A method, device and equipment for identifying abnormal vehicle data

Abstract

An abnormal vehicle data identification method, device and equipment are disclosed in the embodiments of this specification. It includes: obtaining first vehicle operation data collected by a data acquisition device for a target vehicle, determining a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data, judging whether a lane is included in the geographical area corresponding to the target map grid, and if the judgment result indicates that no lane is included in the geographical area corresponding to the target map grid, determining the first vehicle operation data as abnormal vehicle data. When determining abnormal vehicle data, this solution does not need to use a spatial comparison method between adjacent trajectory points for the vehicle operation data to be identified, but only based on the single vehicle operation data itself, it can be determined whether the vehicle operation data is abnormal vehicle data, thereby improving the simplicity and operation efficiency of the abnormal vehicle data identification method.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device and equipment for identifying abnormal vehicle data. Background Art

[0002] When an autonomous driving vehicle is driving on a lane, it is necessary to collect the operation data of the autonomous driving vehicle in real time. The platform analyzes and plans the operation status of the vehicle based on the collected real-time operation data of the vehicle. The real-time vehicle operation data collected by the vehicle data collection equipment usually contains vehicle positioning data. Due to the limitations of the current development of positioning technology, the positioning accuracy of its vehicle positioning data has certain errors. At the same time, due to the influence of uncertain factors such as weather, ionosphere, and building obstruction, the collected vehicle operation data also has certain random deviations. Since the operation planning and collaborative services of the autonomous driving planning platform for vehicles mainly rely on the above-mentioned collected vehicle operation data, it is necessary to eliminate abnormal vehicle operation data to improve the accuracy of the vehicle operation data participating in the platform calculation.

[0003] The method of eliminating abnormal vehicle operation data in the prior art mainly adopts a spatial comparison method between multiple offline vehicle operation data. Each vehicle operation data needs to be calculated and compared with other vehicle operation data for multiple times to find out the vehicle operation data that is abnormal relative to other vehicle operation data. Therefore, the prior art requires the server to perform a large amount of calculations on multiple vehicle operation data to distinguish abnormal vehicle operation data, which requires a large amount of computing resources of the server.

[0004] Therefore, how to simply and quickly determine whether vehicle operation data is abnormal vehicle data has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of this specification provide a method, device and equipment for identifying abnormal vehicle data, which can determine whether the vehicle operation data is abnormal vehicle data based on the single vehicle operation data itself, without the need for each vehicle operation data to be calculated and compared multiple times with other vehicle operation data, thereby improving the simplicity of judging abnormal vehicle data.

[0006] To solve the above technical problems, the embodiments of this specification are implemented as follows:

[0007] A method for identifying abnormal vehicle data, comprising:

[0008] Acquire first vehicle operation data collected from a target vehicle using a data collection device.

[0009] Determine a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; the target map grid is obtained by dividing a map corresponding to a target geographical area into grids.

[0010] Judge whether the geographical area corresponding to the target map grid contains lanes, and obtain a first judgment result.

[0011] If the first judgment result indicates that the geographical area corresponding to the target map grid does not contain lanes, determine the first vehicle operation data as abnormal vehicle data.

[0012] An abnormal vehicle data recognition device includes:

[0013] A first acquisition module, configured to acquire first vehicle operation data collected for a target vehicle by using a data acquisition device.

[0014] A first determination module, configured to determine a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; the target map grid is obtained by dividing a map corresponding to a target geographical area into grids.

[0015] A first judgment module, configured to judge whether the geographical area corresponding to the target map grid contains lanes, and obtain a first judgment result.

[0016] A second determination module, configured to determine the first vehicle operation data as abnormal vehicle data if the first judgment result indicates that the geographical area corresponding to the target map grid does not contain lanes.

[0017] An abnormal vehicle data recognition device includes:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein

[0020] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to:

[0021] Acquire first vehicle operation data collected for a target vehicle by using a data acquisition device.

[0022] Determine a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; the target map grid is obtained by dividing a map corresponding to a target geographical area into grids.

[0023] Determine whether the geographical area corresponding to the target map grid contains a lane to obtain a first determination result.

[0024] If the first determination result indicates that the geographical area corresponding to the target map grid does not contain a lane, then determine the first vehicle operation data as abnormal vehicle data.

[0025] At least one embodiment provided in this specification can achieve the following beneficial effects:

[0026] Based on a single vehicle operation data itself, it can be determined whether the vehicle operation data is abnormal vehicle data, without performing multiple calculations and comparisons between multiple vehicle operation data, so as to avoid the server performing multiple calculations on a large amount of vehicle operation data to distinguish abnormal vehicle data, thereby causing excessive waste of the server's computing resources. Thus, the simplicity and efficiency of determining abnormal vehicle data, as well as the reasonable utilization of the server's computing resources, can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0028] Figure 1 It is a schematic flowchart of a method for identifying abnormal vehicle data provided in an embodiment of this specification;

[0029] Figure 2 It is a schematic diagram of a map grid provided in an embodiment of this specification;

[0030] Figure 3 It is provided in an embodiment of this specification corresponding to Figure 1 a schematic structural diagram of an apparatus for identifying abnormal vehicle data;

[0031] Figure 4 It is provided in an embodiment of this specification corresponding to Figure 1 a schematic structural diagram of a device for identifying abnormal vehicle data. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the following will clearly and completely describe the technical solutions of one or more embodiments of this specification in conjunction with specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by one or more embodiments of this specification.

