System

Abstract

An object of the system according to the embodiment is to analyze data including blind spot information and propose an optimum route and an optimum traveling speed.SOLUTION: A system includes a collection part, an analysis part, a proposal part, and a grasping part. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The suggestion unit suggests an optimum route and traveling speed on the basis of the analysis result obtained by the analysis unit. The grasping unit grasps an action plan of a pedestrian.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that autonomous vehicles are unable to fully recognize blind spot information, making it difficult to avoid danger.

[0005] The system according to the embodiment aims to analyze data including blind spot information and propose an optimal route and driving speed. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a proposal unit, and a recognition unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The proposal unit proposes an optimal route and driving speed based on the analysis results obtained by the analysis unit. The recognition unit recognizes the pedestrian's behavior plan. [Effects of the Invention]

[0007] The system according to the embodiment can analyze data including blind spot information and suggest optimal routes and driving speeds. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The safe operation system for autonomous vehicles according to an embodiment of the present invention provides a mechanism for obtaining blind spot information that cannot be fully recognized by the vehicle alone. This system accumulates roadside cooperative data and identifies dangerous areas in advance. Next, the autonomous vehicle's driving plan and real-time travel history, along with target measurement data from roadside devices, are input, and the generation AI recursively predicts future accidents at dangerous areas. Based on the prediction results, the generation AI proposes optimal routes and driving speeds, including unknown routes. This prevents accidents, contributes to safe vehicle operation, provides passengers with peace of mind, and stimulates further travel motivation. Furthermore, the generation AI grasps pedestrian behavior plans through apps such as those supporting local residents' exercise habits, and makes highly accurate movement predictions. This enables pedestrian-vehicle traffic accidents to be predicted and avoided with a high probability. For example, when a roadside device is installed at an intersection, it collects information on vehicles and pedestrians approaching the intersection in real time, and the generation AI analyzes this information to predict the risk of an accident at the intersection. Based on the prediction results, the generative AI proposes optimal routes and driving speeds for vehicles and notifies pedestrians to take appropriate action. This enables the safe operation of autonomous vehicles and significantly reduces the risk of traffic accidents. It also provides a safer travel environment for pedestrians, improving traffic safety throughout the region.

[0029] A safe operation system for an autonomous vehicle according to an embodiment includes a collection unit, an analysis unit, a proposal unit, and an understanding unit. The collection unit collects data. Examples of the data include, but are not limited to, sensor data, GPS data, and user data. The collection unit, for example, collects road-to-vehicle coordination data and identifies dangerous areas in advance. The collection unit can also acquire vehicle speed and location information in real time and use the information to identify dangerous areas. The collection unit can also collect data from pedestrians' smartphones and understand their movements. For example, the collection unit collects location information from pedestrians' smartphones and understands their current locations. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit analyzes the autonomous vehicle's driving plan and real-time movement history together with target measurement data from a roadside device, and recursively predicts future accidents at dangerous areas. The recursive prediction is performed using, for example, time series analysis or a machine learning model. The proposal unit proposes an optimal route and driving speed based on the analysis results obtained by the analysis unit. The suggestion unit proposes an optimal route and driving speed, including an unknown route, based on the prediction result, for example. The suggestion unit can also propose an optimal route and driving speed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. The understanding unit understands the pedestrian's behavior plan. The understanding unit understands the pedestrian's behavior plan through, for example, an app to support exercise habits for local residents, and performs highly accurate movement prediction. As a result, the safe operation system for autonomous vehicles according to the embodiment can achieve safe operation of autonomous vehicles by linking the elements of data collection, analysis, proposal, and understanding.

[0030] The collection unit collects road-to-vehicle coordination data and can identify dangerous areas in advance. Examples of road-to-vehicle coordination data include, but are not limited to, V2X communication data and traffic signal data. The collection unit, for example, uses a sensor in a roadside device to collect information about vehicles approaching intersections. The collection unit can also collect traffic signal statuses in real time and reflect the information in vehicle operation plans. The collection unit can also collect location information from pedestrians' smartphones and understand their movements. For example, the collection unit collects location information from pedestrians' smartphones to understand their current locations. By collecting road-to-vehicle coordination data, dangerous areas can be identified in advance. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input data acquired from a sensor in a roadside device to a generation AI and cause the generation AI to identify dangerous areas.

[0031] The analysis unit can analyze the autonomous vehicle's driving plan and real-time movement history together with target measurement data from the roadside device to recursively predict future accidents at dangerous locations. The driving plan can include, but is not limited to, routes, speeds, and stopping points. The real-time movement history can include, but is not limited to, GPS data and speed data. The target measurement data can include, but is not limited to, LIDAR data and camera data. The recursive prediction can be performed using, for example, time series analysis or a machine learning model. For example, the analysis unit can analyze the autonomous vehicle's driving plan and real-time movement history together with target measurement data from the roadside device to predict future accident risks. The analysis unit can also refer to past accident data to predict accident risks under specific conditions. Furthermore, the analysis unit can integrate information from different data sources to more accurately predict future accidents. For example, the analysis unit can integrate sensor data from the roadside device and vehicle operation data to predict future accident risks. This allows the risk of accidents to be reduced by recursively predicting future accidents. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input data acquired from the collection unit into the generation AI and cause the generation AI to predict future accidents.

[0032] The suggestion unit can propose an optimal route and driving speed, including unknown routes, based on the prediction results. Examples of unknown routes include, but are not limited to, unregistered roads and newly opened roads. The suggestion unit can propose an optimal route based on criteria such as shortest distance, shortest time, and safety, based on the prediction results. The suggestion unit can also propose an optimal driving speed based on criteria such as a speed appropriate for traffic conditions and the legal speed. Furthermore, the suggestion unit can propose an optimal route and driving speed in bad weather based on weather data. For example, the suggestion unit can propose a non-slip route and an appropriate driving speed in rainy weather. By proposing an optimal route and driving speed, including unknown routes, accidents can be prevented. Some or all of the above-described processing in the suggestion unit is performed using a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input the prediction results obtained from the analysis unit into the generation AI and cause the generation AI to propose an optimal route and driving speed.

[0033] The ascertaining unit can ascertain pedestrians' behavior plans through a local resident's exercise habit support app or the like, and perform highly accurate movement predictions. Exercise habit support apps include, but are not limited to, functions such as a pedometer and GPS tracking. For example, the ascertaining unit collects location information from the local resident's exercise habit support app to ascertain pedestrians' behavior plans. The ascertaining unit can also collect exercise data from the local resident's exercise habit support app and predict behavior at specific times or locations. Furthermore, the ascertaining unit can integrate data from the local resident's exercise habit support app to perform more accurate behavior predictions. For example, the ascertaining unit can integrate location information from the local resident's exercise habit support app and predict future behavior patterns. By doing so, the risk of traffic accidents can be reduced by ascertaining pedestrians' behavior plans. Some or all of the above-described processing by the ascertaining unit may be performed using AI, or may be performed without AI. For example, the ascertaining unit can input data obtained from the exercise habit support app into a generation AI and cause the generation AI to ascertain the behavior plans.

[0034] The suggestion unit can predict a traffic accident between a pedestrian and a vehicle with a high probability and suggest a means to avoid the accident. Examples of high probability include, but are not limited to, prediction accuracy and statistical confidence intervals. For example, the suggestion unit can suggest a route to a vehicle to avoid the risk of contact based on pedestrian behavior data. The suggestion unit can also suggest a driving speed to a vehicle to avoid the risk of contact based on pedestrian movement patterns. Furthermore, the suggestion unit can also suggest a driving plan to a vehicle to avoid the risk of contact based on pedestrian behavior data. For example, the suggestion unit can suggest a route to a vehicle to avoid the risk of contact based on pedestrian location information. This makes it possible to predict a traffic accident with a high probability and suggest a means to avoid the accident, thereby reducing the risk of the accident. Some or all of the above-described processing in the suggestion unit is performed using a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input the prediction results obtained from the analysis unit into the generation AI and cause the generation AI to suggest a means to avoid the accident.

[0035] The collection unit can optimize the collection method according to the weather and time of day when collecting data for road-vehicle cooperation. For example, in rainy weather, the collection unit uses a roadside unit sensor to accurately collect data even in poor visibility conditions. The collection unit can also collect data in the dark at night using an infrared sensor. Furthermore, the collection unit can increase the frequency of data collection during times of heavy traffic to obtain more detailed information. For example, the collection unit uses a weather sensor to optimize data collection during rainy weather. This improves the accuracy of data collection by optimizing the collection method according to the weather and time of day. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit can input data obtained from a weather sensor into the generation AI and cause the generation AI to optimize the collection method.

