Driving behavior guiding method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a driving behavior guidance method and device, electronic equipment and storage medium, which relates to the technical field of Internet of Vehicles, and can acquire driving route, driving position and network quality data of a target vehicle through a vehicle end and upload them to a cloud end, receive dynamic network quality information and same-route vehicle information returned by the cloud end, generate and update an augmented reality virtual guidance interface in combination with a recognized driving event, and form driving behavior evaluation data, network contribution data and trip interaction data according to a response of the target vehicle to the guidance information, so as to solve the problem that the vehicle guidance, network state perception, vehicle cooperation and driving behavior evaluation are mutually isolated in the prior art, the guidance content is difficult to dynamically adjust according to real-time network state, vehicle position and driving event, and achieve the technical effects of improving the accuracy of driving behavior guidance, enhancing the interaction experience between vehicles and forming a closed loop of driving behavior evaluation and network contribution data.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle networking technology, and in particular to a driving behavior guidance method and device, electronic device and storage medium. Background Technology

[0002] With the development of intelligent transportation and in-vehicle display technology, overlaying navigation prompts, driving information, or entertainment information onto the vehicle's forward field of vision using augmented reality has become an important direction for improving the driving experience. Existing in-vehicle augmented reality applications mostly focus on basic navigation prompts or simple information displays, typically operating only around the vehicle's driving status. They lack coordination and interaction with other vehicles on the same route, real-time traffic scenarios, and the external network environment, making it difficult to provide continuous and effective guidance for driving behavior.

[0003] Meanwhile, existing driving incentive programs mostly use points and leaderboards to encourage safe driving, while network quality optimization mainly relies on operator road tests or user complaint feedback. These programs are independent of each other and fail to effectively integrate driving behavior recognition, vehicle collaboration, augmented reality guidance, and network quality perception. This results in a disconnect between virtual guidance content and real-time network status, and the incentive methods are relatively rigid, making it difficult to simultaneously meet the needs of improving driving safety, enhancing user engagement, and supporting network quality optimization. Summary of the Invention

[0004] This disclosure provides a driving behavior guidance method, device, electronic device, and storage medium. Its main purpose is to address the problem that existing in-vehicle guidance, driving incentives, and network quality perception are independent of each other, making it difficult to dynamically guide drivers by combining real-time road conditions, network status, and driving events.

[0005] According to a first aspect of this disclosure, a driving behavior guidance method is provided, comprising:

[0006] Acquire the target vehicle's driving route, driving location, and network quality data, and upload the driving route, driving location, and network quality data to the cloud; Receive dynamic network quality information and information on vehicles on the same route returned from the cloud; Identify driving events of the target vehicle; Based on driving location, dynamic network quality information, information of vehicles on the same route, and driving events, an augmented reality virtual guidance interface is generated and updated, and a guidance response result is generated based on the target vehicle's response to the guidance information in the augmented reality virtual guidance interface. Based on driving events, network quality data, and guidance response results, driving behavior evaluation data, network contribution data, and trip interaction data are generated respectively, and then uploaded to the cloud.

[0007] According to a second aspect of this disclosure, a driving behavior guidance method is provided, comprising: Receives driving routes, driving locations, and network quality data uploaded from multiple vehicle terminals; Spatiotemporal aggregation of driving location and network quality data is performed to generate dynamic network quality information; Based on the target vehicle's driving route, candidate vehicle routes, dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information, determine the information of vehicles on the same route; Send dynamic network quality information and information about vehicles on the same route to the vehicle terminal corresponding to the target vehicle; Receive driving behavior evaluation data, network contribution data, and trip interaction data uploaded by the vehicle; After the trip, settlement and incentive resources are allocated based on driving behavior evaluation data, network contribution data, and trip interaction data.

[0008] According to a third aspect of this disclosure, a driving behavior guidance device is provided, comprising: The acquisition unit is used to acquire the target vehicle's driving route, driving location, and network quality data, and upload the driving route, driving location, and network quality data to the cloud. The first receiving unit is used to receive dynamic network quality information and vehicle information on the same route returned from the cloud. The identification unit is used to identify driving events of the target vehicle; The first generation unit is used to generate and update the augmented reality virtual guidance interface based on driving location, dynamic network quality information, information of vehicles on the same route and driving events, and to generate guidance response results based on the target vehicle's response to the guidance information in the augmented reality virtual guidance interface. The upload unit is used to generate driving behavior evaluation data, network contribution data, and trip interaction data based on driving events, network quality data, and guidance response results, and then upload these data to the cloud.

[0009] According to a fourth aspect of this disclosure, a driving behavior guidance device is provided, comprising: The second receiving unit is used to receive driving routes, driving locations and network quality data uploaded by multiple vehicle terminals; The second generation unit is used to perform spatiotemporal aggregation of driving location and network quality data to generate dynamic network quality information. The determination unit is used to determine the information of vehicles on the same route based on the target vehicle's driving route, candidate vehicle routes, dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information. The sending unit is used to send dynamic network quality information and information of vehicles on the same route to the vehicle terminal corresponding to the target vehicle; and to receive driving behavior evaluation data, network contribution data and trip interaction data uploaded by the vehicle terminal. The settlement unit is used to settle accounts and allocate incentive resources based on driving behavior evaluation data, network contribution data, and trip interaction data after the trip ends.

[0010] According to a fifth aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory that is communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, such that the at least one processor is able to perform the methods described in the first or second aspect above.

[0011] According to a sixth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods of the first or second aspect described above.

[0012] According to a seventh aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method as described in the first or second aspect above.

[0013] The driving behavior guidance method, device, electronic equipment, and storage medium disclosed herein can acquire the target vehicle's driving route, driving location, and network quality data through the vehicle end and upload them to the cloud. It can also receive dynamic network quality information and information about vehicles on the same route returned from the cloud, generate and update an augmented reality virtual guidance interface based on identified driving events, and form driving behavior evaluation data, network contribution data, and trip interaction data according to the target vehicle's response to the guidance information. Therefore, it can solve the problem in existing technologies where vehicle guidance, network status perception, vehicle collaboration, and driving behavior evaluation are fragmented, making it difficult to dynamically adjust guidance content according to real-time network status, vehicle location, and driving events. This achieves the technical effects of improving the accuracy of driving behavior guidance, enhancing the interactive experience between vehicles, and forming a closed loop of driving behavior evaluation and network contribution data.

[0014] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0015] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1A flowchart illustrating a driving behavior guidance method provided in an embodiment of this disclosure; Figure 2 A flowchart illustrating another driving behavior guidance method provided in this embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of a driving behavior guidance device provided in an embodiment of the present disclosure; Figure 4 A schematic diagram of another driving behavior guidance device provided in an embodiment of this disclosure; Figure 5 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0016] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0017] The embodiments disclosed herein, at every technical stage of the data lifecycle, including but not limited to data collection, transmission, storage, computation, use, disclosure, and destruction, are fundamentally based on strict adherence to and embedding of current laws, regulations, and regulatory requirements in their system architecture, protocols, and process controls. At the design level, the solution ensures, through systematic rules and strategies, that all processing activities automatically adhere to the principles of legality, legitimacy, necessity, and good faith, and technically implements core rules such as clear purpose, minimum necessity, transparency, and security.

[0018] For any data collection, processing, or other activities involved in the embodiments of this disclosure, corresponding verification, tracking, and constraint mechanisms are implemented at the system level to ensure that their execution has a clear legal basis or contractual foundation, and to automatically trigger and record the corresponding notification process. The processing purpose of related data is bound to its specific use at the metadata layer, and is strictly limited through the system's embedded flow strategy and access control model, thereby ensuring that data is accessed and used only within the scope necessary to achieve the initial collection purpose and as determined by technical criteria. The system has a multi-layered authorization management and compliance audit mechanism to ensure that related data will not be used for any other purpose without separate legal permission or valid separate consent from the information subject. This solution natively supports and protects the information subject's various legal rights to their data in its technical implementation, and provides standardized interfaces and automated processes to achieve efficient exercise of these rights.

[0019] The driving behavior guidance method and apparatus, electronic device and storage medium of the present disclosure are described below with reference to the accompanying drawings.

[0020] Figure 1 This is a schematic flowchart of a driving behavior guidance method provided in an embodiment of the present disclosure.

[0021] like Figure 1 As shown, the method includes the following steps: Step 101: Obtain the target vehicle's driving route, driving location, and network quality data, and upload the driving route, driving location, and network quality data to the cloud.

[0022] In the embodiments of this disclosure, the vehicle terminal can be an in-vehicle terminal, an in-vehicle infotainment system, an in-vehicle communication device, a mobile terminal, or a processing device connected to the vehicle for communication. After the target vehicle initiates its journey or enters a driving behavior guidance mode, the vehicle terminal retrieves vehicle positioning information and navigation information to determine the target vehicle's current location, destination, and the route from the current location to the destination. The driving location represents the real-time spatial position of the target vehicle during its journey, and the driving route represents the road path the target vehicle is expected to traverse and its sequence of traffic. The vehicle terminal can convert the driving route into route data that can be recognized and processed by the cloud based on the connectivity between consecutive road sections in the navigation path, so that the cloud can subsequently perform segment-level analysis based on data uploaded from multiple vehicle terminals.

