Map application and update methods, devices, equipment and storage media

Abstract

This invention relates to the field of driver assistance technology, and discloses a map application and updating method, apparatus, device, and storage medium. The method includes: matching the vehicle's current location with a local driving interference event marker map to determine whether a driving interference event exists within a preset distance range ahead of the vehicle. The local driving interference event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle. If a driving interference event exists, the vehicle is controlled and / or located based on the event. The driving interference event marker map is used to record various driving interference events experienced by the vehicle. Applying the technical solution of this invention can solve the problems of insufficient robustness of driver assistance systems when real-time sensors fail and limited vehicle perception of potential driving interference events in complex road conditions in existing technologies.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of assisted driving technology, specifically to a map application and update method, device, equipment, and storage medium. Background Technology

[0002] Currently, when vehicles enter areas where GNSS (Global Navigation Satellite System) signals are blocked, such as tunnels and underground parking garages, simultaneous localization and mapping (SLAM) technology based on lidar or visual sensors is commonly used to maintain continuous positioning capabilities. The core of this technology is to achieve positioning by matching real-time sensor data with a pre-built geometric feature map.

[0003] SLAM technology requires the continuous operation of high-precision sensor arrays (such as LiDAR and high-resolution cameras) and consumes a large amount of computing resources for point cloud registration, feature extraction, and attitude estimation. For short-range GNSS failure scenarios of only a few hundred meters, this technical solution suffers from a significant "mismatch of technical resources," leading to a surge in hardware costs and a waste of computing resources.

[0004] SLAM positioning accuracy is highly dependent on the stability and distinguishability of environmental geometric features. In feature-sparse scenarios (such as monotonous walls in tunnels) or feature-similar scenarios (such as dense columns in underground parking lots), the positioning accuracy can drop sharply or even fail due to insufficient number of effective feature points or increased risk of feature confusion, which severely restricts the robustness and scene adaptability of the positioning system. Summary of the Invention

[0005] In view of the above problems, embodiments of the present invention provide a map application and update method, apparatus, device and storage medium to solve the problems of insufficient robustness of driving assistance systems when real-time sensors fail and limited ability of vehicles to perceive potential driving interference events under complex road conditions in the prior art.

[0006] According to one aspect of the present invention, a map application and update method is provided, the method comprising:

[0007] The vehicle's current location is matched with a local driving impact event marker map to determine whether there are driving interference events within a preset distance in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle.

[0008] If a driving interference event exists, the vehicle is controlled and / or located based on the driving interference event. The driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during vehicle operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

[0009] According to another aspect of the present invention, a map updating method is provided, the method comprising:

[0010] Statistical analysis was performed on the received multi-vehicle crowdsourcing data to filter out driving interference events that were reported multiple times at the same location, and these were designated as driving interference events to be labeled.

[0011] Based on the traffic interference events to be labeled, the global traffic impact event labeling map is updated.

[0012] According to another aspect of the present invention, a map application and update apparatus is provided, comprising:

[0013] The judgment module is used to match the vehicle's current position with the local driving impact event marker map to determine whether there is a driving interference event within a preset distance range in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle.

[0014] The application module is used to control and / or locate the vehicle based on the driving interference event if a driving interference event exists. The driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during vehicle operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

[0015] According to another aspect of the present invention, a map updating apparatus is provided, the apparatus comprising:

[0016] The filtering module is used to perform statistical analysis on the received multi-vehicle crowdsourcing data, filter out driving interference events that are reported multiple times at the same location, and use them as driving interference events to be marked.

[0017] The update module is used to update the global driving impact event marking map based on the driving interference events to be marked.

[0018] According to another aspect of the present invention, a map application and update device is provided, comprising:

[0019] The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus.

[0020] The memory is used to store at least one executable instruction that causes the processor to perform the map application and update method as described above.

[0021] According to another aspect of the present invention, a map updating device is provided, comprising:

[0022] The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus.

[0023] The memory is used to store at least one executable instruction that causes the processor to perform the map update method as described above.

[0024] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing at least one executable instruction that causes a map application and update device / apparatus to perform the operation of the map application and update method as described above.

[0025] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing at least one executable instruction that causes a map updating device / apparatus to perform the map updating method as described above.

[0026] This invention matches the current location with a local driving interference event marker map to predict in advance whether driving interference events exist within a preset distance range ahead. The vehicle can obtain relevant information before an interference event occurs and react in advance, thereby reducing the risk caused by sudden interference events. The local driving interference event marker map serves as "prior knowledge," providing compensation information when real-time sensors fail or signal interference occurs. Even if some sensor data is inaccurate, the vehicle can still refer to the map marker information to make decisions, significantly improving the robustness and reliability of the driving assistance system. Control and / or positioning adjustments are made to the vehicle based on driving interference events. This improves the accuracy and stability of vehicle positioning, providing more reliable support for autonomous driving and advanced driver assistance systems. This map application and update method significantly enhances the vehicle's positioning and decision-making capabilities in complex environments through techniques such as early detection of driving interference events, improved robustness of the driving assistance system, and optimized vehicle control and positioning accuracy.

[0027] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0028] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0029] Figure 1 This invention illustrates a flowchart of a first embodiment of the map application and update method provided by the present invention.

[0030] Figure 2 A flowchart illustrating a second embodiment of the map application and update method provided by the present invention is shown.

[0031] Figure 3 A flowchart illustrating an embodiment of the map updating method provided by the present invention is shown;

[0032] Figure 4 A schematic diagram of an embodiment of the map application and updating device provided by the present invention is shown;

[0033] Figure 5 A schematic diagram of an embodiment of the map updating device provided by the present invention is shown;

[0034] Figure 6 A schematic diagram of an embodiment of the map application and update device provided by the present invention is shown;

[0035] Figure 7 A schematic diagram of an embodiment of the map updating device provided by the present invention is shown;

[0036] Figure 8 A structural schematic diagram of an embodiment of the vehicle provided by the present invention is shown. Detailed Implementation

[0037] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0038] Figure 1 A flowchart illustrating a first embodiment of the map application and update method of the present invention is shown, which can be executed by a domain controller in a vehicle. Figure 1 As shown, the method includes the following steps:

[0039] Step 110: Match the vehicle's current location with the local driving impact event marker map to determine whether there are driving interference events within a preset distance range in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle.

[0040] In this step, the vehicle determines its current location using its positioning system and then compares this location information with a local driving interference event marker map. This map is generated in the cloud based on crowdsourced data uploaded by multiple vehicles (including sensor data and driving behavior during vehicle operation), and it records in detail the location and type of various driving interference events that the vehicle may encounter. By matching the data, it can determine whether these interference events exist within a preset distance in front of the vehicle, thus providing a basis for subsequent driving decisions in advance.

[0041] Step 120: If a driving interference event exists, control and / or locate the vehicle based on the driving interference event. A driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during vehicle operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

[0042] If a driving interference event is detected within a preset distance in front of the vehicle, the vehicle will be controlled and / or its positioning adjusted accordingly based on the specific circumstances of the event. Driving interference events refer to events that affect the vehicle's driving status or driving behavior during operation, caused by road conditions (such as construction, potholes), environmental factors (such as inclement weather, obstructed visibility), or other external factors (such as traffic congestion, accidents). The local driving interference event marker map records these events, enabling the vehicle to take proactive control actions based on the marker information on the map, such as adjusting speed, changing routes, and alerting the driver, or correcting the vehicle's positioning system to ensure safe and stable driving in complex road conditions.

[0043] This invention matches the current location with a local driving interference event marker map to predict in advance whether driving interference events exist within a preset distance range ahead. The vehicle can obtain relevant information before an interference event occurs and react in advance, thereby reducing the risk caused by sudden interference events. The local driving interference event marker map serves as "prior knowledge," providing compensation information when real-time sensors fail or signal interference occurs. Even if some sensor data is inaccurate, the vehicle can still refer to the map marker information to make decisions, significantly improving the robustness and reliability of the driving assistance system. Control and / or positioning adjustments are made to the vehicle based on driving interference events. This improves the accuracy and stability of vehicle positioning, providing more reliable support for autonomous driving and advanced driver assistance systems. This map application and update method significantly enhances the vehicle's positioning and decision-making capabilities in complex environments through techniques such as early detection of driving interference events, improved robustness of the driving assistance system, and optimized vehicle control and positioning accuracy.

[0044] Figure 2 A flowchart illustrating another embodiment of the map application and update method of the present invention is shown, which can be executed by a domain controller in a vehicle. Figure 2 As shown, the method includes the following steps:

[0045] Step 210: When the vehicle's sensor functions are limited, the vehicle's current location is matched with the local driving impact event marker map to determine whether there are driving interference events within a preset distance range in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle.