[0036] The collection unit can integrate data from different sensors to identify dangerous areas with higher accuracy. For example, the collection unit can integrate camera data from a roadside device and radar data from a vehicle, and identify dangerous areas by combining visual and distance information. The collection unit can also integrate location information from a pedestrian's smartphone with sensor information from the roadside device to accurately grasp pedestrian movements. Furthermore, the collection unit can integrate data from weather sensors and traffic volume sensors to identify dangerous areas during bad weather. For example, the collection unit can integrate camera data from a roadside device and radar data from a vehicle, and identify dangerous areas by combining visual and distance information. In this way, by integrating data from different sensors, the accuracy of identifying dangerous areas can be improved. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without AI. For example, the collection unit can input data obtained from different sensors into a generation AI and have the generation AI identify dangerous areas.

[0037] The collection unit can refer to past accident data and strengthen data collection under specific conditions. For example, the collection unit can strengthen data collection at intersections where many accidents have occurred in the past to obtain detailed information. The collection unit can also refer to accident data under specific weather conditions (e.g., rainy or snowy weather) to strengthen data collection under similar conditions. The collection unit can also refer to accident data during specific time periods (e.g., rush hour) to strengthen data collection during those time periods. For example, the collection unit can strengthen data collection at intersections where many accidents have occurred in the past to obtain detailed information. In this way, by referring to past accident data, data collection under specific conditions is strengthened. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit can input past accident data into the generation AI and cause the generation AI to strengthen data collection under specific conditions.

[0038] The collection unit can acquire vehicle speed and position information in real time and use it to identify dangerous areas. For example, the collection unit can acquire vehicle speed information in real time and identify areas where sudden braking is required. The collection unit can also acquire vehicle position information in real time and identify dangerous areas such as intersections and curves. Furthermore, the collection unit can combine vehicle speed and position information to identify dangerous driving patterns. For example, the collection unit can acquire vehicle speed information in real time and identify areas where sudden braking is required. In this way, acquiring vehicle speed and position information in real time improves the accuracy of identifying dangerous areas. Some or all of the above-mentioned processing in the collection unit may be performed using AI or may be performed without using AI. For example, the collection unit can input vehicle speed information and position information to a generation AI and cause the generation AI to identify dangerous areas.

[0039] The collection unit can collect data from pedestrians' smartphones and understand the pedestrians' movements. For example, the collection unit can collect location information from the pedestrians' smartphones and understand the pedestrians' current locations. The collection unit can also collect acceleration sensor information from the pedestrians' smartphones and understand the pedestrians' movement patterns. The collection unit can also collect Wi-Fi connection information from the pedestrians' smartphones and understand the pedestrians' movement routes. For example, the collection unit can collect location information from the pedestrians' smartphones and understand the pedestrians' current locations. In this way, by collecting data from the pedestrians' smartphones, the pedestrians' movements can be accurately understood. Some or all of the above-described processing in the collection unit may be performed using AI or without AI. For example, the collection unit can input data acquired from the pedestrians' smartphones into a generation AI and cause the generation AI to understand the pedestrians' movements.

[0040] The collection unit can collect information on traffic signals and signs and reflect it in vehicle operation. For example, the collection unit can collect information on traffic signal status in real time and reflect it in the vehicle operation plan. The collection unit can also collect information on traffic signs and reflect it in the vehicle operation route. Furthermore, the collection unit can collect predicted changes in traffic signals and adjust the vehicle operation speed. For example, the collection unit can collect information on traffic signals in real time and reflect it in the vehicle operation plan. In this way, by collecting information on traffic signals and signs, it is possible to reflect it in the vehicle operation plan. Some or all of the above-mentioned processing in the collection unit may be performed using AI or may be performed without using AI. For example, the collection unit can input information on traffic signals and signs to the generation AI and have the generation AI reflect the information in the operation plan.

[0041] The analysis unit can integrate information from different data sources to perform more accurate future accident predictions. For example, the analysis unit can integrate roadside device sensor data and vehicle operation data to predict future accident risks. The analysis unit can also integrate pedestrian smartphone data and traffic signal data to predict accident risks at intersections. Furthermore, the analysis unit can integrate weather data and traffic volume data to predict accident risks during bad weather. For example, the analysis unit can integrate roadside device sensor data and vehicle operation data to predict future accident risks. In this way, by integrating information from different data sources, the accuracy of future accident predictions is improved. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input information obtained from different data sources into the generation AI and cause the generation AI to perform future accident predictions.

[0042] The analysis unit can optimize the analysis algorithm by referring to past analysis results. For example, the analysis unit can refer to past accident prediction results and optimize the algorithm to improve prediction accuracy. The analysis unit can also improve analysis accuracy under specific conditions based on past data analysis results. Furthermore, the analysis unit can feed back past analysis results and adjust the algorithm in real time. For example, the analysis unit can refer to past accident prediction results and optimize the algorithm to improve prediction accuracy. In this way, the accuracy of the analysis algorithm is improved by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI optimize the algorithm.

[0043] The analysis unit can analyze the vehicle's operation history and extract specific patterns to predict future accidents. For example, the analysis unit can analyze the vehicle's operation history and extract patterns of sudden braking and abrupt steering to predict accident risk. The analysis unit can also predict accident risk at specific time periods or locations based on the vehicle's operation history. Furthermore, the analysis unit can analyze the vehicle's operation history and predict the risk that specific driving patterns will lead to accidents. For example, the analysis unit can analyze the vehicle's operation history and extract patterns of sudden braking and abrupt steering to predict accident risk. In this way, analyzing the vehicle's operation history improves the accuracy of future accident predictions. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the vehicle's operation history into a generation AI and cause the generation AI to perform future accident predictions.

[0044] The analysis unit can analyze pedestrian behavior data and evaluate the risk of contact between pedestrians and vehicles. The analysis unit can, for example, analyze pedestrian location information and evaluate the risk of contact with vehicles. The analysis unit can also analyze pedestrian movement patterns and predict the risk of contact with vehicles. Furthermore, the analysis unit can evaluate the risk of contact at a specific location based on pedestrian behavior data. For example, the analysis unit analyzes pedestrian location information and evaluates the risk of contact with vehicles. In this way, analyzing pedestrian behavior data improves the accuracy of the assessment of contact risk. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input pedestrian behavior data to a generation AI and cause the generation AI to evaluate the risk of contact.

[0045] The analysis unit can analyze traffic volume data and propose an operation plan according to the congestion situation. For example, the analysis unit can analyze traffic volume data and adjust the operation plan for time periods when congestion is expected. The analysis unit can also propose detour routes to avoid congestion based on the traffic volume data. Furthermore, the analysis unit can analyze traffic volume data and propose an operation plan according to the congestion situation at a specific location. For example, the analysis unit analyzes traffic volume data and adjusts the operation plan for time periods when congestion is expected. In this way, by analyzing the traffic volume data, it is possible to propose an operation plan according to the congestion situation. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input traffic volume data to a generation AI and cause the generation AI to propose an operation plan.

[0046] The analysis unit can analyze road conditions and evaluate operational risks. For example, the analysis unit can analyze the road pavement condition and evaluate operational risks in sections where deterioration is progressing. The analysis unit can also analyze road construction information and evaluate operational risks in sections where construction is underway. Furthermore, the analysis unit can evaluate operational risks at specific locations based on road condition data. For example, the analysis unit can analyze the road pavement condition and evaluate operational risks in sections where deterioration is progressing. In this way, analyzing the road condition improves the accuracy of the operational risk evaluation. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input road condition data to a generation AI and have the generation AI perform an operational risk evaluation.

[0047] The suggestion unit can optimize the suggestion algorithm by referring to past suggestion results. For example, the suggestion unit can optimize the algorithm to improve suggestion accuracy by referring to past suggestion results. The suggestion unit can also improve suggestion accuracy under specific conditions based on past data. Furthermore, the suggestion unit can feed back past suggestion results and adjust the algorithm in real time. For example, the suggestion unit can optimize the algorithm to improve suggestion accuracy by referring to past suggestion results. As a result, the accuracy of the suggestion algorithm is improved by referring to past suggestion results. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input past suggestion results into the generation AI and cause the generation AI to optimize the algorithm.