[0023] Simultaneously, the vehicle acquires network quality data during the target vehicle's movement. This network quality data characterizes the network connectivity status corresponding to the target vehicle's current location or road segment, and can include parameters reflecting network quality such as communication signal status, network standard, data transmission rate, latency, jitter, and packet loss. The vehicle can collect network quality data according to a preset collection strategy, such as periodic collection at preset time intervals or triggered collection when the network connectivity status changes. After obtaining the network quality data, the vehicle correlates it with its driving location and collection time, enabling the cloud to determine the network status at different road segments and times.

[0024] When generating and uploading data, the vehicle-side device can encapsulate the target vehicle's vehicle identification, driving route, driving location, collection time, and network quality data to generate vehicle network status data, which is then uploaded to the cloud via the target vehicle's currently available network connection. Upon receiving the vehicle network status data, the cloud can generate dynamic network quality information for road segments based on the driving routes, driving locations, and network quality data uploaded by multiple vehicle-side devices. This provides a data foundation for subsequent generation of augmented reality virtual guidance interfaces, determination of information about vehicles on the same route, and the formation of network contribution data.

[0025] As an example, when the target vehicle travels along the navigation route, the vehicle's terminal can continuously acquire the target vehicle's current location and simultaneously collect the network connection status corresponding to that location. When the target vehicle enters a road segment with poor network quality, the vehicle's terminal uploads the corresponding driving position and network quality data to the cloud, enabling the cloud to combine the data uploaded by other vehicle terminals to determine the network quality changes in that road segment. The above process is not limited to specific positioning methods, navigation data sources, or network parameter types; as long as the target vehicle's driving route, driving position, and network quality data can be obtained and uploaded to the cloud, it is applicable to this embodiment.

[0026] Step 102: Receive dynamic network quality information and information on vehicles on the same route returned from the cloud.

[0027] In the embodiments of this disclosure, after receiving driving routes, driving locations, and network quality data uploaded by multiple vehicle terminals, the cloud can aggregate and analyze the network quality data corresponding to different vehicles on different road segments and at different times to generate dynamic network quality information. Dynamic network quality information is used to characterize the network status of each road segment in the target vehicle's current or expected driving route. It may include the road segment network quality level, the road segment network quality change trend, prompts for road segments with poor network quality, and network status prompts associated with the vehicle's current driving location. After receiving the dynamic network quality information, the vehicle terminal can match it with the locally maintained driving routes and driving locations to determine the network status of the road segment where the target vehicle is currently located, the road segment ahead, or the road segment the target vehicle is expected to pass through.

[0028] Simultaneously, the cloud can determine vehicles on the same route as the target vehicle based on the target vehicle's driving route, candidate vehicle routes, dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information, and return this information to the vehicle. This information characterizes other vehicles that can interact with the target vehicle, and may include route matching relationships, relative positions, driving progress, vehicle status, and status data used to generate interactive content. Upon receiving this information, the vehicle can use it as the data basis for generating the augmented reality virtual guidance interface, enabling the interface to reflect not only the target vehicle's own driving status but also its interaction with other vehicles on the same route.

[0029] In one possible implementation, the vehicle can periodically receive dynamic network quality information and information about vehicles on the same route returned from the cloud. It can also receive updated data from the cloud when the target vehicle's route changes, its location enters a new road segment, network quality changes meet update conditions, or the number of vehicles on the same route changes. Upon receiving the updated data, the vehicle can refresh the locally stored dynamic network quality information and information about vehicles on the same route, so that the augmented reality virtual guidance interface can be generated or updated based on the latest dynamic network quality information and information about vehicles on the same route.

[0030] As an example, when a target vehicle is about to enter a road segment with poor network quality, the vehicle's terminal can receive dynamic network quality information for that road segment from the cloud, and simultaneously receive information about vehicles traveling on the same route that partially overlap with the target vehicle. Based on this, the vehicle's terminal can generate guidance information related to network status and vehicle interaction in subsequent processing, ensuring that the target vehicle's driving guidance content remains consistent with the current driving environment, network status, and the status of vehicles traveling on the same route.

[0031] Step 103: Identify driving events of the target vehicle.

[0032] In the embodiments of this disclosure, the vehicle can acquire environmental perception data of the target vehicle during its driving process through onboard cameras, onboard sensors, driving recorders, or sensing devices connected to the vehicle. The vehicle's processor then analyzes this environmental perception data to determine driving events occurring in the current road scenario. These driving events characterize the behavioral state of the target vehicle during its driving process, interacting with the road environment, traffic objects, or traffic rules. They can serve as the data foundation for subsequently generating augmented reality virtual guidance interfaces and forming driving behavior evaluation data.

[0033] During the recognition process, the vehicle can first identify target objects and road elements related to driving behavior from environmental perception data, such as vehicles, pedestrians, traffic signs, lane lines, intersection areas, zebra crossing areas, and other objects or areas that can reflect the road traffic status. Subsequently, the vehicle analyzes the current driving scenario by combining the target object's position changes, direction of movement, relative distance, and the target vehicle's own driving status over continuous time, thereby determining whether the target vehicle has experienced an event related to driving guidance. This judgment process can be based on image recognition, trajectory analysis, temporal behavior analysis, or multi-source perception data fusion, and is not limited to a specific algorithm.

[0034] In one possible implementation, the vehicle-side can identify whether a target vehicle exhibits driving behaviors such as following traffic rules, yielding to pedestrians, alternating lanes, illegally changing lanes, running red lights, failing to slow down, or cutting in line, based on the relative relationships between the target vehicle and pedestrians, vehicles, and traffic signs. After identifying the corresponding behavior, the vehicle-side can generate a corresponding driving event and associate the driving event with the time, location, event type, and relevant road scene. This allows subsequent steps to determine the guidance information in the augmented reality virtual guidance interface based on the driving event, and further generate driving behavior evaluation data for assessing the target vehicle's driving behavior.

[0035] As an example, when the vehicle identifies a pedestrian crossing area ahead of it using forward view data, and further determines, based on the vehicle's speed, deceleration status, and relative position to the pedestrian, that the vehicle has performed an avoidance or yielding maneuver appropriate to the road scenario, the vehicle can identify this behavior as a driving event related to civilized driving. Similarly, when the vehicle determines, based on lane area, traffic signal status, and changes in the vehicle's trajectory, that the vehicle is engaging in driving behavior that violates road traffic rules, it can generate a driving event related to abnormal driving. The above examples are only used to illustrate the logic of driving event recognition and do not constitute a limitation on the types or methods of driving event recognition.

[0036] Step 104: Based on driving location, dynamic network quality information, information of vehicles on the same route, and driving events, generate and update the augmented reality virtual guidance interface, and generate guidance response results based on the target vehicle's response to the guidance information in the augmented reality virtual guidance interface.

[0037] In the embodiments of this disclosure, the vehicle can use its driving location as the basis for determining the current display scene and the location of the guided object, dynamic network quality information as the basis for determining network status-related guidance content, information on vehicles on the same route as the basis for determining vehicle collaboration or interaction status, and driving events as the basis for determining driving task or driving behavior prompts. The vehicle's processor can fuse the above data to determine the guidance information to be displayed in the current driving scene, and update the display position, content, or status of the guidance information in the augmented reality virtual guidance interface according to changes in the target vehicle's driving location.

[0038] When generating an augmented reality virtual guidance interface, the vehicle-side device can determine the corresponding road scene based on the target vehicle's current driving position and spatially associate the guidance information with that road scene, allowing the guidance information to be overlaid on the vehicle's forward field of vision in an augmented reality manner. For example, the vehicle-side device can generate network status-related prompts when the target vehicle is about to enter a road segment with poor network quality based on dynamic network quality information; it can generate prompts indicating the relative position, driving progress, or interaction status of vehicles on the same route based on information about other vehicles; and it can generate prompts related to the current driving behavior based on driving events. All of these prompts can collectively constitute the guidance information in the augmented reality virtual guidance interface.

[0039] During vehicle operation, the vehicle continuously acquires or updates its location and matches the updated location with the generated guidance information. When the target vehicle approaches, arrives at, or passes through the spatial area corresponding to the guidance information, the vehicle can determine whether the target vehicle has responded to the guidance information by combining driving events and dynamic network quality information. For example, in practical applications, when the augmented reality virtual guidance interface displays guidance information related to civilized driving, the vehicle can determine whether the target vehicle has performed the corresponding driving behavior based on subsequently identified driving events; when the augmented reality virtual guidance interface displays guidance information related to network status, the vehicle can determine the response status of the guidance information based on changes in network quality as the target vehicle passes through the corresponding road segment.

[0040] The vehicle-side system can record and correlate the target vehicle's responses to different guidance information, generating guidance response results. These results characterize the target vehicle's actual response to guidance information in the augmented reality virtual guidance interface during driving, serving as the data foundation for subsequent generation of driving behavior evaluation data, network contribution data, and trip interaction data. The above process does not limit the specific display format of the augmented reality virtual guidance interface; any interface that can be generated and updated based on driving location, dynamic network quality information, information about vehicles on the same route, and driving events, and whose guidance response results are obtained based on the responses, is applicable to this embodiment.

[0041] Step 105: Based on driving events, network quality data, and guidance response results, driving behavior evaluation data, network contribution data, and trip interaction data are generated respectively, and then uploaded to the cloud.

