Driving behavior marking method, identification method, server, equipment and storage medium

Abstract

The invention relates to a driving behavior marking method, a driving behavior recognition method, a server, vehicle-mounted equipment and a computer readable storage medium. The method comprises the following steps: acquiring driving behavior evaluation data uploaded by first vehicle-mounted equipment; the driving behavior evaluation data comprises surrounding vehicle license plates and evaluation results; according to the evaluation result, updating the driving behavior labels corresponding to the license plates of the surrounding vehicles; obtaining a label query request sent by second vehicle-mounted equipment; the label query request carries at least one target vehicle license plate; and querying a target driving behavior tag corresponding to the target vehicle license plate, and feeding back the target driving behavior tag to the second vehicle-mounted device to indicate the second vehicle-mounted device to display the target driving behavior tag in the current man-machine interface. According to the method, the vehicle with the bad driving behavior can be recognized, other vehicles are reminded to pay attention in real time, the probability of traffic accidents is reduced, and the overall safety of the road is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a driving behavior marking method, a driving behavior identification method, a server, a vehicle-mounted device, and a computer-readable storage medium. Background Art

[0002] At present, when a vehicle is driving on the road, the bad driving behavior of surrounding vehicles will affect the normal driving of the vehicle and may also cause safety accidents. At present, the perception information of surrounding vehicles is often limited to information such as speed and distance. The driver cannot know the driving behavior habits of surrounding vehicles, making it difficult to discover and respond to safety hazards in a timely manner. Summary of the invention

[0003] Based on this, it is necessary to provide a driving behavior marking method, a driving behavior identification method, a server, a vehicle-mounted device and a computer-readable storage medium to address the above-mentioned technical problems, so that the driver can know the driving behavior habits of surrounding vehicles and make safer and more reasonable driving decisions.

[0004] In a first aspect, the present application provides a driving behavior marking method, comprising:

[0005] Acquire driving behavior evaluation data uploaded by the first vehicle-mounted device; the driving behavior evaluation data includes license plates of surrounding vehicles and evaluation results;

[0006] According to the evaluation results, the driving behavior labels corresponding to the license plates of surrounding vehicles are updated;

[0007] Obtaining a tag query request sent by the second vehicle-mounted device; the tag query request carries at least one target vehicle license plate;

[0008] The target driving behavior tag corresponding to the target vehicle license plate is queried, and the target driving behavior tag is fed back to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior tag in the current human-machine interface.

[0009] In one embodiment, based on the evaluation results, the driving behavior labels corresponding to the license plates of surrounding vehicles are updated, including:

[0010] Query the driving behavior labels and driving behavior records corresponding to the license plates of surrounding vehicles; the driving behavior labels include any one of bad driving labels, good driving labels, and unknown driving labels; the driving behavior records include at least one of the number of good behaviors and the number of bad behaviors;

[0011] If the evaluation result indicates that the surrounding vehicles have bad driving behaviors, the driving behavior labels corresponding to the license plates of the surrounding vehicles are updated to bad driving labels, and the effective time of the bad driving labels is updated according to the number of bad behaviors corresponding to the license plates of the surrounding vehicles within the first set time period;

[0012] If the queried driving behavior label is a good driving label, and the evaluation result indicates that the surrounding vehicles have not committed bad driving behaviors, the effective time of the good driving label is updated according to the number of bad behaviors corresponding to the license plates of the surrounding vehicles in the second set time period and the number of good behaviors corresponding to the license plates of the surrounding vehicles in the third set time period;

[0013] If the queried driving behavior label is an unknown driving label, the evaluation result indicates that the surrounding vehicles have not engaged in bad driving behavior, the number of bad behaviors corresponding to the surrounding vehicle license plates within the second set time period is not greater than the first threshold, and the number of good behaviors corresponding to the surrounding vehicle license plates within the third set time period is not less than the second threshold, then the driving behavior label corresponding to the surrounding vehicle license plates is updated to a good driving label.

[0014] In one embodiment, the method further comprises:

[0015] Obtaining a complaint request sent by a third vehicle-mounted device; the complaint request includes the current vehicle license plate and the license plate application time;

[0016] Update the driving behavior record corresponding to the current vehicle license plate according to the license plate application time;

[0017] Re-evaluate the driving behavior tag of the current vehicle license plate based on the updated driving behavior record.

[0018] In one embodiment, the driving behavior evaluation data further includes evaluation materials; before updating the driving behavior labels corresponding to the license plates of surrounding vehicles according to the evaluation results, the method further includes:

[0019] Verify the evaluation results based on the evaluation materials;

[0020] After the verification is passed, the step of updating the driving behavior labels corresponding to the license plates of surrounding vehicles is performed according to the evaluation results.

[0021] In a second aspect, the present application also provides a driving behavior recognition method, comprising:

[0022] Obtain environmental information collected by sensors;

[0023] Based on environmental information, identify the license plates, lane lines and speed limit information of surrounding vehicles, and identify the turn signal status, vehicle location and speed information of surrounding vehicles;

[0024] Based on the lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times, the trained driving behavior prediction model is used to make predictions and obtain the evaluation results of surrounding vehicles;

[0025] The surrounding vehicle license plates and evaluation results are uploaded to the server as driving behavior evaluation data to instruct the server to update the driving behavior labels corresponding to the surrounding vehicle license plates according to the evaluation results.

[0026] In one embodiment, the driving behavior evaluation data also includes evaluation materials; and the method further includes:

[0027] Obtain the license plates and evaluation results of surrounding vehicles input by the driver through text or voice;

[0028] Obtain evaluation materials from environmental information collected by sensors;

[0029] The license plates of surrounding vehicles, evaluation results and evaluation materials are uploaded to the server as driving behavior evaluation data.

[0030] In one embodiment, the method further comprises:

[0031] According to the license plates of surrounding vehicles and the vehicle positions of surrounding vehicles, vehicle graphics corresponding to the license plates of surrounding vehicles are displayed in the human-computer interaction interface;

[0032] Send a tag query request to the server; the tag query request carries the license plates of surrounding vehicles to instruct the server to query and feedback the driving behavior tags corresponding to the license plates of surrounding vehicles;

[0033] On the vehicle graphic, the driving behavior labels corresponding to the license plates of surrounding vehicles are displayed.

[0034] In a third aspect, the present application further provides a server, the server being communicatively connected to a plurality of vehicle-mounted devices, the server comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0035] Acquire driving behavior evaluation data uploaded by the first vehicle-mounted device; the driving behavior evaluation data includes license plates of surrounding vehicles and evaluation results;

[0036] According to the evaluation results, the driving behavior labels corresponding to the license plates of surrounding vehicles are updated;

[0037] Obtaining a tag query request sent by the second vehicle-mounted device; the tag query request carries at least one target vehicle license plate;

[0038] The target driving behavior tag corresponding to the target vehicle license plate is queried, and the target driving behavior tag is fed back to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior tag in the current human-machine interface.

