Trajectory determination method, apparatus, device, and medium

Abstract

The present disclosure provides a trajectory determination method, device, equipment and medium, relates to the field of artificial intelligence, in particular to the technical field of intelligent transportation, computer vision and cloud service, and can be applied to the scene of electronic map making and intelligent navigation. The specific implementation scheme of the trajectory determination method is as follows: determining at least one driving trajectory corresponding to a target object; determining the confidence that the traffic tool corresponding to the target object is a speed-limited electric vehicle according to attribute information of the at least one driving trajectory; in response to the confidence being greater than or equal to a predetermined confidence, determining a target trajectory in the at least one driving trajectory; the target trajectory includes a trajectory with a driving feature of a non-speed-limited vehicle; and in response to the target trajectory not being included in the at least one driving trajectory, determining that the driving trajectory corresponding to the target object is a moving trajectory of a speed-limited electric vehicle.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of artificial intelligence, in particular to the technical field of intelligent transportation, computer vision and cloud services, and can be applied to scenarios such as electronic map making and intelligent navigation. BACKGROUND

[0002] With the development of economy and the improvement of living standards, safe and efficient travel has become one of the main demands of people. With the development of computer technology, people usually rely on electronic map guidance to improve travel efficiency. Electronic maps are usually updated and maintained by relying on trajectory data uploaded by authorized client applications. The trajectory data corresponds to the navigation mode selected by the user through the client application. If the navigation mode selected by the user does not match the type of the vehicle used by the user, the accuracy of the electronic map update and maintenance will be affected. SUMMARY

[0003] The present disclosure aims to provide a trajectory determination method, device, electronic equipment and storage medium for providing conditions for high-precision update and maintenance of electronic maps.

[0004] According to one aspect of the present disclosure, a trajectory determination method is provided, comprising: determining at least one driving trajectory corresponding to a target object; determining a confidence that a vehicle corresponding to the target object is a speed-limited electric vehicle according to attribute information of the at least one driving trajectory; determining a target trajectory in the at least one driving trajectory in response to the confidence being greater than or equal to a predetermined confidence; the target trajectory includes a trajectory having a driving feature of a non-speed-limited vehicle; and determining a driving trajectory corresponding to the target object as a moving trajectory of a speed-limited electric vehicle in response to the target trajectory not being included in the at least one driving trajectory.

[0005] According to another aspect of the present disclosure, a trajectory determination device is provided, comprising: a first trajectory determination module configured to determine at least one driving trajectory corresponding to a target object; a confidence determination module configured to determine a confidence that a vehicle corresponding to the target object is a speed-limited electric vehicle according to attribute information of the at least one driving trajectory; a target trajectory determination module configured to determine a target trajectory in the at least one driving trajectory in response to the confidence being greater than or equal to a predetermined confidence; the target trajectory includes a trajectory having a driving feature of a non-speed-limited vehicle; and a second trajectory determination module configured to determine a driving trajectory corresponding to the target object as a moving trajectory of a speed-limited electric vehicle in response to the target trajectory not being included in the at least one driving trajectory.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory connected with the at least one processor in communication; 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 trajectory determination method provided by the present disclosure.

[0007] 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 a computer to perform the trajectory determination method provided by the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising computer programs / instructions stored in at least one of a readable storage medium and an electronic device, and the computer programs / instructions, when executed by a processor, implement the trajectory determination method provided by the present disclosure.

[0009] 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 from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0011] Figure 1 is an application scenario diagram of the trajectory determination method and device according to the embodiments of the present disclosure;

[0012] Figure 2 is a flowchart of the trajectory determination method according to the embodiments of the present disclosure;

[0013] Figure 3 is a principle diagram of determining the confidence that the target object corresponds to a speed-limited electric vehicle according to the embodiments of the present disclosure;

[0014] Figure 4 is a principle diagram of determining the index value of the target object for the driving dimension according to the embodiments of the present disclosure;

[0015] Figure 5 is a principle diagram of determining the index value of the target object for the road network matching dimension according to the embodiments of the present disclosure;

[0016] Figure 6 is a structural block diagram of the trajectory determination device according to the embodiments of the present disclosure; and

[0017] Figure 7 is a block diagram of an electronic device for implementing the trajectory determination method according to the embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] 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 help the understanding of the present disclosure. These should be considered in their entirety only as exemplary. Thus, those of ordinary skill in the art will recognize various changes and modifications of the embodiments described herein, which changes and modifications are also within 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 herein.

[0019] In the update maintenance of the electronic map, it is necessary to rely on the track data uploaded by the authorized client application. In the update maintenance, it is generally considered that the navigation mode corresponding to the uploaded track data is accurate. The navigation mode corresponding to the track data can include one of a driving mode, a cycling mode, and a walking mode. However, if the user using the client application does not select the correct navigation mode, it will bring some interference information to the update maintenance of the electronic map, and bring trouble to the map development.

[0020] For example, in the update maintenance of the electronic map, the road condition needs to be calculated. If there is a traffic jam in the actual scene, and the track data corresponding to the driving mode uploaded is the track data of an electric bicycle, the calculated road condition result will be a non-congestion result that does not match the actual scene because the electric bicycle travels smoothly. Or, in the update maintenance of the electronic map, the road passable condition needs to be updated. If the road is only passable for small-sized traffic tools such as electric bicycles in the actual scene, and the track data corresponding to the driving mode uploaded is the track data of an electric bicycle, an update result that does not match the actual scene will be obtained because the electric bicycle is passable.

[0021] Based on this, for the update maintenance of the electronic map, it is crucial to select the moving track of other traffic tools except non-speed-limited vehicles (such as motor vehicles) from the driving track of the driving mode. For example, considering that the speed of other traffic tools except vehicles is smaller than that of non-speed-limited vehicles, the selection can be made according to the speed of the driving track and the like.

[0022] However, in the case that the speed-limited electric vehicle is modified and the speed of the speed-limited electric vehicle can reach a large value, only selecting the moving track of other traffic tools from the driving track of the driving mode according to the speed will have the problem of low selection accuracy and inaccurate update maintenance of the electronic map.

[0023] To solve this problem, the present disclosure provides a track determination method, device, equipment and medium, which aims to select the moving track of the speed-limited electric vehicle from the driving track. The following first combines Figure 1 The application scenario of the method and device provided by the present disclosure is described.

[0024] Figure 1 This is a schematic diagram illustrating an application scenario of the trajectory determination method and apparatus according to embodiments of this disclosure.