[0042] In the embodiments of this disclosure, after obtaining a driving event, the vehicle can perform structured processing on the driving event to form driving behavior evaluation data. The driving behavior evaluation data characterizes the driving behavior status of the target vehicle during the current trip, and may include the event type, occurrence time, occurrence location, event duration, and corresponding evaluation identifier. The vehicle can convert the driving behavior attributes reflected by the driving event into a data format that can be settled, statistically analyzed, or processed by the cloud, enabling the cloud to determine the target vehicle's driving behavior performance during the current trip based on the driving behavior evaluation data.

[0043] The vehicle-side can also generate network contribution data based on network quality data. Network contribution data characterizes the data contribution of a target vehicle to the network state detection of a road segment during its journey. It can be obtained by associating network quality data with the corresponding driving location, collection time, and driving route. Therefore, network contribution data not only reflects the network state collected by the target vehicle on different road segments, but also enables the cloud to identify the spatial location and temporal range corresponding to that network state, thus providing a data foundation for subsequent road segment network quality analysis, network quality reward calculation, and network state statistics.

[0044] Furthermore, the vehicle can generate trip interaction data based on the guidance response results. Trip interaction data characterizes the target vehicle's response process to guidance information in the augmented reality virtual guidance interface during the trip. Specifically, the vehicle can correlate the guidance response results with content related to guidance information triggering, driving task completion, network status response, and interaction with other vehicles on the same route to obtain data reflecting the target vehicle's trip interaction performance. Trip interaction data can be distinguished from driving behavior evaluation data and network contribution data: driving behavior evaluation data focuses on reflecting driving behavior itself, network contribution data focuses on reflecting network detection contribution, and trip interaction data focuses on reflecting the target vehicle's response and interaction process to guidance information.

[0045] After generating the aforementioned data, the vehicle can encapsulate driving behavior evaluation data, network contribution data, and trip interaction data according to a preset data format and upload them to the cloud via the vehicle's currently available communication connection. Upon receiving this data, the cloud can perform comprehensive processing at the end of the trip to obtain the settlement result corresponding to the target vehicle. As an example, in a real-world application scenario, the vehicle can process a driving event corresponding to yielding to a pedestrian as driving behavior evaluation data, process the network status collected while passing through a road segment as network contribution data, and process the target vehicle's triggering and completion of corresponding guidance information as trip interaction data. This allows the cloud to settle the trip from three dimensions: driving behavior, network contribution, and trip interaction.

[0046] The driving behavior guidance method disclosed herein can acquire the target vehicle's driving route, driving location, and network quality data through the vehicle end and upload them to the cloud. It receives dynamic network quality information and information of vehicles on the same route returned from the cloud, and generates and updates the augmented reality virtual guidance interface by combining the identified driving events. Based on the target vehicle's response to the guidance information, it forms driving behavior evaluation data, network contribution data, and trip interaction data. Therefore, it can solve the problem in the prior art where the guidance, network status perception, vehicle collaboration, and driving behavior evaluation are disconnected, making it difficult to dynamically adjust the guidance content according to the real-time network status, vehicle location, and driving events. It achieves the technical effect of improving the accuracy of driving behavior guidance, enhancing the interaction experience between vehicles, and forming a closed loop of driving behavior evaluation and network contribution data.

[0047] In the embodiments involved in this application, there are various feasible specific implementation methods. To clearly and completely illustrate the technical solutions of this disclosure, the implementation methods listed below are merely exemplary and do not constitute a limitation on the scope of protection of this disclosure. That is, in addition to the following implementation methods, other implementation methods that can be obtained by those skilled in the art based on the technical content disclosed in this disclosure through reasonable logical analysis, reasoning, or limited experimentation should also be covered within the scope of protection of this disclosure. The following specifically describes some exemplary implementation methods: As a specific implementation of this disclosure, based on the basic solution, the driving route, driving location, and network quality data of the target vehicle are obtained, and the driving route, driving location, and network quality data are uploaded to the cloud. Further, the method is defined as follows: the current location, destination, and multiple road segments arranged in traffic order of the target vehicle are determined through vehicle positioning information and navigation information to obtain the driving route; the signal strength, network standard, uplink and downlink speeds, latency, jitter, and packet loss rate of the target vehicle on each road segment are collected through in-vehicle communication equipment or mobile terminals to obtain network quality data; the vehicle identifier, collection time, driving location, driving route, and network quality data are encapsulated into vehicle network status data, and the vehicle network status data is uploaded to the cloud.

[0048] Specifically, the vehicle can obtain the real-time coordinates of the target vehicle through its onboard GPS, or it can obtain the target vehicle's coordinates, destination, and navigation-planned route through map software program interfaces. The vehicle can also collect network quality data through onboard diagnostic interfaces or mobile terminal applications calling system interfaces. Specifically, the vehicle can perform network status collection every 5 seconds, or trigger a network status collection when network changes exceed a preset threshold. Network quality data can include signal strength, network type, and performance indicators. Signal strength can include Reference Signal Received Power (RSRP) and Received Signal Strength Indicator (RSSI). Network type can include 4G, 5G, or Wi-Fi. Performance indicators can include uplink rate, downlink rate, latency, jitter, and packet loss rate. The vehicle network status data generated by the vehicle can adopt the following field structure: {Vehicle ID, Timestamp, GPS Coordinates, Route, Network Parameters}. The Vehicle ID is used to distinguish different vehicles, the Timestamp is used to identify the collection time, the GPS coordinates are used to determine the collection location, the route is used to determine the sequence of road segments the target vehicle is expected to traverse, and the network parameters characterize the network status corresponding to the collection location. The vehicle can upload the aforementioned vehicle network status data to the cloud using its existing network connection, enabling the cloud to aggregate data from multiple vehicles according to road segments and time windows. Besides the above method, other location data sources, navigation data sources, or network status acquisition interfaces can also be used. Any method that can generate network quality data associated with the driving route and location and upload it to the cloud is a viable alternative implementation of this embodiment.

[0049] As a specific implementation of this disclosure, based on the basic solution, the identification of driving events of the target vehicle is further defined as follows: acquiring an in-vehicle video stream of the target vehicle's forward field of view area, and performing traffic object identification on the image frames in the in-vehicle video stream to obtain identification results of vehicles, pedestrians, traffic signs, and road areas; performing temporal behavior identification on vehicle behavior, pedestrian behavior, and traffic sign status based on the identification results to obtain behavior identification results of the target traffic objects; tracking the motion trajectory of the target traffic objects in continuous image frames, and associating the motion trajectory with the road area and traffic sign status to obtain traffic object trajectory association results; classifying the driving events of the target vehicle according to the behavior identification results and traffic object trajectory association results to obtain driving events including regular driving events, reward driving events, and penalty driving events.

[0050] Specifically, the vehicle-side can use object detection models to detect vehicles, pedestrians, and traffic signs in the in-vehicle video stream, action recognition models to identify the temporal behavior of vehicles and pedestrians, optical flow or multi-object tracking models to continuously track the motion trajectories of vehicles and pedestrians, and semantic segmentation models to distinguish road areas, pedestrian crossing areas, lane areas, and background areas in the image frames. Based on this, the vehicle-side can input the object detection results, temporal behavior recognition results, motion trajectories, and road area segmentation results into the behavior evaluation model or preset event judgment rules: if the target vehicle completes a turn, stop, or follow another vehicle when traffic signs permit passage and the driving trajectory conforms to road area constraints, the corresponding event is determined as a regular driving event; if the target vehicle slows down or stops before a pedestrian crossing area and allows pedestrians to cross the corresponding road area, the corresponding event is determined as a reward driving event; if the target vehicle crosses a stop area while prohibited from passing, crosses a lane area without meeting lane change conditions, or fails to form a deceleration trajectory in an area where deceleration is required, the corresponding event is determined as a penalty driving event. In addition to the model combinations mentioned above, other image recognition models, trajectory tracking algorithms, or rule engines can also be used to achieve the same event recognition function. For example, the terminal can use the YOLO object detection model to detect vehicles, pedestrians, and traffic signs in the vehicle video stream, obtaining the category, bounding box coordinates, and confidence score of each object; use the U-Net semantic segmentation model to segment image frames into regions, obtaining road regions, lane regions, pedestrian crossing regions, and background regions; use optical flow or Deep SORT object tracking algorithms to track the trajectories of vehicles and pedestrians in continuous image frames, obtaining the positional changes of target objects over time; and use the LSTM action recognition model to identify continuous behaviors of vehicles and pedestrians, such as identifying whether the target vehicle has run red lights, changed lanes, stopped, failed to slow down, or frequently changed lanes. Furthermore, the vehicle terminal can also use LSTM combined with time series data to perform overall analysis of multiple consecutive driving behaviors to determine whether the target vehicle has repeatedly run red lights or frequently changed lanes, among other abnormal behaviors. For traffic rule compliance evaluation, the vehicle can use the Deep Q-Networks reinforcement learning model to evaluate the behavior recognition results and the traffic object trajectory association results. When the model output indicates that the target vehicle's behavior does not comply with traffic rules, the vehicle will identify the corresponding event as a penalty driving event; when the model output indicates that the target vehicle drives normally according to traffic signs, the vehicle will identify the corresponding event as a normal driving event; when the model output indicates that the target vehicle completes civilized driving behaviors such as yielding to pedestrians or alternating traffic, the vehicle will identify the corresponding event as a reward driving event.

