A target vehicle path determination method based on an encrypted feature vector

Abstract

The present application relates to the technical field of path determination, in particular to a target vehicle path determination method based on encrypted feature vectors. The method comprises: determining whether a target vehicle is an abnormal vehicle according to videos of the target vehicle driving into and out of a target location area, if yes, obtaining vehicle feature data corresponding to the target vehicle, and performing encryption processing on the vehicle feature data corresponding to the target vehicle to obtain an encrypted feature vector corresponding to the target vehicle; sending the encrypted feature vector corresponding to the target vehicle to a video processing platform, so that the video processing platform matches the encrypted feature vector corresponding to the target vehicle with encrypted feature vectors in an initial encrypted feature vector set to obtain a target encrypted feature vector set; and determining a driving path of the target vehicle according to times and locations corresponding to the encrypted feature vectors in the target encrypted feature vector set. The present application can improve the safety and accuracy of the abnormal vehicle path determination process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle path determination, in particular to a target vehicle path determination method based on encrypted feature vectors. BACKGROUND

[0002] The ETC system (Electronic Toll Collection system) provides convenience for vehicle fast passage. However, there are also some problems, for example, there may be a situation that a vehicle follows a front vehicle to enter the ETC lane, that is, the vehicle passes through the ETC barrier within the lifting time triggered by the ETC device of the front vehicle, and does not use its own ETC device to lift the barrier; in order to determine the driving path of the above-mentioned abnormal vehicle (i.e. the vehicle following the front vehicle to enter or exit the ETC lane) and reasonably determine the toll amount of the abnormal vehicle, the features of the abnormal vehicle need to be sent to the video processing platform of the vehicle on the highway by the abnormal vehicle judgment system, so that the video processing platform can capture the position information of the abnormal vehicle; however, if the features of the abnormal vehicle are directly sent to the video processing platform for direct matching of the features, it is not conducive to protecting the feature information of the abnormal vehicle, and there is an unsafe problem; if only the feature (such as the license plate number) capable of uniquely representing the abnormal vehicle is encrypted and sent to the video processing platform for feature matching, since the license plate number of the abnormal vehicle may also change during driving, a situation that the matching fails may occur, resulting in that the path of the abnormal vehicle cannot be accurately obtained; how to improve the safety and accuracy of the abnormal vehicle path determination process is a problem to be solved. SUMMARY

[0003] The present application aims to provide a target vehicle path determination method based on encrypted feature vectors, so as to improve the safety and accuracy of the abnormal vehicle path determination process.

[0004] According to the present application, a target vehicle path determination method based on encrypted feature vectors is provided, and the method comprises the following steps:

[0005] S100, determining whether the target vehicle is an abnormal vehicle according to the video of the target vehicle entering and exiting the target position area, if yes, entering S200.

[0006] S200, obtain vehicle feature data corresponding to the target vehicle, and perform encryption processing on the vehicle feature data corresponding to the target vehicle to obtain an encrypted feature vector corresponding to the target vehicle;The vehicle feature data includes a plurality of vehicle static feature data and a plurality of vehicle driving behavior feature data;Wherein, when the vehicle feature data corresponding to the target vehicle is numerical feature data, the Gaussian noise encryption processing is adopted, and the standard deviation corresponding to the Gaussian noise added when the Gaussian noise encryption processing is adopted is positively correlated with the sensitive distinguishing coefficient of the corresponding vehicle feature, the sensitive distinguishing coefficient of the vehicle feature is obtained according to the sensitivity and the distinguishing degree corresponding to the vehicle feature, the sensitive distinguishing coefficient of the vehicle feature is positively correlated with the sensitivity corresponding to the vehicle feature, and the sensitive distinguishing coefficient of the vehicle feature is negatively correlated with the distinguishing degree corresponding to the vehicle feature.

