Test method, device, equipment, medium and product for vehicle digital twin

Abstract

The present disclosure provides a vehicle digital twin testing method, device, equipment, medium and product, relates to the field of data processing, and particularly relates to the field of cloud technology. The specific implementation scheme is: obtaining digital twin data of a vehicle from the cloud; extracting driving features of the vehicle from the digital twin data, determining whether the vehicle meets an abnormal condition of a candidate abnormal type according to the driving features of the vehicle, and determining a target abnormal type existing in the vehicle from the candidate abnormal type according to a determination result; taking driving features corresponding to the abnormal condition of the target abnormal type as abnormal driving features, and determining an abnormal proportion of the target abnormal type according to the abnormal driving features and the extracted driving features to obtain a testing result of the vehicle digital twin. The scheme of the present disclosure tests the digital twin effect from the data layer of the digital twin data and quantifies the evaluation result of the digital twin effect, thereby improving the accuracy of the testing result of the vehicle digital twin.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of data processing, especially to the field of cloud technology, and in particular to a vehicle digital twin testing method, device, equipment, medium and product. BACKGROUND

[0002] Digital twin traffic is part of smart traffic, and digital twin traffic is to realize virtual digital mapping of real-time collected traffic data.

[0003] However, in the process of virtual digital mapping, the problem of digital twin mapping anomaly may occur, and the abnormal phenomenon needs to be found in time and positioned and repaired. SUMMARY

[0004] The present disclosure provides a vehicle digital twin testing method, device, equipment, medium and product.

[0005] According to an aspect of the present disclosure, a vehicle digital twin testing method is provided, comprising:

[0006] obtaining digital twin data of a vehicle from the cloud;

[0007] extracting driving features of the vehicle from the digital twin data, determining whether the vehicle meets an abnormal condition of a candidate abnormal type according to the driving features of the vehicle, and determining a target abnormal type in which the vehicle exists from the candidate abnormal types according to the determination result;

[0008] taking the driving features corresponding to the abnormal condition of the target abnormal type as abnormal driving features, and determining an abnormal proportion of the target abnormal type according to the abnormal driving features and the extracted driving features to obtain a testing result of the vehicle digital twin.

[0009] According to another aspect of the present disclosure, a vehicle digital twin testing device is provided, comprising:

[0010] a twin data obtaining module configured to obtain digital twin data of a vehicle from the cloud;

[0011] an abnormal type determining module configured to extract driving features of the vehicle from the digital twin data, determine whether the vehicle meets an abnormal condition of a candidate abnormal type according to the driving features of the vehicle, and determine a target abnormal type in which the vehicle exists from the candidate abnormal types according to the determination result;

[0012] a digital twin testing module configured to take the driving features corresponding to the abnormal condition of the target abnormal type as abnormal driving features, and determine an abnormal proportion of the target abnormal type according to the abnormal driving features and the extracted driving features to obtain a testing result of the vehicle digital twin.

[0013] According to another aspect of the present disclosure, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory in communication connection with the at least one processor; wherein

[0016] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the test method of vehicle digital twin according to any one of the embodiments of the present disclosure.

[0017] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the test method of vehicle digital twin according to any one of the embodiments of the present disclosure.

[0018] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the test method of vehicle digital twin according to any one of the embodiments of the present disclosure.

[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0021] Figure 1 is a schematic diagram of a test method of vehicle digital twin according to an embodiment of the present disclosure;

[0022] Figure 2 is a schematic diagram of another test method of vehicle digital twin according to an embodiment of the present disclosure;

[0023] Figure 3 is a schematic diagram of still another test method of vehicle digital twin according to an embodiment of the present disclosure;

[0024] Figure 4 is a schematic diagram of still another test method of vehicle digital twin according to an embodiment of the present disclosure;

[0025] Figure 5 is a structural schematic diagram of a test device of vehicle digital twin according to an embodiment of the present disclosure;

[0026] Figure 6is a block diagram of an electronic device for implementing a test method of vehicle digital twinning according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding them. These should be considered in a descriptive sense only and not limiting. Therefore, it will be recognized by those of ordinary skill that various changes and modifications can be made to the embodiments described here without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0028] Figure 1 is a schematic diagram of a test method of vehicle digital twinning according to an embodiment of the present disclosure. The embodiment can be applied to the optimization of the test method of vehicle digital twinning. The method can be executed by a test device for vehicle digital twinning, which can be implemented in software and / or hardware and integrated in an electronic device. The electronic device involved in the embodiment can be a server or other device with computing and communication capabilities. Specifically, refer to Figure 1 The method specifically includes the following:

[0029] S110, obtaining digital twinning data of a vehicle from the cloud.

[0030] The digital twinning data refers to data obtained by virtually mapping traffic data collected by a roadside device, and the digital twinning effect of a vehicle is displayed at the front end according to the digital twinning data. The digital twinning data includes vehicle feature data corresponding to the data and data collection source information, such as latitude and longitude information of the vehicle during driving, vehicle identification information, vehicle speed, etc.

[0031] Specifically, the roadside device collects vehicle data on the road surface and sends the collected source data to the cloud for virtual mapping by a business processing module in the cloud to obtain digital twinning data, which is displayed at the front end according to the digital twinning data. In order to ensure the timeliness of obtaining vehicle twinning anomalies, after obtaining the digital twinning data in the cloud, the digital twinning data is pushed to the test device for vehicle digital twinning in the embodiment, which directly tests the digital twinning data from the data layer to obtain the test result of vehicle twinning.

[0032] For example, the twinning effect of a vehicle within a range of 1.5 kilometers is tested, and based on roadside devices on multiple road sections within the range, the digital twinning data corresponding to the roadside devices is subscribed from the cloud, and the time of receiving the data is recorded and stored.

[0033] S120, extracting the driving feature of the vehicle from the digital twin data, determining whether the vehicle meets the abnormal condition of the candidate abnormal type according to the driving feature of the vehicle, and determining the target abnormal type existing for the vehicle from the candidate abnormal type according to the determination result.

[0034] The driving feature of the vehicle is used to represent the dimensional information of the vehicle in the driving process, such as timestamp feature, speed feature, latitude and longitude feature, or orientation angle feature. The candidate abnormal type refers to the abnormal twin effect that may occur in the virtual mapping process of the vehicle, for example, including: vehicle reverse, vehicle lag, vehicle flash-off, vehicle disappearance, vehicle rotation, and vehicle static. The abnormal condition of the candidate abnormal type is the data abnormal condition corresponding to the abnormal twin effect determined in advance according to the analysis result of the twin data layer. The corresponding twin abnormal effect problem is obtained by analyzing different abnormal type data at the data layer.

