Road condition risk map construction method, device and equipment based on vehicle operation data

Abstract

The invention relates to the technical field of vehicle big data, and discloses a road condition risk map construction method, device and equipment based on vehicle operation data. Dangerous driving events occurring in the running process of each vehicle and corresponding occurrence positions are determined; the occurrence position and occurrence time of each dangerous driving event in the historical time period are counted, and the historical occurrence probability of the dangerous driving events corresponding to the multiple preset areas in the historical time period is determined; and performing evaluation analysis on the historical occurrence probability of the dangerous driving event in the historical time period to obtain the current occurrence probability of the dangerous driving event in each preset area, and constructing a road condition risk map. Therefore, the road condition risk map is constructed, so that a driver can carry out early warning in advance through the road condition map, and the driving safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle big data technology, and in particular to a method, device and equipment for constructing a road condition risk map based on vehicle operation data. Background Art

[0002] At present, with the continuous increase in the number of vehicles, traffic accidents occur frequently. The limitations of navigation reminders and unreasonable road restriction design have led to many traffic accidents caused by drivers' emergency braking, lane changing and other operations. In order to reduce the occurrence of traffic accidents caused by drivers' dangerous driving behaviors, relevant technical means are urgently needed to remind drivers accordingly.

[0003] In order to reduce the occurrence of dangerous driving behaviors, the main measures are to install sensors on the vehicle and provide distance reminders to avoid dangerous driving behaviors such as sudden braking and speeding. However, for vehicles without active braking and active cruise functions such as ADAS, it is difficult to take timely measures based on the reminders. And even for vehicles with active braking and active cruise functions, they can only respond when dangerous driving behaviors are about to occur. It is often difficult for drivers to prepare in advance for actual road conditions to avoid dangerous driving behaviors. Summary of the invention

[0004] In view of this, the present invention provides a method, device and equipment for constructing a road condition risk map based on vehicle operation data to solve the problem that it is difficult for drivers to prepare in advance for actual road conditions to avoid the occurrence of dangerous driving behaviors.

[0005] In a first aspect, the present invention provides a method for constructing a road condition risk map based on vehicle operation data, the method comprising:

[0006] Based on the operation data of each vehicle collected by the Internet of Vehicles platform during operation, determine the dangerous driving events that occurred during the operation of each vehicle and the location where each dangerous driving event occurred;

[0007] Counting the locations and times of each dangerous driving incident in the historical period, and determining the historical probability of dangerous driving incidents corresponding to each of the multiple preset areas in the historical period;

[0008] Evaluate and analyze the historical probability of dangerous driving events in the historical period to obtain the current probability of dangerous driving events in each preset area;

[0009] Construct a road risk map based on the current probability of dangerous driving incidents in each preset area.

[0010] The method provided in this aspect analyzes the collected vehicle operation data through the Internet of Vehicles platform, determines the dangerous driving events that occur during the operation of the vehicle, and counts the occurrence locations and events corresponding to each dangerous driving event in the historical period, and obtains the historical occurrence probability of dangerous driving events corresponding to each preset area, thereby analyzing the current probability of dangerous driving events in each preset area, and constructing a risky road condition map, so as to realize the construction of a risky road condition map corresponding to dangerous driving events only by analyzing vehicle big data, thereby reducing the construction cost of the risky road condition map, and the constructed risky road condition map can enable the driver to understand the risk status of the current area in advance, so as to avoid driving risks in time and ensure driving safety.

[0011] In an optional implementation, the determining of the dangerous driving events occurring during the operation of each vehicle and the location of each dangerous driving event based on the operation data of each vehicle collected by the Internet of Vehicles platform during the operation includes:

[0012] Determine the real-time running speed and geographical location of each vehicle during the running process according to the running data of each vehicle during the running process;

[0013] Determine whether the vehicle has a dangerous driving incident based on the changes in real-time running speed;

[0014] If a dangerous driving event occurs, the current geographic location of the vehicle is marked as the location where the dangerous driving event occurred.

[0015] This embodiment analyzes the changes in the real-time running speed of the vehicle during operation to determine whether a dangerous driving event has occurred, thereby ensuring the accuracy of the judgment of dangerous driving events. At the same time, the location of the dangerous driving event can be quickly obtained through the geographical location of the vehicle during operation.

[0016] In an optional implementation, the dangerous driving events include: emergency braking, fatigue driving and speeding;

[0017] The determining whether a dangerous driving event occurs to the vehicle according to the change in the real-time running speed includes:

[0018] When the vehicle deceleration is greater than a preset value and lasts for a period longer than a first preset period, determining that the vehicle has experienced emergency deceleration;

[0019] When the vehicle continues to travel for more than a second preset time, it is determined that the vehicle is fatigued;

[0020] When the vehicle speed is greater than a second preset value and lasts for longer than a third preset time, it is determined that the vehicle is speeding.

[0021] In this implementation manner, by setting the judgment conditions corresponding to the three types of dangerous driving events, namely emergency braking, fatigue driving and speeding, according to the actual driving conditions of these three types of dangerous driving events, the accuracy of the judgment of dangerous driving events can be effectively guaranteed.

[0022] In an optional implementation, the statistically analyzing the occurrence locations and occurrence times of each dangerous driving event in the historical period to determine the historical occurrence probabilities of dangerous driving events corresponding to each of a plurality of preset areas in the historical period includes:

[0023] Divide the area corresponding to the road condition risk map to be constructed into multiple preset areas;

[0024] According to the location and time of each dangerous driving incident, the number of vehicles involved in dangerous driving incidents in each preset area during the historical period is counted;

[0025] According to the operation data of each vehicle, the total number of vehicles passing through each preset area in the historical period is counted;

[0026] The historical occurrence probabilities of dangerous driving events corresponding to each of a plurality of preset areas in a historical period are determined according to the total number of vehicles and the number of vehicles having dangerous driving events.