[0046] In this step, when the vehicle's sensors are limited in function due to severe weather, obstruction, or other reasons and cannot accurately perceive the surrounding environment, the vehicle will activate a backup plan to match its current location with the local driving impact event marker map.

[0047] Step 220: If a driving interference event exists, control and / or locate the vehicle based on the driving interference event. A driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during vehicle operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

[0048] In one alternative approach, controlling and / or locating the vehicle based on driving disturbance events may specifically include the following steps:

[0049] From the map data of the local driving impact event marker map, query the control strategy corresponding to the driving interference event. The map data contains control strategy information related to the driving interference event.

[0050] When the vehicle travels to the location corresponding to the traffic interference event, the vehicle is controlled according to the control strategy.

[0051] In this embodiment, control strategies corresponding to detected driving interference events can be found from map data of a local driving interference event marker map. This map not only records the location and type of interference events but also contains specific control strategy information associated with each interference event. These control strategies are pre-set based on the nature and severity of the interference events and are used to guide the actions the vehicle should take when encountering the corresponding events.

[0052] When the vehicle reaches the location corresponding to the traffic interference event, the vehicle is controlled according to the retrieved control strategy. The control strategy may include adjusting the vehicle speed (such as deceleration or acceleration), changing the driving direction (such as changing lanes in advance or detouring), activating specific driving assistance functions (such as automatic emergency braking or lane keeping assist), etc., to ensure that the vehicle can safely and smoothly pass through the interference area, reduce driving risks and improve driving efficiency.

[0053] In one alternative approach, the driving impact event marker map is specifically used to record driving disturbance events related to the vehicle chassis, such as road potholes, slope changes, and bumpy road sections. These events directly affect the vehicle's driving stability and ride comfort. The map data not only records the location and type of the disturbance events but also includes suspension control strategy information for these events. When the vehicle approaches these disturbance events, it can automatically adjust suspension parameters, such as height, damping, and stiffness, based on the suspension control strategy information in the map. This dynamic adjustment effectively reduces the feeling of bumps on uneven road surfaces, improves vehicle passability, and optimizes vehicle handling performance, thereby significantly improving driving performance and ride comfort.

[0054] In one alternative approach, controlling and / or locating the vehicle based on driving disturbance events may specifically include the following steps:

[0055] From the map data of the local driving impact event marker map, query the attribute parameters corresponding to the driving interference events. The map data contains attribute parameter information related to driving interference events.

[0056] When the vehicle approaches the location corresponding to the driving interference event, the vehicle dynamic control system is adjusted in advance based on the attribute parameters.

[0057] In this embodiment, instead of directly providing specific control strategies, it provides attribute parameters related to driving disturbance events. These attribute parameters are pre-recorded information in the map data related to each disturbance event, such as the type, severity, and location coordinates of the disturbance event. When the vehicle approaches the location corresponding to these disturbance events, the vehicle's dynamic control system is adjusted in advance based on the retrieved attribute parameters. This adjustment may include adjusting the suspension stiffness, changing the vehicle speed, and adjusting the steering sensitivity to ensure that the vehicle can pass smoothly and safely when encountering disturbance events, thereby improving driving comfort and safety.

[0058] By introducing a road impact event mapping system, the system can anticipate road conditions tens of meters ahead. For example, when the vehicle is 50 meters from a bump, it can receive a precise instruction: "50 meters ahead, bump level L3, short-term impact." This contrasts sharply with existing technologies where the chassis system can only passively respond at the instant the wheels come into contact with the bump (milliseconds). This invention allows the chassis controller to efficiently and optimally adjust the damping and stiffness of the active suspension or the height of the air suspension, significantly improving ride comfort and driving stability, overcoming the limitations of passive response in existing technologies.

[0059] In one alternative approach, controlling and / or locating the vehicle based on driving disturbance events may specifically include the following steps:

[0060] From the map data of the local driving impact event marker map, query the driving interference sequence data corresponding to the driving interference event. The map data contains driving interference sequence data information related to the driving interference event. The driving interference sequence data is organized in the form of a location sequence, and each location point is associated with the characteristic data of the driving interference event.

[0061] Monitor vehicle driving status information and construct real-time driving interference sequence data;

[0062] The real-time driving interference sequence data is matched with the driving interference sequence data, and the vehicle is located based on the matching results.

[0063] In this embodiment, driving interference sequence data related to driving interference events is obtained from a local driving impact event marker map. This data is organized as a location sequence, with each location point associated with driving interference event characteristic data for that location. During vehicle operation, the vehicle monitors driving status information (such as vehicle speed, acceleration, suspension compression, etc.) using its own sensors and constructs real-time driving interference sequence data based on this information. This real-time data reflects the interference encountered by the vehicle on its current driving path. The real-time driving interference sequence data is matched with the driving interference sequence data in the map. Through this matching, the vehicle's precise location on the map can be determined. For example, if real-time data shows that the vehicle encountered a specific level of bumps at a certain location, and the map data also records similar bump information at that location, the vehicle's current location can be confirmed, thus achieving high-precision positioning. This method is completely decoupled from traditional positioning methods based on geometric features (such as satellite signals, landmarks, etc.) and does not rely on Global Navigation Satellite System (GNSS) signals. Therefore, it provides a new and independent information source for positioning in GNSS failure scenarios, and can still accurately determine the vehicle's position even when satellite signals are blocked or fail, greatly improving the positioning reliability and autonomy of vehicles in complex environments.

[0064] The following example illustrates how to achieve high-precision vehicle positioning in complex environments (such as tunnels) using traffic interference sequence data and vehicle sensor information:

[0065] Before the vehicle enters the tunnel, the last high-precision GPS coordinates are recorded. This is the last precise location information the vehicle can obtain outside the tunnel. Simultaneously, an image containing clear lane lines is captured as visual anchor point A. This image records the lane line position and geometric relationships before the vehicle enters the tunnel, providing a reference point for subsequent positioning.

[0066] Upon entering the tunnel, due to potential GPS signal failure or weakening, the vehicle relies on an inertial measurement unit (IMU) for dead reckoning. The IMU provides acceleration and angular velocity information to estimate the vehicle's trajectory. Simultaneously, the vehicle detects bump events and generates a real-time "bump sequence." This sequence records the location and characteristics of bump events encountered by the vehicle within the tunnel. This real-time bump sequence is then matched with a priori sequence in a "bump map." Since the "bump map" records the bump characteristics at corresponding locations within the tunnel, this matching process can correct the vehicle's longitudinal position, i.e., its displacement in the forward and backward directions within the tunnel.

[0067] As the vehicle exits the tunnel, a new lane line image is captured as visual anchor point B. By comparing the geometric relationship of the lane lines in anchor points A and B, the vehicle's lateral drift within the tunnel—that is, its displacement in the left-right direction—can be accurately calculated. This lateral drift information is then used to perform final lateral position correction on the IMU trajectory. In this way, combining longitudinal and lateral position corrections, high-precision vehicle positioning within the tunnel can be achieved.

[0068] In an alternative embodiment, the map application and updating method of the present invention may further include the following steps:

[0069] When a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0070] The driving interference events to be reported and their corresponding semantic tags are associated and uploaded to the cloud so that the cloud can analyze the multi-vehicle crowdsourced data to update the global driving impact event tagging map.

[0071] In this implementation, when a vehicle detects a traffic interference event to be reported, it can generate a semantic label for the event using the event's multimodal perception data and the local perception model. This semantic label is a concise description of the nature, severity, and other characteristics of the interference event. The vehicle then associates the traffic interference event to be reported with its corresponding semantic label and uploads it to the cloud. The cloud collects similar data uploaded by multiple vehicles, analyzes and processes it to update the global traffic impact event labeling map, enabling the map to more accurately reflect traffic interference on the road and provide other vehicles with more timely and accurate road condition information.

[0072] Specifically, various sensors (such as cameras, radar, and lidar) and the vehicle's electronic control system monitor the vehicle's driving status and surrounding environment in real time. When these sensors or systems detect abnormalities, such as potholes or water accumulation on the road, they consider it a driving interference event.

[0073] Multimodal perception data refers to different types of data acquired by a vehicle through various sensors, including visual modal data, motion modal data, and tire-related data. Visual modal data refers to the real-time capture of visual information such as road texture and vehicle attitude changes by onboard cameras. For example, cameras can identify the shape, location, and size of potholes, as well as changes in vehicle attitude during driving (such as body tilt angle). Motion modal data refers to the motion information such as vibrations and roll angular velocity of the vehicle body sensed by an IMU (Inertial Measurement Unit, including accelerometers and gyroscopes). For example, when a vehicle encounters potholes, the IMU can record sudden changes in the vehicle's Z-axis acceleration (such as the peak value triggered by a bump). Tire-related data refers to the tire grip data acquired by wheel speed sensors and tire pressure monitoring systems, such as wheel lift-off or sudden speed changes. This data reflects the contact state between the tires and the road surface, helping to determine the vehicle's driving stability. These different types of data collectively constitute multimodal perception data, enabling a more comprehensive description of driving disturbance events.

