Navigation starting point road determination method, device, equipment and storage medium

Abstract

The present disclosure provides a navigation starting point road determination method and device, equipment and storage medium, relates to the field of data processing, especially to the technical field of intelligent transportation, automatic driving and the like. The specific implementation scheme is: according to the road data of a plurality of roads corresponding to the current position of a vehicle, a plurality of candidate roads are determined in the plurality of roads, and the road data includes road direction; obtain the forward trajectory point data of the vehicle, the forward trajectory point data is the trajectory point data before the vehicle reaches the current position; according to the forward trajectory point data, the driving direction of the vehicle is determined; according to the driving direction and the road direction of the plurality of candidate roads, the navigation starting point road of the vehicle is determined in the plurality of candidate roads. The accuracy of the starting point binding road is improved.

Description

Technical Field

[0001] This disclosure relates to the technical fields of intelligent transportation and autonomous driving in the field of data processing, and in particular to a method, apparatus, device and storage medium for determining the starting point road of navigation. Background Technology

[0002] Navigation software is an indispensable tool for people's travel. The navigation services it provides can help users drive their vehicles from their current location to their destination.

[0003] The foundation of navigation services is accurate route binding to the vehicle's starting point. This means that when navigation software initiates navigation, the vehicle's starting road must be determined. Only with an accurate location of the vehicle's starting road can the subsequent navigation process proceed smoothly. Incorrect location may lead to problems such as inaccurate navigation voice prompts and incorrect navigation routes.

[0004] In related technologies, the starting point for road binding is mainly determined based on the location of the vehicle and the location of each road. However, for scenarios such as intersections with complex road networks or poor road network accuracy, the accuracy of starting point road binding based on the location of the vehicle and the road is relatively low. Summary of the Invention

[0005] This disclosure provides a method, apparatus, device, and storage medium for determining the starting road of a navigation system.

[0006] According to a first aspect of this disclosure, a method for determining a navigation starting point road is provided, comprising:

[0007] Based on road data of multiple roads corresponding to the vehicle's current location, multiple candidate roads are determined from the multiple roads, wherein the road data includes road direction;

[0008] Obtain the forward trajectory point data of the vehicle, wherein the forward trajectory point data is the trajectory point data of the vehicle before reaching the current position;

[0009] Based on the forward trajectory point data, the driving direction of the vehicle is determined;

[0010] Based on the driving direction and the road directions of the multiple candidate roads, the navigation starting road of the vehicle is determined from the multiple candidate roads.

[0011] According to a second aspect of this disclosure, a navigation starting point road determination device is provided, comprising:

[0012] The first determining unit is configured to determine multiple candidate roads from among the multiple roads based on road data corresponding to the current location of the vehicle, wherein the road data includes road direction;

[0013] The acquisition unit is used to acquire the forward trajectory point data of the vehicle, wherein the forward trajectory point data is the trajectory point data of the vehicle before it reaches the current position;

[0014] The processing unit is used to determine the driving direction of the vehicle based on the forward trajectory point data;

[0015] The second determining unit is used to determine the navigation starting road of the vehicle from among the multiple candidate roads based on the driving direction and the road direction of the multiple candidate roads.

[0016] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of the first aspects.

[0020] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described in any one of the first aspects.

[0021] According to a fifth aspect of this disclosure, a computer program product is provided, the computer program product comprising: a computer program stored in a readable storage medium, wherein at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the method described in the first aspect.

[0022] The navigation starting point road determination method, apparatus, device, and storage medium provided in this disclosure first determine multiple candidate roads from among the multiple roads corresponding to the vehicle's current location, thereby achieving preliminary screening of the navigation starting point road. Then, the vehicle's forward trajectory point data (trajectory point data before the vehicle reached its current location) is acquired, and the vehicle's driving direction is determined based on this data. Then, based on the driving direction and the road directions of the multiple candidate roads, the vehicle's navigation starting point road is determined from among the multiple candidate roads. For scenarios with complex road networks or poor road network accuracy, determining the vehicle's driving direction through forward trajectory point data provides more valuable directional information than road distance, thus improving the accuracy of determining the navigation starting point road during navigation by matching the vehicle's driving direction.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0024] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0025] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0026] Figure 2 A flowchart illustrating the navigation starting point road determination method provided in this embodiment of the disclosure;

[0027] Figure 3 A flowchart illustrating the method for determining candidate roads provided in this embodiment of the disclosure;

[0028] Figure 4 A schematic diagram illustrating a road determination scenario provided in an embodiment of this disclosure;

[0029] Figure 5 A schematic diagram of forward trajectory points provided in an embodiment of this disclosure;

[0030] Figure 6 A schematic diagram illustrating the process of determining the driving direction provided in an embodiment of this disclosure;

[0031] Figure 7 This is a schematic diagram illustrating the determination of the forward trajectory points of a target provided in an embodiment of the present disclosure;

[0032] Figure 8 This is a schematic diagram of the navigation starting point road determination device provided in an embodiment of the present disclosure;

[0033] Figure 9 This is a block diagram of an electronic device used to implement the navigation starting point road determination method of the embodiments of this disclosure. Detailed Implementation

[0034] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0035] In the embodiments of this disclosure, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the access relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone, where A and B can be singular or plural. In the textual description of this disclosure, the character " / " generally indicates that the preceding and following associated objects have an "or" relationship. Furthermore, in the embodiments of this disclosure, "first," "second," "third," "fourth," "fifth," and "sixth" are merely used to distinguish the content of different objects and have no other special meaning.

[0036] Starting point route binding refers to the process of locating the vehicle's initial road when using navigation software. Correctly binding the starting point is fundamental for navigation software to provide navigation services. Only when the vehicle's starting road is correctly located can the navigation software effectively provide navigation services, allowing users to drive correctly from the starting point to their destination. If the starting road is incorrectly located, it may lead to deviations in subsequent navigation services, such as inaccurate navigation voice prompts or incorrect navigation routes.

[0037] For example, it can be combined Figure 1 Understand the process of tying up the starting point. Figure 1 Please refer to the schematic diagram of an application scenario provided by an embodiment of this disclosure. Figure 1 The directed arrows represent different roads, and vehicle 10 is located at a certain position in the road network. When navigation is initiated, the road where vehicle 10 is currently located needs to be determined as the navigation starting point.