[0033] The following will detail the technical solutions provided by each embodiment of this application in conjunction with the drawings.

[0034] Figure 1 It is a schematic flowchart of a method for identifying abnormal vehicle data provided by an embodiment of this specification. From a program perspective, the execution entity of this process can be an abnormal vehicle data detection device, or an application program installed on the abnormal vehicle data detection device. As Figure 1 shown, this process may include the following steps:

[0035] Step 102: Obtain the first vehicle operation data collected for the target vehicle by the data collection device.

[0036] In the embodiments of this specification, the target vehicle can be any vehicle monitored by the autonomous driving planning platform. The data collection device can be an on-board unit (OBU) or a roadside unit (RSU). The on-board unit can collect the vehicle operation data of the vehicle during driving, and the roadside unit can also collect the vehicle operation data of the vehicle through sensors during driving. The first vehicle operation data can be the vehicle operation data at the current moment collected by the data collection device, or the vehicle operation data collected by the data collection device at any previous moment. The vehicle operation data can include information such as vehicle number, vehicle positioning information, vehicle driving speed, vehicle driving heading angle, and the collection time of vehicle data. The data collection device can send the collected vehicle operation data to the autonomous driving planning platform through the wireless base station network, so that the autonomous driving planning platform can make decisions and plans for the automatic driving of the vehicle based on the vehicle operation data collected by the data collection device.

[0037] Step 104: Determine the target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; the target map grid is obtained by dividing the map corresponding to the target geographical area into grids.

[0038] In the embodiments of this specification, the target geographical area is a preset area range set in advance for the planned driving route of the target vehicle. According to the planned driving route of the target vehicle, the target geographical area can be set as the range covered by extending a preset distance around any lane. For example, the area range formed by extending 500 meters north and south along Jianguo Road in Beijing; the target geographical area can also be set as the range covered by any district included in any city. For example, the area covered by Haidian District in Beijing; the target geographical area can also be set as the range covered by any city. For example, the area covered by Beijing. The present invention does not specifically limit the size of the coverage range of the target geographical area.

[0039] In the embodiments of this specification, the map corresponding to the target geographical area is processed into a grid according to a preset rule. The way of grid processing can be to plan m lines in the east-west direction and n lines in the north-south direction for the corresponding map range, and divide the above map range into m×n map grids. The size of each map grid can be the same, or the size of some map grids can be the same, or the size of each map grid can be different. The shape of each map grid can be a regular figure or an irregular figure, and adjacent map grids can be seamlessly connected so that the sum of the areas of the m×n map grids is equal to the area of the above map range. The present invention does not specifically limit the size and shape of each map grid.

[0040] In the embodiments of this specification, according to the first vehicle operation data, the real-time position of the vehicle when the first vehicle operation data is collected can be determined. Find the corresponding position of this real-time position on the map, and determine the map grid to which the corresponding position belongs as the target map grid. For example, when the position of the vehicle when the first vehicle operation data is collected is determined according to the first vehicle operation data as "100 meters west of the intersection of Jianguo Road and Xidawang Road", then this "100 meters west of the intersection of Jianguo Road and Xidawang Road" can be found on the map corresponding to the target geographical area, and then check the map grid to which "100 meters west of the intersection of Jianguo Road and Xidawang Road" belongs. Assuming that the map grid to which it belongs is the a-th map grid, then the a-th map grid is the determined target map grid.

[0041] In the embodiments of this specification, such as Figure 2As shown in the figure, the target map grid where the target vehicle is located may include the following scenarios. When the location of the target vehicle is location d, map grid k is determined as the target map grid; when the location of the target vehicle is location g, any one of map grid I and map grid J is determined as the target map grid; when the location of the target vehicle is location z, any one of map grid E, map grid F, map grid I, and map grid J is determined as the target map grid.

[0042] Step 106: Determine whether the geographical area corresponding to the target map grid contains a lane, and obtain a first determination result.

[0043] In the embodiments of this specification, the lane is the lane that the target vehicle should travel on, which is planned through prior research on the target geographical area. This should-be-traveled lane can be one lane or n lanes, and the specific lane situation depends on the plan made after actual research. The scenario where the geographical area corresponding to the target map grid contains a lane can be a scenario where there is one lane or n lanes in the corresponding geographical area, or a scenario where only a part of a certain lane exists in the corresponding geographical area, or a scenario where any edge of the corresponding geographical area overlaps with an edge of a certain lane, or a scenario where the distance between any edge of the corresponding geographical area and the center line of a certain lane is less than or equal to a preset distance. This preset distance can be determined according to the requirement for the accuracy of the data result in the actual scenario. The higher the requirement for the accuracy of the data result, the smaller the preset distance; conversely, the lower the requirement for the accuracy of the data result, the larger the preset distance.

[0044] Step 108: If the first determination result indicates that the geographical area corresponding to the target map grid does not contain a lane, then determine the first vehicle operation data as abnormal vehicle data.

[0045] In the embodiments of this specification, if it is determined through judgment that there is no such planned lane in the geographical area corresponding to the target map grid, it is determined that there is no lane in the target area grid, that is, it is indicated that the vehicle position determined according to the first vehicle operation data does not belong to the normal driving position pre-planned for the target vehicle. Therefore, the first vehicle operation data can be determined as abnormal vehicle data.