[0027] In this embodiment, by dividing the corresponding area of ​​the road condition risk map into multiple preset areas, and comparing the number of vehicles that have experienced dangerous driving incidents in each preset area during a historical period with the total number of vehicles, the accuracy of the statistical probability of occurrence of dangerous driving incidents in each preset area during a historical period can be ensured.

[0028] In an optional implementation, the historical period includes a plurality of historical sub-periods;

[0029] The evaluating and analyzing the historical occurrence probability of dangerous driving events in the historical period to obtain the current occurrence probability of dangerous driving events in each preset area includes:

[0030] For each preset area, determining the historical occurrence probability of a dangerous driving event corresponding to each historical sub-period in the preset area;

[0031] The current occurrence probability of the dangerous driving event in the preset area is determined according to the preset weights corresponding to the historical sub-periods and the historical occurrence probability of the dangerous driving event.

[0032] In this embodiment, by determining the historical probability of dangerous driving events in each preset area in each sub-period within the historical period, and combining the corresponding preset weights to obtain the current probability of dangerous driving events corresponding to each preset area, the accuracy of the calculated current probability of occurrence can be improved.

[0033] In an optional implementation, the step of constructing a road condition risk map according to the current probability of occurrence of dangerous driving events in each preset area includes:

[0034] A road condition risk map is constructed based on the current probability of emergency braking, fatigue driving and speeding in each preset area.

[0035] In this embodiment, a road condition risk map is constructed according to the current occurrence probabilities of various types of dangerous driving events, so that drivers can understand the occurrence probabilities of various types of dangerous driving events based on the road condition map and make targeted responses.

[0036] In an optional implementation, before determining the dangerous driving events that occurred during the operation of each vehicle and the location where each dangerous driving event occurred, the method further includes:

[0037] The operation data of each vehicle collected by the vehicle networking platform during operation is filtered to remove abnormal data in the operation data.

[0038] In this embodiment, the operation data collected by the Internet of Vehicles is filtered before determining a dangerous driving event to remove abnormal data, thereby ensuring the accuracy of subsequent determinations of dangerous driving events.

[0039] In a second aspect, the present invention provides a device for constructing a road condition risk map based on vehicle operation data, the device comprising:

[0040] A dangerous event determination module is used to determine the dangerous driving events that occurred during the operation of each vehicle and the location where each dangerous driving event occurred based on the operation data of each vehicle collected by the Internet of Vehicles platform during the operation;

[0041] The historical probability statistics module is used to count the location and time of each dangerous driving incident in the historical period, and determine the historical probability of dangerous driving incidents corresponding to each of the multiple preset areas in the historical period;

[0042] A current probability evaluation module is used to evaluate and analyze the historical probability of dangerous driving events in the historical period to obtain the current probability of dangerous driving events in each preset area;

[0043] The risk map construction module is used to construct a road condition risk map based on the current probability of dangerous driving events in each preset area.

[0044] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for constructing a road condition risk map based on vehicle operation data of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for constructing a road condition risk map based on vehicle operation data of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 is a flow chart of a method for constructing a road condition risk map based on vehicle operation data according to an embodiment of the present invention;

[0048] Figure 2 is a flow chart of another method for constructing a road condition risk map based on vehicle operation data according to an embodiment of the present invention;

[0049] Figure 3 is an example diagram of an emergency deceleration determination process according to an embodiment of the present invention;

[0050] Figure 4 This is an example diagram of a fatigue driving determination process according to an embodiment of the present invention;

[0051] Figure 5 is an example diagram of a speeding determination process according to an embodiment of the present invention;

[0052] Figure 6 is a structural block diagram of a device for constructing a road condition risk map based on vehicle operation data according to an embodiment of the present invention;

[0053] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] At present, with the continuous increase in the number of vehicles, traffic accidents occur frequently. The limitations of navigation reminders and unreasonable road restriction design have led to many traffic accidents caused by drivers' emergency braking, lane changing and other operations. In order to reduce the occurrence of traffic accidents caused by drivers' dangerous driving behaviors, relevant technical means are urgently needed to remind drivers accordingly.

[0056] In order to reduce the occurrence of dangerous driving behaviors, the main measures are to install sensors on the vehicle and provide distance reminders to avoid dangerous driving behaviors such as sudden braking and speeding. However, for vehicles without active braking and active cruise functions such as ADAS, it is difficult to take timely measures based on the reminders. And even for vehicles with active braking and active cruise functions, they can only respond when dangerous driving behaviors are about to occur. It is often difficult for drivers to prepare in advance for actual road conditions to avoid dangerous driving behaviors.

[0057] To this end, an embodiment of the present invention provides a method for constructing a road condition risk map based on vehicle operation data, which analyzes the collected vehicle operation data through a vehicle networking platform, determines the dangerous driving events that occur during the vehicle operation process, and performs statistics on the occurrence locations and events corresponding to each dangerous driving event in a historical period, and obtains the historical occurrence probability of dangerous driving events corresponding to each preset area, thereby analyzing the current probability of occurrence of dangerous driving events in each preset area, and constructing a risky road condition map, so as to realize the construction of a risky road condition map corresponding to dangerous driving events only by analyzing vehicle big data, thereby reducing the construction cost of the risky road condition map, and the constructed risky road condition map can enable the driver to understand the risk status of the current area in advance, so as to avoid driving risks in time and ensure driving safety.