[0007] S300, the encrypted feature vector corresponding to the target vehicle is sent to the video processing platform, so that the video processing platform matches the encrypted feature vector corresponding to the target vehicle with the encrypted feature vector in the initial encrypted feature vector set to obtain a target encrypted feature vector set;The target encrypted feature vector set includes the encrypted feature vector in the initial encrypted feature vector set matched with the encrypted feature vector corresponding to the target vehicle.

[0008] S400, the driving path of the target vehicle is determined according to the time and position corresponding to the encrypted feature vector in the target encrypted feature vector set.

[0009] Compared with the prior art, the present application has at least the following beneficial effects:

[0010] After determining that the target vehicle is an abnormal vehicle, the present application obtains a plurality of feature data of the target vehicle, the plurality of feature data including static feature data and driving behavior feature data of the vehicle, and the feature data of the target vehicle is encrypted and transmitted to the video processing platform, so that the video processing platform compares the feature vectors according to the encrypted feature vectors, and then obtains the positions passed by the target vehicle;The object of the comparison process of the present application is the encrypted feature vector, so the comparison process will not leak the direct feature information of the target vehicle, and the security is higher;And the present application uses a plurality of feature data of the target vehicle for comparison, compared with the method of using only one feature which can uniquely represent the target vehicle but may change, the present application can compare the features according to the plurality of features of the target vehicle, and the comparison result will be more accurate;Therefore, the present application can improve the security and accuracy of the abnormal vehicle path determination process.

[0011] Moreover, the present application adopts Gaussian noise encryption processing for numerical characteristic data, and the standard deviation of Gaussian noise added in the Gaussian noise encryption processing is positively correlated with the sensitive differentiation coefficient of the corresponding vehicle characteristic, so that the noise added for the vehicle characteristic with higher sensitivity and smaller differentiation is larger, and the noise added for the vehicle characteristic with lower sensitivity and larger differentiation is smaller, which can achieve the purposes of preventing the vehicle characteristic with higher sensitivity and smaller differentiation from being leaked and preventing the vehicle characteristic with lower sensitivity and larger differentiation from being distorted, and further improves the security and accuracy of the abnormal vehicle path determination process. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Figure 1 The flow chart of the target vehicle path determination method based on the encrypted characteristic vector provided by the embodiment of the present application is shown in the figure.

[0014] Figure 2 The flow chart of the matching process provided by the embodiment of the present application is shown in the figure.

[0015] Figure 3 The flow chart of the process of determining the driving path of the target vehicle provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0017] According to the present embodiment, as shown in the figure, Figure 1 a target vehicle path determination method based on an encrypted characteristic vector is provided, which comprises the following steps:

[0018] S100, determining whether the target vehicle is an abnormal vehicle according to the video of the target vehicle driving into and driving out of the target position area, if yes, entering S200.

[0019] As a specific embodiment, the target position region is an ETC transaction sensing region, and the abnormal vehicle is a vehicle having an abnormal behavior of passing through an ETC barrier; optionally, if the target vehicle passes through the target position region within the lifting time triggered by the ETC device of the preceding vehicle and the target vehicle does not trigger the lifting, the target vehicle is determined as an abnormal vehicle.

[0020] In the embodiment, if the target vehicle is not an abnormal vehicle, it is continued to determine whether the vehicle in the subsequent video is an abnormal vehicle, and S200-S400 are not executed.

[0021] In S200, vehicle feature data corresponding to the target vehicle is acquired, and the vehicle feature data corresponding to the target vehicle is encrypted to obtain an encrypted feature vector corresponding to the target vehicle; the vehicle feature data includes a plurality of vehicle static feature data and a plurality of vehicle driving behavior feature data; when the vehicle feature data corresponding to the target vehicle is numerical feature data, Gaussian noise encryption processing is adopted, and the standard deviation of the Gaussian noise added when the Gaussian noise encryption processing is adopted is positively correlated with a sensitive distinguishing coefficient of the corresponding vehicle feature, the sensitive distinguishing coefficient of the vehicle feature is obtained according to the sensitivity and the distinguishing degree corresponding to the vehicle feature, the sensitive distinguishing coefficient of the vehicle feature is positively correlated with the sensitivity corresponding to the vehicle feature, and the sensitive distinguishing coefficient of the vehicle feature is negatively correlated with the distinguishing degree corresponding to the vehicle feature.