[0046] Figure 1In the method, whether the vehicle operation data is abnormal vehicle data can be determined based on the single vehicle operation data itself, without performing multiple calculations and comparisons between multiple vehicle operation data, so as to avoid the server having to perform multiple calculations on a large amount of vehicle operation data to distinguish abnormal vehicle data, thereby causing excessive waste of the server's computing resources. Thus, the simplicity and efficiency of judging abnormal vehicle data, as well as the reasonable utilization of the server's computing resources, can be improved.

[0047] Based on Figure 1 In the method, some specific implementation schemes of the method are also provided in the embodiments of this specification, which will be described below.

[0048] The first vehicle operation data may include information such as vehicle number, vehicle positioning information, vehicle driving speed, heading angle of vehicle driving, and acquisition time of vehicle data. Based on this, step 104: Determining the target map grid to which the location of the target vehicle belongs according to the first vehicle operation data may specifically include:

[0049] Obtain the vehicle positioning information for the target vehicle included in the first vehicle operation data.

[0050] Obtain the first position range information of the geographical area covered by each map grid.

[0051] According to the vehicle positioning information and the first position range information, determine the target map grid to which the location of the target vehicle belongs from the map grids.

[0052] In the embodiments of this specification, the first vehicle operation data is parsed, and the vehicle positioning information for the target vehicle is obtained from the parsed data. The vehicle positioning information may be positioning information in the form of longitude and latitude, and its format may be longitude: AA.xxxxxx, latitude: BB.xxxxxx.

[0053] In the embodiments of this specification, for each map grid, the first position range information covered by the map grid on the map is determined. The first position range information may be range information in the form of longitude and latitude, and its format may be (longitude: CC.xxxxxx to DD.xxxxxx, latitude: EE.xxxxxx to FF.xxxxxx).

[0054] In the embodiments of this specification, according to the vehicle positioning information for the target vehicle and the first position range information covered by each map grid, the map grid corresponding to the first position range information including the vehicle positioning information is determined as the target map grid.

[0055] In the embodiments of the present specification, determining the target map grid to which the location of the target vehicle belongs based on the location information in the form of longitude and latitude can reduce the error in determining the location of the vehicle, thereby improving the accuracy of determining the target map grid to which the location of the target vehicle belongs.

[0056] The vehicle location information of the target vehicle can specifically be information in the form of longitude and latitude, and the first position range information of the geographical area covered by each map grid can also be information in the form of longitude and latitude. Based on this, the determining, from the map grids, the target map grid to which the location of the target vehicle belongs according to the vehicle location information and the first position range information may specifically include:

[0057] Obtain the first longitude and the first latitude in the vehicle location information.

[0058] Obtain the second longitude range and the second latitude range in the first position range information.

[0059] Determine whether the first longitude is within the second longitude range and the first latitude is within the second latitude range, and obtain a second determination result.

[0060] If the second determination result indicates that the first longitude is within the second longitude range and the first latitude is within the second latitude range, then determine the map grid corresponding to the first position range information as the target map grid to which the location of the target vehicle belongs.

[0061] In the embodiments of the present specification, the vehicle location information in the form of longitude and latitude is decomposed to obtain the first longitude and the first latitude. The form of the first longitude can be AA.xxxxxx, and the form of the first latitude can be BB.xxxxxx.

[0062] In the embodiments of the present specification, the first position range information in the form of longitude and latitude is decomposed to obtain the second longitude range and the second latitude range. The form of the second longitude range can be (CC.xxxxxx to DD.xxxxxx), and the form of the second latitude range can be (EE.xxxxxx to FF.xxxxxx).

[0063] In the embodiments of this specification, the situation where the first longitude is within the second longitude range may be that the first longitude is the same as a certain second longitude within the second longitude range. For example, if the two end longitudes of the second longitude range are CC.xxxxxx and DD.xxxxxx, and a certain intermediate longitude within the second longitude range is GG.xxxxxx, when the first longitude is any one of CC.xxxxxx, DD.xxxxxx, and GG.xxxxxx, then the first longitude can be regarded as being within the second longitude range. The situation where the first latitude is within the second latitude range is similar to the situation where the first longitude is within the second longitude range, so it will not be elaborated here.

[0064] In the embodiments of this specification, when the first longitude is not within the second longitude range, or the first latitude is not within the second latitude range, the location of the target vehicle is not included in the map grid corresponding to the first location range information. Only when the first longitude is within the second longitude range and the first latitude is within the second latitude range, the location of the target vehicle is included in the map grid corresponding to the first location range information. At this time, the map grid corresponding to the first location range information is the determined target map grid.

[0065] In the embodiments of this specification, according to the first longitude being within the second longitude range and the first latitude being within the second latitude range, when both conditions are met, the map grid corresponding to the first location range information is determined as the target map grid, thereby improving the accuracy of determining the target map grid.

[0066] After determining the target map grid to which the location of the target vehicle belongs, it is also necessary to determine whether the target map grid contains a lane. Based on this, step 106: determining whether the geographical area corresponding to the target map grid contains a lane may specifically include:

[0067] Obtain the lane positioning information of the lane.

[0068] Obtain the second location range information of the geographical area corresponding to the target map grid.

[0069] According to the lane positioning information and the second location range information, determine whether the geographical area corresponding to the target map grid contains a lane.

