Route matching method and device for vehicle, processor and vehicle

Abstract

The application discloses a route matching method and device of a vehicle, a processor and the vehicle. The method can comprise the following steps: determining a current initial position of the vehicle at a current time; acquiring current navigation information of a current target position corresponding to the current initial position; determining at least one target road based on a current path in the current navigation information, wherein the target road is used to represent a drivable road of the vehicle; constructing a target road network matched with the vehicle based on topological information of the target road, wherein the topological information is used to represent predecessor information and / or successor information of the target road; and matching at least one trajectory point of the target road network and a current driving route of the vehicle to obtain a matching result, so as to determine a road under the current driving route in the target road network, wherein the current driving route comprises the current initial position, and the matching result is used to represent a matching degree between the trajectory point and the target road network. The application solves the technical problem of low route matching precision.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a route matching method, apparatus, processor, and vehicle for vehicles. Background Technology

[0002] In actual driving, a user's route may differ each time they drive. For example, in a scenario involving going up and down a bridge, if a user goes up the bridge one moment and down the bridge the next, it's easy to align the up bridge step with the down bridge step, resulting in an incorrect map and causing low route matching accuracy.

[0003] There is currently no effective solution to the technical problem of low accuracy in route matching mentioned above. Summary of the Invention

[0004] This invention provides a method, apparatus, processor, and vehicle for route matching, to at least solve the technical problem of low route matching accuracy.

[0005] According to one aspect of the present invention, a route matching method for a vehicle is provided. The method may include: determining the current initial position of the vehicle at the current moment; obtaining current navigation information of a current target position corresponding to the current initial position, wherein the current target position is located in the driving direction of the vehicle, and the current target position maintains a target distance from the current initial position, and the current navigation information includes a current path passing through the current initial position and the current target position; determining at least one target road based on the current path in the current navigation information, wherein the target road is used to represent a road that the vehicle can drive; constructing a target road network matching the vehicle based on the topology information of the target road, wherein the topology information is used to represent the predecessor information and / or successor information of the target road; matching the target road network with at least one trajectory point of the vehicle's current driving route to obtain a matching result, so as to determine the road under the current driving route in the target road network, wherein the current driving route includes the current initial position, and the matching result is used to represent the degree of matching between the trajectory point and the target road network.

[0006] Optionally, based on the topology information of the target road, a target road network matching the vehicle is constructed, including: determining the historical initial position of the vehicle at a historical time; obtaining historical navigation information of the historical target position corresponding to the historical initial position, wherein the historical target position is located in the historical driving direction of the vehicle, and the historical target position and the historical initial position maintain a target distance, and the historical navigation information includes the historical path passing through the historical initial position and the historical target position; and constructing the target road network based on the topology information, the current path, and the historical path in the historical navigation information.

[0007] Optionally, based on topology information, the current path, and historical paths in historical navigation information, a target road network is constructed, including: determining the current roads traversed by the current path and the historical roads traversed by the historical path; and, under the topology information, splicing the current roads and historical roads to obtain the target road network.

[0008] Optionally, based on the current path in the current navigation information, at least one target road is determined, including: determining the historical initial position of the vehicle at a historical moment; obtaining historical navigation information of the historical target position corresponding to the historical initial position, wherein the historical target position is located in the historical driving direction of the vehicle, and the historical target position maintains a target distance from the historical initial position, and the historical navigation information includes historical paths that pass through the historical initial position and the historical target position; traversing the current path and the historical paths in the historical navigation information to obtain traversal results, wherein the traversal results are used to indicate whether there are paths that pass through the same area in the current path and the historical paths; and determining at least one target road based on the traversal results.

[0009] Optionally, the current path includes the current main path where the current initial position is located, and the current sub-path connected to the current main path. The historical path includes the historical main path where the historical initial position is located, and the historical sub-path connected to the historical main path. Traversing the current path and the historical path yields the traversal result, which includes traversing the current main path, the current sub-path, the historical main path, and the historical sub-path to obtain the traversal result.