[0038] In related technologies, determining the road where vehicle 10 originates is mainly based on the high-precision positioning of the vehicle's current location using the Global Positioning System (GPS) and combined with high-precision road network data. During the process of binding the starting point to the road, the distance between vehicle 10 and the road is used as the matching feature with the highest weight.

[0039] The above-mentioned starting point road binding scheme has low accuracy in scenarios such as intersections with complex road networks or poor positioning accuracy, and there is a high possibility that the starting road of the vehicle will be incorrectly located.

[0040] Based on this, this disclosure provides a method for determining the starting road of navigation. For scenarios with complex road networks or poor positioning accuracy, it determines the vehicle's driving direction through forward trajectory point data, providing highly valuable directional information to match the vehicle's navigation starting road, thereby improving the accuracy of starting road assignment. The solution of this disclosure will be described below.

[0041] First, combine Figure 2 To explain, Figure 2 This is a flowchart illustrating the navigation starting point road determination method provided in this embodiment of the disclosure, as shown below. Figure 2 As shown, the method may include:

[0042] S21. Based on the road data of multiple roads corresponding to the vehicle's current location, determine multiple candidate roads from among the multiple roads. The road data includes road direction.

[0043] The execution entity of this disclosure embodiment can be, for example, a terminal device, a server, or other device with certain data processing capabilities. Taking a terminal device as an example, a navigation software program can be installed on the terminal device to provide navigation services.

[0044] Users can initiate navigation through navigation software, and the location where navigation is initiated is the vehicle's current location. In some embodiments, the terminal device can be a user's handheld terminal device, in which case the location of the handheld terminal device can be determined as the vehicle's current location; in some embodiments, the terminal device can be a vehicle-mounted terminal device, in which case the location of the vehicle-mounted terminal device can be determined as the vehicle's current location.

[0045] After determining the vehicle's current location, road data for multiple roads can be obtained based on that location. These roads can be located near the vehicle's current position, such as roads within a 200-meter radius, roads within a 300-meter radius, and so on. The road data includes road-related information such as road direction, location, and width.

[0046] After acquiring road data from multiple roads, preliminary filtering can be performed to identify multiple candidate roads. For example, the distance from the current location to each road can be calculated, and then multiple candidate roads can be selected based on this distance. The vehicle's navigation starting point road is one of these candidate roads.

[0047] S22, Obtain the vehicle's forward trajectory point data, which is the trajectory point data before the vehicle reaches the current position.

[0048] A forward trajectory point is a point on the path a vehicle takes from its current location to its current position. For example, after navigation software is launched but before navigation is initiated, the terminal device can acquire the vehicle's location and use it as a forward trajectory point. The terminal device can acquire the vehicle's location at preset time intervals, thus obtaining multiple forward trajectory points with different time information. For each forward trajectory point, corresponding forward trajectory point data can be obtained, which may include the trajectory point's position, speed, direction, etc.

[0049] S23, determine the vehicle's direction of travel based on the forward trajectory point data.

[0050] After acquiring the forward trajectory point data, the vehicle's driving direction can be determined based on this data. For example, if the forward trajectory point data includes the direction of the trajectory points, the vehicle's driving direction can be determined based on the directions of multiple forward trajectory points; similarly, if the forward trajectory point data includes the position of the trajectory points, the direction of movement of the trajectory points can be obtained based on the positions of multiple forward trajectory points, thereby determining the vehicle's driving direction, and so on.

[0051] S24, Based on the driving direction and the road directions of multiple candidate roads, determine the vehicle's navigation starting road from among multiple candidate roads.

[0052] After determining the vehicle's direction of travel, the navigation starting point can be determined based on the vehicle's direction of travel and the directions of the candidate roads. The direction of travel can be the sole reference factor in determining the navigation starting point; for example, the candidate road with the smallest difference between its direction of travel and the direction of travel can be used as the navigation starting point.

[0053] The direction of travel can also be used as one of the reference factors in determining the starting road for navigation, and can be used to further filter multiple candidate roads. For example, multiple candidate roads can be filtered based on the vehicle's direction of travel and the direction of travel of the candidate roads, and the candidate roads whose direction of travel is less different from the direction of travel can be used as the starting road for navigation.

[0054] If there are multiple candidate roads with a small difference between their direction and the driving direction, further filtering can be done by combining data from other candidate roads to determine the navigation starting point. For example, when there are multiple candidate roads with a small difference between their direction and the driving direction, the candidate road closest to the vehicle's current location can be selected as the navigation starting point based on its location.

[0055] The navigation starting point road determination method provided in this disclosure first determines multiple candidate roads based on road data of multiple roads corresponding to the vehicle's current location, thus achieving preliminary screening of the navigation starting point road. Then, it acquires the vehicle's forward trajectory point data (trajectory point data before the vehicle reached its current location) and determines the vehicle's driving direction based on this data. Finally, based on the driving direction and the road directions of the multiple candidate roads, it determines the vehicle's navigation starting point road from among the candidate roads. For scenarios with complex or poorly accurate road networks, determining the vehicle's driving direction using forward trajectory point data provides more valuable directional information than road distance, allowing for the matching of the vehicle's navigation starting point road based on the driving direction during navigation, thereby improving the accuracy of determining the navigation starting point road.

[0056] Based on the above introduction, the following will provide a more detailed description of the navigation starting point road determination method provided in this disclosure.

[0057] Figure 3 This is a flowchart illustrating the method for determining candidate roads provided in an embodiment of this disclosure, as shown below. Figure 3 As shown, it includes:

[0058] S31. Based on road data, obtain the confidence scores of multiple roads. The confidence scores are used to indicate the probability that the corresponding road is the starting point for navigation.

[0059] When initiating navigation, the vehicle's location is the current location. Based on the vehicle's current location, road data for multiple roads can be obtained. For example, based on the vehicle's current location, local road data within a 200-meter radius can be requested, including 20 roads. Then, the distances from the current location to each of these 20 roads are obtained, and the nearest M roads are identified as multiple roads. M can be, for example, 8, 10, 12, etc.

[0060] After obtaining road data for multiple roads, a road confidence score can be calculated based on this data. The confidence score indicates the probability that the corresponding road is the navigation starting point. A higher confidence score indicates a greater probability that the corresponding road is the navigation starting point, while a lower confidence score indicates a lower probability.