[0070] In the embodiments of this specification, lane positioning information of a lane is obtained from a map database. The lane positioning information may be a set of positioning information in the form of longitude and latitude, and the format of the longitude and latitude positioning information set may be [longitude and latitude 1 (HH.xxxxxx, II.xxxxxx), longitude and latitude 2 (JJ.xxxxxx, KK.xxxxxx), longitude and latitude 3 (MM.xxxxxx, NN.xxxxxx)... longitude and latitude n (ZZ.xxxxxx, ZZ.xxxxxx)].

[0071] In the embodiments of this specification, the second position range information corresponding to the target map grid on the map is determined. The second position range information may be the same as the first position range information covered by the target map grid, or may be different from the first position range information covered by the target map grid. The second position range information may be range information in the form of longitude and latitude, and its format may be (longitude: from OO.xxxxxx to PP.xxxxxx, latitude: from QQ.xxxxxx to RR.xxxxxx).

[0072] In the embodiments of this specification, it is determined whether a lane is included in the target map grid according to whether the lane positioning information is included in the second position range information. When at least one lane positioning data in the lane positioning information is included in the second position range information, it is determined that a lane is included in the target map grid. When no lane positioning data in the lane positioning information is included in the second position range information, it is determined that no lane is included in the target map grid.

[0073] In the embodiments of this specification, determining whether a lane is included in the target map grid according to the positioning information in the form of longitude and latitude can reduce the error in judging whether there is a lane in the target map grid, thereby improving the accuracy of judging whether there is a lane in the target map grid.

[0074] The lane positioning information of the lane may be information in the form of longitude and latitude, and the second position range information of the geographical area corresponding to the target map grid may also be information in the form of longitude and latitude. Based on this, determining whether a lane is included in the geographical area corresponding to the target map grid according to the lane positioning information and the second position range information may specifically include:

[0075] Obtain the third longitude and the third latitude included in each lane positioning data in the lane positioning information.

[0076] Obtain the fourth longitude range and the fourth latitude range in the second position range information.

[0077] Determine whether there is a preset number of target lane positioning data in the lane positioning information, where the third longitude of the target lane positioning data is within the fourth longitude range and the third latitude of the target lane positioning data is within the fourth latitude range, to obtain a third judgment result.

[0078] If the third judgment result indicates that there is a preset number of the target lane positioning data, determine that the geographical area corresponding to the target map network contains lanes.

[0079] If the third judgment result indicates that there is no preset number of the target lane positioning data, determine that the geographical area corresponding to the target map network does not contain lanes.

[0080] In the embodiments of this specification, the lane positioning information may be a set of lane positioning data in the form of longitude and latitude. Arbitrarily select a lane positioning data b from the above set of lane positioning data, decompose the lane positioning data b in the form of longitude and latitude to obtain a third longitude and a third latitude. The form of the third longitude may be HH.xxxxxx, and the form of the third latitude may be II.xxxxxx.

[0081] In the embodiments of this specification, decompose the second position range information in the form of longitude and latitude to obtain a fourth longitude range and a fourth latitude range. The form of the fourth longitude range may be (OO.xxxxxx to PP.xxxxxx), and the form of the fourth latitude range may be (QQ.xxxxxx to RR.xxxxxx).

[0082] In the embodiments of this specification, the situation where the third longitude is within the fourth longitude range may be that the third longitude is the same as a certain fourth longitude within the fourth longitude range. For example: The two end longitudes of the fourth longitude range are OO.xxxxxx and PP.xxxxxx, and a certain intermediate longitude within the fourth longitude range is YY.xxxxxx. When the third longitude is any one of OO.xxxxxx, PP.xxxxxx, and YY.xxxxxx, then the third longitude can be regarded as being within the fourth longitude range. The situation where the third latitude is within the fourth latitude range is similar to the situation where the third longitude is within the fourth longitude range, so it will not be elaborated here.

[0083] In the embodiments of this specification, when the third longitude is not within the fourth longitude range or the third latitude is not within the fourth latitude range, it is determined that the above-mentioned lane positioning data b is not within the second position range information. Only when the third longitude is within the fourth longitude range and the third latitude is within the fourth latitude range, it is determined that the above-mentioned lane positioning data b is within the second position range information. According to the same method, it is determined whether other lane positioning data in the above-mentioned lane positioning data set is within the second position range information. If there is a preset number of lane positioning data b within the second position range information in the above-mentioned lane positioning data set, it is determined that the geographical area corresponding to the target map network contains lanes. If there is no preset number of lane positioning data b within the second position range information in the above-mentioned lane positioning data set, it is determined that the geographical area corresponding to the target map network does not contain lanes. It should be noted that the above-mentioned preset number is associated with the accuracy of determining the existence of lanes within the target map grid. When the preset number is larger, the accuracy of determining the existence of lanes within the target map grid is higher. On the contrary, when the preset number is smaller, the accuracy of determining the existence of lanes within the target map grid is lower. In the solution of the present invention, the specific value of the above-mentioned preset number is not specifically limited.

[0084] In the embodiments of this specification, according to the third longitude being within the fourth longitude range and the third latitude being within the fourth latitude range, only when both conditions are met can it be determined that the corresponding lane positioning data is within the second position range information, and then it can be determined that the geographical area corresponding to the target map network contains lanes, thereby improving the accuracy of determining whether there are lanes within the target map grid.