[0048] The suggestion unit can analyze the vehicle's driving history and propose an optimal route and driving speed under specific conditions. For example, the suggestion unit can analyze the vehicle's driving history and propose an optimal route for a specific time period or location. The suggestion unit can also propose an optimal driving speed under specific conditions based on the vehicle's driving history. Furthermore, the suggestion unit can analyze the vehicle's driving history and propose an optimal route and driving speed based on a specific driving pattern. For example, the suggestion unit can analyze the vehicle's driving history and propose an optimal route for a specific time period or location. As a result, the analysis of the vehicle's driving history improves the accuracy of the proposal of the optimal route and driving speed. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input the vehicle's driving history into the generation AI and cause the generation AI to propose an optimal route and driving speed.

[0049] The suggestion unit can integrate information from different data sources to make more accurate suggestions. For example, the suggestion unit can integrate sensor data from roadside devices and vehicle operation data to suggest an optimal route and driving speed. The suggestion unit can also integrate smartphone data of pedestrians and traffic signal data to suggest an optimal route and driving speed at an intersection. The suggestion unit can also integrate weather data and traffic volume data to suggest an optimal route and driving speed in bad weather. For example, the suggestion unit can integrate sensor data from roadside devices and vehicle operation data to suggest an optimal route and driving speed. This improves the accuracy of suggestions by integrating information from different data sources. Some or all of the above-described processing in the suggestion unit is performed using a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input information obtained from different data sources into the generation AI to improve the accuracy of suggestions.

[0050] The suggestion unit can make suggestions for avoiding the risk of contact between pedestrians and vehicles based on pedestrian behavior data. The suggestion unit can, for example, suggest a route for vehicles to avoid the risk of contact based on pedestrian location information. The suggestion unit can also suggest a driving speed for vehicles to avoid the risk of contact based on pedestrian movement patterns. The suggestion unit can also propose a driving plan for vehicles to avoid the risk of contact based on pedestrian behavior data. For example, the suggestion unit can suggest a route for vehicles to avoid the risk of contact based on pedestrian location information. As a result, making suggestions based on pedestrian behavior data improves the accuracy of avoiding the risk of contact. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input pedestrian behavior data to the generation AI and cause the generation AI to execute a suggestion for avoiding the risk of contact.

[0051] The proposal unit can propose an optimal operation plan based on information about traffic signals and signs. The proposal unit can propose an optimal operation plan for a vehicle based on, for example, the status of traffic signals. The proposal unit can also propose an optimal route for a vehicle based on information about traffic signs. Furthermore, the proposal unit can propose an optimal driving speed for a vehicle based on predicted changes in traffic signals. For example, the proposal unit proposes an optimal operation plan for a vehicle based on the status of traffic signals. As a result, by making proposals based on information about traffic signals and signs, the accuracy of the operation plan is improved. Some or all of the above-mentioned processing in the proposal unit is performed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the proposal unit can input information about traffic signals and signs into the generation AI and cause the generation AI to propose an operation plan.

[0052] The suggestion unit can suggest an optimal route and driving speed in bad weather based on weather data. For example, the suggestion unit can suggest a non-slip route and an appropriate driving speed in rainy weather. The suggestion unit can also suggest a snow-cleared route and a safe driving speed in snowy weather. Furthermore, the suggestion unit can suggest a route with good visibility and an appropriate driving speed in foggy weather. For example, the suggestion unit can suggest a non-slip route and an appropriate driving speed in rainy weather. In this way, by making suggestions based on weather data, it is possible to reduce driving risks in bad weather. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input weather data into the generation AI and cause the generation AI to suggest an optimal route and driving speed in bad weather.

[0053] The grasping unit can analyze the pedestrian's past behavior history and predict his / her future behavior. For example, the grasping unit can analyze the pedestrian's past location information and predict his / her future behavior pattern. The grasping unit can also predict the pedestrian's behavior at a specific time period or location based on the pedestrian's past movement history. Furthermore, the grasping unit can analyze the pedestrian's past behavior data and predict his / her future behavior under specific conditions. For example, the grasping unit can analyze the pedestrian's past location information and predict his / her future behavior pattern. In this way, by analyzing the pedestrian's past behavior history, the accuracy of the future behavior prediction is improved. Some or all of the above-described processing in the grasping unit may be performed using AI, or may be performed without using AI. For example, the grasping unit can input the pedestrian's past behavior data into the generation AI and cause the generation AI to predict his / her future behavior.

[0054] The ascertaining unit can collect data from the pedestrian's smartphone and ascertain the behavior plan in real time. For example, the ascertaining unit can collect location information from the pedestrian's smartphone in real time and ascertain the current behavior plan. The ascertaining unit can also collect acceleration sensor information from the pedestrian's smartphone in real time and ascertain the current movement pattern. Furthermore, the ascertaining unit can collect Wi-Fi connection information from the pedestrian's smartphone in real time and ascertain the current movement route. For example, the ascertaining unit can collect location information from the pedestrian's smartphone in real time and ascertain the current behavior plan. In this way, by collecting data from the pedestrian's smartphone, the behavior plan can be ascertained in real time. Some or all of the above-mentioned processing in the ascertaining unit may be performed using AI or without AI. For example, the ascertaining unit can input data obtained from the pedestrian's smartphone to the generation AI and cause the generation AI to ascertain the behavior plan.

[0055] The ascertaining unit can integrate data from the local resident's exercise habit support app to perform more accurate behavioral predictions. For example, the ascertaining unit can integrate location information from the local resident's exercise habit support app to predict future behavioral patterns. The ascertaining unit can also integrate exercise data from the local resident's exercise habit support app to predict behavior at specific times or locations. Furthermore, the ascertaining unit can analyze data from the local resident's exercise habit support app to predict future behavior under specific conditions. For example, the ascertaining unit can integrate location information from the local resident's exercise habit support app to predict future behavioral patterns. In this way, integrating data from the local resident's exercise habit support app improves the accuracy of behavioral predictions. Some or all of the above-described processing in the ascertaining unit may be performed using AI, or may be performed without AI. For example, the ascertaining unit can input data obtained from the exercise habit support app to a generation AI and cause the generation AI to perform behavioral predictions.

[0056] The ascertaining unit can ascertain a behavior plan based on the geographical location information of the pedestrian. For example, the ascertaining unit may ascertain a current behavior plan based on the geographical location information of the pedestrian. The ascertaining unit may also ascertain behavior at a specific time period or location based on the geographical location information of the pedestrian. Furthermore, the ascertaining unit may ascertain a behavior plan under specific conditions based on the geographical location information of the pedestrian. For example, the ascertaining unit may ascertain a current behavior plan based on the geographical location information of the pedestrian. As a result, by ascertaining a behavior plan based on the geographical location information of the pedestrian, the accuracy of behavior prediction is improved. Some or all of the above-described processing in the ascertaining unit may be performed using AI or may be performed without using AI. For example, the ascertaining unit may input the geographical location information of the pedestrian to the generation AI and cause the generation AI to ascertain the behavior plan.

[0057] The ascertaining unit can analyze the pedestrian's social media activity and ascertain the action plan. For example, the ascertaining unit can analyze the pedestrian's social media check-in information and ascertain the pedestrian's current action plan. The ascertaining unit can also analyze the pedestrian's social media posts and ascertain the pedestrian's behavior at a specific time or location. Furthermore, the ascertaining unit can ascertain the pedestrian's action plan under specific conditions by referring to the pedestrian's friends' activity on social media. For example, the ascertaining unit can analyze the pedestrian's social media check-in information and ascertain the pedestrian's current action plan. In this way, the accuracy of ascertaining the action plan can be improved by analyzing the pedestrian's social media activity. Some or all of the above-described processing in the ascertaining unit may be performed using AI or without AI. For example, the ascertaining unit can input data obtained from social media into the generation AI and cause the generation AI to ascertain the action plan.

[0058] The grasping unit can customize the method of grasping the action plan by reflecting pedestrian feedback. For example, the grasping unit adjusts the method of grasping the action plan based on pedestrian feedback. The grasping unit can also customize the action plan for a specific time period or location by reflecting pedestrian feedback. Furthermore, the grasping unit can analyze pedestrian feedback and optimize the method of grasping the action plan under specific conditions. For example, the grasping unit adjusts the method of grasping the action plan based on pedestrian feedback. In this way, the method of grasping the action plan can be optimized by reflecting pedestrian feedback. Some or all of the above-mentioned processing in the grasping unit may be performed using AI or may be performed without using AI. For example, the grasping unit can input feedback data to the generation AI and cause the generation AI to customize the method of grasping the action plan.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The collection unit can optimize the data collection method depending on the weather and time of day. For example, in rainy weather, the roadside unit's sensors can be used to accurately collect data even in poor visibility. At night, infrared sensors can be used to collect data even in the dark. Furthermore, during times of heavy traffic, the frequency of data collection can be increased to obtain more detailed information. This improves the accuracy of data collection by optimizing the collection method depending on the weather and time of day. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit can input data acquired from a weather sensor into the generation AI and have the generation AI optimize the collection method.