[0051] As a specific implementation of this disclosure, based on the basic solution, an augmented reality virtual guidance interface is generated and updated based on the driving location, dynamic network quality information, information of vehicles on the same route, and driving events. A guidance response result is generated based on the target vehicle's response to the guidance information in the augmented reality virtual guidance interface. This is further defined as follows: generating route display information corresponding to the vehicle's forward field of vision based on the target vehicle's driving route and driving location; generating network status guidance information based on dynamic network quality information; generating vehicle interaction guidance information based on information of vehicles on the same route; and generating driving task guidance information based on driving events. The route display information, network status guidance information, vehicle interaction guidance information, and driving task guidance information are combined into an augmented reality virtual guidance interface. A guidance response result is generated based on the target vehicle's response to the network status guidance information, vehicle interaction guidance information, and driving task guidance information.

[0052] Specifically, when dynamic network quality information indicates poor network quality on the road ahead, the vehicle terminal can generate a network status prompt at the corresponding display location. When vehicle information on the same route indicates the presence of vehicles on the same route matching the target vehicle, the vehicle terminal can display the relative position or travel progress of these vehicles on the interface. When driving events indicate the presence of pedestrian crossings, alternating crossings, or abnormal driving risks ahead, the vehicle terminal can generate corresponding driving task prompts. The vehicle terminal continuously updates its driving position during the target vehicle's journey and determines whether the target vehicle has reached the trigger area corresponding to each guidance information. If the target vehicle reaches the trigger area, based on subsequently identified driving events, network status changes, and the status of vehicles on the same route, the vehicle terminal determines its response to network status guidance information, vehicle interaction guidance information, and driving task guidance information, and generates a guidance response result. In addition to the above display and judgment methods, other coordinate mapping, interface rendering, or response judgment methods can also be used to achieve the same data fusion and guidance response recording.

[0053] As a specific implementation of this disclosure, based on the basic solution, the generation of driving task guidance information based on driving events is further defined as follows: The total route score is determined according to the target vehicle's driving route; and the interval positions of regular scoring guidance elements on the driving route are determined based on the total route distance, the total route score, and the score of a single regular scoring guidance element; regular scoring guidance elements are allocated to corresponding road segments according to the length of each segment, and the positions of the regular scoring guidance elements are made consistent with the driving route to obtain regular driving guidance information; when the driving event includes a reward driving event, reward driving guidance information is generated at the scene location corresponding to the reward driving event, and the reward driving guidance information is associated with the driving task prompt information; when the driving event includes a penalty driving event, penalty driving guidance information is generated at the risk location corresponding to the penalty driving event, and the penalty driving guidance information is associated with the deduction rules.

[0054] Specifically, the interval position of regular scoring guidance elements can be determined according to the following formula: Item Interval Distance = Total Distance / (Total Score / Scoring Item Value). "Total Distance" corresponds to the length of the target vehicle's driving route, "Total Score" corresponds to the preset total score for the driving route, and "Scoring Item Value" corresponds to the score of a single regular scoring guidance element. The vehicle generates regular scoring guidance elements along the driving route based on the item interval distance and distributes them to each segment according to the segment length. For reward driving guidance information, its score can be determined according to the following formula: Item Score = Fixed Score + Fixed Score The location adjustment coefficient is calculated as follows: Adjustment coefficient = Frequency of non-compliance for this event at this location / National average number of non-compliances for this event. Therefore, when the frequency of non-compliance for a driving event is high at a particular location, the reward driving guidance information corresponding to that location will receive a higher score weight. For penalty driving guidance information, its deduction value can be set as a negative multiple of the corresponding reward driving guidance information score. For example, the score for each penalty driving guidance information can be -m times the reward driving guidance information score, where m is a preset deduction coefficient. In addition to the above formula, the corresponding scores can also be adjusted equally according to road level, event type, or driving scenario.

[0055] As a specific implementation of this disclosure, based on the basic scheme, network status guidance information is generated based on dynamic network quality information, further defined as follows: The target vehicle's current travel segment is determined based on the dynamic network quality information to determine whether the network quality is lower than a preset quality condition; when the target vehicle passes through a segment with network quality lower than the preset quality condition, the travel time, current network speed, historical baseline speed, and network quality difference of the target vehicle in that segment are recorded to obtain network experience loss data; network quality reward prompt information is generated based on the network experience loss data, including at least one of traffic compensation prompt information, points reward prompt information, and package discount contribution prompt information; the network quality reward prompt information is overlaid and displayed as part of the network status guidance information on the augmented reality virtual guidance interface.

[0056] Specifically, the preset quality condition can be set to a network quality score below 2.5. When a target vehicle passes through this road segment, the vehicle terminal calculates traffic compensation information according to the following formula: Compensation Traffic = Travel Time × (Base Network Speed ​​- Current Network Speed) × Compensation Coefficient; where travel time is the number of seconds the target vehicle travels through this road segment, the base network speed is the historical average network speed of this road segment, the current network speed is the network speed collected by the target vehicle in this road segment, and the compensation coefficient is used to characterize the degree of network quality degradation. The compensation coefficient can be determined according to the following formula: Compensation Coefficient = |Average Score - Current Score| × 0.1. Where the average score is the historical average network quality score of this road segment, and the current score is the network quality score currently collected by the target vehicle. Further, the points reward information can be determined according to the following formula: Points Reward = Fixed Base Score × Network Quality Deterioration Degree, where the network quality deterioration degree = 1 / network quality score. For package discount contribution prompts, the vehicle terminal can generate contribution prompts based on the target vehicle's network quality data upload volume, and prompt that package discounts can be obtained when the cumulative contribution volume reaches the preset contribution threshold. In addition to the above calculation methods, segmented mapping, level mapping, or table lookup methods can also be used to generate network quality reward notification information.

[0057] On the vehicle side, traffic compensation prompts, points reward prompts, or package discount contribution prompts are displayed as part of the network status guidance information, overlaid on the augmented reality virtual guidance interface, so that the target vehicle can receive guidance prompts corresponding to the current network experience loss when traveling through road sections with poor network quality.

[0058] As a specific implementation of this disclosure, based on the basic scheme, driving behavior evaluation data, network contribution data, and trip interaction data are generated based on driving events, network quality data, and guidance response results, respectively. This is further defined as follows: driving behavior evaluation data is generated to characterize the target vehicle's driving behavior based on regular driving events, reward driving events, and penalty driving events within the driving events; network contribution data is generated to characterize the target vehicle's network detection contribution based on network quality data, network experience loss data, and network quality data upload status; and trip interaction data is generated to characterize the target vehicle's trip interaction performance based on guidance information triggering results, task completion results, network interaction results, and vehicle interaction results within the guidance response results.

[0059] Specifically, the vehicle-side also generates trip interaction data characterizing the target vehicle's trip interaction performance based on the guidance information triggering results, task completion results, network interaction results, and vehicle interaction results in the guidance response results. Guidance information triggering results indicate whether the target vehicle has reached the trigger area of ​​the corresponding guidance information in the augmented reality virtual guidance interface; task completion results indicate whether the target vehicle has completed the driving behavior corresponding to the driving task guidance information; network interaction results indicate the target vehicle's response status within the road segment corresponding to the network status guidance information; and vehicle interaction results indicate the relative driving progress or interaction status between the target vehicle and other vehicles on the same route. The vehicle-side can encapsulate these results according to trip identifiers, time sequences, and road segment identifiers to form trip interaction data that can be uploaded to the cloud and used for subsequent settlement. In addition to the above data structures, event tables, log sequences, or key-value mapping tables can also be used to organize driving behavior evaluation data, network contribution data, and trip interaction data.

[0060] Figure 2 This is a schematic flowchart of another driving behavior guidance method provided in an embodiment of this disclosure.

[0061] like Figure 2 As shown, the method includes the following steps: Step 201: Receive driving routes, driving locations, and network quality data uploaded by multiple vehicle terminals.

[0062] In the embodiments disclosed herein, this embodiment can be applied to a cloud server, an edge computing server, or a cloud processing platform composed of multiple servers. The cloud can establish data connections with multiple vehicle terminals through communication interfaces and receive data uploaded by each vehicle terminal during its journey. The vehicle terminal can associate the driving route, driving location, and network quality data of the target vehicle or other vehicles and upload them to the cloud, enabling the cloud to obtain network status information corresponding to different vehicles at different spatial locations and different stages of travel.

[0063] The driving route represents the road path a vehicle takes from its current location to its destination. It can include road segments, road nodes, or path markers arranged in order of travel. The driving location represents the spatial location of the vehicle when uploading data. It can include vehicle coordinates, the current road segment, or the location of the road segment matched with a road map. Network quality data represents the network connectivity status collected by the vehicle at the corresponding driving location. After receiving the above data, the cloud can perform integrity verification and associated storage. For example, it can verify whether the vehicle identifier, collection time, driving location, and network quality data can form a valid correspondence, and group data belonging to the same vehicle, the same road segment, or the same time window into the corresponding data set.

[0064] In one possible implementation, the cloud can create a vehicle trip record for the data uploaded by each vehicle, and store the mapping relationship between the driving route, driving location, and network quality data in the vehicle trip record. Thus, the cloud can not only identify network status changes of an individual vehicle during its journey, but also aggregate data uploaded by multiple vehicles according to road segment, time, and vehicle dimensions in subsequent steps, providing basic data for generating dynamic network quality information and identifying vehicles on the same route.