[0061] The confidence scores for multiple roads can be obtained using a Gradient Boosting Decision Tree (GBDT) model. GBDT is a classification model; taking a binary classification model as an example, the training samples for GBDT can include sample road data for two sample roads and their corresponding annotations. Sample road data may include one or more of the following: distance from the current location to the sample road, speed limit of the sample road, direction of the sample road, width of the sample road, and road class of the sample road. The annotations represent the probability that a vehicle is on one of the two sample roads. Then, the road data from the two sample roads is input into the GBDT model to obtain the probability output by the GBDT model of a vehicle being on one of the two sample roads. The parameters of the GBDT model can be adjusted based on the sample probabilities and the probabilities output by the GBDT model. After multiple rounds of training, a fully trained GBDT model can be obtained.

[0062] After the GBDT model is trained, the confidence scores of multiple roads can be obtained based on the GBDT model. Specifically, multiple roads can be paired to obtain multiple road pairs, each containing two roads. Taking 10 roads as an example, pairwise pairwise combinations of the 10 roads can yield 45 road pairs.

[0063] For any road pair, the road data of the two roads in the pair can be input into the GBDT model to obtain the probability that a vehicle is currently on one of the two roads. Then, the probability of a vehicle being on one of the two roads is voted on based on the probability of the vehicle being on the other road. For example, for a road pair of roads A and B, the probability distribution of a vehicle being on road A and road B, obtained by the GBDT model, is 0.6 and 0.1, respectively. In this case, the road with the higher probability value can be voted on, meaning road A receives one vote.

[0064] For any road pair, the above method can be used to vote on one of the roads. Then, the votes for all road pairs are summed to obtain the total number of votes for each road. The total number of votes can be used as the confidence level of the road.

[0065] S32, based on the confidence level, identifies multiple candidate roads from among multiple roads.

[0066] Since confidence level indicates the probability that the corresponding road is the navigation starting point, and considering the positioning error of the vehicle's current location, roads with higher confidence levels can be identified as candidate roads. There can be multiple candidate roads. For example, out of 10 roads, the three roads with the highest confidence levels can be identified as candidate roads.

[0067] After identifying multiple candidate roads and their confidence levels, the vehicle's forward trajectory data can be obtained. Before obtaining this data, the road scenario in which the vehicle is located needs to be determined based on the road data of the candidate roads; this scenario can be either an intersection or a non-intersection scenario.

[0068] In this embodiment of the disclosure, the road data includes at least road location and road direction. Based on the road direction of the candidate roads, the road angles between multiple candidate roads can be obtained; based on the road location of the candidate roads, the distance from the vehicle's current location to the candidate roads can be obtained. Based on the road angles between multiple candidate roads and the distance from the current location to the candidate roads, the road scene in which the vehicle is located can be determined.

[0069] The following is combined Figure 4 The determination of the road scene is introduced. Figure 4 This is a schematic diagram of a road determination scenario provided in an embodiment of the present disclosure, such as... Figure 4 As shown, the vehicle's current position is at point O. Figure 4 The example shows three candidate roads: road 41, road 42, and road 43.

[0070] Based on the road directions of the three candidate roads, the angle between the three candidate roads can be obtained. Figure 4 In the diagram, the angle between roads 41 and 42 is α, the angle between roads 41 and 43 is β, and the angle between roads 42 and 43 is γ.

[0071] The angles between multiple candidate roads can be used to determine whether a relative perpendicular relationship exists between them. Specifically, it can be determined whether the angles between multiple candidate roads are within a preset angle range, which can be pre-set as needed. For example, considering factors such as errors in road data accuracy, the preset angle range can be set to 75 to 105 degrees, 80 to 100 degrees, 70 to 120 degrees, and so on.

[0072] When at least two roads have an angle within a preset range, it can be assumed that there is a relative perpendicular relationship between the multiple candidate roads. Figure 4 Taking the three candidate roads as an example, the preset angle range is greater than or equal to 75 degrees and less than or equal to 105 degrees. As long as at least one of the roads α, β, and γ has an included angle within the preset angle range, it is considered that roads 41, 42, and 43 have a relative perpendicular relationship.

[0073] After determining the relative perpendicular relationships between multiple candidate roads, it is also necessary to obtain the distance between the vehicle's current position and the candidate roads based on their road locations. In electronic navigation maps, candidate roads are usually represented by line segments, so the distance between the vehicle's current position and the candidate road can be the distance between the current location and the line segment corresponding to the subsequent road.

[0074] For example in Figure 4 In the diagram, the distance from the current location O to road 41 is d1, the distance from the current location O to road 42 is d2, and the distance from the current location O to road 43 is d3. After obtaining the distances between the vehicle's current location and the candidate roads, these distances are compared with a preset distance d. The preset distance is a pre-set distance that can be set by considering both the positioning error of the current location and the road accuracy. When the distances from the current location to all candidate roads are less than or equal to the preset distance, multiple candidate roads are determined to meet this distance condition. For example, Figure 4 In the given information, d1 is less than or equal to d, d2 is less than or equal to d, and d3 is less than or equal to d.

[0075] When multiple candidate roads are relatively perpendicular to each other, and the distance from the vehicle's current position to all candidate roads is less than or equal to a preset distance, the road scene where the vehicle is located is determined to be an intersection scene. When multiple candidate roads are not relatively perpendicular to each other, or when the distance from the vehicle's current position to a candidate road is greater than a preset distance, the road scene where the vehicle is located is determined to be a non-intersection scene.

[0076] Understandably, the number of candidate roads, the preset angle range, and the preset distance can be preset to different values ​​in different scenarios. Figure 4 The values ​​set are merely examples and do not constitute a limitation on specific values. Based on the number of candidate roads, the preset angle range, and the preset distance, combined with the road data of the candidate roads, the road scene in which the vehicle is located can be determined.

[0077] Determining the road scenario where the vehicle is located allows for different strategies to be adopted for determining the navigation starting point. For non-intersection scenarios, the road conditions are relatively simple, and the multiple candidate roads may include parallel ones, meaning the road directions of the multiple candidate roads are not significantly different. In this case, the directional information has less reference value for determining the vehicle's navigation starting point. Therefore, the candidate road with the highest confidence level can be directly determined as the vehicle's navigation starting point.

[0078] For intersection scenarios, the road conditions involved are quite complex, and the directions of multiple candidate roads differ significantly. Therefore, it is necessary to combine directional information to jointly determine the starting road for vehicle navigation.

[0079] By determining the road environment in which the vehicle is located, a more suitable strategy for determining the navigation starting point can be selected based on the different road environments in which the vehicle is located, thereby improving the accuracy of navigation starting point location.