[0039] In a fourth aspect, the present application further provides a vehicle-mounted device, the vehicle-mounted device is communicatively connected to a server, the vehicle-mounted device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0040] Obtain environmental information collected by sensors;

[0041] Based on environmental information, identify the license plates, lane lines and speed limit information of surrounding vehicles, and identify the turn signal status, vehicle location and speed information of surrounding vehicles;

[0042] Based on the lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times, the trained driving behavior prediction model is used to make predictions and obtain the evaluation results of surrounding vehicles;

[0043] The surrounding vehicle license plates and evaluation results are uploaded to the server as driving behavior evaluation data to instruct the server to update the driving behavior labels corresponding to the surrounding vehicle license plates according to the evaluation results.

[0044] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method of the first aspect or the second aspect above are implemented.

[0045] The above-mentioned driving behavior marking method, driving behavior identification method, server, vehicle-mounted device and computer-readable storage medium obtain driving behavior evaluation data uploaded by the first vehicle-mounted device; the driving behavior evaluation data includes surrounding vehicle license plates and evaluation results; according to the evaluation results, the driving behavior labels corresponding to the surrounding vehicle license plates are updated; the label query request sent by the second vehicle-mounted device is obtained; the label query request carries at least one target vehicle license plate; the target driving behavior label corresponding to the target vehicle license plate is queried, and the target driving behavior label is fed back to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior label in the current human-computer interface. Through the above-mentioned method, the driving behavior label corresponding to each vehicle license plate is updated in time according to the data uploaded by the vehicle-mounted device, and the driving behavior labels of the surrounding vehicles are displayed in the human-computer interface of the vehicle-mounted device that issues the request, so that vehicles with bad driving behavior can be identified, and other vehicles can be reminded in real time, so that the driver can know the driving behavior habits of the surrounding vehicles, so as to make safer and more reasonable driving decisions, reduce the probability of traffic accidents, and improve the overall safety of the road. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0047] FIG1 is a diagram of an application environment of a driving behavior marking method according to an embodiment;

[0048] FIG2 is a schematic diagram of a process flow of a driving behavior marking method in one embodiment;

[0049] FIG3 is a schematic diagram of a flow chart of a driving behavior marking method in another embodiment;

[0050] FIG4 is a schematic diagram of a prediction model in one embodiment;

[0051] FIG5 is a schematic diagram showing the determination of speeding, lane-occupying driving, right-hand overtaking, and emergency braking in one embodiment;

[0052] FIG6 is a schematic diagram showing the determination of lane change without turning on the turn signal and lane change on a solid line in one embodiment;

[0053] FIG7 is a schematic diagram of determining frequent lane changes in one embodiment;

[0054] FIG8 is a schematic diagram of a human-computer interaction interface in one embodiment;

[0055] FIG9 is a schematic diagram of a flow chart of a driving behavior marking method in yet another embodiment;

[0056] FIG10 is a diagram showing the internal structure of a server in one embodiment;

[0057] FIG. 11 is a diagram showing the internal structure of a vehicle-mounted device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] It is understandable that currently, the user's discomfort index is generally determined based on the driver's emotional changes and vehicle movement changes, the vehicle risk cause is confirmed based on the speed of the vehicle to be identified, and the vehicle with reckless behavior is identified based on the determined vehicle risk cause and discomfort index. This method has the following problems:

[0060] The reckless evaluation is triggered by the user's emotions, but the driver's emotions are not entirely triggered by reckless behavior; and the reckless behavior of surrounding vehicles does not necessarily cause the driver's emotions to change. Therefore, this method has the problem of mislabeling or missing labels. The basis for reckless behavior is only based on the change of vehicle speed, but the actual trigger of reckless behavior may be caused by a stable vehicle cutting in line. If other vehicles change speed when triggered, the evaluated vehicle with reckless behavior will be wrong. Therefore, this method has the problem of mislabeling. The basis for reckless behavior is only based on the change of vehicle speed, but in actual reckless behavior, there are not only sudden acceleration and deceleration, but also driving on the line, frequent lane changes, etc. Therefore, this method can only identify a few bad driving behaviors. Reckless behavior can only evaluate the vehicle in front, which has limitations. The evaluation is limited to reckless and non-reckless; the label is single. The vehicle with the reckless label may have changed owners and cannot be appealed, which lacks objectivity and fairness. The reckless label evaluated is not time-effective and cannot adapt to the changes in driving conditions. The accuracy of the label is low.

[0061] Based on this, an embodiment of the present application provides a driving behavior marking method to solve the above problems.

[0062] The driving behavior labeling method provided in the embodiment of the present application can be applied in the application environment shown in FIG. 1 . Among them, the vehicle-mounted device 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the vehicle-mounted device 102 is an intelligent terminal device set on the vehicle; it obtains environmental information through sensors installed on the vehicle, uses environmental information to predict the evaluation results of surrounding vehicles, and uploads the vehicle license plate and the evaluation results to the server 104. The server 104 updates the driving behavior label corresponding to each vehicle license plate according to the data uploaded by each vehicle-mounted device 102. The vehicle-mounted device 102 sends a label query request to the server 104, and the server 104 queries the driving behavior label and feeds it back to the vehicle-mounted device 102. The vehicle-mounted device 102 displays the driving behavior label in the current human-computer interface, so that the driver can know the driving behavior habits of surrounding vehicles, so as to make safer and more reasonable driving decisions. The vehicle-mounted device 102 can communicate with the server 104 through the Internet of Vehicles. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0063] In an exemplary embodiment, as shown in FIG2 , a driving behavior marking method is provided, and the method is applied to the server 104 in FIG1 as an example for explanation, including:

[0064] Step 202, obtaining driving behavior evaluation data uploaded by the first vehicle-mounted device; the driving behavior evaluation data includes license plates of surrounding vehicles and evaluation results.

[0065] Among them, the first vehicle-mounted device, the second vehicle-mounted device and the third vehicle-mounted device proposed in the embodiment of the present application are any one of the multiple vehicle-mounted devices that are communicatively connected to the server. The first vehicle-mounted device, the second vehicle-mounted device and the third vehicle-mounted device can be the same vehicle-mounted device or different vehicle-mounted devices, and this embodiment does not impose any restrictions on this.

[0066] The first vehicle-mounted device can perform the following steps: obtain environmental information collected by sensors; identify the license plates, lane lines and speed limit information of surrounding vehicles based on the environmental information, and identify the turn signal status, vehicle position and speed information of surrounding vehicles; use the trained driving behavior prediction model to make predictions based on the lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times to obtain evaluation results of surrounding vehicles; upload the license plates of surrounding vehicles and evaluation results to the server as driving behavior evaluation data. It can be understood that after identifying the license plates and evaluation results of surrounding vehicles, each vehicle-mounted device that is connected to the server in communication uploads the driving behavior evaluation data to the server.

