Method and device for determining starting road

Abstract

This disclosure provides a method and apparatus for determining a starting road. The method includes: acquiring historical navigation request information of a navigation object, wherein the navigation request information includes at least a historical navigation starting point; acquiring the historical driving trajectory corresponding to the historical navigation request information; inserting the historical navigation starting point into the historical driving trajectory to obtain an interpolated driving trajectory; matching the interpolated driving trajectory with map road network data to obtain a road sequence matching the interpolated driving trajectory; and determining the road containing the historical navigation starting point from the road sequence as the starting road. This method enables automatic and efficient batch acquisition of historical navigation request information and corresponding starting roads from historical navigation data.

Description

Technical Field

[0001] This disclosure relates to the field of navigation technology, and in particular to a method and apparatus for determining a starting point road. Background Technology

[0002] When navigation software receives a navigation request from a user, it typically first determines the user's starting point based on their GPS location. Then, it matches the user's current road location with the destination information in the navigation request and matches the optimal route accordingly. However, because GPS positioning results often fluctuate and cannot accurately pinpoint the user's starting point, the matched starting road may be incorrect. This can lead to errors in the planned navigation route, resulting in a poor or even unsuitable route.

[0003] The inventors discovered that big data and machine learning capabilities can be used to improve the accuracy of navigation starting point road detection. However, training the starting point road detection model requires ground truth, that is, the actual road where the starting point is located, as training data. How to obtain such data has become a technical problem that urgently needs to be solved. Summary of the Invention

[0004] In view of the above problems, this disclosure is made in order to provide a method and apparatus for determining a starting road that overcomes or at least partially solves the above problems.

[0005] In a first aspect, embodiments of this disclosure provide a method for determining a starting road, including:

[0006] Obtain historical navigation request information of the navigation object, wherein the information includes at least the historical navigation starting point;

[0007] Obtain the historical driving trajectory corresponding to the historical navigation request information;

[0008] The historical navigation starting point is inserted into the historical driving trajectory to obtain the interpolated driving trajectory;

[0009] The interpolated driving trajectory is matched with the map road network data to obtain a road sequence that matches the interpolated driving trajectory;

[0010] From the road sequence, the road where the historical navigation starting point is located is determined as the starting road.

[0011] In some optional embodiments, the method further includes using the historical navigation request information and its corresponding starting road as ground truth for training the starting point road-grabbing model.

[0012] In some optional embodiments, the information further includes: the initiation time of the historical navigation request, and the acquisition of the historical driving trajectory corresponding to the historical navigation request information specifically includes:

[0013] From the historical trajectory point records of the navigation object, obtain the sequence of trajectory points whose time covers the initiation time of the historical navigation request as the corresponding historical driving trajectory.

[0014] In some optional embodiments, determining the road where the historical navigation starting point is located from the road sequence as the starting road specifically includes:

[0015] Based on the initiation time and the entry time of each road in the road sequence, determine the matching road for the historical navigation starting point;

[0016] The road in the road sequence that matches the navigation starting point is determined as the starting road.

[0017] In some optional embodiments, the historical navigation starting point is inserted into the historical driving trajectory to obtain an interpolated driving trajectory, specifically including:

[0018] Based on the initiation time of the historical navigation request, the historical navigation starting point is inserted into the historical driving trajectory sorted by time to obtain the interpolated driving trajectory.

[0019] In some optional embodiments, the interpolated driving trajectory is matched with map road network data, specifically including:

[0020] For each trajectory point in the interpolated driving trajectory, alternative roads that can be matched with the trajectory point are determined, the trajectory point including the navigation starting point inserted into the trajectory;

[0021] The weights of the candidate roads are determined according to the set rules, and the candidate road with the highest weight is determined as the matching road for the trajectory point.

[0022] In some optional embodiments, the weights of candidate roads are determined according to predefined rules, including determining the weights of candidate roads based on at least one of the following information:

[0023] The distance from the trajectory point to the alternative road;

[0024] The connectivity between the alternative roads and the roads containing the previous trajectory points of the trajectory points in the direction of the interpolated driving trajectory;

[0025] The first transition probability from the road where the previous trajectory point is located to the alternative road is determined based on the velocity of the previous trajectory point in the direction of travel of the interpolated driving trajectory.