[0085] Due to the influence of the current positioning technology, there will be a certain error in the accuracy of the positioning information data. If there are lanes within the target map grid and the positioning information data of the lanes deviates by a certain distance due to the error, resulting in the positioning information data of the lanes not being within the target map grid, an error will occur in the judgment of the lanes within the target map grid at this time. Based on this, the obtaining of the second position range information of the geographical area corresponding to the target map grid may specifically include:

[0086] Expand the geographical area covered by the target map grid according to a preset distance to obtain the expanded geographical area corresponding to the target map grid.

[0087] Determine the position range information of the expanded geographical area to obtain the second position range information.

[0088] In the embodiments of this specification, the preset distance can be selected as the width of a lane. The geographical area covered by the target map grid is expanded by a distance equal to the width of a lane in all directions, and the position range information of the geographical area covered after the expansion of the target map grid is determined as the second position range information. It should be noted that the preset distance can also be other values than the width of a lane, as long as the accuracy of determining the first vehicle operation data as normal operation data can be improved after the target map grid is expanded by this value.

[0089] In the embodiments of this specification, after the target map grid is expanded by the preset distance, it is determined whether there is a lane in the corresponding geographical area after the expansion, so as to avoid missing the lanes at the edge of the geographical area covered by the target map grid before the expansion, and further improve the accuracy of determining the first vehicle operation data as normal operation data.

[0090] Based on the fact that there is no lane in the target map grid, abnormal vehicle data with a large degree of abnormality can be excluded, but abnormal vehicle data with a small degree of abnormality cannot be excluded. Based on this, step 106: After obtaining the first judgment result by determining whether the geographical area corresponding to the target map network contains a lane, it may further include:

[0091] If the first judgment result indicates that the geographical area corresponding to the target map grid contains a lane, obtain the second vehicle operation data recognized as normal vehicle operation data; the time difference between the first acquisition time of the first vehicle operation data and the second acquisition time of the second vehicle operation data is less than a preset threshold.

[0092] According to the vehicle driving speed and data acquisition time respectively included in the first vehicle operation data and the second vehicle operation data, calculate the first moving distance of the target vehicle, where the first moving distance represents the estimated driving distance of the target vehicle between the second acquisition time and the first acquisition time.

[0093] According to the vehicle positioning information respectively included in the first vehicle operation data and the second vehicle operation data, calculate the second moving distance of the target vehicle, where the second moving distance represents the distance traveled by the target vehicle in the target lane between the second acquisition time and the first acquisition time, and the target lane is the lane where the target vehicle is located determined according to the vehicle positioning information.

[0094] According to the distance difference between the first moving distance and the second moving distance, determine whether the first vehicle operation data is abnormal vehicle data.

[0095] In the embodiments of this specification, when it is determined that there is a lane in the target map grid, the result determined at this time, "the first vehicle operation data is normal vehicle data", is a result with relatively low accuracy. To improve the accuracy of the determination result of "the first vehicle operation data is normal vehicle data", we also need to obtain the second vehicle operation data, which is the vehicle operation data identified as normal vehicle operation data. Since the first vehicle operation data can be the vehicle operation data collected at any time, then the second vehicle operation data can also be the vehicle operation data collected at any other collection time different from the first vehicle operation data, but the condition that needs to be met is that the time difference between the first collection time of the first vehicle operation data and the second collection time of the second vehicle operation data is less than a preset threshold. The preset threshold can be one time, two times, or n times the data collection time interval set by the data collection device. The smaller the preset threshold, the higher the accuracy of determining that the first vehicle operation data is normal vehicle data, and the larger the preset threshold, the lower the accuracy of determining that the first vehicle operation data is normal vehicle data.

[0096] In the embodiments of this specification, the first vehicle operation data includes the first collection time T1 for collecting the first vehicle operation data and the first driving speed V1 of the vehicle at the first collection time. The second vehicle operation data includes the second collection time T2 for collecting the second vehicle operation data and the second driving speed V2 of the vehicle at the second collection time. According to the distance calculation formula: distance S = speed V × time T, the estimated driving distance S1 of the target vehicle between the first collection time and the second collection time can be estimated. In the above formula, the time T can be the time difference T3 between the second collection time T2 and the first collection time T1, and the speed V can be the average value V3 of the sum of the first driving speed V1 and the second driving speed V2. That is, S1 = V3 × T3 = (V1 + V2) ÷ 2 × (T2 - T1).

[0097] In the embodiments of this specification, the first vehicle operation data includes the first vehicle positioning data at the first acquisition moment, and the second vehicle operation data includes the second vehicle positioning data at the second acquisition moment. The lane(s) existing within the target map grid can be one lane or multiple lanes. To determine the target lane where the target vehicle is located, at this time, a circle can be drawn with the position determined on the map by the first vehicle positioning data as the center and a preset radius. The preset radius can be any value within the range greater than or equal to one lane width and less than or equal to two lane widths. Search for all lanes covered by the above circle, and sequentially determine the first distance from the center of the circle to the center line of each lane. Then obtain the first heading angle of the target vehicle included in the first vehicle operation data, and then obtain the respective second heading angles of the lanes falling within the coverage of the circle. Select the target lane line corresponding to the shortest first distance from the determined first distances, and determine the heading angle difference between the second heading angle of the lane where the target lane line is located and the first heading angle. If the heading angle difference is less than or equal to the preset angle, then determine that the lane where the target lane line is located is the target lane where the target vehicle is located. The preset angle can be selected as 45 degrees. If the determined heading angle difference is greater than the preset angle, then sequentially select other first distances in ascending order according to the magnitudes of the respective first distance values, and then according to the method of determining whether the heading angle difference corresponding to the shortest first distance is less than the preset angle, sequentially determine whether the lanes corresponding to other first distances are the target lanes. After determining the target lane, stop selecting the remaining first distances. If none of the lanes corresponding to all first distances are the target lanes, then the size of the above preset angle can be adjusted, and then the required target lane can be found sequentially according to the above determination method. After finding the target lane where the target vehicle is located, draw a perpendicular line from the position where the first vehicle positioning data is located to the center line of the target lane, and obtain the first foot of the perpendicular on the center line of the target lane. Then draw a perpendicular line from the position where the second vehicle positioning data is located to the center line of the target lane, and obtain the second foot of the perpendicular on the center line of the target lane. Take the distance between the first foot of the perpendicular and the second foot of the perpendicular as the actual driving distance of the target vehicle in the target lane from the second acquisition moment to the first acquisition moment. The distance between the first foot of the perpendicular and the second foot of the perpendicular can be expressed as the actual driving distance S2.