[0025] like Figure 1 As shown, the application scenario 100 of this embodiment may include a terminal device 110 and a server 130. The terminal device 110 may be various electronic devices with processing functions, including but not limited to vehicle terminal devices, smartphones, tablets, smartwatches, and laptop computers, etc.

[0026] Terminal device 110 may have various client applications installed, such as navigation applications, instant messaging applications, web browsing applications, music playback applications, etc. (for example only).

[0027] Server 130 may be a backend management server that supports the operation of client applications installed on terminal device 110, or it may be a cloud server or a blockchain server, etc. This disclosure does not limit it.

[0028] In one embodiment, the terminal device 110, when authorized, can upload driving data 120 describing the driving trajectory to the server 130. Upon receiving the driving data 120, the server 130 can process it to determine the true type of the driving trajectory. This true type may include unlimited speed vehicles, speed-limited electric vehicles, pedestrians, bicycles, etc. Subsequently, the server 130 can, for example, update and maintain the map data of the electronic map stored in the database 140 based on the driving data. Specifically, it can update and maintain road data corresponding to the true type of the driving trajectory; this disclosure does not limit this specific action.

[0029] In one embodiment, the server 130 may, for example, respond to a loading request sent by the terminal device 110 by sending map data stored in the database 140 to the terminal device 110, so that the terminal device 110 loads and displays the electronic map.

[0030] It should be noted that the trajectory determination method provided in this disclosure can be executed by server 130 or by any electronic device that is communicatively connected to server 130. Correspondingly, the trajectory determination device provided in this disclosure can be installed in server 130 or in any electronic device that is communicatively connected to server 130.

[0031] It should be understood that Figure 1 The number and type of terminal devices 110, servers 130, and databases 140 shown are merely illustrative. Depending on implementation needs, there can be any number and type of terminal devices 110, servers 130, and databases 140.

[0032] The following will be described in conjunction with Figures 2 to 5 The trajectory determination method provided by the present disclosure will be described in detail.

[0033] Figure 2 is a flowchart of a trajectory determination method according to an embodiment of the present disclosure.

[0034] As Figure 2 indicated, the trajectory determination method 200 of this embodiment can include operation S210 to operation S250.

[0035] In operation S210, at least one driving trajectory corresponding to a target object is determined.

[0036] According to an embodiment of the present disclosure, the target object can be various terminal devices installed with a navigation application, such as a vehicle-mounted terminal device or a handheld terminal device. The at least one driving trajectory corresponding to the target object is a recorded movement trajectory during the target object is provided with navigation information in a driving mode.

[0037] According to an embodiment of the present disclosure, the navigation application installed on the target object can upload driving data including driving trajectories in real time if authorized. This embodiment can periodically process the driving data uploaded by the target object to obtain at least one driving trajectory corresponding to the target object. The driving data may, for example, include attribute information of the driving trajectory. The attribute information can include driving direction, driving speed, position information, etc. of each trajectory point in the driving trajectory.

[0038] In an embodiment, a knowledge graph can be constructed in advance, the nodes in the knowledge graph including object nodes and trajectory nodes, the object nodes indicating a target object, and the trajectory nodes indicating a trajectory. The navigation mode corresponding to the trajectory can include a driving mode, a walking mode, or a cycling mode, etc. In the knowledge graph, there is an edge between the object node corresponding to the target object and the trajectory node corresponding to the trajectory uploaded by the target object. This embodiment can take the trajectory corresponding to the driving mode in the trajectory indicated by the trajectory node connected to the object node indicating the target object as the driving trajectory corresponding to the target object.

[0039] In operation S220, a confidence degree that the vehicle corresponding to the target object is a speed-limited electric vehicle is determined according to attribute information of the at least one driving trajectory.

[0040] According to an embodiment of the present disclosure, the attribute information can include a travel speed of each trajectory point, and the confidence level can be determined according to a distribution of the travel speed of each trajectory point. For example, the higher the proportion of trajectory points with a travel speed less than a first predetermined speed among all trajectory points, the higher the confidence level that the target object corresponds to a speed-limited electric vehicle. For example, the confidence level can also be determined according to the travel direction. For example, the higher the proportion of trajectory points with a travel direction opposite to the allowed travel direction on the road (i.e., in the opposite direction) among all trajectory points, the higher the confidence level that the target object corresponds to a speed-limited electric vehicle. The first predetermined speed can be any value less than 60 km / h, such as 40 km / h or 50 km / h, and the present disclosure does not limit the first predetermined speed.

[0041] The vehicle corresponding to the target object is a vehicle that moves the target object. The speed-limited electric vehicle can be an electric automatic vehicle, an electric tricycle, or any other electric vehicle that needs to limit the travel speed according to relevant regulations.

[0042] In operation S230, it is first determined whether the confidence level is greater than or equal to a predetermined confidence level. If the confidence level is greater than or equal to the predetermined confidence level, it is then determined whether the target trajectory is included in the at least one driving trajectory.

[0043] The predetermined confidence level can be a value close to 1, such as 0.6, 0.7, or 0.8. The predetermined confidence level can be set according to actual needs. For example, when it is necessary to ensure the recall accuracy, a larger predetermined confidence level can be set, such as a value not less than 0.8. When it is necessary to ensure the recall rate, a smaller predetermined confidence level can be set, such as a value not less than 0.6. The present disclosure does not limit the setting of the predetermined confidence level.

[0044] The target trajectory includes a trajectory with a travel characteristic of a non-speed-limited vehicle, such as at least one of a characteristic of visiting a target interest point, a characteristic of having a trajectory point with a travel speed higher than a second predetermined speed, and a characteristic of a smoothness of the trajectory being greater than a predetermined smoothness threshold. The target interest point can be at least one of a refueling point, an electric vehicle battery replacement point, a highway, a car wash, or the like. The second predetermined speed can be any empirical value greater than 60 km / h, such as 70 km / h or 80 km / h. The smoothness of the trajectory can be determined according to, for example, an angle between two trajectory segments formed by connecting adjacent three trajectory points in the driving trajectory. For example, the smaller the angle between the two trajectory segments, the smaller the smoothness.

[0045] In a case where the confidence is greater than or equal to the predetermined confidence and the target track is not included in the at least one driving track, operation S240 can be performed to determine that the driving track corresponding to the target object is the moving track of the speed-limited electric vehicle. Otherwise, operation S250 can be performed to determine that the driving track corresponding to the target object is not the moving track of the speed-limited electric vehicle. For example, in a case where the target track is included in the at least one driving track, it can be determined that the driving track corresponding to the target object is the moving track of the non-speed-limited vehicle, regardless of whether the confidence is greater than or equal to the predetermined confidence.