[0080] For intersection scenarios, after identifying multiple candidate roads, forward trajectory point data of the vehicle can be acquired. This forward trajectory point data refers to the trajectory points before the vehicle reaches its current location. For example, when a user opens navigation software on their terminal device, the device begins acquiring forward trajectory point data. The vehicle's current location is the location at the time navigation is initiated through the navigation software; trajectory point data acquired after the navigation software is opened and before navigation is initiated are all considered forward trajectory point data.

[0081] In this embodiment of the disclosure, the forward trajectory point data includes related data of multiple forward trajectory points. This related data may include, for example, the trajectory point direction, velocity, and position of the forward trajectory point. The vehicle's driving direction can be determined using the forward trajectory point data.

[0082] After acquiring the forward trajectory point data, it is necessary to assess the quality of the data and determine whether it meets the requirements. If the quality of the forward trajectory point data meets the requirements, the vehicle's driving direction is determined based on the data; if the quality of the forward trajectory point data does not meet the requirements, the data is discarded, and the vehicle's navigation starting point is determined directly based on the confidence levels of multiple candidate roads.

[0083] The following is combined Figure 5 This paper introduces the method for determining the quality of forward trajectory point data. Figure 5 For a schematic diagram of the forward trajectory points provided in the embodiments of this disclosure, please refer to [link / reference]. Figure 5 The example shows multiple forward trajectory points, namely trajectory points 1 to 10 arranged in chronological order, where trajectory point 1 is the earliest forward trajectory point and trajectory point 10 is the latest forward trajectory point.

[0084] In this embodiment of the disclosure, when determining the quality of forward trajectory point data, it is first necessary to divide multiple forward trajectory points into multiple trajectory point pairs. Each trajectory point pair includes two adjacent first trajectory points and second trajectory points. The trajectory point pairs are determined based on the time information of the trajectory points, for example, in... Figure 5In the diagram, trajectory points 1 to 10 are 10 trajectory points arranged in chronological order. Trajectory points 1 and 2 can be considered as a pair, trajectory points 2 and 3 as a pair, and so on, with trajectory points 9 and 10 forming another pair. Within a pair, the trajectory point with earlier time information is designated as the first trajectory point, and the trajectory point with later time information is designated as the second trajectory point.

[0085] After determining the trajectory point pairs, trajectory point information for multiple pairs can be obtained based on the forward trajectory point data. This information includes the trajectory point position, direction, and velocity of the first trajectory point. Since the second trajectory point is the next trajectory point after the first, the time difference between them can be determined based on the time information of both the first and second trajectory points. Then, based on the trajectory point position, direction, and velocity of the first trajectory point, as well as the time difference between the first and second trajectory points, the predicted trajectory point position can be determined. The predicted trajectory point position is the position of the trajectory point after a certain time difference, predicted based on the first trajectory point's position, direction, and velocity. After obtaining the predicted trajectory point position, the data quality of the corresponding trajectory point pair can be determined based on the predicted and second trajectory point positions.

[0086] Since the time difference between the first and second trajectory points in a trajectory point pair is usually small, the changes in velocity and direction between them are also relatively small. Therefore, the predicted trajectory point position, obtained from the position, direction, and velocity of the first trajectory point, should be close to the position of the second trajectory point. Thus, after obtaining the predicted trajectory point position, the distance between the predicted and second trajectory point positions is calculated. If the distance between the predicted and second trajectory point positions is less than or equal to a preset threshold, the data quality of the trajectory point pair is considered to meet the requirements.

[0087] by Figure 5 Taking trajectory points 9 and 10 as examples, trajectory point 9 is the first trajectory point, and trajectory point 10 is the second trajectory point. The direction of trajectory point 9 is θ, and its velocity is v. last The coordinates are (x last ,y last ), where dt is the time difference between trajectory point 9 and trajectory point 10.

[0088] Based on the direction θ and velocity v of trajectory point 9 last We can obtain the velocities of trajectory point 9 in the x and y directions, where the velocity v of trajectory point 9 in the x direction is... x =v last×cosθ, the velocity v of trajectory point 9 in the y-direction. y =v last ×sinθ.

[0089] Based on the direction, velocity, and coordinates of trajectory point 9, the coordinates (x, y) of the predicted trajectory point can be obtained, such as... Figure 5 Example of a dashed box in the image, where (x,y)=(x last ,y last )+(v x v y )×dt, that is, x=x last +v x ×dt,y=y last +v y ×dt.

[0090] Let the coordinates of trajectory point 10 be (x cur ,y cur When the following equation (1) is satisfied, the data quality of the trajectory point pair 9 and trajectory point 10 is considered to meet the requirements. In the following equation (1), the equal sign indicates that they are approximately equal.

[0091] (x cur ,y cur )=(x last ,y last )+(v x v y )×dt (1)

[0092] The above method can be used to determine the data quality of any trajectory point pair. After obtaining the data quality of multiple trajectory point pairs, the quality of the forward trajectory point data can be determined based on the data quality of the multiple trajectory point pairs. For example, the proportion of trajectory point pairs whose data quality meets the requirements can be obtained. When the proportion that meets the requirements is greater than or equal to a preset proportion, the quality of the forward trajectory point data is determined to meet the requirements. Alternatively, it can be determined whether the data quality of multiple trajectory point pairs all meets the requirements. If the data quality of multiple trajectory point pairs all meets the requirements, the quality of the forward trajectory point data is determined to meet the requirements.

[0093] After confirming that the quality of the forward trajectory point data meets the requirements, the vehicle's driving direction can be determined based on this data. By assessing the quality of the forward trajectory point data, the driving direction can be determined based on the data, provided the data quality meets the requirements. This improves the accuracy of driving direction determination and, consequently, the accuracy of navigation starting point road positioning. The following section will combine... Figure 6 This process will be described.

[0094] Figure 6 This is a schematic diagram of the process for determining the driving direction provided in an embodiment of this disclosure, such as... Figure 6 As shown, it includes:

[0095] S61, obtain the vehicle's current location and direction.

[0096] The vehicle's current location direction is the direction determined based on the vehicle's current position. When navigation is initiated, the vehicle's current location direction can be obtained.

[0097] S62, based on the position of the trajectory point, obtain the trajectory connection direction between adjacent forward trajectory points.