[0061] The collection unit can integrate data from different sensors to identify dangerous areas with higher accuracy. For example, it can integrate camera data from roadside devices and radar data from vehicles, combining visual and distance information to identify dangerous areas. It can also integrate location information from pedestrians' smartphones with sensor information from roadside devices to accurately grasp pedestrian movements. It can also integrate data from weather sensors and traffic volume sensors to identify dangerous areas during bad weather. By integrating data from different sensors, the accuracy of identifying dangerous areas can be improved. Some or all of the above-described processing in the collection unit may be performed using AI, or may be performed without AI. For example, the collection unit can input data obtained from different sensors into a generation AI and have the generation AI identify dangerous areas.

[0062] The analysis unit can optimize the analysis algorithm by referring to past analysis results. For example, it can refer to past accident prediction results and optimize the algorithm to improve prediction accuracy. It can also improve analysis accuracy under specific conditions based on past data analysis results. Furthermore, it can feed back past analysis results and adjust the algorithm in real time. In this way, the accuracy of the analysis algorithm can be improved by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI optimize the algorithm.

[0063] The suggestion unit can optimize the suggestion algorithm by referring to past suggestion results. For example, the suggestion unit can optimize the algorithm to improve suggestion accuracy by referring to past suggestion results. The suggestion unit can also improve suggestion accuracy under specific conditions based on past data. Furthermore, the suggestion unit can feed back past suggestion results and adjust the algorithm in real time. This improves the accuracy of the suggestion algorithm by referring to past suggestion results. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input past suggestion results into the generation AI and cause the generation AI to optimize the algorithm.

[0064] The analysis unit can analyze the vehicle's operation history and extract specific patterns to predict future accidents. For example, the analysis unit can analyze the vehicle's operation history and extract patterns of sudden braking and sudden steering to predict accident risk. The analysis unit can also predict the risk of accidents at specific times or locations based on the vehicle's operation history. Furthermore, the analysis unit can analyze the vehicle's operation history and predict the risk that specific driving patterns will lead to accidents. Thus, analyzing the vehicle's operation history improves the accuracy of future accident predictions. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the vehicle's operation history into a generation AI and have the generation AI execute future accident predictions.

[0065] The suggestion unit can suggest optimal routes and driving speeds in bad weather based on weather data. For example, in rainy weather, it can suggest a non-slip route and an appropriate driving speed. In snowy weather, it can also suggest a route that has been cleared of snow and a safe driving speed. Furthermore, in foggy weather, it can suggest a route with good visibility and an appropriate driving speed. In this way, by making suggestions based on weather data, it is possible to reduce driving risks in bad weather. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input weather data into the generation AI and have the generation AI suggest optimal routes and driving speeds in bad weather.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The collection unit collects data. This data includes sensor data, GPS data, user data, etc. The collection unit collects road-vehicle coordination data and identifies dangerous areas in advance. It can also obtain vehicle speed and location information in real time, which can be used to identify dangerous areas. It can also collect data from pedestrians' smartphones to understand their movements. For example, it can collect location information from pedestrians' smartphones to understand their current location. Step 2: The analysis unit analyzes the data collected by the collection unit. For example, it analyzes the autonomous vehicle's driving plan and real-time movement records together with target measurement data from roadside devices, and recursively predicts future accidents at dangerous locations. Recursive predictions are made using time series analysis and machine learning models. Step 3: The proposal unit proposes the optimal route and driving speed based on the analysis results obtained by the analysis unit. The proposal unit proposes the optimal route and driving speed, including unknown routes, based on the prediction results. The optimal route and driving speed can also be proposed using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. Step 4: The identification unit identifies the pedestrian's movement plan. For example, it can identify the pedestrian's movement plan through an app that supports exercise habits for local residents, and predicts their movements with high accuracy.

[0068] (Example 2) The safe operation system for autonomous vehicles according to an embodiment of the present invention provides a mechanism for obtaining blind spot information that cannot be fully recognized by the vehicle alone. This system accumulates roadside cooperative data and identifies dangerous areas in advance. Next, the autonomous vehicle's driving plan and real-time travel history, along with target measurement data from roadside devices, are input, and the generation AI recursively predicts future accidents at dangerous areas. Based on the prediction results, the generation AI proposes optimal routes and driving speeds, including unknown routes. This prevents accidents, contributes to safe vehicle operation, provides passengers with peace of mind, and stimulates further travel motivation. Furthermore, the generation AI grasps pedestrian behavior plans through apps such as those supporting local residents' exercise habits, and makes highly accurate movement predictions. This enables pedestrian-vehicle traffic accidents to be predicted and avoided with a high probability. For example, when a roadside device is installed at an intersection, it collects information on vehicles and pedestrians approaching the intersection in real time, and the generation AI analyzes this information to predict the risk of an accident at the intersection. Based on the prediction results, the generative AI proposes optimal routes and driving speeds for vehicles and notifies pedestrians to take appropriate action. This enables the safe operation of autonomous vehicles and significantly reduces the risk of traffic accidents. It also provides a safer travel environment for pedestrians, improving traffic safety throughout the region.

[0069] A safe operation system for an autonomous vehicle according to an embodiment includes a collection unit, an analysis unit, a proposal unit, and an understanding unit. The collection unit collects data. Examples of the data include, but are not limited to, sensor data, GPS data, and user data. The collection unit, for example, collects road-to-vehicle coordination data and identifies dangerous areas in advance. The collection unit can also acquire vehicle speed and location information in real time and use the information to identify dangerous areas. The collection unit can also collect data from pedestrians' smartphones and understand their movements. For example, the collection unit collects location information from pedestrians' smartphones and understands their current locations. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit analyzes the autonomous vehicle's driving plan and real-time movement history together with target measurement data from a roadside device, and recursively predicts future accidents at dangerous areas. The recursive prediction is performed using, for example, time series analysis or a machine learning model. The proposal unit proposes an optimal route and driving speed based on the analysis results obtained by the analysis unit. The suggestion unit proposes an optimal route and driving speed, including an unknown route, based on the prediction result, for example. The suggestion unit can also propose an optimal route and driving speed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. The understanding unit understands the pedestrian's behavior plan. The understanding unit understands the pedestrian's behavior plan through, for example, an app to support exercise habits for local residents, and performs highly accurate movement prediction. As a result, the safe operation system for autonomous vehicles according to the embodiment can achieve safe operation of autonomous vehicles by linking the elements of data collection, analysis, proposal, and understanding.

[0070] The collection unit collects road-to-vehicle coordination data and can identify dangerous areas in advance. Examples of road-to-vehicle coordination data include, but are not limited to, V2X communication data and traffic signal data. The collection unit, for example, uses a sensor in a roadside device to collect information about vehicles approaching intersections. The collection unit can also collect traffic signal statuses in real time and reflect the information in vehicle operation plans. The collection unit can also collect location information from pedestrians' smartphones and understand their movements. For example, the collection unit collects location information from pedestrians' smartphones to understand their current locations. By collecting road-to-vehicle coordination data, dangerous areas can be identified in advance. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input data acquired from a sensor in a roadside device to a generation AI and cause the generation AI to identify dangerous areas.

[0071] The analysis unit can analyze the autonomous vehicle's driving plan and real-time movement history together with target measurement data from the roadside device to recursively predict future accidents at dangerous locations. The driving plan can include, but is not limited to, routes, speeds, and stopping points. The real-time movement history can include, but is not limited to, GPS data and speed data. The target measurement data can include, but is not limited to, LIDAR data and camera data. The recursive prediction can be performed using, for example, time series analysis or a machine learning model. For example, the analysis unit can analyze the autonomous vehicle's driving plan and real-time movement history together with target measurement data from the roadside device to predict future accident risks. The analysis unit can also refer to past accident data to predict accident risks under specific conditions. Furthermore, the analysis unit can integrate information from different data sources to more accurately predict future accidents. For example, the analysis unit can integrate sensor data from the roadside device and vehicle operation data to predict future accident risks. This allows the risk of accidents to be reduced by recursively predicting future accidents. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input data acquired from the collection unit into the generation AI and cause the generation AI to predict future accidents.