[0046] The embodiments of the present disclosure can effectively and accurately filter out the moving track of the speed-limited electric vehicle by combining the confidence determined according to the attribute information and the driving feature of the non-speed-limited vehicle to perform secondary screening on the driving track, and improve the recall rate of the speed-limited electric vehicle. Furthermore, by listing all the driving tracks of the target object whose driving track does not include the target track as the moving track of the speed-limited electric vehicle, the situation that the moving track of the speed-limited electric vehicle is missed due to inaccurate attribute information can be avoided, and the integrity and effectiveness of eliminating the moving track of the speed-limited electric vehicle from the driving track are further ensured, which is beneficial to improving the update dimension accuracy of the electronic map.

[0047] Figure 3 FIG. 1 is a schematic diagram of a principle of determining the confidence that the target object corresponds to the speed-limited electric vehicle according to an embodiment of the present disclosure.

[0048] According to the embodiments of the present disclosure, the attribute information of the driving track can be used to determine the index value of the target object for each dimension in the at least two predetermined dimensions. Subsequently, the confidence that the vehicle used by the target object is the speed-limited electric vehicle is determined according to the index values of the at least two predetermined dimensions.

[0049] The index value can be understood as the index value of the track corresponding to the target object. By considering the index values of the at least two dimensions when determining the confidence, the driving track corresponding to the target object can be evaluated from the at least two dimensions, so that the confidence can be determined according to the evaluation results of the driving track in the at least two dimensions. In this way, the accuracy of the determined confidence can be improved.

[0050] In an embodiment, the at least two dimensions can include at least two of a driving dimension, a road network matching dimension, a road dimension, and a trajectory quantity dimension. The attribute information related to the driving dimension can include at least one of a driving speed, a driving direction, a driving mileage, etc. The attribute information related to the road network matching dimension and the road dimension can include a position of a trajectory point. The road network matching dimension and the road dimension differ in that the road network matching dimension focuses on a matching relationship between a trajectory point and a road, and the road dimension focuses on a type of a road on which a trajectory point is located. The trajectory quantity dimension relates to a quantity of driving trajectories corresponding to the target object.

[0051] For example, the index value of the driving dimension can be negatively correlated with the driving speed and / or the driving mileage, because the driving speed and / or the driving mileage of the speed-limited electric vehicle are usually small, and the greater the driving speed and / or the driving mileage, the smaller the probability that the driving trajectory is the moving trajectory of the speed-limited electric vehicle.

[0052] For example, the index value of the trajectory quantity dimension can be positively correlated with the quantity of driving trajectories. This is because the greater the quantity of driving trajectories, the greater the reference value. By considering the index value of the trajectory quantity dimension, the accuracy and rationality of the confidence of the determination can be improved. In an embodiment, the index value of the target object for the trajectory quantity dimension can also be determined according to the quantity of at least one driving trajectory corresponding to the target object in the following manner: when the driving trajectory is less than or equal to a first predetermined quantity, the index value can be assigned in a stepwise manner in a manner that the index value is positively correlated with the quantity of driving trajectories, and if the driving trajectory is greater than the first predetermined quantity, the index value is determined to be 1. For example, if the quantity of driving trajectories is 1, the index value is determined to be a first value; if the quantity of driving trajectories is 2, the index value is determined to be a second value; if the quantity of driving trajectories is 3, the index value is determined to be a third value; and if the quantity of driving trajectories is greater than 3, the index value is determined to be 1. The first value is less than the second value, and the second value is less than the third value. For example, the first value can be 0.5, the second value can be 0.8, and the third value can be 0.9, and the disclosure does not limit the values of the three values.

[0053] For example, the index value of the road network matching dimension can be determined according to the position of the trajectory point relative to the center of the road. For example, taking the driving rule of driving on the right as an example, if the trajectory point is located on the right side of the center point of the road, the index value of the road network matching dimension is greater, and if the trajectory point is located on the left side of the center point of the road, the index value of the road network matching dimension is smaller.

[0054] For example, the index value of the road dimension can be determined based on the road types involved in the driving trajectory. For instance, if the road involves expressways, highways, elevated bridges, or other roads that restrict the speed of electric vehicles, the index value of the road dimension will be smaller. If all the roads involved are roads that allow the speed of electric vehicles, the index value of the road dimension will be larger. For example, if the roads restricting the speed of electric vehicles are defined as high-grade roads, this embodiment can first determine the road type involved in each driving trajectory based on the attribute information of each driving trajectory in at least one driving trajectory corresponding to the target object. Then, based on the determined road type, a second trajectory involving high-grade roads is determined in at least one driving trajectory. Finally, the index value of the road dimension is determined based on the first proportion of the second trajectory in at least one driving trajectory. This index value can be negatively correlated with the first proportion. This is because the higher the proportion of driving trajectories involving high-grade roads, the lower the probability that the vehicle corresponding to the target object is a speed-restricted electric vehicle. Alternatively, the number of second trajectories can be counted, and the index value of the road dimension can be determined based on this number. This index value is negatively correlated with the number of second trajectories. In one embodiment, the index value of the road dimension can be calculated using the following formula: value r = A + (B * squared of the first proportion - C * first proportion + D). Where A, B, C, and D are constants set according to requirements. For example, the sum of A and D can be 1, the value of A can be 0.6, the value of B can be 40, the value of C can be 8, and the value of D can be 0.4. This disclosure does not limit these values.

[0055] like Figure 3 As shown, taking at least two dimensions including driving dimension, road network matching dimension, road dimension, and trajectory quantity dimension as an example, in this embodiment 300, the attribute information 310 of all driving trajectories determined in the aforementioned operation S210 can first be used to determine the index values ​​of the target object for the driving dimension, road network matching dimension, road dimension, and trajectory quantity dimension, respectively, to obtain index values ​​321 to 324. Subsequently, based on the index values ​​321 to 324, the confidence level 330 of the target object's mode of transportation being a speed-limited electric vehicle is determined.

[0056] For example, the average of indicator values ​​321 to 324 can be used as the confidence level 330. Alternatively, the weighted sum of indicator values ​​321 to 324 can be calculated based on the pre-assigned weights to the indicator values ​​of the four dimensions, and this weighted sum can be used as the confidence level 330.

[0057] The following will combine Figure 4 The principles for determining the index values ​​of driving dimensions are further defined and expanded.

[0058] Figure 4is a schematic diagram of a principle of determining an index value of a target object for a driving dimension according to an embodiment of the present disclosure.

