system

Abstract

Provide a system. The present invention includes a means for collecting road design information and traffic violation data and storing them in a database; A means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road; A means for generating specific road improvement proposals for identified problem areas of the road using the generative AI model; a means for calculating a predicted effect of reducing traffic accidents based on the road improvement plan; means for providing the road improvement proposals and forecast results in a report format; A system including:

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 accidents are a serious problem for society as a whole, and accidents caused by traffic violations in particular are preventable. However, when current road designs induce traffic violations and result in frequent accidents, there is a lack of means to appropriately detect and improve them. Conventional methods have difficulty identifying problems in road designs that are easily overlooked by humans, and lack the objective data and analytical capabilities to derive effective improvement proposals. Against this background, the objective of this invention is to provide a system that prevents traffic violations and the resulting accidents caused by road structures and optimizes road designs. [Means for solving the problem]

[0005] The present invention is a system that includes a means for collecting road design information and traffic violation data and storing them in a database, a means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, a means for generating specific road improvement plans for the identified problem areas using the generative AI model, a means for calculating a predicted effect of traffic accident reduction based on the road improvement plans, and a means for providing the road improvement plans and predicted results in a report format. The generative AI model may also include a means for generating a visual simulation based on the analysis results, or a means for receiving feedback from users and reevaluating and re-proposing based on the feedback. This prevents traffic violations caused by road design and reduces traffic accidents.

[0006] "Road design information" is data related to the design of roads, such as their shape, structure, traffic light arrangement, and lane arrangement.

[0007] "Traffic violation data" is information about violations of traffic rules, specifically data on the location, cause, and frequency of accidents.

[0008] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to analyze data and make predictions.

[0009] "Database" refers to a system for systematically storing and managing collected information.

[0010] "Analysis" is the process of examining collected data in detail and extracting meaningful information from it.

[0011] A "problem section" is a specific part of a road that has safety or efficiency issues, such as frequent violations of traffic rules or traffic accidents.

[0012] "Road improvement proposals" are specific improvement measures proposed by the generative AI model for identified problem areas.

[0013] "Simulation" is a technique for predicting and visualizing the results of proposed improvements.

[0014] "Traffic accident reduction effect" is a prediction that shows the expected effect, such as the reduction rate or number of traffic accidents, if the proposed road improvement plan is followed.

[0015] A "report" is a document or report that summarizes analysis results, improvement proposals, simulation results, etc.

[0016] "Feedback" refers to opinions, ratings, additional information, etc. provided by users.

[0017] "Reevaluation" is the process of analyzing and evaluating again based on the feedback.

[0018] A "re-proposal" is a new improvement proposal based on the results of the re-evaluation. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] 1. Data collection and input

[0041] Users collect road design information and traffic violation data. Road design information includes map data and existing road design drawings, while traffic violation data includes the locations, causes, and frequency of past traffic accidents. Users then enter this data into the system using dedicated web forms or applications.

[0042] 2. Data Receipt and Storage

[0043] The device temporarily stores the data entered by the user. During the storage process, a consistency check is performed to verify the completeness and format of the data. Once the consistency is confirmed, the data is sent from the device to the server.

[0044] 3. Saving to the database

[0045] The server stores the received data in a database, where it checks again for accuracy and completeness and records the data in the database in an appropriate manner.

[0046] 4. Data Analysis

[0047] The server inputs the stored data into the generative AI model and begins data analysis. The server uses the generative AI model to analyze the relationship between road design information and traffic violation data, and identifies problem areas on the road.

[0048] 5. Generation of improvement proposals

[0049] The server generates specific road improvement proposals based on the analysis results. The generative AI model proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. These simulations use a 3D model to show, for example, how traffic flow would change if a dedicated left-turn lane were added to an intersection.

[0050] 6. Prediction of a decrease in traffic accidents

[0051] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These predictions are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[0052] 7. Providing Suggestions and Feedback

[0053] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. The user reviews the information provided and provides feedback as needed. Feedback can include questions about the proposal or requests for additional information.

[0054] 8. Processing and reassessing feedback

[0055] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[0056] Example: Proposal for improving an intersection

[0057] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. The user enters detailed map data for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the improvement in safety. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. After the local government official reviews this information and provides feedback as needed, the server reevaluates and provides further optimal improvement proposals.

[0058] Thus, the present invention increases the likelihood of preventing accidents caused by violations of traffic rules, and improving road safety and efficiency.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user collects road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, traffic light locations, etc. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[0062] Step 2:

[0063] Users enter the collected road design information and traffic violation data into the system using dedicated web forms and applications, ensuring that all data is complete and entered in the correct format.

[0064] Step 3:

[0065] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[0066] Step 4:

[0067] The device sends the data, whose format and integrity have been verified, to the server using a secure communication protocol to ensure confidentiality and security of the data.

[0068] Step 5:

[0069] The server stores the data received from the device in a database, during which the data is checked again for accuracy and completeness and recorded in the database in the appropriate format.

[0070] Step 6:

[0071] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[0072] Step 7:

[0073] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[0074] Step 8:

[0075] The server creates a simulation to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This visual simulation is useful for validating the effectiveness of the proposal.

[0076] Step 9:

[0077] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The calculation is based on the simulation results to predict the extent of the accident reduction effect.

[0078] Step 10:

[0079] The server compiles the calculated prediction results in a report that is easy for local government officials to understand. The report details the specific improvement plans and their effects.

[0080] Step 11:

[0081] The terminal displays the generated reports and simulation results to local government officials, who can easily access them, for example, through a web application dashboard.

[0082] Step 12:

[0083] The user reviews the information provided and provides feedback as needed, including questions about the proposal or requests for additional information.

[0084] Step 13:

[0085] The server re-runs the analytical model based on the feedback received from the user, re-evaluating and re-proposing, and generating new refinements as needed.

[0086] Step 14:

[0087] The server then revisits the proposed improvements and provides them to the local government along with the predicted results of their effects, thereby providing ongoing support to the local government in making optimal road improvements.

[0088] In this way, accidents caused by violations of traffic rules can be prevented, improving road safety and efficiency.

[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] In conventional road design and traffic safety measures, the process of identifying the locations and causes of traffic accidents and then considering improvement measures based on that information takes a lot of time and effort. Furthermore, there are limited ways to predict in advance how effective proposed improvement measures will actually be, making it difficult to implement efficient measures.

[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 road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for generating a visual simulation of the road improvement plan, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plan, means for providing the road improvement plan and the predicted results in a report format, and means for receiving feedback from users and reevaluating and re-proposing based on the feedback, thereby enabling efficient and effective prevention of traffic accidents and improvement of road safety.

[0094] "Road design information" is data relating to the shape, size, configuration, traffic signs, pavement condition, and surrounding environment of the road.

[0095] "Traffic violation data" refers to data that includes the locations, causes, and frequency of past traffic accidents and violations, as well as detailed information about those accidents and violations.

[0096] The "database" is a system for systematically and efficiently managing, storing, and searching collected road design information and traffic violation data.

[0097] "Generative AI model" refers to an artificial intelligence algorithm used to analyze collected data and generate road improvement proposals and predict their effectiveness in reducing traffic accidents.

[0098] "Analysis" refers to the analytical process of using collected road design information and traffic violation data to find correlations and identify problem areas.

[0099] "Problem sections of roads" refer to areas where traffic accidents frequently occur or where there are defects in the road structure.

[0100] "Road Improvement Proposals" refer to specific design changes or measures to improve the safety and efficiency of identified road problem areas.

[0101] "Visual simulation" refers to 3D models and animations that visually demonstrate the effects of generated road improvement proposals.

[0102] "Traffic accident reduction effect" refers to the rate or number of traffic accidents predicted to decrease as a result of the implementation of the proposed road improvement plan.

[0103] "Report" refers to a document summarizing the generated road improvement proposals and their predicted results in written form.

[0104] "Feedback" refers to comments such as questions about the proposal or requests for additional information provided by the user.

[0105] "Reevaluation" is the process of re-analyzing the product based on user feedback and considering new improvement proposals.

[0106] "Re-proposal" refers to submitting a proposal again that includes new improvement proposals generated as a result of re-evaluation.

[0107] The system is designed to collect road design information and traffic violation data, and then carry out a series of processes based on that data, including analysis, generation of improvement proposals, simulation, prediction, and feedback processing.

[0108] 1. Data collection and input

[0109] Users collect road design information (e.g., map data and existing road design drawings) and traffic violation data (e.g., locations, causes, and frequency of past traffic accidents) from public government databases and traffic control centers. Specifically, map data is obtained from OpenStreetMap, and traffic accident data is obtained from the National Police Agency database. Users enter this information using a dedicated web form or mobile application (e.g., Data Input Pro).

[0110] 2. Data Receipt and Storage

[0111] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. The device uses a JSON Schema Validator to verify that the data format is correct. For example, it verifies that map data is represented by the correct coordinates and that accident data is entered in the appropriate format. Once the data is confirmed to be consistent, it is sent to the server via an API.

[0112] 3. Saving to the database

[0113] The server checks the received data and stores it in a database (e.g., MySQL or PostgreSQL). The server further checks the data for accuracy and completeness before storing it. It compares it with other related tables and logs any inconsistencies.

[0114] 4. Data Analysis

[0115] The server inputs the stored data into a pre-trained generative AI model. This model is built using TENSORFLOW (registered trademark) and PyTorch. The server begins analyzing the input data using the generative AI model and identifies problem areas based on the location and cause of traffic accidents. Specifically, it determines that there are many accidents when turning left at a particular intersection.

[0116] 5. Generation of improvement proposals

[0117] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually demonstrate the effects of the proposed improvements.

[0118] 6. Prediction of a decrease in traffic accidents

[0119] The server uses the generative AI model to simulate the effect of reducing traffic accidents if the proposed improvement plan is implemented. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%."

[0120] 7. Providing Suggestions and Feedback

[0121] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The user reviews the proposals and enters feedback through a web form. For example, feedback such as "I would like more detailed explanations for the proposed left-turn lane locations" can be provided.

[0122] 8. Processing and reassessing feedback

[0123] The server takes the feedback received from the user and re-runs the analytical model. If necessary, it generates new refinements based on the feedback and presents them again, including visual simulations.

[0124] Prompt Sentence Examples

[0125] "Please explain the procedure for a local government official to confirm that there are many accidents occurring when turning left at a particular intersection and input detailed map data and traffic accident data from the past year into the system to consider improvement proposals."

[0126] Please provide details on the process by which the terminal receives the data entered by the user into the system, performs integrity checks, and then transmits it to the server.

[0127] In this way, the use of this system makes it possible to efficiently and effectively prevent traffic accidents and improve road safety.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] Users collect road design information and traffic violation data. Users obtain data from public government databases and traffic control centers. Specifically, they collect map data from OpenStreetMap and traffic accident data from the National Police Agency database. These data are input.

[0131] Step 2:

[0132] Users enter this data into the system using dedicated web forms or mobile applications (e.g., Data Input Pro). Users upload map data as files and enter accident data directly into the form. This is where the input data is collected.

[0133] Step 3:

[0134] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. To confirm the data's consistency, the device uses a JSON Schema Validator to validate the format of the data. For example, it checks whether map data is expressed using the correct coordinates and whether accident data has been entered in the appropriate format. This consistency check generates data whose consistency has been confirmed.

[0135] Step 4:

[0136] The device sends the data, whose integrity has been confirmed, to the server via the API. The data sent includes map data and traffic accident data that have passed formal verification. The data is then entered into the server.

[0137] Step 5:

[0138] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Before storing, the server rechecks the data for accuracy and completeness and logs any inconsistencies. This results in a database record that is verified as accurate.

[0139] Step 6:

[0140] The server inputs the stored data into a pre-trained generative AI model. This model is built using TensorFlow and PyTorch. The server uses the generative AI model to begin analyzing the input data. For example, it identifies problem areas based on the location and cause of traffic accidents. As a result of this analysis, problem areas on the road are identified.

[0141] Step 7:

[0142] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually show the effects of the proposed improvement. This data processing results in a visual simulation.

[0143] Step 8:

[0144] The server uses the generative AI model to simulate the effect of introducing the proposed improvement plan on reducing traffic accidents. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%." This data calculation outputs a predicted reduction effect.

[0145] Step 9:

[0146] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The output is a report of the proposals and simulation results.

[0147] Step 10:

[0148] The user reviews the report and simulation results and enters their feedback through a web form. For example, they may provide feedback such as, "I would like more detailed explanations for the proposed left-turn lane locations." This feedback is collected as input data.

[0149] Step 11:

[0150] The server incorporates the feedback received from the user into the system and re-runs the analytical model. If new refinements are necessary based on the feedback, they are generated and presented again, including visual simulations. This re-evaluation generates new refinements and their simulation outputs.

[0151] (Application example 1)

[0152] 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."

[0153] Autonomous vehicles need to perform optimal driving behavior and route selection in real time, but conventional systems have difficulty performing instant and efficient analysis based on road design information and traffic violation data. Therefore, to further improve safety and efficiency, a system that can quickly analyze collected data and propose appropriate driving behavior is required. It is also important to increase the reliability of proposals by performing visual simulations.

[0154] 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.

[0155] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the problem areas on the road identified by the generative AI model, and means installed in the autonomous vehicle for proposing optimal driving behaviors and routes in real time, thereby enabling the autonomous vehicle to perform optimal driving behaviors based on the collected data in real time, thereby achieving both safety and efficiency.

[0156] "Road design information" is data relating to the structure and layout of roads, including map data and existing road design drawings.

[0157] "Traffic violation data" is information about traffic violations and accidents that have occurred in the past, and specifically includes data on the location, cause, and frequency of accidents.

[0158] A "generative AI model" is a system that uses artificial intelligence techniques to analyze specific data and make predictions or suggestions, for example, using deep learning or machine learning algorithms.

[0159] "Analysis" is the process of examining collected data in detail, extracting useful information from it, and deepening understanding.

[0160] "Real-time" means responding immediately to incoming data and events, for example, responding immediately to changes in traffic and road conditions.

[0161] "Driving behavior" refers to the specific maneuvers and actions performed by a vehicle, including all driving operations such as changing lanes, adjusting speed, and stopping.

[0162] "Route suggestions" are the best route or method of travel from a starting point to a destination, taking into account factors such as time, distance, and safety.

[0163] "Visual simulation" is a method of visually displaying analysis results and proposals, for example, using 3D models or graphical data displays to present them in an intuitively understandable way.

[0164] "Feedback" refers to reactions and opinions from users and system operators, and is used as a basis for the system to make improvements and reevaluate.

[0165] "Reevaluation" means reconsidering analyses and proposals that have already been made based on new data and feedback, and making corrections or improvements as necessary.

[0166] 1. Data collection and input

[0167] Users use autonomous vehicles to collect road design information and traffic violation data in real time. Road design information includes data acquired from the vehicle's GPS, cameras, and various sensors, while traffic violation data includes records of past traffic accidents and violations. This data is then entered into dedicated web forms and applications via the vehicle's onboard computing unit.

[0168] 2. Data Receipt and Storage

[0169] The terminal temporarily stores the data entered by the user. When the data is saved, it is checked for integrity and format. Once the integrity of the data is confirmed, it is sent from the terminal to the server.

[0170] 3. Saving to the database

[0171] The server stores the received data in a database, where the accuracy and completeness of the data are checked again and recorded in the database in an appropriate manner.

[0172] 4. Data Analysis

[0173] The server inputs the stored data into the generative AI model and begins data analysis. The generative AI model analyzes the relationship between road design information and traffic violation data, and identifies problem areas on roads for autonomous vehicles. For example, it identifies areas where traffic accidents frequently occur and dangerous areas on roads.

[0174] 5. Generation of improvement proposals

[0175] The server generates specific road improvement proposals based on the analysis results. The generative AI model then proposes optimal design changes for identified problem areas to improve vehicle and pedestrian safety. This could include, for example, adding a dedicated left-turn lane at a specific intersection. The server also creates simulations to visualize the proposed road improvements. These simulations, for example, use 3D models to show how the proposals will affect traffic flow.

[0176] 6. Prediction of a decrease in traffic accidents

[0177] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[0178] 7. Providing Suggestions and Feedback

[0179] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The results are presented in a dedicated dashboard for easy access by the vehicle's driving control system. The user can review the information provided and enter feedback as needed. For example, feedback can include questions about the proposals or requests for additional information.

[0180] 8. Processing and reassessing feedback

[0181] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, generating additional refinements as needed, which are also provided to the autonomous vehicle's driving system, including visual simulations.

[0182] Hardware and software used

[0183] Hardware: The computing unit, GPS, cameras, and sensors installed in the autonomous vehicle.

[0184] Software: Python programs, databases (e.g., MySQL), generative AI models (e.g., GPT-4®).

[0185] Specific examples

[0186] Consider a case where an autonomous vehicle determines that a particular intersection has a high incidence of left-turn accidents. The user inputs detailed road design information for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the particular intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the safety improvement. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. The user reviews this information and provides feedback as needed, and the server reevaluates and provides further optimal improvement suggestions.

[0187] Prompt Sentence Examples

[0188] Analyze the following dataset and propose improvements to road design.

[0189] 1. Road design information: {road_design_data}

[0190] 2. Traffic violation data: {traffic_violation_data}

[0191] Based on the analysis results, present specific improvement proposals and predict their effectiveness.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] A user uses the computing unit of an autonomous vehicle to collect road design information and traffic violation data. The input is real-time data obtained from hardware such as GPS, cameras, and sensors. The output is that this data is entered into a dedicated web form or application.

[0195] Step 2:

[0196] The terminal temporarily stores the data entered by the user. The input is the real-time data entered in step 1. At this stage, an integrity check is performed to verify the completeness and format of the data. The output is that the integrity-checked data is sent to the server.

[0197] Step 3:

[0198] The server stores the received data in the database. The input is the data sent in step 2. When storing, the data is checked again for accuracy and completeness and recorded in the database in an appropriate manner. The output is the state of the database with the data stored accurately.

[0199] Step 4:

[0200] The server inputs the stored data into the generative AI model and begins data analysis. The input is road design information and traffic violation data stored in the database. The server uses this data to identify problem areas on the road using the generative AI model. The output is a list of identified problem areas.

[0201] Step 5:

[0202] The server generates specific road improvement proposals based on the analysis results. The input is the list of problem areas obtained in step 4. The generative AI model is used to propose optimal design changes to improve safety. The output is a list of specific road improvement proposals, such as adding a dedicated left-turn lane at a specific intersection.

[0203] Step 6:

[0204] The server creates a simulation to visualize the proposed road improvement plan. The input is the road improvement plan generated in step 5. The simulation is displayed visually using a 3D model, etc. The output is the visualized simulation result.

[0205] Step 7:

[0206] The server calculates the predicted reduction in traffic accidents when the proposed improvement is implemented. The inputs are the road improvement proposal from Step 5 and the simulation results from Step 6. The generative AI model simulates the effect of the proposed design changes and calculates the predicted results. The output is statistics such as the rate of reduction in traffic accidents and the predicted number of reductions.

[0207] Step 8:

[0208] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The inputs are the prediction results calculated in step 7 and the simulation results from step 6. The results are displayed in a format that is easily accessible to the user and the vehicle's driving control system. The output is the results displayed on the driving system's dashboard.