[0010] Optionally, determining at least one target road based on the traversal results includes: in response to the traversal results indicating that there are paths passing through the same area in the current path and historical paths, deleting the paths passing through the same area from the current path; and determining the historical paths traversed by the historical paths and the current paths traversed by the deleted current paths as target roads.

[0011] Optionally, at least one trajectory point includes the current trajectory point and a previous trajectory point preceding the current trajectory point, wherein the current trajectory point is the last trajectory point among multiple trajectory points. Matching the target road network with at least one trajectory point of the vehicle's current travel route to obtain a matching result includes: determining at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road, wherein the first observation probability is used to represent the probability that the previous trajectory point is located on the target road, and the second observation probability is used to represent the probability that the current trajectory point is located on the target road; determining at least one transition probability from the at least one first observation probability to the at least one second observation probability, wherein the transition probability is used to represent the probability that the first observation probability will transition to the second observation probability; fusing the at least one first observation probability, the at least one second observation probability, and the corresponding transition probability to obtain at least one fused probability from the previous trajectory point to the current trajectory point; and matching the target road network with the at least one trajectory point based on the at least one fused probability, in response to the current trajectory point being the last trajectory point, to obtain a matching result.

[0012] Optionally, in response to the current trajectory point being the last trajectory point, the target road network is matched with at least one trajectory point based on at least one fusion probability to obtain a matching result, including: in response to the current trajectory point being the last trajectory point, determining a target fusion probability from multiple fusion probabilities, wherein the target fusion probability is greater than the probabilities other than the target fusion probability among the multiple fusion probabilities; and matching the target road network with at least one trajectory point using the first observation probability and the second observation probability corresponding to the target fusion probability to obtain a matching result.

[0013] According to another aspect of the present invention, a vehicle route matching device is also provided. The device may include: a first determining unit, configured to determine the current initial position of the vehicle at the current moment; an acquiring unit, configured to acquire current navigation information of a current target position corresponding to the current initial position, wherein the current target position is located in the driving direction of the vehicle, and the current target position maintains a target distance from the current initial position, and the current navigation information includes a current path passing through the current initial position and the current target position; a second determining unit, configured to determine at least one target road based on the current path in the current navigation information, wherein the target road represents a road that the vehicle can drive; a constructing unit, configured to construct a target road network matching the vehicle based on the topology information of the target road, wherein the topology information represents the predecessor information and / or successor information of the target road; and a matching unit, configured to match the target road network with at least one trajectory point of the vehicle's current driving route to obtain a matching result, so as to determine the road under the current driving route in the target road network, wherein the current driving route includes the current initial position, and the matching result represents the degree of matching between the trajectory point and the target road network.

[0014] Optionally, the construction unit may include: a first determining module, used to determine the historical initial position of the vehicle at a historical moment; a first obtaining module, used to obtain historical navigation information of the historical target position corresponding to the historical initial position, wherein the historical target position is located in the historical driving direction of the vehicle, and the historical target position and the historical initial position maintain a target distance, and the historical navigation information includes a historical path passing through the historical initial position and the historical target position; and a construction module, used to construct a target road network based on topology information, the current path, and the historical path in the historical navigation information.

[0015] Optionally, the construction module may include: a first determining submodule, used to determine the current roads traversed by the current path and the historical roads traversed by the historical path; and a splicing submodule, used to splice the current roads and historical roads with topology information to obtain the target road network.

[0016] Optionally, the second determining unit may include: a second determining module, used to determine the historical initial position of the vehicle at a historical moment; a second obtaining module, used to obtain historical navigation information of the historical target position corresponding to the historical initial position, wherein the historical target position is located in the historical driving direction of the vehicle, and the historical target position maintains a target distance from the historical initial position, and the historical navigation information includes a historical path passing through the historical initial position and the historical target position; a traversal module, used to traverse the current path and the historical paths in the historical navigation information to obtain a traversal result, wherein the traversal result is used to indicate whether there is a path passing through the same area in the current path and the historical path; and a third determining module, used to determine at least one target road based on the traversal result.