[0035] Specifically, the corresponding abnormal condition is determined according to the abnormal data feature corresponding to the candidate abnormal type, the driving feature of the vehicle is extracted from the digital twin data according to the data feature required by the abnormal condition, and the matching result of the driving feature and the abnormal condition of the candidate abnormal type is determined. If the driving feature matches the abnormal condition of any candidate abnormal type successfully, the candidate abnormal type that matches successfully is determined as the target abnormal type that may occur when the vehicle displays the twin effect in the front end.

[0036] For example, according to the corresponding relationship between the abnormal twin effect and the data, the abnormal conditions of the six candidate abnormal types are determined respectively. The abnormal condition can be a timestamp anomaly or a data repetition anomaly or a data loss anomaly or a vehicle driving anomaly, etc. The vehicle feature information corresponding to the candidate abnormal condition is extracted from the digital twin data according to the abnormal condition, and whether there is at least one candidate abnormal type whose abnormal condition matches successfully is determined according to the one-to-one comparison result of the vehicle feature information and the candidate abnormal condition. If there is, the at least one candidate abnormal type is determined as the target abnormal type; if not, it means that the vehicle digital twin effect of the virtual mapping according to the digital twin data has no abnormality. Optionally, the target abnormal type can be one or at least two.

[0037] In another optional implementation manner of the embodiment, S120 includes:

[0038] The latitude and longitude feature and / or the orientation angle feature of the vehicle are extracted from the digital twin data, and the latitude and longitude feature and / or the orientation angle feature of the vehicle are used as the driving feature of the vehicle.

[0039] The vehicle is determined to meet an abnormal condition of a candidate abnormal type according to a latitude and longitude feature and / or an orientation angle feature of the vehicle, and a target abnormal type existing for the vehicle is selected from the candidate abnormal type according to a determination result; the candidate abnormal type is a vehicle reverse abnormal type or a vehicle turning abnormal type.

[0040] The candidate abnormal type includes the vehicle reverse abnormal type or the vehicle turning abnormal type, and the vehicle reverse abnormal type corresponds to an abnormal latitude and longitude feature of the vehicle, and the vehicle turning abnormal type corresponds to an abnormal orientation angle feature of the vehicle.

[0041] Specifically, if the candidate abnormal type is determined to be the vehicle reverse abnormal type, the latitude and longitude feature of the vehicle is extracted from the digital twin data, and the latitude and longitude feature is used as a driving feature of the vehicle for checking the vehicle reverse abnormal type; if the candidate abnormal type is determined to be the vehicle turning abnormal type, the orientation angle feature of the vehicle is extracted from the digital twin data, and the orientation angle feature is used as the driving feature of the vehicle for checking the vehicle reverse abnormal type; if the candidate abnormal type is determined to be the vehicle reverse abnormal type and the vehicle turning abnormal type, the latitude and longitude feature and the orientation angle feature of the vehicle are extracted from the digital twin data, and both the latitude and longitude feature and the orientation angle feature are used as the driving feature of the vehicle for checking the vehicle reverse abnormal type.

[0042] A matching result of the extracted driving feature of the vehicle and an abnormal condition corresponding to the candidate abnormal type is determined, and if the matching is successful, the candidate abnormal type is determined to be a target abnormal type that will occur when the vehicle displays a twin effect in the front end.

[0043] By extracting the latitude and longitude feature and / or the orientation angle feature of the vehicle, and determining a matching result of the extracted driving feature and an abnormal condition corresponding to the candidate abnormal type, a target abnormal type existing when the vehicle performs digital twinning is determined according to the matching result. It is realized that the abnormal twin effect of the vehicle reverse or the vehicle turning can be obtained by analyzing the data layer, and the efficiency of discovering the abnormal twin effect of the vehicle reverse or the vehicle turning is improved.

[0044] In S130, the driving feature corresponding to the abnormal condition of the target abnormal type is used as an abnormal driving feature, and an abnormal proportion of the target abnormal type is determined according to the abnormal driving feature and the extracted driving feature, and a test result of the vehicle digital twinning is obtained.

[0045] After the target abnormal type is determined, the driving feature matched with the abnormal condition of the target abnormal type is used as an abnormal driving feature, and an abnormal proportion of the target abnormal type is determined according to a ratio of the abnormal driving feature to the driving feature extracted from all digital twin data, and the effect of the vehicle digital twinning can be quantitatively analyzed according to the abnormal proportion of the target abnormal type, and a test result of the vehicle digital twinning is obtained.

[0046] For example, based on the above examples, if the abnormal condition of the target abnormal type is a timestamp feature abnormality, the timestamp feature that matches the timestamp abnormal condition is taken as an abnormal driving feature, the number of timestamps included in the abnormal driving feature is determined, the number of all extracted timestamp features is determined, and the abnormality proportion of the target abnormal type is determined according to the ratio of the number of abnormal timestamps to the total number of timestamps. For another example, since each piece of digital twin data corresponds to the driving data of a vehicle at a timestamp, and since the extracted driving features in a piece of digital twin data may hit the abnormal conditions of multiple candidate abnormal types, the number of abnormalities of the digital twin data corresponding to the abnormal driving features can be counted, the total proportion of the digital twin effect abnormality is determined according to the ratio of the number of abnormalities to the total number of digital twin data, and the test result of the vehicle digital twin is determined according to the total proportion and the abnormality proportion of each target abnormal type. The test result of the vehicle digital twin determined by the abnormality proportion can realize the quantification of the twin effect quality, and further effectively evaluate the twin effect.

[0047] In another optional implementation of the embodiment, before obtaining the test result of the vehicle digital twin, the method further includes:

[0048] Based on the association relationship between the abnormal conditions of the candidate abnormal types and the candidate abnormal sources, the target abnormal source is determined from the candidate abnormal sources according to the abnormal conditions of the candidate abnormal types satisfied by the vehicle; wherein the candidate abnormal sources include source data and cloud twin data.

[0049] The candidate abnormal source refers to the positioning result of the abnormal feature data, i.e. the error source of the abnormal feature data, so as to position and repair the original error data according to the determined target abnormal source. According to the process of digital twin, it is determined that the source data is obtained by roadside equipment, and the twin data is obtained by virtual mapping in the cloud, so it is possible that the roadside equipment makes a mistake or the cloud makes a mistake when performing virtual mapping, i.e. the candidate abnormal sources include source data and cloud twin data.