[0026] The second transfer probability from the road where the previous trajectory point is located to the alternative road is determined based on the azimuth angle of the previous trajectory point and the interpolated driving trajectory direction.

[0027] In some optional embodiments, after obtaining the interpolated driving trajectory, the method further includes:

[0028] Delete trajectory points whose number of trajectory points between them and the historical navigation starting point exceeds a preset threshold; or,

[0029] Delete trajectory points whose distance from the historical navigation starting point exceeds a preset distance threshold; or,

[0030] Delete trajectory points whose time interval with the historical navigation starting point exceeds a time threshold.

[0031] Secondly, embodiments of this disclosure provide an apparatus for determining a starting road, comprising:

[0032] The first acquisition module is used to acquire historical navigation request information of the navigation object, wherein the information includes at least the historical navigation starting point;

[0033] The second acquisition module is used to acquire the historical driving trajectory corresponding to the historical navigation request information acquired by the first acquisition module.

[0034] An insertion module is used to insert the historical navigation starting point obtained by the first acquisition module into the historical driving trajectory obtained by the second acquisition module to obtain an interpolated driving trajectory.

[0035] The matching module is used to match the interpolated driving trajectory obtained by the insertion module with the map road network data to obtain a road sequence that matches the interpolated driving trajectory;

[0036] The determination module is used to determine the road where the historical navigation starting point is located from the road sequence matched by the matching module as the starting road.

[0037] Thirdly, embodiments of this disclosure provide a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-described method for determining a starting road.

[0038] Fourthly, embodiments of this disclosure provide a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for determining a starting road.

[0039] The beneficial effects of the above-described technical solutions provided in this disclosure include at least the following:

[0040] The process involves: acquiring historical navigation request information and its corresponding historical driving trajectory; inserting the historical navigation starting point into the historical driving trajectory to obtain an interpolated driving trajectory; matching the interpolated driving trajectory with map road network data to obtain a matching road sequence; and determining the road containing the historical navigation starting point as the starting road from the road sequence. Instead of directly determining the starting road based on the GPS positioning of the historical navigation starting point, this method first acquires the corresponding historical driving trajectory, inserts the navigation starting point into the historical driving trajectory, and then determines the starting road based on the road sequence matching the driving trajectory. Because it takes into account the connectivity of matching roads before and after the navigation starting point, the accuracy of the determined starting road is improved. Furthermore, it avoids manual operation, automatically and efficiently acquiring historical navigation request information and starting roads in batches from historical navigation data.

[0041] Other features and advantages of this disclosure will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0042] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0043] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the embodiments of the present disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings:

[0044] Figure 1 This is a flowchart of the method for determining the starting road in Embodiment 1 of this disclosure;

[0045] Figure 2 This is a flowchart illustrating the specific implementation of determining the starting road in Embodiment 2 of this disclosure;

[0046] Figure 3 This is an example diagram of inserting historical driving trajectories into the historical navigation starting point in Embodiment 2 of this disclosure;

[0047] Figure 4 This is a schematic diagram of the device for determining the starting road in an embodiment of this disclosure. Detailed Implementation

[0048] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0049] In order to obtain the starting road corresponding to historical navigation request information from historical navigation data, this disclosure provides a method and apparatus for determining the starting road, which can automatically and efficiently obtain historical navigation request information and starting road in batches from historical navigation data.

[0050] Example 1

[0051] Embodiment 1 of this disclosure provides a method for determining the starting road, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0052] Step S11: Obtain historical navigation request information.

[0053] When navigation software is running, it records the user's driving trajectory points, forming a sequence of trajectory points; when the user initiates a navigation request, it records the user's navigation request information. Therefore, the large amount of historical navigation data stored by navigation software includes the user's historical driving trajectory and historical navigation request information.

[0054] Specifically, the aforementioned historical navigation request information includes at least the historical navigation starting point. The navigation starting point is not the starting point entered by the user when sending the navigation request, but rather the GPS location point at the time the user sent the navigation request—that is, the actual location of the user at the time of sending the navigation request (without considering GPS positioning errors). For example, if a user needs to travel from point A to point B and is familiar with the route from A to B, but requires navigation for the route from B to C, then when the user arrives at point A or starts driving from point A, the starting point entered when initiating the navigation request is B. In this case, the navigation starting point corresponding to the navigation request in this embodiment is the GPS location point of point A, not point B.