[0059] In an embodiment, the driving track corresponding to the target object can be one or at least two. In the case of one driving track, the embodiment can determine a value of a driving parameter of the one driving track according to attribute information of the one driving track, and then determine the index value of the driving dimension according to a size relationship between the driving parameter and a predetermined threshold. In the case of at least two driving tracks, the embodiment can determine an index value for each driving track, and then determine the index value of the driving dimension according to the at least two index values determined for the at least two driving tracks. The embodiment can improve the accuracy of the determined index value by first determining an index value for each driving track and then comprehensively considering the index values of the at least two driving tracks to determine the index value of the target object for the driving dimension, relative to directly determining the index value of the driving dimension according to the driving parameters of all tracks. This is because the driving parameters involved in the driving dimension can have large differences in different driving tracks, and if all driving parameters are comprehensively processed, the differences will be weakened. And in the scene of determining the moving track of the speed-limited electric vehicle, if the driving parameter of a driving track is abnormal, it can be determined that the driving track is the moving track of the speed-limited electric vehicle.

[0060] For example, the driving parameter can include a driving speed or a mileage. The driving speed can be, for example, an average value of driving speeds of a plurality of track points in the driving track, or can be a speed of a predetermined quantile among the driving speeds of the plurality of track points. The predetermined quantile can include, for example, at least one of an 80th quantile, an 85th quantile, and a 90th quantile, without limitation in the present disclosure. The driving speed can also be, for example, an average speed determined according to the mileage and the driving time of the driving track.

[0061] In an embodiment, at least two driving parameters can be set, and the index value of a single driving track in the driving dimension can be determined according to the values of the at least two driving parameters. Accordingly, for example, at least two thresholds corresponding to the at least two driving parameters can be set.

[0062] For example, the at least two driving parameters can include at least two of an average speed, a mileage, and a speed of a predetermined quantile. The predetermined quantile can be set to at least two, and when the at least two driving parameters include the speed of the predetermined quantile, one or more quantiles can be selected from the at least two quantiles, and the speed corresponding to the selected quantile can be set as the speed of the predetermined quantile.

[0063] For example, as shown in FIG. 2, the driving track of the target object can include a first driving track 201 and a second driving track 202. The first driving track 201 can be determined to be the moving track of the speed-limited electric vehicle, and the second driving track 202 can be determined to be the moving track of the non-speed-limited electric vehicle. The embodiment can determine an index value of the first driving track 201 for the driving dimension, and determine an index value of the second driving track 202 for the driving dimension. The embodiment can then determine the index value of the target object for the driving dimension according to the index values of the first driving track 201 and the second driving track 202. Figure 4As shown, in the embodiment 400, the at least two driving parameters set can include a first driving parameter and a second driving parameter. The driving trajectories corresponding to the target object can include a first trajectory 410 and a second trajectory 420. The embodiment 400 can determine the values of the first driving parameter (i.e., driving parameter a1411) and the second driving parameter (i.e., driving parameter b1412) of the first trajectory 410 according to the attribute information of the first trajectory 410. Similarly, the values of the first driving parameter (i.e., driving parameter a2421) and the second driving parameter (i.e., driving parameter b2422) of the second trajectory 420 can be determined.

[0064] Subsequently, the embodiment 400 can determine the sub-index value of the first trajectory 410 for the first driving parameter according to the size relationship between the driving parameter a1411 and the threshold value corresponding to the first driving parameter, obtaining a first sub-index value 413. Meanwhile, the sub-index value of the first trajectory 410 for the second driving parameter can be determined according to the size relationship between the driving parameter b1412 and the threshold value corresponding to the second driving parameter, obtaining a second sub-index value 414. Two sub-index values are obtained for the first trajectory 410. It can be understood that the number of sub-index values obtained for the first trajectory is equal to the number of driving parameters set. Subsequently, the index value of the first trajectory 410 in the driving dimension can be determined according to all the sub-index values obtained for the first trajectory 410, obtaining an index value V1415.

[0065] Similarly, for the second trajectory 420, the third sub-index value 423 can be determined according to the size relationship between the driving parameter a2421 and the threshold value corresponding to the first driving parameter, and the fourth sub-index value 424 can be determined according to the size relationship between the driving parameter b2422 and the threshold value corresponding to the second driving parameter. Subsequently, the index value of the second trajectory 420 in the driving dimension can be determined according to the third sub-index value 423 and the fourth sub-index value 424, obtaining an index value V2425.

[0066] After obtaining the index value of each trajectory in the driving dimension, the index value of the target object for the driving dimension 430 can be determined according to the index values of all trajectories in the driving dimension. For example, the average of the index values of all trajectories in the driving dimension can be taken as the index value of the target object for the driving dimension 430. Alternatively, the minimum value among the index values of all trajectories in the driving dimension can be taken as the index value Value travel 430.

[0067] In an embodiment, when determining the sub-index value of each trajectory for each parameter, the value of each parameter can be compared with the threshold value corresponding to each parameter first. If the value of each parameter is less than or equal to the threshold value corresponding to each parameter, a predetermined value can be assigned to the sub-index value for each parameter. If the value of each parameter is greater than the threshold value corresponding to each parameter, the difference between the value of each parameter and the threshold value corresponding to each parameter can be determined first, and then the sub-index value is determined according to the size of the difference. For example, the sub-index value can be negatively correlated with the difference, and the larger the difference, the smaller the sub-index value.

[0068] The predetermined value can be 1, 0.9, or any value close to 1 and less than or equal to 1, which is not limited in the present disclosure. When the value of each parameter is greater than the threshold value corresponding to each parameter, the sub-index value can be calculated using the following formula: value = 1-E*((P-Thr)). Wherein E is a constant set according to requirements, P is the value of the parameter, and Thr is the threshold value of the corresponding parameter. It can be understood that the constant E can have different values for different driving parameters, and the above formula for calculating the sub-index value is only an example to facilitate understanding of the present disclosure, which is not limited in the present disclosure.

[0069] For example, in an embodiment, the driving parameters can include the 85th percentile speed and mileage, the threshold value for the 85th percentile speed is 40 km / h, and the threshold value for the mileage is 8 km. The sub-index value of each trajectory for the 85th percentile speed can be calculated using the following formula: value s1 = 1-0.2*((P s1 -40)), P s1 is the 85th percentile speed, and value s1 is the sub-index value for the 85th percentile speed. The sub-index value of each trajectory for the mileage can be calculated using the following formula: value m = 1-5.88*0.00001*(P m -8)), P m is the mileage, and value m is the sub-index value for the mileage. It can be understood that the values of the above constant E, 0.2, 5.88, are only examples, which are not limited in the present disclosure.