[0050] Specifically, it is determined that the abnormal conditions of different candidate abnormal types have an association relationship with the candidate abnormal sources according to the data analysis of the candidate abnormal sources in advance, so the corresponding target abnormal source can be determined according to the abnormal conditions satisfied by the abnormal driving features.

[0051] For example, when the candidate abnormal type is vehicle disappearance, the corresponding abnormal condition is that the continuous multiple pieces of digital twin data of the vehicle are completely the same, that is, the corresponding error source is that the cloud repeatedly pushes the digital twin data of the vehicle, and therefore the determined target error source is the cloud digital twin data, and further, according to the abnormal condition of the candidate abnormal type, it can be further determined that the target abnormal reason is that the cloud repeatedly pushes the digital twin data.

[0052] The embodiment determines the association relationship between the abnormal condition of the candidate abnormal type and the candidate abnormal source, and then determines the target abnormal type according to the satisfied abnormal condition of the candidate abnormal type, so as to further determine the target abnormal source, and then improves the positioning repair efficiency of the abnormal driving characteristics according to the target abnormal source.

[0053] The scheme of the embodiment tests the digital twin effect from the data layer of the digital twin data, avoids the low efficiency of discovering abnormal digital twin effect through images after the digital twin effect is displayed, improves the test accuracy of the abnormal digital twin effect, and detects the possible abnormal digital twin effect in advance from the data layer, thereby improving the display accuracy of the digital twin. On the other hand, the test from the data layer can quantify the evaluation results of the digital twin effect, thereby improving the accuracy of the test results.

[0054] Figure 2 is a schematic diagram of another vehicle digital twin testing method according to an embodiment of the present disclosure. The embodiment is a further refinement of the above technical solution. The technical solution in the embodiment can be combined with each optional scheme in one or more of the above embodiments. As shown in Figure 2 The vehicle digital twin testing method includes the following steps:

[0055] S210, obtaining digital twin data of a vehicle from a cloud.

[0056] S220, extracting latitude and longitude features of the vehicle from the digital twin data, and taking the latitude and longitude features of the vehicle as driving features of the vehicle.

[0057] The latitude and longitude features refer to the position information of the vehicle corresponding to the digital twin data. According to the change information of the latitude and longitude features of the vehicle, the change information of the driving direction of the vehicle can be determined, and according to the change information of the driving direction, whether the vehicle reverse abnormal digital twin effect occurs in the driving process of the vehicle can be determined. Therefore, when the candidate abnormal type is determined as the vehicle reverse abnormal, the latitude and longitude features of the vehicle are taken as the driving features of the vehicle.

[0058] S230, determining whether the vehicle satisfies the abnormal condition of the candidate abnormal type according to the latitude and longitude features of the vehicle, and selecting a target abnormal type existing in the vehicle from the candidate abnormal types according to the determination result.

[0059] The candidate abnormal type is a vehicle reverse abnormality. The vehicle reverse abnormality refers to abnormal reverse behavior of the vehicle.

[0060] Specifically, since the vehicle will change the latitude and longitude change direction if the vehicle reverse abnormality occurs, the driving direction change feature of the vehicle is determined according to the latitude and longitude feature of the vehicle, and then it is determined whether the vehicle reverse direction abnormality condition is met according to the driving direction change feature of the vehicle. If it is met, it is determined that the vehicle reverse abnormality effect will occur when the digital twin data corresponding to the latitude and longitude feature is virtually mapped. If it is not met, it is determined that the vehicle reverse abnormality effect will not occur when the digital twin data corresponding to the latitude and longitude feature is virtually mapped.

[0061] For example, the road side equipment based on the collected data on the preset road segment subscribes the corresponding digital twin data pushed by the cloud, and stores the data. The vehicle unique ID in the digital twin data is taken as the key, and the value is set as the latitude and longitude feature of the vehicle, to obtain the latitude and longitude information of the target vehicle in each piece of digital twin data. The feature data information of the target vehicle at different times corresponding to different pieces of digital twin data, so the driving direction change feature of the vehicle can be obtained according to the continuous change information of the latitude and longitude information.

[0062] In another optional implementation of the embodiment, S230 comprises:

[0063] The continuous change direction difference of the vehicle in the driving process is determined according to the latitude and longitude feature of the vehicle.

[0064] If the continuous change direction difference is greater than the preset direction change threshold, it is determined that the vehicle meets the vehicle reverse abnormality condition, and the vehicle reverse abnormality is taken as the target abnormal type of the vehicle.

[0065] The continuous change direction difference represents the driving direction difference of the vehicle determined according to the digital twin data obtained at continuous times.

[0066] Specifically, the continuous change direction difference represents the driving direction angle difference of the target vehicle at three points, for example, the vehicle drives from point A to point B, and then from point B to point C. The first driving direction from point A to point B can be obtained according to the latitude and longitude information of point A and point B, the second driving direction from point B to point C can be obtained according to the latitude and longitude information of point B and point C, and the continuous change direction difference of the vehicle at point B can be obtained according to the first driving direction and the second driving direction.

[0067] If the vehicle belongs to the normal driving process, the value of the continuous change direction difference should be less than or equal to the preset direction change threshold, and if the continuous change direction difference is greater than the preset direction change threshold, it is determined that the vehicle meets the vehicle reverse abnormality condition.

[0068] For example, the longitude and latitude of two adjacent points of the target vehicle are obtained, a plane rectangular coordinate system is established with one point as the origin, the distance between the two points, the longitude difference and the latitude difference of the two points are calculated, the cosine value is calculated, and the radian value corresponding to the included angle is calculated by using the inverse trigonometric function (acos or asin), and then the radian value is converted into an angle value, which corresponds to the first driving direction of the two adjacent points. The second driving direction of one of the two adjacent points and the other adjacent point is calculated, and the difference between the first driving direction and the second driving direction is calculated, which is the continuously changing direction difference. If the absolute value of the difference is greater than 90 degrees, it is determined that the vehicle meets the vehicle reverse abnormal condition.

[0069] Optionally, in order to avoid misjudgment caused by data deviation, the latitude and longitude range where the vehicle exists turning and U-turn is set according to the road information, that is, a tolerance range is set. If the distance between the point where the continuously changing direction difference is greater than the preset direction change threshold and the adjacent point is less than the tolerance range, it is determined that it belongs to the normal U-turn of the vehicle, otherwise, it is considered that the vehicle meets the vehicle reverse abnormal condition. That is, the vehicle reverse abnormal condition not only includes the continuously changing direction difference greater than the preset direction change threshold, but also includes the latitude and longitude difference greater than the preset latitude and longitude range.