[0067] The license plates of surrounding vehicles refer to the license plates of other vehicles within the detection range of the vehicle where the first vehicle-mounted device is located. The evaluation result includes the driving behavior type, and the driving behavior type is any one of speeding, occupying lane driving, overtaking on the right, emergency braking, changing lanes without turning on the turn signal, frequent lane changes, changing lanes on a solid line, and non-bad driving behaviors. The driving behavior type may also include other bad driving behaviors, which are not limited in this embodiment.

[0068] Among them, speeding refers to the surrounding vehicles driving in excess of the speed limit stipulated on the road; occupying lanes refers to the surrounding vehicles occupying non-motorized vehicle lanes, emergency lanes, etc.; overtaking on the right refers to the surrounding vehicles overtaking from the right when not permitted; emergency braking refers to the sudden braking of surrounding vehicles without warning, which may easily lead to rear-end collisions; changing lanes without turning on the turn signal refers to the surrounding vehicles changing lanes without turning on the turn signal in advance; frequent lane changes and solid line lane changes refer to the surrounding vehicles changing lanes frequently and irregularly; non-bad driving behavior refers to the surrounding vehicles not engaging in the aforementioned bad driving behaviors.

[0069] Step 204: Update the driving behavior labels corresponding to the license plates of surrounding vehicles according to the evaluation results.

[0070] The server manages the driving behavior labels corresponding to each vehicle license plate. In a specific implementation, the corresponding driving behavior labels are queried from the managed label data according to the surrounding vehicle license plates, and the queried driving behavior labels are updated according to the set update strategy based on the evaluation results, and the updated driving behavior labels are stored and managed. Optionally, the category of the driving behavior label can be updated, and the effective time of the driving behavior label can also be updated. The driving behavior label includes any one of a bad driving label, a good driving label, and an unknown driving label.

[0071] Step 206, obtaining a tag query request sent by the second vehicle-mounted device; the tag query request carries at least one target vehicle license plate.

[0072] The target vehicle license plate refers to the license plate of other vehicles within the detection range of the vehicle where the second vehicle-mounted device is located. The second vehicle-mounted device identifies the target vehicle license plate through environmental information collected by the sensor, and sends a tag query request to the server based on the identified target vehicle license plate.

[0073] Step 208, query the target driving behavior tag corresponding to the target vehicle license plate, and feed back the target driving behavior tag to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior tag in the current human-machine interface.

[0074] Among them, the server responds to the label query request sent by the second vehicle-mounted device, queries the corresponding target driving behavior label from the managed label data according to the license plate of each target vehicle, and feeds back the queried target driving behavior label to the second vehicle-mounted device.

[0075] It is understandable that after acquiring the target driving behavior tag, the second vehicle-mounted device displays a human-computer interaction interface on the display screen, and the human-computer interaction interface includes the target driving behavior tag, so that the driver can view the driving behavior tags of surrounding vehicles. For example, the server generates a driving behavior tag corresponding to vehicle A based on the evaluation data of multiple vehicle-mounted devices for vehicle A. When vehicle B recognizes vehicle A, the driving behavior tag is displayed in the human-computer interaction interface based on the interaction data between the vehicle-mounted device and the server. If the driving behavior of vehicle A is poor, a bad driving tag is displayed, and the driver of vehicle B can get a prompt through the human-computer interaction interface, thereby avoiding vehicle A or driving carefully, reducing the probability of traffic accidents.

[0076] Optionally, the current human-computer interaction interface may be a car navigation system interface or an ADAS (Advanced Driver Assistance System) interface. It is understandable that a driving scene image simulated according to a real scene is displayed in the human-computer interaction interface, and the driving scene image includes a self-car image and an other-car image, and the other-car image displays a vehicle license plate and a driving behavior label.

[0077] In the above driving behavior labeling method, the driving behavior evaluation data uploaded by the first vehicle-mounted device is obtained; the driving behavior evaluation data includes the license plates of surrounding vehicles and the evaluation results; according to the evaluation results, the driving behavior labels corresponding to the license plates of surrounding vehicles are updated; the label query request sent by the second vehicle-mounted device is obtained; the label query request carries at least one target vehicle license plate; the target driving behavior label corresponding to the target vehicle license plate is queried, and the target driving behavior label is fed back to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior label in the current human-computer interface. Through the above method, the driving behavior label corresponding to each vehicle license plate is updated in time according to the data uploaded by the vehicle-mounted device, and the driving behavior labels of surrounding vehicles are displayed in the human-computer interface of the vehicle-mounted device that issued the request, so that vehicles with bad driving behavior can be identified, and other vehicles can be reminded in real time, so that the driver can know the driving behavior habits of surrounding vehicles, so as to make safer and more reasonable driving decisions, reduce the probability of traffic accidents, and improve the overall safety of the road.

[0078] In an exemplary embodiment, step 204 includes: querying the driving behavior labels and driving behavior records corresponding to the license plates of surrounding vehicles; the driving behavior labels include any one of bad driving labels, good driving labels and unknown driving labels; the driving behavior records include at least one of the number of good behaviors and the number of bad behaviors; if the evaluation result indicates that the surrounding vehicles have bad driving behaviors, the driving behavior labels corresponding to the license plates of the surrounding vehicles are updated to bad driving labels, and the effective time of the bad driving labels is updated according to the number of bad behaviors corresponding to the license plates of the surrounding vehicles in the first set time period; if the queried driving behavior labels are good driving labels and the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors, the effective time of the good driving labels is updated according to the number of bad behaviors corresponding to the license plates of the surrounding vehicles in the second set time period and the number of good behaviors corresponding to the license plates of the surrounding vehicles in the third set time period; if the queried driving behavior labels are unknown driving labels, the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors, the number of bad behaviors corresponding to the license plates of the surrounding vehicles in the second set time period is not greater than the first threshold, and the number of good behaviors corresponding to the license plates of the surrounding vehicles in the third set time period is not less than the second threshold, the driving behavior labels corresponding to the license plates of the surrounding vehicles are updated to good driving labels.

[0079] Among them, the server records the number of good behaviors and the number of bad behaviors of a certain vehicle license plate according to the evaluation results for a certain vehicle license plate received from each vehicle-mounted device. Since each evaluation result corresponds to an upload time, the server can determine the number of good behaviors and the number of bad behaviors of the vehicle license plate within a certain period of time. Optionally, the server obtains driving behavior evaluation data from multiple vehicle-mounted devices, performs deduplication processing on the driving behavior evaluation data, and generates driving behavior records corresponding to each vehicle license plate for the deduplication-processed driving behavior evaluation data. It is understandable that on the same day, multiple vehicle-mounted devices may upload driving behavior evaluation data for the driving behavior of the same vehicle license plate. The server ensures that only one driving behavior record is stored for the same vehicle license plate on the same day through deduplication processing. Among them, for the driving behavior evaluation data for the same vehicle license plate on the same day, the driving behavior record corresponding to the bad driving behavior is stored first.