[0074] The local perception model can be a VLA (Visual-Linguistic-Action Model). A VLA model processes captured sensor data slices into a structured semantic label. A sensor data slice refers to a data segment captured from multiple sensors (such as cameras, IMUs, wheel speed sensors, etc.) within a specific time window. These data slices contain detailed information about the occurrence of driving disturbance events. For example, if a bump event is detected, camera images, IMU data (such as acceleration and angular velocity), and other relevant sensor data from a few seconds before and after the event can be extracted.

[0075] The VLA model fuses visual and motion features through a cross-modal attention mechanism. For example, it combines image features of road surface potholes captured by a camera (such as pothole shape and location) with abrupt changes in vehicle Z-axis acceleration recorded by an IMU. The model transforms the fused features into structured semantic labels. For instance, the generated semantic label might be "moderate bump - road surface pothole - Z-axis acceleration 1.1g - duration 80ms". This semantic label not only describes the type of driving disturbance event (such as road surface pothole) but also quantifies the severity of the event (such as moderate bump, Z-axis acceleration 1.1g) and its duration (such as 80ms). This structured semantic label transforms complex multimodal perception data into easily understood and processed information. It not only describes the nature of driving disturbance events but also provides quantitative indicators, facilitating subsequent data processing and map updates.

[0076] The uploaded data includes overlaid "group tags," such as "mid-size sedan" and "sport mode." These tags describe the vehicle type and driving mode but do not provide detailed information about the specific vehicle. This helps protect the privacy of both the vehicle and the driver to some extent, while providing sufficient information to the cloud for updating the global driving impact event tagging map.

[0077] In addition, simple masking can be applied to surrounding vehicles and pedestrians to further protect privacy. Masking can obscure the specific characteristics of these objects, so that the cloud can only obtain their existence and general location, but cannot obtain detailed personal or vehicle information.

[0078] In one alternative approach, when a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model. Specifically, this may include the following steps:

[0079] When a traffic interference event to be reported is detected, the corresponding event reporting conditions are determined according to the vehicle type;

[0080] Determine whether the traffic interference event to be reported meets the event reporting conditions;

[0081] If the event reporting conditions are met, then semantic labels for the driving interference events to be reported are generated based on the multimodal perception data of the driving interference events to be reported and the local perception model.

[0082] In this implementation, when a vehicle detects a traffic interference event to be reported, the reporting conditions are first determined based on the vehicle's type. Different types of vehicles (such as sedans, SUVs, trucks, buses, etc.) may have different sensitivities to and handling methods for traffic interference events. For example, sedans may be less sensitive to small potholes on the road, while trucks, due to their higher body and center of gravity, may be more sensitive to road unevenness. Therefore, it is necessary to determine which traffic interference events need to be reported based on the vehicle type. For instance, for sedans, potholes are only reported when they reach a certain depth; while for trucks, even small potholes may need to be reported, as this may affect their driving stability and safety.

[0083] For example, the reporting conditions differ between advanced and standard chassis models. Advanced chassis models, equipped with advanced features such as active suspension, primarily contribute to strategy iteration and optimization. Taking bump events as an example, the Z-axis acceleration threshold can be set to >0.8g. This means that when a Z-axis acceleration exceeding 0.8gs is detected, the reporting mechanism is triggered, thereby capturing more bump events available for strategy optimization. Standard chassis models, on the other hand, primarily contribute to discovering new and severe physical risks. Therefore, their threshold setting is more stringent. Specifically, the reporting mechanism is only triggered when the Z-axis acceleration is >1.2g and the duration is >50ms. This setting effectively filters out a large amount of minor bump information that has no practical value for strategy optimization, ensuring that reported events have high analytical value.

[0084] This invention effectively reduces unnecessary data uploads by setting specific reporting conditions for different vehicle types, thereby improving the relevance and effectiveness of the data. By utilizing multimodal perception data combined with a local perception model to generate semantic labels, it can more accurately describe the nature and severity of driving interference events, solving the problem of inaccurate descriptions of driving interference events in existing technologies, which leads to inaccurate localization and decision-making. Updating the global driving impact event labeling map in the cloud based on uploaded data from multiple vehicles can more effectively integrate data from different vehicles, improving the robustness and reliability of the map.

[0085] In one alternative approach, when a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model. Specifically, this may include the following steps:

[0086] When a traffic interference event to be reported is detected, the geographical area of ​​the traffic interference event to be reported on the local traffic impact event marker map is determined.

[0087] Search within the geographic area for whether there are any labeled traffic interference events that meet the preset similarity criteria with the traffic interference event to be reported;

[0088] If it exists, the reporting of the traffic interference event to be reported is cancelled; otherwise, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0089] In this implementation, when a vehicle detects a traffic interference event to be reported, it first determines the geographical area of ​​the event on the local traffic impact event marking map. Next, it searches within this geographical area for any already marked traffic interference events that meet a preset similarity condition to the event to be reported. If such a similar event exists, it indicates that the interference event has already been recorded and reported; therefore, the vehicle cancels the reporting of the current event to be reported, avoiding duplicate uploading of the same or similar information. Only when no already marked event meeting the similarity condition is found within the geographical area will the vehicle generate a semantic label for the event based on the multimodal perception data and the local perception model, and then proceed with the subsequent reporting operation. This method effectively reduces the uploading of redundant data, improves data accuracy and effectiveness, and alleviates the burden of cloud processing and storage.

[0090] In addition, for extreme events that exceed the normal control capabilities of all vehicles, such as severe road collapses or obstacles, once these events are first reported by a few vehicles and confirmed as permanent high-risk events, other vehicles do not need to report them repeatedly. The purpose of this step is to avoid a large number of vehicles repeatedly reporting the same high-risk events, reduce redundant data, and ensure that high-risk events are recorded and processed in a timely manner.

[0091] In one optional approach, the traffic interference events to be reported and their corresponding semantic tags are associated and uploaded to the cloud, which may include the following steps:

[0092] When a traffic interference event to be reported occurs in an area covered by high-precision satellite signals, traffic interference sequence data for the event is generated based on the high-precision satellite signals.

[0093] When a traffic interference event to be reported occurs in a region where high-precision satellite signals are lost, traffic interference sequence data for the event is generated based on the inertial measurement unit signal.

[0094] The traffic interference events to be reported, along with their corresponding semantic tags and traffic interference sequence data, are uploaded to the cloud.

[0095] In this implementation, if the reported traffic interference event occurs in an area covered by high-precision satellite signals, the vehicle will use the high-precision satellite signals to generate traffic interference sequence data for the event, as satellite signals can provide accurate location and time information in these areas. However, if the event occurs in an area where high-precision satellite signals are unavailable, the vehicle will instead rely on inertial measurement unit (IMU) signals to generate traffic interference sequence data. The IMU can provide motion information such as vehicle acceleration and angular velocity, thus recording the vehicle's driving status even when satellite signals are unavailable. Finally, the vehicle associates the reported traffic interference event, its corresponding semantic tag, and the generated traffic interference sequence data, and then uploads them together to the cloud.

[0096] This invention matches the current location with a local driving interference event marker map to predict in advance whether driving interference events exist within a preset distance range ahead. The vehicle can obtain relevant information before an interference event occurs and react in advance, thereby reducing the risk caused by sudden interference events. The local driving interference event marker map serves as "prior knowledge," providing compensation information when real-time sensors fail or signal interference occurs. Even if some sensor data is inaccurate, the vehicle can still refer to the map marker information to make decisions, significantly improving the robustness and reliability of the driving assistance system. Control and / or positioning adjustments are made to the vehicle based on driving interference events. This improves the accuracy and stability of vehicle positioning, providing more reliable support for autonomous driving and advanced driver assistance systems. This map application and update method significantly enhances the vehicle's positioning and decision-making capabilities in complex environments through techniques such as early detection of driving interference events, improved robustness of the driving assistance system, and optimized vehicle control and positioning accuracy.

[0097] The above embodiments provide a detailed and clear explanation of the map application and update method provided by the present invention from the perspective of the vehicle. The present invention will now be further elaborated from the perspective of the cloud.