[0058] According to an embodiment of the present invention, an embodiment of a method for constructing a road condition risk map based on vehicle operation data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0059] In this embodiment, a method for constructing a road condition risk map based on vehicle operation data is provided, which can be used to construct the above-mentioned road condition map. Figure 1 is a flow chart of a method for constructing a road condition risk map based on vehicle operation data according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0060] Step S101, based on the operation data of each vehicle collected by the Internet of Vehicles platform during the operation process, determine the dangerous driving events that occurred during the operation of each vehicle and the location where each dangerous driving event occurred.

[0061] With the development of Internet of Vehicles technology, the detection of vehicle operation data can be realized through the Internet of Vehicles platform. For example, each car company can collect the vehicle speed, location, time and other information through the on-board TBOX on its own vehicle, and upload it to the cloud Internet of Vehicles platform. For a specific vehicle, by analyzing the vehicle's operation data, such as speed, running time, acceleration and other information, it can be determined whether the vehicle has experienced dangerous driving events such as sudden braking and speeding during operation. In the process of collecting and detecting vehicle operation data, it can be determined whether the vehicle has experienced a dangerous driving event and its specific location by the change in speed or other corresponding judgment methods, and the relevant information of the dangerous driving event, such as the specific location, time of occurrence, type of dangerous driving event, etc., is recorded on the Internet of Vehicles platform.

[0062] Step S102 , counting the occurrence locations and occurrence times of each dangerous driving event in the historical period, and determining the historical occurrence probabilities of dangerous driving events corresponding to each of a plurality of preset areas in the historical period.

[0063] Through the above step S101, dangerous driving events that occur during vehicle operation can be determined. Then, the specific occurrence time and location of each dangerous driving event in the historical period need to be counted to determine the specific occurrence of dangerous driving events in each preset area in the historical period.

[0064] For the preset area, it can be understood that for a certain city or province, it can be divided into multiple preset areas according to the actual traffic routes, and each preset area can be a section of road or a subdivided area. For each preset area, according to the occurrence and location of each dangerous driving incident, the number of dangerous driving incidents that occurred in the preset area in the historical period is counted, so as to determine the historical probability of dangerous driving incidents in the preset area, that is, the proportion of vehicles in which dangerous driving incidents occurred in the area in the historical period compared to the total number of passing vehicles. In some cases, the number of dangerous driving incidents in the area in the historical period can also be counted as an indicator to measure the occurrence of dangerous driving incidents.

[0065] Step S103 , evaluating and analyzing the historical occurrence probability of dangerous driving events in the historical period, and obtaining the current occurrence probability of dangerous driving events in each preset area.

[0066] After completing the statistics of dangerous driving events in each preset area within the historical period, quantitative information such as the changes in the historical probability of dangerous driving events within the historical period or the historical probability of occurrence in different historical periods can be evaluated to predict the current probability of dangerous driving events in each preset area.

[0067] For example, for a preset area, the probability of dangerous driving events occurring every day or every week in a historical period can be counted, and the probability of dangerous driving events occurring in each sub-period in the historical period can be analyzed and calculated by combining relevant statistical analysis methods, so as to obtain the probability of dangerous driving events occurring in the current period, that is, the current probability of occurrence. The specific statistical analysis method can be selected based on the actual situation. For example, linear regression, machine learning model, etc. can be used for analysis and evaluation. The specific mathematical analysis method is not limited here.

[0068] Step S104: construct a road condition risk map according to the current occurrence probability of dangerous driving events in each preset area.

[0069] After obtaining the current probability of occurrence of dangerous driving events in each preset area, the probability of occurrence of dangerous driving events corresponding to each preset area can be displayed on the map to achieve the construction of a road condition risk map.

[0070] For example, for a certain area, it can be determined whether to display relevant prompt information according to the interval of the current probability of dangerous driving events in the area. If prompted, the preset area is circled in the map with a corresponding color and displayed in the map in combination with relevant text information to remind drivers to promptly understand the dangerous driving situation in the current driving area. Similarly, corresponding display processing is performed for each preset area in the map.

[0071] The display method of the probability of dangerous driving events in the above map is only an exemplary method. The display method can be optimized based on actual conditions to display relevant information in the map, as long as the driver can understand the relevant information of dangerous driving events in the current driving area through the risk road condition map.

[0072] The method for constructing a road condition risk map based on vehicle operation data provided in this embodiment analyzes the collected vehicle operation data through the Internet of Vehicles platform, determines the dangerous driving events that occurred during the vehicle operation process, and counts the occurrence locations and events corresponding to each dangerous driving event in the historical period, so as to obtain the historical occurrence probability of dangerous driving events corresponding to each preset area, thereby analyzing the current probability of occurrence of dangerous driving events in each preset area, and constructing a risky road condition map, so as to realize the construction of a risky road condition map corresponding to dangerous driving events only by analyzing vehicle big data, thereby reducing the construction cost of the risky road condition map, and the constructed risky road condition map can enable the driver to understand the risk status of the current area in advance, so as to avoid driving risks in time and ensure driving safety.

[0073] According to an embodiment of the present invention, another method for constructing a road condition risk map based on vehicle operation data is provided, which can be used to construct the above-mentioned road condition map. Figure 2 FIG. 4 is a flowchart of another method for constructing a road condition risk map based on vehicle operation data according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0074] Step S201, based on the operation data of each vehicle collected by the Internet of Vehicles platform during the operation process, determine the dangerous driving events that occurred during the operation of each vehicle and the location where each dangerous driving event occurred.

[0075] Specifically, in the above step S201, before determining the dangerous driving events that occurred during the operation of each vehicle and the location where each dangerous driving event occurred, the method further includes:

[0076] The operating data of each vehicle collected by the Internet of Vehicles platform during operation is filtered to remove abnormal data in the operating data.