[0080] It can be understood that the server stores driving behavior labels corresponding to each vehicle license plate, including any one of a bad driving label, a good driving label and an unknown driving label. The bad driving label and the good driving label are time-limited, and their effective duration is used as the expiration start time from the last update time. If the bad driving label or the good driving label of a vehicle license plate has expired, the driving behavior label and the effective duration will be reset based on the driving behavior record of the vehicle license plate within a certain period of time.

[0081] For the evaluation results received this time, if the evaluation results indicate that the surrounding vehicles have bad driving behaviors, that is, the driving behavior type of the evaluation results is any one of speeding, occupying lanes, overtaking on the right, emergency braking, changing lanes without turning on the turn signal, frequent lane changes, and solid line lane changes, then the driving behavior label corresponding to the license plate of the surrounding vehicles is updated to a bad driving label. It can be understood that if the server pre-queries that the driving behavior label corresponding to the license plate of the surrounding vehicles is a good driving label or an unknown driving label, then this time the driving behavior label is updated to a bad driving label, and the effective duration of the label is updated. If the server pre-queries that the driving behavior label corresponding to the license plate of the surrounding vehicles is a bad driving label, then this time only the effective duration of the bad driving label can be updated. The first set time period is a time period set in advance for determining the effective duration of the bad driving label. Optionally, the first set time period includes multiple time periods with different time intervals. Under different time periods, the number of determination thresholds are different, and the effective duration set for the bad driving label is different. The longer the time interval of the time period, the larger the number of determination thresholds, and the longer the effective duration set. In an optional implementation, if bad driving behavior occurs once, the effective period of the bad driving label is set to 7 days; if bad driving behavior occurs 2 or more times in the last 7 days, the effective period of the bad driving label is set to 30 days; if bad driving behavior occurs 4 or more times in the last 30 days, the effective period of the bad driving label is set to 90 days; if bad driving behavior occurs 10 or more times in the last 60 days, the effective period of the bad driving label is set to 180 days. When multiple judgment rules are met at the same time, a longer effective period is set for the bad driving label first.

[0082] For the evaluation results received this time, if the driving behavior label queried is a good driving label, and the evaluation results indicate that the surrounding vehicles have not had bad driving behaviors, that is, the driving behavior type of the evaluation results is non-bad driving behavior, then the effective duration of the good driving label is updated according to the number of bad behaviors corresponding to the license plates of the surrounding vehicles in the second set time period and the number of good behaviors corresponding to the license plates of the surrounding vehicles in the third set time period. It can be understood that under the good driving label judgment rule, it is required that no bad driving behavior occurs in the second set time period, and at the same time there is a driving behavior record in the third set time period, and the good driving label is also time-effective. Optionally, the third set time period includes multiple time periods with different time intervals. In different time periods, the thresholds for judgment are different, and the effective duration set for the good driving label is different. The longer the time interval of the time period, the larger the threshold for judgment, and the longer the effective duration set. In an optional implementation, if the number of bad behaviors within 180 days is 0, and there are driving behavior records for at least two days within the last 7 days (that is, the number of good behaviors within the last 7 days is not less than 2), the effective period of the good driving label is set to 7 days; if the number of bad behaviors within 180 days is 0, and there are driving behavior records for at least 4 days within the last 30 days (that is, the number of good behaviors within the last 30 days is not less than 4), the effective period of the good driving label is set to 30 days.

[0083] For the evaluation results received this time, if the driving behavior label queried is an unknown driving label, the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors (i.e., the driving behavior type of the evaluation result is non-bad driving behavior), the number of bad behaviors corresponding to the license plates of the surrounding vehicles in the second set time period is not greater than the first threshold (for example, the number of bad behaviors within 180 days is 0), and the number of good behaviors corresponding to the license plates of the surrounding vehicles in the third set time period is not less than the second threshold (for example, the number of good behaviors within the last 7 days is not less than 2, and the number of good behaviors within the last 30 days is not less than 4), then the driving behavior label corresponding to the license plates of the surrounding vehicles is updated to a good driving label. Further, referring to the update method of the good driving label, the effective duration of the good driving label is updated.

[0084] In this embodiment, a label determination rule is provided, which can update the driving behavior label and effective time of each vehicle license plate according to the evaluation results uploaded by the vehicle-mounted device and the driving behavior record. It can adapt to the variability of driving conditions and be updated with the driver's driving proficiency and driving frequency, providing the driver with real-time and accurate driving behavior labels, so as to make safer and more reasonable driving decisions and reduce the probability of traffic accidents.

[0085] In an exemplary embodiment, the method also includes: obtaining a complaint request sent by a third vehicle-mounted device; the complaint request includes the current vehicle license plate and the license plate application time; updating the driving behavior record corresponding to the current vehicle license plate according to the license plate application time; and re-evaluating the driving behavior label of the current vehicle license plate according to the updated driving behavior record.

[0086] Among them, the current vehicle license plate is the vehicle license plate of the vehicle where the third vehicle-mounted device is located. The appeal request also includes supporting materials. After receiving the appeal request, the server verifies whether the previous vehicle license plate carried in the appeal request matches the third vehicle-mounted device, and verifies whether the license plate application time is true and valid based on the supporting materials. After the verification is passed, the driving behavior record corresponding to the current vehicle license plate is updated based on the license plate application time. Specifically, the driving behavior records before the license plate application time are cleared. According to the aforementioned label judgment rules, the updated driving behavior record re-evaluates the driving behavior label of the current vehicle license plate.

[0087] In this embodiment, a label appeal function is provided so that a new car owner can appeal against the driving behavior label of the previous car owner, which can adapt to the variability of driving conditions and provide the driver with real-time and accurate driving behavior labels.

[0088] In an exemplary embodiment, the driving behavior evaluation data also includes evaluation materials; before step 204, the method further includes: verifying the evaluation results according to the evaluation materials; after the verification is passed, executing step 204.

[0089] The evaluation material may be a file of the image or video type, or data collected by a sensor on the vehicle where the first vehicle-mounted device is located. The server verifies the evaluation result uploaded by the first vehicle-mounted device based on the evaluation material, which may be verified manually or by an automated program, and this embodiment does not limit this.

[0090] In this embodiment, the vehicle-mounted device performs driving behavior evaluation and the server verifies the evaluation result of the vehicle-mounted device, which can improve the accuracy of the driving behavior evaluation and thus improve the accuracy of the marked driving behavior label.

[0091] In an exemplary embodiment, as shown in FIG3 , a driving behavior marking method is provided, which is described by taking the method applied to the vehicle-mounted device 102 in FIG1 as an example, including:

[0092] Step 302: Acquire environmental information collected by the sensor.