[0070] In this embodiment, the continuously changing direction difference is determined according to the latitude and longitude characteristics, and then whether the vehicle has a reverse abnormal problem is determined according to the continuously changing direction difference, which improves the accuracy and efficiency of the vehicle reverse abnormal judgment.

[0071] Optionally, the vehicle reverse abnormal condition also includes whether the time stamp feature appears in reverse order, whether the change of the road side equipment corresponding to the data source is different from the driving direction of the vehicle, and whether the data is missing in the digital twin data.

[0072] Specifically, the time stamp information in the digital twin data is extracted, and whether the reverse order appears is judged according to the order of the time stamp information. If it appears, it is determined that the vehicle meets the vehicle reverse abnormal condition. For example, it is judged whether the time of the two adjacent points is reversed. Each package of digital twin data contains the time stamp of data reporting. For a vehicle, whether the reporting time in the two packages of digital twin data appears time reversal, if so, it is determined that the vehicle rendering will appear reverse behavior.

[0073] Extract the road side device number information corresponding to the data source in the digital twin data, judge whether the sequence of the number information is the same as the driving direction of the vehicle, if not, determine that the vehicle meets the vehicle reverse abnormal condition. For example, there is a device id in each packet of digital twin data, which corresponds to the collection hardware device number information of the source data of the digital twin data. If the driving direction of the vehicle is upward, the hardware device number information should be from small to large, if the driving direction of the vehicle is upward, the hardware device number information should be from large to small, if the device number information in the sequentially received digital twin data appears out of order, it is determined that the vehicle rendering will appear reverse.

[0074] If the hardware device collects data with data missing phenomenon, the digital twin data is determined in the cloud, and the missing data is predicted according to the preset prediction program, and the missing data is added with prediction mark. If the prediction mark appears in the sequentially received digital twin data, it is determined that the vehicle rendering will appear reverse. For example, each packet of digital twin data contains a source field, and the source field is not predicted. If the prediction and non prediction appear alternately in different packet data, it is determined that the vehicle rendering will appear reverse.

[0075] S240, the driving feature corresponding to the abnormal condition of the target abnormal type is taken as the abnormal driving feature, and the abnormal proportion of the target abnormal type is determined according to the abnormal driving feature and the extracted driving feature, so as to obtain the test result of the vehicle digital twin.

[0076] In another optional implementation of the embodiment, the vehicle reverse abnormal condition further includes whether the collection time stamp corresponding to the abnormal latitude and longitude feature meeting the condition that the continuous change direction difference is greater than the preset direction change threshold meets the growth relationship;

[0077] Correspondingly, the target abnormal source is determined from the candidate abnormal source according to the abnormal condition of the candidate abnormal type met by the vehicle, including:

[0078] If the abnormal condition of the candidate abnormal type met by the vehicle is that the continuous change direction difference is greater than the preset direction change threshold, and the collection time stamp corresponding to the abnormal latitude and longitude feature meets the growth relationship, it is determined that the abnormal source of the vehicle reverse abnormality existing in the vehicle is the source data.

[0079] If the abnormal condition of the candidate abnormal type met by the vehicle is that the continuous change direction difference is greater than the preset direction change threshold, and the collection time stamp corresponding to the abnormal latitude and longitude feature does not meet the growth relationship, it is determined that the abnormal source is the cloud twin data.

[0080] According to the association between the abnormal conditions of the candidate abnormal types and the candidate abnormal sources, a target abnormal source is determined from the candidate abnormal sources according to the abnormal conditions of the candidate abnormal types that are met by the vehicle; wherein the candidate abnormal sources include source data and cloud twin data.

[0081] After determining that the vehicle exists the reverse abnormality according to the difference between the continuous change directions being greater than the preset direction change threshold, it is determined whether the abnormal driving feature exists the growth relationship of the collection time stamp, if yes, it is determined that the abnormal source of the vehicle reverse abnormality existing in the vehicle is the source data, that is, the roadside equipment has an abnormality when collecting data; otherwise, it is determined that the abnormal source of the vehicle reverse abnormality existing in the vehicle is the cloud twin data, that is, the cloud has a disorder abnormality when performing data twin, such as disorder of cloud pushing data.

[0082] The embodiment determines the abnormal source of the vehicle reverse abnormality according to the time stamp change relationship in the vehicle reverse abnormality condition, improves the efficiency of error data positioning, and quickly positions and repairs the abnormal data according to the abnormal source.

[0083] The scheme of the embodiment tests the vehicle reverse abnormality display effect through the latitude and longitude features of the digital twin data, improves the test accuracy of the vehicle reverse abnormality twin effect, and can detect the possible abnormal twin effect in advance from the data level, thereby improving the display accuracy of the digital twin. On the other hand, the test from the data level can quantify the evaluation results of the digital twin effect, thereby improving the accuracy of the test results.

[0084] Figure 3 is a schematic diagram of another vehicle digital twin test method according to the embodiments of the present disclosure. The embodiment is a further refinement of the above technical solution. The technical solution in the embodiment can be combined with each optional scheme in one or more of the above embodiments. As shown in Figure 3 The vehicle digital twin test method includes the following steps:

[0085] S310, obtaining digital twin data of a vehicle from a cloud.

[0086] S320, extracting an orientation angle feature of the vehicle from the digital twin data, and taking the orientation angle feature of the vehicle as a driving feature of the vehicle.

[0087] The orientation angle feature refers to the heading direction information of the vehicle corresponding to the digital twin data. The heading direction change information of the vehicle can be determined according to the orientation angle feature change information of the vehicle. Whether the vehicle appears the vehicle turning abnormality twin effect in the driving process can be determined according to the heading direction change information. Therefore, when the candidate abnormal type is determined as the vehicle turning abnormality, the orientation angle feature of the vehicle is taken as the driving feature of the vehicle.

[0088] S330, determine whether the vehicle meets the abnormal condition of the candidate abnormal type according to the orientation angle feature of the vehicle, and select the target abnormal type existing in the vehicle from the candidate abnormal type according to the determination result.

[0089] The candidate abnormal type is a vehicle reverse abnormality or a vehicle circle abnormality. The vehicle reverse abnormality refers to an abnormal circle behavior of the vehicle.

[0090] Specifically, since the orientation angle change direction of the vehicle will also change if the vehicle circle abnormality occurs, the orientation angle direction change feature of the vehicle is determined according to the orientation angle feature of the vehicle, and then whether the vehicle circle direction abnormal condition is met according to the orientation angle direction change feature of the vehicle. If it is met, it is determined that the vehicle circle abnormality effect will occur when the digital twin data corresponding to the orientation angle feature is virtually mapped; if it is not met, it is determined that the vehicle circle abnormality effect will not occur when the digital twin data corresponding to the orientation angle feature is virtually mapped.