[0098] Figure 3 A flowchart illustrating an embodiment of the map update method of the present invention is shown, which can be executed by a cloud server. Figure 3 As shown, the method includes the following steps:

[0099] Step 310: Perform statistical analysis on the received multi-vehicle crowdsourcing data, filter out driving interference events that are reported multiple times at the same location, and designate them as driving interference events to be marked.

[0100] Step 320: Update the global traffic impact event labeling map based on the traffic interference events to be labeled.

[0101] In this implementation, the cloud system counts the frequency of reported traffic interference events at each location. Specifically, it calculates the number of times a traffic interference event is reported at each location. A threshold is set by the cloud to determine whether the reporting frequency of a particular traffic interference event is statistically significant. Only when the reporting frequency exceeds this threshold will the event be selected as a traffic interference event to be labeled. Additionally, anonymous image fragments can be used for auxiliary verification to confirm the authenticity of the reported traffic interference events. Anonymous image fragments refer to image data that has been anonymized and uploaded simultaneously by the vehicle when reporting a traffic interference event. This image data can provide visual evidence of the event but does not contain specific vehicle or individual identification information.

[0102] Considering that different vehicle types may perceive and report the same event differently, the cloud may perform separate statistical analysis on data for different vehicle types to ensure the accuracy of the filtering results. Based on the filtered driving interference events with statistical significance, the cloud updates the global driving impact event labeling map. For example, if a road segment is found to have multiple reported bump events within a one-week observation period, and the retrieved image clips also show potholes on the road surface, the cloud will label the bump event on the map.

[0103] In one alternative approach, the global driving impact event labeling map is updated based on the driving interference events to be labeled, which may specifically include the following steps:

[0104] Based on multi-vehicle crowdsourced data, the attribute parameters of the driving interference events to be labeled are determined;

[0105] The attribute parameters are stored in a database associated with the global driving impact event marker map to update the global driving impact event marker map;

[0106] The attribute parameters include at least one of the following: event type, event level, vehicle safety and performance impact parameters, and validity period. The vehicle safety and performance impact parameters are quantitative indicators of the degree of impact of driving interference events on vehicle driving status or driving behavior. The validity period refers to the time range during which the driving interference event has an impact, used to describe the duration of the impact of the event. The event level refers to the severity of the driving interference event, used to quantify the impact of different driving interference events on vehicle driving safety and comfort.

[0107] Event type categorizes driving interference events, describing the nature of the event. Examples include potholes and water accumulation on the road. Event level quantifies the severity of a driving interference event, typically categorized into multiple levels (e.g., minor, moderate, severe). Vehicle safety and performance impact parameters are quantitative indicators of the impact of driving interference events on vehicle driving status or driving behavior. The cloud can assess the severity of corresponding driving interference events, determine the event level, and quantify the impact of driving interference events on vehicle driving status or driving behavior based on reported data.

[0108] Among these, vehicle safety and performance impact parameters can specifically include the vehicle stability impact coefficient, which is a quantitative indicator used to assess the degree of impact of driving disturbance events on vehicle stability. Its calculation formula is shown below:

[0109] ;

[0110] CSI stands for Vehicle Stability Influence Coefficient. v(t) represents the time series of the vehicle's vertical acceleration (unit: m / s²); v(t) represents the time series of the vehicle's velocity (unit: m / s). , The start and end times of the event are represented, defining the time window (in seconds) for calculating CSI; L represents the vehicle wheelbase (in meters); and g represents the gravitational acceleration (9.81 m / s²).

[0111] The attribute parameters of driving interference events can also include long-term and short-term attributes. Long-term and short-term attributes refer to the duration of the impact of the event on the vehicle's driving status or driving behavior over time.

[0112] The cloud stores the determined attribute parameters in a database associated with the global driving impact event marker map, thereby enabling the updating of the global driving impact event marker map.

[0113] In an alternative embodiment, the map updating method provided by the present invention may further include the following steps:

[0114] When the validity period of a traffic interference event in the global traffic impact event marker map expires, the event level of the corresponding traffic interference event is reduced, and an event detection task is issued to vehicles that are about to pass through the location of the traffic interference event.

[0115] When the detection result of the event detection task is received and the result indicates that the driving interference event no longer exists, the driving interference event will be deleted from the global driving impact event marker map.

[0116] Driving interference events have an associated expiration period, which describes the duration of the event's impact. When a driving interference event reaches its expiration period, the cloud automatically downgrades the event's level and issues an event detection task to vehicles about to pass the event's location. This task requires vehicles to use their sensor systems (such as cameras, radar, IMUs, etc.) to detect whether the driving interference event still exists as they pass the location. The cloud receives the detection results from the vehicles. These results may indicate that the driving interference event still exists or has disappeared. If the detection results indicate that the driving interference event has disappeared, the cloud removes the event from the global driving impact event marking map. This ensures that only currently valid driving interference events are displayed on the map, thus providing drivers with the most accurate information.

[0117] For example, a "Flooding Event L3" related to heavy rain is marked on a road segment. The validity period of this event is set to "rainfall duration + 2 hours". This is to ensure that the road segment remains marked for a period even after the rain stops, as the floodwater may not recede immediately. After the validity period expires, or if no effective rainfall is detected in the area for 72 consecutive hours, the event is not directly deleted but automatically downgraded to "Flooding Event L1 (Pending Verification)". Simultaneously, a "sampling detection" task is issued to a small number of vehicles about to pass through this road segment. This task requires these vehicles to collect data using their onboard sensors (such as cameras, IMUs, etc.) to verify whether the flooding event no longer exists. If the reported sampling detection data (such as image semantic analysis showing a dry road surface, and IMU feedback indicating no dynamic changes in vehicles caused by flooding) all show a dry road surface, the event will be finally removed or archived as historical data. This dynamic lifecycle management ensures that the information in the global driving impact event marking map is timely and accurate.

[0118] In an alternative embodiment, the map updating method provided by the present invention may further include the following steps:

[0119] When multiple negative feedback results are received for a specific vehicle model regarding the control strategy for the same type of driving interference event, the control strategy update operation is performed, and the updated control strategy is sent to the corresponding vehicle of that vehicle model.

[0120] In this implementation, when the cloud receives multiple negative feedback results from the control strategy for a specific vehicle model targeting similar driving interference events, it means that these vehicles have found the current control strategy to be ineffective or have certain problems in practical applications. At this time, the cloud will perform a control strategy update operation to optimize or adjust the existing strategy. After the update is complete, the cloud will distribute the new control strategy to the vehicles corresponding to that vehicle model.

[0121] In an alternative embodiment, the map updating method provided by the present invention may further include the following steps:

[0122] If multiple negative feedback results are received regarding the latest control policy within a preset time period after the policy is issued, the event level of the corresponding driving interference event will be adjusted.

[0123] In this embodiment, if the cloud receives multiple negative feedback execution results for the latest control policy within a preset time period after issuing the latest control policy, it indicates that the current control policy is still not effective enough. At this time, the event level of the corresponding driving interference event can be adjusted to the highest level.

[0124] To further explain the working principle of the above-mentioned reporting decision-making mechanism and strategy iteration closed loop, the following specific implementation methods are provided, taking into account the characteristics of different vehicle models.

[0125] Three Z-axis amplitude thresholds were defined for turbulence events:

[0126] Normal range: Amplitude ≤ 0.5cm. Within this range, the vehicle's driving condition is in a comfortable range and no special treatment is required.

[0127] Physically controllable range: 0.5cm < amplitude ≤ 1.0cm. This range indicates that bumps have already affected comfort, but for vehicles equipped with advanced chassis, comfort can theoretically be improved through active adjustments.

[0128] Additional control / strategy failure range: Amplitude > 1.0 cm. This range indicates that the turbulence is very severe, conventional active adjustment strategies may fail, or strategy iteration is required.

[0129] Two types of vehicles were defined:

[0130] Vehicle A (Advanced Chassis Model): Equipped with active air suspension, the goal of which is to suppress the final amplitude of all controllable bump events to within 1.0 cm.

[0131] Vehicle B (standard chassis model): Equipped only with passive coil spring suspension, without active adjustment capability.

[0132] Vehicle A and Vehicle B passed through the same bump event location P one after the other. This bump event has been initially marked as "bump level L3" on the driving impact event marking map.

[0133] For vehicle A:

[0134] When vehicle A approaches position P, the control strategy corresponding to the bump event is executed, and the damping and stiffness of the suspension are adjusted in advance.

[0135] Vehicle A passes position P, and its IMU sensor records the actual amplitude after active adjustment. At this point, a strategy iteration decision is triggered:

[0136] Strategy success: If the actual amplitude is successfully suppressed to 0.8 cm (within the target range of 0.5-1.0 cm), the strategy is marked as effective. This "positive feedback" data will be used to strengthen the confidence of the current control strategy, and since the result is as expected, it does not need to be reported to reduce data redundancy.