[0017] Optionally, the current path includes the current main path where the current initial position is located, and the current sub-path connected to the current main path; the historical path includes the historical main path where the historical initial position is located, and the historical sub-path connected to the historical main path; the traversal module may include: a traversal sub-module, used to traverse the current main path, the current sub-path, the historical main path, and the historical sub-path to obtain the traversal result.

[0018] Optionally, the third determining module may include: a deletion submodule, used to delete paths that pass through the same area from the current path in response to the traversal result indicating that there are paths that pass through the same area in the current path and the historical path; and a second determining submodule, used to determine the historical roads traversed by the historical path and the current roads traversed by the deleted current path as the target road.

[0019] Optionally, at least one trajectory point includes the current trajectory point and a previous trajectory point preceding the current trajectory point, wherein the current trajectory point is the last trajectory point among multiple trajectory points. The matching unit may include: a fourth determining module, used to determine at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road, wherein the first observation probability is used to represent the probability that the previous trajectory point is located on the target road, and the second observation probability is used to represent the probability that the current trajectory point is located on the target road; a fifth determining module, used to determine at least one transition probability from at least one first observation probability to at least one second observation probability, wherein the transition probability is used to represent the probability that the first observation probability will transition to the second observation probability; a fusion module, used to fuse the at least one first observation probability, the at least one second observation probability, and the corresponding transition probability to obtain at least one fused probability from the previous trajectory point to the current trajectory point; and a matching module, used to match the at least one trajectory point with the target road network based on the at least one fused probability in response to the current trajectory point being the last trajectory point, to obtain a matching result.

[0020] Optionally, the matching module may include: a third determining submodule, used to determine a target fusion probability from multiple fusion probabilities in response to the current trajectory point being the last trajectory point, wherein the target fusion probability is greater than the probabilities other than the target fusion probability among the multiple fusion probabilities; and a matching submodule, used to match the target road network with at least one trajectory point using the first observation probability and the second observation probability corresponding to the target fusion probability, to obtain a matching result.

[0021] According to another aspect of the present invention, a vehicle is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program, when running, performs the method described in any of the above.

[0022] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, the device where the storage medium is located executes any of the methods described above.

[0023] According to another aspect of the present invention, a computer program product is also provided, the computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of any of the above.

[0024] In this embodiment of the invention, when matching a vehicle's route, the vehicle's current initial position at the current moment can be determined, and the current navigation information of the current target position corresponding to the current initial position can be obtained. Based on the current path in the obtained current navigation information, at least one target road can be determined. Based on the topology information of the determined target road, a target road network matching the vehicle can be constructed, and the constructed target road network can be matched with at least one trajectory point of the vehicle's current driving route to obtain a matching result. Since in this embodiment, based on the determined target road, a target road network matching the vehicle can be constructed according to the topology information of the target road, and at least one trajectory point of the vehicle's current driving route can be matched within the constructed target road network to obtain the degree of matching between the trajectory point and the target road network, the accuracy of the target road network can be guaranteed, thereby solving the technical problem of low route matching accuracy and achieving the technical effect of improving route matching accuracy. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0026] Figure 1(a) is a schematic diagram of an application scenario of a vehicle route matching method according to an embodiment of the present invention;

[0027] Figure 1(b) is a flowchart of a vehicle route matching method according to an embodiment of the present invention;

[0028] Figure 2(a) is a flowchart of a method for distinguishing different roads by memorizing multiple driving routes according to an embodiment of the present invention;

[0029] Figure 2(b) is a schematic diagram of the trajectory observation effect of a vehicle according to an embodiment of the present invention;

[0030] Figure 2(c) is a schematic diagram of the matching effect between the trajectory points of a vehicle and the road network according to an embodiment of the present invention;

[0031] Figure 2(d) is a schematic diagram of data interaction between a vehicle and a server according to an embodiment of the present invention;

[0032] Figure 3 This is a structural block diagram of a vehicle route matching device according to an embodiment of the present invention;

[0033] Figure 4 This is a structural block diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] According to an embodiment of the present invention, a route matching method for vehicles is provided.