[0070] For example, when determining the sub-index value according to the difference between the value of each parameter and the threshold corresponding to the each parameter, it can be determined that the value of the sub-index value is 0 if the difference is greater than a difference threshold. By setting the difference threshold, the value of the sub-index value calculated by the above formula can be avoided to be negative, and thus the determined sub-index value is more reasonable, and the accuracy of the determined sub-index value is improved. For example, the difference threshold can be 5 km / h for the 85th percentile speed, and the difference threshold can be 17 km for the mileage.

[0071] In an embodiment, the driving parameters can further include the 93th percentile speed, and the threshold for the 93th percentile speed is for example 48 km / h. The sub-index value of each trajectory for the 93th percentile speed can be calculated by the following formula: value s2 = 1 - 0.2*((P s2 - 48)), P s2 is the 93th percentile speed, and value s2 is the sub-index value for the 93th percentile speed. In an embodiment, the difference threshold for the 93th percentile speed can be 5 km / h.

[0072] In an embodiment, the driving parameters can further include the average speed, and the threshold for the average speed is for example 30 km / h. The sub-index value of each trajectory for the average speed can be calculated by the following formula: value s3 = 1 - 0.1*((P s3 - 30)), P s3 is the average speed, and value s3 is the sub-index value for the average speed. In an embodiment, the difference threshold for the average speed can be 10 km / h.

[0073] In an embodiment, the driving parameters can include two or more of the above-mentioned 85th percentile speed, mileage, 93th percentile speed and average speed, and then two or more sub-index values can be obtained for each trajectory for the two or more driving parameters. The minimum value of the two or more sub-index values can be taken as the index value of each trajectory in the driving dimension. The average value of at least one index value of at least one driving trajectory in the driving dimension can be taken as the index value of the target object in the driving dimension.

[0074] In an embodiment, when determining the index value of the target object for the driving dimension, the driving direction can also be considered. If the number of trajectories in which reverse driving occurs in the at least one driving trajectory corresponding to the target object is large, the index value of the target object for the driving dimension is large. That is, the index value is positively correlated with the number of trajectories in which reverse driving occurs. By considering the number of trajectories in which reverse driving occurs, the accuracy and rationality of the determined index value of the driving dimension can be improved.

[0075] For example, the driving direction of each trajectory point in each trajectory can be determined according to the attribute information of each trajectory. If there is a trajectory point in which the driving direction is opposite to the driving direction allowed by the road among the plurality of trajectory points included in each trajectory, it is determined that the each trajectory is a first trajectory involving reverse driving. Subsequently, the embodiment can count the number of first trajectories in the at least one driving trajectory, and determine the index value of the target object for the driving dimension according to the number of first trajectories.

[0076] For example, the index value of the target object for the driving dimension can be determined according to the number of first trajectories in the following manner: when the number of first trajectories is less than or equal to a second predetermined number, the index value can be assigned in a stepwise manner in which the index value is positively correlated with the number of first trajectories, and if the number of first trajectories is greater than the second predetermined number, the index value is determined to be 1.2. For example, if the number of first trajectories is 1, the index value is determined to be a fourth value; if the number of first trajectories is 2, the index value is determined to be a fifth value; if the number of first trajectories is 3, the index value is determined to be a sixth value; and if the number of first trajectories is greater than 3, the index value is determined to be 1.2. The fourth value is less than the fifth value, and the fifth value is less than the sixth value. For example, the fourth value can be 1, the second value can be 1.1, and the third value can be 1.12, and the present disclosure does not limit the values of the three values.

[0077] In an embodiment, when determining the index value of the target object for the driving dimension, both the driving speed and / or mileage and the driving direction can be considered. In this embodiment, the index value determined according to the driving speed and / or mileage by the principle shown in Figure 4 is taken as a first index value, and the index value determined according to the driving direction is taken as a second index value. Subsequently, the first index value and the second index value are both taken as the index value of the target object for the driving dimension, or the average or product of the first index value and the second index value is taken as the index value of the target object for the driving dimension.

[0078] The principle of calculating the index value of the road network matching dimension will be further limited and expanded below. Figure 5 The principle of determining the index value of the target object for the road network matching dimension according to an embodiment of the present disclosure is shown in the following table.

[0079] Figure 5 The principle of determining the index value of the target object for the road network matching dimension according to an embodiment of the present disclosure is shown in the following table.

[0080] In one embodiment, when determining the index value for the road network matching dimension, not only the projection orientation but also the projection distance can be considered. Specifically, a projection point corresponding to the trajectory point can be obtained by projecting the trajectory points in the driving trajectory onto the road topology network (i.e., the road network). The orientation of the trajectory point relative to the projection point is used as the projection orientation, and the distance between the trajectory point and the projection point is used as the projection distance. When projecting the trajectory point into the road network, the location information of the trajectory point can be used as the basis.

[0081] like Figure 5 As shown in Embodiment 500, when determining the index value for the road network matching dimension, all trajectory points 520 in at least one driving trajectory 510 can be counted first. Subsequently, based on the attribute information of at least one driving trajectory, specifically based on the position information of all trajectory points 520 in at least one driving trajectory, the projection orientation 531 and projection distance 532 of each trajectory point relative to the roads in the predetermined road network are determined. The predetermined road network can be the road network in the actual scene corresponding to the latest electronic map, and this disclosure does not limit it.

[0082] After obtaining the projected orientation and projection distance of each trajectory point, the target trajectory point 521 among all trajectory points can be determined based on these orientations and distances. Subsequently, based on the second proportion 540 of the target trajectory point 521 among all trajectory points 520, the index value 550 of the target object for the road network matching dimension can be determined. For example, the index value of the target object for the road network matching dimension can be positively correlated with the second proportion.

[0083] The target trajectory point 521 can be a trajectory point whose projected orientation conforms to the driving rules and whose projected distance is greater than a predetermined distance. For example, if the driving rule is to drive on the right, the target orientation can be the right-hand side. The predetermined distance can be set according to actual needs, for example, it can be set to 5m. In one embodiment, a distance range can be set for the projected distance, and trajectory points whose projected orientation is the target orientation and whose projected distance is within the predetermined distance range can be used as target trajectory points. The predetermined distance range can be 5m to 10m. Setting this distance range is to exclude trajectory points that are too far away from the projection point located on the road centerline and are not located on the road.