[0098] The trajectory connection direction between adjacent forward trajectory points refers to the direction from the previous forward trajectory point to the next forward trajectory point, relative to two adjacent forward trajectory points. For example, in Figure 5 In the diagram, the trajectory connection direction between trajectory points 2 and 3 is the direction from trajectory point 2 to trajectory point 3, and the trajectory connection direction between trajectory points 8 and 9 is the direction from trajectory point 8 to trajectory point 9. For any two adjacent forward trajectory points, the trajectory connection direction between adjacent forward trajectory points can be obtained based on their trajectory point positions and time information.

[0099] S63, determine the driving direction based on the positioning direction, the trajectory point direction, and the direction of connection between trajectory points.

[0100] In this embodiment of the disclosure, a total of three types of directions are involved: positioning direction, trajectory point direction, and trajectory connection direction. The positioning direction refers to the direction of the vehicle obtained by locating the vehicle at its current position. The trajectory point direction refers to the direction of multiple forward trajectory points. The trajectory connection direction refers to the direction determined based on the position of the trajectory points between adjacent forward trajectory points.

[0101] After obtaining the positioning direction, trajectory point direction, and trajectory connection direction, the target forward trajectory point can be determined from multiple forward trajectory points based on these three directions. The target forward trajectory point refers to a forward trajectory point where the angle difference between the positioning direction, the corresponding trajectory point direction, and the corresponding trajectory connection direction meets the requirements. The following will combine... Figure 7 This process will be described.

[0102] Figure 7 This is a schematic diagram illustrating the determination of the forward trajectory points of a target provided in an embodiment of this disclosure, such as... Figure 7 As shown, there are 10 forward trajectory points, which are arranged in chronological order from front to back as trajectory point 1, trajectory point 2, ..., trajectory point 10.

[0103] Let the current positioning direction of the vehicle be Dir. curThe set of trajectory points directions formed by multiple trajectory points is G, where G = [G1, G2, ..., G...]. m ], where m is the number of trajectory points, G i Let be the trajectory direction of the i-th trajectory point; let D be the set of trajectory connection directions formed by multiple adjacent forward trajectory points, where D = [D1, D2, ..., D]. m ], D i Let m be the direction connecting the ith trajectory point and the (i+1)th trajectory point, where the (m+1)th trajectory point represents the vehicle's current position. For example, in... Figure 7 In the diagram, the directed dashed line represents the direction of the trajectory connection formed by adjacent forward trajectory points, the directed solid line on the forward trajectory point represents the trajectory direction of the forward trajectory point, and the directed solid line on the current position O represents the positioning direction.

[0104] For any i-th trajectory point, the positioning direction Dir can be obtained. cur The trajectory direction G of the i-th trajectory point i The first angle difference between them, the positioning direction Dir cur The trajectory connection direction D corresponding to the i-th trajectory point i The second angle difference between them, and the trajectory connection direction D corresponding to the i-th trajectory point. i and trajectory point direction G i The difference in the third angle between them.

[0105] Among them, the positioning direction Dir cur With respect to the direction G of the trajectory point i The first angle difference between them can be expressed as |Dir cur -G i |, Positioning Direction Dir cur Direction D connected to the trajectory i The second angle difference between them can be expressed as |Dir cur -D i |, Trajectory connection direction D i and trajectory point direction G i The difference in the third angle between them can be expressed as |D i -G i |,|a| represents the absolute value of a.

[0106] After obtaining the first angle difference, second angle difference, and third angle difference corresponding to the i-th trajectory point, the first angle difference, second angle difference, and third angle difference can be compared with the preset angle. When the first angle difference, second angle difference, and third angle difference are all less than or equal to the preset angle, the i-th trajectory point can be determined as a target forward trajectory point.

[0107] Let N be the number of forward trajectory points of the target, and N is initially 0. For m forward trajectory points, we can start from i=1 and traverse all trajectory points to determine whether the i-th forward trajectory point is the target forward trajectory point.

[0108] If so, update N = N + 1, and update i = i + 1 when i is less than m. Repeat the above steps to determine the forward trajectory points of the target until i equals m, then stop the traversal steps.

[0109] If not, then change the direction of the trajectory point G. i Remove from the set of trajectory point directions G, and connect the trajectory in direction D. i Remove it from the set D of trajectory connection directions.

[0110] When i is less than m, update i = i + 1, and repeat the above steps to determine the forward trajectory points of the target. When i equals m, stop the above traversal steps, and finally obtain the number N of the forward trajectory points of the target and the set G of the updated trajectory point directions. new The set of directions D connecting the updated trajectory new , where the updated set of trajectory point directions G new It includes the trajectory point directions of N target forward trajectory points, and the updated trajectory connection direction set D. new It includes the trajectory connection directions of N target forward trajectory points.

[0111] By filtering forward trajectory points and identifying target forward trajectory points in the same direction of travel, we can eliminate forward trajectory points with poor directional data, thus retaining only the data of target forward trajectory points with more accurate positioning, which helps improve the accuracy of determining the direction of travel.

[0112] After determining the target forward trajectory points, the vehicle's direction of travel can be determined based on the number of target forward trajectory points. Specifically, the number of target forward trajectory points can be compared with a preset value, where the preset value k is a value greater than 0 and less than m (the number of forward trajectory points).

[0113] When the number N of target forward trajectory points is greater than or equal to a preset value, the driving direction can be determined based on the trajectory point direction, trajectory connection direction, and positioning direction corresponding to the target forward trajectory points. For example, the driving direction can be obtained by averaging the trajectory point directions, trajectory connection directions, and positioning directions of multiple target forward trajectory points. When the number N of target forward trajectory points is less than the preset value, the driving direction can be determined as the preset direction.

[0114] Equation (2) below illustrates one implementation scheme for determining the direction of travel:

[0115]

[0116] Among them, Dir valid Where N is the direction of travel, k is the number of forward trajectory points of the target, and G is the preset value. new D is the updated set of trajectory point directions. new For the updated set of trajectory connection directions, Dir cur To determine the direction, average(G) new D new Dir cur ) represents G new Elements in D new Elements in, and Dir cur Find the mean.

[0117] After determining the vehicle's direction of travel, a weighted value can be obtained for multiple candidate roads based on the vehicle's direction of travel and the road directions of multiple candidate roads. For example, the angle difference between the vehicle's direction of travel and the road directions of the candidate roads can be obtained, and the weighted value of the candidate roads can be obtained based on the angle difference.

[0118] The weighting value can be determined, for example, based on the angle difference between the angle difference and a preset angle. For instance, the weighting value can be negatively correlated with the angle difference; the larger the angle difference, the smaller the weighting value, and vice versa. Furthermore, the weighting value can be set to different values ​​based on the magnitude of the angle difference, and so on.