[0055] Step S12: Obtain the historical driving trajectory corresponding to the historical navigation request information.

[0056] In one embodiment, the historical trajectory can be obtained from the historical trajectory point records of the navigation object, with the time covering the initiation time of the historical navigation request as the corresponding historical driving trajectory.

[0057] Specifically, obtaining the driving trajectory based on the initiation time in the navigation request information can be achieved by obtaining a sequence of trajectory points from the driving trajectory data of the user who initiated the navigation request, where the time covers the initiation time and the time interval between adjacent trajectory points does not exceed a first time threshold.

[0058] Specifically, the first time threshold can be set in advance based on actual driving conditions. If the time interval between adjacent trajectory points does not exceed the first time threshold, they can be considered to be within the same trip; if the time interval between adjacent trajectory points exceeds the first time threshold, the two adjacent trajectory points can be considered to be within different trips. For example, the first time threshold can be set to half an hour, or alternatively, other time thresholds can be set.

[0059] For example, if a user initiates a navigation request at 9:10, the time corresponding to the obtained driving trajectory may be a period of time starting from 9:10 and continuing thereafter, or it may be a period of time in the middle where 9:10 is located.

[0060] Optionally, when historical navigation request information and historical driving trajectory are recorded together, the historical driving trajectory can also be obtained directly based on the navigation request information and the tags of the driving trajectory.

[0061] Step S13: Insert the historical navigation starting point into the historical driving trajectory to obtain the interpolated driving trajectory.

[0062] In one embodiment, the historical navigation starting point can be inserted into the historical driving trajectory sorted by time based on the initiation time of the historical navigation request, thus obtaining the interpolated driving trajectory.

[0063] Because the trajectory points in the navigation data are thinned points—for example, thinned at 5-second intervals (meaning the time interval between two adjacent trajectory points is greater than or equal to 5 seconds)—a user might send a navigation request precisely when a nearby road change is occurring, either just before or after the change. If the historical navigation starting point isn't pre-inserted into the historical trajectory point sequence, the matched road is prone to errors. Pre-inserting the navigation starting point into the trajectory point sequence, then matching the trajectory point sequence with the road sequence to determine the road corresponding to the navigation starting point, improves the accuracy of the starting road selection.

[0064] Step S14: Match the interpolated driving trajectory with the map road network data to obtain a road sequence that matches the interpolated driving trajectory.

[0065] In one embodiment, for each trajectory point in the interpolated driving trajectory, alternative roads that can be matched with the trajectory point are determined; the weights of the alternative roads are determined according to a set rule, and the alternative road with the highest weight is determined as the matching road for the trajectory point. The aforementioned trajectory points include the navigation starting point inserted into the driving trajectory.

[0066] In one embodiment, the weights of candidate roads are determined according to a set rule, and the weights of candidate roads can be determined based on at least one of the following information:

[0067] The distance from the trajectory point to the alternative road;

[0068] The connectivity between the alternative roads and the roads containing the previous trajectory points of the trajectory points in the direction of the interpolated driving trajectory;

[0069] The first transition probability from the road where the previous trajectory point is located to the alternative road is determined based on the sum of the trajectory points and the velocity of the previous trajectory point in the direction of travel of the interpolated trajectory.

[0070] The second transition probability from the road where the previous trajectory point is located to the alternative road is determined based on the azimuth angle of the previous trajectory point and the interpolated travel trajectory forward direction trajectory point.

[0071] Determining the road for trajectory point matching not only considers the distance from the trajectory point to the road and the connectivity between adjacent trajectory points and matching roads, but also the transition probability between point-to-point and road-to-road connections, resulting in higher accuracy in road matching.

[0072] Step S15: From the road sequence, determine the road where the historical navigation starting point is located as the starting road.

[0073] In one embodiment, the matching road of the historical navigation starting point can be determined based on the navigation request initiation time and the entry time of each road in the road sequence; the road in the road sequence that matches the navigation starting point can be determined as the starting road.