[0022] In the embodiment, the classification vehicle feature is a qualitative feature, which is a feature used to describe the vehicle attribute and cannot be measured by the relative numerical size relationship, such as the vehicle type and the vehicle color; the numerical vehicle feature is a feature capable of measuring the difference by the relative numerical size relationship, such as the vehicle body height, the vehicle body width and the vehicle body length.

[0023] In the embodiment, the value of the vehicle static feature data is fixed and does not change during high-speed driving. For example, the vehicle static feature includes the vehicle type, the vehicle color, the vehicle body height, the vehicle body width and the vehicle body length, and the vehicle static feature data includes the vehicle type data, the vehicle color data, the vehicle body height data, the vehicle body width data and the vehicle body length data, wherein the vehicle type data and the vehicle color data are classification feature data, and the vehicle body height, the vehicle body width and the vehicle body length are numerical feature data.

[0024] As a specific embodiment, each numerical feature data corresponding to the target vehicle is greater than or equal to 0 and less than or equal to 1. As a specific embodiment, the vehicle type data of the target vehicle is 0 (the vehicle type data of 0 indicates that the vehicle type is a sedan; the vehicle type data of 1 indicates that the vehicle type is a sports utility vehicle; the vehicle type data of 2 indicates that the vehicle type is a multi-purpose vehicle, and the vehicle type data of 3 indicates that the vehicle type is a sports car, etc.), the vehicle color data is 1 (the vehicle color data of 0 indicates that the vehicle color is white, the vehicle color data of 1 indicates that the vehicle color is black, the vehicle color data of 2 indicates that the vehicle color is silver, the vehicle color data of 3 indicates that the vehicle color is gray, the vehicle color data of 4 indicates that the vehicle color is red, the vehicle color data of 5 indicates that the vehicle color is blue, and the vehicle color data of 6 indicates that the vehicle color is yellow), the body height data is 0.93 (the body height data of 0.93 indicates that the body height is 0.93xH, H is a preset maximum body height), the body width data is 0.75 (the body width data of 0.75 indicates that the body width is 0.75xW, W is a preset maximum body width), and the body length data is 0.8 (the body length data of 0.8 indicates that the body length is 0.8xL, L is a preset maximum body length).

[0025] The vehicle driving behavior feature data can be used to represent the driving habits of the driver driving the vehicle. Optionally, the driving behavior feature data of the target vehicle is the driving behavior feature data of the target vehicle when driving on the highway before. Different drivers have different driving behaviors, and the driving behavior has uniqueness. In a period of time, the driving style of the driver is relatively stable and will not change frequently and significantly, and the driving behavior has relative stability. Therefore, the target vehicle driving behavior feature data can be used for vehicle matching. The vehicle driving behavior features include the following: the following distance on the highway, the speed change mode, the average speed, and the lane change frequency type, etc. Among them, the following distance on the highway and the average speed are numerical features, and the speed change mode and the lane change frequency type are categorical features. For example, the following distance of the target vehicle is 0.7 (the following distance of the target vehicle is 0.7, which indicates that the following distance of the target vehicle is 0.7xD, D is a preset maximum following distance), the average speed of the target vehicle is 0.92 (the average speed of the target vehicle is 0.92, which indicates that the average speed of the target vehicle is 0.92xV, V is a preset maximum average speed), the speed change mode is 1 (the speed change mode of 0 indicates that the speed fluctuation is small, and the speed change mode of 1 indicates that the speed fluctuation is large), and the lane change frequency type is 0 (the lane change frequency type of 0 indicates that the lane change is frequent, and the lane change frequency type of 1 indicates that the lane change is not frequent).