[0119] After determining the weighting values ​​of the candidate roads, the confidence scores of the candidate roads can be weighted according to the weighting values ​​to obtain the weighted confidence scores. The following equation (3) illustrates a possible method for calculating the weighted confidence scores of candidate roads:

[0120]

[0121] Among them, V ix V is the weighted confidence level of candidate road i. i L is the confidence level of candidate road i before weighted processing. i Dir represents the road direction of candidate road i. valid The direction of travel is β, and the preset angle is β. When the angle difference is less than the preset angle β, the weighting value is 1.3. When the angle difference is greater than or equal to the preset angle, the weighting value is 1.

[0122] It is understandable that the weighted value in the above formula is merely an example and does not constitute a limitation on the value of the weighted value. After weighting the confidence of candidate roads according to the weighted value to obtain the weighted confidence, the navigation starting road can be determined from multiple candidate roads based on the weighted confidence. For example, multiple candidate roads can be reordered according to the weighted confidence, and then the candidate road with the highest weighted confidence can be determined as the navigation starting road. By combining the driving direction and the road direction of the candidate roads to perform weighted update processing on the confidence of candidate roads, and then determining the navigation starting road based on the weighted confidence, the accuracy of starting road binding is improved.

[0123] In summary, the navigation starting point road determination method provided in this embodiment first performs preliminary screening of multiple roads based on road data corresponding to the current location, identifying multiple candidate roads and their corresponding confidence levels. Then, by determining the road scenario where the vehicle is located, it acquires forward trajectory point data for intersection scenarios, thereby determining the vehicle's driving direction based on the forward trajectory point data. The confidence levels of the candidate roads are then updated with weights based on the vehicle's driving direction and the road directions of the candidate roads. Finally, the navigation starting point road is determined from the multiple candidate roads. This solution, for intersection scenarios, does not use the distance between the current location and the road as the most weighted matching feature, but instead provides more accurate directional information as a reference for subsequently determining the navigation starting point road, thereby improving the accuracy of starting point positioning.

[0124] Figure 8 This is a schematic diagram of the navigation starting point road determination device provided in the embodiments of this disclosure, as shown below. Figure 8 As shown, the navigation starting point road determination device 80 may include:

[0125] The first determining unit 81 is used to determine multiple candidate roads from among the multiple roads based on road data corresponding to the current location of the vehicle, wherein the road data includes road direction;

[0126] Acquisition unit 82 is used to acquire forward trajectory point data of the vehicle, wherein the forward trajectory point data is the trajectory point data of the vehicle before reaching the current position;

[0127] Processing unit 83 is used to determine the driving direction of the vehicle based on the forward trajectory point data;

[0128] The second determining unit 84 is used to determine the navigation starting road of the vehicle from among the multiple candidate roads based on the driving direction and the road direction of the multiple candidate roads.

[0129] In one possible implementation, the acquisition unit 82 includes:

[0130] The first determining module is used to determine the road scene where the vehicle is located based on the road data of the multiple candidate roads, wherein the road scene is an intersection scene or a non-intersection scene.

[0131] The first acquisition module is used to acquire the forward trajectory point data when the road scene is the intersection scene.

[0132] In one possible implementation, the road data further includes road location; the first determining module includes:

[0133] The first acquisition submodule is used to acquire the road angle between the multiple candidate roads based on the road directions of the multiple candidate roads;

[0134] The second acquisition submodule is used to obtain the distance between the current position and the multiple candidate roads based on the road locations of the multiple candidate roads;

[0135] The first determining submodule is used to determine the road scene based on the road angle and the distance between the current position and the candidate road.

[0136] In one possible implementation, the forward trajectory point data includes the trajectory point direction, trajectory point velocity, and trajectory point position of multiple forward trajectory points; the processing unit 83 includes:

[0137] The second determining module is used to determine the data quality of the forward trajectory point based on the direction of the trajectory point, the velocity of the trajectory point, and the position of the trajectory point;

[0138] The third determining module is used to determine the driving direction based on the direction and position of the trajectory point when the quality of the forward trajectory point data meets the requirements.

[0139] In one possible implementation, the second determining module includes:

[0140] The second determining submodule is used to determine multiple pairs of trajectory points in the forward trajectory points, wherein the pairs of trajectory points include two adjacent first trajectory points and second trajectory points;

[0141] The third acquisition submodule is used to acquire trajectory point information of the plurality of trajectory point pairs, wherein the trajectory point information includes the trajectory point position, trajectory point direction and trajectory point velocity of the first trajectory point;

[0142] The third determining submodule is used to determine the data quality of the multiple trajectory point pairs based on the trajectory point information of the multiple trajectory point pairs;

[0143] The fourth determination submodule is used to determine the quality of the forward trajectory point data based on the data quality of the multiple trajectory point pairs.

[0144] In one possible implementation, for any one of the plurality of trajectory point pairs; the third determining submodule is specifically used for:

[0145] Based on the time information of the first trajectory point and the time information of the second trajectory point, determine the time difference between the first trajectory point and the second trajectory point;

[0146] The predicted trajectory point position is determined based on the trajectory point position, trajectory point direction, trajectory point velocity, and the time difference of the first trajectory point.

[0147] The data quality of the trajectory point pair is determined based on the predicted trajectory point position and the position of the second trajectory point.

[0148] In one possible implementation, the third determining module includes:

[0149] The fourth acquisition submodule is used to acquire the current positioning direction of the vehicle;

[0150] The fifth acquisition submodule is used to obtain the trajectory connection direction between adjacent forward trajectory points based on the position of the trajectory point;

[0151] The fifth determining submodule is used to determine the driving direction based on the positioning direction, the trajectory point direction, and the trajectory connection direction.

[0152] In one possible implementation, the fifth determining submodule is specifically used for:

[0153] Based on the positioning direction, the trajectory point direction, and the trajectory connection direction, determine the target forward trajectory point from among the plurality of forward trajectory points;

[0154] The driving direction is determined based on the number of forward trajectory points of the target.

[0155] In one possible implementation, the fifth determining submodule is specifically used for:

[0156] For any forward trajectory point, obtain the first angle difference between the positioning direction and the trajectory point direction, the second angle difference between the positioning direction and the trajectory connection direction, and the third angle difference between the trajectory connection direction and the trajectory point direction;

[0157] The forward trajectory points whose first angle difference, second angle difference, and third angle difference are all less than or equal to a preset angle are determined as the target forward trajectory points.