[0093] Step 304, based on the environmental information, identify the license plates, lane lines and speed limit information of the surrounding vehicles, and identify the turn signal status, vehicle position and speed information of the surrounding vehicles.

[0094] Among them, the sensors are radar sensors and visual sensors. Optionally, the recognition method of the license plates of surrounding vehicles is as follows: start the radar sensor of the vehicle, collect the positions of surrounding vehicles and continue to track them, and obtain the field of view angle of the surrounding vehicles relative to the vehicle according to the size of the surrounding vehicles and their relative positions to the vehicle; start the visual sensor of the vehicle, collect image data around the vehicle, crop the image in the direction of the field of view angle, and recognize the license plate number in the cropped image; match the vehicle position with the vehicle license plate to complete the recognition of the license plate information of the surrounding vehicles.

[0095] Among them, radar sensors are used to identify the position and speed of the vehicle, and continuous tracking can obtain the driving trajectory of surrounding vehicles. Visual sensors are used to collect image data near the vehicle, and the image is cropped in the direction of the field of view angle to identify the turn signal status of the corresponding vehicle. Visual sensors are used to identify speed limit icons and collect lane speed limit information. ADAS can also be used to obtain the speed limit information of the current lane from a high-precision map. Visual sensors are used to identify lane lines, and lane information is accurately identified in combination with the lane line point cloud of the radar sensor. The above-mentioned state information collected is stored in the form of a time series.

[0096] Step 306, based on the lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times, use the trained driving behavior prediction model to make predictions to obtain evaluation results of surrounding vehicles.

[0097] In the process of training the prediction model, the time series data and labels of the surrounding vehicles are processed into the data set required for the training model. Referring to FIG4, FIG4 is a schematic diagram of a prediction model in an embodiment, using the vehicle position, speed, turn signal, speed limit, lane state time series, and aligned label time series, input RNN (Recurrent Neural Network, recurrent neural network) neural network training to obtain a bad driving prediction model. The bad driving prediction model predicts based on the motion state of each vehicle (including lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times), and outputs the confidence of each driving behavior type. The driving behavior type is any one of speeding, occupying the lane, overtaking on the right, emergency braking, changing lanes without turning on the turn signal, frequent lane changes, solid line lane changes, and non-bad driving behaviors. The driving behavior type with the highest confidence is used as the evaluation result of the surrounding vehicles.

[0098] In an optional implementation, the vehicle-mounted device or server can determine the driving behavior type of the surrounding vehicles according to the following judgment rules. Referring to FIG5, FIG5 is a schematic diagram of the judgment of speeding, occupying the lane, overtaking on the right, and emergency braking in one embodiment; vehicle A is the vehicle where the vehicle-mounted device is located, and vehicle B is the surrounding vehicle; referring to FIG5 (1), the visual sensor collects and analyzes the image to obtain the road speed limit information (the speed limit information of the current lane can also be obtained with the help of the vehicle ADAS high-precision map), and the relative speed of the vehicle is obtained by the radar sensor, thereby calculating the speed of the surrounding vehicles. If the speed of the surrounding vehicles is greater than the speed limit requirement of the current lane, it is determined that the vehicle is speeding. Referring to FIG5 (2), the lane information is obtained with the help of the vehicle ADAS. If it is detected that the surrounding vehicles are driving on the emergency lane or the non-motorized vehicle lane, it is determined that the vehicle is occupying the lane. Referring to FIG5 (3), the radar sensor collects the driving trajectory of vehicle B. If vehicle B completes the driving trajectory of overtaking on the right within 10 seconds, it is determined that the vehicle is overtaking on the right. 5 (4), the radar sensor collects the driving trajectory of vehicle B and calculates its driving speed. If the deceleration of vehicle B per second reaches 6m / s^2 or above, it is determined that the vehicle is in emergency braking.

[0099] Referring to FIG6 , FIG6 is a schematic diagram of determining lane changes without a turn signal and lane changes on a solid line in one embodiment; vehicle A is the vehicle where the vehicle-mounted device is located, and vehicle B is the surrounding vehicle; referring to FIG6 (1), the radar sensor collects the driving trajectory of vehicle B. If vehicle B is overtaking, and the image data collected by the vehicle vision sensor does not detect the flashing of the vehicle lights, it is determined that the vehicle is changing lanes without a turn signal. Referring to FIG6 (2), the radar sensor and the vision sensor collect image information and obtain lane information. The radar sensor collects the driving trajectory of vehicle B. If vehicle B changes lanes in the solid line area, it is determined that the vehicle is changing lanes on a solid line.

[0100] Referring to Figure 7, Figure 7 is a schematic diagram of determining frequent lane changes in one embodiment; vehicle A is the vehicle where the on-board device is located, and vehicle B is a surrounding vehicle; the radar sensor and the visual sensor collect image information and obtain lane information, and the radar sensor collects the driving trajectory of vehicle B; if vehicle B changes lanes twice within 3 seconds, it is determined that the vehicle changes lanes frequently.

[0101] Step 308 : Upload the surrounding vehicle license plates and the evaluation results as driving behavior evaluation data to the server, so as to instruct the server to update the driving behavior tags corresponding to the surrounding vehicle license plates according to the evaluation results.

[0102] Among them, the server can execute the following steps: obtain driving behavior evaluation data uploaded by the first vehicle-mounted device; the driving behavior evaluation data includes surrounding vehicle license plates and evaluation results; according to the evaluation results, update the driving behavior labels corresponding to the surrounding vehicle license plates; obtain the label query request sent by the second vehicle-mounted device; the label query request carries at least one target vehicle license plate; query the target driving behavior label corresponding to the target vehicle license plate, and feed back the target driving behavior label to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior label in the current human-computer interface.

[0103] Optionally, the driving behavior evaluation data also includes evaluation materials, which collect data collected by sensors within a set time period and upload them as evaluation materials. For example, the evaluation materials include image data collected by visual sensors and radar sensors within the first 3 seconds after the driving behavior monitoring is completed.

[0104] In the above-mentioned driving behavior labeling method, the on-board equipment evaluates the driving behavior types of surrounding vehicles in real time based on the environmental information collected by the sensor, and uploads the driving behavior evaluation data to the server, so that the server can timely update the driving behavior label corresponding to each vehicle license plate, thereby improving the accuracy and real-time performance of the marked driving behavior label.

[0105] In an exemplary embodiment, the driving behavior evaluation data also includes evaluation materials; the method also includes: obtaining the surrounding vehicle license plates and evaluation results input by the driver through text or voice; obtaining the evaluation materials from the environmental information collected by the sensor; and uploading the surrounding vehicle license plates, evaluation results and evaluation materials as driving behavior evaluation data to the server.

