like TensorFlow and PyTorch to train models to predict the next day's traffic conditions based on past traffic patterns. The predictive models use neural networks and other machine learning algorithms.

[0702] Step 4:

[0703] Emotion recognition by emotion engine

[0704] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[0705] Input: Driver's facial expression data, voice data.

[0706] Output: Emotion recognition results (such as stress level and fatigue level).

[0707] How it works: The server uses OpenCV and deep learning models to perform facial recognition and emotion analysis. For voice data, it uses a speech recognition tool (e.g., Google Cloud Speech-to-Text API) to analyze it. For example, if a driver is tired, their emotional state is recognized as "fatigue."

[0708] Step 5:

[0709] Notification function

[0710] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[0711] Input: Analysis results (optimal departure time and route, etc.), emotion recognition results (stress level, fatigue level, etc.).

[0712] Output: Informational message.

[0713] What it does: The server uses a push notification service such as Firebase Cloud Messaging to send notifications to the smartphone. For example, a message saying, "Please leave 10 minutes early due to expected traffic congestion" is sent. If the driver is feeling stressed, advice such as "Take a deep breath and relax" is also sent.

[0714] Step 6:

[0715] Accumulation and analysis of long-term traffic data

[0716] The server accumulates traffic data over the long term and identifies areas with chronic congestion.

[0717] Input: Long-term traffic data.

[0718] Output: Traffic congestion analysis results.

[0719] How it works: The server uses a time-series database (e.g., InfluxDB) to store data from each sensor over time. It then runs queries to identify chronic congestion points. For example, if traffic volume at a particular intersection is high over a period of time, that point is considered a chronic congestion point.

[0720] Step 7:

[0721] Generate improvement suggestions

[0722] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization.

[0723] Input: Traffic congestion analysis results.

[0724] Output: Improvement proposals (specific measures).

[0725] How it works: The server uses the generation AI to automatically generate improvement proposals, such as adjusting traffic light timing. The proposals are automatically generated as a PDF report and sent to the traffic management organization via API.

[0726] Step 8:

[0727] Proposal for legal reform

[0728] The server will propose new legislative changes regarding identified issues, if necessary.

[0729] Input: Traffic congestion analysis results, improvement proposals.

[0730] Output: Proposed law change.

[0731] What it does: The server automatically generates reports containing proposed legal changes and notifies traffic management organizations via email or a dedicated portal, including proposals for new traffic regulations or infrastructure improvements.

[0732] (Application example 2)

[0733] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0734] Conventional traffic information systems have limited functionality in effectively analyzing real-time traffic data and providing drivers with optimal departure times and routes. Furthermore, they lacked the means to recognize the driver's emotional state and provide appropriate advice, which meant that they were unable to adequately reduce driver stress or support safe driving. Furthermore, they were unable to effectively propose and implement improvements to chronically congested areas through the accumulation and analysis of long-term traffic data. It is desirable to solve these problems and realize a more effective traffic information system.

[0735] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; means for collecting traffic information; means for preprocessing the collected data; means for notifying the driver based on the preprocessed data; emotion recognition means for recognizing the driver's emotional state and adjusting the content of the notification; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; and means for transmitting the generated improvement proposals to a traffic management organization. This not only enables the provision of real-time traffic information but also support according to the driver's emotional state, making it possible to effectively analyze long-term traffic problems and propose improvements.

[0736] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate new information from data and perform specific tasks.

[0737] "Traffic data" refers to information that indicates traffic conditions such as road congestion, vehicle flow, and traffic light timing.

[0738] "Driver" means a person who drives a motor vehicle.

[0739] "Departure time" refers to the time when you start driving to your destination.

[0740] A "route" is a path from a starting point to a destination.

[0741] "Traffic information" refers to data that indicates current and predicted road conditions and congestion levels.

[0742] "Data preprocessing" refers to the process of converting collected raw data into a form suitable for analysis.

[0743] "Notification" refers to the action of the system providing information to the driver.

[0744] "Emotional state" refers to the driver's psychological and physiological state, such as stress level and fatigue level.

[0745] "Emotion recognition means" refers to technology that analyzes the driver's facial expressions and voice to identify their emotional state.

[0746] "Chronic congestion spots" are specific roads or intersections where congestion frequently occurs.

[0747] "Improvement proposals" are specific measures or proposed changes to improve traffic conditions.

[0748] "Traffic management organization" means a public or private organization that manages road traffic and helps it operate smoothly.

[0749] This invention is a system that uses generative AI and an emotion engine to analyze traffic data in real time and provide drivers with optimal departure times and routes. This system includes traffic data collection, data preprocessing, data analysis using generative AI, emotion recognition, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions.

[0750] The server first collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, user reports, etc. Cloud infrastructure (e.g., Google Cloud Platform or Amazon Web Services) is used at this stage.

[0751] The server then pre-processes the collected traffic data to remove noise and errors, improving the accuracy of the analysis. This pre-processing includes data filtering techniques and generating a clean dataset.

[0752] The pre-processed data is then analyzed through a generative AI model (e.g., GPT-4), which predicts traffic flow and congestion, calculates optimal departure times and routes for drivers, and provides customized information that takes into account the individual needs of the driver.

[0753] The emotion engine uses the driver's camera and sensor devices to recognize the driver's emotional state in real time. For example, deep learning frameworks (e.g., TensorFlow and OpenCV) are used for facial recognition and voice analysis. Notification content is then tailored based on this emotional state.

[0754] Based on the analysis and emotion recognition results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is even more effective because it is adjusted taking into account the driver's emotional state. For example, if the driver is feeling stressed, the notification will include a message saying, "Take a deep breath and relax."

[0755] Long-term traffic data is stored on a server and used to identify chronic congestion points. Based on this data, concrete improvement proposals can be generated for traffic management organizations, and even legal reforms can be proposed if necessary.

[0756] A concrete example would be a scenario where a user sets a destination and if their current stress level is high, the prompt "Relax" is displayed. For example, if a driver sets Tokyo Station as their destination in a smartphone navigation app, the following prompt sentence is used:

[0757] gps_data = GPSSensor().get_data(destination="Tokyo Station")

[0758] In this way, the system of the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[0759] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0760] Step 1:

[0761] The server collects traffic data. The input is real-time data from road traffic cameras, GPS devices, traffic sensors, and user reports. The output is a set of collected raw data. This step includes, for example, obtaining location information from GPS devices and image data from cameras.

[0762] Step 2:

[0763] The server preprocesses the collected data. The input is the raw data collected in step 1. The output is a cleaned dataset with noise and errors removed. In this step, data cleansing such as data filtering and outlier removal is performed. Specifically, image processing algorithms are applied to image data, and location information is corrected for GPS data.

[0764] Step 3:

[0765] The server inputs the preprocessed data into a generative AI to analyze the optimal departure time and route. The input is cleaned traffic data. The output is optimal departure time and route information to provide to the driver. In this step, for example, a generative AI model (GPT-4) is used to analyze multiple data points to perform congestion prediction and time route optimization. The generative AI model analyzes traffic patterns and congestion trends and generates predictions.

[0766] Step 4:

[0767] The server uses an emotion engine to recognize the driver's emotional state. The input is the driver's camera and audio data. The output is the driver's emotional state (e.g., stress level and fatigue level). In this step, a deep learning framework (TensorFlow or OpenCV) is used to perform facial recognition and audio analysis to identify the driver's emotional state. Specifically, the server determines the driver's emotion by detecting changes in facial expression from the driver's facial image and analyzing the tone and speed of voice from the audio.

[0768] Step 5:

[0769] Based on the analysis results and emotion recognition results, the server notifies the driver of the optimal departure time and route, as well as advice based on the driver's emotional state. The input is the optimized departure time, route, and the driver's emotional state. The output is a notification message to be displayed on the driver's smartphone or car navigation system. In this step, the notification system is used to send advice based on the calculated information and emotions to the driver's device. For example, messages such as "The optimal departure time is 8:30. There is no traffic jam at the moment" or "Relax. The next rest stop is 20 km away" are displayed.

[0770] Step 6:

[0771] The server accumulates and analyzes long-term traffic data. The input is traffic data collected daily. The output is the analysis results on chronic congestion points. In this step, the collected past data is stored in a database and statistical analysis is performed. For example, it identifies which days of the week and at what times of day a particular road is prone to congestion.

[0772] Step 7:

[0773] The server generates improvement proposals based on the accumulated data and sends them to the traffic management organization. The input is the long-term traffic analysis results. The output is a specific improvement proposal. In this step, improvement proposals are generated, including, for example, signal timing adjustments and road widening proposals, and are sent to the traffic management organization via email or a dedicated management system.

[0774] This will not only provide real-time traffic information, but also support tailored to the driver's emotional state, as well as analyze and propose improvements to long-term traffic problems.

[0775] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0776] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0777] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0778] [Third embodiment]

[0779] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0780] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0781] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0782] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0783] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0784] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0785] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0786] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0787] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0788] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0789] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0790] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0791] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[0792] A natural language description of the program's processing

[0793] 1. Collecting traffic data

[0794] The server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, to provide up-to-date information on traffic conditions.

[0795] 2. Data Preprocessing

[0796] The server preprocesses the collected traffic data to remove noise and errors, preparing a clean dataset suitable for analysis.

[0797] 3. Data analysis using generative AI

[0798] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, and based on this, calculates the optimal departure time and route for each driver.

[0799] 4. Notification function

[0800] Based on the analysis results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[0801] 5. Accumulation and analysis of long-term traffic data

[0802] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it clear which areas are experiencing problems.

[0803] 6. Generate improvement suggestions

[0804] The server generates improvement proposals for identified chronic congestion points and sends them to the traffic management organization, and also proposes legal changes if necessary.

[0805] Specific examples

[0806] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0807] 1. The user sets a destination

[0808] The user sets the destination in the navigation app on their smartphone, and this information is sent to the server.

[0809] 2. The server collects traffic data

[0810] The server collects the latest traffic data for routes to the destination from various sensors and cameras.

[0811] 3. Data Preprocessing

[0812] The server filters the collected data to remove noise and errors.

[0813] 4. Analysis by generative AI

[0814] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[0815] 5. Notification function

[0816] The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[0817] 6. Long-term congestion analysis

[0818] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0819] 7. Generate improvement suggestions

[0820] Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to traffic management organizations.

[0821] In this way, the system according to the present invention provides drivers with optimal information in real time, contributing to the improvement of chronic traffic congestion.