[0084] In an embodiment, when the second proportion is less than a predetermined proportion threshold, the indicator value for the road network matching dimension can be set as a fixed value, for example, 1, or any value less than 1. When the second proportion is greater than or equal to the predetermined proportion threshold, the indicator value for the road network matching dimension can be set as a value greater than the fixed value, and the value is positively correlated with the second proportion. Alternatively, when the second proportion is less than the predetermined proportion threshold, the indicator value for the road network matching dimension can be determined as the second proportion. When the second proportion is greater than or equal to the predetermined proportion threshold, the indicator value for the road network matching dimension can be expanded to a certain extent, for example, the indicator value for the road network matching dimension can be positively correlated with the second proportion, and the indicator value for the road network matching dimension is greater than the second proportion. For example, when the second proportion is greater than or equal to the predetermined proportion threshold, the indicator value for the road network matching dimension can be calculated according to the following formula: value rm = second proportion / 2 + F, where value rm is the indicator value for the road network matching dimension, and F is a constant. For example, the value of F can be any value greater than the predetermined proportion threshold / 2. For example, the predetermined proportion threshold is 0.7, and F can be 0.65.

[0085] This embodiment can highlight the influence of the road network matching dimension on the confidence to a certain extent when calculating the confidence by expanding the indicator value for the road network matching dimension when the second proportion is greater than or equal to the predetermined proportion threshold, which is beneficial to improve the accuracy of the determined confidence. This is because the reasonable setting of the predetermined distance interval can ensure that the target trajectory point is usually a trajectory point on a non-motor vehicle road. If the second proportion is large, the probability of the driving trajectory being a speed-limited electric vehicle is high, and accordingly, the confidence should also be high.

[0086] In an embodiment, after determining the indicator value of the target object for each dimension in the at least two predetermined dimensions, the embodiment can take the product of the at least two indicator values for the at least two predetermined dimensions as the confidence that the traffic tool used by the target object is a speed-limited electric vehicle. For example, when the product is a value greater than 1, the embodiment can take 1 as the confidence; when the product is a value less than or equal to 1, the embodiment takes the product as the confidence. In this way, it can be ensured that the value of the confidence is a value in the interval [0, 1].

[0087] Based on the trajectory determination method provided by the present disclosure, the present disclosure also provides a trajectory determination device. The device will be described in detail below. Figure 6

[0088] Figure 6 is a structural block diagram of a trajectory determination device according to an embodiment of the present disclosure.

[0089] As Figure 6 ​As shown, the trajectory determination apparatus 600 of the embodiment can include a first trajectory determination module 610, a confidence determination module 620, a target trajectory determination module 630, and a second trajectory determination module 640.

[0090] The first trajectory determination module 610 is configured to determine at least one driving trajectory corresponding to the target object. In an embodiment, the first trajectory determination module 610 can be configured to perform the operation S210 described above, and details are not repeated here.

[0091] The confidence determination module 620 is configured to determine a confidence that the vehicle used by the target object is a speed-limited electric vehicle according to attribute information of the at least one driving trajectory. In an embodiment, the confidence determination module 620 can be configured to perform the operation S220 described above, and details are not repeated here.

[0092] The target trajectory determination module 630 is configured to determine a target trajectory in the at least one driving trajectory in response to the confidence being greater than or equal to a predetermined confidence, the target trajectory including a trajectory having a driving feature of a non-speed-limited vehicle. In an embodiment, the target trajectory determination module 630 can be configured to perform the operation S230 described above, and details are not repeated here.

[0093] The second trajectory determination module 640 is configured to determine a driving trajectory corresponding to the target object as a moving trajectory of a speed-limited electric vehicle in response to the target trajectory not being included in the at least one driving trajectory. In an embodiment, the second trajectory determination module 640 can be configured to perform the operation S240 described above, and details are not repeated here.

[0094] According to an embodiment of the present disclosure, the confidence determination module 620 can include an indicator value determination sub-module and a confidence determination sub-module. The indicator value determination sub-module is configured to determine an indicator value of the target object for each of at least two predetermined dimensions according to attribute information of the at least one driving trajectory, to obtain at least two indicator values. The confidence determination sub-module is configured to determine a confidence that the vehicle used by the target object is a speed-limited electric vehicle according to the at least two indicator values.

[0095] According to an embodiment of the present disclosure, the predetermined dimensions include a driving dimension. The above-mentioned indicator value determination sub-module can include a parameter value determination unit, a first indicator determination unit, and a second indicator determination unit. The parameter value determination unit is configured to determine a value of a driving parameter of each driving trajectory according to attribute information of each driving trajectory. The first indicator determination unit is configured to determine an indicator value of each driving trajectory in the driving dimension according to a size relationship between the value of the driving parameter and a predetermined threshold. The second indicator determination unit is configured to determine a first indicator value of the target object in the driving dimension according to the indicator values of the at least one driving trajectory in the driving dimension.

[0096] According to an embodiment of the present disclosure, the driving parameters include at least two parameters, and the predetermined threshold values include at least two threshold values corresponding to the at least two parameters respectively. The first index determining unit can include a sub-index determining sub-unit and an index determining sub-unit. The sub-index determining sub-unit is configured to determine a sub-index value of each driving track for each parameter according to a size relationship between a value of each parameter and a threshold value corresponding to each parameter, and obtain at least two sub-index values. The index determining sub-unit is configured to determine an index value of each driving track in the driving dimension according to the at least two sub-index values.

[0097] According to an embodiment of the present disclosure, the sub-index determining sub-unit is configured to: in response to the value of each parameter being less than or equal to the threshold value corresponding to each parameter, determine the sub-index value of each driving track for each parameter as a predetermined value; and in response to the value of each parameter being greater than the threshold value corresponding to each parameter, determine the sub-index value of each driving track for each parameter according to a difference between the value of each parameter and the threshold value corresponding to each parameter.

[0098] According to an embodiment of the present disclosure, the driving parameters include at least one of the following parameters: average speed, mileage, speed of a predetermined quantile; and the predetermined quantile includes at least two quantiles.

[0099] According to an embodiment of the present disclosure, the predetermined dimension includes the driving dimension, and the index value determining sub-module can include a first track determining unit and a third index determining unit. The first track determining unit is configured to determine a first track involving reverse driving in the at least one driving track according to the attribute information of the at least one driving track. The third index determining unit is configured to determine a second index value of the target object for the driving dimension according to a number of the first track.

[0100] According to an embodiment of the present disclosure, the predetermined dimension includes a road network matching dimension. The index value determining sub-module can include a projection determining unit and a fourth index determining unit. The projection determining unit is configured to determine a projection direction and a projection distance of each track point in the at least one driving track relative to a road in a predetermined road network according to the attribute information of the at least one driving track. The fourth index determining unit is configured to determine an index value of the target object for the road network matching dimension according to a second proportion of a target track point in all track points included in the at least one driving track.