[0106] Among them, the driver can manually identify and actively report the driving behavior evaluation data, which can be divided into immediate evaluation scenarios and post-evaluation scenarios. In the immediate evaluation scenario, the driver can directly submit the driving behavior evaluation data through voice commands. The voice command needs to include the vehicle license plate and the evaluation results, and directly link the image data collected by the visual sensor and radar sensor within 30 seconds before the voice trigger as the evaluation material. For example, the driver's voice input: bad driving, vehicle license plate A, changing lanes without turning on the turn signal, the driving behavior evaluation data is shown in the following table:

[0107]

[0108] In the post-evaluation scenario, the driver directly submits the vehicle license plate, evaluation results, and evaluation materials (picture and video type files) when not driving.

[0109] In this embodiment, a variety of reporting methods for driving behavior evaluation data are provided, the reporting process of driving behavior evaluation data is simplified, and the data resources of the server are enriched, thereby improving the accuracy of the marked driving behavior labels.

[0110] In an exemplary embodiment, the method also includes: displaying vehicle graphics corresponding to the surrounding vehicle license plates in a human-computer interaction interface based on the surrounding vehicle license plates and the vehicle positions of the surrounding vehicles; sending a label query request to a server; the label query request carries the surrounding vehicle license plates to instruct the server to query and feedback the driving behavior labels corresponding to the surrounding vehicle license plates; and displaying the driving behavior labels corresponding to the surrounding vehicle license plates on the vehicle graphics.

[0111] Among them, the human-computer interaction interface can be a car navigation system interface or an ADAS (Advanced Driver Assistance System) interface. It is understandable that, according to the license plates of surrounding vehicles and the vehicle positions of surrounding vehicles, a driving scene image simulated according to the real scene is displayed in the human-computer interaction interface, and the driving scene image includes a self-vehicle graphic and a graphics of other vehicles, and the vehicle license plate is displayed on the graphics of other vehicles. The vehicle-mounted device sends a label query request to the server, obtains the driving behavior labels corresponding to the license plates of surrounding vehicles from the data managed by the server, and displays the driving behavior labels corresponding to the license plates of surrounding vehicles on the graphics of other vehicles on the human-computer interaction interface. In an optional implementation, refer to Figure 8, which is a schematic diagram of the human-computer interaction interface in an embodiment; the vehicle-mounted device updates the vehicle label on the ADAS human-computer interaction interface according to the label result queried by the server. In this way, the driver is prompted so that the driver can know the driving behavior habits of surrounding vehicles, so as to make safer and more reasonable driving decisions, reduce the probability of traffic accidents, and improve the overall safety of the road.

[0112] In an exemplary embodiment, referring to FIG. 9 , FIG. 9 is a flow chart of a driving behavior marking method in another embodiment; wherein the visual sensor on the vehicle-mounted device collects images, the radar sensor collects positions, and the ADAS collects map information. The specific steps of the driving behavior marking method are as follows:

[0113] Step S101, obtaining environmental information collected by vehicle radar sensors and visual sensors, and identifying the license plate data of the vehicle to be evaluated.

[0114] Step S102, obtaining environmental information collected by vehicle radar sensors and visual sensors, and identifying the status of turn signals of surrounding vehicles.

[0115] Step S103, obtaining lane marking and speed limit information according to the vehicle radar sensor, visual sensor or ADAS.

[0116] Step S104, obtaining environmental information collected by the vehicle radar sensor, and identifying the vehicle position and speed information.

[0117] Step S105, according to step S101 and step S104, the vehicle license plate and location information are obtained, and the ADAS human-computer interaction interface can simulate the real scene to display the recognized vehicle license plate.

[0118] Step S106: Use the wireless gateway to report the identified vehicle license plate to the cloud server.

[0119] Step S107, the cloud server records the license plate driving record (only one record per day), and updates the driving behavior label of the vehicle license plate according to the label determination rule.

[0120] Step S108, storing the vehicle position, speed, turn signal status, lane line and speed limit information collected in steps S102, S103 and S104 in the form of a time series.

[0121] Step S109, processing the time-serialized data of surrounding vehicles into a data set required for training the model.

[0122] Step S110 , training is performed according to the driving behavior type determination rules shown in FIGS. 5 to 7 to generate a bad driving behavior prediction model.

[0123] Step S111, using the bad driving behavior prediction model generated in step S110, predict surrounding vehicles in real time.

[0124] Step S112: Based on the bad driving behavior identified in step S111 (this embodiment uses bad driving behavior as an example, it can also be non-bad driving behavior), it is integrated with the vehicle license plate information and sent to the driver for confirmation. The driving behavior evaluation data is shown in the following table:

[0125]

[0126] After the driver confirms the driving behavior evaluation data, the process may jump to step S115.

[0127] In step S113, the driver can manually identify and actively report the driving behavior types of surrounding vehicles.

[0128] Step S114: The driver collects driving behavior evaluation data by himself, and provides the vehicle license plate, evaluation results, and collection information as evaluation materials.

[0129] Step S115, uploading the vehicle license plate, evaluation results and evaluation materials finally given in step S112 or S114 to the cloud server.

[0130] Step S116: After the cloud server receives the vehicle license plate, evaluation results and evaluation materials, the auditor will check and confirm them through the program of the remote server. After confirmation, the bad behavior will be recorded once. The auditor here can be realized manually or by program.

[0131] Step S117, based on the number of good behaviors and the number of bad behaviors within a certain period of time, the driving behavior label of the vehicle license plate is updated according to the label judgment rules. After the update is successful, the process can jump to step S122.

[0132] Step S118: The cloud server queries the latest tag corresponding to the submitted vehicle license plate.

[0133] Step S119: If the driver recognizes that his driving behavior tag belongs to the previous owner of the license plate, he is prepared to provide complaint certification materials including the license plate application time.

[0134] In step S120, the wireless gateway uploads the complaint certification materials including the license application time to the cloud server.

[0135] In step S121, the auditor of the cloud server confirms the appeal proof materials including the license application time, and then proceeds to step S117.

[0136] In step S122, the vehicle updates the vehicle label on the ADAS human-computer interaction interface according to the label result queried by the cloud server to prompt the driver.

[0137] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0138] In an exemplary embodiment, the present application further provides a driving behavior marking device, which is applied to a vehicle and includes:

[0139] Information acquisition module, used to obtain voice commands, vehicle images, vehicle speed, vehicle location, etc.;

[0140] Bad driving judgment module, used to determine bad behavior based on vehicle speed, vehicle position, and vehicle trajectory;

[0141] The information reporting module is used to upload the vehicle license plate, evaluation results, and evaluation materials to the server.