[0137] Strategy Failure: If the actual amplitude is 1.2cm (exceeding the target upper limit of 1.0cm), this will trigger a "strategy iteration" process. This "negative feedback" (i.e., "the current strategy cannot suppress L3 bumps within 1.0cm") will be treated as high-value data and sent to the cloud. After receiving multiple negative feedback results from vehicle model A regarding this bump event, the cloud will update the control strategy and distribute it to all vehicle model A vehicles via OTA.

[0138] If, after receiving the updated strategy, vehicle A passes through location P again and its actual vibration amplitude still cannot be reduced to below 1.0 cm, a final determination can be made: the physical impact intensity at this location has exceeded the physical controllable limit of vehicle A's active suspension. In this case, the strategy will no longer be optimized; instead, the map database will be corrected, increasing the bump level of the bump event at location P from L3 to L4 (extreme level), and marking it as "Advanced active suspension still cannot completely suppress it."

[0139] For vehicle B:

[0140] As vehicle B passes position P, its IMU records the raw physical amplitude, e.g., 1.5 cm, without any adjustment, since there is no active suspension.

[0141] When vehicle B prepares to report this data, it reads its own characteristic label ("standard chassis"). Since vehicle B lacks active adjustment capabilities, the 1.5cm amplitude data it reports has low information gain for the core objective of "control strategy iteration" (because it cannot provide feedback on the effectiveness of the strategy). Therefore, unless point P is a completely new point not recorded on the map, it will likely suppress this reporting, thereby greatly reducing duplicate data from low-configuration models that are of little value for strategy optimization.

[0142] As can be seen from this implementation, the system architecture of this invention is not a simple "data collection-processing" system, but a highly intelligent self-learning and self-regulating ecosystem. By distinguishing vehicle characteristics, it achieves valuable and selective data reporting, greatly improving the system's operating efficiency. More importantly, it constructs a perfect closed loop from "map-guided strategy" to "strategy effect feedback to correct the map and strategy itself," enabling the entire system's perception capabilities and control level to continuously and accurately iterate and evolve in the real world.

[0143] This invention, through statistical analysis of received multi-vehicle crowdsourced data, effectively filters out driving interference events reported multiple times at the same location. This verification mechanism based on multi-source data ensures the authenticity and reliability of driving interference events, avoiding map data errors caused by false reports from a single vehicle. Based on the filtered driving interference events to be marked, the global driving impact event marking map is updated, enabling the map to reflect the latest road condition information in real time. This dynamic update mechanism ensures the timeliness of map data, providing users with the most accurate road condition information.

[0144] Through the comprehensive analysis from both the vehicle and cloud perspectives described above, this invention, with its unique system architecture, achieves significant technical advantages in driving safety, functional expansion, and deployment costs, realizing a synergistic and efficient overall effect, specifically manifested as follows:

[0145] The newly added "Chassis Map" function breaks through the limitations of traditional maps. Existing technologies only describe the geometric and topological attributes of roads, lacking dimensions that support chassis control based on driving sensations. This invention constructs a dynamically updated driving influence map layer, quantifies physical events during driving (such as bumps and sideslips) through a multimodal VLA model, generates standardized indicators (such as the vehicle stability coefficient), and aggregates them to the cloud via a crowdsourcing model. This innovation enables precise instructions to be received tens of meters before driving interference events occur, achieving a leap from "passive response" to "active prediction," revolutionarily improving driving comfort and handling stability.

[0146] This invention constructs a multi-layered security protection system to achieve proactive risk prediction. Addressing the shortcomings of existing technologies, such as the difficulty in detecting recurring risks using real-time snapshot modes and insufficient robustness in GNSS failure positioning, this invention employs a three-pronged approach: post-hoc detection to uncover patterned risks in specific scenarios; using a driving impact map (i.e., a map marking driving impact events) as prior knowledge to provide crucial compensation information in the event of sensor failure; and utilizing bump sequence matching to achieve independent positioning in the event of GNSS failure. This system, through collective intelligence, achieves advance prediction of predictable risks, awareness of fixed risks even in the event of sensor failure, and bump-based positioning in the event of GNSS failure, forming a deep redundancy security guarantee unmatched by existing technologies.

[0147] Significantly reducing system deployment and operation costs, and promoting large-scale commercialization. Addressing the high operational and hardware costs associated with existing technologies that rely on large-scale data backhaul and costly SLAM positioning, this invention implements three optimizations: filtering redundant data at the edge through intelligent reporting decisions; transforming uploaded content from raw data into semantic tags or anonymized image fragments using a federated learning architecture; and employing a lightweight GNSS compensation scheme to avoid dependence on LiDAR and high-performance chips. This results in a reduction of tens of thousands of times in data upload volume per vehicle and an order of magnitude reduction in positioning compensation hardware and computing power costs, enabling the system to be deployed on a large scale in mass-produced consumer vehicles at extremely low marginal costs, truly achieving technology democratization.

[0148] Figure 4 A schematic diagram of an embodiment of the map application and updating device of the present invention is shown. Figure 4 As shown, the device 400 includes a judgment module 410 and an application module 420.

[0149] The judgment module is used to match the vehicle's current location with the local driving impact event marker map to determine whether there are driving interference events within a preset distance in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle.

[0150] The application module is used to control and / or locate the vehicle based on the driving interference events if they exist. Driving interference events refer to events that affect the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during vehicle operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

[0151] In one alternative approach, the application module is specifically used for:

[0152] From the map data of the local driving impact event marker map, query the control strategy corresponding to the driving interference event. The map data contains control strategy information related to the driving interference event.

[0153] When the vehicle travels to the location corresponding to the traffic interference event, the vehicle is controlled according to the control strategy.

[0154] In one alternative approach, the application module is specifically used for:

[0155] From the map data of the local driving impact event marker map, query the attribute parameters corresponding to the driving interference events. The map data contains attribute parameter information related to driving interference events.

[0156] When the vehicle approaches the location corresponding to the driving interference event, the vehicle dynamic control system is adjusted in advance based on the attribute parameters.

[0157] In one alternative approach, the application module is specifically used for:

[0158] From the map data of the local driving impact event marker map, query the driving interference sequence data corresponding to the driving interference event. The map data contains driving interference sequence data information related to the driving interference event. The driving interference sequence data is organized in the form of a location sequence, and each location point is associated with the characteristic data of the driving interference event.

[0159] Monitor vehicle driving status information and construct real-time driving interference sequence data;

[0160] The real-time driving interference sequence data is matched with the driving interference sequence data, and the vehicle is located based on the matching results.

[0161] In one alternative approach, the decision module is specifically used for:

[0162] When the vehicle's sensor functions are limited, the vehicle's current location is matched with a local driving impact event marker map to determine whether there are driving interference events within a preset distance range in front of the vehicle.

[0163] In an alternative embodiment, the map application and updating device of the present invention is further used for:

[0164] When a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0165] The driving interference events to be reported and their corresponding semantic tags are associated and uploaded to the cloud so that the cloud can analyze the multi-vehicle crowdsourced data to update the global driving impact event tagging map.

[0166] In an alternative embodiment, the map application and updating device of the present invention is further used for:

[0167] When a traffic interference event to be reported is detected, the corresponding event reporting conditions are determined according to the vehicle type;

[0168] Determine whether the traffic interference event to be reported meets the event reporting conditions;

[0169] If the event reporting conditions are met, then semantic labels for the driving interference events to be reported are generated based on the multimodal perception data of the driving interference events to be reported and the local perception model.

[0170] In an alternative embodiment, the map application and updating device of the present invention is further used for:

[0171] When a traffic interference event to be reported is detected, the geographical area of ​​the traffic interference event to be reported on the local traffic impact event marker map is determined.

[0172] Search within the geographic area for whether there are any labeled traffic interference events that meet the preset similarity criteria with the traffic interference event to be reported;

[0173] If it exists, the reporting of the traffic interference event to be reported is cancelled; otherwise, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0174] In an alternative embodiment, the map application and updating device of the present invention is further used for:

[0175] When a traffic interference event to be reported occurs in an area covered by high-precision satellite signals, traffic interference sequence data for the event is generated based on the high-precision satellite signals.

[0176] When a traffic interference event to be reported occurs in a region where high-precision satellite signals are lost, traffic interference sequence data for the event is generated based on the inertial measurement unit signal.

[0177] The traffic interference events to be reported, along with their corresponding semantic tags and traffic interference sequence data, are uploaded to the cloud.