[0209] Step 9:

[0210] The user checks the provided information and enters feedback as necessary. The input is the report or simulation results displayed in step 8. The feedback may include questions about the proposal or requests for additional information. The output is the feedback content.

[0211] Step 10:

[0212] The server re-runs and re-evaluates the analytical model based on the feedback received from the user. The input is the feedback obtained in step 9. If necessary, additional refinements are generated and provided to the autonomous vehicle's driving system, including a visual simulation. The output is the re-evaluated refinements and the simulation results.

[0213] 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.

[0214] 1. Data collection and input

[0215] Users collect road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users then enter this data into the system using dedicated web forms and applications.

[0216] 2. Data Receipt and Storage

[0217] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[0218] 3. Saving to the database

[0219] The terminal sends the data, whose format and completeness have been checked, to the server, which stores the received data in a database. During this process, the data is checked again for accuracy and completeness, and recorded in the database in the appropriate format.

[0220] 4. Data Analysis

[0221] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[0222] 5. Generation of improvement proposals

[0223] The server generates specific road improvement proposals based on the analysis results. It proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. The simulations use 3D models to show, for example, how traffic flow would change if a left-turn lane were added to an intersection.

[0224] 6. Prediction of a decrease in traffic accidents

[0225] The server calculates the predicted effect of traffic accident reduction if the improvement plan is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents or the predicted number of reductions.

[0226] 7. Providing Suggestions and Feedback

[0227] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Users review the information provided and provide feedback, if necessary. Feedback can include questions about the proposal or requests for additional information.

[0228] 8. Processing and reassessing feedback

[0229] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[0230] 9. Incorporating an Emotional Engine

[0231] The server incorporates a new emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's emotions in real time as they input data and collects it as data.

[0232] 10. Emotionally driven feedback response

[0233] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into account, aiming to increase user satisfaction.

[0234] 11. Monitoring Emotional Data

[0235] The server periodically monitors changes in emotional data and analyzes the user's emotional trends, aiming to improve long-term user engagement and improve feedback accuracy.

[0236] Example: Intersection improvement proposals and emotional feedback

[0237] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of accidents when turning left and would like to improve the intersection. The user enters detailed map data about the intersection and traffic accident data from the past year into the system. Additionally, the emotion engine collects the user's emotional state in real time. The device verifies the data integrity and sends it to the server. The server stores the data in a database and analyzes it using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation and adds a detailed explanation that takes customer satisfaction into consideration. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. The local government official reviews this information and provides feedback. The server then reevaluates the proposal based on the feedback and provides further optimal improvement proposals.

[0238] In this way, the present invention can prevent accidents caused by violations of traffic rules, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of improvement proposals and the level of satisfaction.

[0239] The processing flow will be explained below.

[0240] Step 1:

[0241] The user collects road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations, while traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[0242] Step 2:

[0243] Users enter the collected road design information and traffic violation data into the system using a dedicated web form or application. When entering data, they check to make sure that all data is complete and that there are no omissions.

[0244] Step 3:

[0245] The terminal temporarily stores the data entered by the user, and while storing it, checks the format and completeness of the data to ensure that it is accurate and in the proper format.

[0246] Step 4:

[0247] The device sends the data, whose format and integrity have been verified, to the server, using a secure communication protocol to ensure confidentiality and security of the data.

[0248] Step 5:

[0249] The server stores the data received from the device in a database, where it checks the accuracy and completeness of the data once again and records it in the database in the appropriate format.

[0250] Step 6:

[0251] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the relationship between road design information and traffic violation data to identify problem areas on the road.

[0252] Step 7:

[0253] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[0254] Step 8:

[0255] The server creates simulations to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This simulation is useful for validating the effectiveness of the proposals.

[0256] Step 9:

[0257] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The predicted results include the accident reduction rate and predicted number of reductions, which are used to show the specific effects.

[0258] Step 10:

[0259] The server uses an emotion engine to analyze the user's emotions in real time as they are input. The results of this analysis are stored in a database and used for subsequent feedback responses.

[0260] Step 11:

[0261] The server displays the generated reports and simulation results to local government officials. Based on the emotional data analyzed by the emotion engine, the tone and content of the report are adjusted, presenting the information in a format that is easy for the official to understand. For example, if the official is feeling stressed, more detailed and careful explanations are added.

[0262] Step 12:

[0263] The user checks the provided reports and simulation results and enters feedback as necessary. The emotion engine then analyzes the user's emotions when entering feedback and records them in a database.

[0264] Step 13:

[0265] The server re-executes the analysis model based on the feedback received from the user, re-evaluates and re-proposes, and generates new improvement proposals. The generated improvement proposals are visualized again through simulation.

[0266] Step 14:

[0267] The server then provides the revised improvement plan to the local government official. Based on the emotional data analyzed by the emotion engine, the presentation is made in a format and with content that is easy to understand. This allows the server to provide ongoing support to local governments in implementing optimal road improvements.

[0268] In this way, accidents caused by violations of traffic rules can be prevented, and road safety and efficiency can be improved. In addition, proposals can be made that take user feelings into account, which increases the likelihood of improvement proposals being accepted.

[0269] Example 2

[0270] 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."

[0271] To reduce traffic accidents, it is necessary to quickly propose effective road design improvement plans and present them to stakeholders in an actionable form. It is also important to optimize the proposals by taking into account user feedback and emotional states, thereby improving user satisfaction. Conventional systems have had difficulty meeting these requirements, making it impossible to resolve problems rationally and quickly.

[0272] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0273] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plans, means for providing the road improvement plans and the predicted results in a report format, means including an emotion analysis engine for analyzing the user's emotional state and collecting it as data, and means for adjusting reports and feedback responses based on the emotion analysis data. This makes it possible to improve the effectiveness of road design improvements and make optimal proposals that take the user's emotions into consideration.

[0274] "Road design information" refers to data related to road structure and design, such as map data, existing road design drawings, intersection locations, and traffic light locations.

[0275] "Traffic violation data" refers to data related to traffic violations, such as the location, cause, and frequency of traffic accidents in a specific section.

[0276] A "generative AI model" is a model that uses machine learning and deep learning techniques to analyze input data and identify and predict specific problems.

[0277] An "emotion analysis engine" is a system that analyzes user input and behavior in real time and evaluates and judges the user's emotional state.

[0278] "Means for storing in a database" refers to a method or system for integrating collected data and storing it in a database in an appropriate format.

[0279] "Road improvement proposals" are proposals for specific design changes to improve safety and convenience for problem areas on roads identified based on the analysis results.

[0280] "Traffic accident reduction effect" is the predicted reduction in the percentage or number of traffic accidents if the proposed road improvement plan is implemented.

[0281] The "means for adjusting feedback response" refers to a method or system for readjusting suggestions or responses to an appropriate form based on the user's emotional state and the feedback content.

[0282] "Visual simulation" is a technique that uses 3D models and graphics to visually represent proposed road improvements and their effects.

[0283] The "means for re-evaluating and re-proposing" refers to a method or system for re-executing the analysis model based on feedback from the user, and generating and proposing new improvement proposals.

[0284] The present invention relates to a system for analyzing road design information and traffic violation data to generate effective road improvement proposals. Specific embodiments for carrying out the present invention will be described below.

[0285] 1. Data collection and input

[0286] First, users collect road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users enter this data into the system using dedicated web forms and applications.

[0287] 2. Data Receipt and Storage

[0288] The terminal temporarily receives and stores the data entered by the user. At this stage, the terminal checks the data format and integrity. If invalid data is detected, an error message is displayed to the user, prompting them to re-enter the data.

[0289] 3. Saving to the database

[0290] The terminal sends the data, whose format and completeness have been checked, to the server. The server receives the data, checks it again, and stores it in the database. During this process, the server double-checks the accuracy and completeness of the data and records it in the database in the appropriate format.

[0291] 4. Data Analysis

[0292] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model uses machine learning and deep learning techniques, specifically libraries such as TensorFlow and PyTorch. In this process, various features are extracted from the loaded data, and problem areas on the road are identified as analysis results.

[0293] 5. Generation of improvement proposals

[0294] The server generates specific road improvement proposals based on the results of the data analysis. For example, these proposals may include adding dedicated left-turn lanes or changing the placement of traffic lights. These improvement proposals are visualized using 3D simulation software (e.g., Unity). The server runs the simulation and displays the changes in traffic flow in a 3D model.

[0295] 6. Prediction of a decrease in traffic accidents

[0296] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the proposed improvement is implemented. Specifically, it uses Monte Carlo simulation to estimate the extent to which the proposed design change will be effective. The results are output as the reduction rate and predicted number of traffic accidents.

[0297] 7. Providing Suggestions and Feedback

[0298] The device displays the generated reports and simulation results to local government officials, who can then view and download the results through a dedicated web application or dashboard. Users can then review the information provided and enter feedback through a dedicated form.

[0299] 8. Processing and reassessing feedback

[0300] The server receives user feedback, re-runs the analysis model, re-evaluates any newly proposed improvements, and generates additional improvements as needed, all while updating the 3D simulation and providing a visual presentation.

[0301] 9. Incorporating an Emotional Engine

[0302] The server incorporates an emotion engine that analyzes the user's emotional state in real time. The emotion engine uses technology such as IBM Watson (registered trademark) Tone Analyzer. When the user inputs data, the emotion engine analyzes the text and input actions, and collects the user's emotional state as data.

[0303] 10. Emotionally driven feedback response

[0304] The server adjusts the feedback response based on the collected emotional data. For example, if the server determines that the user is feeling stressed, it will provide more attentive support and detailed explanations. It also adjusts the improvement proposals based on the emotional data to improve user satisfaction.

[0305] 11. Monitoring Emotional Data

[0306] The server periodically monitors changes in emotional data and analyzes the user's emotional trends over the long term, which aims to improve long-term user engagement and improve feedback accuracy.

[0307] Example: Intersection improvement proposals and emotional feedback

[0308] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. When a user enters detailed map data about the intersection and traffic accident data from the past year into the system, the emotion engine collects the user's emotional state in real time. The device verifies the data's integrity and sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis identifies that adding a dedicated left-turn lane at the intersection would be effective. The server visualizes this suggestion in a 3D simulation and provides a detailed explanation. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. After the official reviews this information and provides feedback, the server reevaluates and provides further optimal improvement proposals.

[0309] In this way, the present invention provides an effective means for preventing traffic accidents, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of the suggestions and the level of satisfaction.

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1:

[0312] Users collect and input road design information and traffic violation data. They input map data, road design drawings, intersection layouts, and traffic light locations into the system using dedicated web forms and applications. They also input traffic violation data such as the location, cause, and frequency of accidents in specific sections. The input data is sent to the terminal via a dedicated application.

[0313] Input: Map data, road design, intersection layout, traffic light location, location, cause, and frequency data of traffic accidents

[0314] Output: Input data saved on the device

[0315] Step 2:

[0316] The terminal temporarily stores the data sent by the user. The terminal checks the format and completeness of the data to ensure consistency. Specifically, it runs a script to check for missing or incorrectly formatted data, and displays an error message to the user if invalid data is present.

[0317] Input: Data submitted by the user

[0318] Output: Data that has been checked for consistency, error message (if invalid data)

[0319] Step 3:

[0320] The device sends the data, whose integrity has been confirmed, to the server. The server receives the data and checks it again. Specifically, the server reconfirms the accuracy and completeness of the data and records it in the database in the appropriate format. During this process, the data is temporarily stored in cache memory, and after reconfirmation, it is saved in the official database.

[0321] Input: Data that has been integrity checked

[0322] Output: Data stored in the database

[0323] Step 4:

[0324] The server inputs the stored data into the generative AI model and begins analysis. During this process, the generative AI model uses machine learning algorithms (e.g., TensorFlow or PyTorch) to extract features from the data and generate analysis results. In particular, it calculates the accident rate and frequency for each intersection and performs scoring to identify problem areas.

[0325] Input: Data stored in a database

[0326] Output: Analysis results from the generative AI model (identification of problem areas)

[0327] Step 5:

[0328] The server generates specific road improvement proposals based on the results of data analysis. It devises optimal design change proposals (e.g., adding dedicated left-turn lanes or changing the placement of traffic lights) for identified problem areas. The server also visualizes these proposals using 3D simulation software (e.g., Unity). The server runs the simulation and displays changes in traffic flow in a 3D model.

[0329] Input: Analysis results from generative AI model

[0330] Output: Specific road improvement plans, visualization through 3D simulation

[0331] Step 6:

[0332] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the improvement plan is implemented. Specifically, it estimates the effect of new design changes using Monte Carlo simulation and other methods, and calculates the predicted results. The results are output as the reduction rate and predicted number of traffic accidents.

[0333] Input: Specific road improvement proposals

[0334] Output: Predicted results of traffic accident reduction effect

[0335] Step 7:

[0336] The terminal displays the generated reports and simulation results to local government officials. The results are then made available for viewing and download through a dedicated web application or dashboard. Users can then review this information and enter feedback through a dedicated form.

[0337] Input: Predicted results of traffic accident reduction, specific road improvement plans, 3D simulation results

[0338] Output: Feedback (by local government officials)

[0339] Step 8:

[0340] The server receives user feedback, re-runs the analysis model, re-evaluates newly proposed improvements, and generates additional refinements as needed, all while updating the 3D simulation and providing a visual presentation.

[0341] Input: Feedback (by local government officials)

[0342] Output: Reevaluated analysis results and suggested improvements, updated 3D simulation

[0343] Step 9:

[0344] The server incorporates an emotion engine to analyze the user's emotional state in real time. The emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's input and behavior, and collect the user's emotional state as data.

[0345] Input: User input data (feedback statements and actions)

[0346] Output: User's emotional state data

[0347] Step 10:

[0348] The server adjusts the feedback response based on the collected emotional data. If the user is feeling stressed, it provides more attentive support and detailed explanations. It also adjusts improvement proposals based on the emotional data, aiming to increase user satisfaction.

[0349] Input: User emotional state data, feedback data

[0350] Output: Adjusted feedback response, revised improvement proposals

[0351] Step 11:

[0352] The server periodically monitors changes in emotional data and analyzes the user's emotional trends over the long term, thereby understanding the user's emotional state and aiming to improve long-term user engagement and feedback accuracy.

[0353] Input: Continuously collected emotional state data

[0354] Output: User sentiment analysis results

[0355] At each step, the server, terminal, and user perform specific actions to advance the overall system processing. Each process processes and calculates data based on the input data, and passes the results on to the next step. This allows for effective proposals and responses to improve road safety.

[0356] (Application example 2)

[0357] 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."

[0358] Conventional road design and traffic management systems have had difficulty efficiently identifying the locations and causes of traffic accidents and proposing appropriate improvement plans. Furthermore, the proposed improvement plans often fail to take into account user emotions and usage conditions, resulting in poor acceptance. Furthermore, automated driving vehicles are insufficient in recognizing roads and intersections with a high risk of traffic accidents in real time and responding immediately to avoid them.

[0359] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the problem areas on the road identified by the generative AI model, means for calculating the predicted traffic accident reduction effect, means integrated into the navigation system of the driving vehicle to identify roads and intersections with a high traffic accident risk in real time and propose optimal routes, means for collecting driver emotional data and adjusting feedback responses according to the driver's emotional state, and means for providing the road improvement plans and prediction results in report format. This makes it possible to reduce the risk of traffic accidents and provide more acceptable improvement plans that take the driver's emotional state into consideration.

[0360] "Road design information" refers to detailed information about road infrastructure, such as map data, existing road design drawings, intersection locations, and traffic light locations.

[0361] "Traffic violation data" refers to data on violations such as the location, cause, and frequency of traffic accidents in a specific section.

[0362] A "database" is an information management system that organizes and stores collected information for later analysis and reference.

[0363] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and generates output tailored to a specific purpose.

[0364] A "navigation system" is an in-vehicle device and software that provides vehicle route guidance and a route to a destination.

[0365] "Emotional data" is information used to collect and analyze a user's emotional state in real time.

[0366] "Feedback" refers to information provided by users that the system receives and uses to improve its services and features.

[0367] "Traffic accident reduction effect" refers to the predicted reduction in the rate or number of traffic accidents after the proposed road improvement plan is implemented.

[0368] "Report format" is a method of providing analysis results and proposals in a document format that is easy to understand.

[0369] "Visual simulation" is a means of visually representing improvement proposals generated by a generative AI model using three-dimensional models, etc.

[0370] 1. Data collection and input

[0371] Users collect road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users enter this data into the system using dedicated web forms and applications.

[0372] 2. Data Receipt and Storage

[0373] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[0374] 3. Saving to the database

[0375] The terminal sends the data, whose format and completeness have been checked, to the server, which stores the received data in a database. During this process, the data is checked again for accuracy and completeness, and recorded in the database in the appropriate format.

[0376] 4. Data Analysis

[0377] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[0378] 5. Generation of improvement proposals

[0379] The server generates specific road improvement proposals based on the analysis results. It proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. The simulations use 3D models to show, for example, how traffic flow would change if a left-turn lane were added to an intersection.

[0380] 6. Prediction of a decrease in traffic accidents

[0381] The server calculates the predicted effect of traffic accident reduction if the improvement plan is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents or the predicted number of reductions.

[0382] 7. Providing Suggestions and Feedback

[0383] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Users review the information provided and provide feedback, if necessary. Feedback can include questions about the proposal or requests for additional information.

[0384] 8. Processing and reassessing feedback

[0385] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[0386] 9. Incorporating an Emotional Engine

[0387] The server incorporates a new emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's emotions in real time as they input data and collects it as data.

[0388] 10. Emotionally driven feedback response

[0389] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into account, aiming to increase user satisfaction.

[0390] 11. Monitoring Emotional Data

[0391] The server periodically monitors changes in emotional data and analyzes the user's emotional trends, aiming to improve long-term user engagement and improve feedback accuracy.

[0392] Hardware and software used

[0393] The implementation of this system uses the following hardware and software:

[0394] Hardware: Autonomous vehicle control systems, on-board computers, various sensors, digital panels

[0395] Software: Navigation system integration software, Python program, Scipy library, HTTP API

[0396] Examples of concrete examples and prompts

[0397] As a concrete example, consider a scenario in which an autonomous vehicle is traveling within a certain city and the system acquires data showing that a particular intersection has been the site of many accidents in the past, and suggests an optimal route to avoid the intersection before reaching it. If the driver feels anxious or stressed, the system will provide detailed instructions to reassure them.

[0398] An example prompt for a generative AI model is:

[0399] "Based on data on intersections where accidents have occurred frequently over the past year, please generate road design improvement proposals that include those intersections. The intersection's coordinates are xxx, yyy, and the user is currently feeling anxious or stressed. Please provide specific improvement proposals and visualizations of the simulation, along with information on how to explain this to the user."

[0400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0401] Step 1:

[0402] Users collect road design information and traffic violation data and input it into the system using dedicated web forms and applications. The information input includes map data, existing road design drawings, intersection layouts, traffic light locations, and the locations, causes, and frequency of traffic accidents. This is how data is collected and input. The input data becomes the basic information needed for subsequent analysis.