[0074] The above-described solution provided in this disclosure obtains historical navigation request information and its corresponding historical driving trajectory; inserts the historical navigation starting point into the historical driving trajectory to obtain an interpolated driving trajectory; matches the interpolated driving trajectory with map road network data to obtain a matching road sequence; and determines the road where the historical navigation starting point is located as the starting road from the road sequence. Instead of directly determining the starting road based on the GPS positioning of the historical navigation starting point, it first obtains the corresponding historical driving trajectory, inserts the navigation starting point into the historical driving trajectory, and then determines the starting road based on the road sequence matching the driving trajectory. Because it takes into account the connectivity of matching roads before and after the navigation starting point, it improves the accuracy of the determined starting road; and it avoids manual operation, automatically and efficiently obtaining historical navigation request information and starting roads in batches from historical navigation data.

[0075] Example 2

[0076] Embodiment 2 of this disclosure provides a specific method for determining the starting road, the process of which is as follows: Figure 2 As shown, it includes the following steps:

[0077] Step S21: Obtain the historical navigation request information of the navigation object, and obtain the corresponding historical driving trajectory based on the initiation time of the historical navigation request in the information.

[0078] From the historical trajectory point records of the navigation object, obtain the sequence of trajectory points whose time covers the initiation time of the historical navigation request as the corresponding historical driving trajectory.

[0079] Step S22: Based on the initiation time of the historical navigation request, insert the historical navigation starting point into the historical driving trajectory sorted by time to obtain the interpolated driving trajectory.

[0080] Specifically, along the trajectory's direction of travel, the historical navigation starting point is inserted before trajectory points whose recording time is earlier than the initiation time, and after trajectory points whose recording time is later than the initiation time. Here, "before" and "after" are relative to the trajectory's direction of travel. (See reference...) Figure 3 As shown, Figure 3 The image shows three trajectory points in the historical driving trajectory: trajectory point 1, trajectory point 2, and trajectory point 3. Based on the initiation time of the historical navigation request, it is determined that the time period between the recording time of trajectory point 1 and the recording time of trajectory point 2 covers the initiation time. Therefore, the historical navigation starting point is inserted between trajectory point 1 and trajectory point 2.

[0081] Step S23: Divide the interpolated driving trajectory according to the preset rules.

[0082] Specifically, this could involve deleting trajectory points whose number of trajectory points relative to the historical navigation starting point exceeds a preset threshold; and / or deleting trajectory points whose distance from the historical navigation starting point exceeds a preset distance threshold; and / or deleting trajectory points whose time interval with the historical navigation starting point exceeds a second time threshold.

[0083] For example, if the preset threshold for the number of trajectory points between the historical navigation starting point and the historical navigation starting point is 2N, then all trajectory points before the Nth trajectory point forward from the historical navigation starting point and after the Nth trajectory point backward in the interpolated driving trajectory will be deleted.

[0084] By reducing the number of trajectory points obtained before matching the road sequence, the amount of computation can be reduced without affecting the accuracy of the determined starting road, making the matching more efficient.

[0085] Step S24: Match the road sequence to the trajectory point sequence.

[0086] Along the direction of travel of the trajectory, for each trajectory point in the sequence of trajectory points into which the requested starting point is inserted, roads are matched in turn to obtain a sequence of roads that match the sequence of trajectory points.

[0087] Step S25: Match the interpolated driving trajectory with the map road network data to obtain a road sequence that matches the interpolated driving trajectory.

[0088] Taking road matching of a trajectory point A in the interpolated driving trajectory as an example, it can be done by obtaining roads around trajectory point A from the map road network data as candidate roads based on the location information of trajectory point A; determining the weight of each candidate road according to a preset method, and determining the candidate road with the highest weight as the matching road for trajectory point A.

[0089] The specific method for determining the weights of candidate roads is not limited in this embodiment.

[0090] Step S26: From the road sequence, determine the road where the historical navigation starting point is located as the starting road.

[0091] Each trajectory point in the interpolated driving trajectory has a corresponding matching road, that is, one or more trajectory points correspond to one matching road. Therefore, after completing the matching of the road sequence, the road sequence is checked back, and the road in the road sequence corresponding to the historical navigation starting point is determined as the starting road.