[0822] The processing flow will be explained below.

[0823] Step 1:

[0824] The server collects traffic data in real time from data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[0825] Step 2:

[0826] The server filters the collected data, removing noise and errors to create a clean dataset suitable for analysis.

[0827] Step 3:

[0828] The server uses the generated AI to analyze the filtered data, predict traffic flow and congestion, and calculate the optimal departure time and route based on that.

[0829] Step 4:

[0830] The server sends the analysis results to the device, which then notifies the user's smartphone or car navigation system of the optimal departure time and route.

[0831] Step 5:

[0832] The user receives a notification and adjusts their departure plans according to the suggested departure time and route displayed on the device.

[0833] Step 6:

[0834] The server stores long-term traffic data. Data collected from traffic sensors and GPS devices is stored for long periods of time and analyzed to identify chronic congestion areas.

[0835] Step 7:

[0836] The server generates improvement proposals for the identified chronic congestion points and presents specific measures to the traffic management organization.

[0837] Step 8:

[0838] The server sends improvement proposals to traffic management organizations, such as adjusting traffic lights or adding lanes, to resolve congestion.

[0839] Example 1

[0840] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0841] Conventional traffic information systems have difficulty providing optimal departure times and routes in real time, and are not sufficient for long-term congestion analysis or improvement proposals. As a result, drivers are unable to obtain accurate information to avoid congestion and often end up stuck in it. There is also a lack of a means to make effective improvement proposals to traffic management organizations.

[0842] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0843] In this invention, the server includes means for collecting traffic data in real time from multiple data sources, means for preprocessing the collected traffic data and removing noise and errors, means for analyzing the preprocessed data using a generative AI model to predict traffic flow and congestion, means for notifying the driver of the optimal departure time and route based on the analysis results, means for accumulating long-term traffic data and identifying chronic congestion points, and means for generating improvement proposals for chronic congestion points and transmitting them to a traffic management organization. This allows drivers to obtain optimal traffic information in real time and make effective improvement proposals to the traffic management organization.

[0844] "Data Source" refers to any device or method by which traffic data can be collected, such as road traffic cameras, GPS devices, traffic sensors, or user reports.

[0845] "Preprocessing" refers to the process of removing noise and errors from collected data and preparing a clean dataset suitable for analysis.

[0846] A "generative AI model" refers to an algorithm or program that uses machine learning to learn from past traffic data and predict traffic flow and congestion based on current conditions.

[0847] "Analysis results" are the data obtained after analysis by the generative AI model, which includes information on optimal departure times and routes.

[0848] "Notification" is a means of transmitting information to the driver based on the analysis results, and is done using devices such as smartphones and car navigation systems.

[0849] "Chronic congestion spots" refer to specific locations or areas where congestion occurs frequently over the long term.

[0850] "Improvement proposals" refer to proposals that outline specific measures and countermeasures to resolve chronic congestion.

[0851] "Transportation Management Organization" means a public or private organization that supervises and manages transportation.

[0852] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. The system collects traffic data from data sources, preprocesses it, analyzes it using a generative AI model, and notifies the driver of the results. It also accumulates long-term traffic data and makes improvement suggestions for chronic congestion areas.

[0853] First, the server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. Specific data sources include road traffic cameras (high-resolution cameras), GPS devices (location information acquisition devices), and traffic sensors (traffic condition sensors).

[0854] The server then pre-processes the collected traffic data using data cleaning tools (e.g., "data processing software") to remove noise and errors, preparing a clean dataset suitable for analysis.

[0855] The pre-processed data is then analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms (e.g., a "machine learning engine") to predict traffic flow and congestion. The model learns from past data and calculates optimal departure times and routes for each driver based on current conditions.

[0856] The server then notifies the driver's device (e.g., a mobile information terminal or a car navigation system) of the optimal departure time and route based on the analysis results. This notification can be made using a push notification API (e.g., a messaging service).

[0857] The server also accumulates long-term traffic data and uses it to identify chronic congestion points. For this purpose, it stores the long-term data in a time-series database (e.g., a "data storage system") and periodically feeds this data into a machine learning model to analyze congestion trends at specific points.

[0858] Finally, the server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The improvement proposals are automatically generated using a generative AI model and then sent to the traffic management organization via email or API, allowing the traffic management organization to take appropriate measures.

[0859] For example, if a user is using a navigation app on their smartphone, the system works as follows:

[0860] 1. The user sets a destination in the navigation app on their smartphone. This information is sent to the server.

[0861] 2. The server collects the latest traffic data for the route to the destination from various sensors and cameras.

[0862] 3. The server filters the collected data to remove noise and errors.

[0863] 4. The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[0864] 5. The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[0865] 6. The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0866] 7. Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to the traffic management organization.

[0867] Example prompt sentence:

[0868] "My current location is in XX municipality in Tokyo, and my destination is in △△ municipality in Tokyo. Please tell me the best route and departure time, taking traffic congestion into consideration."

[0869] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0870] Step 1:

[0871] The server collects real-time traffic data from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. The server retrieves data from these sources through APIs and stores it as an initial dataset, providing up-to-date traffic information.

[0872] Step 2:

[0873] The server preprocesses the collected traffic data. The input is the initial dataset collected in step 1, and here noise and errors are removed. Specifically, data cleaning tools (e.g., data processing software) are used to impute missing values ​​and remove outliers. The output is a clean dataset, suitable for analysis.

[0874] Step 3:

[0875] The server's generative AI model analyzes the pre-processed data. The input is the clean dataset generated in step 2. Here, a generative AI model (e.g., a machine learning engine) is used to learn from past data and predict traffic flow and congestion based on current conditions. The output is the optimal departure time and route for each driver.

[0876] Step 4:

[0877] The server notifies the driver's device of the optimal departure time and route based on the analysis results. The input is the departure time and route information calculated in step 3. The server sends a message to the driver's device (smartphone, car navigation system, etc.) via a push notification API (e.g., messaging service). The output is a notification sent to the driver, suggesting the optimal action to avoid congestion.

[0878] Step 5:

[0879] The server accumulates long-term traffic data and identifies chronic congestion locations. The input is continuously collected traffic data. Specifically, the data is stored in a time-series database (e.g., a data storage system) and periodically input into a machine learning model to analyze congestion trends. The output is congestion trend data at specific locations.

[0880] Step 6:

[0881] The server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The input is the congestion trend data obtained in step 5. Specific improvement proposals are automatically generated using the generative AI model and sent to the traffic management organization via email or API. The output is the specific improvement proposals received by the traffic management organization.

[0882] (Application example 1)

[0883] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0884] In modern society, traffic congestion and traffic accidents have become commonplace problems, requiring efficient traffic management for drivers and traffic managers. However, current traffic management systems lack sufficient real-time traffic data analysis and proposals for optimal routes and departure times, and improvements are needed. Furthermore, long-term measures for chronic congestion in specific areas are insufficient, necessitating the development of efficient guidance for drivers and optimization of traffic flow. Furthermore, as autonomous vehicles become more widespread, the vehicles themselves will need to be equipped with advanced traffic analysis capabilities.

[0885] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0886] In this invention, the server includes: a means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; a means for collecting traffic information; a means for preprocessing the collected data; a means for notifying the driver based on the preprocessed data; a means for accumulating long-term traffic data and generating improvement proposals for chronic congestion points; a means for transmitting the generated improvement proposals to a traffic management organization; a means for collecting traffic information from sensors installed in the vehicle and external data sources; a means for performing data analysis using an in-vehicle edge AI computing unit; a means for notifying the vehicle's infotainment system of the calculated optimal route information; and a means for notifying the driver using voice guidance. This enables autonomous vehicles to obtain optimal traffic information in real time and provide efficient guidance to the driver. Furthermore, long-term data accumulation contributes to overall improvements in traffic management.

[0887] "Generative AI" refers to artificial intelligence technology that uses machine learning algorithms to analyze data and generate new information and predictions.

[0888] "Traffic data" refers to all information related to traffic, such as the flow of vehicles on roads, speed, location, traffic volume, and accident information.

[0889] "Driver" means a person who operates a motor vehicle or other means of transportation to travel to a destination.

[0890] "Departure time" means the time at which a driver begins traveling to a particular destination.

[0891] "Route" refers to the path from the starting point to the destination.

[0892] "Means" refers to methods, devices, techniques, etc. used to achieve a specific purpose.

[0893] "Traffic information" refers to information related to driving, such as current road conditions, congestion information, accident information, and road construction information.

[0894] "Collection" refers to the act or process of gathering the necessary data.

[0895] "Preprocessing" refers to processes that remove noise, clean, or transform raw data to make it easier to analyze.

[0896] "Notification" refers to the act of communicating important information to relevant parties.

[0897] "Storage" means collecting and storing data or information over a long period of time.

[0898] "Improvement proposal" refers to the act of presenting a specific plan to solve current problems.

[0899] "Traffic management organization" refers to a public agency or private organization that manages and supervises traffic flow and safety.

[0900] A "sensor" refers to a device that detects physical phenomena and outputs that information as an electrical signal.

[0901] An "external data source" is an information source that provides data obtained from outside the system.

[0902] An "edge AI computing unit" refers to a computing device that performs AI processing near the device without relying on the cloud.

[0903] "Infotainment system" refers to a system installed in a vehicle that provides information and entertainment functions.

[0904] "Voice guidance" refers to a function that conveys information to the driver using voice.

[0905] This invention is a system for autonomous vehicles that uses generative AI to analyze real-time traffic information and provide the driver with the optimal departure time and route. The system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[0906] 1. Collecting traffic data

[0907] The server collects real-time traffic information from sensors installed in vehicles and external data sources (public transportation databases, user-provided data, etc.), making it possible to instantly grasp the latest traffic conditions.

[0908] Sensors include LiDAR, cameras, and radar, while external data sources include V2X communication.

[0909] 2. Data Preprocessing

[0910] The server preprocesses the collected traffic data to remove noise and outliers, preparing a clean dataset suitable for analysis by generative AI.

[0911] In the pre-processing process, data processors such as NVIDIA's Jetson and Qualcomm's Snapdragon Automotive are used.

[0912] 3. Data analysis using generative AI

[0913] The server's edge AI computing unit uses pre-processed data to predict traffic flow and congestion, using a generative AI model such as GPT-4 or a custom version of it.

[0914] The generative AI model analyzes prompts given to it to calculate the optimal departure time and route for the driver. An example of a prompt is, "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..."