[0037] As an optional implementation, the above-described vehicle route matching method can be applied, but is not limited to, the application scenario shown in Figure 1(a). Figure 1(a) is a schematic diagram of an application scenario of a vehicle route matching method according to an embodiment of the present invention. As shown in Figure 1(a), in the application scenario, the mobile terminal 10 can communicate with the server 13 via the network 11, but is not limited to. The server 13 can perform operations on the database, such as writing or reading data. The mobile terminal 10 can be a terminal device, which can include, but is not limited to, a human-computer interaction screen, a processor, and a memory. The human-computer interaction screen can be used, but is not limited to, to display a virtual machine on the mobile terminal 10. The vehicle 12 can be used, but is not limited to, to respond to the above-described human-computer interaction operation, execute the corresponding operation, or generate the corresponding instruction and send the generated instruction to the server 13. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0038] For example, the vehicle route matching method in this application can be used to provide route differentiation functionality for preset application scenarios. These preset application scenarios can include the following scenarios in the vehicle field: autonomous driving scenarios for commuting, AI-powered driver assistance scenarios for family cars, automatic parking assistance (APA) scenarios (such as memory parking for self-owned parking spaces in garages, intelligent parking for designated parking spaces in parking lots, etc.), and navigation-guided pilot (NGP) scenarios in urban or highway areas. Furthermore, these preset application scenarios may also include, but are not limited to: intelligent transportation scenarios for intelligent driving trucks or unmanned trucks in the logistics and transportation field, and intelligent farming scenarios for autonomous agricultural vehicles in the agricultural machinery field.

[0039] When the aforementioned preset application scenario is a scenario in a field other than the vehicle field, those skilled in the art should understand that the vehicles in the above-mentioned vehicle route matching method can be replaced with other objects (e.g., agricultural machinery, drones, and robots), and correspondingly, the various devices and systems included in the vehicle can be replaced with devices and systems related to other objects. Based on this, this application embodiment takes the vehicle field as an example to illustrate the specific implementation of the above-mentioned vehicle numbering method.

[0040] Figure 1(b) is a flowchart of a vehicle route matching method according to an embodiment of the present invention. As shown in Figure 1(b), the method may include the following steps:

[0041] Step S112: Determine the current initial position of the vehicle at the current moment.

[0042] In the technical solution provided by step S112 of the present invention, the current initial position can be represented by coordinates, which can be any one of the following forms or a combination thereof: two-dimensional coordinates and three-dimensional coordinates, etc.

[0043] In this embodiment, the current initial position of the vehicle at the current moment is determined. Optionally, if the vehicle is detected to be in motion, this embodiment locates the location the vehicle has reached at the current moment to obtain the current initial position of the vehicle at the current moment.

[0044] Optionally, the vehicle's current location can be determined by locating the location it has reached at the current moment. For example, using the Global Positioning System (GPS) to locate the vehicle's current location can yield the vehicle's current initial location; or, using Bluetooth positioning to locate the vehicle's current location can yield the vehicle's current initial location.

[0045] Step S114: Obtain the current navigation information of the current target position corresponding to the current initial position.

[0046] In the technical solution provided by step S114 of the present invention, the current target position can be located in the driving direction of the vehicle, and the current target position can maintain a target distance from the current initial position. The target distance can be a pre-set initial distance, or an adjusted distance obtained by adjusting the initial distance based on the vehicle's historical driving records. This is merely an example and not a specific limitation.

[0047] In this embodiment, the current navigation information may include the current path passing through the current initial position and the current target position. The current navigation information may be navigation information of the current target position obtained from a navigation application (App), and may be, but is not limited to, v2 navigation information; this is merely an example and not a specific limitation.