[0101] According to an embodiment of the present disclosure, the target track point includes a track point whose projection direction relative to the road in the road network is a target direction and whose projection distance is in a predetermined distance interval. In a case where the second proportion is greater than or equal to a predetermined proportion threshold value, the index value of the target object for the road network matching dimension is positively correlated with the second proportion, and the index value of the target object for the road network matching dimension is greater than the second proportion.

[0102] According to an embodiment of the present disclosure, the predetermined dimension includes a road dimension. The index value determination submodule can include a type determination unit, a second trajectory determination unit, and a fifth index determination unit. The type determination unit is configured to determine, according to attribute information of each driving trajectory, a road type of a road involved in each driving trajectory. The second trajectory determination unit is configured to determine, according to the road type, a second trajectory in the at least one driving trajectory that involves a road on which speed-limited electric vehicles are restricted to travel. The fifth index determination unit is configured to determine, according to a first proportion of the second trajectory in the at least one driving trajectory, an index value of the target object for the road dimension.

[0103] According to an embodiment of the present disclosure, the predetermined dimension includes a trajectory number dimension. The index value determination submodule can include a sixth index determination unit configured to determine, according to a number of the at least one driving trajectory, an index value of the target object for the trajectory number dimension.

[0104] According to an embodiment of the present disclosure, the driving feature of the non-speed-limited vehicle includes at least one of the following: a feature of visiting a target point of interest; a feature of a smoothness of a trajectory being greater than a predetermined smoothness threshold.

[0105] It should be noted that, in the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information involved in the technical solutions of the present disclosure comply with relevant laws and regulations, necessary security measures are taken, and do not violate public order and good customs. In the technical solutions of the present disclosure, the authorization or consent of the user is obtained before the user personal information is obtained or collected.

[0106] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program product.

[0107] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement the trajectory determination method according to an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0108] As Figure 7As shown, the device 700 includes a computing unit 701 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0109] Various components in the device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, etc., an output unit 707, such as various types of displays, speakers, etc., a storage unit 708, such as a magnetic disk, an optical disk, etc., and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0110] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose 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 701 performs various methods and processes described above, such as the trajectory determination method. For example, in some embodiments, the trajectory determination method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the trajectory determination method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the trajectory determination method by any other appropriate means, such as by means of firmware.

[0111] The various embodiments of the systems and techniques described above can be implemented 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 complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments 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.

[0112] 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 the functions / operations specified in the flowcharts and / or the 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, or entirely on a remote machine or server.

[0113] In the context of the present 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.

[0114] 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.

[0115] 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), and the Internet.

[0116] 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. A server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS (Virtual Private Server, or VPS for short) services. The server can also be a server of a distributed system, or a server combined with a blockchain.

[0117] It should be understood that various forms of flow shown above can be used with orders of steps reordered, added to, or removed. For example, the steps recited 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 are achieved, which are not limited herein.

[0118] The above detailed description does not limit the scope of the disclosure. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the disclosure shall be included in the scope of the disclosure.

Claims

1. A trajectory determination method, comprising: determining at least one driving trajectory corresponding to a target object; determining a confidence level that a vehicle corresponding to the target object is a speed-limited electric vehicle according to attribute information of the at least one driving trajectory; in response to the confidence level being greater than or equal to a predetermined confidence level, determining a target trajectory in the at least one driving trajectory; the target trajectory comprises a trajectory having a driving feature of a non-speed-limited vehicle; and in response to the target trajectory not being included in the at least one driving trajectory, determining that a driving trajectory corresponding to the target object is a moving trajectory of the speed-limited electric vehicle; wherein the determining the confidence level that the vehicle corresponding to the target object is the speed-limited electric vehicle according to the attribute information comprises: determining an index value of the target object for a driving dimension, a road network matching dimension, a road dimension and a trajectory number dimension, respectively, according to the attribute information; determining the confidence level that the vehicle corresponding to the target object is the speed-limited electric vehicle according to the index values of the driving dimension, the road network matching dimension, the road dimension and the trajectory number dimension. The determining the index value of the target object for the driving dimension, the road network matching dimension, the road dimension and the trajectory number dimension, respectively, according to the attribute information comprises: determining a value of a driving parameter of each driving trajectory according to attribute information of each driving trajectory; 2. The method of claim 1, wherein, determining an index value of each driving trajectory in the driving dimension according to a size relationship between the value of the driving parameter and a predetermined threshold; and determining a first index value of the target object for the driving dimension according to the index values of the at least one driving trajectory in the driving dimension. The driving parameter comprises at least two parameters; the predetermined threshold comprises at least two thresholds corresponding to the at least two parameters; the determining the index value of each driving trajectory in the driving dimension according to the size relationship between the value of the driving parameter and the predetermined threshold comprises: determining a sub-index value of each driving trajectory for each parameter according to a size relationship between a value of each parameter in the at least two parameters and a threshold corresponding to the each parameter, to obtain at least two sub-index values; and 3. The method of claim 2, wherein, determining the index value of each driving trajectory in the driving dimension according to the at least two sub-index values. The determining the sub-index value of each driving trajectory for each parameter according to the size relationship between the value of each parameter in the at least two parameters and the threshold corresponding to the each parameter comprises: in response to the value of the each parameter being less than or equal to the threshold corresponding to the each parameter, determining the sub-index value of each driving trajectory for the each parameter as a predetermined value; and 4. The method of claim 3, wherein, in response to the value of the each parameter being greater than the threshold corresponding to the each parameter, determining the sub-index value of each driving trajectory for the each parameter according to a difference between the value of the each parameter and the threshold corresponding to the each parameter. 5.The method of any one of claims 2-4, wherein: ​ ​ The driving parameters include at least one of the following parameters: average speed, mileage, and speed of a predetermined quantile; The predetermined quantile includes at least two quantiles.

6. The method of claim 1, wherein, The determining, according to the attribute information, of the index values of the target object for the driving dimension, the road network matching dimension, the road dimension, and the trajectory quantity dimension includes: According to the attribute information of at least one of the driving trajectories, determining a first trajectory involving reverse driving in at least one of the driving trajectories; and According to the number of the first trajectories, determining a second index value of the target object for the driving dimension.

7. The method of claim 1, wherein, The determining, according to the attribute information, of the index values of the target object for the driving dimension, the road network matching dimension, the road dimension, and the trajectory quantity dimension includes: According to the attribute information of at least one of the driving trajectories, determining a projection direction and a projection distance of each trajectory point in at least one of the driving trajectories relative to a road in a predetermined road network; According to the projection direction and the projection distance, determining a target trajectory point in at least one of the driving trajectories; and According to a second proportion of the target trajectory point in all trajectory points included in at least one of the driving trajectories, determining an index value of the target object for the road network matching dimension.