[0403] Step 2:

[0404] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the data format and completeness to ensure that the data is in the correct format. Input: Data entered by the user. Output: Data whose consistency has been confirmed. Specifically, the data format is checked and missing values ​​are checked.

[0405] Step 3:

[0406] The terminal sends data whose format and completeness have been confirmed to the server. The server stores the received data in a database. Input: Data whose format and completeness have been confirmed. Output: Data stored in the database. Specifically, the data is sent via an HTTP request and recorded in the database.

[0407] Step 4:

[0408] The server inputs the saved data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road. Input: Saved road design information and traffic violation data. Output: Identified problem areas on the road. Specifically, the data is preprocessed and input into the generative AI model.

[0409] Step 5:

[0410] The server generates specific road improvement proposals based on the analysis results. For identified problem areas, it proposes optimal design changes to improve safety for cars and pedestrians. Input: Identified problem areas on the road. Output: Specific road improvement proposals. Specific operations include performing simulations using a generative AI model and proposing the results.

[0411] Step 6:

[0412] The server calculates the predicted effect of traffic accident reduction when the improvement proposal is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. Input: Specific road improvement proposal. Output: Predicted effect of traffic accident reduction. The specific operation is to predict the effect using the simulation model.

[0413] Step 7:

[0414] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Input: Prediction results and improvement proposals. Output: Reports and simulations displayed to officials. Specifically, the results are displayed using HTML and a graph generation library.

[0415] Step 8:

[0416] The user reviews the provided information and enters feedback as needed. Feedback may include questions about the proposal or requests for additional information. Input: Provided information and feedback. Output: Feedback content. Specific operations include collecting feedback using a web form.

[0417] Step 9:

[0418] The server re-runs the analytical model based on the feedback received from the user and performs a re-evaluation. If necessary, additional improvement suggestions are generated and provided to the local government, also including a visual simulation. Input: Received feedback. Output: Re-evaluation results and additional improvement suggestions. Specifically, the server re-runs the analytical model and simulates the results.

[0419] Step 10:

[0420] The server incorporates a new emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's emotions in real time as they are input and collects them as data. Input: User's emotional data. Output: Analyzed emotional state. Specifically, it performs real-time analysis using an emotion analysis algorithm.

[0421] Step 11:

[0422] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more thoughtful and detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into consideration to increase user satisfaction. Input: Analyzed emotional data. Output: Adjusted feedback and improvement proposals. Specifically, it adjusts the tone and content of the feedback response.

[0423] Step 12:

[0424] The server periodically monitors changes in emotional data and analyzes the user's emotional trends. This aims to improve long-term user engagement and improve feedback accuracy. Input: Changes in emotional data. Output: Analysis results and trend evaluation. Specifically, it performs cumulative analysis of data and trend analysis.

[0425] 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.

[0426] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0427] 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.

[0428] [Second embodiment]

[0429] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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."

[0441] 1. Data collection and input

[0442] Users collect road design information and traffic violation data. Road design information includes map data and existing road design drawings, while traffic violation data includes the locations, causes, and frequency of past traffic accidents. Users then enter this data into the system using dedicated web forms or applications.

[0443] 2. Data Receipt and Storage

[0444] The device temporarily stores the data entered by the user. During the storage process, a consistency check is performed to verify the completeness and format of the data. Once the consistency is confirmed, the data is sent from the device to the server.

[0445] 3. Saving to the database

[0446] The server stores the received data in a database, where it checks again for accuracy and completeness and records the data in the database in an appropriate manner.

[0447] 4. Data Analysis

[0448] The server inputs the stored data into the generative AI model and begins data analysis. The server uses the generative AI model to analyze the relationship between road design information and traffic violation data, and identifies problem areas on the road.

[0449] 5. Generation of improvement proposals

[0450] The server generates specific road improvement proposals based on the analysis results. The generative AI model proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. These simulations use a 3D model to show, for example, how traffic flow would change if a dedicated left-turn lane were added to an intersection.

[0451] 6. Prediction of a decrease in traffic accidents

[0452] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These predictions are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[0453] 7. Providing Suggestions and Feedback

[0454] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. The user reviews the information provided and provides feedback as needed. Feedback can include questions about the proposal or requests for additional information.

[0455] 8. Processing and reassessing feedback

[0456] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[0457] Example: Proposal for improving an intersection

[0458] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. The user enters detailed map data for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the improvement in safety. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. After the local government official reviews this information and provides feedback as needed, the server reevaluates and provides further optimal improvement proposals.

[0459] Thus, the present invention increases the likelihood of preventing accidents caused by violations of traffic rules, and improving road safety and efficiency.

[0460] The processing flow will be explained below.

[0461] Step 1:

[0462] The user collects road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, traffic light locations, etc. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[0463] Step 2:

[0464] Users enter the collected road design information and traffic violation data into the system using dedicated web forms and applications, ensuring that all data is complete and entered in the correct format.

[0465] Step 3:

[0466] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[0467] Step 4:

[0468] The device sends the data, whose format and integrity have been verified, to the server using a secure communication protocol to ensure confidentiality and security of the data.

[0469] Step 5:

[0470] The server stores the data received from the device in a database, during which the data is checked again for accuracy and completeness and recorded in the database in the appropriate format.

[0471] Step 6:

[0472] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[0473] Step 7:

[0474] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[0475] Step 8:

[0476] The server creates a simulation to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This visual simulation is useful for validating the effectiveness of the proposal.

[0477] Step 9:

[0478] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The calculation is based on the simulation results to predict the extent of the accident reduction effect.

[0479] Step 10:

[0480] The server compiles the calculated prediction results in a report that is easy for local government officials to understand. The report details the specific improvement plans and their effects.

[0481] Step 11:

[0482] The terminal displays the generated reports and simulation results to local government officials, who can easily access them, for example, through a web application dashboard.

[0483] Step 12:

[0484] The user reviews the information provided and provides feedback as needed, including questions about the proposal or requests for additional information.

[0485] Step 13:

[0486] The server re-runs the analytical model based on the feedback received from the user, re-evaluating and re-proposing, and generating new refinements as needed.

[0487] Step 14:

[0488] The server then revisits the proposed improvements and provides them to the local government along with the predicted results of their effects, thereby providing ongoing support to the local government in making optimal road improvements.

[0489] In this way, accidents caused by violations of traffic rules can be prevented, improving road safety and efficiency.

[0490] Example 1

[0491] 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."

[0492] In conventional road design and traffic safety measures, the process of identifying the locations and causes of traffic accidents and then considering improvement measures based on that information takes a lot of time and effort. Furthermore, there are limited ways to predict in advance how effective proposed improvement measures will actually be, making it difficult to implement efficient measures.

[0493] 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.

[0494] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for generating a visual simulation of the road improvement plan, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plan, means for providing the road improvement plan and the predicted results in a report format, and means for receiving feedback from users and reevaluating and re-proposing based on the feedback, thereby enabling efficient and effective prevention of traffic accidents and improvement of road safety.

[0495] "Road design information" is data relating to the shape, size, configuration, traffic signs, pavement condition, and surrounding environment of the road.

[0496] "Traffic violation data" refers to data that includes the locations, causes, and frequency of past traffic accidents and violations, as well as detailed information about those accidents and violations.

[0497] The "database" is a system for systematically and efficiently managing, storing, and searching collected road design information and traffic violation data.

[0498] "Generative AI model" refers to an artificial intelligence algorithm used to analyze collected data and generate road improvement proposals and predict their effectiveness in reducing traffic accidents.

[0499] "Analysis" refers to the analytical process of using collected road design information and traffic violation data to find correlations and identify problem areas.

[0500] "Problem sections of roads" refer to areas where traffic accidents frequently occur or where there are defects in the road structure.

[0501] "Road Improvement Proposals" refer to specific design changes or measures to improve the safety and efficiency of identified road problem areas.

[0502] "Visual simulation" refers to 3D models and animations that visually demonstrate the effects of generated road improvement proposals.

[0503] "Traffic accident reduction effect" refers to the rate or number of traffic accidents predicted to decrease as a result of the implementation of the proposed road improvement plan.

[0504] "Report" refers to a document summarizing the generated road improvement proposals and their predicted results in written form.

[0505] "Feedback" refers to comments such as questions about the proposal or requests for additional information provided by the user.

[0506] "Reevaluation" is the process of re-analyzing the product based on user feedback and considering new improvement proposals.

[0507] "Re-proposal" refers to submitting a proposal again that includes new improvement proposals generated as a result of re-evaluation.

[0508] The system is designed to collect road design information and traffic violation data, and then carry out a series of processes based on that data, including analysis, generation of improvement proposals, simulation, prediction, and feedback processing.

[0509] 1. Data collection and input

[0510] Users collect road design information (e.g., map data and existing road design drawings) and traffic violation data (e.g., locations, causes, and frequency of past traffic accidents) from public government databases and traffic control centers. Specifically, map data is obtained from OpenStreetMap, and traffic accident data is obtained from the National Police Agency database. Users enter this information using a dedicated web form or mobile application (e.g., Data Input Pro).

[0511] 2. Data Receipt and Storage

[0512] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. The device uses a JSON Schema Validator to verify that the data format is correct. For example, it verifies that map data is represented by the correct coordinates and that accident data is entered in the appropriate format. Once the data is confirmed to be consistent, it is sent to the server via an API.

[0513] 3. Saving to the database

[0514] The server checks the received data and stores it in a database (e.g. MySQL or PostgreSQL). The server further verifies the accuracy and completeness of the data before storing it, comparing it with other related tables and logging any inconsistencies.

[0515] 4. Data Analysis

[0516] The server inputs the stored data into a pre-trained generative AI model, which is built using TensorFlow and PyTorch. The server then uses the generative AI model to analyze the input data and identify problem areas based on the location and cause of traffic accidents. Specifically, it determines that left-turn accidents are more common at certain intersections.

[0517] 5. Generation of improvement proposals

[0518] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually demonstrate the effects of the proposed improvements.

[0519] 6. Prediction of a decrease in traffic accidents

[0520] The server uses the generative AI model to simulate the effect of reducing traffic accidents if the proposed improvement plan is implemented. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%."

[0521] 7. Providing Suggestions and Feedback

[0522] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The user reviews the proposals and enters feedback through a web form. For example, feedback such as "I would like more detailed explanations for the proposed left-turn lane locations" can be provided.

[0523] 8. Processing and reassessing feedback

[0524] The server takes the feedback received from the user and re-runs the analytical model. If necessary, it generates new refinements based on the feedback and presents them again, including visual simulations.

[0525] Prompt Sentence Examples

[0526] "Please explain the procedure for a local government official to confirm that there are many accidents occurring when turning left at a particular intersection and input detailed map data and traffic accident data from the past year into the system to consider improvement proposals."

[0527] Please provide details on the process by which the terminal receives the data entered by the user into the system, performs integrity checks, and then transmits it to the server.

[0528] In this way, the use of this system makes it possible to efficiently and effectively prevent traffic accidents and improve road safety.

[0529] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0530] Step 1:

[0531] Users collect road design information and traffic violation data. Users obtain data from public government databases and traffic control centers. Specifically, they collect map data from OpenStreetMap and traffic accident data from the National Police Agency database. These data are input.

[0532] Step 2:

[0533] Users enter this data into the system using dedicated web forms or mobile applications (e.g., Data Input Pro). Users upload map data as files and enter accident data directly into the form. This is where the input data is collected.

[0534] Step 3:

[0535] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. To confirm the data's consistency, the device uses a JSON Schema Validator to validate the format of the data. For example, it checks whether map data is expressed using the correct coordinates and whether accident data has been entered in the appropriate format. This consistency check generates data whose consistency has been confirmed.

[0536] Step 4:

[0537] The device sends the data, whose integrity has been confirmed, to the server via the API. The data sent includes map data and traffic accident data that have passed formal verification. The data is then entered into the server.

[0538] Step 5:

[0539] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Before storing, the server rechecks the data for accuracy and completeness and logs any inconsistencies. This results in a database record that is verified as accurate.

[0540] Step 6:

[0541] The server inputs the stored data into a pre-trained generative AI model. This model is built using TensorFlow and PyTorch. The server uses the generative AI model to begin analyzing the input data. For example, it identifies problem areas based on the location and cause of traffic accidents. As a result of this analysis, problem areas on the road are identified.

[0542] Step 7:

[0543] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually show the effects of the proposed improvement. This data processing results in a visual simulation.

[0544] Step 8:

[0545] The server uses the generative AI model to simulate the effect of introducing the proposed improvement plan on reducing traffic accidents. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%." This data calculation outputs a predicted reduction effect.

[0546] Step 9:

[0547] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The output is a report of the proposals and simulation results.

[0548] Step 10:

[0549] The user reviews the report and simulation results and enters their feedback through a web form. For example, they may provide feedback such as, "I would like more detailed explanations for the proposed left-turn lane locations." This feedback is collected as input data.

[0550] Step 11:

[0551] The server incorporates the feedback received from the user into the system and re-runs the analytical model. If new refinements are necessary based on the feedback, they are generated and presented again, including visual simulations. This re-evaluation generates new refinements and their simulation outputs.

[0552] (Application example 1)

[0553] 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."

[0554] Autonomous vehicles need to perform optimal driving behavior and route selection in real time, but conventional systems have difficulty performing instant and efficient analysis based on road design information and traffic violation data. Therefore, to further improve safety and efficiency, a system that can quickly analyze collected data and propose appropriate driving behavior is required. It is also important to increase the reliability of proposals by performing visual simulations.

[0555] 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.

[0556] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the problem areas on the road identified by the generative AI model, and means installed in the autonomous vehicle for proposing optimal driving behaviors and routes in real time, thereby enabling the autonomous vehicle to perform optimal driving behaviors based on the collected data in real time, thereby achieving both safety and efficiency.

[0557] "Road design information" is data relating to the structure and layout of roads, including map data and existing road design drawings.

[0558] "Traffic violation data" is information about traffic violations and accidents that have occurred in the past, and specifically includes data on the location, cause, and frequency of accidents.

[0559] A "generative AI model" is a system that uses artificial intelligence techniques to analyze specific data and make predictions or suggestions, for example, using deep learning or machine learning algorithms.

[0560] "Analysis" is the process of examining collected data in detail, extracting useful information from it, and deepening understanding.

[0561] "Real-time" means responding immediately to incoming data and events, for example, responding immediately to changes in traffic and road conditions.

[0562] "Driving behavior" refers to the specific maneuvers and actions performed by a vehicle, including all driving operations such as changing lanes, adjusting speed, and stopping.

[0563] "Route suggestions" are the best route or method of travel from a starting point to a destination, taking into account factors such as time, distance, and safety.

[0564] "Visual simulation" is a method of visually displaying analysis results and proposals, for example, using 3D models or graphical data displays to present them in an intuitively understandable way.

[0565] "Feedback" refers to reactions and opinions from users and system operators, and is used as a basis for the system to make improvements and reevaluate.

[0566] "Reevaluation" means reconsidering analyses and proposals that have already been made based on new data and feedback, and making corrections or improvements as necessary.

[0567] 1. Data collection and input

[0568] Users use autonomous vehicles to collect road design information and traffic violation data in real time. Road design information includes data acquired from the vehicle's GPS, cameras, and various sensors, while traffic violation data includes records of past traffic accidents and violations. This data is then entered into dedicated web forms and applications via the vehicle's onboard computing unit.

[0569] 2. Data Receipt and Storage

[0570] The terminal temporarily stores the data entered by the user. When the data is saved, it is checked for integrity and format. Once the integrity of the data is confirmed, it is sent from the terminal to the server.

[0571] 3. Saving to the database

[0572] The server stores the received data in a database, where the accuracy and completeness of the data are checked again and recorded in the database in an appropriate manner.

[0573] 4. Data Analysis

[0574] The server inputs the stored data into the generative AI model and begins data analysis. The generative AI model analyzes the relationship between road design information and traffic violation data, and identifies problem areas on roads for autonomous vehicles. For example, it identifies areas where traffic accidents frequently occur and dangerous areas on roads.

[0575] 5. Generation of improvement proposals

[0576] The server generates specific road improvement proposals based on the analysis results. The generative AI model then proposes optimal design changes for identified problem areas to improve vehicle and pedestrian safety. This could include, for example, adding a dedicated left-turn lane at a specific intersection. The server also creates simulations to visualize the proposed road improvements. These simulations, for example, use 3D models to show how the proposals will affect traffic flow.

[0577] 6. Prediction of a decrease in traffic accidents

[0578] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[0579] 7. Providing Suggestions and Feedback

[0580] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The results are presented in a dedicated dashboard for easy access by the vehicle's driving control system. The user can review the information provided and enter feedback as needed. For example, feedback can include questions about the proposals or requests for additional information.

[0581] 8. Processing and reassessing feedback

[0582] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, generating additional refinements as needed, which are also provided to the autonomous vehicle's driving system, including visual simulations.

[0583] Hardware and software used

[0584] Hardware: The computing unit, GPS, cameras, and sensors installed in the autonomous vehicle.

[0585] Software: Python programs, databases (e.g., MySQL), generative AI models (e.g., GPT-4).

[0586] Specific examples

[0587] Consider a case where an autonomous vehicle determines that a particular intersection has a high incidence of left-turn accidents. The user inputs detailed road design information for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the particular intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the safety improvement. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. The user reviews this information and provides feedback as needed, and the server reevaluates and provides further optimal improvement suggestions.

[0588] Prompt Sentence Examples

[0589] Analyze the following dataset and propose improvements to road design.

[0590] 1. Road design information: {road_design_data}

[0591] 2. Traffic violation data: {traffic_violation_data}

[0592] Based on the analysis results, present specific improvement proposals and predict their effectiveness.

[0593] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0594] Step 1:

[0595] A user uses the computing unit of an autonomous vehicle to collect road design information and traffic violation data. The input is real-time data obtained from hardware such as GPS, cameras, and sensors. The output is that this data is entered into a dedicated web form or application.

[0596] Step 2:

[0597] The terminal temporarily stores the data entered by the user. The input is the real-time data entered in step 1. At this stage, an integrity check is performed to verify the completeness and format of the data. The output is that the integrity-checked data is sent to the server.

[0598] Step 3:

[0599] The server stores the received data in the database. The input is the data sent in step 2. When storing, the data is checked again for accuracy and completeness and recorded in the database in an appropriate manner. The output is the state of the database with the data stored accurately.

[0600] Step 4:

[0601] The server inputs the stored data into the generative AI model and begins data analysis. The input is road design information and traffic violation data stored in the database. The server uses this data to identify problem areas on the road using the generative AI model. The output is a list of identified problem areas.

[0602] Step 5:

[0603] The server generates specific road improvement proposals based on the analysis results. The input is the list of problem areas obtained in step 4. The generative AI model is used to propose optimal design changes to improve safety. The output is a list of specific road improvement proposals, such as adding a dedicated left-turn lane at a specific intersection.

[0604] Step 6:

[0605] The server creates a simulation to visualize the proposed road improvement plan. The input is the road improvement plan generated in step 5. The simulation is displayed visually using a 3D model, etc. The output is the visualized simulation result.