[0915] 4. Notification function

[0916] Based on the analysis results, the server notifies the driver's device (infotainment system, smartphone, etc.) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[0917] The vehicle's infotainment system includes visual displays and voice guidance, such as "Turn right at the next traffic light."

[0918] 5. Accumulation and analysis of long-term traffic data

[0919] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it possible to solve traffic problems in specific areas based on the data.

[0920] The accumulated data is stored in the cloud and organized in a way that is easy for traffic managers to access.

[0921] 6. Generate improvement suggestions

[0922] The server automatically generates and sends improvement proposals to traffic management organizations for identified chronic congestion points, and also proposes legal reforms if necessary.

[0923] For example, suggestions include "re-adjust the timing of the traffic lights at this intersection."

[0924] In this way, the system can provide drivers with optimal information in real time and improve overall traffic efficiency in the long term.

[0925] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0926] Step 1:

[0927] The server collects real-time traffic information from vehicle-mounted sensors (LiDAR, cameras, radar) and external data sources (V2X communication, public transport databases, user-provided data). The input includes real-time traffic data from each data source, and the output is the collected raw traffic data.

[0928] Step 2:

[0929] The server preprocesses the collected raw traffic data, which includes removing noise and outliers. The input is the raw data collected in step 1, and the output is clean traffic data with noise removed. Specifically, the data is filtered using a processor such as NVIDIA's Jetson or Qualcomm's Snapdragon Automotive.

[0930] Step 3:

[0931] The server's edge AI computing unit analyzes the preprocessed, cleaned traffic data using a generative AI model (e.g., GPT-4 or a custom version). The input is the cleaned data from step 2, and the prompt is "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..." The output is the optimal departure time and route.

[0932] Step 4:

[0933] The server notifies the driver's device (vehicle infotainment system, smartphone, etc.) based on the analysis results obtained from the generation AI. The input is the analysis results obtained in step 3, and the output is the optimal departure time and route information displayed on the driver's device. This includes visual displays and audio guidance.

[0934] Step 5:

[0935] The server stores long-term traffic data, including the real-time data acquired in steps 1 to 4. The input contains all traffic data collected over time, and the output is the accumulated historical traffic database.

[0936] Step 6:

[0937] The server identifies chronic congestion points based on the accumulated long-term traffic data and generates improvement proposals for the traffic management organization. The input is the historical traffic data accumulated in Step 5, and the output is the identified congestion points and their improvement proposals. A specific example is "Re-adjust the timing of the traffic lights at this intersection."

[0938] Step 7:

[0939] The server sends the generated improvement proposals to the traffic management organization via email or a dedicated management system. The input is the improvement proposal data obtained in step 6, and the output is the traffic management organization that received the improvement proposals.

[0940] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0941] This invention relates to a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[0942] A natural language description of the program's processing

[0943] 1. Collecting traffic data

[0944] The server collects real-time traffic information from various data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, allowing users to obtain the latest information on traffic conditions at all times.

[0945] 2. Data Preprocessing

[0946] The server preprocesses the collected traffic data to remove noise and errors, resulting in a clean dataset that improves the accuracy of the analysis.

[0947] 3. Data analysis using generative AI

[0948] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, allowing it to calculate optimal departure times and routes for drivers and provide customized information taking into account the individual needs of the driver.

[0949] 4. Emotion Recognition by Emotion Engine

[0950] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[0951] 5. Notification function

[0952] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[0953] 6. Accumulation and analysis of long-term traffic data

[0954] The server accumulates traffic data over time and identifies chronic congestion points, allowing for a clear understanding of problem areas.

[0955] 7. Generate improvement suggestions

[0956] The server generates improvement proposals for chronic congestion points based on the accumulated data and sends them to the traffic management organization. These proposals include specific measures.

[0957] 8. Proposals for legal reform

[0958] If necessary, the server will propose new legislative changes regarding the identified issues, which will also be sent to the traffic management organization.

[0959] Specific examples

[0960] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[0961] 1. The user sets a destination

[0962] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[0963] 2. The server collects traffic data

[0964] The server collects the latest traffic data around the destination from various sensors and cameras.

[0965] 3. Data Preprocessing

[0966] The server filters the collected data to remove noise and errors.

[0967] 4. Analysis by generative AI

[0968] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[0969] 5. Emotion Recognition by Emotion Engine

[0970] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[0971] 6. Notification function

[0972] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[0973] 7. Long-term congestion analysis

[0974] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[0975] 8. Generate improvement suggestions

[0976] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[0977] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[0978] The processing flow will be explained below.

[0979] Step 1:

[0980] The server collects traffic data from multiple data sources, including road traffic cameras, GPS devices, traffic sensors, and real-time reports from users, and accumulates up-to-date information on traffic conditions.

[0981] Step 2:

[0982] The server preprocesses the collected traffic data, filtering out noise and errors in the data to prepare a clean dataset suitable for analysis.

[0983] Step 3:

[0984] The server uses the generated AI to analyze the pre-processed data in real time, predicting traffic flow and congestion and calculating the optimal departure time and route for each driver.

[0985] Step 4:

[0986] The server uses an emotion engine to analyze the driver's emotional state based on data acquired from the user's smartphone and in-car camera. It analyzes facial expressions and voice data to evaluate stress levels and fatigue levels.

[0987] Step 5:

[0988] The server generates notifications based on the analysis results and data from the emotion engine, providing optimal departure times and routes, as well as messages and advice based on the driver's emotional state.

[0989] Step 6:

[0990] The server generates a notification and sends it to the user's device (smartphone or car navigation system). For example, it may say, "Delaying your departure time by 15 minutes will help you avoid traffic jams. Please relax and drive safely."

[0991] Step 7:

[0992] The user receives a notification, sees the departure time and route notification displayed on the device, and adjusts departure plans accordingly.

[0993] Step 8:

[0994] The server accumulates long-term traffic data and identifies chronic congestion points. Recurring congestion points are extracted from the data, and problem areas are clarified.

[0995] Step 9:

[0996] The server generates improvement proposals for identified chronic congestion areas, such as "re-adjusting traffic light timing" or "widening specific road sections."

[0997] Step 10:

[0998] The server generates and sends improvement proposals to the traffic management organization. The proposals are specific, actionable, and aimed at reducing traffic congestion, and may also include proposals for legal reform, if necessary.

[0999] Example 2

[1000] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1001] Traffic congestion and traffic accidents are serious issues in modern society. In particular, there is a need for real-time traffic information and appropriate route suggestions tailored to the needs of individual drivers. It is also important to provide information tailored to the emotional state of the driver and to improve chronic congestion areas through long-term data accumulation. However, there is currently no system that can solve these issues in one go.

[1002] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with an optimal departure time and route; means for collecting traffic information; means for preprocessing the collected traffic data; means for notifying the driver based on the preprocessed data; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; means for transmitting the generated improvement proposals to a traffic management organization; and means for providing information based on individual needs using an emotion engine that recognizes the driver's emotional state. This enables the server to propose optimal routes in real time, provide information according to the driver's emotional state, and propose long-term traffic improvements.

[1003] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and make predictions and generate results.

[1004] "Traffic data" refers to information relating to road traffic conditions such as vehicle speed, location information, traffic volume, and accident information.

[1005] A "driver" is a person who operates a vehicle and uses the system to travel to a destination.

[1006] The "departure time" is the optimum time for the driver to depart for the specified destination.

[1007] A "route" is the optimal path a driver takes to reach a destination.

[1008] "Traffic information" is information that includes data and events related to current traffic conditions.

[1009] "Preprocessing" is a data processing step to remove noise and errors from collected data and make it ready for analysis.

[1010] "Notification" is the process in which the server sends the analysis results to the user's terminal and displays them.

[1011] "Long-term traffic data" refers to data on traffic conditions that is accumulated over a certain period of time.

[1012] A "chronic congestion spot" is a traffic congestion spot that occurs repeatedly in a specific location.

[1013] An "improvement proposal" is a specific measure generated by the server to improve the traffic situation.

[1014] A "traffic management organization" is a public agency or organization that promotes road safety and traffic flow.

[1015] The "emotion engine" is a technology that recognizes the driver's emotional state by analyzing their facial expressions and voice data.

[1016] "Individual needs" are the unique conditions that correspond to each driver's particular requirements and expectations.

[1017] This invention is a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[1018] Specifically, the system is implemented in the following manner.

[1019] 1. Collecting traffic data

[1020] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports. For example, the server periodically calls an API to retrieve data from each data source. Data from GPS devices can be received in JSON format.

[1021] 2. Data Preprocessing

[1022] The server preprocesses the collected traffic data to remove noise and errors, including imputing missing values ​​and normalizing the data. Specifically, it uses Python libraries (e.g., pandas and NumPy) to clean up the collected data, excluding noisy data points and filtering out abnormal sensor data.

[1023] 3. Data analysis using generative AI

[1024] The server's generation AI analyzes the preprocessed data and predicts traffic flow and congestion, calculating the optimal departure time and route for the driver. For example, the generation AI trains a model using frameworks such as TensorFlow and PyTorch to predict the next day's traffic conditions based on past traffic patterns.

[1025] 4. Emotion Recognition by Emotion Engine

[1026] The server's emotion engine recognizes each driver's emotional state in real time. For example, it uses cameras and sensor devices to analyze the driver's facial expressions and voice data to assess their stress level and fatigue. This is achieved by using OpenCV and deep learning models for facial recognition and emotion analysis. For voice data, it uses speech recognition tools (e.g., Google Cloud Speech-to-Text API).

[1027] 5. Notification function

[1028] Based on the analysis results and the emotion recognition results of the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state. For example, a push notification service such as Firebase Cloud Messaging could be used to send a message to the smartphone such as "Please leave 10 minutes earlier as traffic congestion is expected."

[1029] 6. Accumulation and analysis of long-term traffic data

[1030] The server accumulates traffic data over the long term and identifies chronic congestion areas, allowing for a clear understanding of traffic problem areas. Specifically, a time-series database (e.g., InfluxDB) is used to store data from each sensor over the long term.

[1031] 7. Generate improvement suggestions

[1032] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization. For example, it automatically generates a proposal to "adjust traffic light timing" and sends it to the traffic management organization via API.

[1033] 8. Proposals for legal reform

[1034] If necessary, the server will propose new legal changes regarding the identified issues, which will also be included in the automatically generated report and communicated to the traffic management organization via email or a dedicated portal.