[0158] In one possible implementation, the fifth determining submodule is specifically used for:

[0159] When the number of the target forward trajectory points is greater than or equal to a preset value, the driving direction is determined according to the trajectory point direction, trajectory connection direction and positioning direction corresponding to the target forward trajectory points;

[0160] When the number of forward trajectory points of the target is less than the preset value, the driving direction is determined to be the preset direction.

[0161] In one possible implementation, the first determining unit 81 includes:

[0162] The second acquisition module is used to acquire the confidence level of the multiple roads based on the road data, wherein the confidence level is used to indicate the probability that the corresponding road is the navigation starting point road;

[0163] The fourth determining module is used to determine the multiple candidate roads among the multiple roads based on the confidence level.

[0164] In one possible implementation, the second determining unit 84 includes:

[0165] The third acquisition module is used to acquire the weighted value of the multiple candidate roads based on the driving direction and the road direction of the multiple candidate roads;

[0166] The first processing module is used to perform weighted processing on the confidence scores of the corresponding candidate roads according to the weighted values ​​to obtain the weighted confidence scores;

[0167] The second processing module is used to determine the navigation starting point road from the multiple candidate roads based on the weighted confidence level.

[0168] The navigation starting point road determination device provided in this application embodiment is used to execute the above method embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0169] This disclosure provides a method, apparatus, device, and storage medium for determining the starting road of a navigation system, which can be applied to fields such as intelligent transportation and autonomous driving in data processing technology, in order to improve the accuracy of starting road determination during vehicle navigation.

[0170] It should be noted that the head model in this embodiment is not a head model specific to any particular user and does not reflect the personal information of any particular user. It should also be noted that the two-dimensional face image in this embodiment comes from a publicly available dataset.

[0171] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0172] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0173] According to embodiments of this disclosure, this disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, at least one processor of an electronic device being able to read the computer program from the readable storage medium, and the at least one processor executing the computer program causing the electronic device to perform the scheme provided in any of the above embodiments.

[0174] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0175] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0176] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0177] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 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 suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the navigation starting point road determination method. For example, in some embodiments, the navigation starting point road determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by computing unit 901, one or more steps of the navigation starting point road determination method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the navigation starting point road determination method by any other suitable means (e.g., by means of firmware).

[0178] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0179] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0180] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0181] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; 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 sound input, voice input, or tactile input).

[0182] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0183] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0184] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0185] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining a navigation starting road, comprising: determining a plurality of candidate roads from a plurality of roads corresponding to a current position of a vehicle, according to road data of the plurality of roads, the road data comprising road directions; obtaining forward trajectory point data of the vehicle, the forward trajectory point data being trajectory point data before the vehicle reaches the current position, the forward trajectory point data comprising trajectory point directions, trajectory point speeds and trajectory point positions of a plurality of forward trajectory points; when a quality of the forward trajectory point data meets a requirement, determining a driving direction of the vehicle according to the trajectory point directions and the trajectory point positions; determining a navigation starting road of the vehicle from the plurality of candidate roads according to the driving direction and the road directions of the plurality of candidate roads; wherein determining the driving direction according to the trajectory point directions and the trajectory point positions comprises: obtaining a current orientation of the vehicle; obtaining a trajectory connection direction between adjacent forward trajectory points according to the trajectory point positions; determining the driving direction according to the orientation, the trajectory point directions and the trajectory connection direction.

2. The method of claim 1, wherein, obtaining the forward trajectory point data of the vehicle comprises: determining a road scene in which the vehicle is located according to the road data of the plurality of candidate roads, the road scene being a road intersection scene or a non-road intersection scene; when the road scene is the road intersection scene, obtaining the forward trajectory point data.

3. The method of claim 2, wherein, the road data further comprises road positions; and determining the road scene in which the vehicle is located according to the road data of the plurality of candidate roads comprises: obtaining road angles between the plurality of candidate roads according to the road directions of the plurality of candidate roads; obtaining distances between the current position and the plurality of candidate roads according to the road positions of the plurality of candidate roads; determining the road scene according to the road angles and the distances between the current position and the candidate roads.

4. The method of claim 1, wherein, determining the quality of the forward trajectory point data comprises: determining the quality of the forward trajectory point data according to the trajectory point directions, the trajectory point speeds and the trajectory point positions.

5. The method of claim 4, wherein, determining the quality of the forward trajectory point data according to the trajectory point directions, the trajectory point speeds and the trajectory point positions comprises: determining a plurality of trajectory point pairs in the forward trajectory point data, the trajectory point pair comprising two adjacent first and second trajectory points; obtaining trajectory point information of the plurality of trajectory point pairs, the trajectory point information comprising the trajectory point positions, the trajectory point directions and the trajectory point speeds of the first trajectory points; determining data qualities of the plurality of trajectory point pairs according to the trajectory point information of the plurality of trajectory point pairs; determining the quality of the forward trajectory point data according to the data qualities of the plurality of trajectory point pairs.

6. The method of claim 5, wherein, for any one of the plurality of trajectory point pairs; determining the data quality of the trajectory point pair according to the trajectory point information of the trajectory point pair comprises: determining a time difference between the first and second trajectory points according to time information of the first trajectory point and time information of the second trajectory point. determine a predicted trajectory point position according to the trajectory point position, the trajectory point direction and the trajectory point speed of the first trajectory point, and the time difference; determine data quality of the pair of trajectory points according to the predicted trajectory point position and the trajectory point position of the second trajectory point.

7. The method of claim 1, wherein, determine the driving direction according to the positioning direction, the trajectory point direction and the trajectory connection direction, including: determine a target forward trajectory point in the plurality of forward trajectory points according to the positioning direction, the trajectory point direction and the trajectory connection direction; determine the driving direction according to the number of the target forward trajectory points.

8. The method of claim 7, wherein, determine a target forward trajectory point in the plurality of forward trajectory points according to the positioning direction, the trajectory point direction and the trajectory connection direction, including: for any forward trajectory point, obtain a first angle difference between the positioning direction and the trajectory point direction, a second angle difference between the positioning direction and the trajectory connection direction, and a third angle difference between the trajectory connection direction and the trajectory point direction; determine the forward trajectory point as the target forward trajectory point when the first angle difference, the second angle difference and the third angle difference are all less than or equal to a preset angle.