[0091] For example, the roadside equipment based on the data collected on the preset road segment subscribes the corresponding digital twin data pushed by the cloud, and stores the data. Taking the unique ID of the vehicle in the digital twin data as the key, the value is set as the orientation angle of the vehicle, and the orientation angle information of the target vehicle in each piece of digital twin data is obtained. The feature data information of the target vehicle at different times corresponding to different pieces of data twin data, so the direction change feature of the vehicle can be obtained according to the continuous change information of the orientation angle.

[0092] In another optional implementation of the embodiment, S330 comprises:

[0093] Determine the continuous change difference of the orientation angle of the vehicle in the driving process according to the orientation angle feature of the vehicle.

[0094] If there are a preset number of continuous change differences of the orientation angle greater than a preset orientation angle threshold, it is determined that the vehicle meets the vehicle circle abnormal condition, and the vehicle circle abnormality is taken as the target abnormal type existing in the vehicle.

[0095] Wherein, the continuous change difference of the orientation angle refers to the difference information of the orientation angle of the vehicle at two consecutive points. The difference information can determine the change of the vehicle head direction at the two points.

[0096] Specifically, the orientation angle difference information of the vehicle at multiple points is continuously determined, and if there are a preset number of orientation angle difference information greater than a preset orientation angle threshold, it is determined that the vehicle meets the vehicle circle abnormal condition.

[0097] For example, the roadside device based on the collected data on the preset section subscribes to the corresponding digital twin data pushed by the cloud, and stores the data. Taking the unique ID of the vehicle in the digital twin data as the key, the value is set as the orientation angle of the vehicle. Taking the vehicle as the latitude, the orientation angle information of each vehicle is obtained, and the difference value of the continuous three groups of orientation angles is calculated. If the absolute values of these difference values are all greater than 90 degrees, it is determined that the vehicle meets the vehicle turning abnormal condition, and the vehicle turning abnormality is determined as the target abnormal type of the vehicle.

[0098] The embodiment determines the orientation angle continuous change information according to the orientation angle feature, and further determines whether the vehicle has a turning abnormal problem according to the orientation angle continuous change information, thereby improving the accuracy and efficiency of the vehicle turning abnormality judgment.

[0099] Based on the association relationship between the abnormal conditions of the candidate abnormal types and the candidate abnormal sources, if the vehicle meets the vehicle turning abnormal condition, the abnormal source of the vehicle turning abnormality of the vehicle is determined to be the source data, and the error reason is the orientation angle abnormality of the source data pushed by the roadside.

[0100] S340, the driving feature corresponding to the abnormal condition of the target abnormal type is taken as an abnormal driving feature, and the abnormal proportion of the target abnormal type is determined according to the abnormal driving feature and the extracted driving feature, to obtain the test result of the vehicle digital twin.

[0101] The scheme of the embodiment tests the vehicle turning abnormality through the orientation angle feature of the digital twin data, improves the test accuracy of the vehicle turning abnormality twin effect, and can detect the abnormal twin effect that may occur in advance from the data level, thereby improving the display accuracy of the digital twin. On the other hand, the evaluation result of the digital twin effect can be quantified by testing from the data level, thereby improving the accuracy of the test result.

[0102] Figure 4 is a schematic diagram of another vehicle digital twin test method according to an embodiment of the present disclosure. The embodiment is a further refinement of the above technical solution. The technical solution in the embodiment can be combined with each optional scheme in one or more of the above embodiments. As shown in Figure 4 The vehicle digital twin test method includes the following steps:

[0103] S410, obtaining the digital twin data of the vehicle from the cloud.

[0104] S420, extracting the driving feature of the vehicle from the digital twin data.

[0105] S430, determining a repetition degree parameter according to the driving feature of the vehicle.

[0106] The repetition degree parameter represents the feature repetition rate or push repetition rate in the driving feature of the vehicle, i.e., the repetition rate of the driving feature of the vehicle in continuous different digital twin data or the receiving time interval of the digital twin data of the vehicle. According to the repetition degree parameter, the push rule of the digital twin data can be determined, and then the target abnormal type is determined according to the push rule.

[0107] Specifically, when the repetition degree parameter represents the feature repetition rate in the driving feature of the vehicle, all dimensional features of the vehicle are extracted from the digital twin data, including vehicle direction, latitude and longitude, source, speed, etc. The number of digital twin data with consistent all-dimensional features or the receiving time range of continuous digital twin data is determined, and is determined as the first repetition degree parameter. For example, based on the road side equipment collecting data on the preset road section, the corresponding digital twin data pushed by the cloud is subscribed, and the data is written to the disk. The vehicle unique ID in the digital twin data is taken as the key, and the value is set as various information (such as vehicle direction, latitude and longitude, source, speed, etc.). The latitude of the vehicle is taken as the latitude, and the number of consecutive digital twin data with the same value or the time range of receiving these consecutive digital twin data is determined, such as the value of 5 consecutive digital twin data being the same, or the digital twin data pushed for more than 2s being consistent, and then the number or the time range is determined as the first repetition degree parameter.

[0108] If it is determined that the timestamps in the continuous digital twin data are inconsistent, and the other dimensional features are consistent, the number of corresponding digital twin data or the receiving time range is determined as the second repetition degree parameter. The other dimensional features refer to the other dimensions in the digital twin data except the timestamp dimension. For example, based on the road side equipment collecting data on the preset road section, the corresponding digital twin data pushed by the cloud is subscribed, and the data is written to the disk. The vehicle unique ID in the digital twin data is taken as the key, and the value is set as various information (such as vehicle direction, latitude and longitude, source, speed, orientation angle, etc.). The latitude of the vehicle is taken as the latitude, and the number of consecutive digital twin data with consistent latitude and longitude information, source, speed, and orientation angle but inconsistent timestamps or the time range of receiving these consecutive digital twin data is determined, and then the number or the time range is determined as the second repetition degree parameter.

[0109] The repetition degree parameter represents the push repetition rate, the timestamp feature of the vehicle is extracted from the digital twin data, and the timestamp feature is taken as the driving feature of the vehicle. The time interval of the vehicle during driving is determined according to the timestamp feature of the vehicle. If there is a time interval greater than a preset time threshold without receiving new digital twin data, the timeout non-receiving time interval is determined as a third repetition degree parameter. For example, based on multiple road segments, the vehicle data pushed by the cloud is subscribed, and the time of receiving the data is recorded and stored. Then, the third repetition degree parameter is determined by analyzing the time interval of each group of data.