[0077] It can be understood that in the process of collecting vehicle operation data by the Internet of Vehicles, due to problems that may exist in the actual collection process, such as data collection abnormalities, signal interruptions, etc., the collected data may contain abnormal data. For example, the speed of the vehicle collected during a certain period of time is 50, 50, 51, 52, 51, 90, 53, 52, (empty), 52... Each piece of data corresponds to a collection frame, 90 and (empty) are abnormal data, 90 may be due to the abnormality of the collection device causing the collected speed to be too high, (empty) may be due to signal interruption or signal abnormality causing the data not to be uploaded, and thus displayed as empty.

[0078] Therefore, it is necessary to filter the collected operating data to eliminate such abnormal data, so as to ensure the accuracy of the subsequent judgment of dangerous driving events. Specifically, after the corresponding abnormal data is proposed, the data corresponding to the proposed empty acquisition frame can be filled with the intermediate value to facilitate the subsequent judgment of dangerous driving events. It is also possible that when judging dangerous driving events, only when the collected data is continuously in a normal state, the corresponding dangerous driving event judgment is made for the collected data in this period. The specific processing situation can be set according to the actual situation.

[0079] Specifically, in step S201, based on the operation data of each vehicle collected by the vehicle networking platform during operation, the dangerous driving events that occurred during the operation of each vehicle and the locations where each dangerous driving event occurred are determined, including:

[0080] Step S201 - 1 , determining the real-time running speed and geographical location of each vehicle during the running process according to the running data of each vehicle during the running process.

[0081] It can be understood that the vehicle operation data collected by the Internet of Vehicles includes multiple types of data, such as vehicle power, engine speed, vehicle speed, vehicle location, etc. Among these data, the data required for determining dangerous driving events of vehicles is the real-time speed and geographical location of the vehicle.

[0082] Step S201-2, judging whether a dangerous driving event occurs in the vehicle according to the change of the real-time running speed.

[0083] The determination of dangerous driving events is mainly based on the changes in vehicle speed during vehicle operation. For example, when the vehicle's deceleration is too large and lasts longer than the preset event, it can be determined that the vehicle has experienced a dangerous driving event of sudden deceleration; when the vehicle's speed is not 0 for a long time, that is, it is in a running state for a long time, it can be determined that the driver of the vehicle has experienced a dangerous driving event of fatigue driving. Similarly, the corresponding dangerous driving event evaluation rules can be specified according to the actual operating conditions related to various dangerous driving events, which will not be repeated here.

[0084] Step S201 - 3 : if a dangerous driving event occurs, the current geographical location of the vehicle is marked as the location where the dangerous driving event occurred.

[0085] When the Internet of Vehicles platform determines that a dangerous driving incident has occurred in the vehicle based on the vehicle's operating data, it will determine the specific geographic location of the current vehicle and mark it as the location where the dangerous driving incident occurred to facilitate subsequent related statistics.

[0086] Specifically, dangerous driving incidents include: emergency braking, fatigue driving and speeding;

[0087] In step S201-2, judging whether a dangerous driving event occurs to the vehicle according to the change of the real-time running speed includes:

[0088] Step S201-2-1, when the vehicle deceleration is greater than a preset value and lasts for more than a first preset time, it is determined that the vehicle has emergency deceleration.

[0089] It can be understood that for a certain vehicle, when the Internet of Vehicles platform determines the dangerous driving event of emergency deceleration based on the real-time operating speed of the vehicle, when the vehicle's deceleration is greater than a preset value such as 8km / h and lasts for more than a preset time, such as two seconds, it is determined that an emergency deceleration has occurred.

[0090] For details, please refer to Figure 3 FIG. 1 is a diagram showing an example of an emergency deceleration determination process according to an embodiment of the present invention.

[0091] When the vehicle's engine is running, the speed data can be collected through specific devices on the vehicle, such as TBOX. The Internet of Vehicles platform will determine whether there are any abnormalities in the speed data. If there are any abnormalities, filtering will be performed to remove the abnormal data. Then it is determined whether the collected speed data is continuous in time, that is, whether there is no corresponding speed data in certain time frames due to signal abnormalities or filtering. If it is not continuous, the time judgment of sudden deceleration will not be performed, and the corresponding time judgment will be performed after new data is collected. If the previous and subsequent times are continuous, it is determined whether the current speed data has a speed deceleration greater than 8km / h and the duration is greater than 2s. If yes, it is determined that a sudden deceleration event has occurred.

[0092] Step S201-2-2: when the vehicle's continuous driving time exceeds a second preset time, it is determined that the vehicle is fatigued.

[0093] Similarly, for a certain vehicle, when the Internet of Vehicles platform determines the dangerous event of fatigue driving based on the real-time operating speed of the vehicle, when the speed of the vehicle is not zero, that is, the time in the running state exceeds the second preset time, such as 4 hours, it is determined that fatigue driving has occurred.

[0094] For details, please refer to Figure 4 As shown in the figure, an example diagram of a fatigue driving determination process according to an embodiment of the present invention is shown. Figure 3 Similarly, when the vehicle's engine is running, the vehicle speed data can be collected through specific devices on the vehicle, such as TBOX. The Internet of Vehicles platform will determine whether there are any abnormalities in the vehicle speed data. If there are any abnormalities, it will filter and remove the abnormal data. Then it will determine whether the vehicle has running data within a continuous interval of 5 minutes. Only when there is running data will subsequent fatigue driving judgment be made. If there is running data within a continuous interval of five minutes, it will determine whether the vehicle's running duration exceeds 4 hours. If it exceeds, it will determine the occurrence of a fatigue driving event.