[0065] As an example, when multiple vehicles pass through the same road segment, each vehicle can upload its corresponding driving location and network quality data at different times. After receiving this data, the cloud can determine the road segment it belongs to based on its driving location and the time range it belongs to based on the collection time. This allows the data uploaded by different vehicles to be aggregated into a data set of the same or adjacent road segments for subsequent spatiotemporal aggregation processing.

[0066] Step 202: Perform spatiotemporal aggregation of driving location and network quality data to generate dynamic network quality information.

[0067] In the embodiments of this disclosure, after receiving driving location and network quality data uploaded by multiple vehicle terminals, the cloud can first perform road matching processing on the driving locations to determine the road segment locations corresponding to each set of network quality data. Road matching processing can be implemented based on map data, road segment boundaries, road nodes, or road segment identifiers, used to convert the spatial coordinates uploaded by different vehicle terminals into a unified road segment dimension. Therefore, even if the data uploaded by different vehicle terminals comes from different sources and is collected at different times, the cloud can still group them into the same or adjacent road spatial units, forming a road segment-oriented network quality data set.

[0068] Furthermore, the cloud can divide network quality data into time windows based on the collection time. Specifically, the cloud can group network quality data within the same road segment, within the same or adjacent time ranges, into the same time window, and aggregate the network quality data of multiple vehicles within that time window. Aggregation processing may include outlier filtering, duplicate data merging, missing data marking, and statistical calculations to reduce the impact of single-vehicle acquisition errors on the road segment network status assessment results. Through road segment merging in the spatial dimension and window division in the temporal dimension, the cloud can form a foundation for network status analysis with spatiotemporal attributes.

[0069] When generating dynamic network quality information, the cloud can determine the network status of each road segment within the corresponding time window based on the aggregated network quality data. Dynamic network quality information can characterize the network quality of different road segments over time, and may include road segment network quality scores, network quality levels, network status change trends, warning information for road segments with poor network quality, or network status data displayed on the vehicle's interface. The cloud can continuously update dynamic network quality information based on new data uploaded by vehicles, enabling the information to reflect changes in road segment network quality caused by vehicle movement, time variations, or network load changes.

[0070] In one possible implementation, the cloud can match dynamic network quality information with the target vehicle's travel route to determine the network status of the target vehicle's current road segment, the road segments it is about to pass through, and the corresponding road segments in its subsequent travel route. As an example, when network quality data uploaded by multiple vehicles on the same road segment all indicate high latency, low transmission rate, or high packet loss, the cloud can mark that road segment as having poor network quality and include a network status indicator for that road segment in the generated dynamic network quality information. Subsequently, the cloud can send the dynamic network quality information to the target vehicle's corresponding vehicle terminal, enabling the vehicle terminal to generate guidance information related to the network status based on the dynamic network quality information.

[0071] Step 203: Based on the target vehicle's driving route, candidate vehicle routes, dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information, determine the information of vehicles on the same route.

[0072] In the embodiments of this disclosure, the cloud can first identify candidate vehicles that are in the same or similar driving areas as the target vehicle from data uploaded by multiple vehicle terminals, and obtain the target vehicle's driving route and the corresponding candidate vehicle routes. Both the driving route and the candidate vehicle routes can be represented as a sequence of road segments arranged in the order of passage. The cloud can perform road segmentation processing on the target vehicle's driving route to obtain multiple target road segments that the target vehicle is expected to pass through, and compare the target road segments with the candidate vehicle routes to determine whether the candidate vehicles have a route matching relationship with the target vehicle in terms of road segments, number of road segments, and road segment order. In this way, the cloud can filter out vehicles with a common travel path from a large number of vehicles, avoiding the identification of vehicles that are only spatially close but have different driving directions or paths as vehicles on the same route.

[0073] Furthermore, the cloud can determine the network quality status of the target vehicle and candidate vehicles on the shared road segment based on dynamic network quality information, and calculate the network quality similarity between the target vehicle and candidate vehicles accordingly. Network quality similarity is used to characterize the degree of consistency of the network environment in which the two vehicles are located on the shared road segment. If the network status of the two vehicles on the shared road segment differs significantly, it may lead to inconsistent interaction rhythms in subsequent vehicle interactions or augmented reality virtual guidance processes; therefore, the cloud can use dynamic network quality information as one of the important inputs for determining information about vehicles on the same route.

[0074] The cloud can also determine the behavior matching of candidate vehicles based on their driving behavior data. This data can include safe driving evaluations, abnormal driving records, and driving event statistics from historical or current trips, reflecting the candidate vehicle's driving behavior status. Based on this data, the cloud can avoid matching vehicles with significantly different driving behaviors into the same guided interaction process. Simultaneously, the cloud can determine the spatial and temporal matching between the target vehicle and candidate vehicles based on dynamic location information. This information can include the vehicle's current location, speed, estimated arrival time, and distance from the start or end point of a shared road segment. Based on this location information, the cloud can determine whether candidate vehicles can maintain an interactive driving relationship with the target vehicle within the same route range.

[0075] In one possible implementation, the cloud can generate multiple matching indicators based on route matching relationships, network quality similarity, candidate vehicle driving behavior data, and location dynamic information. These indicators are then comprehensively processed to obtain the matching degree between the candidate vehicle and the target vehicle. If the matching degree of a candidate vehicle meets preset matching conditions, the cloud can identify that candidate vehicle as a vehicle on the same route as the target vehicle and generate information about vehicles on the same route. This information may include the vehicle identifier, the relative position of the vehicles on the same route, their travel progress, route overlap, matching degree, and status data used by the vehicle to generate interactive guidance information.

[0076] As an example, if the target vehicle's route includes multiple consecutive target road segments, and a candidate vehicle's route covers multiple target road segments in the same traffic order, and the candidate vehicle's network quality status on the shared road segments is similar to the target vehicle's, its historical driving behavior data meets the matching criteria, and its estimated arrival time is similar to the target vehicle's, then the cloud can identify the candidate vehicle as a vehicle on the same route. If, during the journey, the target vehicle or a vehicle on the same route deviates from its route, its speed difference increases, or its network quality status changes, the cloud can re-execute the matching process to update the information on vehicles on the same route.

[0077] Step 204: Send dynamic network quality information and information about vehicles on the same route to the vehicle terminal corresponding to the target vehicle.

[0078] In the embodiments of this disclosure, after generating dynamic network quality information and determining information about vehicles traveling on the same route, the cloud can determine the vehicle terminal corresponding to the target vehicle based on the target vehicle's vehicle identifier, communication connection identifier, or trip identifier, and send data related to the current trip to that vehicle terminal. The dynamic network quality information may include the network quality status of road segments related to the target vehicle's current travel route, network quality change information, or prompts for road segments with poor network quality; the information about vehicles traveling on the same route may include the vehicle identifier, relative position, travel progress, route overlap relationship, and status data used to generate vehicle interaction guidance information. The cloud can filter the dynamic network quality information and the information about vehicles traveling on the same route based on the target vehicle's travel location and route, ensuring that the data sent to the vehicle terminal is relevant to the target vehicle's current trip.

[0079] During data transmission, the cloud can synchronize data using periodic delivery, event-triggered delivery, or a combination of both. For example, when a target vehicle enters a new road segment, dynamic network quality information is updated, information about vehicles on the same route changes, or a vehicle deviates from its route, the cloud can send updated dynamic network quality information and information about vehicles on the same route to the vehicle. After receiving this information, the vehicle can associate it with its local location, driving events, and augmented reality virtual guidance interface to generate or update network status guidance information and vehicle interaction guidance information.

[0080] As an example, when the cloud determines that the network quality of the road segment ahead of the target vehicle is lower than a preset quality condition, and has already matched the target vehicle with other vehicles on the same route, the cloud can send the network quality status of that road segment ahead, as well as the relative positions and travel progress of other vehicles on the same route, to the vehicle. After receiving the above data, the vehicle can display guidance information related to the network status and other vehicles on the same route in the augmented reality virtual guidance interface. The above sending method is not limited to a specific communication protocol or data format; as long as it enables the vehicle to obtain dynamic network quality information and information about other vehicles on the same route, it can be applied to this embodiment.

[0081] Step 205: Receive driving behavior evaluation data, network contribution data, and trip interaction data uploaded by the vehicle.

[0082] In the embodiments of this disclosure, during or after a trip, the vehicle can upload driving behavior evaluation data, network contribution data, and trip interaction data, formed based on local identification, collection, and interaction records, to the cloud. Upon receiving this data, the cloud can aggregate and associate the driving behavior evaluation data, network contribution data, and trip interaction data according to vehicle identifier, trip identifier, collection time, or road segment identifier, enabling the three types of data to correspond to the same trip of the same target vehicle.

[0083] Driving behavior evaluation data characterizes the driving behavior of the target vehicle during its journey, and can originate from the vehicle's identification results of driving events. The cloud can use this data to determine the target vehicle's driving behavior in different road sections or scenarios, such as compliant, rewarding, or punishing driving behaviors. Network contribution data characterizes the data contribution of the target vehicle to network status detection during its journey. This can include network quality data associated with the driving location, collection time, and driving route, as well as network experience loss information based on changes in network quality. The cloud can use this data to determine which road sections, time windows, and network states are covered by the network detection data provided by the target vehicle.