[0092] In one embodiment, historical navigation request information and its corresponding starting road can be used as ground truth for training the starting point road grasping model, thereby establishing the starting point road grasping model.

[0093] Based on the same inventive concept, this disclosure also provides a device for determining the starting point of a road, the structure of which is as follows: Figure 4 As shown, it includes:

[0094] The first acquisition module 41 is used to acquire historical navigation request information of the navigation object, wherein the information includes at least the historical navigation starting point;

[0095] The second acquisition module 42 is used to acquire the historical driving trajectory corresponding to the historical navigation request information acquired by the first acquisition module 41;

[0096] The insertion module 43 is used to insert the historical navigation starting point obtained by the first acquisition module 41 into the historical driving trajectory obtained by the second acquisition module 42 to obtain the interpolated driving trajectory.

[0097] Matching module 44 is used to match the interpolated driving trajectory obtained by the insertion module 43 with the map road network data to obtain a road sequence that matches the interpolated driving trajectory;

[0098] The determining module 45 is used to determine the road where the historical navigation starting point is located from the road sequence matched by the matching module 43 as the starting road.

[0099] In some optional embodiments, the information acquired by the first acquisition module 41 further includes: the initiation time of the historical navigation request; the second acquisition module 42 is specifically used for:

[0100] From the historical trajectory point records of the navigation object, obtain the sequence of trajectory points whose time covers the initiation time of the historical navigation request as the corresponding historical driving trajectory.

[0101] In some optional embodiments, the determining module 45 is specifically used for:

[0102] Based on the initiation time and the entry time of each road in the road sequence, the matching road of the historical navigation starting point is determined; the road in the road sequence that matches the navigation starting point is determined as the starting road.

[0103] In some alternative embodiments, the insertion module 43 is specifically used for:

[0104] Based on the initiation time of the historical navigation request, the historical navigation starting point is inserted into the historical driving trajectory sorted by time to obtain the interpolated driving trajectory.

[0105] In some optional embodiments, the matching module 44 is specifically used for:

[0106] For each trajectory point in the interpolated driving trajectory, a candidate road that can be matched with the trajectory point is determined, the trajectory point including the navigation starting point inserted into the trajectory; the weight of the candidate road is determined according to the set rules, and the candidate road with the highest weight is determined as the matching road of the trajectory point.

[0107] In some optional embodiments, the matching module 44 is specifically used for:

[0108] Determine the weight of the candidate roads based on at least one of the following information:

[0109] The distance from the trajectory point to the alternative road;

[0110] The connectivity between the alternative roads and the roads containing the previous trajectory points of the trajectory points in the direction of the interpolated driving trajectory;

[0111] The first transition probability from the road where the previous trajectory point is located to the alternative road is determined based on the velocity of the previous trajectory point in the direction of travel of the interpolated driving trajectory.

[0112] The second transfer probability from the road where the previous trajectory point is located to the alternative road is determined based on the azimuth angle of the previous trajectory point and the interpolated driving trajectory direction.

[0113] In some optional embodiments, the above-described apparatus further includes a deletion module 46, which, after the insertion module 43 obtains the interpolated driving trajectory, is used to:

[0114] Delete trajectory points whose number of trajectory points relative to the historical navigation starting point exceeds a preset threshold; or, delete trajectory points whose distance from the historical navigation starting point exceeds a preset distance threshold; or, delete trajectory points whose time interval with the historical navigation starting point exceeds a time threshold.

[0115] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0116] Based on the same inventive concept, this disclosure also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the above-described method for determining a starting road.

[0117] Based on the same inventive concept, this disclosure also provides a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for determining the starting road.

[0118] Unless otherwise specifically stated, terms such as processing, calculation, operation, determination, display, etc., may refer to the actions and / or processes of one or more processing or computing systems or similar devices that represent the manipulation and conversion of data representing physical (e.g., electronic) quantities within the registers or memory of the processing system into other data similarly representing physical quantities within the memory, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0119] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0120] In the above detailed description, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, this disclosure is in a state of having fewer features than all of the features of a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of this disclosure.