[1035] Specific examples

[1036] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[1037] 1. The user sets a destination

[1038] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[1039] 2. The server collects traffic data

[1040] The server collects the latest traffic data around the destination from various sensors and cameras.

[1041] 3. Data Preprocessing

[1042] The server filters the collected data to remove noise and errors.

[1043] 4. Analysis by generative AI

[1044] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[1045] 5. Emotion Recognition by Emotion Engine

[1046] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[1047] 6. Notification function

[1048] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[1049] 7. Long-term congestion analysis

[1050] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[1051] 8. Generate improvement suggestions

[1052] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[1053] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[1054] Example prompt sentence:

[1055] "Due to traffic congestion, please leave 10 minutes earlier."

[1056] "Take a deep breath and relax."

[1057] This allows drivers to travel more comfortably and efficiently.

[1058] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1059] Step 1:

[1060] Traffic data collection

[1061] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[1062] Input: Video data from road traffic cameras, location information from GPS devices, traffic sensor data, and traffic reports from users.

[1063] Output: Raw data (raw traffic information).

[1064] How it works: The server periodically calls the API to retrieve data from each data source. For example, data from a GPS device is received in JSON format, and video from a road traffic camera is received as stream data.

[1065] Step 2:

[1066] Data Preprocessing

[1067] The server preprocesses the collected traffic data to remove noise and errors, as well as impute missing values ​​and normalize the data.

[1068] Input: Raw data (raw traffic information).

[1069] Output: Clean data (data with noise and errors removed).

[1070] What it does: The server uses Python libraries (e.g., pandas, NumPy) to clean up the collected data. It filters out noisy data points and outliers from sensors. For example, it defines outliers as data outside a certain range and filters them out.

[1071] Step 3:

[1072] Data analysis with generative AI

[1073] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion.

[1074] Input: Clean data (data with noise and errors removed).

[1075] Output: Analysis results (optimal departure time and route, etc.).

[1076] How it works: Generative AI uses frameworks like TensorFlow and PyTorch to train models to predict the next day's traffic conditions based on past traffic patterns. The predictive models use neural networks and other machine learning algorithms.

[1077] Step 4:

[1078] Emotion recognition by emotion engine

[1079] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[1080] Input: Driver's facial expression data, voice data.

[1081] Output: Emotion recognition results (such as stress level and fatigue level).

[1082] How it works: The server uses OpenCV and deep learning models to perform facial recognition and emotion analysis. For voice data, it uses a speech recognition tool (e.g., Google Cloud Speech-to-Text API) to analyze it. For example, if a driver is tired, their emotional state is recognized as "fatigue."

[1083] Step 5:

[1084] Notification function

[1085] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[1086] Input: Analysis results (optimal departure time and route, etc.), emotion recognition results (stress level, fatigue level, etc.).

[1087] Output: Informational message.

[1088] What it does: The server uses a push notification service such as Firebase Cloud Messaging to send notifications to the smartphone. For example, a message saying, "Please leave 10 minutes early due to expected traffic congestion" is sent. If the driver is feeling stressed, advice such as "Take a deep breath and relax" is also sent.

[1089] Step 6:

[1090] Accumulation and analysis of long-term traffic data

[1091] The server accumulates traffic data over the long term and identifies areas with chronic congestion.

[1092] Input: Long-term traffic data.

[1093] Output: Traffic congestion analysis results.

[1094] How it works: The server uses a time-series database (e.g., InfluxDB) to store data from each sensor over time. It then runs queries to identify chronic congestion points. For example, if traffic volume at a particular intersection is high over a period of time, that point is considered a chronic congestion point.

[1095] Step 7:

[1096] Generate improvement suggestions

[1097] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization.

[1098] Input: Traffic congestion analysis results.

[1099] Output: Improvement proposals (specific measures).

[1100] How it works: The server uses the generation AI to automatically generate improvement proposals, such as adjusting traffic light timing. The proposals are automatically generated as a PDF report and sent to the traffic management organization via API.

[1101] Step 8:

[1102] Proposal for legal reform

[1103] The server will propose new legislative changes regarding identified issues, if necessary.

[1104] Input: Traffic congestion analysis results, improvement proposals.

[1105] Output: Proposed law change.

[1106] What it does: The server automatically generates reports containing proposed legal changes and notifies traffic management organizations via email or a dedicated portal, including proposals for new traffic regulations or infrastructure improvements.

[1107] (Application example 2)

[1108] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1109] Conventional traffic information systems have limited functionality in effectively analyzing real-time traffic data and providing drivers with optimal departure times and routes. Furthermore, they lacked the means to recognize the driver's emotional state and provide appropriate advice, which meant that they were unable to adequately reduce driver stress or support safe driving. Furthermore, they were unable to effectively propose and implement improvements to chronically congested areas through the accumulation and analysis of long-term traffic data. It is desirable to solve these problems and realize a more effective traffic information system.

[1110] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; means for collecting traffic information; means for preprocessing the collected data; means for notifying the driver based on the preprocessed data; emotion recognition means for recognizing the driver's emotional state and adjusting the content of the notification; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; and means for transmitting the generated improvement proposals to a traffic management organization. This not only enables the provision of real-time traffic information but also support according to the driver's emotional state, making it possible to effectively analyze long-term traffic problems and propose improvements.

[1111] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate new information from data and perform specific tasks.

[1112] "Traffic data" refers to information that indicates traffic conditions such as road congestion, vehicle flow, and traffic light timing.

[1113] "Driver" means a person who drives a motor vehicle.

[1114] "Departure time" refers to the time when you start driving to your destination.

[1115] A "route" is a path from a starting point to a destination.

[1116] "Traffic information" refers to data that indicates current and predicted road conditions and congestion levels.

[1117] "Data preprocessing" refers to the process of converting collected raw data into a form suitable for analysis.

[1118] "Notification" refers to the action of the system providing information to the driver.

[1119] "Emotional state" refers to the driver's psychological and physiological state, such as stress level and fatigue level.

[1120] "Emotion recognition means" refers to technology that analyzes the driver's facial expressions and voice to identify their emotional state.

[1121] "Chronic congestion spots" are specific roads or intersections where congestion frequently occurs.

[1122] "Improvement proposals" are specific measures or proposed changes to improve traffic conditions.

[1123] "Traffic management organization" means a public or private organization that manages road traffic and helps it operate smoothly.

[1124] This invention is a system that uses generative AI and an emotion engine to analyze traffic data in real time and provide drivers with optimal departure times and routes. This system includes traffic data collection, data preprocessing, data analysis using generative AI, emotion recognition, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions.

[1125] The server first collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, user reports, etc. Cloud infrastructure (e.g., Google Cloud Platform or Amazon Web Services) is used at this stage.

[1126] The server then pre-processes the collected traffic data to remove noise and errors, improving the accuracy of the analysis. This pre-processing includes data filtering techniques and generating a clean dataset.

[1127] The pre-processed data is then analyzed through a generative AI model (e.g., GPT-4), which predicts traffic flow and congestion, calculates optimal departure times and routes for drivers, and provides customized information that takes into account the individual needs of the driver.

[1128] The emotion engine uses the driver's camera and sensor devices to recognize the driver's emotional state in real time. For example, deep learning frameworks (e.g., TensorFlow and OpenCV) are used for facial recognition and voice analysis. Notification content is then tailored based on this emotional state.

[1129] Based on the analysis and emotion recognition results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is even more effective because it is adjusted taking into account the driver's emotional state. For example, if the driver is feeling stressed, the notification will include a message saying, "Take a deep breath and relax."

[1130] Long-term traffic data is stored on a server and used to identify chronic congestion points. Based on this data, concrete improvement proposals can be generated for traffic management organizations, and even legal reforms can be proposed if necessary.

[1131] A concrete example would be a scenario where a user sets a destination and if their current stress level is high, the prompt "Relax" is displayed. For example, if a driver sets Tokyo Station as their destination in a smartphone navigation app, the following prompt sentence is used:

[1132] gps_data = GPSSensor().get_data(destination="Tokyo Station")

[1133] In this way, the system of the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[1134] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1135] Step 1:

[1136] The server collects traffic data. The input is real-time data from road traffic cameras, GPS devices, traffic sensors, and user reports. The output is a set of collected raw data. This step includes, for example, obtaining location information from GPS devices and image data from cameras.

[1137] Step 2:

[1138] The server preprocesses the collected data. The input is the raw data collected in step 1. The output is a cleaned dataset with noise and errors removed. In this step, data cleansing such as data filtering and outlier removal is performed. Specifically, image processing algorithms are applied to image data, and location information is corrected for GPS data.

[1139] Step 3:

[1140] The server inputs the preprocessed data into a generative AI to analyze the optimal departure time and route. The input is cleaned traffic data. The output is optimal departure time and route information to provide to the driver. In this step, for example, a generative AI model (GPT-4) is used to analyze multiple data points to perform congestion prediction and time route optimization. The generative AI model analyzes traffic patterns and congestion trends and generates predictions.

[1141] Step 4:

[1142] The server uses an emotion engine to recognize the driver's emotional state. The input is the driver's camera and audio data. The output is the driver's emotional state (e.g., stress level and fatigue level). In this step, a deep learning framework (TensorFlow or OpenCV) is used to perform facial recognition and audio analysis to identify the driver's emotional state. Specifically, the server determines the driver's emotion by detecting changes in facial expression from the driver's facial image and analyzing the tone and speed of voice from the audio.

[1143] Step 5:

[1144] Based on the analysis results and emotion recognition results, the server notifies the driver of the optimal departure time and route, as well as advice based on the driver's emotional state. The input is the optimized departure time, route, and the driver's emotional state. The output is a notification message to be displayed on the driver's smartphone or car navigation system. In this step, the notification system is used to send advice based on the calculated information and emotions to the driver's device. For example, messages such as "The optimal departure time is 8:30. There is no traffic jam at the moment" or "Relax. The next rest stop is 20 km away" are displayed.

[1145] Step 6:

[1146] The server accumulates and analyzes long-term traffic data. The input is traffic data collected daily. The output is the analysis results on chronic congestion points. In this step, the collected past data is stored in a database and statistical analysis is performed. For example, it identifies which days of the week and at what times of day a particular road is prone to congestion.

[1147] Step 7:

[1148] The server generates improvement proposals based on the accumulated data and sends them to the traffic management organization. The input is the long-term traffic analysis results. The output is a specific improvement proposal. In this step, improvement proposals are generated, including, for example, signal timing adjustments and road widening proposals, and are sent to the traffic management organization via email or a dedicated management system.