[0098] It should be noted that since the second vehicle operation data is the selected normal vehicle operation data, the lane determined according to the second vehicle operation data can also be used as the target lane.

[0099] In the embodiments of this specification, the distance difference between the estimated driving distance S1 and the actual driving distance S2 of the target vehicle obtained above can be used to determine whether the target vehicle is driving on the pre-planned target lane, and further determine whether the first vehicle operation data is abnormal vehicle data.

[0100] In the embodiments of this specification, abnormal vehicle data with a relatively small abnormality manifestation can be excluded by the distance difference between the estimated driving distance and the actual driving distance of the target vehicle in the target lane, thereby improving the accuracy of determining abnormal vehicle data.

[0101] Based on the distance difference between the estimated driving distance and the actual driving distance of the target vehicle in the target lane to determine whether the first vehicle operation data is abnormal vehicle data, it can be determined based on the distance difference itself, or based on the ratio between the distance difference and the estimated driving distance or the actual driving distance of the target vehicle in the target lane. Based on this, the step of determining whether the first vehicle operation data is abnormal vehicle data according to the distance difference between the first moving distance and the second moving distance may specifically include:

[0102] Determine whether the ratio between the absolute value of the distance difference and the second moving distance is less than a preset value to obtain a fourth determination result.

[0103] If the fourth determination result indicates that the ratio is less than the preset value, it is determined that the first vehicle operation data is normal vehicle data.

[0104] If the fourth determination result indicates that the ratio is greater than or equal to the preset value, it is determined that the first vehicle operation data is abnormal vehicle data.

[0105] In the embodiments of this specification, when the estimated driving distance of the target vehicle in the target lane is greater than or equal to the actual driving distance, the above distance difference is the estimated driving distance minus the actual driving distance; when the estimated driving distance of the target vehicle in the target lane is less than the actual driving distance, the above distance difference is the actual driving distance minus the estimated driving distance. Therefore, in order to ensure that the obtained distance difference is always a positive number, the absolute value of the distance difference calculated by any of the above methods is calculated. Calculate the first ratio between the absolute value of the above distance difference and the actual driving distance, and determine whether the first ratio is greater than or equal to a first preset value. If the first ratio is greater than or equal to the first preset value, it is determined that the first vehicle operation data is abnormal vehicle data; if the first ratio is less than the first preset value, it is determined that the first vehicle operation data is normal vehicle data. The above first preset value can be reasonably set according to requirements. The smaller the first preset value, the higher the accuracy of determining abnormal vehicle data; the larger the first preset value, the lower the accuracy of determining abnormal vehicle data. It should be noted that it is also possible to calculate the second ratio between the absolute value of the above distance difference and the estimated driving distance, and determine whether the first vehicle operation data is abnormal vehicle data according to whether the second ratio is greater than or equal to a second preset value, which will not be elaborated here in detail.

[0106] In the embodiments of this specification, by determining whether the ratio of the absolute value of the distance difference between the estimated driving distance and the actual driving distance of the target vehicle on the target lane to the actual driving distance is greater than or equal to a preset value, it is determined whether the first vehicle operation data is abnormal vehicle data, thereby improving the accuracy of determining abnormal vehicle data.

[0107] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method. Figure 3 For the embodiments of this specification, it corresponds to Figure 1 a structural schematic diagram of an abnormal vehicle data recognition device. As Figure 3 shown, the device may include:

[0108] A first acquisition module 302, configured to acquire first vehicle operation data collected for the target vehicle by using a data acquisition device.

[0109] A first determination module 304, configured to determine a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; the target map grid is obtained by dividing the map corresponding to the target geographical area into grids.

[0110] A first judgment module 306, configured to judge whether the geographical area corresponding to the target map grid contains a lane, and obtain a first judgment result.

[0111] A second determination module 308, configured to, if the first judgment result indicates that the geographical area corresponding to the target map grid does not contain a lane, determine the first vehicle operation data as abnormal vehicle data.

[0112] Optionally, the first determination module 304 may specifically include:

[0113] A first acquisition unit, configured to acquire vehicle positioning information for the target vehicle included in the first vehicle operation data.

[0114] A second acquisition unit, configured to acquire first position range information of the geographical area covered by each map grid.

[0115] A first determination unit, configured to determine, from the map grids, a target map grid to which the location of the target vehicle belongs according to the vehicle positioning information and the first position range information.