[0142] In an exemplary embodiment, the present application also provides a driving behavior marking device, which is applied to a server and includes:

[0143] An information receiving module, used to obtain the vehicle license plate, evaluation results, and evaluation materials uploaded by the vehicle;

[0144] An evaluation acquisition module is used to extract historical evaluation information based on the vehicle license plate in the pre-stored driving record;

[0145] An evaluation update module, used to update the vehicle's historical evaluation information based on the evaluation materials;

[0146] The vehicle labeling module is used to label the vehicle when the vehicle history evaluation record meets the judgment rules of "good driving label, bad driving label, unknown driving label".

[0147] In an exemplary embodiment, a server is provided, which may be a server, and its internal structure diagram may be shown in FIG10. The server includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the server is used to provide computing and control capabilities. The memory of the server includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the server is used to store driving behavior labels and driving behavior records corresponding to each vehicle license plate. The input / output interface of the server is used to exchange information between the processor and an external device. The communication interface of the server is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a driving behavior marking method is implemented.

[0148] In an exemplary embodiment, a vehicle-mounted device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG11. The vehicle-mounted device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the vehicle-mounted device is used to provide computing and control capabilities. The memory of the vehicle-mounted device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the vehicle-mounted device is used to exchange information between the processor and an external device. The communication interface of the vehicle-mounted device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a driving behavior recognition method is implemented. The display unit of the vehicle-mounted device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the vehicle-mounted equipment can be a touch layer covering the display screen, or a button, trackball or touchpad set on the housing of the vehicle-mounted equipment, or an external keyboard, touchpad or mouse.

[0149] Those skilled in the art will understand that the structure shown in FIG. 10 or 11 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the vehicle-mounted device or server to which the scheme of the present application is applied. The specific vehicle-mounted device or server may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0150] In an exemplary embodiment, a server is provided, which is communicatively connected to a plurality of vehicle-mounted devices, and includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program: obtaining driving behavior evaluation data uploaded by a first vehicle-mounted device; the driving behavior evaluation data includes surrounding vehicle license plates and evaluation results; updating driving behavior labels corresponding to surrounding vehicle license plates according to the evaluation results; obtaining a label query request sent by a second vehicle-mounted device; the label query request carries at least one target vehicle license plate; querying a target driving behavior label corresponding to the target vehicle license plate, and feeding back the target driving behavior label to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior label in the current human-computer interface.

[0151] In one embodiment, when the processor executes the computer program, the following steps are further implemented: querying the driving behavior labels and driving behavior records corresponding to the license plates of surrounding vehicles; the driving behavior labels include any one of bad driving labels, good driving labels and unknown driving labels; the driving behavior records include at least one of the number of good behaviors and the number of bad behaviors; if the evaluation result indicates that the surrounding vehicles have bad driving behaviors, the driving behavior labels corresponding to the license plates of surrounding vehicles are updated to bad driving labels, and the effective duration of the bad driving labels is updated according to the number of bad behaviors corresponding to the license plates of surrounding vehicles in the first set time period; if the queried driving behavior labels are good driving labels, and the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors, the effective duration of the good driving labels is updated according to the number of bad behaviors corresponding to the license plates of surrounding vehicles in the second set time period and the number of good behaviors corresponding to the license plates of surrounding vehicles in the third set time period; if the queried driving behavior labels are unknown driving labels, the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors, the number of bad behaviors corresponding to the license plates of surrounding vehicles in the second set time period is not greater than the first threshold, and the number of good behaviors corresponding to the license plates of surrounding vehicles in the third set time period is not less than the second threshold, then the driving behavior labels corresponding to the license plates of surrounding vehicles are updated to good driving labels.

[0152] In one embodiment, when the processor executes the computer program, it also implements the following steps: obtaining a complaint request sent by a third vehicle-mounted device; the complaint request includes the current vehicle license plate and the license plate application time; according to the license plate application time, updating the driving behavior record corresponding to the current vehicle license plate; and re-evaluating the driving behavior label of the current vehicle license plate based on the updated driving behavior record.

[0153] In one embodiment, when the processor executes the computer program, the following steps are also implemented: verifying the evaluation results based on the evaluation materials; after the verification is passed, executing the step of updating the driving behavior labels corresponding to the license plates of surrounding vehicles based on the evaluation results.

[0154] In an exemplary embodiment, a vehicle-mounted device is provided, which is communicatively connected to a server, and includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program: obtaining environmental information collected by a sensor; identifying surrounding vehicle license plates, lane lines and speed limit information based on the environmental information, and identifying the turn signal status, vehicle position and speed information of surrounding vehicles; using a trained driving behavior prediction model to make predictions based on the lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times to obtain evaluation results of surrounding vehicles; uploading the surrounding vehicle license plates and the evaluation results to the server as driving behavior evaluation data to instruct the server to update the driving behavior labels corresponding to the surrounding vehicle license plates based on the evaluation results.

[0155] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining the license plates of surrounding vehicles and evaluation results input by the driver through text or voice; obtaining evaluation materials from the environmental information collected by the sensor; and uploading the license plates of surrounding vehicles, evaluation results and evaluation materials as driving behavior evaluation data to the server.

[0156] In one embodiment, the processor also implements the following steps when executing the computer program: displaying vehicle graphics corresponding to the surrounding vehicle license plates in the human-computer interaction interface based on the surrounding vehicle license plates and the vehicle positions of the surrounding vehicles; sending a label query request to the server; the label query request carries the surrounding vehicle license plates to instruct the server to query and feedback the driving behavior labels corresponding to the surrounding vehicle license plates; and displaying the driving behavior labels corresponding to the surrounding vehicle license plates on the vehicle graphics.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining driving behavior evaluation data uploaded by a first vehicle-mounted device; the driving behavior evaluation data includes surrounding vehicle license plates and evaluation results; according to the evaluation results, updating the driving behavior labels corresponding to the surrounding vehicle license plates; obtaining a label query request sent by a second vehicle-mounted device; the label query request carries at least one target vehicle license plate; querying a target driving behavior label corresponding to the target vehicle license plate, and feeding back the target driving behavior label to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior label in the current human-computer interface.

[0158] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: querying the driving behavior labels and driving behavior records corresponding to the license plates of surrounding vehicles; the driving behavior labels include any one of bad driving labels, good driving labels and unknown driving labels; the driving behavior records include at least one of good behavior times and bad behavior times; if the evaluation result indicates that the surrounding vehicles have bad driving behaviors, the driving behavior labels corresponding to the license plates of surrounding vehicles are updated to bad driving labels, and the effective duration of the bad driving labels is updated according to the bad behavior times corresponding to the license plates of surrounding vehicles in the first set time period; if the queried driving behavior labels are good driving labels and the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors, the effective duration of the good driving labels is updated according to the bad behavior times corresponding to the license plates of surrounding vehicles in the second set time period and the good behavior times corresponding to the license plates of surrounding vehicles in the third set time period; if the queried driving behavior labels are unknown driving labels, the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors, the bad behavior times corresponding to the license plates of surrounding vehicles in the second set time period are not greater than the first threshold, and the good behavior times corresponding to the license plates of surrounding vehicles in the third set time period are not less than the second threshold, the driving behavior labels corresponding to the license plates of surrounding vehicles are updated to good driving labels.