[0072] The suggestion unit can propose an optimal route and driving speed, including unknown routes, based on the prediction results. Examples of unknown routes include, but are not limited to, unregistered roads and newly opened roads. The suggestion unit can propose an optimal route based on criteria such as shortest distance, shortest time, and safety, based on the prediction results. The suggestion unit can also propose an optimal driving speed based on criteria such as a speed appropriate for traffic conditions and the legal speed. Furthermore, the suggestion unit can propose an optimal route and driving speed in bad weather based on weather data. For example, the suggestion unit can propose a non-slip route and an appropriate driving speed in rainy weather. By proposing an optimal route and driving speed, including unknown routes, accidents can be prevented. Some or all of the above-described processing in the suggestion unit is performed using a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input the prediction results obtained from the analysis unit into the generation AI and cause the generation AI to propose an optimal route and driving speed.

[0073] The ascertaining unit can ascertain pedestrians' behavior plans through a local resident's exercise habit support app or the like, and perform highly accurate movement predictions. Exercise habit support apps include, but are not limited to, functions such as a pedometer and GPS tracking. For example, the ascertaining unit collects location information from the local resident's exercise habit support app to ascertain pedestrians' behavior plans. The ascertaining unit can also collect exercise data from the local resident's exercise habit support app and predict behavior at specific times or locations. Furthermore, the ascertaining unit can integrate data from the local resident's exercise habit support app to perform more accurate behavior predictions. For example, the ascertaining unit can integrate location information from the local resident's exercise habit support app and predict future behavior patterns. By doing so, the risk of traffic accidents can be reduced by ascertaining pedestrians' behavior plans. Some or all of the above-described processing by the ascertaining unit may be performed using AI, or may be performed without AI. For example, the ascertaining unit can input data obtained from the exercise habit support app into a generation AI and cause the generation AI to ascertain the behavior plans.

[0074] The suggestion unit can predict a traffic accident between a pedestrian and a vehicle with a high probability and suggest a means to avoid the accident. Examples of high probability include, but are not limited to, prediction accuracy and statistical confidence intervals. For example, the suggestion unit can suggest a route to a vehicle to avoid the risk of contact based on pedestrian behavior data. The suggestion unit can also suggest a driving speed to a vehicle to avoid the risk of contact based on pedestrian movement patterns. Furthermore, the suggestion unit can also suggest a driving plan to a vehicle to avoid the risk of contact based on pedestrian behavior data. For example, the suggestion unit can suggest a route to a vehicle to avoid the risk of contact based on pedestrian location information. This makes it possible to predict a traffic accident with a high probability and suggest a means to avoid the accident, thereby reducing the risk of the accident. Some or all of the above-described processing in the suggestion unit is performed using a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input the prediction results obtained from the analysis unit into the generation AI and cause the generation AI to suggest a means to avoid the accident.

[0075] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection to reduce the user's burden. Furthermore, if the user is relaxed, the collection unit can increase the frequency of data collection to obtain more detailed information. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting only important data and process it quickly. For example, the collection unit can capture the user's facial expressions with a camera and estimate the emotions using an emotion estimation algorithm. This adjusts the timing of data collection based on the user's emotions, thereby reducing the user's burden. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using AI, or without AI. For example, the collection unit can input image data of the user captured with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0076] The collection unit can optimize the collection method according to the weather and time of day when collecting data for road-vehicle cooperation. For example, in rainy weather, the collection unit uses a roadside unit sensor to accurately collect data even in poor visibility conditions. The collection unit can also collect data in the dark at night using an infrared sensor. Furthermore, the collection unit can increase the frequency of data collection during times of heavy traffic to obtain more detailed information. For example, the collection unit uses a weather sensor to optimize data collection during rainy weather. This improves the accuracy of data collection by optimizing the collection method according to the weather and time of day. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit can input data obtained from a weather sensor into the generation AI and cause the generation AI to optimize the collection method.

[0077] The collection unit can integrate data from different sensors to identify dangerous areas with higher accuracy. For example, the collection unit can integrate camera data from a roadside device and radar data from a vehicle, and identify dangerous areas by combining visual and distance information. The collection unit can also integrate location information from a pedestrian's smartphone with sensor information from the roadside device to accurately grasp pedestrian movements. Furthermore, the collection unit can integrate data from weather sensors and traffic volume sensors to identify dangerous areas during bad weather. For example, the collection unit can integrate camera data from a roadside device and radar data from a vehicle, and identify dangerous areas by combining visual and distance information. In this way, by integrating data from different sensors, the accuracy of identifying dangerous areas can be improved. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without AI. For example, the collection unit can input data obtained from different sensors into a generation AI and have the generation AI identify dangerous areas.

[0078] The collection unit can refer to past accident data and strengthen data collection under specific conditions. For example, the collection unit can strengthen data collection at intersections where many accidents have occurred in the past to obtain detailed information. The collection unit can also refer to accident data under specific weather conditions (e.g., rainy or snowy weather) to strengthen data collection under similar conditions. The collection unit can also refer to accident data during specific time periods (e.g., rush hour) to strengthen data collection during those time periods. For example, the collection unit can strengthen data collection at intersections where many accidents have occurred in the past to obtain detailed information. In this way, by referring to past accident data, data collection under specific conditions is strengthened. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit can input past accident data into the generation AI and cause the generation AI to strengthen data collection under specific conditions.

[0079] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit prioritizes collecting only important data, thereby reducing the user's burden. Furthermore, when the user is relaxed, the collection unit can prioritize collecting detailed data to obtain highly accurate information. Furthermore, when the user is in a hurry, the collection unit can prioritize collecting data that requires rapid processing. For example, the collection unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. This reduces the user's burden by prioritizing the data to be collected based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using AI, or without AI. For example, the collection unit can input image data of the user captured with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0080] The collection unit can acquire vehicle speed and position information in real time and use it to identify dangerous areas. For example, the collection unit can acquire vehicle speed information in real time and identify areas where sudden braking is required. The collection unit can also acquire vehicle position information in real time and identify dangerous areas such as intersections and curves. Furthermore, the collection unit can combine vehicle speed and position information to identify dangerous driving patterns. For example, the collection unit can acquire vehicle speed information in real time and identify areas where sudden braking is required. In this way, acquiring vehicle speed and position information in real time improves the accuracy of identifying dangerous areas. Some or all of the above-mentioned processing in the collection unit may be performed using AI or may be performed without using AI. For example, the collection unit can input vehicle speed information and position information to a generation AI and cause the generation AI to identify dangerous areas.

[0081] The collection unit can collect data from pedestrians' smartphones and understand the pedestrians' movements. For example, the collection unit can collect location information from the pedestrians' smartphones and understand the pedestrians' current locations. The collection unit can also collect acceleration sensor information from the pedestrians' smartphones and understand the pedestrians' movement patterns. The collection unit can also collect Wi-Fi connection information from the pedestrians' smartphones and understand the pedestrians' movement routes. For example, the collection unit can collect location information from the pedestrians' smartphones and understand the pedestrians' current locations. In this way, by collecting data from the pedestrians' smartphones, the pedestrians' movements can be accurately understood. Some or all of the above-described processing in the collection unit may be performed using AI or without AI. For example, the collection unit can input data acquired from the pedestrians' smartphones into a generation AI and cause the generation AI to understand the pedestrians' movements.

[0082] The collection unit can collect information on traffic signals and signs and reflect it in vehicle operation. For example, the collection unit can collect information on traffic signal status in real time and reflect it in the vehicle operation plan. The collection unit can also collect information on traffic signs and reflect it in the vehicle operation route. Furthermore, the collection unit can collect predicted changes in traffic signals and adjust the vehicle operation speed. For example, the collection unit can collect information on traffic signals in real time and reflect it in the vehicle operation plan. In this way, by collecting information on traffic signals and signs, it is possible to reflect it in the vehicle operation plan. Some or all of the above-mentioned processing in the collection unit may be performed using AI or may be performed without using AI. For example, the collection unit can input information on traffic signals and signs to the generation AI and have the generation AI reflect the information in the operation plan.

[0083] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. This reduces the burden on the user by adjusting the display method of the analysis results based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the analysis unit can be performed using AI or without AI. For example, the analysis unit can input image data of the user captured with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0084] The analysis unit can integrate information from different data sources to perform more accurate future accident predictions. For example, the analysis unit can integrate roadside device sensor data and vehicle operation data to predict future accident risks. The analysis unit can also integrate pedestrian smartphone data and traffic signal data to predict accident risks at intersections. Furthermore, the analysis unit can integrate weather data and traffic volume data to predict accident risks during bad weather. For example, the analysis unit can integrate roadside device sensor data and vehicle operation data to predict future accident risks. In this way, by integrating information from different data sources, the accuracy of future accident predictions is improved. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input information obtained from different data sources into the generation AI and cause the generation AI to perform future accident predictions.