[0026] In this embodiment, the encrypted feature vector corresponding to the target vehicle includes a deterministic feature sub-vector and a random feature sub-vector, the deterministic feature sub-vector is composed of a deterministic encryption processing result corresponding to the sub-type feature data corresponding to the target vehicle, and the random feature sub-vector is composed of a noise encryption processing result corresponding to the numerical feature data corresponding to the target vehicle. Optionally, the deterministic encryption processing result is a hash encryption processing result.

[0027] In this embodiment, the vehicle features to be obtained are preset, whether any vehicle feature is a sub-type feature or a numerical feature is also preset, and the sensitivity division coefficient, the degree of division, and the sensitivity of any numerical feature are also preset; the greater the sensitivity of a certain vehicle feature, the stronger the privacy of the vehicle feature, and the more the corresponding data needs to be prevented from being leaked; the greater the degree of division of a certain vehicle feature, the better the data of the vehicle feature can distinguish different vehicles. As a preferred specific embodiment, the sensitive division coefficient of the jth numerical feature corresponding to the target vehicle is a j , a j =k1×b j +k2×(1-c j ), b j is the sensitivity of the jth numerical feature corresponding to the target vehicle, c j is the degree of division of the jth numerical feature corresponding to the target vehicle, k1 and k2 are respectively preset sensitivity weight and division weight, k1 and k2 are both greater than 0 and less than 1, k1+k2=1, b j and c j are both greater than or equal to 0 and less than or equal to 1, the value range of j is 1 to m, and m is the number of numerical features. Based on this preferred specific embodiment, the sensitive division coefficient of any numerical feature can be obtained.

[0028] As a preferred specific embodiment, when the Gaussian noise corresponding to the standard deviation σ j is added to the Gaussian noise encryption processing of the jth numerical feature data corresponding to the target vehicle, σ j =ε / (p×(2-a j )), ε is a preset deviation threshold, p is a preset adjustment coefficient, p≥2, 0≤a j≤1. Based on the preferred specific implementation, when each numerical feature data corresponding to the target vehicle is greater than or equal to 0 and less than or equal to 1, the standard deviation corresponding to the added Gaussian noise becomes larger as the sensitive differentiation coefficient becomes larger, and becomes smaller as the sensitive differentiation coefficient becomes smaller, so that the noise value added to the numerical feature data with a larger sensitive differentiation coefficient is more likely to be larger than the noise value added to the numerical feature data with a smaller sensitive differentiation coefficient, which can prevent the vehicle feature with a larger sensitive differentiation coefficient from being leaked and prevent the vehicle feature with a smaller sensitive differentiation coefficient from being distorted too much, and further improve the security and accuracy of the abnormal vehicle path determination process.

[0029] In the embodiment, the numerical feature data is processed by Gaussian noise encryption, and the standard deviation of the added Gaussian noise is positively correlated with the sensitive differentiation coefficient of the corresponding vehicle feature when the Gaussian noise encryption is used. Therefore, the noise added to the vehicle feature with higher sensitivity and smaller differentiation degree is larger, and the noise added to the vehicle feature with lower sensitivity and larger differentiation degree is smaller, which can achieve the purpose of preventing the vehicle feature with higher sensitivity and smaller differentiation degree from being leaked and preventing the vehicle feature with lower sensitivity and larger differentiation degree from being distorted too much, and further improve the security and accuracy of the abnormal vehicle path determination process.

[0030] S300, the encrypted feature vector corresponding to the target vehicle is sent to the video processing platform, so that the video processing platform matches the encrypted feature vector corresponding to the target vehicle with the encrypted feature vectors in the initial encrypted feature vector set to obtain a target encrypted feature vector set; the target encrypted feature vector set includes the encrypted feature vectors in the initial encrypted feature vector set that match the encrypted feature vector corresponding to the target vehicle.