[0159] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining a complaint request sent by a third vehicle-mounted device; the complaint request includes the current vehicle license plate and the license plate application time; according to the license plate application time, updating the driving behavior record corresponding to the current vehicle license plate; and re-evaluating the driving behavior label of the current vehicle license plate based on the updated driving behavior record.

[0160] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: verifying the evaluation results based on the evaluation materials; after the verification is passed, executing the step of updating the driving behavior labels corresponding to the license plates of surrounding vehicles based on the evaluation results.

[0161] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining environmental information collected by sensors; identifying the license plates, lane lines and speed limit information of surrounding vehicles based on the environmental information, and identifying the turn signal status, vehicle position and speed information of surrounding vehicles; using the trained driving behavior prediction model to make predictions based on the lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times to obtain evaluation results of surrounding vehicles; uploading the license plates of surrounding vehicles and the evaluation results as driving behavior evaluation data to the server to instruct the server to update the driving behavior labels corresponding to the license plates of surrounding vehicles based on the evaluation results.

[0162] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the license plates of surrounding vehicles and evaluation results input by the driver through text or voice; obtaining evaluation materials from the environmental information collected by the sensor; and uploading the license plates of surrounding vehicles, evaluation results and evaluation materials as driving behavior evaluation data to the server.

[0163] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the surrounding vehicle license plates and the vehicle positions of the surrounding vehicles, a vehicle graphic corresponding to the surrounding vehicle license plates is displayed in the human-computer interaction interface; a label query request is sent to the server; the label query request carries the surrounding vehicle license plates to instruct the server to query and feedback the driving behavior labels corresponding to the surrounding vehicle license plates; and the driving behavior labels corresponding to the surrounding vehicle license plates are displayed on the vehicle graphic.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0165] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0166] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0167] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A driving behavior marking method, characterized in that: The method comprises: Acquire driving behavior evaluation data uploaded by the first vehicle-mounted device; the driving behavior evaluation data includes license plates of surrounding vehicles and evaluation results; According to the evaluation result, the driving behavior labels corresponding to the license plates of the surrounding vehicles are updated; Obtaining a label query request sent by a second vehicle-mounted device; the label query request carries at least one target vehicle license plate; The target driving behavior tag corresponding to the target vehicle license plate is queried, and the target driving behavior tag is fed back to the second vehicle-mounted device to instruct the second vehicle-mounted device to display the target driving behavior tag in the current human-machine interface.

2. The method according to claim 1, characterized in that: The updating of the driving behavior labels corresponding to the license plates of the surrounding vehicles according to the evaluation results includes: Querying the driving behavior labels and driving behavior records corresponding to the license plates of the surrounding vehicles; the driving behavior labels include any one of bad driving labels, good driving labels, and unknown driving labels; the driving behavior records include at least one of the number of good behaviors and the number of bad behaviors; If the evaluation result indicates that the surrounding vehicles have bad driving behaviors, the driving behavior labels corresponding to the license plates of the surrounding vehicles are updated to bad driving labels, and the effective time of the bad driving labels is updated according to the number of bad behaviors corresponding to the license plates of the surrounding vehicles within the first set time period; If the queried driving behavior label is a good driving label, and the evaluation result indicates that the surrounding vehicles have not had bad driving behaviors, then the effective time of the good driving label is updated according to the number of bad behaviors corresponding to the license plates of the surrounding vehicles in the second set time period and the number of good behaviors corresponding to the license plates of the surrounding vehicles in the third set time period; If the queried driving behavior label is an unknown driving label, the evaluation result indicates that no bad driving behavior has occurred in the surrounding vehicles, the number of bad behaviors corresponding to the surrounding vehicle license plates within the second set time period is not greater than the first threshold, and the number of good behaviors corresponding to the surrounding vehicle license plates within the third set time period is not less than the second threshold, then the driving behavior label corresponding to the surrounding vehicle license plates is updated to a good driving label.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining a complaint request sent by a third vehicle-mounted device; the complaint request includes the current vehicle license plate and the license plate application time; According to the license plate application time, the driving behavior record corresponding to the current vehicle license plate is updated; The driving behavior label of the current vehicle license plate is re-evaluated according to the updated driving behavior record.

4. The method according to any one of claims 1 to 3, characterized in that The driving behavior evaluation data also includes evaluation materials; before updating the driving behavior labels corresponding to the license plates of the surrounding vehicles according to the evaluation results, the method further includes: Verifying the evaluation results according to the evaluation materials; After the verification is passed, a step of updating the driving behavior labels corresponding to the license plates of the surrounding vehicles is performed according to the evaluation results.

5. A driving behavior recognition method, characterized in that: The method comprises: Obtain environmental information collected by sensors; Based on the environmental information, identify the license plates, lane lines and speed limit information of surrounding vehicles, and identify the turn signal status, vehicle position and speed information of surrounding vehicles; Based on the lane lines, speed limit information, turn signal status, vehicle position and speed information identified at multiple times, the trained driving behavior prediction model is used to make predictions and obtain the evaluation results of surrounding vehicles; The surrounding vehicle license plates and the evaluation results are uploaded to a server as driving behavior evaluation data to instruct the server to update the driving behavior tags corresponding to the surrounding vehicle license plates according to the evaluation results.

6. The method according to claim 5, characterized in that The driving behavior evaluation data also includes evaluation materials; the method also includes: Obtain the license plates and evaluation results of surrounding vehicles input by the driver through text or voice; Obtain evaluation materials from environmental information collected by sensors; The surrounding vehicle license plates, the evaluation results and the evaluation materials are uploaded to a server as driving behavior evaluation data.

7. The method according to claim 5, characterized in that The method further comprises: According to the license plates of the surrounding vehicles and the vehicle positions of the surrounding vehicles, displaying vehicle graphics corresponding to the license plates of the surrounding vehicles in the human-computer interaction interface; Sending a tag query request to the server; the tag query request carries the surrounding vehicle license plate to instruct the server to query and feedback the driving behavior tag corresponding to the surrounding vehicle license plate; The driving behavior labels corresponding to the license plates of the surrounding vehicles are displayed on the vehicle graphic.

8. A server, characterized in that: The server is communicatively connected to a plurality of vehicle-mounted devices, and the server comprises a memory and a processor. The memory stores a computer program, and the processor implements the steps of the method described in any one of claims 1 to 4 when executing the computer program.

9. A vehicle-mounted device, characterized in that: The vehicle-mounted device is communicatively connected to a server, and the vehicle-mounted device includes a memory and a processor. The memory stores a computer program, and the processor implements the steps of any one of claims 5 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images