[0048] In this embodiment, after determining the vehicle's current initial position at the current moment, the current navigation information of the current target position corresponding to the current initial position is obtained. Optionally, based on determining the vehicle's current initial position at the current moment, this embodiment can determine the current target position corresponding to the current initial position along the vehicle's driving direction at a target distance from the determined current initial position. The current navigation information of the determined current target position can be obtained from the navigation app. For example, the current path passing through the current initial position and the current target position can be obtained. This is only an example and is not specifically limited.

[0049] Step S116: Based on the current path in the current navigation information, determine at least one target road.

[0050] In the technical solution provided in step S116 of the present invention, the target road can be used to represent a road on which vehicles can travel. For example, the target road can be represented by "road," which is only an example and not a specific limitation.

[0051] In this embodiment, after obtaining the current navigation information of the current target location corresponding to the current initial location, at least one target road is determined based on the current path in the current navigation information. Optionally, based on the obtained current navigation information, this embodiment can extract the current path passing through the current initial location and the current target location from the obtained current navigation information. Based on the extracted current path, at least one target road can be determined.

[0052] Optionally, based on the extracted current path, at least one target road can be determined. That is, the vehicle's initial historical position at a given time can be determined. Based on this initial historical position, the historical target position corresponding to the initial historical position can be determined along the vehicle's historical travel direction, at a target distance from the initial historical position. Historical navigation information for the determined historical target position can be obtained from the navigation app; for example, the historical path passing through the initial historical position and the target historical position can be retrieved. Based on the current path and the historical path, at least one target road can be determined.

[0053] It should be noted that the method described above for determining at least one target road based on the current path in the current navigation information is merely illustrative and is not intended to impose specific limitations. Any process or method that can determine at least one target road based on the current path in the current navigation information is within the protection scope of this application's embodiments, and will not be described in detail here.

[0054] Step S118: Based on the topology information of the target road, construct a target road network that matches the vehicle.

[0055] In the technical solution provided by step S118 of the present invention, the aforementioned topology information can be used to represent the preceding and / or following information of the target road. For example, if the target road is a dead-end road, the topology information can be used to represent the preceding or following information of the target road; if the target road is a connected road, the topology information can be used to represent both the preceding and following information of the target road. This is merely an example and is not intended to be specific.

[0056] In this embodiment, after determining at least one target road based on the current path in the current navigation information, a target road network matching the vehicle is constructed based on the topology information of the target road. Optionally, this embodiment can determine the topology information of the target road after determining at least one target road. Based on the determined topology information and the current path passing through the current initial position and the current target position, a target road network matching the vehicle can be constructed.

[0057] Optionally, if the target road is a dead-end road, the preceding or following information of the target road can be determined. Based on the determined preceding or following information, and the current path passing through the current initial position and the current target position, a target road network matching the vehicle can be constructed.

[0058] Optionally, if the target road is a connected road, the predecessor and successor information of the target road can be determined. Based on the determined predecessor and successor information, as well as the current path passing through the current initial position and the current target position, a target road network matching the vehicle can be constructed.

[0059] Step S120: Match at least one trajectory point of the target road network with the vehicle's current driving route to obtain a matching result, so as to determine the road under the current driving route in the target road network.

[0060] In the technical solution provided by step S120 of the present invention, the current driving route may include the current initial position. The matching result can be used to represent the degree of matching between the trajectory points and the target road network.

[0061] In this embodiment, after constructing a target road network matching the vehicle based on the topology information of the target road, the target road network is matched with at least one trajectory point of the vehicle's current driving route to obtain a matching result, thereby determining the road under the current driving route in the target road network. Optionally, based on the constructed target road network matching the vehicle, this embodiment can determine the current trajectory point and the previous trajectory point located before the current trajectory point from at least one trajectory point of the vehicle's current driving route. Matching the constructed target road network with the current trajectory point and the previous trajectory point of the vehicle's current driving route can obtain a first matching result and a second matching result. The matching results include the first matching result and the second matching result. The first matching result can be used to represent the degree of matching between the current trajectory point and the target road network, and the second matching result can be used to represent the degree of matching between the previous trajectory point and the target road network.