[1149] This will not only provide real-time traffic information, but also support tailored to the driver's emotional state, as well as analyze and propose improvements to long-term traffic problems.

[1150] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1151] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1152] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1153] [Fourth embodiment]

[1154] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1155] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1157] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1158] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1161] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1162] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1163] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1165] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1166] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1167] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[1168] A natural language description of the program's processing

[1169] 1. Collecting traffic data

[1170] The server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, to provide up-to-date information on traffic conditions.

[1171] 2. Data Preprocessing

[1172] The server preprocesses the collected traffic data to remove noise and errors, preparing a clean dataset suitable for analysis.

[1173] 3. Data analysis using generative AI

[1174] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, and based on this, calculates the optimal departure time and route for each driver.

[1175] 4. Notification function

[1176] Based on the analysis results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[1177] 5. Accumulation and analysis of long-term traffic data

[1178] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it clear which areas are experiencing problems.

[1179] 6. Generate improvement suggestions

[1180] The server generates improvement proposals for identified chronic congestion points and sends them to the traffic management organization, and also proposes legal changes if necessary.

[1181] Specific examples

[1182] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[1183] 1. The user sets a destination

[1184] The user sets the destination in the navigation app on their smartphone, and this information is sent to the server.

[1185] 2. The server collects traffic data

[1186] The server collects the latest traffic data for routes to the destination from various sensors and cameras.

[1187] 3. Data Preprocessing

[1188] The server filters the collected data to remove noise and errors.

[1189] 4. Analysis by generative AI

[1190] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[1191] 5. Notification function

[1192] The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[1193] 6. Long-term congestion analysis

[1194] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[1195] 7. Generate improvement suggestions

[1196] Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to traffic management organizations.

[1197] In this way, the system according to the present invention provides drivers with optimal information in real time, contributing to the improvement of chronic traffic congestion.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The server collects traffic data in real time from data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[1201] Step 2:

[1202] The server filters the collected data, removing noise and errors to create a clean dataset suitable for analysis.

[1203] Step 3:

[1204] The server uses the generated AI to analyze the filtered data, predict traffic flow and congestion, and calculate the optimal departure time and route based on that.

[1205] Step 4:

[1206] The server sends the analysis results to the device, which then notifies the user's smartphone or car navigation system of the optimal departure time and route.

[1207] Step 5:

[1208] The user receives a notification and adjusts their departure plans according to the suggested departure time and route displayed on the device.

[1209] Step 6:

[1210] The server stores long-term traffic data. Data collected from traffic sensors and GPS devices is stored for long periods of time and analyzed to identify chronic congestion areas.

[1211] Step 7:

[1212] The server generates improvement proposals for the identified chronic congestion points and presents specific measures to the traffic management organization.

[1213] Step 8:

[1214] The server sends improvement proposals to traffic management organizations, such as adjusting traffic lights or adding lanes, to resolve congestion.

[1215] Example 1

[1216] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1217] Conventional traffic information systems have difficulty providing optimal departure times and routes in real time, and are not sufficient for long-term congestion analysis or improvement proposals. As a result, drivers are unable to obtain accurate information to avoid congestion and often end up stuck in it. There is also a lack of a means to make effective improvement proposals to traffic management organizations.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1219] In this invention, the server includes means for collecting traffic data in real time from multiple data sources, means for preprocessing the collected traffic data and removing noise and errors, means for analyzing the preprocessed data using a generative AI model to predict traffic flow and congestion, means for notifying the driver of the optimal departure time and route based on the analysis results, means for accumulating long-term traffic data and identifying chronic congestion points, and means for generating improvement proposals for chronic congestion points and transmitting them to a traffic management organization. This allows drivers to obtain optimal traffic information in real time and make effective improvement proposals to the traffic management organization.

[1220] "Data Source" refers to any device or method by which traffic data can be collected, such as road traffic cameras, GPS devices, traffic sensors, or user reports.

[1221] "Preprocessing" refers to the process of removing noise and errors from collected data and preparing a clean dataset suitable for analysis.

[1222] A "generative AI model" refers to an algorithm or program that uses machine learning to learn from past traffic data and predict traffic flow and congestion based on current conditions.

[1223] "Analysis results" are the data obtained after analysis by the generative AI model, which includes information on optimal departure times and routes.

[1224] "Notification" is a means of transmitting information to the driver based on the analysis results, and is done using devices such as smartphones and car navigation systems.

[1225] "Chronic congestion spots" refer to specific locations or areas where congestion occurs frequently over the long term.

[1226] "Improvement proposals" refer to proposals that outline specific measures and countermeasures to resolve chronic congestion.

[1227] "Transportation Management Organization" means a public or private organization that supervises and manages transportation.

[1228] This invention relates to a system that uses generative AI to analyze real-time traffic information and provide drivers with optimal departure times and routes. The system collects traffic data from data sources, preprocesses it, analyzes it using a generative AI model, and notifies the driver of the results. It also accumulates long-term traffic data and makes improvement suggestions for chronic congestion areas.

[1229] First, the server collects real-time traffic information from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. Specific data sources include road traffic cameras (high-resolution cameras), GPS devices (location information acquisition devices), and traffic sensors (traffic condition sensors).

[1230] The server then pre-processes the collected traffic data using data cleaning tools (e.g., "data processing software") to remove noise and errors, preparing a clean dataset suitable for analysis.

[1231] The pre-processed data is then analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms (e.g., a "machine learning engine") to predict traffic flow and congestion. The model learns from past data and calculates optimal departure times and routes for each driver based on current conditions.

[1232] The server then notifies the driver's device (e.g., a mobile information terminal or a car navigation system) of the optimal departure time and route based on the analysis results. This notification can be made using a push notification API (e.g., a messaging service).

[1233] The server also accumulates long-term traffic data and uses it to identify chronic congestion points. For this purpose, it stores the long-term data in a time-series database (e.g., a "data storage system") and periodically feeds this data into a machine learning model to analyze congestion trends at specific points.

[1234] Finally, the server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The improvement proposals are automatically generated using a generative AI model and then sent to the traffic management organization via email or API, allowing the traffic management organization to take appropriate measures.

[1235] For example, if a user is using a navigation app on their smartphone, the system works as follows:

[1236] 1. The user sets a destination in the navigation app on their smartphone. This information is sent to the server.

[1237] 2. The server collects the latest traffic data for the route to the destination from various sensors and cameras.

[1238] 3. The server filters the collected data to remove noise and errors.

[1239] 4. The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time to avoid traffic jams.

[1240] 5. The server notifies the user of the calculated results on their smartphone. For example, a message such as "You can avoid traffic jams by delaying your current departure time by 15 minutes" is displayed.

[1241] 6. The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[1242] 7. Based on long-term data, the server automatically generates and sends improvement suggestions, such as "adjusting traffic light timing," to the traffic management organization.

[1243] Example prompt sentence:

[1244] "My current location is in XX municipality in Tokyo, and my destination is in △△ municipality in Tokyo. Please tell me the best route and departure time, taking traffic congestion into consideration."

[1245] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] The server collects real-time traffic data from multiple data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports. The server retrieves data from these sources through APIs and stores it as an initial dataset, providing up-to-date traffic information.

[1248] Step 2:

[1249] The server preprocesses the collected traffic data. The input is the initial dataset collected in step 1, and here noise and errors are removed. Specifically, data cleaning tools (e.g., data processing software) are used to impute missing values ​​and remove outliers. The output is a clean dataset, suitable for analysis.

[1250] Step 3:

[1251] The server's generative AI model analyzes the pre-processed data. The input is the clean dataset generated in step 2. Here, a generative AI model (e.g., a machine learning engine) is used to learn from past data and predict traffic flow and congestion based on current conditions. The output is the optimal departure time and route for each driver.

[1252] Step 4:

[1253] The server notifies the driver's device of the optimal departure time and route based on the analysis results. The input is the departure time and route information calculated in step 3. The server sends a message to the driver's device (smartphone, car navigation system, etc.) via a push notification API (e.g., messaging service). The output is a notification sent to the driver, suggesting the optimal action to avoid congestion.

[1254] Step 5:

[1255] The server accumulates long-term traffic data and identifies chronic congestion locations. The input is continuously collected traffic data. Specifically, the data is stored in a time-series database (e.g., a data storage system) and periodically input into a machine learning model to analyze congestion trends. The output is congestion trend data at specific locations.

[1256] Step 6:

[1257] The server generates improvement proposals for chronic congestion points and sends them to the traffic management organization. The input is the congestion trend data obtained in step 5. Specific improvement proposals are automatically generated using the generative AI model and sent to the traffic management organization via email or API. The output is the specific improvement proposals received by the traffic management organization.

[1258] (Application example 1)

[1259] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1260] In modern society, traffic congestion and traffic accidents have become commonplace problems, requiring efficient traffic management for drivers and traffic managers. However, current traffic management systems lack sufficient real-time traffic data analysis and proposals for optimal routes and departure times, and improvements are needed. Furthermore, long-term measures for chronic congestion in specific areas are insufficient, necessitating the development of efficient guidance for drivers and optimization of traffic flow. Furthermore, as autonomous vehicles become more widespread, the vehicles themselves will need to be equipped with advanced traffic analysis capabilities.

[1261] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1262] In this invention, the server includes: a means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; a means for collecting traffic information; a means for preprocessing the collected data; a means for notifying the driver based on the preprocessed data; a means for accumulating long-term traffic data and generating improvement proposals for chronic congestion points; a means for transmitting the generated improvement proposals to a traffic management organization; a means for collecting traffic information from sensors installed in the vehicle and external data sources; a means for performing data analysis using an in-vehicle edge AI computing unit; a means for notifying the vehicle's infotainment system of the calculated optimal route information; and a means for notifying the driver using voice guidance. This enables autonomous vehicles to obtain optimal traffic information in real time and provide efficient guidance to the driver. Furthermore, long-term data accumulation contributes to overall improvements in traffic management.

[1263] "Generative AI" refers to artificial intelligence technology that uses machine learning algorithms to analyze data and generate new information and predictions.

[1264] "Traffic data" refers to all information related to traffic, such as the flow of vehicles on roads, speed, location, traffic volume, and accident information.

[1265] "Driver" means a person who operates a motor vehicle or other means of transportation to travel to a destination.

[1266] "Departure time" means the time at which a driver begins traveling to a particular destination.

[1267] "Route" refers to the path from the starting point to the destination.