[0095] Step S201-2-3: when the vehicle speed is greater than the second preset value and the duration exceeds the third preset duration, it is determined that the vehicle is speeding.

[0096] When the Internet of Vehicles platform determines the dangerous event of fatigue driving based on the vehicle's real-time operating speed, if the vehicle's speed is too high, such as exceeding 120km / h, and the duration exceeds the preset time, such as 5 minutes, it is determined that speeding has occurred.

[0097] For details, please refer to Figure 5The embodiment shown is an example diagram of a speeding determination process according to an embodiment of the present invention. Similar to the determination process of the above two types of dangerous driving events, after collecting the vehicle speed data, it is necessary to determine and filter the abnormal data, which will not be repeated here. After completing the filtering process, it is necessary to determine whether the vehicle speed exceeds 120km / h for 5 consecutive minutes. If yes, it is determined that a speeding event has occurred.

[0098] Step S202: Count the occurrence locations and occurrence times of each dangerous driving event in the historical period, and determine the historical occurrence probabilities of dangerous driving events corresponding to each of the plurality of preset areas in the historical period.

[0099] Specifically, in step S202, it includes:

[0100] Step S202-1, dividing the area corresponding to the road risk map to be constructed into a plurality of preset areas.

[0101] It can be understood that the road risk map that is expected to be constructed may correspond to a regional map corresponding to a city or a province. The region can be divided into multiple preset areas, each of which can be a section of traffic road or a subdivision area, such as a district, a village, a street, and other subdivision areas.

[0102] Step S202-2, based on the location and time of occurrence of each dangerous driving event, count the number of vehicles in each preset area that have experienced dangerous driving events within a historical period.

[0103] Since the specific location of a dangerous driving incident will be marked when it is determined, and the corresponding timestamp will be recorded in the Internet of Vehicles platform, the number of vehicles that have experienced dangerous driving incidents in the historical period can be counted for each preset area, for example, the number of vehicles that have experienced dangerous driving incidents in a preset area A in the past two weeks. Furthermore, when counting, the number of vehicles that have experienced dangerous driving incidents on a daily basis can be subdivided to facilitate refined statistics.

[0104] Step S202-3, counting the total number of vehicles passing through each preset area during a historical period based on the operation data of each vehicle.

[0105] For the Internet of Vehicles platform, the location information of each vehicle operation data within the historical period can be called up to count the total number of vehicles passing through each preset area within the historical period.

[0106] Step S202-4, determining the historical occurrence probability of dangerous driving events corresponding to each of a plurality of preset areas in a historical period according to the total number of vehicles and the number of vehicles having dangerous driving events.

[0107] For each preset area, after determining the number of vehicles that have experienced dangerous driving incidents in the historical period and the total number of vehicles traveling in the same area, the two can be compared to determine the historical probability of dangerous driving incidents in the historical period. Further, the historical period can be refined and statistically analyzed to determine the historical probability of dangerous driving incidents for each day in the historical period. The historical probability of dangerous driving incidents in the historical period includes: the historical probability of occurrence corresponding to each day in the historical period, so as to facilitate the subsequent analysis and evaluation of the current probability of occurrence.

[0108] Step S203 , evaluating and analyzing the historical occurrence probability of dangerous driving events in the historical period, and obtaining the current occurrence probability of dangerous driving events in each preset area.

[0109] Specifically, the historical period includes multiple historical sub-periods.

[0110] For example, the historical period may be the past four weeks, where each week corresponds to a historical sub-period.

[0111] In step S203, the historical occurrence probability of dangerous driving events in the historical period is evaluated and analyzed to obtain the current occurrence probability of dangerous driving events in each preset area, including:

[0112] Step S203 - 1 : for each preset area, determine the historical occurrence probability of a dangerous driving event corresponding to the preset area in each historical sub-period.

[0113] It can be understood that for each preset area, before evaluating the current probability of occurrence based on the historical probability of occurrence of dangerous driving events, the historical probability of occurrence of dangerous driving events in each historical sub-period within the historical period can be determined first. For example, the historical period can be the past 4 weeks, where each week corresponds to a historical sub-period, and the historical probability of occurrence corresponding to each historical sub-period is determined based on the above-mentioned relevant statistical information. The specific statistical method of the historical probability of occurrence of each sub-period can refer to the above-mentioned statistical related steps, or it can be counted in advance when counting dangerous driving events in the historical period, so as to facilitate direct call, which will not be repeated here.

[0114] Step S203-2, determining the current occurrence probability of dangerous driving events in the preset area according to the preset weights corresponding to each historical sub-period and the historical occurrence probability of dangerous driving events.

[0115] For each historical sub-period, a corresponding preset weight may be preset, so that the historical probability of occurrence of a dangerous driving event corresponding to each historical sub-period is multiplied by the corresponding preset weight to determine the current probability of occurrence.

[0116] For example, the historical period is the past four weeks, and it is assumed that the historical probability of dangerous driving events corresponding to these four weeks is 0.1, 0.2, 0.2, and 0.1. The corresponding preset weights are 0.1, 0.2, 0.3, and 0.4. After calculation, the current probability of dangerous driving events corresponding to the current week is the weighted calculation of the historical probability of occurrence and the corresponding preset weight, that is, 0.01+0.04+0.06+0.04=0.15. Specifically, in actual evaluation, a more complex and more accurate prediction and evaluation method can be combined. The above evaluation method is only an exemplary implementation method and is not limited here. The selection of mathematical analysis methods can be combined with actual practice. For example, the corresponding evaluation prediction can be carried out through spatiotemporal aggregation algorithm and redundancy algorithm.