[0116] Optionally, the first determination unit may specifically include:

[0117] A first acquisition subunit, configured to acquire a first longitude and a first latitude in the vehicle positioning information.

[0118] A second acquisition subunit, configured to acquire a second longitude range and a second latitude range in the first position range information.

[0119] A first determination subunit, configured to determine whether the first longitude is within the second longitude range and the first latitude is within the second latitude range, so as to obtain a second determination result.

[0120] A first determination subunit, configured to, if the second determination result indicates that the first longitude is within the second longitude range and the first latitude is within the second latitude range, determine the map grid corresponding to the first position range information as the target map grid to which the location of the target vehicle belongs.

[0121] Optionally, the first determination module 306 may specifically include:

[0122] A third acquisition unit, configured to acquire lane positioning information of a lane.

[0123] A fourth acquisition unit, configured to acquire second position range information of a geographical area corresponding to the target map grid.

[0124] A first determination unit, configured to determine whether a lane is included in the geographical area corresponding to the target map grid according to the lane positioning information and the second position range information.

[0125] Optionally, the first determination unit may specifically include:

[0126] A third acquisition subunit, configured to acquire a third longitude and a third latitude included in each lane positioning data in the lane positioning information.

[0127] A fourth acquisition subunit, configured to acquire a fourth longitude range and a fourth latitude range in the second position range information.

[0128] A second determination subunit, configured to determine whether there is a preset number of target lane positioning data in the lane positioning information, where the third longitude of the target lane positioning data is within the fourth longitude range and the third latitude of the target lane positioning data is within the fourth latitude range, so as to obtain a third determination result.

[0129] A second determination subunit, configured to, if the third determination result indicates that there is a preset number of the target lane positioning data, determine that a lane is included in the geographical area corresponding to the target map network.

[0130] A third determination subunit, configured to, if the third determination result indicates that there is no preset number of the target lane positioning data, determine that no lane is included in the geographical area corresponding to the target map network.

[0131] Optionally, the fourth acquisition unit may specifically include:

[0132] A first expansion subunit, configured to expand the geographical area covered by the target map grid according to a preset distance to obtain an expanded geographical area corresponding to the target map grid.

[0133] A fourth determination subunit, configured to determine position range information of the expanded geographical area to obtain the second position range information.

[0134] Optionally, after the first determination module 306, the following may further be included:

[0135] A second acquisition module, configured to, if the first determination result indicates that a lane is included in the geographical area corresponding to the target map grid, acquire second vehicle operation data recognized as normal vehicle operation data; a time difference between a first acquisition time of the first vehicle operation data and a second acquisition time of the second vehicle operation data is less than a preset threshold.

[0136] A first calculation module, configured to calculate a first moving distance of the target vehicle according to vehicle driving speeds and data acquisition times respectively included in the first vehicle operation data and the second vehicle operation data, where the first moving distance represents an estimated driving distance of the target vehicle between the second acquisition time and the first acquisition time.

[0137] A second calculation module, configured to calculate a second moving distance of the target vehicle according to vehicle positioning information respectively included in the first vehicle operation data and the second vehicle operation data, where the second moving distance represents a distance traveled by the target vehicle in a target lane between the second acquisition time and the first acquisition time, and the target lane is a lane where the target vehicle is located determined according to the vehicle positioning information.

[0138] A second determination module, configured to determine whether the first vehicle operation data is abnormal vehicle data according to a distance difference between the first moving distance and the second moving distance.

[0139] Optionally, the second determination module may specifically include:

[0140] A second determination unit, configured to determine whether a ratio of an absolute value of the distance difference to the second moving distance is less than a preset value to obtain a fourth determination result.

[0141] A second determination unit, configured to, if the fourth determination result indicates that the ratio is less than the preset value, determine that the first vehicle operation data is normal vehicle data.

[0142] A third determination unit, configured to determine the first vehicle operation data as abnormal vehicle data if the fourth determination result indicates that the ratio is greater than or equal to the preset value.

[0143] Based on the same idea, an embodiment of this specification also provides a device corresponding to the above method.

[0144] Figure 4 For the embodiment of this specification, it provides a Figure 1 structural schematic diagram of an abnormal vehicle data recognition device. As Figure 4 shown, the device 400 may include:

[0145] At least one processor 410; and,

[0146] A memory 430 communicatively connected to the at least one processor; wherein,

[0147] The memory 430 stores instructions 420 executable by the at least one processor 410, and when the instructions are executed by the at least one processor 410, the at least one processor 410 is enabled to:

[0148] Obtain the first vehicle operation data collected for the target vehicle by using a data acquisition device.

[0149] According to the first vehicle operation data, determine the target map grid to which the location of the target vehicle belongs; the target map grid is obtained by dividing the map corresponding to the target geographical area into grids.

[0150] Judge whether the geographical area corresponding to the target map grid contains lanes, and obtain a first judgment result.

[0151] If the first judgment result indicates that the geographical area corresponding to the target map grid does not contain lanes, determine the first vehicle operation data as abnormal vehicle data.

[0152] It should be understood that in the method described in one or more embodiments of this specification, the order of some steps can be adjusted according to actual needs, or some steps can be omitted.

[0153] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for Figure 3 the device shown, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiment.