[0606] Step 7:

[0607] The server calculates the predicted reduction in traffic accidents when the proposed improvement is implemented. The inputs are the road improvement proposal from Step 5 and the simulation results from Step 6. The generative AI model simulates the effect of the proposed design changes and calculates the predicted results. The output is statistics such as the rate of reduction in traffic accidents and the predicted number of reductions.

[0608] Step 8:

[0609] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The inputs are the prediction results calculated in step 7 and the simulation results from step 6. The results are displayed in a format that is easily accessible to the user and the vehicle's driving control system. The output is the results displayed on the driving system's dashboard.

[0610] Step 9:

[0611] The user checks the provided information and enters feedback as necessary. The input is the report or simulation results displayed in step 8. The feedback may include questions about the proposal or requests for additional information. The output is the feedback content.

[0612] Step 10:

[0613] The server re-runs and re-evaluates the analytical model based on the feedback received from the user. The input is the feedback obtained in step 9. If necessary, additional refinements are generated and provided to the autonomous vehicle's driving system, including a visual simulation. The output is the re-evaluated refinements and the simulation results.

[0614] 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.

[0615] 1. Data collection and input

[0616] Users collect road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users then enter this data into the system using dedicated web forms and applications.

[0617] 2. Data Receipt and Storage

[0618] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[0619] 3. Saving to the database

[0620] The terminal sends the data, whose format and completeness have been checked, to the server, which stores the received data in a database. During this process, the data is checked again for accuracy and completeness, and recorded in the database in the appropriate format.

[0621] 4. Data Analysis

[0622] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[0623] 5. Generation of improvement proposals

[0624] The server generates specific road improvement proposals based on the analysis results. It proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. The simulations use 3D models to show, for example, how traffic flow would change if a left-turn lane were added to an intersection.

[0625] 6. Prediction of a decrease in traffic accidents

[0626] The server calculates the predicted effect of traffic accident reduction if the improvement plan is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents or the predicted number of reductions.

[0627] 7. Providing Suggestions and Feedback

[0628] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Users review the information provided and provide feedback, if necessary. Feedback can include questions about the proposal or requests for additional information.

[0629] 8. Processing and reassessing feedback

[0630] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[0631] 9. Incorporating an Emotional Engine

[0632] The server incorporates a new emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's emotions in real time as they input data and collects it as data.

[0633] 10. Emotionally driven feedback response

[0634] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into account, aiming to increase user satisfaction.

[0635] 11. Monitoring Emotional Data

[0636] The server periodically monitors changes in emotional data and analyzes the user's emotional trends, aiming to improve long-term user engagement and improve feedback accuracy.

[0637] Example: Intersection improvement proposals and emotional feedback

[0638] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of accidents when turning left and would like to improve the intersection. The user enters detailed map data about the intersection and traffic accident data from the past year into the system. Additionally, the emotion engine collects the user's emotional state in real time. The device verifies the data integrity and sends it to the server. The server stores the data in a database and analyzes it using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation and adds a detailed explanation that takes customer satisfaction into consideration. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. The local government official reviews this information and provides feedback. The server then reevaluates the proposal based on the feedback and provides further optimal improvement proposals.

[0639] In this way, the present invention can prevent accidents caused by violations of traffic rules, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of improvement proposals and the level of satisfaction.

[0640] The processing flow will be explained below.

[0641] Step 1:

[0642] The user collects road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations, while traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[0643] Step 2:

[0644] Users enter the collected road design information and traffic violation data into the system using a dedicated web form or application. When entering data, they check to make sure that all data is complete and that there are no omissions.

[0645] Step 3:

[0646] The terminal temporarily stores the data entered by the user, and while storing it, checks the format and completeness of the data to ensure that it is accurate and in the proper format.

[0647] Step 4:

[0648] The device sends the data, whose format and integrity have been verified, to the server, using a secure communication protocol to ensure confidentiality and security of the data.

[0649] Step 5:

[0650] The server stores the data received from the device in a database, where it checks the accuracy and completeness of the data once again and records it in the database in the appropriate format.

[0651] Step 6:

[0652] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the relationship between road design information and traffic violation data to identify problem areas on the road.

[0653] Step 7:

[0654] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[0655] Step 8:

[0656] The server creates simulations to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This simulation is useful for validating the effectiveness of the proposals.

[0657] Step 9:

[0658] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The predicted results include the accident reduction rate and predicted number of reductions, which are used to show the specific effects.

[0659] Step 10:

[0660] The server uses an emotion engine to analyze the user's emotions in real time as they are input. The results of this analysis are stored in a database and used for subsequent feedback responses.

[0661] Step 11:

[0662] The server displays the generated reports and simulation results to local government officials. Based on the emotional data analyzed by the emotion engine, the tone and content of the report are adjusted, presenting the information in a format that is easy for the official to understand. For example, if the official is feeling stressed, more detailed and careful explanations are added.

[0663] Step 12:

[0664] The user checks the provided reports and simulation results and enters feedback as necessary. The emotion engine then analyzes the user's emotions when entering feedback and records them in a database.

[0665] Step 13:

[0666] The server re-executes the analysis model based on the feedback received from the user, re-evaluates and re-proposes, and generates new improvement proposals. The generated improvement proposals are visualized again through simulation.

[0667] Step 14:

[0668] The server then provides the revised improvement plan to the local government official. Based on the emotional data analyzed by the emotion engine, the presentation is made in a format and with content that is easy to understand. This allows the server to provide ongoing support to local governments in implementing optimal road improvements.

[0669] In this way, accidents caused by violations of traffic rules can be prevented, and road safety and efficiency can be improved. In addition, proposals can be made that take user feelings into account, which increases the likelihood of improvement proposals being accepted.

[0670] Example 2

[0671] 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."

[0672] To reduce traffic accidents, it is necessary to quickly propose effective road design improvement plans and present them to stakeholders in an actionable form. It is also important to optimize the proposals by taking into account user feedback and emotional states, thereby improving user satisfaction. Conventional systems have had difficulty meeting these requirements, making it impossible to resolve problems rationally and quickly.

[0673] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0674] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plans, means for providing the road improvement plans and the predicted results in a report format, means including an emotion analysis engine for analyzing the user's emotional state and collecting it as data, and means for adjusting reports and feedback responses based on the emotion analysis data. This makes it possible to improve the effectiveness of road design improvements and make optimal proposals that take the user's emotions into consideration.

[0675] "Road design information" refers to data related to road structure and design, such as map data, existing road design drawings, intersection locations, and traffic light locations.

[0676] "Traffic violation data" refers to data related to traffic violations, such as the location, cause, and frequency of traffic accidents in a specific section.

[0677] A "generative AI model" is a model that uses machine learning and deep learning techniques to analyze input data and identify and predict specific problems.

[0678] An "emotion analysis engine" is a system that analyzes user input and behavior in real time and evaluates and judges the user's emotional state.

[0679] "Means for storing in a database" refers to a method or system for integrating collected data and storing it in a database in an appropriate format.

[0680] "Road improvement proposals" are proposals for specific design changes to improve safety and convenience for problem areas on roads identified based on the analysis results.

[0681] "Traffic accident reduction effect" is the predicted reduction in the percentage or number of traffic accidents if the proposed road improvement plan is implemented.

[0682] The "means for adjusting feedback response" refers to a method or system for readjusting suggestions or responses to an appropriate form based on the user's emotional state and the feedback content.

[0683] "Visual simulation" is a technique that uses 3D models and graphics to visually represent proposed road improvements and their effects.

[0684] The "means for re-evaluating and re-proposing" refers to a method or system for re-executing the analysis model based on feedback from the user, and generating and proposing new improvement proposals.

[0685] The present invention relates to a system for analyzing road design information and traffic violation data to generate effective road improvement proposals. Specific embodiments for carrying out the present invention will be described below.

[0686] 1. Data collection and input

[0687] First, users collect road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users enter this data into the system using dedicated web forms and applications.

[0688] 2. Data Receipt and Storage

[0689] The terminal temporarily receives and stores the data entered by the user. At this stage, the terminal checks the data format and integrity. If invalid data is detected, an error message is displayed to the user, prompting them to re-enter the data.

[0690] 3. Saving to the database

[0691] The terminal sends the data, whose format and completeness have been checked, to the server. The server receives the data, checks it again, and stores it in the database. During this process, the server double-checks the accuracy and completeness of the data and records it in the database in the appropriate format.

[0692] 4. Data Analysis

[0693] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model uses machine learning and deep learning techniques, specifically libraries such as TensorFlow and PyTorch. In this process, various features are extracted from the loaded data, and problem areas on the road are identified as analysis results.

[0694] 5. Generation of improvement proposals

[0695] The server generates specific road improvement proposals based on the results of the data analysis. For example, these proposals may include adding dedicated left-turn lanes or changing the placement of traffic lights. These improvement proposals are visualized using 3D simulation software (e.g., Unity). The server runs the simulation and displays the changes in traffic flow in a 3D model.

[0696] 6. Prediction of a decrease in traffic accidents

[0697] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the proposed improvement is implemented. Specifically, it uses Monte Carlo simulation to estimate the extent to which the proposed design change will be effective. The results are output as the reduction rate and predicted number of traffic accidents.

[0698] 7. Providing Suggestions and Feedback

[0699] The device displays the generated reports and simulation results to local government officials, who can then view and download the results through a dedicated web application or dashboard. Users can then review the information provided and enter feedback through a dedicated form.

[0700] 8. Processing and reassessing feedback

[0701] The server receives user feedback, re-runs the analysis model, re-evaluates any newly proposed improvements, and generates additional improvements as needed, all while updating the 3D simulation and providing a visual presentation.

[0702] 9. Incorporating an Emotional Engine

[0703] The server incorporates an emotion engine that analyzes the user's emotional state in real time. The emotion engine uses technology such as IBM Watson Tone Analyzer. When the user enters data, the emotion engine analyzes the text and input actions, and collects the user's emotional state as data.

[0704] 10. Emotionally driven feedback response

[0705] The server adjusts the feedback response based on the collected emotional data. For example, if the server determines that the user is feeling stressed, it will provide more attentive support and detailed explanations. It also adjusts the improvement proposals based on the emotional data to improve user satisfaction.

[0706] 11. Monitoring Emotional Data

[0707] The server periodically monitors changes in emotional data and analyzes the user's emotional trends over the long term, which aims to improve long-term user engagement and improve feedback accuracy.

[0708] Example: Intersection improvement proposals and emotional feedback

[0709] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. When a user enters detailed map data about the intersection and traffic accident data from the past year into the system, the emotion engine collects the user's emotional state in real time. The device verifies the data's integrity and sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis identifies that adding a dedicated left-turn lane at the intersection would be effective. The server visualizes this suggestion in a 3D simulation and provides a detailed explanation. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. After the official reviews this information and provides feedback, the server reevaluates and provides further optimal improvement proposals.

[0710] In this way, the present invention provides an effective means for preventing traffic accidents, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of the suggestions and the level of satisfaction.

[0711] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0712] Step 1:

[0713] Users collect and input road design information and traffic violation data. They input map data, road design drawings, intersection layouts, and traffic light locations into the system using dedicated web forms and applications. They also input traffic violation data such as the location, cause, and frequency of accidents in specific sections. The input data is sent to the terminal via a dedicated application.

[0714] Input: Map data, road design, intersection layout, traffic light location, location, cause, and frequency data of traffic accidents

[0715] Output: Input data saved on the device

[0716] Step 2:

[0717] The terminal temporarily stores the data sent by the user. The terminal checks the format and completeness of the data to ensure consistency. Specifically, it runs a script to check for missing or incorrectly formatted data, and displays an error message to the user if invalid data is present.

[0718] Input: Data submitted by the user

[0719] Output: Data that has been checked for consistency, error message (if invalid data)

[0720] Step 3:

[0721] The device sends the data, whose integrity has been confirmed, to the server. The server receives the data and checks it again. Specifically, the server reconfirms the accuracy and completeness of the data and records it in the database in the appropriate format. During this process, the data is temporarily stored in cache memory, and after reconfirmation, it is saved in the official database.

[0722] Input: Data that has been integrity checked

[0723] Output: Data stored in the database

[0724] Step 4:

[0725] The server inputs the stored data into the generative AI model and begins analysis. During this process, the generative AI model uses machine learning algorithms (e.g., TensorFlow or PyTorch) to extract features from the data and generate analysis results. In particular, it calculates the accident rate and frequency for each intersection and performs scoring to identify problem areas.

[0726] Input: Data stored in a database

[0727] Output: Analysis results from the generative AI model (identification of problem areas)

[0728] Step 5:

[0729] The server generates specific road improvement proposals based on the results of data analysis. It devises optimal design change proposals (e.g., adding dedicated left-turn lanes or changing the placement of traffic lights) for identified problem areas. The server also visualizes these proposals using 3D simulation software (e.g., Unity). The server runs the simulation and displays changes in traffic flow in a 3D model.

[0730] Input: Analysis results from generative AI model

[0731] Output: Specific road improvement plans, visualization through 3D simulation

[0732] Step 6:

[0733] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the improvement plan is implemented. Specifically, it estimates the effect of new design changes using Monte Carlo simulation and other methods, and calculates the predicted results. The results are output as the reduction rate and predicted number of traffic accidents.

[0734] Input: Specific road improvement proposals

[0735] Output: Predicted results of traffic accident reduction effect

[0736] Step 7:

[0737] The terminal displays the generated reports and simulation results to local government officials. The results are then made available for viewing and download through a dedicated web application or dashboard. Users can then review this information and enter feedback through a dedicated form.

[0738] Input: Predicted results of traffic accident reduction, specific road improvement plans, 3D simulation results

[0739] Output: Feedback (by local government officials)

[0740] Step 8:

[0741] The server receives user feedback, re-runs the analysis model, re-evaluates newly proposed improvements, and generates additional refinements as needed, all while updating the 3D simulation and providing a visual presentation.

[0742] Input: Feedback (by local government officials)

[0743] Output: Reevaluated analysis results and suggested improvements, updated 3D simulation

[0744] Step 9:

[0745] The server incorporates an emotion engine to analyze the user's emotional state in real time. The emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's input and behavior, and collect the user's emotional state as data.

[0746] Input: User input data (feedback statements and actions)

[0747] Output: User's emotional state data

[0748] Step 10:

[0749] The server adjusts the feedback response based on the collected emotional data. If the user is feeling stressed, it provides more attentive support and detailed explanations. It also adjusts improvement proposals based on the emotional data, aiming to increase user satisfaction.

[0750] Input: User emotional state data, feedback data

[0751] Output: Adjusted feedback response, revised improvement proposals

[0752] Step 11:

[0753] The server periodically monitors changes in emotional data and analyzes the user's emotional trends over the long term, thereby understanding the user's emotional state and aiming to improve long-term user engagement and feedback accuracy.

[0754] Input: Continuously collected emotional state data

[0755] Output: User sentiment analysis results

[0756] At each step, the server, terminal, and user perform specific actions to advance the overall system processing. Each process processes and calculates data based on the input data, and passes the results on to the next step. This allows for effective proposals and responses to improve road safety.

[0757] (Application example 2)

[0758] 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."

[0759] Conventional road design and traffic management systems have had difficulty efficiently identifying the locations and causes of traffic accidents and proposing appropriate improvement plans. Furthermore, the proposed improvement plans often fail to take into account user emotions and usage conditions, resulting in poor acceptance. Furthermore, automated driving vehicles are insufficient in recognizing roads and intersections with a high risk of traffic accidents in real time and responding immediately to avoid them.

[0760] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the problem areas on the road identified by the generative AI model, means for calculating the predicted traffic accident reduction effect, means integrated into the navigation system of the driving vehicle to identify roads and intersections with a high traffic accident risk in real time and propose optimal routes, means for collecting driver emotional data and adjusting feedback responses according to the driver's emotional state, and means for providing the road improvement plans and prediction results in report format. This makes it possible to reduce the risk of traffic accidents and provide more acceptable improvement plans that take the driver's emotional state into consideration.

[0761] "Road design information" refers to detailed information about road infrastructure, such as map data, existing road design drawings, intersection locations, and traffic light locations.

[0762] "Traffic violation data" refers to data on violations such as the location, cause, and frequency of traffic accidents in a specific section.

[0763] A "database" is an information management system that organizes and stores collected information for later analysis and reference.

[0764] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and generates output tailored to a specific purpose.

[0765] A "navigation system" is an in-vehicle device and software that provides vehicle route guidance and a route to a destination.

[0766] "Emotional data" is information used to collect and analyze a user's emotional state in real time.

[0767] "Feedback" refers to information provided by users that the system receives and uses to improve its services and features.

[0768] "Traffic accident reduction effect" refers to the predicted reduction in the rate or number of traffic accidents after the proposed road improvement plan is implemented.

[0769] "Report format" is a method of providing analysis results and proposals in a document format that is easy to understand.

[0770] "Visual simulation" is a means of visually representing improvement proposals generated by a generative AI model using three-dimensional models, etc.

[0771] 1. Data collection and input

[0772] Users collect road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users enter this data into the system using dedicated web forms and applications.

[0773] 2. Data Receipt and Storage

[0774] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[0775] 3. Saving to the database

[0776] The terminal sends the data, whose format and completeness have been checked, to the server, which stores the received data in a database. During this process, the data is checked again for accuracy and completeness, and recorded in the database in the appropriate format.

[0777] 4. Data Analysis

[0778] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[0779] 5. Generation of improvement proposals

[0780] The server generates specific road improvement proposals based on the analysis results. It proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. The simulations use 3D models to show, for example, how traffic flow would change if a left-turn lane were added to an intersection.

[0781] 6. Prediction of a decrease in traffic accidents

[0782] The server calculates the predicted effect of traffic accident reduction if the improvement plan is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents or the predicted number of reductions.

[0783] 7. Providing Suggestions and Feedback

[0784] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Users review the information provided and provide feedback, if necessary. Feedback can include questions about the proposal or requests for additional information.

[0785] 8. Processing and reassessing feedback

[0786] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[0787] 9. Incorporating an Emotional Engine

[0788] The server incorporates a new emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's emotions in real time as they input data and collects it as data.

[0789] 10. Emotionally driven feedback response

[0790] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into account, aiming to increase user satisfaction.

[0791] 11. Monitoring Emotional Data

[0792] The server periodically monitors changes in emotional data and analyzes the user's emotional trends, aiming to improve long-term user engagement and improve feedback accuracy.

[0793] Hardware and software used

[0794] The implementation of this system uses the following hardware and software:

[0795] Hardware: Autonomous vehicle control systems, on-board computers, various sensors, digital panels

[0796] Software: Navigation system integration software, Python program, Scipy library, HTTP API

[0797] Examples of concrete examples and prompts

[0798] As a concrete example, consider a scenario in which an autonomous vehicle is traveling within a certain city and the system acquires data showing that a particular intersection has been the site of many accidents in the past, and suggests an optimal route to avoid the intersection before reaching it. If the driver feels anxious or stressed, the system will provide detailed instructions to reassure them.