[0117] For example, when the relevant map platform uses the spatiotemporal aggregation algorithm and the redundancy algorithm to make corresponding assessment and prediction, it mainly aggregates the events such as sudden deceleration, fatigue driving, speeding, etc. according to the time and location based on the longitude and latitude information, and counts and judges the events and their degree (scope) based on the vehicle flow and the proportion of vehicles in the event. The margins of the statistical area are based on the longitude and latitude aggregation of the vehicles reporting the event, and the progress of the event is judged based on the vehicle's operating status (speed, location): identification of sudden deceleration, fatigue driving, speeding and other areas, and the distribution of changes in speed and duration, statistical event size, event authenticity and event scope. According to the dynamic event changes, the trend of the time and region of the impact is statistically analyzed.

[0118] Step S204: construct a road condition risk map according to the current probability of occurrence of dangerous driving events in each preset area.

[0119] Specifically, in step S204, a road condition risk map is constructed according to the current occurrence probability of dangerous driving events in each preset area, including:

[0120] A road condition risk map is constructed based on the current probability of emergency braking, fatigue driving and speeding in each preset area.

[0121] It can be understood that the dangerous driving events mentioned above may include the three different types of dangerous driving events, namely, emergency braking, fatigue driving, and speeding. The current probability of occurrence of each type of dangerous driving event can be determined using the above steps, which will not be repeated here.

[0122] When constructing a risky road condition map, various types of dangerous driving events can be displayed accordingly in the risky road condition map, and the specific display method can be set according to the actual situation.

[0123] The method for constructing a road condition risk map based on vehicle operation data provided in this embodiment analyzes the collected vehicle operation data through the Internet of Vehicles platform, determines the dangerous driving events that occurred during the vehicle operation process, and counts the occurrence locations and events corresponding to each dangerous driving event in the historical period, so as to obtain the historical occurrence probability of dangerous driving events corresponding to each preset area, thereby analyzing the current probability of occurrence of dangerous driving events in each preset area, and constructing a risky road condition map, so as to realize the construction of a risky road condition map corresponding to dangerous driving events only by analyzing vehicle big data, thereby reducing the construction cost of the risky road condition map, and the constructed risky road condition map can enable the driver to understand the risk status of the current area in advance, so as to avoid driving risks in time and ensure driving safety.

[0124] The construction process of the risk road condition map in the above method embodiment can be assisted by the following content: when the vehicle is working, a scheduled task is started to determine whether events such as sudden deceleration, fatigue driving, speeding, etc. occur; after the event occurs, the time, current status, and corresponding location information are counted according to the category, and the statistics are reported; the industry data platform determines the reliability of the event based on the spatiotemporal aggregation and redundancy algorithm of the events transmitted by each enterprise; a map layer is generated for the event and published on the navigation map of each map supplier.

[0125] Specifically, when performing event determination, it is mainly achieved through the following steps:

[0126] First, data is collected when the engine is running, and it is determined whether there are data anomalies between the continuous vehicle speed data, and filtered. It is determined whether the time interval between vehicle speed collection exceeds a certain time threshold (sudden deceleration, fatigue driving, speeding, etc. will take at least a certain time threshold to complete). It is determined whether the vehicle position changes after a certain time threshold (there may be changes in the fuel tank due to missing data), and sudden deceleration, fatigue driving, speeding and other events are generated according to the judgment rules for each type of time, and the platform performs statistical analysis.

[0127] The implementation logic of the overall method embodiment is to use the time series data change curve of the vehicle speed, position, and time data detected by the vehicle-mounted TBOX for regional safety event identification (the number of vehicles with hazard warning lights turned on), ensure the robustness of behavior identification such as sudden deceleration, fatigue driving, and speeding, and reduce the omission and loss of information. At the same time, in the process of identifying events, the decision regression tree method is introduced to reduce the interference of sensor noise and improve the recognition accuracy.

[0128] Based on the reporting of map events (safety incidents, sudden deceleration, speeding, etc.), combined with vehicle location information and speed change relationships, machine learning is used, and then the data consistency within the regional range is used to judge the accuracy of the event. The industry's Internet of Vehicles real-time vehicle operation data (vehicle speed, time, longitude and latitude) is used to correct different functional logics and improve the accuracy of the functions.

[0129] Based on the vehicle speed, position, and time data received by the Internet of Vehicles, data quality is verified, data offset data and abnormal data (front and back deviations greater than 5%) are filtered out, a valid and reasonable data range (5-100%) is identified, and front and back vehicle speed, position, and time data are identified to be greater than a certain difference, and the occurrence of events is identified (sudden deceleration, fatigue driving, speeding, etc. generally require more than a certain time threshold to complete, and the specific algorithm threshold refers to the map layer algorithm).

[0130] Specifically, when collecting statistics on dangerous driving events, the naive Bayes algorithm can be used to perform statistical analysis at each time, as follows:

[0131] Taking the emergency braking time as an example, H is used to represent the vehicle speed, and the vehicle speed change is divided into 1, 2, and 3 levels, represented by h1, h2, and h3 respectively, representing emergency deceleration events of different deceleration levels.

[0132] The geographical range is represented by G, and is also divided into 1, 2, and 3 levels, represented by g1, g2, and g3 respectively. In addition, the time is represented by W, and is divided into 1 and 2 levels. The last week and one week ago are represented by w1 and w2 respectively.

[0133] Through past and current data, we can calculate the probability of h and g appearing when sudden deceleration, fatigue driving, speeding, etc., that is, P(H|W) and P(G|W).