[0110] S440, determining whether the vehicle meets the abnormal condition of the candidate abnormal type according to the repetition degree parameter.

[0111] The candidate abnormal type is vehicle flash-off abnormality, vehicle disappearance abnormality or vehicle static abnormality.

[0112] If the repetition degree parameter determined according to the driving feature of the vehicle is the first repetition degree parameter, when the first repetition degree parameter is greater than a preset consistency threshold, it is determined that the vehicle meets the vehicle flash-off or vehicle disappearance. For example, taking the vehicle as the latitude, the number of consecutive digital twin data with the same value or the time range of receiving these consecutive digital twin data is determined, such as 5 consecutive digital twin data with the same value or more than 2s of digital twin data with the same value, to determine that the vehicle meets the vehicle flash-off or vehicle disappearance. If there is no new digital twin data of the vehicle after the value consistent digital twin data, it is determined that the vehicle disappears, and if there is new digital twin data, it is determined that the vehicle flashes off.

[0113] Based on the association relationship between the abnormal condition of the candidate abnormal type and the candidate abnormal source, if the vehicle meets the first repetition degree parameter abnormal condition, it is determined that the abnormal source of the vehicle flash-off or vehicle disappearance abnormality existing in the vehicle is the repetition of the cloud push data.

[0114] If the repetition degree parameter determined according to the driving feature of the vehicle is the second repetition degree parameter, when the second repetition degree parameter is greater than a preset consistency threshold, it is determined that the vehicle meets the vehicle static. For example, taking the vehicle as the latitude, the latitude and longitude information, source, speed and direction angle of the consecutive digital twin data are consistent, but the reporting timestamp is inconsistent, so the vehicle is determined to be static.

[0115] Based on the association relationship between the abnormal condition of the candidate abnormal type and the candidate abnormal source, if the vehicle meets the second repetition degree parameter abnormal condition, it is determined that the abnormal source of the vehicle static abnormality existing in the vehicle is the source data, and the error reason is that the road side push data is repeated except for the inconsistent working time.

[0116] If the repetition degree parameter determined according to the driving feature of the vehicle is a third repetition degree parameter, when the third repetition degree parameter is greater than a preset time interval, it is determined that the vehicle meets the vehicle disappearance or vehicle flicker. For example, after the digital twin data of the target vehicle is not received for more than a preset time interval, it is determined that the vehicle disappears; after the digital twin data of the target vehicle is received after a preset time interval, it is determined that the vehicle flickers.

[0117] Based on the association relationship between the abnormal condition of the candidate abnormal type and the candidate abnormal source, if the vehicle meets the third repetition degree parameter abnormal condition, it is determined that the abnormal source of the vehicle disappearance or the vehicle flicker abnormality of the vehicle existing is the cloud push data regularity.

[0118] S450, determining the target abnormal type of the vehicle existing from the candidate abnormal type according to the determination result.

[0119] In another optional implementation of the embodiment, after S410, the method further includes:

[0120] Monitoring memory performance information of the twin effect display front end;

[0121] Determining whether the vehicle meets the abnormal condition of the candidate abnormal type according to the memory performance information, and determining the target abnormal type of the vehicle existing from the candidate abnormal type according to the determination result.

[0122] The twin effect display front end refers to a front end device for rendering and displaying the vehicle, such as a display device, and the memory performance information is used to represent the server memory information of the front end when rendering the vehicle. For example, the memory performance information includes memory occupancy rate, CPU usage rate, and display frame rate.

[0123] Specifically, in order to determine the influence of the front end performance on the twin effect in time, the performance of the front end is monitored, including memory occupancy rate, CPU usage rate, and display frame rate.

[0124] The memory occupancy rate can be used to monitor the memory size used by the current page. If the memory continues to grow and is not released, that is, the memory is greater than a preset memory value, there may be a memory leak problem, and it is determined that the vehicle meets the abnormal condition of the candidate abnormal type. The CPU usage rate can be used to monitor the CPU usage of the page. If the CPU usage rate is greater than a preset CPU threshold, there may be a performance problem, causing the vehicle to freeze, be stationary, or disappear. The display frame rate can be used to monitor the rendering performance of the page. If the frame rate is less than a preset frame rate threshold, the vehicle may freeze, be stationary, or disappear. The frame rate is determined according to the difference between the initial display time of the current frame and the current time when the current frame is not updated.

[0125] The embodiment improves the discovery efficiency of vehicle twin abnormal phenomena caused by performance problems by monitoring the front-end memory performance information, thereby improving the test efficiency of the vehicle digital twin, and determining the source of the vehicle abnormality.

[0126] In S460, the driving feature corresponding to the abnormal condition of the target abnormal type is taken as an abnormal driving feature, and the abnormal proportion of the target abnormal type is determined according to the abnormal driving feature and the extracted driving feature, to obtain the test result of the vehicle digital twin.

[0127] The scheme of the embodiment tests the display effect of other vehicle abnormalities through the repetition degree parameter of the digital twin data, thereby improving the test accuracy of the display effect of other vehicle abnormalities.

[0128] Figure 5 FIG. 1 is a structural schematic diagram of a vehicle digital twin testing device according to an embodiment of the present disclosure. The device can execute the vehicle digital twin testing method involved in any embodiment of the present disclosure. Referring to FIG. 1, the vehicle digital twin testing device 500 includes a twin data acquisition module 510, an abnormal type determination module 520, and a digital twin testing module 530. Figure 5

[0129] The twin data acquisition module 510 is configured to acquire digital twin data of a vehicle from the cloud.

[0130] The abnormal type determination module 520 is configured to extract driving features of the vehicle from the digital twin data, determine whether the vehicle meets an abnormal condition of a candidate abnormal type according to the driving features of the vehicle, and determine a target abnormal type existing in the vehicle from the candidate abnormal types according to a determination result.

[0131] The digital twin testing module 530 is configured to take a driving feature corresponding to the abnormal condition of the target abnormal type as an abnormal driving feature, and determine an abnormal proportion of the target abnormal type according to the abnormal driving feature and the extracted driving feature, to obtain a test result of the vehicle digital twin.

[0132] The scheme of the embodiment tests the display effect of other vehicle abnormalities through the repetition degree parameter of the digital twin data, thereby improving the test accuracy of the display effect of other vehicle abnormalities.