[0062] Optionally, if the matching degree indicated by the matching result is higher than the matching threshold, the road under the current driving route can be determined in the constructed target road network. For example, if the matching degree indicated by the first matching result is higher than the matching threshold, and the matching degree indicated by the second matching result is higher than the matching threshold, the road under the current driving route can be determined in the constructed target road network.

[0063] It should be noted that the vehicle temperature control method in this application can also be applied to at least the following scenarios: autonomous driving scenario, assisted driving scenario, and passive driving scenario (which can be simply referred to as human-driven scenario). Specifically, the autonomous driving scenario can be used to describe a scenario where the vehicle's control system controls the vehicle's driving during driving, and the driver does not need to maintain control or supervision of the driving; the assisted driving scenario can be used to describe a scenario where the vehicle's control system provides auxiliary functions during driving, but the driver still needs to maintain control and supervision of the driving; and the passive driving scenario can be used to describe a scenario where the driver controls the vehicle to complete driving operations.

[0064] In AI-powered assisted driving for autonomous vehicles, commuting mode typically refers to a driving mode specifically designed for commuting to and from get off work or daily commutes. The AI-assisted driver collects data by learning the user's driving routes and behaviors. Once the learning process is complete, the collected data is filtered and checked, and then automatically uploaded to a cloud server to construct a cloud-based map. The next time the user chooses the same route, the AI-assisted driver is activated, and the vehicle is driven to its destination according to the constructed cloud map. Matching and complementing offline maps with the constructed cloud map improves the accuracy of the cloud map.

[0065] In steps S112 to S120 of this application, when matching a vehicle's route, the vehicle's current initial position at the current moment can be determined, and the current navigation information of the current target position corresponding to the current initial position can be obtained. Based on the current path in the obtained current navigation information, at least one target road can be determined. Based on the topology information of the determined target road, a target road network matching the vehicle can be constructed, and the constructed target road network can be matched with at least one trajectory point of the vehicle's current driving route to obtain a matching result. Since in this embodiment, based on the determined target road, a target road network matching the vehicle can be constructed according to the topology information of the target road, and at least one trajectory point of the vehicle's current driving route can be matched within the constructed target road network to obtain the degree of matching between the trajectory point and the target road network, the accuracy of the target road network can be guaranteed, thereby solving the technical problem of low route matching accuracy and achieving the technical effect of improving route matching accuracy.

[0066] The method described in this embodiment will be further described below.

[0067] As an optional embodiment, step S118 involves constructing a target road network matching the vehicle based on the topology information of the target road, including: determining the vehicle's historical initial position at a historical time; obtaining historical navigation information of the historical target position corresponding to the historical initial position; and constructing the target road network based on the topology information, the current path, and the historical path in the historical navigation information.

[0068] In this embodiment, the aforementioned historical initial position can be represented in coordinate form, which can be any one of the following forms or a combination thereof: two-dimensional coordinate form and three-dimensional coordinate form, etc.

[0069] In this embodiment, after constructing a target road network matching the vehicle based on the topology information of the target road, the initial historical position of the vehicle at a historical time is determined. Optionally, this embodiment can locate the location reached by the vehicle at a historical time when it is detected that the vehicle is in motion, thereby obtaining the initial historical position of the vehicle at a historical time. This achieves the purpose of determining the historical position of the vehicle and realizes the technical effect of improving the accuracy of data positioning.

[0070] In this embodiment, the aforementioned historical target location may be located in the vehicle's historical driving direction, and the aforementioned historical target location may maintain a target distance from the historical initial location.