[0031] In this embodiment, the initial encrypted feature vector set is obtained by encrypting the vehicle feature data corresponding to the vehicles traveling on the target road network in the target time period. Each encrypted feature vector in the initial encrypted feature vector set corresponds to a monitoring point, a time, and a location. For example, a certain encrypted feature vector in the initial encrypted feature vector set is obtained by encrypting the vehicle feature data corresponding to a certain vehicle passing through a first monitoring point. The first monitoring point is the monitoring point corresponding to the encrypted feature vector, the time at which the vehicle passes through the first monitoring point is the time corresponding to the encrypted feature vector, and the location of the first monitoring point is the location corresponding to the encrypted feature vector. The target time period is the predicted time period during which the target vehicle travels on the highway. The length of the time period can be an empirical value, such as 2 hours, 4 hours, 8 hours, 12 hours, or 24 hours. For example, if the target vehicle is determined to be an abnormal vehicle at the entrance of the highway, a certain number of hours after the target vehicle enters the highway is determined as the target time period. If the target vehicle is determined to be an abnormal vehicle at the exit of the highway, a certain number of hours before the target vehicle exits the highway is determined as the target time period. The target road network is the road network in the area where the target vehicle travels on the highway. It can be an empirical value, such as the entire highway network. The process of encrypting the vehicle feature data corresponding to the vehicles traveling on the road network is the same as the process of encrypting the vehicle feature data corresponding to the target vehicle, which will not be described here.

[0032] As shown in Figure 2 The matching process includes:

[0033] S310, compare the deterministic feature sub-vector in the specified encrypted feature vector with the deterministic feature sub-vector in the encrypted feature vector corresponding to the target vehicle; the specified encrypted feature vector is any encrypted feature vector in the initial encrypted feature vector set.

[0034] In this embodiment, the elements at the same positions in the deterministic feature sub-vector in the specified encrypted feature vector and the deterministic feature sub-vector in the encrypted feature vector corresponding to the target vehicle represent the same deterministic feature.

[0035] S320, if the comparison result is the same, go to S330; otherwise, determine that the specified encrypted feature vector and the encrypted feature vector corresponding to the target vehicle do not match.

[0036] In this embodiment, if all the elements at the same positions in the deterministic feature sub-vector in the specified encrypted feature vector and the deterministic feature sub-vector in the encrypted feature vector corresponding to the target vehicle are the same, it is determined that the comparison result is the same; otherwise, it is determined that the comparison result is not the same.

[0037] S330, obtain a similarity between the random feature sub-vector in the specified encrypted feature vector and the random feature sub-vector in the encrypted feature vector corresponding to the target vehicle.

[0038] As a preferred specific implementation, the similarity between the random feature sub-vector in the specified encrypted feature vector and the random feature sub-vector in the encrypted feature vector corresponding to the target vehicle is r, r = 1 - ∑ n i=1 (w i × d i ), d i is a difference value between the i-th element in the normalized random feature sub-vector in the specified encrypted feature vector and the i-th element in the random feature sub-vector in the encrypted feature vector corresponding to the target vehicle, w i is a weight of the numerical feature corresponding to the i-th element in the random feature sub-vector, w i is negatively related to the sensitive discrimination coefficient of the numerical feature corresponding to the i-th element in the random feature sub-vector, ∑ n i=1 w i = 1, w i is greater than 0 and less than 1, the value range of i is 1 to n, and n is the number of elements included in the random feature sub-vector. Based on the preferred specific implementation, w i is negatively related to the sensitive discrimination coefficient of the numerical feature corresponding to the i-th element in the random feature sub-vector, which can improve the accuracy of matching.

[0039] S340, if the similarity is greater than or equal to a preset similarity threshold, it is determined that the specified encrypted feature vector matches the encrypted feature vector corresponding to the target vehicle; otherwise, it is determined that the specified encrypted feature vector does not match the encrypted feature vector corresponding to the target vehicle.

[0040] In this embodiment, the preset similarity threshold is an empirical value.