[0178] This invention matches the current location with a local driving interference event marker map to predict in advance whether driving interference events exist within a preset distance range ahead. The vehicle can obtain relevant information before an interference event occurs and react in advance, thereby reducing the risk caused by sudden interference events. The local driving interference event marker map serves as "prior knowledge," providing compensation information when real-time sensors fail or signal interference occurs. Even if some sensor data is inaccurate, the vehicle can still refer to the map marker information to make decisions, significantly improving the robustness and reliability of the driving assistance system. Control and / or positioning adjustments are made to the vehicle based on driving interference events. This improves the accuracy and stability of vehicle positioning, providing more reliable support for autonomous driving and advanced driver assistance systems. This map application and update method significantly enhances the vehicle's positioning and decision-making capabilities in complex environments through techniques such as early detection of driving interference events, improved robustness of the driving assistance system, and optimized vehicle control and positioning accuracy.

[0179] Figure 5 A schematic diagram of an embodiment of the map updating device of the present invention is shown. Figure 5 As shown, the device 500 includes a screening module 510 and an update module 520.

[0180] The filtering module is used to perform statistical analysis on the received multi-vehicle crowdsourcing data, filter out driving interference events that are reported multiple times at the same location, and use them as driving interference events to be marked.

[0181] The update module is used to update the global traffic impact event labeling map based on the traffic interference events to be labeled.

[0182] In one alternative approach, the update module is specifically used for:

[0183] Based on multi-vehicle crowdsourced data, the attribute parameters of the driving interference events to be labeled are determined;

[0184] The attribute parameters are stored in a database associated with the global driving impact event marker map to update the global driving impact event marker map;

[0185] The attribute parameters include at least one of the following: event type, event level, vehicle safety and performance impact parameters, and validity period. The vehicle safety and performance impact parameters are quantitative indicators of the degree of impact of driving interference events on vehicle driving status or driving behavior. The validity period refers to the time range during which the driving interference event has an impact, used to describe the duration of the impact of the event. The event level refers to the severity of the driving interference event, used to quantify the impact of different driving interference events on vehicle driving safety and comfort.

[0186] In one alternative embodiment, the map updating device of the present invention is further configured to:

[0187] When the validity period of a traffic interference event in the global traffic impact event marker map expires, the event level of the corresponding traffic interference event is reduced, and an event detection task is issued to vehicles that are about to pass through the location of the traffic interference event.

[0188] When the detection result of the event detection task is received and the result indicates that the driving interference event no longer exists, the driving interference event will be deleted from the global driving impact event marker map.

[0189] In one alternative embodiment, the map updating device of the present invention is further configured to:

[0190] When multiple negative feedback results are received for a specific vehicle model regarding the control strategy for the same type of driving interference event, the control strategy update operation is performed, and the updated control strategy is sent to the corresponding vehicle of that vehicle model.

[0191] In one alternative embodiment, the map updating device of the present invention is further configured to:

[0192] If multiple negative feedback results are received regarding the latest control policy within a preset time period after the policy is issued, the event level of the corresponding driving interference event will be adjusted.

[0193] This invention, through statistical analysis of received multi-vehicle crowdsourced data, effectively filters out driving interference events reported multiple times at the same location. This verification mechanism based on multi-source data ensures the authenticity and reliability of driving interference events, avoiding map data errors caused by false reports from a single vehicle. Based on the filtered driving interference events to be marked, the global driving impact event marking map is updated, enabling the map to reflect the latest road condition information in real time. This dynamic update mechanism ensures the timeliness of map data, providing users with the most accurate road condition information.

[0194] Figure 6 The diagram shows a structural schematic of an embodiment of the map application and update device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the map application and update device.

[0195] like Figure 6 As shown, the map application and update device may include: a processor 602, a communications interface 604, a memory 606, and a communication bus 608.

[0196] The processor 602, communication interface 604, and memory 606 communicate with each other via communication bus 608. Communication interface 604 is used to communicate with other network elements, such as clients or other servers. The processor 602 executes program 610, specifically performing the relevant steps described in the embodiments for map application and update methods.

[0197] Specifically, program 610 may include program code, which includes computer-executable instructions.

[0198] Processor 602 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The map application and update device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0199] Memory 606 is used to store program 610. Memory 606 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0200] Specifically, program 610 can be called by processor 602 to enable the map application and update device to perform the following operations:

[0201] The vehicle's current location is matched with a local driving impact event marker map to determine whether there are driving interference events within a preset distance in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle.

[0202] If a driving interference event exists, the vehicle will be controlled and / or located based on the driving interference event. A driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during the vehicle's operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

[0203] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0204] From the map data of the local driving impact event marker map, query the control strategy corresponding to the driving interference event. The map data contains control strategy information related to the driving interference event.

[0205] When the vehicle travels to the location corresponding to the traffic interference event, the vehicle is controlled according to the control strategy.

[0206] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0207] From the map data of the local driving impact event marker map, query the attribute parameters corresponding to the driving interference events. The map data contains attribute parameter information related to driving interference events.

[0208] When the vehicle approaches the location corresponding to the driving interference event, the vehicle dynamic control system is adjusted in advance based on the attribute parameters.

[0209] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0210] From the map data of the local driving impact event marker map, query the driving interference sequence data corresponding to the driving interference event. The map data contains driving interference sequence data information related to the driving interference event. The driving interference sequence data is organized in the form of a location sequence, and each location point is associated with the characteristic data of the driving interference event.

[0211] Monitor vehicle driving status information and construct real-time driving interference sequence data;

[0212] The real-time driving interference sequence data is matched with the driving interference sequence data, and the vehicle is located based on the matching results.

[0213] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0214] When the vehicle's sensor functions are limited, the vehicle's current location is matched with a local driving impact event marker map to determine whether there are driving interference events within a preset distance range in front of the vehicle.

[0215] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0216] When a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0217] The driving interference events to be reported and their corresponding semantic tags are associated and uploaded to the cloud so that the cloud can analyze the multi-vehicle crowdsourced data to update the global driving impact event tagging map.

[0218] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0219] When a traffic interference event to be reported is detected, the corresponding event reporting conditions are determined according to the vehicle type;

[0220] Determine whether the traffic interference event to be reported meets the event reporting conditions;

[0221] If the event reporting conditions are met, then semantic labels for the driving interference events to be reported are generated based on the multimodal perception data of the driving interference events to be reported and the local perception model.

[0222] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0223] When a traffic interference event to be reported is detected, the geographical area of ​​the traffic interference event to be reported on the local traffic impact event marker map is determined.

[0224] Search within the geographic area for whether there are any labeled traffic interference events that meet the preset similarity criteria with the traffic interference event to be reported;

[0225] If it exists, the reporting of the traffic interference event to be reported is cancelled; otherwise, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0226] In an alternative manner, program 610 is invoked by processor 602 to cause the map application and update device to perform the following operations:

[0227] When a traffic interference event to be reported occurs in an area covered by high-precision satellite signals, traffic interference sequence data for the event is generated based on the high-precision satellite signals.

[0228] When a traffic interference event to be reported occurs in a region where high-precision satellite signals are lost, traffic interference sequence data for the event is generated based on the inertial measurement unit signal.

[0229] The traffic interference events to be reported, along with their corresponding semantic tags and traffic interference sequence data, are uploaded to the cloud.

[0230] This invention matches the current location with a local driving interference event marker map to predict in advance whether driving interference events exist within a preset distance range ahead. The vehicle can obtain relevant information before an interference event occurs and react in advance, thereby reducing the risk caused by sudden interference events. The local driving interference event marker map serves as "prior knowledge," providing compensation information when real-time sensors fail or signal interference occurs. Even if some sensor data is inaccurate, the vehicle can still refer to the map marker information to make decisions, significantly improving the robustness and reliability of the driving assistance system. Control and / or positioning adjustments are made to the vehicle based on driving interference events. This improves the accuracy and stability of vehicle positioning, providing more reliable support for autonomous driving and advanced driver assistance systems. This map application and update method significantly enhances the vehicle's positioning and decision-making capabilities in complex environments through techniques such as early detection of driving interference events, improved robustness of the driving assistance system, and optimized vehicle control and positioning accuracy.

[0231] Figure 7 The diagram shows a structural schematic of an embodiment of the map update device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the map update device.

[0232] like Figure 7 As shown, the map update device may include: a processor 702, a communications interface 704, a memory 706, and a communications bus 708.

[0233] The processor 702, communication interface 704, and memory 706 communicate with each other via communication bus 708. Communication interface 704 is used to communicate with other network elements such as clients or other servers. The processor 702 executes program 710, specifically performing the relevant steps described above in the map update method embodiment.

[0234] Specifically, program 710 may include program code, which includes computer-executable instructions.