[1268] "Means" refers to methods, devices, techniques, etc. used to achieve a specific purpose.

[1269] "Traffic information" refers to information related to driving, such as current road conditions, congestion information, accident information, and road construction information.

[1270] "Collection" refers to the act or process of gathering the necessary data.

[1271] "Preprocessing" refers to processes that remove noise, clean, or transform raw data to make it easier to analyze.

[1272] "Notification" refers to the act of communicating important information to relevant parties.

[1273] "Storage" means collecting and storing data or information over a long period of time.

[1274] "Improvement proposal" refers to the act of presenting a specific plan to solve current problems.

[1275] "Traffic management organization" refers to a public agency or private organization that manages and supervises traffic flow and safety.

[1276] A "sensor" refers to a device that detects physical phenomena and outputs that information as an electrical signal.

[1277] An "external data source" is an information source that provides data obtained from outside the system.

[1278] An "edge AI computing unit" refers to a computing device that performs AI processing near the device without relying on the cloud.

[1279] "Infotainment system" refers to a system installed in a vehicle that provides information and entertainment functions.

[1280] "Voice guidance" refers to a function that conveys information to the driver using voice.

[1281] This invention is a system for autonomous vehicles that uses generative AI to analyze real-time traffic information and provide the driver with the optimal departure time and route. The system consists of traffic data collection, data preprocessing, data analysis by generative AI, notification function, long-term traffic data accumulation and analysis, and generation of improvement proposals.

[1282] 1. Collecting traffic data

[1283] The server collects real-time traffic information from sensors installed in vehicles and external data sources (public transportation databases, user-provided data, etc.), making it possible to instantly grasp the latest traffic conditions.

[1284] Sensors include LiDAR, cameras, and radar, while external data sources include V2X communication.

[1285] 2. Data Preprocessing

[1286] The server preprocesses the collected traffic data to remove noise and outliers, preparing a clean dataset suitable for analysis by generative AI.

[1287] In the pre-processing process, data processors such as NVIDIA's Jetson and Qualcomm's Snapdragon Automotive are used.

[1288] 3. Data analysis using generative AI

[1289] The server's edge AI computing unit uses pre-processed data to predict traffic flow and congestion, using a generative AI model such as GPT-4 or a custom version of it.

[1290] The generative AI model analyzes prompts given to it to calculate the optimal departure time and route for the driver. An example of a prompt is, "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..."

[1291] 4. Notification function

[1292] Based on the analysis results, the server notifies the driver's device (infotainment system, smartphone, etc.) of the optimal departure time and route, allowing the driver to avoid traffic jams and reach their destination efficiently.

[1293] The vehicle's infotainment system includes visual displays and voice guidance, such as "Turn right at the next traffic light."

[1294] 5. Accumulation and analysis of long-term traffic data

[1295] The server accumulates traffic data over the long term and identifies chronic congestion areas, making it possible to solve traffic problems in specific areas based on the data.

[1296] The accumulated data is stored in the cloud and organized in a way that is easy for traffic managers to access.

[1297] 6. Generate improvement suggestions

[1298] The server automatically generates and sends improvement proposals to traffic management organizations for identified chronic congestion points, and also proposes legal reforms if necessary.

[1299] For example, suggestions include "re-adjust the timing of the traffic lights at this intersection."

[1300] In this way, the system can provide drivers with optimal information in real time and improve overall traffic efficiency in the long term.

[1301] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1302] Step 1:

[1303] The server collects real-time traffic information from vehicle-mounted sensors (LiDAR, cameras, radar) and external data sources (V2X communication, public transport databases, user-provided data). The input includes real-time traffic data from each data source, and the output is the collected raw traffic data.

[1304] Step 2:

[1305] The server preprocesses the collected raw traffic data, which includes removing noise and outliers. The input is the raw data collected in step 1, and the output is clean traffic data with noise removed. Specifically, the data is filtered using a processor such as NVIDIA's Jetson or Qualcomm's Snapdragon Automotive.

[1306] Step 3:

[1307] The server's edge AI computing unit analyzes the preprocessed, cleaned traffic data using a generative AI model (e.g., GPT-4 or a custom version). The input is the cleaned data from step 2, and the prompt is "Predict the optimal route from departure point A to destination B. Current real-time traffic data is as follows..." The output is the optimal departure time and route.

[1308] Step 4:

[1309] The server notifies the driver's device (vehicle infotainment system, smartphone, etc.) based on the analysis results obtained from the generation AI. The input is the analysis results obtained in step 3, and the output is the optimal departure time and route information displayed on the driver's device. This includes visual displays and audio guidance.

[1310] Step 5:

[1311] The server stores long-term traffic data, including the real-time data acquired in steps 1 to 4. The input contains all traffic data collected over time, and the output is the accumulated historical traffic database.

[1312] Step 6:

[1313] The server identifies chronic congestion points based on the accumulated long-term traffic data and generates improvement proposals for the traffic management organization. The input is the historical traffic data accumulated in Step 5, and the output is the identified congestion points and their improvement proposals. A specific example is "Re-adjust the timing of the traffic lights at this intersection."

[1314] Step 7:

[1315] The server sends the generated improvement proposals to the traffic management organization via email or a dedicated management system. The input is the improvement proposal data obtained in step 6, and the output is the traffic management organization that received the improvement proposals.

[1316] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1317] This invention relates to a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[1318] A natural language description of the program's processing

[1319] 1. Collecting traffic data

[1320] The server collects real-time traffic information from various data sources, such as road traffic cameras, GPS devices, traffic sensors, and user reports, allowing users to obtain the latest information on traffic conditions at all times.

[1321] 2. Data Preprocessing

[1322] The server preprocesses the collected traffic data to remove noise and errors, resulting in a clean dataset that improves the accuracy of the analysis.

[1323] 3. Data analysis using generative AI

[1324] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion, allowing it to calculate optimal departure times and routes for drivers and provide customized information taking into account the individual needs of the driver.

[1325] 4. Emotion Recognition by Emotion Engine

[1326] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[1327] 5. Notification function

[1328] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[1329] 6. Accumulation and analysis of long-term traffic data

[1330] The server accumulates traffic data over time and identifies chronic congestion points, allowing for a clear understanding of problem areas.

[1331] 7. Generate improvement suggestions

[1332] The server generates improvement proposals for chronic congestion points based on the accumulated data and sends them to the traffic management organization. These proposals include specific measures.

[1333] 8. Proposals for legal reform

[1334] If necessary, the server will propose new legislative changes regarding the identified issues, which will also be sent to the traffic management organization.

[1335] Specific examples

[1336] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[1337] 1. The user sets a destination

[1338] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[1339] 2. The server collects traffic data

[1340] The server collects the latest traffic data around the destination from various sensors and cameras.

[1341] 3. Data Preprocessing

[1342] The server filters the collected data to remove noise and errors.

[1343] 4. Analysis by generative AI

[1344] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[1345] 5. Emotion Recognition by Emotion Engine

[1346] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[1347] 6. Notification function

[1348] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[1349] 7. Long-term congestion analysis

[1350] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[1351] 8. Generate improvement suggestions

[1352] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[1353] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[1354] The processing flow will be explained below.

[1355] Step 1:

[1356] The server collects traffic data from multiple data sources, including road traffic cameras, GPS devices, traffic sensors, and real-time reports from users, and accumulates up-to-date information on traffic conditions.

[1357] Step 2:

[1358] The server preprocesses the collected traffic data, filtering out noise and errors in the data to prepare a clean dataset suitable for analysis.

[1359] Step 3:

[1360] The server uses the generated AI to analyze the pre-processed data in real time, predicting traffic flow and congestion and calculating the optimal departure time and route for each driver.

[1361] Step 4:

[1362] The server uses an emotion engine to analyze the driver's emotional state based on data acquired from the user's smartphone and in-car camera. It analyzes facial expressions and voice data to evaluate stress levels and fatigue levels.

[1363] Step 5:

[1364] The server generates notifications based on the analysis results and data from the emotion engine, providing optimal departure times and routes, as well as messages and advice based on the driver's emotional state.

[1365] Step 6:

[1366] The server generates a notification and sends it to the user's device (smartphone or car navigation system). For example, it may say, "Delaying your departure time by 15 minutes will help you avoid traffic jams. Please relax and drive safely."

[1367] Step 7:

[1368] The user receives a notification, sees the departure time and route notification displayed on the device, and adjusts departure plans accordingly.

[1369] Step 8:

[1370] The server accumulates long-term traffic data and identifies chronic congestion points. Recurring congestion points are extracted from the data, and problem areas are clarified.

[1371] Step 9:

[1372] The server generates improvement proposals for identified chronic congestion areas, such as "re-adjusting traffic light timing" or "widening specific road sections."

[1373] Step 10:

[1374] The server generates and sends improvement proposals to the traffic management organization. The proposals are specific, actionable, and aimed at reducing traffic congestion, and may also include proposals for legal reform, if necessary.

[1375] Example 2

[1376] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1377] Traffic congestion and traffic accidents are serious issues in modern society. In particular, there is a need for real-time traffic information and appropriate route suggestions tailored to the needs of individual drivers. It is also important to provide information tailored to the emotional state of the driver and to improve chronic congestion areas through long-term data accumulation. However, there is currently no system that can solve these issues in one go.

[1378] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with an optimal departure time and route; means for collecting traffic information; means for preprocessing the collected traffic data; means for notifying the driver based on the preprocessed data; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; means for transmitting the generated improvement proposals to a traffic management organization; and means for providing information based on individual needs using an emotion engine that recognizes the driver's emotional state. This enables the server to propose optimal routes in real time, provide information according to the driver's emotional state, and propose long-term traffic improvements.

[1379] "Generative AI" is artificial intelligence that uses machine learning and deep learning technologies to analyze data and make predictions and generate results.

[1380] "Traffic data" refers to information relating to road traffic conditions such as vehicle speed, location information, traffic volume, and accident information.

[1381] A "driver" is a person who operates a vehicle and uses the system to travel to a destination.

[1382] The "departure time" is the optimum time for the driver to depart for the specified destination.

[1383] A "route" is the optimal path a driver takes to reach a destination.

[1384] "Traffic information" is information that includes data and events related to current traffic conditions.

[1385] "Preprocessing" is a data processing step to remove noise and errors from collected data and make it ready for analysis.

[1386] "Notification" is the process in which the server sends the analysis results to the user's terminal and displays them.