[0121] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0122] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0123] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0124] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

Claims

1. A method for determining a starting road, characterized in that, The method includes: Obtain historical navigation request information of the navigation object, the information including at least the historical navigation starting point, which is the GPS location point when the user sent the navigation request; Obtain the historical driving trajectory corresponding to the historical navigation request information; The historical navigation starting point is inserted into the historical driving trajectory to obtain the interpolated driving trajectory; The interpolated driving trajectory is matched with the map road network data to obtain a road sequence that matches the interpolated driving trajectory; From the road sequence, determine the road where the historical navigation starting point is located as the starting road; This includes matching the interpolated driving trajectory with map road network data, specifically: For each trajectory point in the interpolated driving trajectory, alternative roads that can be matched with the trajectory point are determined, the trajectory point including the navigation starting point inserted into the trajectory; The weights of the candidate roads are determined according to the set rules, and the candidate road with the highest weight is determined as the matching road for the trajectory point.

2. The method according to claim 1, characterized in that, The method further includes using the historical navigation request information and its corresponding starting road as ground values ​​for training the starting point road-grabbing model.

3. The method according to claim 1, wherein the information further comprises: The initiation time of the historical navigation request, and the acquisition of the historical driving trajectory corresponding to the historical navigation request information, specifically include: From the historical trajectory point records of the navigation object, obtain the sequence of trajectory points whose time covers the initiation time of the historical navigation request as the corresponding historical driving trajectory.

4. The method according to claim 3, characterized in that, From the road sequence, the road where the historical navigation starting point is located is determined as the starting road, specifically including: Based on the initiation time and the entry time of each road in the road sequence, determine the matching road for the historical navigation starting point; The road in the road sequence that matches the navigation starting point is determined as the starting road.

5. The method according to claim 3, characterized in that, The historical navigation starting point is inserted into the historical driving trajectory to obtain the interpolated driving trajectory, specifically including: Based on the initiation time of the historical navigation request, the historical navigation starting point is inserted into the historical driving trajectory sorted by time to obtain the interpolated driving trajectory.

6. The method according to claim 1, characterized in that, The weights of candidate roads are determined according to set rules, including determining the weights of candidate roads based on at least one of the following information: The distance from the trajectory point to the alternative road; The connectivity between the alternative roads and the roads containing the previous trajectory points of the trajectory points in the direction of the interpolated driving trajectory; The first transition probability from the road where the previous trajectory point is located to the alternative road is determined based on the velocity of the previous trajectory point in the direction of travel of the interpolated driving trajectory. The second transfer probability from the road where the previous trajectory point is located to the alternative road is determined based on the azimuth angle of the previous trajectory point and the interpolated driving trajectory direction.

7. The method according to any one of claims 1 to 6, characterized in that, After obtaining the interpolated driving trajectory, the method further includes: Delete trajectory points whose number of trajectory points between them and the historical navigation starting point exceeds a preset threshold; or, Delete trajectory points whose distance from the historical navigation starting point exceeds a preset distance threshold; or, Delete trajectory points whose time interval with the historical navigation starting point exceeds a time threshold.

8. A device for determining a starting road, characterized in that, The device includes: The first acquisition module is used to acquire historical navigation request information of the navigation object. The information includes at least the historical navigation starting point, which is the GPS location point when the user sent the navigation request. The second acquisition module is used to acquire the historical driving trajectory corresponding to the historical navigation request information acquired by the first acquisition module. An insertion module is used to insert the historical navigation starting point obtained by the first acquisition module into the historical driving trajectory obtained by the second acquisition module to obtain an interpolated driving trajectory. The matching module is used to match the interpolated driving trajectory obtained by the insertion module with the map road network data to obtain a road sequence that matches the interpolated driving trajectory; The determining module is used to determine the road where the historical navigation starting point is located from the road sequence matched by the matching module as the starting road; This includes matching the interpolated driving trajectory with map road network data, specifically: For each trajectory point in the interpolated driving trajectory, alternative roads that can be matched with the trajectory point are determined, the trajectory point including the navigation starting point inserted into the trajectory; The weights of the candidate roads are determined according to the set rules, and the candidate road with the highest weight is determined as the matching road for the trajectory point.

9. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the method for determining a starting road as described in any one of claims 1 to 7.

Images