[0799] An example prompt for a generative AI model is:

[0800] "Based on data on intersections where accidents have occurred frequently over the past year, please generate road design improvement proposals that include those intersections. The intersection's coordinates are xxx, yyy, and the user is currently feeling anxious or stressed. Please provide specific improvement proposals and visualizations of the simulation, along with information on how to explain this to the user."

[0801] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0802] Step 1:

[0803] Users collect road design information and traffic violation data and input it into the system using dedicated web forms and applications. The information input includes map data, existing road design drawings, intersection layouts, traffic light locations, and the locations, causes, and frequency of traffic accidents. This is how data is collected and input. The input data becomes the basic information needed for subsequent analysis.

[0804] Step 2:

[0805] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the data format and completeness to ensure that the data is in the correct format. Input: Data entered by the user. Output: Data whose consistency has been confirmed. Specifically, the data format is checked and missing values ​​are checked.

[0806] Step 3:

[0807] The terminal sends data whose format and completeness have been confirmed to the server. The server stores the received data in a database. Input: Data whose format and completeness have been confirmed. Output: Data stored in the database. Specifically, the data is sent via an HTTP request and recorded in the database.

[0808] Step 4:

[0809] The server inputs the saved data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road. Input: Saved road design information and traffic violation data. Output: Identified problem areas on the road. Specifically, the data is preprocessed and input into the generative AI model.

[0810] Step 5:

[0811] The server generates specific road improvement proposals based on the analysis results. For identified problem areas, it proposes optimal design changes to improve safety for cars and pedestrians. Input: Identified problem areas on the road. Output: Specific road improvement proposals. Specific operations include performing simulations using a generative AI model and proposing the results.

[0812] Step 6:

[0813] The server calculates the predicted effect of traffic accident reduction when the improvement proposal is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. Input: Specific road improvement proposal. Output: Predicted effect of traffic accident reduction. The specific operation is to predict the effect using the simulation model.

[0814] Step 7:

[0815] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Input: Prediction results and improvement proposals. Output: Reports and simulations displayed to officials. Specifically, the results are displayed using HTML and a graph generation library.

[0816] Step 8:

[0817] The user reviews the provided information and enters feedback as needed. Feedback may include questions about the proposal or requests for additional information. Input: Provided information and feedback. Output: Feedback content. Specific operations include collecting feedback using a web form.

[0818] Step 9:

[0819] The server re-runs the analytical model based on the feedback received from the user and performs a re-evaluation. If necessary, additional improvement suggestions are generated and provided to the local government, also including a visual simulation. Input: Received feedback. Output: Re-evaluation results and additional improvement suggestions. Specifically, the server re-runs the analytical model and simulates the results.

[0820] Step 10:

[0821] The server incorporates a new emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's emotions in real time as they are input and collects them as data. Input: User's emotional data. Output: Analyzed emotional state. Specifically, it performs real-time analysis using an emotion analysis algorithm.

[0822] Step 11:

[0823] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more thoughtful and detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into consideration to increase user satisfaction. Input: Analyzed emotional data. Output: Adjusted feedback and improvement proposals. Specifically, it adjusts the tone and content of the feedback response.

[0824] Step 12:

[0825] The server periodically monitors changes in emotional data and analyzes the user's emotional trends. This aims to improve long-term user engagement and improve feedback accuracy. Input: Changes in emotional data. Output: Analysis results and trend evaluation. Specifically, it performs cumulative analysis of data and trend analysis.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] [Third embodiment]

[0830] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0831] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0832] 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).

[0833] 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.

[0834] 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.

[0835] 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).

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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."

[0842] 1. Data collection and input

[0843] Users collect road design information and traffic violation data. Road design information includes map data and existing road design drawings, while traffic violation data includes the locations, causes, and frequency of past traffic accidents. Users then enter this data into the system using dedicated web forms or applications.

[0844] 2. Data Receipt and Storage

[0845] The device temporarily stores the data entered by the user. During the storage process, a consistency check is performed to verify the completeness and format of the data. Once the consistency is confirmed, the data is sent from the device to the server.

[0846] 3. Saving to the database

[0847] The server stores the received data in a database, where it checks again for accuracy and completeness and records the data in the database in an appropriate manner.

[0848] 4. Data Analysis

[0849] The server inputs the stored data into the generative AI model and begins data analysis. The server uses the generative AI model to analyze the relationship between road design information and traffic violation data, and identifies problem areas on the road.

[0850] 5. Generation of improvement proposals

[0851] The server generates specific road improvement proposals based on the analysis results. The generative AI model proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. These simulations use a 3D model to show, for example, how traffic flow would change if a dedicated left-turn lane were added to an intersection.

[0852] 6. Prediction of a decrease in traffic accidents

[0853] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These predictions are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[0854] 7. Providing Suggestions and Feedback

[0855] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. The user reviews the information provided and provides feedback as needed. Feedback can include questions about the proposal or requests for additional information.

[0856] 8. Processing and reassessing feedback

[0857] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[0858] Example: Proposal for improving an intersection

[0859] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. The user enters detailed map data for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the improvement in safety. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. After the local government official reviews this information and provides feedback as needed, the server reevaluates and provides further optimal improvement proposals.

[0860] Thus, the present invention increases the likelihood of preventing accidents caused by violations of traffic rules, and improving road safety and efficiency.

[0861] The processing flow will be explained below.

[0862] Step 1:

[0863] The user collects road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, traffic light locations, etc. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[0864] Step 2:

[0865] Users enter the collected road design information and traffic violation data into the system using dedicated web forms and applications, ensuring that all data is complete and entered in the correct format.

[0866] Step 3:

[0867] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[0868] Step 4:

[0869] The device sends the data, whose format and integrity have been verified, to the server using a secure communication protocol to ensure confidentiality and security of the data.

[0870] Step 5:

[0871] The server stores the data received from the device in a database, during which the data is checked again for accuracy and completeness and recorded in the database in the appropriate format.

[0872] Step 6:

[0873] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[0874] Step 7:

[0875] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[0876] Step 8:

[0877] The server creates a simulation to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This visual simulation is useful for validating the effectiveness of the proposal.

[0878] Step 9:

[0879] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The calculation is based on the simulation results to predict the extent of the accident reduction effect.

[0880] Step 10:

[0881] The server compiles the calculated prediction results in a report that is easy for local government officials to understand. The report details the specific improvement plans and their effects.

[0882] Step 11:

[0883] The terminal displays the generated reports and simulation results to local government officials, who can easily access them, for example, through a web application dashboard.

[0884] Step 12:

[0885] The user reviews the information provided and provides feedback as needed, including questions about the proposal or requests for additional information.

[0886] Step 13:

[0887] The server re-runs the analytical model based on the feedback received from the user, re-evaluating and re-proposing, and generating new refinements as needed.

[0888] Step 14:

[0889] The server then revisits the proposed improvements and provides them to the local government along with the predicted results of their effects, thereby providing ongoing support to the local government in making optimal road improvements.

[0890] In this way, accidents caused by violations of traffic rules can be prevented, improving road safety and efficiency.

[0891] Example 1

[0892] 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."

[0893] In conventional road design and traffic safety measures, the process of identifying the locations and causes of traffic accidents and then considering improvement measures based on that information takes a lot of time and effort. Furthermore, there are limited ways to predict in advance how effective proposed improvement measures will actually be, making it difficult to implement efficient measures.

[0894] 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.

[0895] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for generating a visual simulation of the road improvement plan, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plan, means for providing the road improvement plan and the predicted results in a report format, and means for receiving feedback from users and reevaluating and re-proposing based on the feedback, thereby enabling efficient and effective prevention of traffic accidents and improvement of road safety.

[0896] "Road design information" is data relating to the shape, size, configuration, traffic signs, pavement condition, and surrounding environment of the road.

[0897] "Traffic violation data" refers to data that includes the locations, causes, and frequency of past traffic accidents and violations, as well as detailed information about those accidents and violations.

[0898] The "database" is a system for systematically and efficiently managing, storing, and searching collected road design information and traffic violation data.

[0899] "Generative AI model" refers to an artificial intelligence algorithm used to analyze collected data and generate road improvement proposals and predict their effectiveness in reducing traffic accidents.

[0900] "Analysis" refers to the analytical process of using collected road design information and traffic violation data to find correlations and identify problem areas.

[0901] "Problem sections of roads" refer to areas where traffic accidents frequently occur or where there are defects in the road structure.

[0902] "Road Improvement Proposals" refer to specific design changes or measures to improve the safety and efficiency of identified road problem areas.

[0903] "Visual simulation" refers to 3D models and animations that visually demonstrate the effects of generated road improvement proposals.

[0904] "Traffic accident reduction effect" refers to the rate or number of traffic accidents predicted to decrease as a result of the implementation of the proposed road improvement plan.

[0905] "Report" refers to a document summarizing the generated road improvement proposals and their predicted results in written form.

[0906] "Feedback" refers to comments such as questions about the proposal or requests for additional information provided by the user.

[0907] "Reevaluation" is the process of re-analyzing the product based on user feedback and considering new improvement proposals.

[0908] "Re-proposal" refers to submitting a proposal again that includes new improvement proposals generated as a result of re-evaluation.

[0909] The system is designed to collect road design information and traffic violation data, and then carry out a series of processes based on that data, including analysis, generation of improvement proposals, simulation, prediction, and feedback processing.

[0910] 1. Data collection and input

[0911] Users collect road design information (e.g., map data and existing road design drawings) and traffic violation data (e.g., locations, causes, and frequency of past traffic accidents) from public government databases and traffic control centers. Specifically, map data is obtained from OpenStreetMap, and traffic accident data is obtained from the National Police Agency database. Users enter this information using a dedicated web form or mobile application (e.g., Data Input Pro).

[0912] 2. Data Receipt and Storage

[0913] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. The device uses a JSON Schema Validator to verify that the data format is correct. For example, it verifies that map data is represented by the correct coordinates and that accident data is entered in the appropriate format. Once the data is confirmed to be consistent, it is sent to the server via an API.

[0914] 3. Saving to the database

[0915] The server checks the received data and stores it in a database (e.g. MySQL or PostgreSQL). The server further verifies the accuracy and completeness of the data before storing it, comparing it with other related tables and logging any inconsistencies.

[0916] 4. Data Analysis

[0917] The server inputs the stored data into a pre-trained generative AI model, which is built using TensorFlow and PyTorch. The server then uses the generative AI model to analyze the input data and identify problem areas based on the location and cause of traffic accidents. Specifically, it determines that left-turn accidents are more common at certain intersections.

[0918] 5. Generation of improvement proposals

[0919] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually demonstrate the effects of the proposed improvements.

[0920] 6. Prediction of a decrease in traffic accidents

[0921] The server uses the generative AI model to simulate the effect of reducing traffic accidents if the proposed improvement plan is implemented. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%."

[0922] 7. Providing Suggestions and Feedback

[0923] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The user reviews the proposals and enters feedback through a web form. For example, feedback such as "I would like more detailed explanations for the proposed left-turn lane locations" can be provided.

[0924] 8. Processing and reassessing feedback

[0925] The server takes the feedback received from the user and re-runs the analytical model. If necessary, it generates new refinements based on the feedback and presents them again, including visual simulations.

[0926] Prompt Sentence Examples

[0927] "Please explain the procedure for a local government official to confirm that there are many accidents occurring when turning left at a particular intersection and input detailed map data and traffic accident data from the past year into the system to consider improvement proposals."

[0928] Please provide details on the process by which the terminal receives the data entered by the user into the system, performs integrity checks, and then transmits it to the server.

[0929] In this way, the use of this system makes it possible to efficiently and effectively prevent traffic accidents and improve road safety.

[0930] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0931] Step 1:

[0932] Users collect road design information and traffic violation data. Users obtain data from public government databases and traffic control centers. Specifically, they collect map data from OpenStreetMap and traffic accident data from the National Police Agency database. These data are input.

[0933] Step 2:

[0934] Users enter this data into the system using dedicated web forms or mobile applications (e.g., Data Input Pro). Users upload map data as files and enter accident data directly into the form. This is where the input data is collected.

[0935] Step 3:

[0936] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. To confirm the data's consistency, the device uses a JSON Schema Validator to validate the format of the data. For example, it checks whether map data is expressed using the correct coordinates and whether accident data has been entered in the appropriate format. This consistency check generates data whose consistency has been confirmed.

[0937] Step 4:

[0938] The device sends the data, whose integrity has been confirmed, to the server via the API. The data sent includes map data and traffic accident data that have passed formal verification. The data is then entered into the server.

[0939] Step 5:

[0940] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Before storing, the server rechecks the data for accuracy and completeness and logs any inconsistencies. This results in a database record that is verified as accurate.

[0941] Step 6:

[0942] The server inputs the stored data into a pre-trained generative AI model. This model is built using TensorFlow and PyTorch. The server uses the generative AI model to begin analyzing the input data. For example, it identifies problem areas based on the location and cause of traffic accidents. As a result of this analysis, problem areas on the road are identified.

[0943] Step 7:

[0944] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually show the effects of the proposed improvement. This data processing results in a visual simulation.

[0945] Step 8:

[0946] The server uses the generative AI model to simulate the effect of introducing the proposed improvement plan on reducing traffic accidents. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%." This data calculation outputs a predicted reduction effect.

[0947] Step 9:

[0948] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The output is a report of the proposals and simulation results.

[0949] Step 10:

[0950] The user reviews the report and simulation results and enters their feedback through a web form. For example, they may provide feedback such as, "I would like more detailed explanations for the proposed left-turn lane locations." This feedback is collected as input data.

[0951] Step 11:

[0952] The server incorporates the feedback received from the user into the system and re-runs the analytical model. If new refinements are necessary based on the feedback, they are generated and presented again, including visual simulations. This re-evaluation generates new refinements and their simulation outputs.

[0953] (Application example 1)

[0954] 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."

[0955] Autonomous vehicles need to perform optimal driving behavior and route selection in real time, but conventional systems have difficulty performing instant and efficient analysis based on road design information and traffic violation data. Therefore, to further improve safety and efficiency, a system that can quickly analyze collected data and propose appropriate driving behavior is required. It is also important to increase the reliability of proposals by performing visual simulations.

[0956] 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.

[0957] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the problem areas on the road identified by the generative AI model, and means installed in the autonomous vehicle for proposing optimal driving behaviors and routes in real time, thereby enabling the autonomous vehicle to perform optimal driving behaviors based on the collected data in real time, thereby achieving both safety and efficiency.

[0958] "Road design information" is data relating to the structure and layout of roads, including map data and existing road design drawings.

[0959] "Traffic violation data" is information about traffic violations and accidents that have occurred in the past, and specifically includes data on the location, cause, and frequency of accidents.

[0960] A "generative AI model" is a system that uses artificial intelligence techniques to analyze specific data and make predictions or suggestions, for example, using deep learning or machine learning algorithms.

[0961] "Analysis" is the process of examining collected data in detail, extracting useful information from it, and deepening understanding.

[0962] "Real-time" means responding immediately to incoming data and events, for example, responding immediately to changes in traffic and road conditions.

[0963] "Driving behavior" refers to the specific maneuvers and actions performed by a vehicle, including all driving operations such as changing lanes, adjusting speed, and stopping.

[0964] "Route suggestions" are the best route or method of travel from a starting point to a destination, taking into account factors such as time, distance, and safety.

[0965] "Visual simulation" is a method of visually displaying analysis results and proposals, for example, using 3D models or graphical data displays to present them in an intuitively understandable way.

[0966] "Feedback" refers to reactions and opinions from users and system operators, and is used as a basis for the system to make improvements and reevaluate.

[0967] "Reevaluation" means reconsidering analyses and proposals that have already been made based on new data and feedback, and making corrections or improvements as necessary.

[0968] 1. Data collection and input

[0969] Users use autonomous vehicles to collect road design information and traffic violation data in real time. Road design information includes data acquired from the vehicle's GPS, cameras, and various sensors, while traffic violation data includes records of past traffic accidents and violations. This data is then entered into dedicated web forms and applications via the vehicle's onboard computing unit.

[0970] 2. Data Receipt and Storage

[0971] The terminal temporarily stores the data entered by the user. When the data is saved, it is checked for integrity and format. Once the integrity of the data is confirmed, it is sent from the terminal to the server.

[0972] 3. Saving to the database

[0973] The server stores the received data in a database, where the accuracy and completeness of the data are checked again and recorded in the database in an appropriate manner.

[0974] 4. Data Analysis

[0975] The server inputs the stored data into the generative AI model and begins data analysis. The generative AI model analyzes the relationship between road design information and traffic violation data, and identifies problem areas on roads for autonomous vehicles. For example, it identifies areas where traffic accidents frequently occur and dangerous areas on roads.

[0976] 5. Generation of improvement proposals

[0977] The server generates specific road improvement proposals based on the analysis results. The generative AI model then proposes optimal design changes for identified problem areas to improve vehicle and pedestrian safety. This could include, for example, adding a dedicated left-turn lane at a specific intersection. The server also creates simulations to visualize the proposed road improvements. These simulations, for example, use 3D models to show how the proposals will affect traffic flow.

[0978] 6. Prediction of a decrease in traffic accidents

[0979] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[0980] 7. Providing Suggestions and Feedback

[0981] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The results are presented in a dedicated dashboard for easy access by the vehicle's driving control system. The user can review the information provided and enter feedback as needed. For example, feedback can include questions about the proposals or requests for additional information.

[0982] 8. Processing and reassessing feedback

[0983] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, generating additional refinements as needed, which are also provided to the autonomous vehicle's driving system, including visual simulations.

[0984] Hardware and software used

[0985] Hardware: The computing unit, GPS, cameras, and sensors installed in the autonomous vehicle.

[0986] Software: Python programs, databases (e.g., MySQL), generative AI models (e.g., GPT-4).

[0987] Specific examples

[0988] Consider a case where an autonomous vehicle determines that a particular intersection has a high incidence of left-turn accidents. The user inputs detailed road design information for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the particular intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the safety improvement. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. The user reviews this information and provides feedback as needed, and the server reevaluates and provides further optimal improvement suggestions.

[0989] Prompt Sentence Examples

[0990] Analyze the following dataset and propose improvements to road design.

[0991] 1. Road design information: {road_design_data}

[0992] 2. Traffic violation data: {traffic_violation_data}

[0993] Based on the analysis results, present specific improvement proposals and predict their effectiveness.

[0994] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0995] Step 1:

[0996] A user uses the computing unit of an autonomous vehicle to collect road design information and traffic violation data. The input is real-time data obtained from hardware such as GPS, cameras, and sensors. The output is that this data is entered into a dedicated web form or application.

[0997] Step 2:

[0998] The terminal temporarily stores the data entered by the user. The input is the real-time data entered in step 1. At this stage, an integrity check is performed to verify the completeness and format of the data. The output is that the integrity-checked data is sent to the server.

[0999] Step 3:

[1000] The server stores the received data in the database. The input is the data sent in step 2. When storing, the data is checked again for accuracy and completeness and recorded in the database in an appropriate manner. The output is the state of the database with the data stored accurately.

[1001] Step 4:

[1002] The server inputs the stored data into the generative AI model and begins data analysis. The input is road design information and traffic violation data stored in the database. The server uses this data to identify problem areas on the road using the generative AI model. The output is a list of identified problem areas.