[0084] Trip interaction data is used to characterize the interaction process of the target vehicle in the augmented reality virtual guidance interface, and it can originate from the guidance response results generated by the vehicle itself. The cloud can use trip interaction data to determine whether the target vehicle triggered the corresponding guidance information, completed the corresponding driving task, passed through the road segment corresponding to the network status guidance information, and formed an effective interaction relationship with vehicles on the same route. Therefore, trip interaction data can serve as the data basis for subsequently determining the trip interaction score.

[0085] In one possible implementation, after receiving driving behavior evaluation data, network contribution data, and trip interaction data, the cloud can first perform data verification. For example, the cloud can determine whether the three types of data contain the same vehicle identifier and the same trip identifier, whether the data time range falls within the target vehicle's trip time, and whether the road segment information in the network contribution data matches the driving route. If the data verification passes, the cloud writes the driving behavior evaluation data, network contribution data, and trip interaction data into the corresponding trip settlement data set; if the data is missing or abnormal, the cloud can mark the missing fields or request the vehicle to re-upload the corresponding data.

[0086] As an example, the vehicle can upload a data packet at the end of the trip containing pedestrian yielding events, records of poor network quality sections, and corresponding guidance information triggering information. Upon receiving this data packet, the cloud categorizes the pedestrian yielding events into driving behavior evaluation data, the poor network quality section records into network contribution data, and the guidance information triggering information into trip interaction data, linking all three to the same trip record for later use in the settlement process.

[0087] Step 206: After the trip ends, settlement and incentive resources are allocated based on driving behavior evaluation data, network contribution data, and trip interaction data.

[0088] In the embodiments of this disclosure, the cloud can determine whether the current trip has ended based on the trip status of the target vehicle. Trip end can be triggered by arrival information uploaded by the vehicle, or it can be determined by the cloud based on the location relationship between the target vehicle's driving position and the destination, the end status of the trip marker, or the completion status of the navigation route. After confirming the trip's end, the cloud reads the driving behavior evaluation data, network contribution data, and trip interaction data corresponding to the target vehicle's current trip, and performs correlation verification on the above data to ensure that the data involved in the settlement belongs to the same target vehicle, the same trip, and the corresponding time range.

[0089] The cloud platform can determine settlement items for driving behavior dimensions based on driving behavior evaluation data. This data reflects driving events and their evaluation attributes that occurred during the trip. The cloud platform generates corresponding driving behavior settlement results based on regular, rewarding, and punitive driving behaviors. These settlement results characterize the target vehicle's driving compliance and task completion during the trip.

[0090] The cloud platform can also determine settlement items for the network contribution dimension based on network contribution data. Network contribution data reflects the road segment coverage, temporal coverage, and corresponding network status changes of the target vehicle uploading network quality data during its journey. Based on this data, the cloud platform can determine the target vehicle's data contribution to network status detection during this trip and generate a network contribution settlement result. This result can be used to determine incentive resources related to network status detection.

[0091] Meanwhile, the cloud can determine the settlement items for the trip interaction dimensions based on the trip interaction data. Trip interaction data can reflect the target vehicle's triggering, response, and completion of guidance information in the augmented reality virtual guidance interface, as well as the interaction status between the target vehicle and other vehicles on the same route. The cloud generates trip interaction settlement results based on the trip interaction data to characterize the target vehicle's interactive participation in this trip.

[0092] After obtaining the driving behavior settlement result, network contribution settlement result, and trip interaction settlement result, the cloud can integrate these three according to preset settlement rules to obtain a unified settlement result. The unified settlement result may include the total score, reward level, network contribution, type of allocable incentive resources, and quantity of incentive resources for this trip. Subsequently, the cloud allocates incentive resources to the target vehicle's corresponding account based on the unified settlement result. Incentive resources may include at least one of points, data compensation, and package discounts. As an example, when the target vehicle generates rewarding driving behavior, uploads valid network quality data, and completes the corresponding guidance tasks in the augmented reality virtual guidance interface during this trip, the cloud can generate a unified settlement result based on the above data and allocate points or data compensation matching the unified settlement result to the target vehicle's corresponding account.

[0093] In the embodiments involved in this application, there are various feasible specific implementation methods. To clearly and completely illustrate the technical solutions of this disclosure, the implementation methods listed below are merely exemplary and do not constitute a limitation on the scope of protection of this disclosure. That is, in addition to the following implementation methods, other implementation methods that can be obtained by those skilled in the art based on the technical content disclosed in this disclosure through reasonable logical analysis, reasoning, or limited experimentation should also be covered within the scope of protection of this disclosure. The following specifically describes some exemplary implementation methods: As a specific implementation of this disclosure, based on the basic scheme, spatiotemporal aggregation of driving location and network quality data is performed to generate dynamic network quality information. This is further defined as follows: based on the driving locations uploaded by multiple vehicle terminals, the network quality data uploaded by each vehicle terminal is mapped to corresponding road segments, and the network quality data within the same road segment is divided into corresponding time windows according to the collection time; the downlink rate score, uplink rate score, latency score, jitter score, packet loss rate correction score, and signal strength score of each road segment within the corresponding time window are calculated respectively; the weights of each network quality indicator are determined according to the business scenario, and the downlink rate score, uplink rate score, latency score, jitter score, packet loss rate correction score, and signal strength score are weighted and fused to obtain a comprehensive network quality score for the road segment; a network quality level and a dynamic network quality heatmap are generated based on the comprehensive network quality score of the road segment, and at least one of the comprehensive network quality score of the road segment, the network quality level, and the dynamic network quality heatmap is used as dynamic network quality information.

[0094] Specifically, the cloud can map dimensions such as latency, packet loss rate, throughput, jitter, and connection stability in network quality data to different levels. For example, latency less than 10 milliseconds corresponds to the best level, 10 to 30 milliseconds corresponds to a good level, 30 to 100 milliseconds corresponds to a fair level, 100 to 300 milliseconds corresponds to a poor level, and greater than 300 milliseconds corresponds to the worst level; a packet loss rate less than or equal to 0.1% corresponds to the best level, 0.1% to 1% corresponds to a good level, 1% to 3% corresponds to a fair level, 3% to 5% corresponds to a poor level, and greater than 5% corresponds to the worst level. When calculating the comprehensive network quality score of a road segment in the cloud, the following formula can be used: Comprehensive network quality score of road segment = w1 × downlink rate score + w2 × uplink rate score + w3 × latency score + w4 × jitter score + w5 × (100 - packet loss rate score) + w6 × signal strength score, where w1 + w2 + ... + w6 = 1, and w1 to w6 are the weights corresponding to downlink rate, uplink rate, latency, jitter, packet loss rate and signal strength, respectively. As an example, in a general scenario, w1=0.3, w2=0.2, w3=0.2, w4=0.1, w5=0.1, w6=0.1; in cloud gaming or real-time video scenarios, w1=0.2, w2=0.1, w3=0.3, w4=0.3, w5=0.1, w6=0.0; and in large file upload scenarios, w1=0.1, w2=0.5, w3=0.1, w4=0.1, w5=0.1, w6=0.1. The cloud can map scores of 80-100 as excellent, 60-80 as good, 40-60 as average, 20-40 as poor, and 0-20 as very poor, generating a dynamic network quality heatmap using different colors. In addition to the weight configuration and level mapping methods mentioned above, equivalent weight adjustment and level division methods can also be adopted according to the actual business type, road type or network standard.

[0095] As a specific implementation of this disclosure, based on the basic scheme, the information of vehicles on the same route is determined based on the target vehicle's driving route, candidate vehicle routes, dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information. This is further specified as follows: the target vehicle's driving route is divided into multiple target road segments arranged in traffic order, and candidate vehicle routes are obtained; it is determined whether the candidate vehicle routes contain multiple target road segments in terms of road segments, number of road segments, and road segment order, and candidate vehicles that satisfy the inclusion relationship are identified as initial screening vehicles; the network quality similarity between the target vehicle and the initial screening vehicles on common road segments is calculated based on dynamic network quality information, behavioral matching indicators are determined based on candidate vehicle driving behavior data, and location matching indicators are determined based on location dynamic information; the network quality similarity, behavioral matching indicators, and location matching indicators are fused to obtain the vehicle matching degree, and the information of vehicles on the same route is determined based on the vehicle matching degree.

[0096] Specifically, the cloud can break down the target vehicle's travel route into continuous segments such as A0-A1, A1-A2, A2-A3, A3-A4, A4-A5, A5-A6, A6-A7, A7-A8, A8-A9, and A9-A10. If the target vehicle's actual travel path is A1-A2, A2-A3, A3-A4, A4-A5, A5-A6, A6-A7, A7-A8, and A8-A9, and a candidate vehicle's candidate route includes A0-A1, A1-A2, A2-A3, A3-A4, A4-A5, A5-A6, A6-A7, A7-A8, A8-A9, and A9-A10, then this candidate vehicle route covers the target vehicle's travel route in terms of segments, number of segments, and segment order, and the cloud can identify it as a preliminary screening vehicle. For vehicles initially screened, the cloud can use a weighted scoring model to calculate the vehicle matching degree M, for example: M = a × N + b × B + c × P, where N represents network quality similarity, B represents behavioral matching index, P represents location matching index, and a, b, and c are the corresponding weights, and a + b + c = 1. Network quality similarity N can be determined based on the difference in network quality level or network quality score between two vehicles on the same road segment; behavioral matching index B can be determined based on the candidate vehicle's safety score and number of violations; and location matching index P can be determined based on the real-time GPS location, speed deviation, and estimated arrival time difference between the two vehicles. The cloud can select the initially screened vehicle with the highest vehicle matching degree M or whose vehicle matching degree M meets a preset threshold as a vehicle on the same route, and can update the matching results every 5 minutes, or re-execute the matching when a vehicle's route deviation, speed deviation exceeding the threshold, or estimated arrival time difference increasing is detected. In addition to the above weighted scoring model, normalized scoring, segmented scoring, or ranking models can also be used to fuse multiple matching indicators.