8. The method of claim 7, wherein: The target trajectory point includes a trajectory point whose projection direction relative to a road in a road network is a target direction and whose projection distance is in a predetermined distance interval; In a case where the second proportion is greater than or equal to a predetermined proportion threshold, the index value of the target object for the road network matching dimension is positively correlated with the second proportion, and the index value of the target object for the road network matching dimension is greater than the second proportion.

9. The method of claim 1, wherein, The determining, according to the attribute information, of the index values of the target object for the driving dimension, the road network matching dimension, the road dimension, and the trajectory quantity dimension includes: According to the attribute information of each of the driving trajectories, determining a road type of a road involved in each of the driving trajectories; According to the road type, determining a second trajectory involving a road that restricts driving of the speed-limited electric vehicle in at least one of the driving trajectories; and According to a first proportion of the second trajectory in at least one of the driving trajectories, determining an index value of the target object for the road dimension.

10. The method of claim 1, wherein, The determining, according to the attribute information, of the index values of the target object for the driving dimension, the road network matching dimension, the road dimension, and the trajectory quantity dimension includes: According to the number of at least one of the driving trajectories, determining an index value of the target object for the trajectory quantity dimension.

11. The method of claim 1, wherein, The driving feature of the non-speed-limited vehicle includes at least one of the following: A feature of visiting a target point of interest; A feature of a trajectory having a smoothness greater than a predetermined smoothness threshold.

12. A trajectory determination apparatus, comprising: a first trajectory determination module configured to determine at least one driving trajectory corresponding to a target object; a confidence determination module configured to determine, according to attribute information of at least one of the driving trajectories, a confidence that a vehicle corresponding to the target object is a speed-limited electric vehicle. The target trajectory determination module is configured to determine a target trajectory in the at least one driving trajectory in response to the confidence being greater than or equal to a predetermined confidence, the target trajectory including a trajectory having a driving feature of a non-speed-limited vehicle. And The second trajectory determination module is configured to determine a driving trajectory corresponding to the target object as a moving trajectory of the speed-limited electric vehicle in response to the target trajectory not being included in the at least one driving trajectory. The confidence determination module includes: The index value determination submodule is configured to determine an index value of the target object for a driving dimension, a road network matching dimension, a road dimension, and a trajectory number dimension, respectively, according to the attribute information; and The confidence determination submodule is configured to determine a confidence that the target object corresponds to a speed-limited electric vehicle according to the index values of the driving dimension, the road network matching dimension, the road dimension, and the trajectory number dimension.

13. The apparatus of claim 12, wherein, The index value determination submodule includes: The parameter value determination unit is configured to determine a value of a driving parameter of each of the driving trajectories according to attribute information of each of the driving trajectories; The first index determination unit is configured to determine an index value of each of the driving trajectories in the driving dimension according to a size relationship between the value of the driving parameter and a predetermined threshold value; and The second index determination unit is configured to determine a first index value of the target object for the driving dimension according to the index value of at least one of the driving trajectories in the driving dimension.

14. The apparatus of claim 13, wherein, The driving parameter includes at least two parameters, the predetermined threshold value includes at least two threshold values corresponding to the at least two parameters, and the first index determination unit includes: The sub-index determination subunit is configured to determine a sub-index value of each of the driving trajectories for each of the at least two parameters according to a size relationship between a value of each of the at least two parameters and a threshold value corresponding to the each of the at least two parameters, to obtain at least two sub-index values; and The index determination subunit is configured to determine the index value of each of the driving trajectories in the driving dimension according to the at least two sub-index values.

15. The apparatus of claim 14, wherein, The sub-index determination subunit is configured to: determine the sub-index value of each of the driving trajectories for the each of the at least two parameters as a predetermined value in response to the value of the each of the at least two parameters being less than or equal to the threshold value corresponding to the each of the at least two parameters; and determine the sub-index value of each of the driving trajectories for the each of the at least two parameters according to a difference between the value of the each of the at least two parameters and the threshold value corresponding to the each of the at least two parameters in response to the value of the each of the at least two parameters being greater than the threshold value corresponding to the each of the at least two parameters.

16. The apparatus of any one of claims 13-15, wherein: The driving parameter includes at least one of the following parameters: an average speed, a mileage, a speed of a predetermined quantile; The predetermined quantile includes at least two quantiles.

17. The apparatus of claim 12, wherein, The index value determination submodule includes: The first trajectory determination unit is configured to determine a first trajectory involving reverse driving in the at least one driving trajectory according to attribute information of the at least one driving trajectory; and The third index determination unit is configured to determine a second index value of the target object for the driving dimension according to a number of the first trajectories.

18. The apparatus of claim 12, wherein, The index value determination submodule comprises: a projection determination unit configured to determine, according to attribute information of at least one of the driving trajectories, a projection direction and a projection distance of each trajectory point in the at least one driving trajectory relative to a road in a predetermined road network; and a fourth index determination unit configured to determine, according to a second proportion of the target trajectory point in all trajectory points included in the at least one driving trajectory, an index value of the target object for the road network matching dimension.

19. The apparatus of claim 18, wherein: the target trajectory point comprises a trajectory point whose projection direction relative to a road in a road network is a target direction and whose projection distance is in a predetermined distance interval; in a case where the second proportion is greater than or equal to a predetermined proportion threshold, the index value of the target object for the road network matching dimension is positively correlated with the second proportion, and the index value of the target object for the road network matching dimension is greater than the second proportion.

20. The apparatus of claim 12, wherein, The index value determination submodule comprises: a type determination unit configured to determine, according to attribute information of each of the driving trajectories, a road type of a road involved in each of the driving trajectories; a second trajectory determination unit configured to determine, according to the road type, a second trajectory in the at least one driving trajectory that involves a road on which the speed-limited electric vehicle is restricted to travel; and a fifth index determination unit configured to determine, according to a first proportion of the second trajectory in the at least one driving trajectory, an index value of the target object for the road dimension.

21. The apparatus of claim 12, wherein, The index value determination submodule comprises: a sixth index determination unit configured to determine, according to a number of the at least one driving trajectory, an index value of the target object for a trajectory number dimension.

22. The apparatus of claim 12, wherein, The driving feature of the non-speed-limited vehicle comprises at least one of: a feature of visiting a target point of interest; a feature of a trajectory having a smoothness greater than a predetermined smoothness threshold.

23. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and 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 1-11.

24. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-11.

25. A computer program product comprising computer programs / instructions stored on at least one of a readable storage medium and an electronic device, the computer programs / instructions, when executed by a processor, implementing the steps of the method of any one of claims 1-11.

Images