[0154] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for identifying abnormal vehicle data, characterized in that, Including: Obtaining first vehicle operation data collected for a target vehicle by using a data collection device; Determining a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; The target map grid is obtained by dividing a map corresponding to a target geographical area into grids; Judging whether a lane is included in the geographical area corresponding to the target map grid to obtain a first judgment result; If the first judgment result indicates that no lane is included in the geographical area corresponding to the target map grid, determining the first vehicle operation data as abnormal vehicle data.

2. The method according to claim 1, wherein The determining the target map grid to which the location of the target vehicle belongs according to the first vehicle operation data specifically includes: Obtaining vehicle positioning information for the target vehicle included in the first vehicle operation data; Obtaining first position range information of the geographical area covered by each map grid; Determining the target map grid to which the location of the target vehicle belongs from the map grids according to the vehicle positioning information and the first position range information.

3. The method according to claim 2, wherein The determining the target map grid to which the location of the target vehicle belongs from the map grids according to the vehicle positioning information and the first position range information specifically includes: Obtaining a first longitude and a first latitude in the vehicle positioning information; Obtaining a second longitude range and a second latitude range in the first position range information; Judging whether the first longitude is within the second longitude range and the first latitude is within the second latitude range to obtain a second judgment result; If the second judgment result indicates that the first longitude is within the second longitude range and the first latitude is within the second latitude range, determining the map grid corresponding to the first position range information as the target map grid to which the location of the target vehicle belongs.

4. The method according to claim 1, wherein The judging whether a lane is included in the geographical area corresponding to the target map grid specifically includes: Obtaining lane positioning information of the lane; Obtaining second position range information of the geographical area corresponding to the target map grid; Judging whether a lane is included in the geographical area corresponding to the target map grid according to the lane positioning information and the second position range information.

5. The method according to claim 4, wherein The judging whether a lane is included in the geographical area corresponding to the target map grid according to the lane positioning information and the second position range information specifically includes: Obtaining a third longitude and a third latitude included in each lane positioning data in the lane positioning information; Obtaining a fourth longitude range and a fourth latitude range in the second position range information; Judging whether there is a preset number of target lane positioning data in the lane positioning information, where the third longitude of the target lane positioning data is within the fourth longitude range and the third latitude of the target lane positioning data is within the fourth latitude range to obtain a third judgment result; If the third judgment result indicates that there is a preset number of the target lane positioning data, determining that a lane is included in the geographical area corresponding to the target map network; If the third judgment result indicates that there is no preset quantity of the target lane positioning data, it is determined that the geographical area corresponding to the target map network does not include a lane.

6. The method according to claim 4, wherein The obtaining of the second position range information of the geographical area corresponding to the target map grid specifically includes: Expanding the geographical area covered by the target map grid according to a preset distance to obtain an expanded geographical area corresponding to the target map grid; Determining the position range information of the expanded geographical area to obtain the second position range information.

7. The method according to claim 1, wherein After obtaining the first judgment result by judging whether the geographical area corresponding to the target map network includes a lane, it further includes: If the first judgment result indicates that the geographical area corresponding to the target map grid includes a lane, obtaining second vehicle operation data recognized as normal vehicle operation data; the time difference between the first collection time of the first vehicle operation data and the second collection time of the second vehicle operation data is less than a preset threshold; Calculating a first moving distance of the target vehicle according to the vehicle driving speed and the data collection time respectively included in the first vehicle operation data and the second vehicle operation data, where the first moving distance represents the estimated driving distance of the target vehicle between the second collection time and the first collection time; Calculating a second moving distance of the target vehicle according to the vehicle positioning information respectively included in the first vehicle operation data and the second vehicle operation data, where the second moving distance represents the distance traveled by the target vehicle in the target lane between the second collection time and the first collection time, and the target lane is the lane where the target vehicle is located determined according to the vehicle positioning information; Judging whether the first vehicle operation data is abnormal vehicle data according to the distance difference between the first moving distance and the second moving distance.

8. The method according to claim 7, wherein The judging whether the first vehicle operation data is abnormal vehicle data according to the distance difference between the first moving distance and the second moving distance specifically includes: Judging whether the ratio of the absolute value of the distance difference to the second moving distance is less than a preset value to obtain a fourth judgment result; If the fourth judgment result indicates that the ratio is less than the preset value, determining that the first vehicle operation data is normal vehicle data; If the fourth judgment result indicates that the ratio is greater than or equal to the preset value, determining that the first vehicle operation data is abnormal vehicle data.

9. An abnormal vehicle data recognition device, characterized in that It includes: A first obtaining module, configured to obtain first vehicle operation data collected for a target vehicle by using a data collection device; A first determining module, configured to determine a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; The target map grid is obtained by dividing the map corresponding to the target geographical area into grids; A first judging module, configured to judge whether the geographical area corresponding to the target map grid includes a lane to obtain a first judgment result; A second determination module, configured to determine the first vehicle operation data as abnormal vehicle data if the first determination result indicates that the geographical area corresponding to the target map grid does not include a lane.

10. An abnormal vehicle data recognition device, characterized in that, Comprising: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to: Obtain first vehicle operation data collected for a target vehicle by a data collection device; Determine a target map grid to which the location of the target vehicle belongs according to the first vehicle operation data; the target map grid is obtained by dividing a map corresponding to a target geographical area into grids; Judge whether the geographical area corresponding to the target map grid contains a lane, and obtain a first determination result; If the first determination result indicates that the geographical area corresponding to the target map grid does not include a lane, determine the first vehicle operation data as abnormal vehicle data.

Images