[0097] As a specific implementation of this disclosure, based on the basic scheme, after the trip ends, settlement and allocation of incentive resources are performed based on driving behavior evaluation data, network contribution data, and trip interaction data. This is further defined as follows: after the target vehicle reaches the trip's destination, the target vehicle's regular driving score, reward driving score, and penalty driving deduction points for this trip are determined based on the driving behavior evaluation data; the target vehicle's network quality reward information and network data contribution amount for this trip are determined based on the network contribution data; the target vehicle's trip interaction score for this trip is determined based on the trip interaction data; the regular driving score, reward driving score, penalty driving deduction points, network quality reward information, network data contribution amount, and trip interaction score are integrated to obtain a unified settlement result; and based on the unified settlement result, at least one incentive resource among points, data traffic compensation, and package discounts is allocated to the user corresponding to the target vehicle.

[0098] Specifically, if the network contribution data indicates that the target vehicle is passing through a road segment with network quality lower than the preset quality conditions, the cloud can determine the traffic compensation information according to the following formula: Compensation Traffic (MB) = Travel Time (seconds) × (Base Network Speed ​​- Current Network Speed) × Compensation Coefficient; where the base network speed is the historical average network speed of the road segment, the current network speed is the network speed collected by the target vehicle in the road segment, and the compensation coefficient is used to characterize the degree of network quality difference. The compensation coefficient can be expressed as: Compensation Coefficient = |Average Score - Current Score| × 0.1; where the average score is the historical average network quality score of the road segment, and the current score is the network quality score corresponding to the target vehicle's current passage through the road segment. The cloud can also determine the points reward according to the following formula: Points Reward = Fixed Base Score × Network Quality Deterioration Degree, where the network quality deterioration degree = 1 / network quality score. For trip interaction scores, the cloud can determine regular interaction scores, reward interaction scores, and penalty interaction deductions based on the trigger results of regular guidance information, completion results of reward guidance information, and trigger results of penalty guidance information in the trip interaction data, respectively. For interaction comparisons of vehicles on the same route, the scores of vehicles on the same route can be determined according to the following formula: Score of vehicles on the same route = Total score × (Distance traveled by vehicles on the same route / Total distance of vehicles on the same route) - Deductions of vehicles on the same route.

[0099] The cloud platform integrates regular driving scores, reward driving scores, penalty driving points, network quality reward information, network data contribution, and trip interaction scores to obtain a unified settlement result. Based on this unified settlement result, it allocates at least one incentive resource from points, data compensation, and package discounts to the user corresponding to the target vehicle. In addition to the above-mentioned formulaic settlement method, the cloud platform can also use a level mapping table, segmented reward rules, or account cumulative contribution rules to determine incentive resources.

[0100] As a specific implementation of this disclosure, based on the basic solution, the trip interaction score of the target vehicle in this trip is determined based on the trip interaction data, and further specified as follows: the regular interaction score of the target vehicle in the driving route is determined based on the triggering results of the regular score guidance elements in the trip interaction data; the reward interaction score of the target vehicle in the reward driving event is determined based on the triggering results of the reward driving guidance information and the task completion results in the trip interaction data; the penalty interaction deduction score of the target vehicle in the penalty driving event is determined based on the triggering results of the penalty driving guidance information in the trip interaction data; the driving progress and deduction results of vehicles on the same route are determined based on the information of vehicles on the same route, and the trip interaction score is determined based on the regular interaction score, reward interaction score, penalty interaction deduction score, driving progress and deduction results of vehicles on the same route.

[0101] Specifically, the cloud can break down trip interaction data into data triggered by regular scoring guidance elements, response data to reward driving guidance information, trigger data to penalty driving guidance information, and interaction data with vehicles on the same route, based on the type of guidance information. Specifically, the cloud first determines the number of regular scoring guidance elements actually triggered by the target vehicle along the route based on the trigger results of the regular scoring guidance elements, and then determines the regular interaction score by combining the score of each regular scoring guidance element. Next, based on the trigger results of reward driving guidance information and the task completion results, it determines whether the target vehicle completed the corresponding driving task at the scene location corresponding to the reward driving event, thus determining the reward interaction score. Simultaneously, based on the trigger results of penalty driving guidance information, it determines whether the target vehicle triggered the risk location corresponding to the penalty driving guidance information, thus determining the penalty interaction deduction.

[0102] It should be noted that the embodiments of this disclosure may include multiple steps. For ease of description, these steps are numbered, but these numbers are not a limitation on the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of this disclosure do not limit this.

[0103] Corresponding to the driving behavior guidance method described above, this disclosure also proposes a driving behavior guidance device. Since the device embodiments of this disclosure correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to the method embodiments described above, and will not be repeated here.

[0104] Figure 3 This is a schematic diagram of the structure of a driving behavior guidance device provided in an embodiment of the present disclosure, as shown below. Figure 3 As shown, it includes: The acquisition unit 31 is used to acquire the target vehicle's driving route, driving location, and network quality data, and upload the driving route, driving location, and network quality data to the cloud. The first receiving unit 32 is used to receive dynamic network quality information and vehicle information on the same route returned from the cloud. The identification unit 33 is used to identify driving events of the target vehicle; The first generation unit 34 is used to generate and update the augmented reality virtual guidance interface based on the driving location, dynamic network quality information, information of vehicles on the same route and driving events, and to generate guidance response results based on the target vehicle's response to the guidance information in the augmented reality virtual guidance interface. Upload unit 35 is used to generate driving behavior evaluation data, network contribution data, and trip interaction data based on driving events, network quality data, and guidance response results, and upload the driving behavior evaluation data, network contribution data, and trip interaction data to the cloud.

[0105] Figure 4This is a schematic diagram of the structure of a driving behavior guidance device provided in an embodiment of the present disclosure, as shown below. Figure 4 As shown, it includes: The second receiving unit 41 is used to receive driving route, driving location and network quality data uploaded by multiple vehicle terminals; The second generation unit 42 is used to perform spatiotemporal aggregation of driving location and network quality data to generate dynamic network quality information. The determining unit 43 is used to determine the information of vehicles on the same route based on the target vehicle's driving route, candidate vehicle routes, dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information. The sending unit 44 is used to send dynamic network quality information and information of vehicles on the same route to the vehicle terminal corresponding to the target vehicle; and to receive driving behavior evaluation data, network contribution data and trip interaction data uploaded by the vehicle terminal. Settlement unit 45 is used to settle and allocate incentive resources based on driving behavior evaluation data, network contribution data and trip interaction data after the trip ends.

[0106] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0107] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0108] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0109] like Figure 5As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 502 or a computer program loaded from storage unit 508 into RAM (Random Access Memory) 503. The RAM 503 can also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An I / O (Input / Output) interface 505 is also connected to the bus 504.

[0110] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0111] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as driving behavior guidance methods. For example, in some embodiments, the driving behavior guidance method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the aforementioned driving behavior guidance method by any other suitable means (e.g., by means of firmware).

[0112] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0116] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0117] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0118] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0119] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0120] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0121] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0122] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for guiding driving behavior, characterized in that, Applications in vehicles include: The system acquires the target vehicle's driving route, driving location, and network quality data, and uploads these data to the cloud. Receive dynamic network quality information and vehicle information on the same route returned by the cloud; Identify driving events of the target vehicle; Based on the driving location, the dynamic network quality information, the information of vehicles on the same route, and the driving event, an augmented reality virtual guidance interface is generated and updated, and a guidance response result is generated based on the target vehicle's response to the guidance information in the augmented reality virtual guidance interface. Based on the driving event, the network quality data, and the guidance response result, driving behavior evaluation data, network contribution data, and trip interaction data are generated respectively, and the driving behavior evaluation data, the network contribution data, and the trip interaction data are uploaded to the cloud.

2. The method according to claim 1, characterized in that, The process of acquiring the target vehicle's driving route, driving location, and network quality data, and uploading the driving route, driving location, and network quality data to the cloud, includes: The current location, destination, and multiple road segments arranged in traffic order of the target vehicle are determined by vehicle positioning information and navigation information to obtain the driving route; The network quality data is obtained by collecting the signal strength, network type, uplink and downlink speeds, latency, jitter and packet loss rate of the target vehicle on each road segment through vehicle-mounted communication equipment or mobile terminals. The vehicle identification, collection time, driving location, driving route, and network quality data are encapsulated into vehicle network status data, and the vehicle network status data is uploaded to the cloud.