9. The method of claim 8, wherein, determine the driving direction according to the number of the target forward trajectory points, including: when the number of the target forward trajectory points is greater than or equal to a preset value, determine the driving direction according to the trajectory point direction, the trajectory connection direction and the positioning direction corresponding to the target forward trajectory point; when the number of the target forward trajectory points is less than the preset value, determine the driving direction as a preset direction.

10. The method of any one of claims 1-9, wherein, determine a plurality of candidate roads in a plurality of roads corresponding to a current position of a vehicle according to road data of the plurality of roads, including: obtain a confidence degree of the plurality of roads according to the road data, the confidence degree being used to indicate a probability that a corresponding road is the navigation starting point road; determine the plurality of candidate roads in the plurality of roads according to the confidence degree.

11. The method of claim 10, wherein, determine a navigation starting point road of the vehicle in the plurality of candidate roads according to the driving direction and road directions of the plurality of candidate roads, including: obtain a weighted value of the plurality of candidate roads according to the driving direction and the road directions of the plurality of candidate roads; perform weighted processing on the confidence degree of a corresponding candidate road according to the weighted value to obtain a weighted confidence degree; determine the navigation starting point road in the plurality of candidate roads according to the weighted confidence degree.

12. A navigation starting point road determination apparatus, comprising: a first determination unit configured to determine a plurality of candidate roads in a plurality of roads corresponding to a current position of a vehicle according to road data of the plurality of roads, the road data including road directions; an obtaining unit configured to obtain forward trajectory point data of the vehicle, the forward trajectory point data being trajectory point data before the vehicle reaches the current position, the forward trajectory point data including trajectory point directions, trajectory point speeds and trajectory point positions of a plurality of forward trajectory points; The processing unit comprises a third determination module; the third determination module is configured to determine a driving direction of the vehicle according to the trajectory point direction and the trajectory point position when the quality of the forward trajectory point data meets a requirement; The second determination unit is configured to determine a navigation starting point road of the vehicle from the plurality of candidate roads according to the driving direction and road directions of the plurality of candidate roads; The third determination module comprises: A fourth acquisition sub-module configured to acquire a current positioning direction of the vehicle; A fifth acquisition sub-module configured to acquire a trajectory connection direction between adjacent forward trajectory points according to the trajectory point position; A fifth determination sub-module configured to determine the driving direction according to the positioning direction, the trajectory point direction and the trajectory connection direction.

13. The apparatus of claim 12, wherein, The acquisition unit comprises: A first determination module configured to determine a road scene in which the vehicle is located according to road data of the plurality of candidate roads, the road scene being a road intersection scene or a non-road intersection scene; A first acquisition module configured to acquire the forward trajectory point data when the road scene is the road intersection scene.

14. The apparatus of claim 13, wherein, The road data further comprises road positions; the first determination module comprises: A first acquisition sub-module configured to acquire road included angles between the plurality of candidate roads according to road directions of the plurality of candidate roads; A second acquisition sub-module configured to acquire distances between the current position and the plurality of candidate roads according to road positions of the plurality of candidate roads; A first determination sub-module configured to determine the road scene according to the road included angles and the distances between the current position and the candidate roads.

15. The apparatus of claim 12, wherein, The processing unit further comprises: A second determination module configured to determine the quality of the forward trajectory point data according to the trajectory point direction, the trajectory point speed and the trajectory point position.

16. The apparatus of claim 15, wherein, The second determination module comprises: A second determination sub-module configured to determine a plurality of trajectory point pairs from the forward trajectory points, each trajectory point pair comprising two adjacent first and second trajectory points; A third acquisition sub-module configured to acquire trajectory point information of the plurality of trajectory point pairs, the trajectory point information comprising the trajectory point position, the trajectory point direction and the trajectory point speed of the first trajectory point; A third determination sub-module configured to determine data quality of the plurality of trajectory point pairs according to the trajectory point information of the plurality of trajectory point pairs; A fourth determination sub-module configured to determine the quality of the forward trajectory point data according to the data quality of the plurality of trajectory point pairs.

17. The apparatus of claim 16, wherein, For any one of the plurality of trajectory point pairs; the third determination sub-module is specifically configured to: determine a time difference between the first and second trajectory points according to time information of the first trajectory point and time information of the second trajectory point; determine a predicted trajectory point position according to the trajectory point position, the trajectory point direction and the trajectory point speed of the first trajectory point and the time difference; determine the data quality of the trajectory point pair according to the predicted trajectory point position and the position of the second trajectory point.

18. The apparatus of claim 12, wherein, The fifth determination sub-module is specifically configured to: determine a target forward trajectory point from the plurality of forward trajectory points according to the positioning direction, the trajectory point direction and the trajectory connection direction; determine the driving direction according to a quantity of the target forward trajectory points.

19. The apparatus of claim 18, wherein, The fifth determining sub-module is specifically used for: obtaining a first angle difference between the positioning direction and the trajectory point direction, a second angle difference between the positioning direction and the trajectory connection direction, and a third angle difference between the trajectory connection direction and the trajectory point direction for any forward trajectory point; determining a forward trajectory point with the first angle difference, the second angle difference and the third angle difference all less than or equal to a preset angle as the target forward trajectory point.

20. The apparatus of claim 19, wherein, The fifth determining sub-module is specifically used for: determining the driving direction according to the trajectory point direction, the trajectory connection direction and the positioning direction of the target forward trajectory point when the quantity of the target forward trajectory points is greater than or equal to a preset value; determining the driving direction as a preset direction when the quantity of the target forward trajectory points is less than the preset value.

21. The apparatus of any one of claims 12-20, wherein, The first determining unit comprises: a second obtaining module configured to obtain a confidence degree of the plurality of roads according to the road data, the confidence degree being used to indicate a probability that a corresponding road is the navigation starting point road; a fourth determining module configured to determine the plurality of candidate roads from the plurality of roads according to the confidence degree.

22. The apparatus of claim 21, wherein, The second determining unit comprises: a third obtaining module configured to obtain a weighted value of the plurality of candidate roads according to the driving direction and a road direction of the plurality of candidate roads; a first processing module configured to perform weighted processing on the confidence degree of a corresponding candidate road according to the weighted value to obtain a weighted confidence degree; a second processing module configured to determine the navigation starting point road from the plurality of candidate roads according to the weighted confidence degree. 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 a computer program which, when executed by a processor, implements the steps of the method of any one of claims 1-11.

Images