[0041] Based on S310-S340, the encrypted feature vector in the initial encrypted feature vector set that matches the encrypted feature vector corresponding to the target vehicle can be determined. The encrypted feature vector in the initial encrypted feature vector set that matches the encrypted feature vector corresponding to the target vehicle is also the encrypted feature vector corresponding to the target vehicle. The time and position corresponding to the encrypted feature vector in the initial encrypted feature vector set that matches the encrypted feature vector corresponding to the target vehicle are the relevant data generated by the target vehicle at different positions when driving on the expressway.

[0042] S400, determine the driving path of the target vehicle according to the time and position corresponding to the encrypted feature vector in the target encrypted feature vector set.

[0043] As an optional specific implementation method, such as Figure 3 As shown, S400 includes:

[0044] S410, arrange the positions of the encrypted feature vectors in the target encrypted feature vector set according to the corresponding time sequence.

[0045] S420 generates a sub-path between any two adjacent locations based on the road network.

[0046] It should be understood that sub-paths are part of the road network.

[0047] S430, determine the driving path of the target vehicle based on the sub-path.

[0048] As an optional implementation method, connecting the sub-paths in sequence constitutes the driving path of the target vehicle.

[0049] In this embodiment, after determining that the target vehicle is an abnormal vehicle, multiple feature data of the target vehicle are acquired. These multiple feature data include static feature data and driving behavior feature data of the vehicle. The feature data of the target vehicle is encrypted and then transmitted to the video processing platform, so that the video processing platform can compare the feature vectors based on the encrypted feature vectors to obtain the location of the target vehicle. The comparison process in this embodiment is based on the encrypted feature vectors, so the comparison process does not disclose the direct feature information of the target vehicle, thus improving security. Furthermore, this embodiment uses multiple feature data of the target vehicle for comparison. Compared with the method of using only a single feature that can uniquely identify the target vehicle but may change, this embodiment can perform feature comparison based on multiple features of the target vehicle, resulting in more accurate comparison results. Therefore, this embodiment can improve the security and accuracy of the abnormal vehicle path determination process.

[0050] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. It should also be understood that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for determining the path of a target vehicle based on encrypted feature vectors, characterized in that, The method includes the following steps: S100: Determine whether the target vehicle is an abnormal vehicle based on the video of the target vehicle entering and leaving the target location area. If so, proceed to S200. S200: Obtain vehicle feature data corresponding to the target vehicle, and encrypt the vehicle feature data corresponding to the target vehicle to obtain an encrypted feature vector corresponding to the target vehicle; the vehicle feature data includes several vehicle static feature data and several vehicle driving behavior feature data; wherein, when the vehicle feature data corresponding to the target vehicle is numerical feature data, Gaussian noise encryption is used, and the standard deviation of the Gaussian noise added during Gaussian noise encryption is positively correlated with the sensitivity discrimination coefficient of the corresponding vehicle feature. The sensitivity discrimination coefficient of the vehicle feature is obtained based on the sensitivity and discrimination of the vehicle feature, and the sensitivity discrimination coefficient of the vehicle feature is positively correlated with the sensitivity of the vehicle feature and negatively correlated with the discrimination of the vehicle feature. S300, the encrypted feature vector corresponding to the target vehicle is sent to the video processing platform so that the video processing platform can match the encrypted feature vector corresponding to the target vehicle with the encrypted feature vectors in the initial encrypted feature vector set to obtain the target encrypted feature vector set; the target encrypted feature vector set includes the encrypted feature vectors in the initial encrypted feature vector set that match the encrypted feature vector corresponding to the target vehicle. S400 determines the driving path of the target vehicle based on the time and location corresponding to the encrypted feature vectors in the target encrypted feature vector set.

2. The target vehicle path determination method based on encrypted feature vectors according to claim 1, characterized in that, The encrypted feature vector corresponding to the target vehicle includes a deterministic feature sub-vector and a random feature sub-vector. The deterministic feature sub-vector is composed of the deterministic encryption processing result corresponding to the categorical feature data of the target vehicle, and the random feature sub-vector is composed of the noise encryption processing result corresponding to the numerical feature data of the target vehicle.