[0235] The processor 702 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The map update device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0236] Memory 706 is used to store program 710. Memory 706 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0237] Specifically, program 710 can be called by processor 702 to cause the map update device to perform the following operations:

[0238] Statistical analysis was performed on the received multi-vehicle crowdsourcing data to filter out driving interference events that were reported multiple times at the same location, and these were designated as driving interference events to be labeled.

[0239] The global traffic impact event labeling map is updated based on the traffic interference events to be labeled.

[0240] In an alternative manner, program 710 is invoked by processor 702 to cause the map updating device to perform the following operations:

[0241] Based on multi-vehicle crowdsourced data, the attribute parameters of the driving interference events to be labeled are determined;

[0242] The attribute parameters are stored in a database associated with the global driving impact event marker map to update the global driving impact event marker map;

[0243] The attribute parameters include at least one of the following: event type, event level, vehicle safety and performance impact parameters, and validity period. The vehicle safety and performance impact parameters are quantitative indicators of the degree of impact of driving interference events on vehicle driving status or driving behavior. The validity period refers to the time range during which the driving interference event has an impact, used to describe the duration of the impact of the event. The event level refers to the severity of the driving interference event, used to quantify the impact of different driving interference events on vehicle driving safety and comfort.

[0244] In an alternative manner, program 710 is invoked by processor 702 to cause the map updating device to perform the following operations:

[0245] When the validity period of a traffic interference event in the global traffic impact event marker map expires, the event level of the corresponding traffic interference event is reduced, and an event detection task is issued to vehicles that are about to pass through the location of the traffic interference event.

[0246] When the detection result of the event detection task is received and the result indicates that the driving interference event no longer exists, the driving interference event will be deleted from the global driving impact event marker map.

[0247] In an alternative manner, program 710 is invoked by processor 702 to cause the map updating device to perform the following operations:

[0248] When multiple negative feedback results are received for a specific vehicle model regarding the control strategy for the same type of driving interference event, the control strategy update operation is performed, and the updated control strategy is sent to the corresponding vehicle of that vehicle model.

[0249] In an alternative manner, program 710 is invoked by processor 702 to cause the map updating device to perform the following operations:

[0250] If multiple negative feedback results are received regarding the latest control policy within a preset time period after the policy is issued, the event level of the corresponding driving interference event will be adjusted.

[0251] This invention, through statistical analysis of received multi-vehicle crowdsourced data, effectively filters out driving interference events reported multiple times at the same location. This verification mechanism based on multi-source data ensures the authenticity and reliability of driving interference events, avoiding map data errors caused by false reports from a single vehicle. Based on the filtered driving interference events to be marked, the global driving impact event marking map is updated, enabling the map to reflect the latest road condition information in real time. This dynamic update mechanism ensures the timeliness of map data, providing users with the most accurate road condition information.

[0252] Figure 8 A structural schematic diagram of an embodiment of the vehicle of the present invention is shown. (As shown) Figure 8 As shown, the vehicle 800 includes: sensors, cameras, one or more processors, and communication interfaces;

[0253] Sensors and cameras are used to collect multimodal sensing data;

[0254] The processor is used to execute the steps in the above embodiments of map application and update methods.

[0255] This invention matches the current location with a local driving interference event marker map to predict in advance whether driving interference events exist within a preset distance range ahead. The vehicle can obtain relevant information before an interference event occurs and react in advance, thereby reducing the risk caused by sudden interference events. The local driving interference event marker map serves as "prior knowledge," providing compensation information when real-time sensors fail or signal interference occurs. Even if some sensor data is inaccurate, the vehicle can still refer to the map marker information to make decisions, significantly improving the robustness and reliability of the driving assistance system. Control and / or positioning adjustments are made to the vehicle based on driving interference events. This improves the accuracy and stability of vehicle positioning, providing more reliable support for autonomous driving and advanced driver assistance systems. This map application and update method significantly enhances the vehicle's positioning and decision-making capabilities in complex environments through techniques such as early detection of driving interference events, improved robustness of the driving assistance system, and optimized vehicle control and positioning accuracy.

[0256] This invention provides a computer-readable storage medium storing at least one executable instruction that, when executed on a map application and update device / app, causes the map application and update device / app to perform the map application and update method in any of the above method embodiments.

[0257] Specifically, the executable instructions can be used to cause map applications and update devices / devices to perform the following operations:

[0258] The vehicle's current location is matched with a local driving impact event marker map to determine whether there are driving interference events within a preset distance in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle.

[0259] If a driving interference event exists, the vehicle will be controlled and / or located based on the driving interference event. A driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during the vehicle's operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

[0260] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0261] From the map data of the local driving impact event marker map, query the control strategy corresponding to the driving interference event. The map data contains control strategy information related to the driving interference event.

[0262] When the vehicle travels to the location corresponding to the traffic interference event, the vehicle is controlled according to the control strategy.

[0263] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0264] From the map data of the local driving impact event marker map, query the attribute parameters corresponding to the driving interference events. The map data contains attribute parameter information related to driving interference events.

[0265] When the vehicle approaches the location corresponding to the driving interference event, the vehicle dynamic control system is adjusted in advance based on the attribute parameters.

[0266] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0267] From the map data of the local driving impact event marker map, query the driving interference sequence data corresponding to the driving interference event. The map data contains driving interference sequence data information related to the driving interference event. The driving interference sequence data is organized in the form of a location sequence, and each location point is associated with the characteristic data of the driving interference event.

[0268] Monitor vehicle driving status information and construct real-time driving interference sequence data;

[0269] The real-time driving interference sequence data is matched with the driving interference sequence data, and the vehicle is located based on the matching results.

[0270] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0271] When the vehicle's sensor functions are limited, the vehicle's current location is matched with a local driving impact event marker map to determine whether there are driving interference events within a preset distance range in front of the vehicle.

[0272] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0273] When a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0274] The driving interference events to be reported and their corresponding semantic tags are associated and uploaded to the cloud so that the cloud can analyze the multi-vehicle crowdsourced data to update the global driving impact event tagging map.

[0275] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0276] When a traffic interference event to be reported is detected, the corresponding event reporting conditions are determined according to the vehicle type;

[0277] Determine whether the traffic interference event to be reported meets the event reporting conditions;

[0278] If the event reporting conditions are met, then semantic labels for the driving interference events to be reported are generated based on the multimodal perception data of the driving interference events to be reported and the local perception model.

[0279] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0280] When a traffic interference event to be reported is detected, the geographical area of ​​the traffic interference event to be reported on the local traffic impact event marker map is determined.

[0281] Search within the geographic area for whether there are any labeled traffic interference events that meet the preset similarity criteria with the traffic interference event to be reported;

[0282] If it exists, the reporting of the traffic interference event to be reported is cancelled; otherwise, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

[0283] In one alternative approach, executable instructions cause the map application and update device / device to perform the following operations:

[0284] When a traffic interference event to be reported occurs in an area covered by high-precision satellite signals, traffic interference sequence data for the event is generated based on the high-precision satellite signals.

[0285] When a traffic interference event to be reported occurs in a region where high-precision satellite signals are lost, traffic interference sequence data for the event is generated based on the inertial measurement unit signal.

[0286] The traffic interference events to be reported, along with their corresponding semantic tags and traffic interference sequence data, are uploaded to the cloud.

[0287] This invention matches the current location with a local driving interference event marker map to predict in advance whether driving interference events exist within a preset distance range ahead. The vehicle can obtain relevant information before an interference event occurs and react in advance, thereby reducing the risk caused by sudden interference events. The local driving interference event marker map serves as "prior knowledge," providing compensation information when real-time sensors fail or signal interference occurs. Even if some sensor data is inaccurate, the vehicle can still refer to the map marker information to make decisions, significantly improving the robustness and reliability of the driving assistance system. Control and / or positioning adjustments are made to the vehicle based on driving interference events. This improves the accuracy and stability of vehicle positioning, providing more reliable support for autonomous driving and advanced driver assistance systems. This map application and update method significantly enhances the vehicle's positioning and decision-making capabilities in complex environments through techniques such as early detection of driving interference events, improved robustness of the driving assistance system, and optimized vehicle control and positioning accuracy.

[0288] This invention provides another computer-readable storage medium storing at least one executable instruction that, when run on a map update device / apparatus, causes the map update device / apparatus to perform the map update method in any of the above method embodiments.

[0289] Specifically, the executable instructions can be used to cause the map update device / device to perform the following operations:

[0290] Statistical analysis was performed on the received multi-vehicle crowdsourcing data to filter out driving interference events that were reported multiple times at the same location, and these were designated as driving interference events to be labeled.

[0291] The global traffic impact event labeling map is updated based on the traffic interference events to be labeled.