[1003] Step 5:

[1004] The server generates specific road improvement proposals based on the analysis results. The input is the list of problem areas obtained in step 4. The generative AI model is used to propose optimal design changes to improve safety. The output is a list of specific road improvement proposals, such as adding a dedicated left-turn lane at a specific intersection.

[1005] Step 6:

[1006] The server creates a simulation to visualize the proposed road improvement plan. The input is the road improvement plan generated in step 5. The simulation is displayed visually using a 3D model, etc. The output is the visualized simulation result.

[1007] Step 7:

[1008] The server calculates the predicted reduction in traffic accidents when the proposed improvement is implemented. The inputs are the road improvement proposal from Step 5 and the simulation results from Step 6. The generative AI model simulates the effect of the proposed design changes and calculates the predicted results. The output is statistics such as the rate of reduction in traffic accidents and the predicted number of reductions.

[1009] Step 8:

[1010] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The inputs are the prediction results calculated in step 7 and the simulation results from step 6. The results are displayed in a format that is easily accessible to the user and the vehicle's driving control system. The output is the results displayed on the driving system's dashboard.

[1011] Step 9:

[1012] The user checks the provided information and enters feedback as necessary. The input is the report or simulation results displayed in step 8. The feedback may include questions about the proposal or requests for additional information. The output is the feedback content.

[1013] Step 10:

[1014] The server re-runs and re-evaluates the analytical model based on the feedback received from the user. The input is the feedback obtained in step 9. If necessary, additional refinements are generated and provided to the autonomous vehicle's driving system, including a visual simulation. The output is the re-evaluated refinements and the simulation results.

[1015] 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.

[1016] 1. Data collection and input

[1017] Users collect road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users then enter this data into the system using dedicated web forms and applications.

[1018] 2. Data Receipt and Storage

[1019] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[1020] 3. Saving to the database

[1021] The terminal sends the data, whose format and completeness have been checked, to the server, which stores the received data in a database. During this process, the data is checked again for accuracy and completeness, and recorded in the database in the appropriate format.

[1022] 4. Data Analysis

[1023] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[1024] 5. Generation of improvement proposals

[1025] The server generates specific road improvement proposals based on the analysis results. It proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. The simulations use 3D models to show, for example, how traffic flow would change if a left-turn lane were added to an intersection.

[1026] 6. Prediction of a decrease in traffic accidents

[1027] The server calculates the predicted effect of traffic accident reduction if the improvement plan is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents or the predicted number of reductions.

[1028] 7. Providing Suggestions and Feedback

[1029] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Users review the information provided and provide feedback, if necessary. Feedback can include questions about the proposal or requests for additional information.

[1030] 8. Processing and reassessing feedback

[1031] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[1032] 9. Incorporating an Emotional Engine

[1033] The server incorporates a new emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's emotions in real time as they input data and collects it as data.

[1034] 10. Emotionally driven feedback response

[1035] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into account, aiming to increase user satisfaction.

[1036] 11. Monitoring Emotional Data

[1037] The server periodically monitors changes in emotional data and analyzes the user's emotional trends, aiming to improve long-term user engagement and improve feedback accuracy.

[1038] Example: Intersection improvement proposals and emotional feedback

[1039] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of accidents when turning left and would like to improve the intersection. The user enters detailed map data about the intersection and traffic accident data from the past year into the system. Additionally, the emotion engine collects the user's emotional state in real time. The device verifies the data integrity and sends it to the server. The server stores the data in a database and analyzes it using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation and adds a detailed explanation that takes customer satisfaction into consideration. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. The local government official reviews this information and provides feedback. The server then reevaluates the proposal based on the feedback and provides further optimal improvement proposals.

[1040] In this way, the present invention can prevent accidents caused by violations of traffic rules, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of improvement proposals and the level of satisfaction.

[1041] The processing flow will be explained below.

[1042] Step 1:

[1043] The user collects road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations, while traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[1044] Step 2:

[1045] Users enter the collected road design information and traffic violation data into the system using a dedicated web form or application. When entering data, they check to make sure that all data is complete and that there are no omissions.

[1046] Step 3:

[1047] The terminal temporarily stores the data entered by the user, and while storing it, checks the format and completeness of the data to ensure that it is accurate and in the proper format.

[1048] Step 4:

[1049] The device sends the data, whose format and integrity have been verified, to the server, using a secure communication protocol to ensure confidentiality and security of the data.

[1050] Step 5:

[1051] The server stores the data received from the device in a database, where it checks the accuracy and completeness of the data once again and records it in the database in the appropriate format.

[1052] Step 6:

[1053] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the relationship between road design information and traffic violation data to identify problem areas on the road.

[1054] Step 7:

[1055] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[1056] Step 8:

[1057] The server creates simulations to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This simulation is useful for validating the effectiveness of the proposals.

[1058] Step 9:

[1059] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The predicted results include the accident reduction rate and predicted number of reductions, which are used to show the specific effects.

[1060] Step 10:

[1061] The server uses an emotion engine to analyze the user's emotions in real time as they are input. The results of this analysis are stored in a database and used for subsequent feedback responses.

[1062] Step 11:

[1063] The server displays the generated reports and simulation results to local government officials. Based on the emotional data analyzed by the emotion engine, the tone and content of the report are adjusted, presenting the information in a format that is easy for the official to understand. For example, if the official is feeling stressed, more detailed and careful explanations are added.

[1064] Step 12:

[1065] The user checks the provided reports and simulation results and enters feedback as necessary. The emotion engine then analyzes the user's emotions when entering feedback and records them in a database.

[1066] Step 13:

[1067] The server re-executes the analysis model based on the feedback received from the user, re-evaluates and re-proposes, and generates new improvement proposals. The generated improvement proposals are visualized again through simulation.

[1068] Step 14:

[1069] The server then provides the revised improvement plan to the local government official. Based on the emotional data analyzed by the emotion engine, the presentation is made in a format and with content that is easy to understand. This allows the server to provide ongoing support to local governments in implementing optimal road improvements.

[1070] In this way, accidents caused by violations of traffic rules can be prevented, and road safety and efficiency can be improved. In addition, proposals can be made that take user feelings into account, which increases the likelihood of improvement proposals being accepted.

[1071] Example 2

[1072] 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."

[1073] To reduce traffic accidents, it is necessary to quickly propose effective road design improvement plans and present them to stakeholders in an actionable form. It is also important to optimize the proposals by taking into account user feedback and emotional states, thereby improving user satisfaction. Conventional systems have had difficulty meeting these requirements, making it impossible to resolve problems rationally and quickly.

[1074] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1075] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plans, means for providing the road improvement plans and the predicted results in a report format, means including an emotion analysis engine for analyzing the user's emotional state and collecting it as data, and means for adjusting reports and feedback responses based on the emotion analysis data. This makes it possible to improve the effectiveness of road design improvements and make optimal proposals that take the user's emotions into consideration.

[1076] "Road design information" refers to data related to road structure and design, such as map data, existing road design drawings, intersection locations, and traffic light locations.

[1077] "Traffic violation data" refers to data related to traffic violations, such as the location, cause, and frequency of traffic accidents in a specific section.

[1078] A "generative AI model" is a model that uses machine learning and deep learning techniques to analyze input data and identify and predict specific problems.

[1079] An "emotion analysis engine" is a system that analyzes user input and behavior in real time and evaluates and judges the user's emotional state.

[1080] "Means for storing in a database" refers to a method or system for integrating collected data and storing it in a database in an appropriate format.

[1081] "Road improvement proposals" are proposals for specific design changes to improve safety and convenience for problem areas on roads identified based on the analysis results.

[1082] "Traffic accident reduction effect" is the predicted reduction in the percentage or number of traffic accidents if the proposed road improvement plan is implemented.

[1083] The "means for adjusting feedback response" refers to a method or system for readjusting suggestions or responses to an appropriate form based on the user's emotional state and the feedback content.

[1084] "Visual simulation" is a technique that uses 3D models and graphics to visually represent proposed road improvements and their effects.

[1085] The "means for re-evaluating and re-proposing" refers to a method or system for re-executing the analysis model based on feedback from the user, and generating and proposing new improvement proposals.

[1086] The present invention relates to a system for analyzing road design information and traffic violation data to generate effective road improvement proposals. Specific embodiments for carrying out the present invention will be described below.

[1087] 1. Data collection and input

[1088] First, users collect road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users enter this data into the system using dedicated web forms and applications.

[1089] 2. Data Receipt and Storage

[1090] The terminal temporarily receives and stores the data entered by the user. At this stage, the terminal checks the data format and integrity. If invalid data is detected, an error message is displayed to the user, prompting them to re-enter the data.

[1091] 3. Saving to the database

[1092] The terminal sends the data, whose format and completeness have been checked, to the server. The server receives the data, checks it again, and stores it in the database. During this process, the server double-checks the accuracy and completeness of the data and records it in the database in the appropriate format.

[1093] 4. Data Analysis

[1094] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model uses machine learning and deep learning techniques, specifically libraries such as TensorFlow and PyTorch. In this process, various features are extracted from the loaded data, and problem areas on the road are identified as analysis results.

[1095] 5. Generation of improvement proposals

[1096] The server generates specific road improvement proposals based on the results of the data analysis. For example, these proposals may include adding dedicated left-turn lanes or changing the placement of traffic lights. These improvement proposals are visualized using 3D simulation software (e.g., Unity). The server runs the simulation and displays the changes in traffic flow in a 3D model.

[1097] 6. Prediction of a decrease in traffic accidents

[1098] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the proposed improvement is implemented. Specifically, it uses Monte Carlo simulation to estimate the extent to which the proposed design change will be effective. The results are output as the reduction rate and predicted number of traffic accidents.

[1099] 7. Providing Suggestions and Feedback

[1100] The device displays the generated reports and simulation results to local government officials, who can then view and download the results through a dedicated web application or dashboard. Users can then review the information provided and enter feedback through a dedicated form.

[1101] 8. Processing and reassessing feedback

[1102] The server receives user feedback, re-runs the analysis model, re-evaluates any newly proposed improvements, and generates additional improvements as needed, all while updating the 3D simulation and providing a visual presentation.

[1103] 9. Incorporating an Emotional Engine

[1104] The server incorporates an emotion engine that analyzes the user's emotional state in real time. The emotion engine uses technology such as IBM Watson Tone Analyzer. When the user enters data, the emotion engine analyzes the text and input actions, and collects the user's emotional state as data.

[1105] 10. Emotionally driven feedback response

[1106] The server adjusts the feedback response based on the collected emotional data. For example, if the server determines that the user is feeling stressed, it will provide more attentive support and detailed explanations. It also adjusts the improvement proposals based on the emotional data to improve user satisfaction.

[1107] 11. Monitoring Emotional Data

[1108] The server periodically monitors changes in emotional data and analyzes the user's emotional trends over the long term, which aims to improve long-term user engagement and improve feedback accuracy.

[1109] Example: Intersection improvement proposals and emotional feedback

[1110] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. When a user enters detailed map data about the intersection and traffic accident data from the past year into the system, the emotion engine collects the user's emotional state in real time. The device verifies the data's integrity and sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis identifies that adding a dedicated left-turn lane at the intersection would be effective. The server visualizes this suggestion in a 3D simulation and provides a detailed explanation. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. After the official reviews this information and provides feedback, the server reevaluates and provides further optimal improvement proposals.

[1111] In this way, the present invention provides an effective means for preventing traffic accidents, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of the suggestions and the level of satisfaction.

[1112] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1113] Step 1:

[1114] Users collect and input road design information and traffic violation data. They input map data, road design drawings, intersection layouts, and traffic light locations into the system using dedicated web forms and applications. They also input traffic violation data such as the location, cause, and frequency of accidents in specific sections. The input data is sent to the terminal via a dedicated application.

[1115] Input: Map data, road design, intersection layout, traffic light location, location, cause, and frequency data of traffic accidents

[1116] Output: Input data saved on the device

[1117] Step 2:

[1118] The terminal temporarily stores the data sent by the user. The terminal checks the format and completeness of the data to ensure consistency. Specifically, it runs a script to check for missing or incorrectly formatted data, and displays an error message to the user if invalid data is present.

[1119] Input: Data submitted by the user

[1120] Output: Data that has been checked for consistency, error message (if invalid data)

[1121] Step 3:

[1122] The device sends the data, whose integrity has been confirmed, to the server. The server receives the data and checks it again. Specifically, the server reconfirms the accuracy and completeness of the data and records it in the database in the appropriate format. During this process, the data is temporarily stored in cache memory, and after reconfirmation, it is saved in the official database.

[1123] Input: Data that has been integrity checked

[1124] Output: Data stored in the database

[1125] Step 4:

[1126] The server inputs the stored data into the generative AI model and begins analysis. During this process, the generative AI model uses machine learning algorithms (e.g., TensorFlow or PyTorch) to extract features from the data and generate analysis results. In particular, it calculates the accident rate and frequency for each intersection and performs scoring to identify problem areas.

[1127] Input: Data stored in a database

[1128] Output: Analysis results from the generative AI model (identification of problem areas)

[1129] Step 5:

[1130] The server generates specific road improvement proposals based on the results of data analysis. It devises optimal design change proposals (e.g., adding dedicated left-turn lanes or changing the placement of traffic lights) for identified problem areas. The server also visualizes these proposals using 3D simulation software (e.g., Unity). The server runs the simulation and displays changes in traffic flow in a 3D model.

[1131] Input: Analysis results from generative AI model

[1132] Output: Specific road improvement plans, visualization through 3D simulation

[1133] Step 6:

[1134] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the improvement plan is implemented. Specifically, it estimates the effect of new design changes using Monte Carlo simulation and other methods, and calculates the predicted results. The results are output as the reduction rate and predicted number of traffic accidents.

[1135] Input: Specific road improvement proposals

[1136] Output: Predicted results of traffic accident reduction effect

[1137] Step 7:

[1138] The terminal displays the generated reports and simulation results to local government officials. The results are then made available for viewing and download through a dedicated web application or dashboard. Users can then review this information and enter feedback through a dedicated form.

[1139] Input: Predicted results of traffic accident reduction, specific road improvement plans, 3D simulation results

[1140] Output: Feedback (by local government officials)

[1141] Step 8:

[1142] The server receives user feedback, re-runs the analysis model, re-evaluates newly proposed improvements, and generates additional refinements as needed, all while updating the 3D simulation and providing a visual presentation.

[1143] Input: Feedback (by local government officials)

[1144] Output: Reevaluated analysis results and suggested improvements, updated 3D simulation

[1145] Step 9:

[1146] The server incorporates an emotion engine to analyze the user's emotional state in real time. The emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's input and behavior, and collect the user's emotional state as data.

[1147] Input: User input data (feedback statements and actions)

[1148] Output: User's emotional state data

[1149] Step 10:

[1150] The server adjusts the feedback response based on the collected emotional data. If the user is feeling stressed, it provides more attentive support and detailed explanations. It also adjusts improvement proposals based on the emotional data, aiming to increase user satisfaction.

[1151] Input: User emotional state data, feedback data

[1152] Output: Adjusted feedback response, revised improvement proposals

[1153] Step 11:

[1154] The server periodically monitors changes in emotional data and analyzes the user's emotional trends over the long term, thereby understanding the user's emotional state and aiming to improve long-term user engagement and feedback accuracy.

[1155] Input: Continuously collected emotional state data

[1156] Output: User sentiment analysis results

[1157] At each step, the server, terminal, and user perform specific actions to advance the overall system processing. Each process processes and calculates data based on the input data, and passes the results on to the next step. This allows for effective proposals and responses to improve road safety.

[1158] (Application example 2)

[1159] 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."

[1160] Conventional road design and traffic management systems have had difficulty efficiently identifying the locations and causes of traffic accidents and proposing appropriate improvement plans. Furthermore, the proposed improvement plans often fail to take into account user emotions and usage conditions, resulting in poor acceptance. Furthermore, automated driving vehicles are insufficient in recognizing roads and intersections with a high risk of traffic accidents in real time and responding immediately to avoid them.

[1161] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the problem areas on the road identified by the generative AI model, means for calculating the predicted traffic accident reduction effect, means integrated into the navigation system of the driving vehicle to identify roads and intersections with a high traffic accident risk in real time and propose optimal routes, means for collecting driver emotional data and adjusting feedback responses according to the driver's emotional state, and means for providing the road improvement plans and prediction results in report format. This makes it possible to reduce the risk of traffic accidents and provide more acceptable improvement plans that take the driver's emotional state into consideration.

[1162] "Road design information" refers to detailed information about road infrastructure, such as map data, existing road design drawings, intersection locations, and traffic light locations.

[1163] "Traffic violation data" refers to data on violations such as the location, cause, and frequency of traffic accidents in a specific section.

[1164] A "database" is an information management system that organizes and stores collected information for later analysis and reference.

[1165] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and generates output tailored to a specific purpose.

[1166] A "navigation system" is an in-vehicle device and software that provides vehicle route guidance and a route to a destination.

[1167] "Emotional data" is information used to collect and analyze a user's emotional state in real time.

[1168] "Feedback" refers to information provided by users that the system receives and uses to improve its services and features.

[1169] "Traffic accident reduction effect" refers to the predicted reduction in the rate or number of traffic accidents after the proposed road improvement plan is implemented.

[1170] "Report format" is a method of providing analysis results and proposals in a document format that is easy to understand.

[1171] "Visual simulation" is a means of visually representing improvement proposals generated by a generative AI model using three-dimensional models, etc.

[1172] 1. Data collection and input

[1173] Users collect road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users enter this data into the system using dedicated web forms and applications.

[1174] 2. Data Receipt and Storage

[1175] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[1176] 3. Saving to the database

[1177] The terminal sends the data, whose format and completeness have been checked, to the server, which stores the received data in a database. During this process, the data is checked again for accuracy and completeness, and recorded in the database in the appropriate format.

[1178] 4. Data Analysis

[1179] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[1180] 5. Generation of improvement proposals

[1181] The server generates specific road improvement proposals based on the analysis results. It proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. The simulations use 3D models to show, for example, how traffic flow would change if a left-turn lane were added to an intersection.

[1182] 6. Prediction of a decrease in traffic accidents

[1183] The server calculates the predicted effect of traffic accident reduction if the improvement plan is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents or the predicted number of reductions.

[1184] 7. Providing Suggestions and Feedback

[1185] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Users review the information provided and provide feedback, if necessary. Feedback can include questions about the proposal or requests for additional information.

[1186] 8. Processing and reassessing feedback

[1187] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[1188] 9. Incorporating an Emotional Engine

[1189] The server incorporates a new emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's emotions in real time as they input data and collects it as data.

[1190] 10. Emotionally driven feedback response

[1191] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into account, aiming to increase user satisfaction.

[1192] 11. Monitoring Emotional Data

[1193] The server periodically monitors changes in emotional data and analyzes the user's emotional trends, aiming to improve long-term user engagement and improve feedback accuracy.