[0134] Where H, G, and W are within the previously mentioned classification range. Assuming that the speed change H and the geographical range G are relatively independent, the probability of an event in a certain week is:

[0135] P=P(W|G,H)=P(W|G)*P(W|H);

[0136] It can be converted to: P = [P(G|W)P(W) / P(G)]*[P(H|W)P(W) / P(H)].

[0137] In the above formula, P(G|W) and P(H|W) are the previously calculated probabilities, and P(W) is the probability of sudden deceleration, fatigue driving, speeding and other events within a week and a week ago. The probability P(W1) of sudden deceleration, fatigue driving, speeding and the like within a week and the probability P(W2) a week ago can be calculated, while P(G) and P(H) are constants for each category.

[0138] Probability of sudden deceleration, fatigue driving, speeding, etc. within a week:

[0139] P1=P(w1|G,H)=[P(G|W1)P(W1) / P(G)]*[P(H|W1)P(W1) / P(H)];

[0140] Probability of sudden deceleration, fatigue driving, speeding, etc. one week ago:

[0141] P2=P(w2|G,H)=[P(G|W2)P(W2) / P(G)]*[P(H|W2)P(W2) / P(H)];

[0142] When all the terms on the right side of the equation are known, for example, the speed change on a certain day is h1, and the area range is g1, then compare the size of P1 and P2 to predict the probability of the current dangerous driving event.

[0143] General Naive Bayes Classification:

[0144] 1. Let x = / a1,a2,.......a m / is an item to be classified, and each a is a characteristic attribute of x (vehicle speed, time, area).

[0145] 2. Classified collections C= / y1,y2,.......y n / .

[0146] 3. Calculate P(y1|x), P(y2|x), ..., P(y n |x), sudden deceleration, fatigue driving, speeding and other areas (range, time, vehicle density).

[0147] The calculated information is mapped to the map to compare changes in sudden deceleration, fatigue driving, speeding, etc.

[0148] This solution uses big data tools to collect and process signals and time series data related to vehicle speed, location, etc., and processes based on this data to achieve a highly robust recognition method for the spatiotemporal characteristics of mobile vehicle behavior in the Internet of Vehicles big data scenario. Based on second-level continuous data, it is used to identify events and location information such as sudden deceleration, fatigue driving, and speeding. Its advantages are: high real-time performance, map data is updated once a certain time threshold; low cost, vehicles do not need to be equipped with any sensors, and vehicles from car manufacturers do not need any hardware installation; easy to use, according to the algorithm to update the layer in real time, can timely obtain sudden deceleration, fatigue driving, speeding and other events; high safety, can timely identify sudden deceleration, fatigue driving, speeding and other events, and promptly notify users and surrounding car owners.

[0149] In this embodiment, a device for constructing a road risk map based on vehicle operation data is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0150] This embodiment provides a device for constructing a road condition risk map based on vehicle operation data, such as Figure 6 As shown, including:

[0151] The dangerous event determination module 401 is used to determine the dangerous driving events that occur during the operation of each vehicle and the location where each dangerous driving event occurs based on the operation data of each vehicle collected by the vehicle networking platform during the operation.

[0152] The historical probability statistics module 402 is used to count the occurrence locations and occurrence times of each dangerous driving event in the historical period, and determine the historical occurrence probability of the dangerous driving event corresponding to each of the multiple preset areas in the historical period.

[0153] The current probability evaluation module 403 is used to evaluate and analyze the historical occurrence probability of dangerous driving events in the historical period to obtain the current occurrence probability of dangerous driving events in each preset area.

[0154] The risk map construction module 404 is used to construct a road condition risk map according to the current probability of occurrence of dangerous driving events in each preset area.

[0155] In some optional implementations, the dangerous event determination module 401, when determining the dangerous driving events occurring during the operation of each vehicle and the occurrence locations of each dangerous driving event based on the operation data of each vehicle collected by the Internet of Vehicles platform during the operation, includes:

[0156] According to the running data of each vehicle during the running process, the real-time running speed and geographical location of each vehicle during the running process are determined;

[0157] Determine whether the vehicle has a dangerous driving incident based on the changes in real-time running speed;

[0158] If a dangerous driving incident occurs, the vehicle's current geographic location is marked as the location where the dangerous driving incident occurred.

[0159] In some optional embodiments, dangerous driving events include: emergency braking, fatigue driving and speeding;

[0160] The dangerous event determination module 401, when judging whether a dangerous driving event occurs to the vehicle according to the change of the real-time running speed, includes:

[0161] When the vehicle deceleration is greater than a preset value and lasts for more than a first preset time, it is determined that the vehicle has emergency deceleration;

[0162] When the vehicle continues to travel for more than a second preset time, it is determined that the vehicle is fatigued;

[0163] When the vehicle speed is greater than the second preset value and lasts for longer than the third preset time, it is determined that the vehicle is speeding.

[0164] In some optional implementations, the historical probability statistics module 402, when counting the occurrence locations and occurrence times of each dangerous driving event in the historical period, determines the historical occurrence probabilities of dangerous driving events corresponding to each of the plurality of preset areas in the historical period, includes:

[0165] Divide the area corresponding to the road condition risk map to be constructed into multiple preset areas;

[0166] According to the location and time of each dangerous driving incident, the number of vehicles involved in dangerous driving incidents in each preset area during the historical period is counted;

[0167] According to the operation data of each vehicle, the total number of vehicles passing through each preset area in the historical period is counted;

[0168] The historical occurrence probabilities of dangerous driving events corresponding to each of a plurality of preset areas in a historical period are determined according to the total number of vehicles and the number of vehicles involved in the dangerous driving events.