[0292] In one alternative approach, executable instructions cause the map updating device / app to perform the following operations:

[0293] Based on multi-vehicle crowdsourced data, the attribute parameters of the driving interference events to be labeled are determined;

[0294] The attribute parameters are stored in a database associated with the global driving impact event marker map to update the global driving impact event marker map;

[0295] The attribute parameters include at least one of the following: event type, event level, vehicle safety and performance impact parameters, and validity period. The vehicle safety and performance impact parameters are quantitative indicators of the degree of impact of driving interference events on vehicle driving status or driving behavior. The validity period refers to the time range during which the driving interference event has an impact, used to describe the duration of the impact of the event. The event level refers to the severity of the driving interference event, used to quantify the impact of different driving interference events on vehicle driving safety and comfort.

[0296] In one alternative approach, executable instructions cause the map updating device / app to perform the following operations:

[0297] When the validity period of a traffic interference event in the global traffic impact event marker map expires, the event level of the corresponding traffic interference event is reduced, and an event detection task is issued to vehicles that are about to pass through the location of the traffic interference event.

[0298] When the detection result of the event detection task is received and the result indicates that the driving interference event no longer exists, the driving interference event will be deleted from the global driving impact event marker map.

[0299] In one alternative approach, executable instructions cause the map updating device / app to perform the following operations:

[0300] When multiple negative feedback results are received for a specific vehicle model regarding the control strategy for the same type of driving interference event, the control strategy update operation is performed, and the updated control strategy is sent to the corresponding vehicle of that vehicle model.

[0301] In one alternative approach, executable instructions cause the map updating device / app to perform the following operations:

[0302] If multiple negative feedback results are received regarding the latest control policy within a preset time period after the policy is issued, the event level of the corresponding driving interference event will be adjusted.

[0303] This invention, through statistical analysis of received multi-vehicle crowdsourced data, effectively filters out driving interference events reported multiple times at the same location. This verification mechanism based on multi-source data ensures the authenticity and reliability of driving interference events, avoiding map data errors caused by false reports from a single vehicle. Based on the filtered driving interference events to be marked, the global driving impact event marking map is updated, enabling the map to reflect the latest road condition information in real time. This dynamic update mechanism ensures the timeliness of map data, providing users with the most accurate road condition information.

[0304] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.

[0305] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0306] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.

[0307] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A map application and update method, characterized in that, Applied to the vehicle end, the method includes: The vehicle's current location is matched with a local driving impact event marker map to determine whether there are driving interference events within a preset distance in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle. If a driving interference event exists, the vehicle is controlled and / or located based on the driving interference event. The driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during vehicle operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

2. The method according to claim 1, characterized in that, The control and / or positioning of the vehicle based on the driving interference event includes: From the map data of the local driving interference event marker map, query the control strategy corresponding to the driving interference event, wherein the map data contains control strategy information related to the driving interference event; When the vehicle travels to the location corresponding to the traffic interference event, the vehicle is controlled according to the control strategy.

3. The method according to claim 1, characterized in that, The control and / or positioning of the vehicle based on the driving interference event includes: From the map data of the local driving interference event marker map, query the attribute parameters corresponding to the driving interference event. The map data contains attribute parameter information related to the driving interference event. When the vehicle approaches the location corresponding to the driving interference event, the vehicle dynamic control system is adjusted in advance based on the attribute parameters.

4. The method according to claim 1, characterized in that, The control and / or positioning of the vehicle based on the driving interference event includes: From the map data of the local driving impact event marker map, query the driving interference sequence data corresponding to the driving interference event. The map data contains driving interference sequence data information related to the driving interference event. The driving interference sequence data is organized in the form of a location sequence, and each location point is associated with the feature data of the driving interference event. Monitor vehicle driving status information and construct real-time driving interference sequence data; The real-time traffic interference sequence data is matched with the traffic interference sequence data, and the vehicle is located based on the matching result.

5. The method according to any one of claims 1-4, characterized in that, The step of matching the vehicle's current location with a local driving interference event marker map to determine whether there are driving interference events within a preset distance range in front of the vehicle includes: When the vehicle's sensor functions are limited, the vehicle's current position is matched with the local driving impact event marker map to determine whether there are driving interference events within a preset distance range in front of the vehicle.

6. The method according to any one of claims 1-4, characterized in that, The method further includes: When a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model. The reported traffic interference events and their corresponding semantic tags are associated and uploaded to the cloud so that the cloud can analyze the multi-vehicle crowdsourced data to update the global traffic impact event tagging map.

7. The method according to claim 6, characterized in that, When a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model, including: When a traffic interference event to be reported is detected, the corresponding event reporting conditions are determined according to the vehicle type; Determine whether the traffic interference event to be reported meets the event reporting conditions; If the event reporting conditions are met, then a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

8. The method according to claim 6, characterized in that, When a traffic interference event to be reported is detected, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model, including: When a traffic interference event to be reported is detected, the geographical area range of the traffic interference event to be reported on the local traffic impact event marking map is determined. Within the geographical area, search for whether there are any labeled traffic interference events that meet the preset similarity conditions with the traffic interference event to be reported; If it exists, the reporting of the traffic interference event to be reported is cancelled; otherwise, a semantic label for the traffic interference event to be reported is generated based on the multimodal perception data of the traffic interference event to be reported and the local perception model.

9. The method according to claim 6, characterized in that, The step of associating the reported traffic interference events with their corresponding semantic tags and uploading them to the cloud includes: When the traffic interference event to be reported occurs in the area covered by high-precision satellite signals, traffic interference sequence data for the event is generated based on the high-precision satellite signals; When the traffic interference event to be reported occurs in a high-precision satellite signal failure area, traffic interference sequence data for the event is generated based on the inertial measurement unit signal; The reported traffic interference events, their corresponding semantic tags, and traffic interference sequence data are associated and uploaded to the cloud.

10. A map updating method, characterized in that, Applied to the cloud, the method includes: Statistical analysis was performed on the received multi-vehicle crowdsourcing data to filter out driving interference events that were reported multiple times at the same location, and these were designated as driving interference events to be labeled. Based on the traffic interference events to be labeled, the global traffic impact event labeling map is updated.

11. The method according to claim 10, characterized in that, The update of the global driving impact event labeling map based on the driving interference events to be labeled includes: Based on the multi-vehicle crowdsourced data, the attribute parameters of the driving interference events to be labeled are determined; The attribute parameters are stored in a database associated with the global driving impact event marker map to update the global driving impact event marker map; The attribute parameters include at least one of event type, event level, vehicle safety and performance impact parameters, and validity period. The vehicle safety and performance impact parameters are quantitative indicators of the degree of influence of driving interference events on vehicle driving status or driving behavior. The validity period refers to the time range during which the driving interference event has an impact, used to describe the duration of the event's impact. The event level refers to the severity of the driving interference event, used to quantify the impact of different driving interference events on vehicle driving safety and comfort.

12. The method according to claim 10 or 11, characterized in that, The method further includes: When the validity period of a traffic interference event in the global traffic impact event marker map expires, the event level of the corresponding traffic interference event is reduced, and an event detection task is issued to vehicles that are about to pass through the location of the traffic interference event. When the detection result of the event detection task is received and the result indicates that the driving interference event no longer exists, the driving interference event is deleted from the global driving impact event marker map.

13. The method according to claim 10 or 11, characterized in that, The method further includes: When multiple negative feedback results are received for a specific vehicle model regarding the control strategy for the same type of driving interference event, the control strategy update operation is performed, and the updated control strategy is sent to the corresponding vehicle of that vehicle model.

14. The method according to claim 13, characterized in that, The method further includes: If multiple negative feedback results are received regarding the latest control policy within a preset time period after the policy is issued, the event level of the corresponding driving interference event will be adjusted.

15. A map application and updating device, characterized in that, The device includes: The judgment module is used to match the vehicle's current position with the local driving impact event marker map to determine whether there is a driving interference event within a preset distance range in front of the vehicle. The local driving impact event marker map is generated by analyzing multi-vehicle crowdsourced data in the cloud and sent to the vehicle. The application module is used to control and / or locate the vehicle based on the driving interference event if a driving interference event exists. The driving interference event refers to an event that affects the vehicle's driving status or driving behavior due to road conditions, environmental factors or other external factors during vehicle operation. The driving interference event marker map is used to record various driving interference events experienced by the vehicle.

16. A map updating device, characterized in that, The device includes: The filtering module is used to perform statistical analysis on the received multi-vehicle crowdsourcing data, filter out driving interference events that are reported multiple times at the same location, and use them as driving interference events to be marked. The update module is used to update the global driving impact event marking map based on the driving interference events to be marked.

Images