[1387] "Long-term traffic data" refers to data on traffic conditions that is accumulated over a certain period of time.

[1388] A "chronic congestion spot" is a traffic congestion spot that occurs repeatedly in a specific location.

[1389] An "improvement proposal" is a specific measure generated by the server to improve the traffic situation.

[1390] A "traffic management organization" is a public agency or organization that promotes road safety and traffic flow.

[1391] The "emotion engine" is a technology that recognizes the driver's emotional state by analyzing their facial expressions and voice data.

[1392] "Individual needs" are the unique conditions that correspond to each driver's particular requirements and expectations.

[1393] This invention is a system that uses generative AI and an emotion engine to analyze real-time traffic information and provide drivers with optimal departure times and routes. This system combines traffic data collection, data preprocessing, data analysis using generative AI, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions, as well as an emotion engine that recognizes the driver's emotions, to provide information tailored to the driver's emotional state.

[1394] Specifically, the system is implemented in the following manner.

[1395] 1. Collecting traffic data

[1396] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports. For example, the server periodically calls an API to retrieve data from each data source. Data from GPS devices can be received in JSON format.

[1397] 2. Data Preprocessing

[1398] The server preprocesses the collected traffic data to remove noise and errors, including imputing missing values ​​and normalizing the data. Specifically, it uses Python libraries (e.g., pandas and NumPy) to clean up the collected data, excluding noisy data points and filtering out abnormal sensor data.

[1399] 3. Data analysis using generative AI

[1400] The server's generation AI analyzes the preprocessed data and predicts traffic flow and congestion, calculating the optimal departure time and route for the driver. For example, the generation AI trains a model using frameworks such as TensorFlow and PyTorch to predict the next day's traffic conditions based on past traffic patterns.

[1401] 4. Emotion Recognition by Emotion Engine

[1402] The server's emotion engine recognizes each driver's emotional state in real time. For example, it uses cameras and sensor devices to analyze the driver's facial expressions and voice data to assess their stress level and fatigue. This is achieved by using OpenCV and deep learning models for facial recognition and emotion analysis. For voice data, it uses speech recognition tools (e.g., Google Cloud Speech-to-Text API).

[1403] 5. Notification function

[1404] Based on the analysis results and the emotion recognition results of the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state. For example, a push notification service such as Firebase Cloud Messaging could be used to send a message to the smartphone such as "Please leave 10 minutes earlier as traffic congestion is expected."

[1405] 6. Accumulation and analysis of long-term traffic data

[1406] The server accumulates traffic data over the long term and identifies chronic congestion areas, allowing for a clear understanding of traffic problem areas. Specifically, a time-series database (e.g., InfluxDB) is used to store data from each sensor over the long term.

[1407] 7. Generate improvement suggestions

[1408] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization. For example, it automatically generates a proposal to "adjust traffic light timing" and sends it to the traffic management organization via API.

[1409] 8. Proposals for legal reform

[1410] If necessary, the server will propose new legal changes regarding the identified issues, which will also be included in the automatically generated report and communicated to the traffic management organization via email or a dedicated portal.

[1411] Specific examples

[1412] For example, if a user is using a navigation app on their smartphone, the system operates as follows:

[1413] 1. The user sets a destination

[1414] The user sets a destination in the navigation app on their smartphone, which sends information about the destination to the server.

[1415] 2. The server collects traffic data

[1416] The server collects the latest traffic data around the destination from various sensors and cameras.

[1417] 3. Data Preprocessing

[1418] The server filters the collected data to remove noise and errors.

[1419] 4. Analysis by generative AI

[1420] The server's generation AI analyzes the pre-processed data and calculates the optimal route and departure time, and also makes appropriate suggestions taking into account the fact that drivers are busy in the morning.

[1421] 5. Emotion Recognition by Emotion Engine

[1422] The server's emotion engine analyzes the driver's emotional state in real time via the user's smartphone or in-car camera, detecting, for example, when the driver is feeling stressed.

[1423] 6. Notification function

[1424] The server notifies drivers of the optimal departure time and route, as well as providing advice on how to relax for drivers with high stress levels, such as "Take a deep breath and relax."

[1425] 7. Long-term congestion analysis

[1426] The server accumulates chronic congestion data at specific locations over the long term and analyzes it.

[1427] 8. Generate improvement suggestions

[1428] Based on long-term data, the server automatically generates improvement proposals to traffic management organizations, sending suggestions such as "adjusting traffic light timing."

[1429] In this way, the system according to the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[1430] Example prompt sentence:

[1431] "Due to traffic congestion, please leave 10 minutes earlier."

[1432] "Take a deep breath and relax."

[1433] This allows drivers to travel more comfortably and efficiently.

[1434] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1435] Step 1:

[1436] Traffic data collection

[1437] The server collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, and user reports.

[1438] Input: Video data from road traffic cameras, location information from GPS devices, traffic sensor data, and traffic reports from users.

[1439] Output: Raw data (raw traffic information).

[1440] How it works: The server periodically calls the API to retrieve data from each data source. For example, data from a GPS device is received in JSON format, and video from a road traffic camera is received as stream data.

[1441] Step 2:

[1442] Data Preprocessing

[1443] The server preprocesses the collected traffic data to remove noise and errors, as well as impute missing values ​​and normalize the data.

[1444] Input: Raw data (raw traffic information).

[1445] Output: Clean data (data with noise and errors removed).

[1446] What it does: The server uses Python libraries (e.g., pandas, NumPy) to clean up the collected data. It filters out noisy data points and outliers from sensors. For example, it defines outliers as data outside a certain range and filters them out.

[1447] Step 3:

[1448] Data analysis with generative AI

[1449] The server's generation AI analyzes the pre-processed data and predicts traffic flow and congestion.

[1450] Input: Clean data (data with noise and errors removed).

[1451] Output: Analysis results (optimal departure time and route, etc.).

[1452] How it works: Generative AI uses frameworks like TensorFlow and PyTorch to train models to predict the next day's traffic conditions based on past traffic patterns. The predictive models use neural networks and other machine learning algorithms.

[1453] Step 4:

[1454] Emotion recognition by emotion engine

[1455] The server's emotion engine recognizes each driver's emotional state in real time, for example, by analyzing the driver's facial expressions and voice data using cameras and sensor devices to assess their stress level and fatigue.

[1456] Input: Driver's facial expression data, voice data.

[1457] Output: Emotion recognition results (such as stress level and fatigue level).

[1458] How it works: The server uses OpenCV and deep learning models to perform facial recognition and emotion analysis. For voice data, it uses a speech recognition tool (e.g., Google Cloud Speech-to-Text API) to analyze it. For example, if a driver is tired, their emotional state is recognized as "fatigue."

[1459] Step 5:

[1460] Notification function

[1461] Based on the analysis results and emotion recognition results from the emotion engine, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is adjusted taking into account the driver's emotional state.

[1462] Input: Analysis results (optimal departure time and route, etc.), emotion recognition results (stress level, fatigue level, etc.).

[1463] Output: Informational message.

[1464] What it does: The server uses a push notification service such as Firebase Cloud Messaging to send notifications to the smartphone. For example, a message saying, "Please leave 10 minutes early due to expected traffic congestion" is sent. If the driver is feeling stressed, advice such as "Take a deep breath and relax" is also sent.

[1465] Step 6:

[1466] Accumulation and analysis of long-term traffic data

[1467] The server accumulates traffic data over the long term and identifies areas with chronic congestion.

[1468] Input: Long-term traffic data.

[1469] Output: Traffic congestion analysis results.

[1470] How it works: The server uses a time-series database (e.g., InfluxDB) to store data from each sensor over time. It then runs queries to identify chronic congestion points. For example, if traffic volume at a particular intersection is high over a period of time, that point is considered a chronic congestion point.

[1471] Step 7:

[1472] Generate improvement suggestions

[1473] The server generates improvement proposals for chronic congestion areas based on the accumulated data and sends them to the traffic management organization.

[1474] Input: Traffic congestion analysis results.

[1475] Output: Improvement proposals (specific measures).

[1476] How it works: The server uses the generation AI to automatically generate improvement proposals, such as adjusting traffic light timing. The proposals are automatically generated as a PDF report and sent to the traffic management organization via API.

[1477] Step 8:

[1478] Proposal for legal reform

[1479] The server will propose new legislative changes regarding identified issues, if necessary.

[1480] Input: Traffic congestion analysis results, improvement proposals.

[1481] Output: Proposed law change.

[1482] What it does: The server automatically generates reports containing proposed legal changes and notifies traffic management organizations via email or a dedicated portal, including proposals for new traffic regulations or infrastructure improvements.

[1483] (Application example 2)

[1484] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1485] Conventional traffic information systems have limited functionality in effectively analyzing real-time traffic data and providing drivers with optimal departure times and routes. Furthermore, they lacked the means to recognize the driver's emotional state and provide appropriate advice, which meant that they were unable to adequately reduce driver stress or support safe driving. Furthermore, they were unable to effectively propose and implement improvements to chronically congested areas through the accumulation and analysis of long-term traffic data. It is desirable to solve these problems and realize a more effective traffic information system.

[1486] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for analyzing traffic data in real time using a generation AI and providing the driver with the optimal departure time and route; means for collecting traffic information; means for preprocessing the collected data; means for notifying the driver based on the preprocessed data; emotion recognition means for recognizing the driver's emotional state and adjusting the content of the notification; means for accumulating long-term traffic data and generating improvement proposals for chronic congestion locations; and means for transmitting the generated improvement proposals to a traffic management organization. This not only enables the provision of real-time traffic information but also support according to the driver's emotional state, making it possible to effectively analyze long-term traffic problems and propose improvements.

[1487] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate new information from data and perform specific tasks.

[1488] "Traffic data" refers to information that indicates traffic conditions such as road congestion, vehicle flow, and traffic light timing.

[1489] "Driver" means a person who drives a motor vehicle.

[1490] "Departure time" refers to the time when you start driving to your destination.

[1491] A "route" is a path from a starting point to a destination.

[1492] "Traffic information" refers to data that indicates current and predicted road conditions and congestion levels.

[1493] "Data preprocessing" refers to the process of converting collected raw data into a form suitable for analysis.

[1494] "Notification" refers to the action of the system providing information to the driver.

[1495] "Emotional state" refers to the driver's psychological and physiological state, such as stress level and fatigue level.

[1496] "Emotion recognition means" refers to technology that analyzes the driver's facial expressions and voice to identify their emotional state.