[0133] In an optional implementation of the embodiment, the abnormal type determination module includes:

[0134] ​extracting, from the digital twin data, a latitude and longitude feature and / or an orientation angle feature of the vehicle, and taking the latitude and longitude feature and / or the orientation angle feature of the vehicle as a driving feature of the vehicle;

[0135] determining, according to the latitude and longitude feature and / or the orientation angle feature of the vehicle, whether the vehicle satisfies an abnormal condition of a candidate abnormal type, and selecting, according to a determination result, a target abnormal type existing in the vehicle from the candidate abnormal type; the candidate abnormal type is a vehicle reverse abnormal type or a vehicle rotation abnormal type.

[0136] In an optional implementation of the embodiment, the abnormal type determination unit is specifically configured to:

[0137] determining a continuous change direction difference of the vehicle in a driving process according to the latitude and longitude feature of the vehicle;

[0138] if the continuous change direction difference is greater than a preset direction change threshold, determining that the vehicle satisfies a vehicle reverse abnormal condition, and taking the vehicle reverse abnormal type as the target abnormal type existing in the vehicle.

[0139] In an optional implementation of the embodiment, the device further includes an abnormal source determination module configured to:

[0140] before obtaining a test result of the vehicle digital twin, determining, according to an abnormal condition of a candidate abnormal type satisfied by the vehicle, a target abnormal source from candidate abnormal sources based on an association relationship between the abnormal condition of the candidate abnormal type and the candidate abnormal sources; wherein the candidate abnormal sources include source data and cloud twin data.

[0141] In an optional implementation of the embodiment, the vehicle reverse abnormal condition further includes whether an acquisition time stamp corresponding to an abnormal latitude and longitude feature satisfying the continuous change direction difference greater than the preset direction change threshold satisfies a growth relationship.

[0142] Correspondingly, the abnormal source determination module is specifically configured to:

[0143] if the abnormal condition of the candidate abnormal type satisfied by the vehicle is that the continuous change direction difference is greater than the preset direction change threshold and the acquisition time stamp corresponding to the abnormal latitude and longitude feature satisfies the growth relationship, determining that the abnormal source of the vehicle reverse abnormal type existing in the vehicle is the source data.

[0144] if the abnormal condition of the candidate abnormal type satisfied by the vehicle is that the continuous change direction difference is greater than the preset direction change threshold and the acquisition time stamp corresponding to the abnormal latitude and longitude feature does not satisfy the growth relationship, determining that the abnormal source is the cloud twin data.

[0145] In an optional implementation of the embodiment, the abnormal type determination unit is specifically configured to:

[0146] determine a continuous change difference of the orientation angle of the vehicle during driving according to the orientation angle feature of the vehicle;

[0147] if there are a preset number of continuous change differences of the orientation angle greater than a preset orientation angle threshold, it is determined that the vehicle meets the vehicle turning circle abnormal condition, and the vehicle turning circle abnormality is taken as the target abnormal type of the vehicle.

[0148] In an optional implementation of the embodiment, the abnormal type determination module comprises an abnormal condition matching unit, which is specifically configured to:

[0149] determine a repetition degree parameter according to the driving feature of the vehicle;

[0150] determine whether the vehicle meets the abnormal condition of the candidate abnormal type according to the repetition degree parameter; wherein the candidate abnormal type is vehicle flickering, vehicle disappearance or vehicle static.

[0151] In an optional implementation of the embodiment, the device further comprises a front-end monitoring module configured to:

[0152] after obtaining the digital twin data of the vehicle from the cloud, monitor the memory performance information of the twin effect display front end;

[0153] determine whether the vehicle meets the abnormal condition of the candidate abnormal type according to the memory performance information, and determine the target abnormal type of the vehicle from the candidate abnormal type according to the determination result.

[0154] The vehicle digital twin testing device described above can execute the vehicle digital twin testing method provided by any embodiment of the present disclosure, has the corresponding function modules and beneficial effects of the execution method. Technical details not described in detail in the embodiment can be referred to the vehicle digital twin testing method provided by any embodiment of the present disclosure.

[0155] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution comply with the relevant legal regulations and do not violate public order and good customs.

[0156] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0157] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0158] like Figure 6 As shown, device 600 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 600. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0159] Multiple components in device 600 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0160] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, such as the testing method of a vehicle digital twin. For example, in some embodiments, the testing method of a vehicle digital twin can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 502 and / or the communication unit 509. When the computer program is loaded onto the RAM 503 and executed by the computing unit 501, one or more steps of the testing method of a vehicle digital twin described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the method testing of a vehicle digital twin by any other appropriate means, such as by means of firmware.

[0161] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0162] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0163] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0164] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0165] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), blockchain networks, and the Internet.

[0166] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0167] It should be understood that the various forms of flow shown above can be re-ordered, added to, or have steps deleted, using the flow. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present disclosure can be achieved, which are not limited herein.

[0168] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle digital twin testing method, comprising: obtaining digital twin data of a vehicle from the cloud; extracting latitude and longitude features and / or orientation angle features of the vehicle from the digital twin data, and taking the latitude and longitude features and / or the orientation angle features of the vehicle as driving features of the vehicle; determining whether the vehicle satisfies an abnormal condition of a candidate abnormal type according to the latitude and longitude features and / or the orientation angle features of the vehicle, and selecting a target abnormal type in which the vehicle exists from the candidate abnormal type according to a determination result; the candidate abnormal type being a vehicle reverse abnormal type or a vehicle turning abnormal type; taking driving features corresponding to the abnormal condition of the target abnormal type as abnormal driving features, and determining an abnormal proportion of the target abnormal type according to the abnormal driving features and the extracted driving features, to obtain a testing result of the vehicle digital twin.

2. The method of claim 1, wherein, The determining whether the vehicle satisfies an abnormal condition of a candidate abnormal type according to the latitude and longitude features of the vehicle, and selecting a target abnormal type in which the vehicle exists from the candidate abnormal type according to a determination result, comprises: determining a continuous change direction difference of the vehicle in a driving process according to the latitude and longitude features of the vehicle; if the continuous change direction difference is greater than a preset direction change threshold, it is determined that the vehicle satisfies a vehicle reverse abnormal condition, and the vehicle reverse abnormal type is taken as the target abnormal type in which the vehicle exists.

3. The method of claim 2, before obtaining the testing result of the vehicle digital twin, the method further comprises: determining a target abnormal source from candidate abnormal sources according to the abnormal condition of the candidate abnormal type satisfied by the vehicle based on an association relationship between the abnormal condition of the candidate abnormal type and the candidate abnormal sources; wherein the candidate abnormal sources include source data and cloud twin data.