[1194] Hardware and software used

[1195] The implementation of this system uses the following hardware and software:

[1196] Hardware: Autonomous vehicle control systems, on-board computers, various sensors, digital panels

[1197] Software: Navigation system integration software, Python program, Scipy library, HTTP API

[1198] Examples of concrete examples and prompts

[1199] As a concrete example, consider a scenario in which an autonomous vehicle is traveling within a certain city and the system acquires data showing that a particular intersection has been the site of many accidents in the past, and suggests an optimal route to avoid the intersection before reaching it. If the driver feels anxious or stressed, the system will provide detailed instructions to reassure them.

[1200] An example prompt for a generative AI model is:

[1201] "Based on data on intersections where accidents have occurred frequently over the past year, please generate road design improvement proposals that include those intersections. The intersection's coordinates are xxx, yyy, and the user is currently feeling anxious or stressed. Please provide specific improvement proposals and visualizations of the simulation, along with information on how to explain this to the user."

[1202] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1203] Step 1:

[1204] Users collect road design information and traffic violation data and input it into the system using dedicated web forms and applications. The information input includes map data, existing road design drawings, intersection layouts, traffic light locations, and the locations, causes, and frequency of traffic accidents. This is how data is collected and input. The input data becomes the basic information needed for subsequent analysis.

[1205] Step 2:

[1206] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the data format and completeness to ensure that the data is in the correct format. Input: Data entered by the user. Output: Data whose consistency has been confirmed. Specifically, the data format is checked and missing values ​​are checked.

[1207] Step 3:

[1208] The terminal sends data whose format and completeness have been confirmed to the server. The server stores the received data in a database. Input: Data whose format and completeness have been confirmed. Output: Data stored in the database. Specifically, the data is sent via an HTTP request and recorded in the database.

[1209] Step 4:

[1210] The server inputs the saved data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road. Input: Saved road design information and traffic violation data. Output: Identified problem areas on the road. Specifically, the data is preprocessed and input into the generative AI model.

[1211] Step 5:

[1212] The server generates specific road improvement proposals based on the analysis results. For identified problem areas, it proposes optimal design changes to improve safety for cars and pedestrians. Input: Identified problem areas on the road. Output: Specific road improvement proposals. Specific operations include performing simulations using a generative AI model and proposing the results.

[1213] Step 6:

[1214] The server calculates the predicted effect of traffic accident reduction when the improvement proposal is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. Input: Specific road improvement proposal. Output: Predicted effect of traffic accident reduction. The specific operation is to predict the effect using the simulation model.

[1215] Step 7:

[1216] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Input: Prediction results and improvement proposals. Output: Reports and simulations displayed to officials. Specifically, the results are displayed using HTML and a graph generation library.

[1217] Step 8:

[1218] The user reviews the provided information and enters feedback as needed. Feedback may include questions about the proposal or requests for additional information. Input: Provided information and feedback. Output: Feedback content. Specific operations include collecting feedback using a web form.

[1219] Step 9:

[1220] The server re-runs the analytical model based on the feedback received from the user and performs a re-evaluation. If necessary, additional improvement suggestions are generated and provided to the local government, also including a visual simulation. Input: Received feedback. Output: Re-evaluation results and additional improvement suggestions. Specifically, the server re-runs the analytical model and simulates the results.

[1221] Step 10:

[1222] The server incorporates a new emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's emotions in real time as they are input and collects them as data. Input: User's emotional data. Output: Analyzed emotional state. Specifically, it performs real-time analysis using an emotion analysis algorithm.

[1223] Step 11:

[1224] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more thoughtful and detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into consideration to increase user satisfaction. Input: Analyzed emotional data. Output: Adjusted feedback and improvement proposals. Specifically, it adjusts the tone and content of the feedback response.

[1225] Step 12:

[1226] The server periodically monitors changes in emotional data and analyzes the user's emotional trends. This aims to improve long-term user engagement and improve feedback accuracy. Input: Changes in emotional data. Output: Analysis results and trend evaluation. Specifically, it performs cumulative analysis of data and trend analysis.

[1227] 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.

[1228] 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.

[1229] 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.

[1230] [Fourth embodiment]

[1231] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1232] 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.

[1233] 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).

[1234] 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.

[1235] 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.

[1236] 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).

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] 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.

[1243] 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."

[1244] 1. Data collection and input

[1245] Users collect road design information and traffic violation data. Road design information includes map data and existing road design drawings, while traffic violation data includes the locations, causes, and frequency of past traffic accidents. Users then enter this data into the system using dedicated web forms or applications.

[1246] 2. Data Receipt and Storage

[1247] The device temporarily stores the data entered by the user. During the storage process, a consistency check is performed to verify the completeness and format of the data. Once the consistency is confirmed, the data is sent from the device to the server.

[1248] 3. Saving to the database

[1249] The server stores the received data in a database, where it checks again for accuracy and completeness and records the data in the database in an appropriate manner.

[1250] 4. Data Analysis

[1251] The server inputs the stored data into the generative AI model and begins data analysis. The server uses the generative AI model to analyze the relationship between road design information and traffic violation data, and identifies problem areas on the road.

[1252] 5. Generation of improvement proposals

[1253] The server generates specific road improvement proposals based on the analysis results. The generative AI model proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. These simulations use a 3D model to show, for example, how traffic flow would change if a dedicated left-turn lane were added to an intersection.

[1254] 6. Prediction of a decrease in traffic accidents

[1255] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These predictions are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[1256] 7. Providing Suggestions and Feedback

[1257] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. The user reviews the information provided and provides feedback as needed. Feedback can include questions about the proposal or requests for additional information.

[1258] 8. Processing and reassessing feedback

[1259] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[1260] Example: Proposal for improving an intersection

[1261] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. The user enters detailed map data for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the improvement in safety. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. After the local government official reviews this information and provides feedback as needed, the server reevaluates and provides further optimal improvement proposals.

[1262] Thus, the present invention increases the likelihood of preventing accidents caused by violations of traffic rules, and improving road safety and efficiency.

[1263] The processing flow will be explained below.

[1264] Step 1:

[1265] The user collects road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, traffic light locations, etc. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[1266] Step 2:

[1267] Users enter the collected road design information and traffic violation data into the system using dedicated web forms and applications, ensuring that all data is complete and entered in the correct format.

[1268] Step 3:

[1269] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[1270] Step 4:

[1271] The device sends the data, whose format and integrity have been verified, to the server using a secure communication protocol to ensure confidentiality and security of the data.

[1272] Step 5:

[1273] The server stores the data received from the device in a database, during which the data is checked again for accuracy and completeness and recorded in the database in the appropriate format.

[1274] Step 6:

[1275] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[1276] Step 7:

[1277] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[1278] Step 8:

[1279] The server creates a simulation to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This visual simulation is useful for validating the effectiveness of the proposal.

[1280] Step 9:

[1281] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The calculation is based on the simulation results to predict the extent of the accident reduction effect.

[1282] Step 10:

[1283] The server compiles the calculated prediction results in a report that is easy for local government officials to understand. The report details the specific improvement plans and their effects.

[1284] Step 11:

[1285] The terminal displays the generated reports and simulation results to local government officials, who can easily access them, for example, through a web application dashboard.

[1286] Step 12:

[1287] The user reviews the information provided and provides feedback as needed, including questions about the proposal or requests for additional information.

[1288] Step 13:

[1289] The server re-runs the analytical model based on the feedback received from the user, re-evaluating and re-proposing, and generating new refinements as needed.

[1290] Step 14:

[1291] The server then revisits the proposed improvements and provides them to the local government along with the predicted results of their effects, thereby providing ongoing support to the local government in making optimal road improvements.

[1292] In this way, accidents caused by violations of traffic rules can be prevented, improving road safety and efficiency.

[1293] Example 1

[1294] 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."

[1295] In conventional road design and traffic safety measures, the process of identifying the locations and causes of traffic accidents and then considering improvement measures based on that information takes a lot of time and effort. Furthermore, there are limited ways to predict in advance how effective proposed improvement measures will actually be, making it difficult to implement efficient measures.

[1296] 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.

[1297] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for generating a visual simulation of the road improvement plan, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plan, means for providing the road improvement plan and the predicted results in a report format, and means for receiving feedback from users and reevaluating and re-proposing based on the feedback, thereby enabling efficient and effective prevention of traffic accidents and improvement of road safety.

[1298] "Road design information" is data relating to the shape, size, configuration, traffic signs, pavement condition, and surrounding environment of the road.

[1299] "Traffic violation data" refers to data that includes the locations, causes, and frequency of past traffic accidents and violations, as well as detailed information about those accidents and violations.

[1300] The "database" is a system for systematically and efficiently managing, storing, and searching collected road design information and traffic violation data.

[1301] "Generative AI model" refers to an artificial intelligence algorithm used to analyze collected data and generate road improvement proposals and predict their effectiveness in reducing traffic accidents.

[1302] "Analysis" refers to the analytical process of using collected road design information and traffic violation data to find correlations and identify problem areas.

[1303] "Problem sections of roads" refer to areas where traffic accidents frequently occur or where there are defects in the road structure.

[1304] "Road Improvement Proposals" refer to specific design changes or measures to improve the safety and efficiency of identified road problem areas.

[1305] "Visual simulation" refers to 3D models and animations that visually demonstrate the effects of generated road improvement proposals.

[1306] "Traffic accident reduction effect" refers to the rate or number of traffic accidents predicted to decrease as a result of the implementation of the proposed road improvement plan.

[1307] "Report" refers to a document summarizing the generated road improvement proposals and their predicted results in written form.

[1308] "Feedback" refers to comments such as questions about the proposal or requests for additional information provided by the user.

[1309] "Reevaluation" is the process of re-analyzing the product based on user feedback and considering new improvement proposals.

[1310] "Re-proposal" refers to submitting a proposal again that includes new improvement proposals generated as a result of re-evaluation.

[1311] The system is designed to collect road design information and traffic violation data, and then carry out a series of processes based on that data, including analysis, generation of improvement proposals, simulation, prediction, and feedback processing.

[1312] 1. Data collection and input

[1313] Users collect road design information (e.g., map data and existing road design drawings) and traffic violation data (e.g., locations, causes, and frequency of past traffic accidents) from public government databases and traffic control centers. Specifically, map data is obtained from OpenStreetMap, and traffic accident data is obtained from the National Police Agency database. Users enter this information using a dedicated web form or mobile application (e.g., Data Input Pro).

[1314] 2. Data Receipt and Storage

[1315] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. The device uses a JSON Schema Validator to verify that the data format is correct. For example, it verifies that map data is represented by the correct coordinates and that accident data is entered in the appropriate format. Once the data is confirmed to be consistent, it is sent to the server via an API.

[1316] 3. Saving to the database

[1317] The server checks the received data and stores it in a database (e.g. MySQL or PostgreSQL). The server further verifies the accuracy and completeness of the data before storing it, comparing it with other related tables and logging any inconsistencies.

[1318] 4. Data Analysis

[1319] The server inputs the stored data into a pre-trained generative AI model, which is built using TensorFlow and PyTorch. The server then uses the generative AI model to analyze the input data and identify problem areas based on the location and cause of traffic accidents. Specifically, it determines that left-turn accidents are more common at certain intersections.

[1320] 5. Generation of improvement proposals

[1321] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually demonstrate the effects of the proposed improvements.

[1322] 6. Prediction of a decrease in traffic accidents

[1323] The server uses the generative AI model to simulate the effect of reducing traffic accidents if the proposed improvement plan is implemented. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%."

[1324] 7. Providing Suggestions and Feedback

[1325] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The user reviews the proposals and enters feedback through a web form. For example, feedback such as "I would like more detailed explanations for the proposed left-turn lane locations" can be provided.

[1326] 8. Processing and reassessing feedback

[1327] The server takes the feedback received from the user and re-runs the analytical model. If necessary, it generates new refinements based on the feedback and presents them again, including visual simulations.

[1328] Prompt Sentence Examples

[1329] "Please explain the procedure for a local government official to confirm that there are many accidents occurring when turning left at a particular intersection and input detailed map data and traffic accident data from the past year into the system to consider improvement proposals."

[1330] Please provide details on the process by which the terminal receives the data entered by the user into the system, performs integrity checks, and then transmits it to the server.

[1331] In this way, the use of this system makes it possible to efficiently and effectively prevent traffic accidents and improve road safety.

[1332] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1333] Step 1:

[1334] Users collect road design information and traffic violation data. Users obtain data from public government databases and traffic control centers. Specifically, they collect map data from OpenStreetMap and traffic accident data from the National Police Agency database. These data are input.

[1335] Step 2:

[1336] Users enter this data into the system using dedicated web forms or mobile applications (e.g., Data Input Pro). Users upload map data as files and enter accident data directly into the form. This is where the input data is collected.

[1337] Step 3:

[1338] The device temporarily stores the data entered by the user, using internal memory or a temporary cache. To confirm the data's consistency, the device uses a JSON Schema Validator to validate the format of the data. For example, it checks whether map data is expressed using the correct coordinates and whether accident data has been entered in the appropriate format. This consistency check generates data whose consistency has been confirmed.

[1339] Step 4:

[1340] The device sends the data, whose integrity has been confirmed, to the server via the API. The data sent includes map data and traffic accident data that have passed formal verification. The data is then entered into the server.

[1341] Step 5:

[1342] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Before storing, the server rechecks the data for accuracy and completeness and logs any inconsistencies. This results in a database record that is verified as accurate.

[1343] Step 6:

[1344] The server inputs the stored data into a pre-trained generative AI model. This model is built using TensorFlow and PyTorch. The server uses the generative AI model to begin analyzing the input data. For example, it identifies problem areas based on the location and cause of traffic accidents. As a result of this analysis, problem areas on the road are identified.

[1345] Step 7:

[1346] The server generates specific road improvement proposals based on the analysis results. For example, it generates a proposal to add a dedicated left-turn lane at an intersection. The server uses Unity or Blender to create a 3D simulation model to visually show the effects of the proposed improvement. This data processing results in a visual simulation.

[1347] Step 8:

[1348] The server uses the generative AI model to simulate the effect of introducing the proposed improvement plan on reducing traffic accidents. For example, it calculates a predicted result such as "annual traffic accidents will decrease by 30%." This data calculation outputs a predicted reduction effect.

[1349] Step 9:

[1350] The terminal provides the generated reports and simulation results to local government officials. The results are displayed through a dedicated web application or dashboard (e.g., Admin Panel Pro). The output is a report of the proposals and simulation results.

[1351] Step 10:

[1352] The user reviews the report and simulation results and enters their feedback through a web form. For example, they may provide feedback such as, "I would like more detailed explanations for the proposed left-turn lane locations." This feedback is collected as input data.

[1353] Step 11:

[1354] The server incorporates the feedback received from the user into the system and re-runs the analytical model. If new refinements are necessary based on the feedback, they are generated and presented again, including visual simulations. This re-evaluation generates new refinements and their simulation outputs.

[1355] (Application example 1)

[1356] 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."

[1357] Autonomous vehicles need to perform optimal driving behavior and route selection in real time, but conventional systems have difficulty performing instant and efficient analysis based on road design information and traffic violation data. Therefore, to further improve safety and efficiency, a system that can quickly analyze collected data and propose appropriate driving behavior is required. It is also important to increase the reliability of proposals by performing visual simulations.

[1358] 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.

[1359] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the problem areas on the road identified by the generative AI model, and means installed in the autonomous vehicle for proposing optimal driving behaviors and routes in real time, thereby enabling the autonomous vehicle to perform optimal driving behaviors based on the collected data in real time, thereby achieving both safety and efficiency.

[1360] "Road design information" is data relating to the structure and layout of roads, including map data and existing road design drawings.

[1361] "Traffic violation data" is information about traffic violations and accidents that have occurred in the past, and specifically includes data on the location, cause, and frequency of accidents.

[1362] A "generative AI model" is a system that uses artificial intelligence techniques to analyze specific data and make predictions or suggestions, for example, using deep learning or machine learning algorithms.

[1363] "Analysis" is the process of examining collected data in detail, extracting useful information from it, and deepening understanding.

[1364] "Real-time" means responding immediately to incoming data and events, for example, responding immediately to changes in traffic and road conditions.

[1365] "Driving behavior" refers to the specific maneuvers and actions performed by a vehicle, including all driving operations such as changing lanes, adjusting speed, and stopping.

[1366] "Route suggestions" are the best route or method of travel from a starting point to a destination, taking into account factors such as time, distance, and safety.

[1367] "Visual simulation" is a method of visually displaying analysis results and proposals, for example, using 3D models or graphical data displays to present them in an intuitively understandable way.

[1368] "Feedback" refers to reactions and opinions from users and system operators, and is used as a basis for the system to make improvements and reevaluate.

[1369] "Reevaluation" means reconsidering analyses and proposals that have already been made based on new data and feedback, and making corrections or improvements as necessary.

[1370] 1. Data collection and input

[1371] Users use autonomous vehicles to collect road design information and traffic violation data in real time. Road design information includes data acquired from the vehicle's GPS, cameras, and various sensors, while traffic violation data includes records of past traffic accidents and violations. This data is then entered into dedicated web forms and applications via the vehicle's onboard computing unit.

[1372] 2. Data Receipt and Storage

[1373] The terminal temporarily stores the data entered by the user. When the data is saved, it is checked for integrity and format. Once the integrity of the data is confirmed, it is sent from the terminal to the server.

[1374] 3. Saving to the database

[1375] The server stores the received data in a database, where the accuracy and completeness of the data are checked again and recorded in the database in an appropriate manner.

[1376] 4. Data Analysis

[1377] The server inputs the stored data into the generative AI model and begins data analysis. The generative AI model analyzes the relationship between road design information and traffic violation data, and identifies problem areas on roads for autonomous vehicles. For example, it identifies areas where traffic accidents frequently occur and dangerous areas on roads.

[1378] 5. Generation of improvement proposals

[1379] The server generates specific road improvement proposals based on the analysis results. The generative AI model then proposes optimal design changes for identified problem areas to improve vehicle and pedestrian safety. This could include, for example, adding a dedicated left-turn lane at a specific intersection. The server also creates simulations to visualize the proposed road improvements. These simulations, for example, use 3D models to show how the proposals will affect traffic flow.

[1380] 6. Prediction of a decrease in traffic accidents

[1381] The server calculates the predicted reduction in traffic accidents if the proposed improvement is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents and the predicted reduction in the number of accidents.

[1382] 7. Providing Suggestions and Feedback

[1383] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The results are presented in a dedicated dashboard for easy access by the vehicle's driving control system. The user can review the information provided and enter feedback as needed. For example, feedback can include questions about the proposals or requests for additional information.

[1384] 8. Processing and reassessing feedback

[1385] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, generating additional refinements as needed, which are also provided to the autonomous vehicle's driving system, including visual simulations.

[1386] Hardware and software used

[1387] Hardware: The computing unit, GPS, cameras, and sensors installed in the autonomous vehicle.

[1388] Software: Python programs, databases (e.g., MySQL), generative AI models (e.g., GPT-4).

[1389] Specific examples

[1390] Consider a case where an autonomous vehicle determines that a particular intersection has a high incidence of left-turn accidents. The user inputs detailed road design information for the intersection and traffic accident data from the past year into the system. The device reviews this data, checks its consistency, and then sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the particular intersection would be effective. The server visualizes this proposal in a 3D simulation, demonstrating the safety improvement. The report also summarizes the results, predicting that adding a dedicated left-turn lane would reduce annual traffic accidents by 30%. The user reviews this information and provides feedback as needed, and the server reevaluates and provides further optimal improvement suggestions.