[0169] In some optional embodiments, the historical period includes a plurality of historical sub-periods;

[0170] The current probability evaluation module 403 evaluates and analyzes the historical probability of dangerous driving events in the historical period to obtain the current probability of dangerous driving events in each preset area, including:

[0171] For each preset area, determining the historical occurrence probability of dangerous driving events corresponding to each historical sub-period in the preset area;

[0172] The current probability of occurrence of dangerous driving events in the preset area is determined according to the preset weights corresponding to each historical sub-period and the historical probability of occurrence of dangerous driving events.

[0173] In some optional implementations, the risk map construction module 404, when constructing a road condition risk map according to the current occurrence probability of dangerous driving events in each preset area, includes:

[0174] A road condition risk map is constructed based on the current probability of emergency braking, fatigue driving and speeding in each preset area.

[0175] In some optional implementations, before determining the dangerous driving events that occurred during the operation of each vehicle and the locations where each dangerous driving event occurred, the dangerous event determination module 401 is further used to:

[0176] The operating data of each vehicle collected by the Internet of Vehicles platform during operation is filtered to remove abnormal data in the operating data.

[0177] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0178] The road condition risk map construction device based on vehicle operation data in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0179] The embodiment of the present invention also provides a computer device having the above Figure 6 The device shown is a road condition risk map construction device based on vehicle operation data.

[0180] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0181] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0182] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0183] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0184] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0185] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0186] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0187] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0188] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for constructing a road condition risk map based on vehicle operation data, characterized in that: The method comprises: Based on the operation data of each vehicle collected by the Internet of Vehicles platform during operation, determine the dangerous driving events that occurred during the operation of each vehicle and the location where each dangerous driving event occurred; Counting the locations and times of each dangerous driving incident in the historical period, and determining the historical probability of dangerous driving incidents corresponding to each of the multiple preset areas in the historical period; Evaluate and analyze the historical probability of dangerous driving events in the historical period to obtain the current probability of dangerous driving events in each preset area; Construct a road risk map based on the current probability of dangerous driving incidents in each preset area.

2. The method according to claim 1, characterized in that The operation data of each vehicle collected by the vehicle networking platform during operation is used to determine the dangerous driving events that occurred during the operation of each vehicle and the locations where each dangerous driving event occurred, including: Determine the real-time running speed and geographical location of each vehicle during the running process according to the running data of each vehicle during the running process; Determine whether the vehicle has a dangerous driving incident based on the changes in real-time running speed; If a dangerous driving event occurs, the current geographic location of the vehicle is marked as the location where the dangerous driving event occurred.

3. The method according to claim 2, characterized in that The dangerous driving incidents include: emergency braking, fatigue driving and speeding; The determining whether a dangerous driving event occurs to the vehicle according to the change in the real-time running speed includes: When the vehicle deceleration is greater than a preset value and lasts for a period longer than a first preset period, determining that the vehicle has experienced emergency deceleration; When the vehicle continues to travel for more than a second preset time, it is determined that the vehicle is fatigued; When the vehicle speed is greater than a second preset value and lasts for longer than a third preset time, it is determined that the vehicle is speeding.

4. The method according to claim 1, characterized in that: The statistically analyzing the occurrence locations and occurrence times of each dangerous driving event in the historical period, and determining the historical occurrence probabilities of dangerous driving events corresponding to each of the plurality of preset areas in the historical period, includes: Divide the area corresponding to the road condition risk map to be constructed into multiple preset areas; According to the location and time of each dangerous driving incident, the number of vehicles involved in dangerous driving incidents in each preset area during the historical period is counted; According to the operation data of each vehicle, the total number of vehicles passing through each preset area in the historical period is counted; The historical occurrence probabilities of dangerous driving events corresponding to each of a plurality of preset areas in a historical period are determined according to the total number of vehicles and the number of vehicles having dangerous driving events.

5. The method according to claim 1, characterized in that: The historical period includes a plurality of historical sub-periods; The evaluating and analyzing the historical occurrence probability of dangerous driving events in the historical period to obtain the current occurrence probability of dangerous driving events in each preset area includes: For each preset area, determining the historical occurrence probability of a dangerous driving event corresponding to each historical sub-period in the preset area; The current occurrence probability of the dangerous driving event in the preset area is determined according to the preset weights corresponding to the historical sub-periods and the historical occurrence probability of the dangerous driving event.

6. The method according to claim 3, characterized in that: The construction of a road condition risk map according to the current probability of occurrence of dangerous driving events in each preset area includes: A road condition risk map is constructed based on the current probability of emergency braking, fatigue driving and speeding in each preset area.

7. The method according to claim 1, characterized in that Before determining the dangerous driving events that occurred during the operation of each vehicle and the locations where each dangerous driving event occurred, the method further includes: The operation data of each vehicle collected by the vehicle networking platform during operation is filtered to remove abnormal data in the operation data.

8. A device for constructing a road condition risk map based on vehicle operation data, characterized in that: The device comprises: A dangerous event determination module is used to determine the dangerous driving events that occurred during the operation of each vehicle and the location of each dangerous driving event based on the operation data of each vehicle collected by the vehicle networking platform during the operation; The historical probability statistics module is used to count the location and time of each dangerous driving event in the historical period, and determine the historical probability of dangerous driving events corresponding to each of the multiple preset areas in the historical period; A current probability evaluation module is used to evaluate and analyze the historical probability of dangerous driving events in the historical period to obtain the current probability of dangerous driving events in each preset area; The risk map construction module is used to construct a road condition risk map based on the current probability of dangerous driving events in each preset area.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for constructing a road condition risk map based on vehicle operation data according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for constructing a road condition risk map based on vehicle operation data according to any one of claims 1 to 7.

Images