[0085] The analysis unit can optimize the analysis algorithm by referring to past analysis results. For example, the analysis unit can refer to past accident prediction results and optimize the algorithm to improve prediction accuracy. The analysis unit can also improve analysis accuracy under specific conditions based on past data analysis results. Furthermore, the analysis unit can feed back past analysis results and adjust the algorithm in real time. For example, the analysis unit can refer to past accident prediction results and optimize the algorithm to improve prediction accuracy. In this way, the accuracy of the analysis algorithm is improved by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI optimize the algorithm.

[0086] The analysis unit can analyze the vehicle's operation history and extract specific patterns to predict future accidents. For example, the analysis unit can analyze the vehicle's operation history and extract patterns of sudden braking and abrupt steering to predict accident risk. The analysis unit can also predict accident risk at specific time periods or locations based on the vehicle's operation history. Furthermore, the analysis unit can analyze the vehicle's operation history and predict the risk that specific driving patterns will lead to accidents. For example, the analysis unit can analyze the vehicle's operation history and extract patterns of sudden braking and abrupt steering to predict accident risk. In this way, analyzing the vehicle's operation history improves the accuracy of future accident predictions. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the vehicle's operation history into a generation AI and cause the generation AI to perform future accident predictions.

[0087] The analysis unit can estimate the user's emotions and prioritize analysis results based on the estimated user emotions. For example, when the user is stressed, the analysis unit can prioritize displaying only important analysis results. Furthermore, when the user is relaxed, the analysis unit can prioritize displaying detailed analysis results. Furthermore, when the user is in a hurry, the analysis unit can prioritize displaying analysis results that require a quick response. For example, the analysis unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. This prioritizes the analysis results based on the user's emotions, thereby reducing the user's burden. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input image data of the user captured with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0088] The analysis unit can analyze pedestrian behavior data and evaluate the risk of contact between pedestrians and vehicles. The analysis unit can, for example, analyze pedestrian location information and evaluate the risk of contact with vehicles. The analysis unit can also analyze pedestrian movement patterns and predict the risk of contact with vehicles. Furthermore, the analysis unit can evaluate the risk of contact at a specific location based on pedestrian behavior data. For example, the analysis unit analyzes pedestrian location information and evaluates the risk of contact with vehicles. In this way, analyzing pedestrian behavior data improves the accuracy of the assessment of contact risk. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input pedestrian behavior data to a generation AI and cause the generation AI to evaluate the risk of contact.

[0089] The analysis unit can analyze traffic volume data and propose an operation plan according to the congestion situation. For example, the analysis unit can analyze traffic volume data and adjust the operation plan for time periods when congestion is expected. The analysis unit can also propose detour routes to avoid congestion based on the traffic volume data. Furthermore, the analysis unit can analyze traffic volume data and propose an operation plan according to the congestion situation at a specific location. For example, the analysis unit analyzes traffic volume data and adjusts the operation plan for time periods when congestion is expected. In this way, by analyzing the traffic volume data, it is possible to propose an operation plan according to the congestion situation. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input traffic volume data to a generation AI and cause the generation AI to propose an operation plan.

[0090] The analysis unit can analyze road conditions and evaluate operational risks. For example, the analysis unit can analyze the road pavement condition and evaluate operational risks in sections where deterioration is progressing. The analysis unit can also analyze road construction information and evaluate operational risks in sections where construction is underway. Furthermore, the analysis unit can evaluate operational risks at specific locations based on road condition data. For example, the analysis unit can analyze the road pavement condition and evaluate operational risks in sections where deterioration is progressing. In this way, analyzing the road condition improves the accuracy of the operational risk evaluation. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input road condition data to a generation AI and have the generation AI perform an operational risk evaluation.

[0091] The suggestion unit can estimate the user's emotions and adjust the way suggestions are presented based on the estimated user emotions. For example, if the user is nervous, the suggestion unit can provide simple, highly visible suggestions. Furthermore, if the user is relaxed, the suggestion unit can provide suggestions that include detailed information. Furthermore, if the user is in a hurry, the suggestion unit can provide suggestions that focus on the main points. For example, the suggestion unit can capture the user's facial expression with a camera and estimate the user's emotions using an emotion estimation algorithm. This can reduce the user's burden by adjusting the way suggestions are presented based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit is performed using the generation AI. For example, the suggestion unit can input image data of the user captured with a camera into the generation AI and cause the generation AI to adjust the way suggestions are presented.

[0092] The suggestion unit can optimize the suggestion algorithm by referring to past suggestion results. For example, the suggestion unit can optimize the algorithm to improve suggestion accuracy by referring to past suggestion results. The suggestion unit can also improve suggestion accuracy under specific conditions based on past data. Furthermore, the suggestion unit can feed back past suggestion results and adjust the algorithm in real time. For example, the suggestion unit can optimize the algorithm to improve suggestion accuracy by referring to past suggestion results. As a result, the accuracy of the suggestion algorithm is improved by referring to past suggestion results. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input past suggestion results into the generation AI and cause the generation AI to optimize the algorithm.

[0093] The suggestion unit can analyze the vehicle's driving history and propose an optimal route and driving speed under specific conditions. For example, the suggestion unit can analyze the vehicle's driving history and propose an optimal route for a specific time period or location. The suggestion unit can also propose an optimal driving speed under specific conditions based on the vehicle's driving history. Furthermore, the suggestion unit can analyze the vehicle's driving history and propose an optimal route and driving speed based on a specific driving pattern. For example, the suggestion unit can analyze the vehicle's driving history and propose an optimal route for a specific time period or location. As a result, the analysis of the vehicle's driving history improves the accuracy of the proposal of the optimal route and driving speed. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input the vehicle's driving history into the generation AI and cause the generation AI to propose an optimal route and driving speed.

[0094] The suggestion unit can integrate information from different data sources to make more accurate suggestions. For example, the suggestion unit can integrate sensor data from roadside devices and vehicle operation data to suggest an optimal route and driving speed. The suggestion unit can also integrate smartphone data of pedestrians and traffic signal data to suggest an optimal route and driving speed at an intersection. The suggestion unit can also integrate weather data and traffic volume data to suggest an optimal route and driving speed in bad weather. For example, the suggestion unit can integrate sensor data from roadside devices and vehicle operation data to suggest an optimal route and driving speed. This improves the accuracy of suggestions by integrating information from different data sources. Some or all of the above-described processing in the suggestion unit is performed using a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input information obtained from different data sources into the generation AI to improve the accuracy of suggestions.

[0095] The suggestion unit can estimate the user's emotions and prioritize suggestions based on the estimated user emotions. For example, if the user is feeling stressed, the suggestion unit can prioritize only important suggestions. Furthermore, if the user is relaxed, the suggestion unit can prioritize detailed suggestions. Furthermore, if the user is in a hurry, the suggestion unit can prioritize suggestions that require a quick response. For example, the suggestion unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. This can reduce the burden on the user by prioritizing suggestions based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit is performed using the generation AI. For example, the suggestion unit can input image data of the user captured with a camera into the generation AI and cause the generation AI to determine the priority of suggestions.

[0096] The suggestion unit can make suggestions for avoiding the risk of contact between pedestrians and vehicles based on pedestrian behavior data. The suggestion unit can, for example, suggest a route for vehicles to avoid the risk of contact based on pedestrian location information. The suggestion unit can also suggest a driving speed for vehicles to avoid the risk of contact based on pedestrian movement patterns. The suggestion unit can also propose a driving plan for vehicles to avoid the risk of contact based on pedestrian behavior data. For example, the suggestion unit can suggest a route for vehicles to avoid the risk of contact based on pedestrian location information. As a result, making suggestions based on pedestrian behavior data improves the accuracy of avoiding the risk of contact. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the suggestion unit can input pedestrian behavior data to the generation AI and cause the generation AI to execute a suggestion for avoiding the risk of contact.

[0097] The proposal unit can propose an optimal operation plan based on information about traffic signals and signs. The proposal unit can propose an optimal operation plan for a vehicle based on, for example, the status of traffic signals. The proposal unit can also propose an optimal route for a vehicle based on information about traffic signs. Furthermore, the proposal unit can propose an optimal driving speed for a vehicle based on predicted changes in traffic signals. For example, the proposal unit proposes an optimal operation plan for a vehicle based on the status of traffic signals. As a result, by making proposals based on information about traffic signals and signs, the accuracy of the operation plan is improved. Some or all of the above-mentioned processing in the proposal unit is performed using a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the proposal unit can input information about traffic signals and signs into the generation AI and cause the generation AI to propose an operation plan.