4. The method of claim 3, wherein, The vehicle reverse abnormal condition further comprises: whether an acquisition time stamp corresponding to abnormal latitude and longitude features satisfying that the continuous change direction difference is greater than the preset direction change threshold satisfies a growth relationship; Correspondingly, the determining a target abnormal source from the candidate abnormal sources according to the abnormal condition of the candidate abnormal type satisfied by the vehicle comprises: if the abnormal condition of the candidate abnormal type satisfied by the vehicle is that the continuous change direction difference is greater than the preset direction change threshold, and the acquisition time stamp corresponding to the abnormal latitude and longitude features satisfies the growth relationship, it is determined that the abnormal source of the vehicle reverse abnormal type in which the vehicle exists is the source data; if the abnormal condition of the candidate abnormal type satisfied by the vehicle is that the continuous change direction difference is greater than the preset direction change threshold, and the acquisition time stamp corresponding to the abnormal latitude and longitude features does not satisfy the growth relationship, it is determined that the abnormal source is the cloud twin data.

5. The method of claim 1, wherein, The determining whether the vehicle satisfies an abnormal condition of a candidate abnormal type according to the orientation angle features of the vehicle, and selecting a target abnormal type in which the vehicle exists from the candidate abnormal type according to a determination result, comprises: determining an orientation angle continuous change difference value of the vehicle in a driving process according to the orientation angle features of the vehicle; if there are a preset number of orientation angle continuous change difference values greater than a preset orientation angle threshold, it is determined that the vehicle satisfies a vehicle turning abnormal condition, and the vehicle turning abnormal type is taken as the target abnormal type in which the vehicle exists.

6. The method of claim 1, wherein, The method comprises the following steps: determining whether the vehicle meets an abnormal condition of a candidate abnormal type according to the driving characteristics of the vehicle, comprising: determining a repetition degree parameter according to the driving characteristics of the vehicle; determining whether the vehicle meets an abnormal condition of a candidate abnormal type according to the repetition degree parameter; wherein the candidate abnormal type is vehicle flicking, vehicle disappearance or vehicle static.

7. The method of claim 1, after obtaining the digital twin data of the vehicle from the cloud, the method further comprises: monitoring memory performance information of the twin effect display front end; determining whether the vehicle meets an abnormal condition of a candidate abnormal type according to the memory performance information, and determining a target abnormal type of the vehicle from the candidate abnormal type according to the determination result.

8. A testing device for vehicle digital twin, comprising: a twin data acquisition module for obtaining digital twin data of a vehicle from the cloud; an abnormal type determination module for extracting driving characteristics of the vehicle from the digital twin data, determining whether the vehicle meets an abnormal condition of a candidate abnormal type according to the driving characteristics of the vehicle, and determining a target abnormal type of the vehicle from the candidate abnormal type according to the determination result; a digital twin testing module for taking the driving characteristics corresponding to the abnormal condition of the target abnormal type as abnormal driving characteristics, and determining an abnormal proportion of the target abnormal type according to the abnormal driving characteristics and the extracted driving characteristics to obtain a testing result of the vehicle digital twin; wherein the abnormal type determination module comprises: a driving characteristic extraction unit for extracting latitude and longitude characteristics and / or orientation angle characteristics of the vehicle from the digital twin data, and taking the latitude and longitude characteristics and / or orientation angle characteristics of the vehicle as driving characteristics of the vehicle; 9. The apparatus of claim 8, wherein, an abnormal type determination unit for determining whether the vehicle meets an abnormal condition of a candidate abnormal type according to the latitude and longitude characteristics and / or orientation angle characteristics of the vehicle, and selecting a target abnormal type of the vehicle from the candidate abnormal type according to the determination result; the candidate abnormal type is vehicle reverse abnormal or vehicle turning abnormal. The abnormal type determination unit is specifically configured to: determine a continuous change direction difference of the vehicle in the driving process according to the latitude and longitude characteristics of the vehicle; if the continuous change direction difference is greater than a preset direction change threshold, it is determined that the vehicle meets a vehicle reverse abnormal condition, and the vehicle reverse abnormal is taken as the target abnormal type of the vehicle. Before obtaining the test result of the vehicle digital twin, based on the association relationship between the abnormal conditions of the candidate abnormal types and the candidate abnormal sources, a target abnormal source is determined from the candidate abnormal sources according to the abnormal conditions of the candidate abnormal types met by the vehicle; wherein 10. The device of claim 9, further comprising an abnormal source determination module configured to:

11. The apparatus of claim 10, wherein, the candidate abnormal source comprises source data and cloud twin data. the vehicle reverse abnormal condition further comprises whether an acquisition timestamp corresponding to the abnormal latitude and longitude characteristics that meet the condition that the continuous change direction difference is greater than the preset direction change threshold meets a growth relationship; correspondingly, the abnormal source determination module is specifically configured to: if the abnormal condition of the candidate abnormal type met by the vehicle is that the continuous change direction difference is greater than the preset direction change threshold, and the acquisition timestamp corresponding to the abnormal latitude and longitude characteristics meets the growth relationship, it is determined that the vehicle reverse abnormal source of the vehicle is the source data. If the abnormal condition of the candidate abnormal type that the vehicle satisfies is that the continuous change direction difference is greater than a preset direction change threshold, and the collection time stamp corresponding to the abnormal latitude and longitude feature does not satisfy the growth relationship, it is determined that the abnormal source is the cloud twin data.

12. The apparatus of claim 8, wherein, The abnormal type determination unit is specifically configured to: determine a change in the orientation angle of the vehicle during driving according to the orientation angle feature of the vehicle; if there are a preset number of orientation angle continuous change difference values greater than a preset orientation angle threshold, it is determined that the vehicle satisfies the vehicle turning abnormal condition, and the vehicle turning abnormality is determined as the target abnormal type of the vehicle.

13. The apparatus of claim 8, wherein, The abnormal type determination module includes an abnormal condition matching unit, which is specifically configured to: determine a repetition degree parameter according to the driving feature of the vehicle; determine whether the vehicle satisfies the abnormal condition of the candidate abnormal type according to the repetition degree parameter; wherein the candidate abnormal type is vehicle flashing, vehicle disappearance or vehicle static.

14. The apparatus of claim 8, further comprising: The front-end monitoring module is configured to: monitor the memory performance information of the front end of the twin effect display after obtaining the digital twin data of the vehicle from the cloud; determine whether the vehicle satisfies the abnormal condition of the candidate abnormal type according to the memory performance information, and determine the target abnormal type of the vehicle from the candidate abnormal type according to the determination result.

15. An electronic device comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to make the computer execute the method according to any one of claims 1-7.

17. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions are executed by the processor to implement the steps of the method according to any one of claims 1-7. The computer program / instructions are executed by the processor to implement the steps of the method according to any one of claims 1-7.

Images