[1391] Prompt Sentence Examples

[1392] Analyze the following dataset and propose improvements to road design.

[1393] 1. Road design information: {road_design_data}

[1394] 2. Traffic violation data: {traffic_violation_data}

[1395] Based on the analysis results, present specific improvement proposals and predict their effectiveness.

[1396] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1397] Step 1:

[1398] A user uses the computing unit of an autonomous vehicle to collect road design information and traffic violation data. The input is real-time data obtained from hardware such as GPS, cameras, and sensors. The output is that this data is entered into a dedicated web form or application.

[1399] Step 2:

[1400] The terminal temporarily stores the data entered by the user. The input is the real-time data entered in step 1. At this stage, an integrity check is performed to verify the completeness and format of the data. The output is that the integrity-checked data is sent to the server.

[1401] Step 3:

[1402] The server stores the received data in the database. The input is the data sent in step 2. When storing, the data is checked again for accuracy and completeness and recorded in the database in an appropriate manner. The output is the state of the database with the data stored accurately.

[1403] Step 4:

[1404] The server inputs the stored data into the generative AI model and begins data analysis. The input is road design information and traffic violation data stored in the database. The server uses this data to identify problem areas on the road using the generative AI model. The output is a list of identified problem areas.

[1405] Step 5:

[1406] The server generates specific road improvement proposals based on the analysis results. The input is the list of problem areas obtained in step 4. The generative AI model is used to propose optimal design changes to improve safety. The output is a list of specific road improvement proposals, such as adding a dedicated left-turn lane at a specific intersection.

[1407] Step 6:

[1408] The server creates a simulation to visualize the proposed road improvement plan. The input is the road improvement plan generated in step 5. The simulation is displayed visually using a 3D model, etc. The output is the visualized simulation result.

[1409] Step 7:

[1410] The server calculates the predicted reduction in traffic accidents when the proposed improvement is implemented. The inputs are the road improvement proposal from Step 5 and the simulation results from Step 6. The generative AI model simulates the effect of the proposed design changes and calculates the predicted results. The output is statistics such as the rate of reduction in traffic accidents and the predicted number of reductions.

[1411] Step 8:

[1412] The terminal displays the generated reports and simulation results in real time to the autonomous vehicle's driving system. The inputs are the prediction results calculated in step 7 and the simulation results from step 6. The results are displayed in a format that is easily accessible to the user and the vehicle's driving control system. The output is the results displayed on the driving system's dashboard.

[1413] Step 9:

[1414] The user checks the provided information and enters feedback as necessary. The input is the report or simulation results displayed in step 8. The feedback may include questions about the proposal or requests for additional information. The output is the feedback content.

[1415] Step 10:

[1416] The server re-runs and re-evaluates the analytical model based on the feedback received from the user. The input is the feedback obtained in step 9. If necessary, additional refinements are generated and provided to the autonomous vehicle's driving system, including a visual simulation. The output is the re-evaluated refinements and the simulation results.

[1417] 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.

[1418] 1. Data collection and input

[1419] Users collect road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users then enter this data into the system using dedicated web forms and applications.

[1420] 2. Data Receipt and Storage

[1421] The terminal temporarily stores the data entered by the user. At this stage, a consistency check is performed on the format and completeness of the data to ensure that it is in the correct format.

[1422] 3. Saving to the database

[1423] The terminal sends the data, whose format and completeness have been checked, to the server, which stores the received data in a database. During this process, the data is checked again for accuracy and completeness, and recorded in the database in the appropriate format.

[1424] 4. Data Analysis

[1425] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the correlation between the input road design information and traffic violation data, and identifies problem areas on the road.

[1426] 5. Generation of improvement proposals

[1427] The server generates specific road improvement proposals based on the analysis results. It proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians. The server also creates simulations to visualize the proposed road improvements. The simulations use 3D models to show, for example, how traffic flow would change if a left-turn lane were added to an intersection.

[1428] 6. Prediction of a decrease in traffic accidents

[1429] The server calculates the predicted effect of traffic accident reduction if the improvement plan is implemented. The generative AI model simulates the effect of the proposed design change and calculates the predicted results. These prediction results are calculated as the reduction rate of traffic accidents or the predicted number of reductions.

[1430] 7. Providing Suggestions and Feedback

[1431] The terminal displays the generated reports and simulation results to local government officials. The results are presented in an easily accessible format to officials through a dedicated web application or dashboard. Users review the information provided and provide feedback, if necessary. Feedback can include questions about the proposal or requests for additional information.

[1432] 8. Processing and reassessing feedback

[1433] The server re-runs and re-evaluates the analytical model based on the feedback received from the user, and if necessary, generates additional refinements that are also provided to the local government, including visual simulations.

[1434] 9. Incorporating an Emotional Engine

[1435] The server incorporates a new emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's emotions in real time as they input data and collects it as data.

[1436] 10. Emotionally driven feedback response

[1437] The server adjusts the feedback response based on the collected emotional data. For example, if the user is feeling stressed, it will provide more detailed suggestions and support. It also adjusts improvement proposals taking the emotional data into account, aiming to increase user satisfaction.

[1438] 11. Monitoring Emotional Data

[1439] The server periodically monitors changes in emotional data and analyzes the user's emotional trends, aiming to improve long-term user engagement and improve feedback accuracy.

[1440] Example: Intersection improvement proposals and emotional feedback

[1441] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of accidents when turning left and would like to improve the intersection. The user enters detailed map data about the intersection and traffic accident data from the past year into the system. Additionally, the emotion engine collects the user's emotional state in real time. The device verifies the data integrity and sends it to the server. The server stores the data in a database and analyzes it using a generative AI model. The analysis results indicate that adding a dedicated left-turn lane to the intersection would be effective. The server visualizes this proposal in a 3D simulation and adds a detailed explanation that takes customer satisfaction into consideration. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. The local government official reviews this information and provides feedback. The server then reevaluates the proposal based on the feedback and provides further optimal improvement proposals.

[1442] In this way, the present invention can prevent accidents caused by violations of traffic rules, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of improvement proposals and the level of satisfaction.

[1443] The processing flow will be explained below.

[1444] Step 1:

[1445] The user collects road design information and traffic violation data. Road design information includes map data, existing road plans, intersection layouts, and traffic light locations, while traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections.

[1446] Step 2:

[1447] Users enter the collected road design information and traffic violation data into the system using a dedicated web form or application. When entering data, they check to make sure that all data is complete and that there are no omissions.

[1448] Step 3:

[1449] The terminal temporarily stores the data entered by the user, and while storing it, checks the format and completeness of the data to ensure that it is accurate and in the proper format.

[1450] Step 4:

[1451] The device sends the data, whose format and integrity have been verified, to the server, using a secure communication protocol to ensure confidentiality and security of the data.

[1452] Step 5:

[1453] The server stores the data received from the device in a database, where it checks the accuracy and completeness of the data once again and records it in the database in the appropriate format.

[1454] Step 6:

[1455] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model analyzes the relationship between road design information and traffic violation data to identify problem areas on the road.

[1456] Step 7:

[1457] The server uses the generative AI model to generate specific road improvement proposals based on the analysis results, and proposes optimal design changes for identified problem areas to improve safety for vehicles and pedestrians.

[1458] Step 8:

[1459] The server creates simulations to visualize proposed road improvements, such as a 3D model showing how traffic flow would change if a left-turn lane were added to an intersection. This simulation is useful for validating the effectiveness of the proposals.

[1460] Step 9:

[1461] The server uses a generative AI model to calculate the effect of traffic accident reduction when the improvement plan is implemented. The predicted results include the accident reduction rate and predicted number of reductions, which are used to show the specific effects.

[1462] Step 10:

[1463] The server uses an emotion engine to analyze the user's emotions in real time as they are input. The results of this analysis are stored in a database and used for subsequent feedback responses.

[1464] Step 11:

[1465] The server displays the generated reports and simulation results to local government officials. Based on the emotional data analyzed by the emotion engine, the tone and content of the report are adjusted, presenting the information in a format that is easy for the official to understand. For example, if the official is feeling stressed, more detailed and careful explanations are added.

[1466] Step 12:

[1467] The user checks the provided reports and simulation results and enters feedback as necessary. The emotion engine then analyzes the user's emotions when entering feedback and records them in a database.

[1468] Step 13:

[1469] The server re-executes the analysis model based on the feedback received from the user, re-evaluates and re-proposes, and generates new improvement proposals. The generated improvement proposals are visualized again through simulation.

[1470] Step 14:

[1471] The server then provides the revised improvement plan to the local government official. Based on the emotional data analyzed by the emotion engine, the presentation is made in a format and with content that is easy to understand. This allows the server to provide ongoing support to local governments in implementing optimal road improvements.

[1472] In this way, accidents caused by violations of traffic rules can be prevented, and road safety and efficiency can be improved. In addition, proposals can be made that take user feelings into account, which increases the likelihood of improvement proposals being accepted.

[1473] Example 2

[1474] 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."

[1475] To reduce traffic accidents, it is necessary to quickly propose effective road design improvement plans and present them to stakeholders in an actionable form. It is also important to optimize the proposals by taking into account user feedback and emotional states, thereby improving user satisfaction. Conventional systems have had difficulty meeting these requirements, making it impossible to resolve problems rationally and quickly.

[1476] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1477] In this invention, the server includes means for collecting road design information and traffic violation data and storing them in a database, means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road, means for generating specific road improvement plans for the identified problem areas on the road using the generative AI model, means for calculating a predicted effect of reducing traffic accidents based on the road improvement plans, means for providing the road improvement plans and the predicted results in a report format, means including an emotion analysis engine for analyzing the user's emotional state and collecting it as data, and means for adjusting reports and feedback responses based on the emotion analysis data. This makes it possible to improve the effectiveness of road design improvements and make optimal proposals that take the user's emotions into consideration.

[1478] "Road design information" refers to data related to road structure and design, such as map data, existing road design drawings, intersection locations, and traffic light locations.

[1479] "Traffic violation data" refers to data related to traffic violations, such as the location, cause, and frequency of traffic accidents in a specific section.

[1480] A "generative AI model" is a model that uses machine learning and deep learning techniques to analyze input data and identify and predict specific problems.

[1481] An "emotion analysis engine" is a system that analyzes user input and behavior in real time and evaluates and judges the user's emotional state.

[1482] "Means for storing in a database" refers to a method or system for integrating collected data and storing it in a database in an appropriate format.

[1483] "Road improvement proposals" are proposals for specific design changes to improve safety and convenience for problem areas on roads identified based on the analysis results.

[1484] "Traffic accident reduction effect" is the predicted reduction in the percentage or number of traffic accidents if the proposed road improvement plan is implemented.

[1485] The "means for adjusting feedback response" refers to a method or system for readjusting suggestions or responses to an appropriate form based on the user's emotional state and the feedback content.

[1486] "Visual simulation" is a technique that uses 3D models and graphics to visually represent proposed road improvements and their effects.

[1487] The "means for re-evaluating and re-proposing" refers to a method or system for re-executing the analysis model based on feedback from the user, and generating and proposing new improvement proposals.

[1488] The present invention relates to a system for analyzing road design information and traffic violation data to generate effective road improvement proposals. Specific embodiments for carrying out the present invention will be described below.

[1489] 1. Data collection and input

[1490] First, users collect road design information and traffic violation data. Road design information includes map data, existing road designs, intersection layouts, and traffic light locations. Traffic violation data includes the locations, causes, and frequency of traffic accidents in specific sections. Users enter this data into the system using dedicated web forms and applications.

[1491] 2. Data Receipt and Storage

[1492] The terminal temporarily receives and stores the data entered by the user. At this stage, the terminal checks the data format and integrity. If invalid data is detected, an error message is displayed to the user, prompting them to re-enter the data.

[1493] 3. Saving to the database

[1494] The terminal sends the data, whose format and completeness have been checked, to the server. The server receives the data, checks it again, and stores it in the database. During this process, the server double-checks the accuracy and completeness of the data and records it in the database in the appropriate format.

[1495] 4. Data Analysis

[1496] The server inputs the stored data into the generative AI model and begins analysis. The generative AI model uses machine learning and deep learning techniques, specifically libraries such as TensorFlow and PyTorch. In this process, various features are extracted from the loaded data, and problem areas on the road are identified as analysis results.

[1497] 5. Generation of improvement proposals

[1498] The server generates specific road improvement proposals based on the results of the data analysis. For example, these proposals may include adding dedicated left-turn lanes or changing the placement of traffic lights. These improvement proposals are visualized using 3D simulation software (e.g., Unity). The server runs the simulation and displays the changes in traffic flow in a 3D model.

[1499] 6. Prediction of a decrease in traffic accidents

[1500] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the proposed improvement is implemented. Specifically, it uses Monte Carlo simulation to estimate the extent to which the proposed design change will be effective. The results are output as the reduction rate and predicted number of traffic accidents.

[1501] 7. Providing Suggestions and Feedback

[1502] The device displays the generated reports and simulation results to local government officials, who can then view and download the results through a dedicated web application or dashboard. Users can then review the information provided and enter feedback through a dedicated form.

[1503] 8. Processing and reassessing feedback

[1504] The server receives user feedback, re-runs the analysis model, re-evaluates any newly proposed improvements, and generates additional improvements as needed, all while updating the 3D simulation and providing a visual presentation.

[1505] 9. Incorporating an Emotional Engine

[1506] The server incorporates an emotion engine that analyzes the user's emotional state in real time. The emotion engine uses technology such as IBM Watson Tone Analyzer. When the user enters data, the emotion engine analyzes the text and input actions, and collects the user's emotional state as data.

[1507] 10. Emotionally driven feedback response

[1508] The server adjusts the feedback response based on the collected emotional data. For example, if the server determines that the user is feeling stressed, it will provide more attentive support and detailed explanations. It also adjusts the improvement proposals based on the emotional data to improve user satisfaction.

[1509] 11. Monitoring Emotional Data

[1510] The server periodically monitors changes in emotional data and analyzes the user's emotional trends over the long term, which aims to improve long-term user engagement and improve feedback accuracy.

[1511] Example: Intersection improvement proposals and emotional feedback

[1512] Consider a case where a local government official suspects that a particular intersection is experiencing a high rate of left-turn accidents and would like to improve the intersection. When a user enters detailed map data about the intersection and traffic accident data from the past year into the system, the emotion engine collects the user's emotional state in real time. The device verifies the data's integrity and sends it to the server. The server stores the data in a database and performs data analysis using a generative AI model. The analysis identifies that adding a dedicated left-turn lane at the intersection would be effective. The server visualizes this suggestion in a 3D simulation and provides a detailed explanation. The tone and content of the report are also adjusted based on the user's emotions measured by the emotion engine. After the official reviews this information and provides feedback, the server reevaluates and provides further optimal improvement proposals.

[1513] In this way, the present invention provides an effective means for preventing traffic accidents, and furthermore, by taking into account the user's emotional data, it is possible to improve the acceptability of the suggestions and the level of satisfaction.

[1514] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1515] Step 1:

[1516] Users collect and input road design information and traffic violation data. They input map data, road design drawings, intersection layouts, and traffic light locations into the system using dedicated web forms and applications. They also input traffic violation data such as the location, cause, and frequency of accidents in specific sections. The input data is sent to the terminal via a dedicated application.

[1517] Input: Map data, road design, intersection layout, traffic light location, location, cause, and frequency data of traffic accidents

[1518] Output: Input data saved on the device

[1519] Step 2:

[1520] The terminal temporarily stores the data sent by the user. The terminal checks the format and completeness of the data to ensure consistency. Specifically, it runs a script to check for missing or incorrectly formatted data, and displays an error message to the user if invalid data is present.

[1521] Input: Data submitted by the user

[1522] Output: Data that has been checked for consistency, error message (if invalid data)

[1523] Step 3:

[1524] The device sends the data, whose integrity has been confirmed, to the server. The server receives the data and checks it again. Specifically, the server reconfirms the accuracy and completeness of the data and records it in the database in the appropriate format. During this process, the data is temporarily stored in cache memory, and after reconfirmation, it is saved in the official database.

[1525] Input: Data that has been integrity checked

[1526] Output: Data stored in the database

[1527] Step 4:

[1528] The server inputs the stored data into the generative AI model and begins analysis. During this process, the generative AI model uses machine learning algorithms (e.g., TensorFlow or PyTorch) to extract features from the data and generate analysis results. In particular, it calculates the accident rate and frequency for each intersection and performs scoring to identify problem areas.

[1529] Input: Data stored in a database

[1530] Output: Analysis results from the generative AI model (identification of problem areas)

[1531] Step 5:

[1532] The server generates specific road improvement proposals based on the results of data analysis. It devises optimal design change proposals (e.g., adding dedicated left-turn lanes or changing the placement of traffic lights) for identified problem areas. The server also visualizes these proposals using 3D simulation software (e.g., Unity). The server runs the simulation and displays changes in traffic flow in a 3D model.

[1533] Input: Analysis results from generative AI model

[1534] Output: Specific road improvement plans, visualization through 3D simulation

[1535] Step 6:

[1536] The server uses the generative AI model to calculate the predicted reduction in traffic accidents when the improvement plan is implemented. Specifically, it estimates the effect of new design changes using Monte Carlo simulation and other methods, and calculates the predicted results. The results are output as the reduction rate and predicted number of traffic accidents.

[1537] Input: Specific road improvement proposals

[1538] Output: Predicted results of traffic accident reduction effect

[1539] Step 7:

[1540] The terminal displays the generated reports and simulation results to local government officials. The results are then made available for viewing and download through a dedicated web application or dashboard. Users can then review this information and enter feedback through a dedicated form.

[1541] Input: Predicted results of traffic accident reduction, specific road improvement plans, 3D simulation results

[1542] Output: Feedback (by local government officials)

[1543] Step 8:

[1544] The server receives user feedback, re-runs the analysis model, re-evaluates newly proposed improvements, and generates additional refinements as needed, all while updating the 3D simulation and providing a visual presentation.

[1545] Input: Feedback (by local government officials)

[1546] Output: Reevaluated analysis results and suggested improvements, updated 3D simulation

[1547] Step 9:

[1548] The server incorporates an emotion engine to analyze the user's emotional state in real time. The emotion engine (e.g., IBM Watson Tone Analyzer) is used to analyze the user's input and behavior, and collect the user's emotional state as data.

[1549] Input: User input d...

Claims

1. a means for collecting and storing road design information and traffic violation data in a database; A means for analyzing the road design information and the traffic violation data using a generative AI model to identify problem areas on the road; A means for generating specific road improvement proposals for identified problem areas of the road using the generative AI model; a means for calculating a predicted effect of reducing traffic accidents based on the road improvement plan; means for providing the road improvement proposals and forecast results in a report format; A system including:

2. The system of claim 1 , wherein the generative AI model further comprises means for generating a visual simulation based on the analysis results.

3. The system of claim 1 , further comprising means for receiving feedback from the user and re-evaluating and re-suggesting based thereon.

Images