3. The target vehicle path determination method based on encrypted feature vectors according to claim 2, characterized in that, The matching process includes: S310, compare the deterministic feature sub-vector in the specified encrypted feature vector with the deterministic feature sub-vector in the encrypted feature vector corresponding to the target vehicle; the specified encrypted feature vector is any encrypted feature vector in the initial encrypted feature vector set; S320, if the comparison results are the same, proceed to S330; otherwise, determine that the specified encrypted feature vector does not match the encrypted feature vector corresponding to the target vehicle. S330, obtain the similarity between the random feature subvector in the specified encrypted feature vector and the random feature subvector in the encrypted feature vector corresponding to the target vehicle; S340, if the similarity is greater than or equal to a preset similarity threshold, then it is determined that the specified encrypted feature vector matches the encrypted feature vector corresponding to the target vehicle; otherwise, it is determined that the specified encrypted feature vector does not match the encrypted feature vector corresponding to the target vehicle.

4. The target vehicle path determination method based on encrypted feature vectors according to claim 3, characterized in that, Let r be the similarity between the random feature vector in the specified encrypted feature vector and the random feature vector in the encrypted feature vector corresponding to the target vehicle, where r = 1 - ∑ n i=1 (w i ×d i ), d i w is the difference between the i-th element of the randomness feature subvector in the normalized specified encrypted feature vector and the i-th element of the randomness feature subvector in the encrypted feature vector corresponding to the target vehicle. i w represents the weight of the numerical feature corresponding to the i-th element in the randomness feature vector. i The sensitivity discrimination coefficient of the numerical feature corresponding to the i-th element in the randomness feature sub-vector is negatively correlated, ∑ n i=1 w i =1, w i The value of i is greater than 0 and less than 1, and the range of i is from 1 to n, where n is the number of elements included in the random feature vector.

5. The target vehicle path determination method based on encrypted feature vectors according to claim 1, characterized in that, The sensitivity discrimination coefficient of the j-th numerical feature corresponding to the target vehicle is a. j a j =k1×b j +k2×(1-c j ), b j Let c be the sensitivity of the j-th numerical feature corresponding to the target vehicle. j Let k1 and k2 be the discrimination index of the j-th numerical feature corresponding to the target vehicle, respectively, where k1 and k2 are preset sensitivity weights and discrimination weights, respectively. Both k1 and k2 are greater than 0 and less than 1, and k1 + k2 = 1. j and c j All values ​​are greater than or equal to 0 and less than or equal to 1, and the value of j ranges from 1 to m, where m is the number of numerical features.

6. The target vehicle path determination method based on encrypted feature vectors according to claim 1, characterized in that, S100 includes: If the target vehicle passes through the target location area within the time frame triggered by the ETC device of the preceding vehicle, and the target vehicle does not trigger the barrier to lift, then the target vehicle is determined to be an abnormal vehicle.

7. The target vehicle path determination method based on encrypted feature vectors according to claim 1, characterized in that, Each numerical feature data corresponding to the target vehicle is greater than or equal to 0 and less than or equal to 1.

8. The target vehicle path determination method based on encrypted feature vectors according to claim 1, characterized in that, The S400 includes: S410, Arrange the positions of the encrypted feature vectors in the target encrypted feature vector set according to the corresponding time sequence; S420: Generate a sub-path between any two adjacent locations based on the target road network; S430, determine the driving path of the target vehicle based on the sub-path.

9. The target vehicle path determination method based on encrypted feature vectors according to claim 1, characterized in that, The initial encrypted feature vector set is obtained by encrypting the vehicle feature data corresponding to vehicles traveling on the target road network within the target time period.

10. The target vehicle path determination method based on encrypted feature vectors according to claim 2, characterized in that, The result of deterministic encryption is the same as the result of hash encryption.

Images