[0098] The suggestion unit can suggest an optimal route and driving speed in bad weather based on weather data. For example, the suggestion unit can suggest a non-slip route and an appropriate driving speed in rainy weather. The suggestion unit can also suggest a snow-cleared route and a safe driving speed in snowy weather. Furthermore, the suggestion unit can suggest a route with good visibility and an appropriate driving speed in foggy weather. For example, the suggestion unit can suggest a non-slip route and an appropriate driving speed in rainy weather. In this way, by making suggestions based on weather data, it is possible to reduce driving risks in bad weather. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input weather data into the generation AI and cause the generation AI to suggest an optimal route and driving speed in bad weather.

[0099] The grasping unit can estimate the user's emotions and adjust the method of grasping the pedestrian's behavior plan based on the estimated user's emotions. For example, if the user is nervous, the grasping unit grasps the pedestrian's behavior plan in a simple, highly visible manner. Furthermore, if the user is relaxed, the grasping unit can grasp the pedestrian's behavior plan in a manner that includes detailed information. Furthermore, if the user is in a hurry, the grasping unit can grasp the pedestrian's behavior plan in a manner that focuses on the main points. For example, the grasping unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. This reduces the burden on the user by adjusting the method of grasping the pedestrian's behavior plan based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the grasping unit may be performed using AI or without AI. For example, the understanding unit can input image data of a user taken with a camera into the generation AI and cause the generation AI to adjust the method of understanding the pedestrian's behavior plan.

[0100] The grasping unit can analyze the pedestrian's past behavior history and predict his / her future behavior. For example, the grasping unit can analyze the pedestrian's past location information and predict his / her future behavior pattern. The grasping unit can also predict the pedestrian's behavior at a specific time period or location based on the pedestrian's past movement history. Furthermore, the grasping unit can analyze the pedestrian's past behavior data and predict his / her future behavior under specific conditions. For example, the grasping unit can analyze the pedestrian's past location information and predict his / her future behavior pattern. In this way, by analyzing the pedestrian's past behavior history, the accuracy of the future behavior prediction is improved. Some or all of the above-described processing in the grasping unit may be performed using AI, or may be performed without using AI. For example, the grasping unit can input the pedestrian's past behavior data into the generation AI and cause the generation AI to predict his / her future behavior.

[0101] The ascertaining unit can collect data from the pedestrian's smartphone and ascertain the behavior plan in real time. For example, the ascertaining unit can collect location information from the pedestrian's smartphone in real time and ascertain the current behavior plan. The ascertaining unit can also collect acceleration sensor information from the pedestrian's smartphone in real time and ascertain the current movement pattern. Furthermore, the ascertaining unit can collect Wi-Fi connection information from the pedestrian's smartphone in real time and ascertain the current movement route. For example, the ascertaining unit can collect location information from the pedestrian's smartphone in real time and ascertain the current behavior plan. In this way, by collecting data from the pedestrian's smartphone, the behavior plan can be ascertained in real time. Some or all of the above-mentioned processing in the ascertaining unit may be performed using AI or without AI. For example, the ascertaining unit can input data obtained from the pedestrian's smartphone to the generation AI and cause the generation AI to ascertain the behavior plan.

[0102] The ascertaining unit can integrate data from the local resident's exercise habit support app to perform more accurate behavioral predictions. For example, the ascertaining unit can integrate location information from the local resident's exercise habit support app to predict future behavioral patterns. The ascertaining unit can also integrate exercise data from the local resident's exercise habit support app to predict behavior at specific times or locations. Furthermore, the ascertaining unit can analyze data from the local resident's exercise habit support app to predict future behavior under specific conditions. For example, the ascertaining unit can integrate location information from the local resident's exercise habit support app to predict future behavioral patterns. In this way, integrating data from the local resident's exercise habit support app improves the accuracy of behavioral predictions. Some or all of the above-described processing in the ascertaining unit may be performed using AI, or may be performed without AI. For example, the ascertaining unit can input data obtained from the exercise habit support app to a generation AI and cause the generation AI to perform behavioral predictions.

[0103] The grasping unit can estimate the user's emotions and prioritize action plans based on the estimated user emotions. For example, when the user is stressed, the grasping unit prioritizes only important action plans. Furthermore, when the user is relaxed, the grasping unit can prioritize detailed action plans. Furthermore, when the user is in a hurry, the grasping unit can prioritize action plans that require a quick response. For example, the grasping unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. This reduces the burden on the user by prioritizing action plans based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the grasping unit may be performed using AI, or may be performed without AI. For example, the grasping unit can input image data of the user captured with a camera into the generation AI and have the generation AI determine the priority of the action plans.

[0104] The ascertaining unit can ascertain a behavior plan based on the geographical location information of the pedestrian. For example, the ascertaining unit may ascertain a current behavior plan based on the geographical location information of the pedestrian. The ascertaining unit may also ascertain behavior at a specific time period or location based on the geographical location information of the pedestrian. Furthermore, the ascertaining unit may ascertain a behavior plan under specific conditions based on the geographical location information of the pedestrian. For example, the ascertaining unit may ascertain a current behavior plan based on the geographical location information of the pedestrian. As a result, by ascertaining a behavior plan based on the geographical location information of the pedestrian, the accuracy of behavior prediction is improved. Some or all of the above-described processing in the ascertaining unit may be performed using AI or may be performed without using AI. For example, the ascertaining unit may input the geographical location information of the pedestrian to the generation AI and cause the generation AI to ascertain the behavior plan.

[0105] The ascertaining unit can analyze the pedestrian's social media activity and ascertain the action plan. For example, the ascertaining unit can analyze the pedestrian's social media check-in information and ascertain the pedestrian's current action plan. The ascertaining unit can also analyze the pedestrian's social media posts and ascertain the pedestrian's behavior at a specific time or location. Furthermore, the ascertaining unit can ascertain the pedestrian's action plan under specific conditions by referring to the pedestrian's friends' activity on social media. For example, the ascertaining unit can analyze the pedestrian's social media check-in information and ascertain the pedestrian's current action plan. In this way, the accuracy of ascertaining the action plan can be improved by analyzing the pedestrian's social media activity. Some or all of the above-described processing in the ascertaining unit may be performed using AI or without AI. For example, the ascertaining unit can input data obtained from social media into the generation AI and cause the generation AI to ascertain the action plan.

[0106] The grasping unit can customize the method of grasping the action plan by reflecting pedestrian feedback. For example, the grasping unit adjusts the method of grasping the action plan based on pedestrian feedback. The grasping unit can also customize the action plan for a specific time period or location by reflecting pedestrian feedback. Furthermore, the grasping unit can analyze pedestrian feedback and optimize the method of grasping the action plan under specific conditions. For example, the grasping unit adjusts the method of grasping the action plan based on pedestrian feedback. In this way, the method of grasping the action plan can be optimized by reflecting pedestrian feedback. Some or all of the above-mentioned processing in the grasping unit may be performed using AI or may be performed without using AI. For example, the grasping unit can input feedback data to the generation AI and cause the generation AI to customize the method of grasping the action plan. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, proposal unit, and understanding unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects data using the camera 42 and GPS data of the smart device 14, and collects road-vehicle coordination data using the specific processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the collected data using the specific processing unit 290 of the data processing device 12 and recursively predicts future accidents at dangerous locations. For example, the proposal unit proposes an optimal route and driving speed using the specific processing unit 290 of the data processing device 12, and notifies the vehicle of the optimal route and driving speed using the control unit 46A of the smart device 14. For example, the understanding unit understands pedestrian behavior plans from a local resident exercise habit support app using the control unit 46A of the smart device 14, and performs highly accurate movement prediction using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, proposal unit, and understanding unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects data using the camera 42 and GPS data of the smart glasses 214, and collects road-vehicle coordination data by the identification processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the collected data by the identification processing unit 290 of the data processing device 12 and recursively predicts future accidents at dangerous locations. For example, the proposal unit proposes an optimal route and driving speed by the identification processing unit 290 of the data processing device 12, and notifies the vehicle by the control unit 46A of the smart glasses 214. For example, the understanding unit understands pedestrian behavior plans from a local resident exercise habit support app by the control unit 46A of the smart glasses 214, and performs highly accurate movement prediction by the identification processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, proposal unit, and understanding unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects data using the camera 42 and GPS data of the headset-type terminal 314, and collects road-vehicle coordination data using the identification processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the collected data using the identification processing unit 290 of the data processing device 12 and recursively predicts future accidents at dangerous locations. For example, the proposal unit proposes an optimal route and driving speed using the identification processing unit 290 of the data processing device 12, and notifies the vehicle of the proposal using the control unit 46A of the headset-type terminal 314. For example, the understanding unit understands pedestrian behavior plans from a local resident exercise habit support app using the control unit 46A of the headset-type terminal 314, and performs highly accurate movement prediction using the identification processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, proposal unit, and understanding unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects data using the camera 42 and GPS data of the robot 414, and collects road-vehicle coordination data by the identification processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the collected data by the identification processing unit 290 of the data processing device 12 and recursively predicts future accidents at dangerous locations. For example, the proposal unit proposes an optimal route and driving speed by the identification processing unit 290 of the data processing device 12, and notifies the vehicle by the control unit 46A of the robot 414. For example, the understanding unit understands pedestrian behavior plans from a local resident exercise habit support app by the control unit 46A of the robot 414, and performs highly accurate movement prediction by the identification processing unit 290 of the data processing device 12.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. This reduces the burden on the user by adjusting the display method of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using AI, or without AI. For example, the analysis unit can input image data of the user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0109] The collection unit can optimize the data collection method depending on the weather and time of day. For example, in rainy weather, the roadside unit's sensors can be used to accurately collect data even in poor visibility. At night, infrared sensors can be used to collect data even in the dark. Furthermore, during times of heavy traffic, the frequency of data collection can be increased to obtain more detailed information. This improves the accuracy of data collection by optimizing the collection method depending on the weather and time of day. Some or all of the above-mentioned processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit can input data acquired from a weather sensor into the generation AI and have the generation AI optimize the collection method.