[1497] "Chronic congestion spots" are specific roads or intersections where congestion frequently occurs.

[1498] "Improvement proposals" are specific measures or proposed changes to improve traffic conditions.

[1499] "Traffic management organization" means a public or private organization that manages road traffic and helps it operate smoothly.

[1500] This invention is a system that uses generative AI and an emotion engine to analyze traffic data in real time and provide drivers with optimal departure times and routes. This system includes traffic data collection, data preprocessing, data analysis using generative AI, emotion recognition, notification functions, long-term traffic data accumulation and analysis, and generation of improvement suggestions.

[1501] The server first collects real-time traffic information from various data sources such as road traffic cameras, GPS devices, traffic sensors, user reports, etc. Cloud infrastructure (e.g., Google Cloud Platform or Amazon Web Services) is used at this stage.

[1502] The server then pre-processes the collected traffic data to remove noise and errors, improving the accuracy of the analysis. This pre-processing includes data filtering techniques and generating a clean dataset.

[1503] The pre-processed data is then analyzed through a generative AI model (e.g., GPT-4), which predicts traffic flow and congestion, calculates optimal departure times and routes for drivers, and provides customized information that takes into account the individual needs of the driver.

[1504] The emotion engine uses the driver's camera and sensor devices to recognize the driver's emotional state in real time. For example, deep learning frameworks (e.g., TensorFlow and OpenCV) are used for facial recognition and voice analysis. Notification content is then tailored based on this emotional state.

[1505] Based on the analysis and emotion recognition results, the server notifies the driver's device (smartphone or car navigation system) of the optimal departure time and route. This notification is even more effective because it is adjusted taking into account the driver's emotional state. For example, if the driver is feeling stressed, the notification will include a message saying, "Take a deep breath and relax."

[1506] Long-term traffic data is stored on a server and used to identify chronic congestion points. Based on this data, concrete improvement proposals can be generated for traffic management organizations, and even legal reforms can be proposed if necessary.

[1507] A concrete example would be a scenario where a user sets a destination and if their current stress level is high, the prompt "Relax" is displayed. For example, if a driver sets Tokyo Station as their destination in a smartphone navigation app, the following prompt sentence is used:

[1508] gps_data = GPSSensor().get_data(destination="Tokyo Station")

[1509] In this way, the system of the present invention can provide drivers with optimal information and advice in real time, reducing driver stress and traffic congestion.

[1510] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1511] Step 1:

[1512] The server collects traffic data. The input is real-time data from road traffic cameras, GPS devices, traffic sensors, and user reports. The output is a set of collected raw data. This step includes, for example, obtaining location information from GPS devices and image data from cameras.

[1513] Step 2:

[1514] The server preprocesses the collected data. The input is the raw data collected in step 1. The output is a cleaned dataset with noise and errors removed. In this step, data cleansing such as data filtering and outlier removal is performed. Specifically, image processing algorithms are applied to image data, and location information is corrected for GPS data.

[1515] Step 3:

[1516] The server inputs the preprocessed data into a generative AI to analyze the optimal departure time and route. The input is cleaned traffic data. The output is optimal departure time and route information to provide to the driver. In this step, for example, a generative AI model (GPT-4) is used to analyze multiple data points to perform congestion prediction and time route optimization. The generative AI model analyzes traffic patterns and congestion trends and generates predictions.

[1517] Step 4:

[1518] The server uses an emotion engine to recognize the driver's emotional state. The input is the driver's camera and audio data. The output is the driver's emotional state (e.g., stress level and fatigue level). In this step, a deep learning framework (TensorFlow or OpenCV) is used to perform facial recognition and audio analysis to identify the driver's emotional state. Specifically, the server determines the driver's emotion by detecting changes in facial expression from the driver's facial image and analyzing the tone and speed of voice from the audio.

[1519] Step 5:

[1520] Based on the analysis results and emotion recognition results, the server notifies the driver of the optimal departure time and route, as well as advice based on the driver's emotional state. The input is the optimized departure time, route, and the driver's emotional state. The output is a notification message to be displayed on the driver's smartphone or car navigation system. In this step, the notification system is used to send advice based on the calculated information and emotions to the driver's device. For example, messages such as "The optimal departure time is 8:30. There is no traffic jam at the moment" or "Relax. The next rest stop is 20 km away" are displayed.

[1521] Step 6:

[1522] The server accumulates and analyzes long-term traffic data. The input is traffic data collected daily. The output is the analysis results on chronic congestion points. In this step, the collected past data is stored in a database and statistical analysis is performed. For example, it identifies which days of the week and at what times of day a particular road is prone to congestion.

[1523] Step 7:

[1524] The server generates improvement proposals based on the accumulated data and sends them to the traffic management organization. The input is the long-term traffic analysis results. The output is a specific improvement proposal. In this step, improvement proposals are generated, including, for example, signal timing adjustments and road widening proposals, and are sent to the traffic management organization via email or a dedicated management system.

[1525] This will not only provide real-time traffic information, but also support tailored to the driver's emotional state, as well as analyze and propose improvements to long-term traffic problems.

[1526] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1527] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1528] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1529] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1530] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1531] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1532] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1533] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1534] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1535] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1536] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1537] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1538] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1539] 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.

[1540] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1541] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1542] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1543] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1544] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1545] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1546] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1547] The following is further disclosed regarding the above embodiment.

[1548] (Claim 1)

[1549] A means to use generative AI to analyze traffic data in real time and provide drivers with optimal departure times and routes;

[1550] a means for collecting traffic information;

[1551] a means for pre-processing the collected data;

[1552] means for notifying a driver based on the preprocessed data;

[1553] A means of accumulating long-term traffic data and generating improvement proposals for chronic congestion areas;

[1554] means for transmitting the generated improvement suggestions to a traffic management organization;

[1555] A system including:

[1556] (Claim 2)

[1557] 2. The system according to claim 1, further comprising means for providing traffic information based on the individual needs of the driver using a generating AI.

[1558] (Claim 3)

[1559] 2. The system according to claim 1, further comprising means for analyzing data relating to chronic congestion locations and proposing legal changes.

[1560] "Example 1"

[1561] (Claim 1)

[1562] a means for collecting traffic data in real time from multiple data sources;

[1563] A means of pre-processing the collected traffic data to remove noise and errors;

[1564] A means of analyzing pre-processed data using generative AI models to predict traffic flow and congestion;

[1565] A means for informing the driver of the optimal departure time and route based on the analysis results;

[1566] A means of accumulating long-term traffic data and identifying chronic congestion areas,

[1567] A means for generating improvement proposals for chronic congestion locations and transmitting them to a traffic management organization;

[1568] A system including:

[1569] (Claim 2)

[1570] The system of claim 1, which uses a generating AI to provide traffic information based on the driver's individual needs.

[1571] (Claim 3)

[1572] 2. The system according to claim 1, further comprising means for analyzing data relating to chronic congestion locations and proposing legal changes.

[1573] "Application Example 1"

[1574] (Claim 1)

[1575] A means to use generative AI to analyze traffic data in real time and provide drivers with optimal departure times and routes;

[1576] a means for collecting traffic information;

[1577] a means for pre-processing the collected data;

[1578] means for notifying a driver based on the preprocessed data;

[1579] A means of accumulating long-term traffic data and generating improvement proposals for chronic congestion areas;

[1580] means for transmitting the generated improvement suggestions to a traffic management organization;

[1581] means for collecting traffic information from sensors mounted on the vehicle and external data sources;

[1582] A means of performing data analysis using an in-vehicle edge AI computing unit;

[1583] a means for notifying an infotainment system of the vehicle of the calculated optimal route information;

[1584] means for notifying the driver using voice guidance;

[1585] A system including:

[1586] (Claim 2)

[1587] 2. The system according to claim 1, further comprising means for providing traffic information based on the individual needs of the driver using a generating AI.

[1588] (Claim 3)

[1589] 2. The system according to claim 1, further comprising means for analyzing data relating to chronic congestion locations and proposing legal changes.

[1590] "Example 2: Combining Emotion Engines"

[1591] (Claim 1)

[1592] The server uses generated AI to analyze traffic data in real time and provide drivers with the optimal departure time and route.

[1593] A means for the server to collect traffic information;

[1594] means for preprocessing the collected traffic data by the server;

[1595] A means for the server to notify the driver based on the preprocessed data;

[1596] A means for the server to accumulate long-term traffic data and generate improvement proposals for chronic congestion points;

[1597] means for transmitting the server-generated improvement suggestions to a traffic management organization;

[1598] A means for providing information based on individual needs using an emotion engine in which the server recognizes the driver's emotional state;

[1599] A system including:

[1600] (Claim 2)

[1601] 2. The system according to claim 1, wherein the server comprises means for using the generating AI to provide traffic information based on the individual needs of the driver.

[1602] (Claim 3)

[1603] 2. The system according to claim 1, wherein the server comprises means for analyzing data relating to chronic congestion locations and proposing legal reforms.

[1604] "Application example 2 when combining emotion engines"

[1605] (Claim 1)

[1606] A means to use generative AI to analyze traffic data in real time and provide drivers with optimal departure times and routes;

[1607] a means for collecting traffic information;

[1608] a means for pre-processing the collected data;

[1609] means for notifying a driver based on the preprocessed data;

[1610] An emotion recognition means for recognizing the driver's emotional state and adjusting the notification content;

[1611] A means of accumulating long-term traffic data and generating improvement proposals for chronic congestion areas;

[1612] means for transmitting the generated improvement suggestions to a traffic management organization;

[1613] A system including:

[1614] (Claim 2)

[1615] 10. The system of claim 1, further comprising means for using generative AI to provide traffic information based on the driver's individual needs and advice based on the driver's emotional state.

[1616] (Claim 3)

[1617] 2. The system of claim 1, further comprising means for analyzing data on chronic congestion points and for proposing legislative changes and driver assistance based on emotion recognition. [Explanation of symbols]

[1618] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to use generative AI to analyze traffic data in real time and provide drivers with optimal departure times and routes; a means for collecting traffic information; a means for pre-processing the collected data; means for notifying a driver based on the preprocessed data; A means of accumulating long-term traffic data and generating improvement proposals for chronic congestion areas; means for transmitting the generated improvement suggestions to a traffic management organization; A system including:

2. 2. The system according to claim 1, further comprising means for providing traffic information based on individual driver needs using a generating AI.

3. 2. The system of claim 1, further comprising means for analyzing data relating to chronic congestion locations and making recommendations for law changes.

Images