3. The method according to claim 1, characterized in that, The identification of driving events for the target vehicle includes: The vehicle video stream of the forward field of view of the target vehicle is acquired, and traffic object recognition is performed on the image frames in the vehicle video stream to obtain the recognition results of vehicles, pedestrians, traffic signs and road areas. Based on the recognition results, temporal behavior recognition is performed on vehicle behavior, pedestrian behavior, and traffic sign status to obtain the behavior recognition results of the target traffic object. The motion trajectory of the target traffic object in consecutive image frames is tracked, and the motion trajectory is associated with the road area and the traffic sign status to obtain the traffic object trajectory association result; Based on the behavior recognition results and the traffic object trajectory association results, the driving events of the target vehicle are classified to obtain the driving events including regular driving events, reward driving events, and penalty driving events.

4. The method according to claim 1, characterized in that, The augmented reality virtual guidance interface is generated and updated based on the driving location, the dynamic network quality information, the information of vehicles on the same route, and the driving event. A guidance response result is generated based on the target vehicle's response to the guidance information in the augmented reality virtual guidance interface, including: Generate route display information corresponding to the field of vision in front of the vehicle based on the target vehicle's driving route and driving position; Network status guidance information is generated based on the dynamic network quality information, vehicle interaction guidance information is generated based on the information of vehicles on the same route, and driving task guidance information is generated based on the driving events. The route display information, the network status guidance information, the vehicle interaction guidance information, and the driving task guidance information are combined into the augmented reality virtual guidance interface; The guidance response result is generated based on the target vehicle's response to the network status guidance information, the vehicle interaction guidance information, and the driving task guidance information.

5. The method according to claim 4, characterized in that, The generation of driving task guidance information based on the driving event includes: The total route score is determined based on the target vehicle's driving route, and the interval position of the regular score guide element on the driving route is determined based on the total route distance, the total route score, and the score of a single regular score guide element. The regular scoring guidance elements are assigned to the corresponding road segments according to the length of each road segment, and the positions of the regular scoring guidance elements are made consistent with the driving route to obtain regular driving guidance information. When the driving event includes a reward driving event, reward driving guidance information is generated at the scene location corresponding to the reward driving event, and the reward driving guidance information is associated with driving task prompt information; When the driving event includes a penalty driving event, penalty driving guidance information is generated at the risk location corresponding to the penalty driving event, and the penalty driving guidance information is associated with the demerit point rules.

6. The method according to claim 4, characterized in that, The generation of network state guidance information based on the dynamic network quality information includes: Based on the dynamic network quality information, determine whether the current road segment of the target vehicle is a road segment with network quality lower than the preset quality condition; When the target vehicle passes through a road segment where the network quality is lower than the preset quality condition, the travel time of the target vehicle in that road segment, the current network speed, the historical baseline speed and the network quality difference are recorded to obtain network experience loss data. Based on the network experience loss data, a network quality reward notification is generated, which includes at least one of traffic compensation notification, points reward notification, and package discount contribution notification. The network quality reward notification information is overlaid on the augmented reality virtual guidance interface as part of the network status guidance information.

7. The method according to claim 1, characterized in that, The process of generating driving behavior evaluation data, network contribution data, and trip interaction data based on the driving event, network quality data, and guidance response results, respectively, includes: Based on the regular driving events, reward driving events, and penalty driving events in the driving events, driving behavior evaluation data is generated to characterize the driving behavior of the target vehicle; Based on the network quality data, network experience loss data, and network quality data upload status, network contribution data is generated to characterize the network detection contribution of the target vehicle. Based on the guidance information triggering result, task completion result, network interaction result, and vehicle interaction result in the guidance response result, the trip interaction data used to characterize the trip interaction performance of the target vehicle is generated.

8. A method for guiding driving behavior, characterized in that, Applied to the cloud, including: Receives driving routes, driving locations, and network quality data uploaded from multiple vehicle terminals; The driving location and the network quality data are spatiotemporally aggregated to generate dynamic network quality information; Based on the target vehicle's driving route, candidate vehicle routes, the dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information, information on vehicles traveling on the same route is determined. Send the dynamic network quality information and the information of vehicles on the same route to the vehicle terminal corresponding to the target vehicle; Receive driving behavior evaluation data, network contribution data, and trip interaction data uploaded by the vehicle terminal; After the trip is completed, settlement and incentive resources are allocated based on the driving behavior evaluation data, the network contribution data, and the trip interaction data.

9. The method according to claim 8, characterized in that, The step of spatiotemporally aggregating the driving location and the network quality data to generate dynamic network quality information includes: Based on the driving locations uploaded by multiple vehicle terminals, the network quality data uploaded by each vehicle terminal is mapped to the corresponding road segment, and the network quality data within the same road segment is divided into the corresponding time window according to the collection time. Calculate the downlink rate score, uplink rate score, latency score, jitter score, packet loss rate correction score, and signal strength score for each segment within the corresponding time window; The weights of each network quality indicator are determined based on the business scenario, and the downlink rate score, uplink rate score, latency score, jitter score, packet loss rate correction score and signal strength score are weighted and fused to obtain the comprehensive network quality score of the road segment. Based on the comprehensive network quality score of the road segment, a network quality level and a dynamic network quality heat map are generated, and at least one of the comprehensive network quality score of the road segment, the network quality level, and the dynamic network quality heat map is used as the dynamic network quality information.

10. The method according to claim 8, characterized in that, The process of determining vehicle information along the same route based on the target vehicle's driving route, candidate vehicle routes, dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information includes: The travel route of the target vehicle is divided into multiple target road segments arranged in the order of passage, and the candidate vehicle routes are obtained; Determine whether the candidate vehicle route contains the multiple target road segments in terms of road segment, number of road segments, and road segment order, and determine the candidate vehicles that satisfy the inclusion relationship as the initial screening vehicles; The network quality similarity between the target vehicle and the pre-screened vehicle on the same road segment is calculated based on the dynamic network quality information. The behavior matching index is determined based on the candidate vehicle driving behavior data, and the location matching index is determined based on the location dynamic information. The network quality similarity, the behavior matching index, and the location matching index are fused to obtain the vehicle matching degree, and the information of vehicles on the same route is determined based on the vehicle matching degree.

11. The method according to claim 8, characterized in that, The process of settling accounts and allocating incentive resources based on the driving behavior evaluation data, the network contribution data, and the trip interaction data after the trip is completed includes: After the target vehicle reaches the end of the trip, the driving behavior evaluation data is used to determine the target vehicle's regular driving score, reward driving score, and penalty driving deduction points for this trip. Based on the network contribution data, determine the network quality reward information and network data contribution amount of the target vehicle in this trip; The trip interaction score of the target vehicle in this trip is determined based on the trip interaction data; The regular driving score, the reward driving score, the penalty driving score, the network quality reward information, the network data contribution, and the trip interaction score are integrated to obtain a unified settlement result; Based on the unified settlement result, at least one incentive resource among points, data traffic compensation, and package discounts is allocated to the user corresponding to the target vehicle.

12. The method according to claim 11, characterized in that, The process of determining the trip interaction score of the target vehicle in this trip based on the trip interaction data includes: Based on the triggering results of the regular score guidance elements in the trip interaction data, the regular interaction score of the target vehicle in the driving route is determined; Based on the reward driving guidance information triggering results and task completion results in the trip interaction data, the reward interaction score of the target vehicle in the reward driving event is determined; Based on the penalty driving guidance information triggering results in the trip interaction data, the penalty interaction points of the target vehicle in the penalty driving event are determined; Based on the information of vehicles on the same route, the travel progress and deduction results of vehicles on the same route are determined, and the trip interaction score is determined according to the regular interaction score, the reward interaction score, the penalty interaction deduction, the travel progress and deduction results of vehicles on the same route.

13. A driving behavior guidance device, characterized in that, Applications in vehicles include: The acquisition unit is used to acquire the target vehicle's driving route, driving location, and network quality data, and upload the driving route, driving location, and network quality data to the cloud. The first receiving unit is used to receive dynamic network quality information and vehicle information on the same route returned by the cloud. The identification unit is used to identify driving events of the target vehicle; The first generation unit is used to generate and update the augmented reality virtual guidance interface based on the driving location, the dynamic network quality information, the information of vehicles on the same route, and the driving event, and to generate a guidance response result based on the response of the target vehicle to the guidance information in the augmented reality virtual guidance interface. The uploading unit is used to generate driving behavior evaluation data, network contribution data, and trip interaction data based on the driving event, the network quality data, and the guidance response result, respectively, and upload the driving behavior evaluation data, network contribution data, and trip interaction data to the cloud.

14. A driving behavior guidance device, characterized in that, Applied to the cloud, including: The second receiving unit is used to receive driving routes, driving locations and network quality data uploaded by multiple vehicle terminals; The second generation unit is used to perform spatiotemporal aggregation of the driving location and the network quality data to generate dynamic network quality information. The determining unit is used to determine vehicle information on the same route based on the target vehicle's driving route, candidate vehicle routes, the dynamic network quality information, candidate vehicle driving behavior data, and location dynamic information. The sending unit is used to send the dynamic network quality information and the information of vehicles on the same route to the vehicle terminal corresponding to the target vehicle; and to receive driving behavior evaluation data, network contribution data and trip interaction data uploaded by the vehicle terminal. The settlement unit is used to settle accounts and allocate incentive resources based on the driving behavior evaluation data, the network contribution data, and the trip interaction data after the trip is completed.

15. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7 or 8-12.

16. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7 or 8-12.

Images