[0110] The suggestion unit can estimate the user's emotions and adjust the way suggestions are presented based on the estimated user emotions. For example, if the user is nervous, the suggestion unit can provide simple, highly visible suggestions. If the user is relaxed, the suggestion unit can provide detailed suggestions. If the user is in a hurry, the suggestion unit can provide suggestions that focus on the main points. This reduces the burden on the user by adjusting the way suggestions are presented based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the suggestion unit is performed using the generation AI. For example, the suggestion unit can input image data of the user captured with a camera into the generation AI and cause the generation AI to adjust the way suggestions are presented.

[0111] The collection unit can integrate data from different sensors to identify dangerous areas with higher accuracy. For example, it can integrate camera data from roadside devices and radar data from vehicles, combining visual and distance information to identify dangerous areas. It can also integrate location information from pedestrians' smartphones with sensor information from roadside devices to accurately grasp pedestrian movements. It can also integrate data from weather sensors and traffic volume sensors to identify dangerous areas during bad weather. By integrating data from different sensors, the accuracy of identifying dangerous areas can be improved. Some or all of the above-described processing in the collection unit may be performed using AI, or may be performed without AI. For example, the collection unit can input data obtained from different sensors into a generation AI and have the generation AI identify dangerous areas.

[0112] The comprehension unit can estimate the user's emotions and prioritize action plans based on the estimated user emotions. For example, if the user is stressed, only important action plans can be prioritized. Also, if the user is relaxed, detailed action plans can be prioritized. Furthermore, if the user is in a hurry, action plans that require a quick response can be prioritized. This reduces the burden on the user by prioritizing action plans based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the comprehension unit can be performed using AI or without AI. For example, the comprehension unit can input image data of the user captured by a camera into the generation AI and have the generation AI determine the priority of action plans.

[0113] The analysis unit can optimize the analysis algorithm by referring to past analysis results. For example, it can refer to past accident prediction results and optimize the algorithm to improve prediction accuracy. It can also improve analysis accuracy under specific conditions based on past data analysis results. Furthermore, it can feed back past analysis results and adjust the algorithm in real time. In this way, the accuracy of the analysis algorithm can be improved by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI optimize the algorithm.

[0114] The suggestion unit can optimize the suggestion algorithm by referring to past suggestion results. For example, the suggestion unit can optimize the algorithm to improve suggestion accuracy by referring to past suggestion results. The suggestion unit can also improve suggestion accuracy under specific conditions based on past data. Furthermore, the suggestion unit can feed back past suggestion results and adjust the algorithm in real time. This improves the accuracy of the suggestion algorithm by referring to past suggestion results. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input past suggestion results into the generation AI and cause the generation AI to optimize the algorithm.

[0115] The collection unit can estimate the user's emotions and prioritize the data to be collected based on the estimated user emotions. For example, if the user is feeling stressed, only important data can be collected preferentially, reducing the user's burden. Also, if the user is relaxed, detailed data can be collected preferentially to obtain highly accurate information. Furthermore, if the user is in a hurry, data that requires rapid processing can be collected preferentially. This reduces the user's burden by prioritizing the data to be collected based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using AI, or without AI. For example, the collection unit can input image data of the user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0116] The analysis unit can analyze the vehicle's operation history and extract specific patterns to predict future accidents. For example, the analysis unit can analyze the vehicle's operation history and extract patterns of sudden braking and sudden steering to predict accident risk. The analysis unit can also predict the risk of accidents at specific times or locations based on the vehicle's operation history. Furthermore, the analysis unit can analyze the vehicle's operation history and predict the risk that specific driving patterns will lead to accidents. Thus, analyzing the vehicle's operation history improves the accuracy of future accident predictions. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the vehicle's operation history into a generation AI and have the generation AI execute future accident predictions.

[0117] The suggestion unit can suggest optimal routes and driving speeds in bad weather based on weather data. For example, in rainy weather, it can suggest a non-slip route and an appropriate driving speed. In snowy weather, it can also suggest a route that has been cleared of snow and a safe driving speed. Furthermore, in foggy weather, it can suggest a route with good visibility and an appropriate driving speed. In this way, by making suggestions based on weather data, it is possible to reduce driving risks in bad weather. Some or all of the above-mentioned processing in the suggestion unit is performed using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the suggestion unit can input weather data into the generation AI and have the generation AI suggest optimal routes and driving speeds in bad weather.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The collection unit collects data. This data includes sensor data, GPS data, user data, etc. The collection unit collects road-vehicle coordination data and identifies dangerous areas in advance. It can also obtain vehicle speed and location information in real time, which can be used to identify dangerous areas. It can also collect data from pedestrians' smartphones to understand their movements. For example, it can collect location information from pedestrians' smartphones to understand their current location. Step 2: The analysis unit analyzes the data collected by the collection unit. For example, it analyzes the autonomous vehicle's driving plan and real-time movement records together with target measurement data from roadside devices, and recursively predicts future accidents at dangerous locations. Recursive predictions are made using time series analysis and machine learning models. Step 3: The proposal unit proposes the optimal route and driving speed based on the analysis results obtained by the analysis unit. The proposal unit proposes the optimal route and driving speed, including unknown routes, based on the prediction results. The optimal route and driving speed can also be proposed using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. Step 4: The identification unit identifies the pedestrian's movement plan. For example, it can identify the pedestrian's movement plan through an app that supports exercise habits for local residents, and predicts their movements with high accuracy.

[0120] 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.

[0121] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0123] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0126] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0127] 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.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0129] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0134] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] 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.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0142] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0143] 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.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0145] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0146] 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.

[0147] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0148] 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.

[0149] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] 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.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0159] 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.

[0160] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0161] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0162] 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.

[0163] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0164] 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.

[0165] 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.

[0166] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0167] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0171] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0173] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0174] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0175] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0176] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0177] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0178] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0179] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0180] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0181] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0182] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0183] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0184] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0185] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0186] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0187] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0188] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0189] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0190] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0191] [Explanation of symbols]

[0192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects data; an analysis unit that analyzes the data collected by the collection unit; a suggestion unit that suggests an optimal route and driving speed based on the analysis result obtained by the analysis unit; and a grasping unit that grasps the pedestrian's action plan. A system characterized by:

2. The collecting unit Collecting road-vehicle coordination data and identifying dangerous areas in advance 2. The system of claim 1.

3. The analysis unit Analyze the driving plans and real-time movement records of autonomous vehicles together with target measurement data from roadside devices to recursively predict future accidents at dangerous locations.

2. The system of claim 1.

4. The proposal unit Based on the prediction results, the system proposes optimal routes and driving speeds, including unknown routes.

2. The system of claim 1.

5. The grasping unit Understanding pedestrian movement plans through apps that support local residents' exercise habits and making highly accurate predictions of movement 2. The system of claim 1.

6. The proposal unit Highly predictable traffic accidents between pedestrians and vehicles and suggest ways to avoid them 2. The system of claim 1.

7. The collecting unit Inferring user emotions and adjusting the timing of data collection based on the estimated user emotions 2. The system of claim 1.

8. The collecting unit Optimize data collection methods for road-vehicle coordination depending on weather and time of day 2. The system of claim 1.

Images