[0071] In this embodiment, the aforementioned historical navigation information includes a historical path that passes through a historical initial location and a historical target location. This historical navigation information can be navigation information for a historical target location obtained from a navigation app.

[0072] In this embodiment, after determining the vehicle's initial historical position at a given historical moment, historical navigation information of the corresponding historical target position is obtained. Optionally, based on the determined initial historical position, this embodiment can determine the corresponding historical target position along the vehicle's historical driving direction at a target distance from the determined initial historical position. The historical navigation information of the determined target position can be obtained from the navigation app; for example, the historical path passing through the initial historical position and the target position can be obtained. This achieves the goal of determining the vehicle's historical navigation information and improves the accuracy of data positioning.

[0073] In this embodiment, after obtaining historical navigation information of the historical target location corresponding to the historical initial location, a target road network is constructed based on topology information, the current path, and historical paths in the historical navigation information. Optionally, based on the obtained historical navigation information, this embodiment can determine the current roads traversed by the current path and the historical roads traversed by the historical path. Based on the topology information, the current roads traversed by the current path, and the historical roads traversed by the historical path, a target road network can be constructed, thereby achieving the goal of constructing a road network suitable for this vehicle and realizing the technical effect of improving the accuracy of road network construction.

[0074] The following description further illustrates the method for constructing a target road network based on topological information, the current path, and historical paths in historical navigation information in this embodiment.

[0075] As an optional implementation method, a target road network is constructed based on topology information, the current path, and historical paths in historical navigation information, including: determining the current roads traversed by the current path and the historical roads traversed by the historical path; and concatenating the current roads and historical roads under the topology information to obtain the target road network.

[0076] In this embodiment, after obtaining historical navigation information of the historical target location corresponding to the historical initial location, the current roads traversed by the current path and the historical roads traversed by the historical path are determined. Optionally, based on the obtained historical navigation information, this embodiment performs road traversal on the current path to obtain the current roads traversed by the current path, and performs road traversal on the historical path to obtain the historical roads traversed by the historical path. This achieves the goal of determining the road to be spliced, and realizes the technical effect of improving the accuracy of road acquisition.

[0077] In this embodiment, the above splicing can be used to represent deduplication splicing.

[0078] In this embodiment, after determining the current roads traversed by the current path and the historical roads traversed by the historical path, the current roads and historical roads are concatenated using topological information to obtain the target road network. Optionally, based on the determined current roads and historical roads, this embodiment performs road deduplication on the current roads and historical roads using the topological information of the target roads, and then concatenates the deduplicated current roads and deduplicated historical roads to obtain the target road network. This achieves the goal of constructing a road network suitable for this vehicle and realizes the technical effect of improving the accuracy of road network construction.

[0079] The method for determining at least one target road based on the current path in the current navigation information described in this embodiment will be further explained below.

[0080] As an optional embodiment, step S116, determining at least one target road based on the current path in the current navigation information, includes: determining the historical initial position of the vehicle at a historical time; obtaining historical navigation information of the historical target position corresponding to the historical initial position; traversing the current path and the historical path in the historical navigation information to obtain the traversal result; and determining at least one target road based on the traversal result.

[0081] In this embodiment, the aforementioned historical initial position can be represented in coordinate form, which can be any one of the following forms or a combination thereof: two-dimensional coordinate form and three-dimensional coordinate form, etc.

[0082] In this embodiment, after obtaining the current navigation information of the current target location corresponding to the current initial location, the historical initial location of the vehicle at a historical moment is determined. Optionally, this embodiment, when detecting that the vehicle is in motion, locates the location reached by the vehicle at a historical moment, thereby obtaining the historical initial location of the vehicle at that historical moment. This achieves the purpose of determining the historical location of the vehicle and realizes the technical effect of improving the accuracy of data positioning.

[0083] In this embodiment, the aforementioned historical target location may be located in the vehicle's historical driving direction, and the aforementioned historical target location may maintain a target distance from the historical initial location.

[0084] In this embodiment, the aforementioned historical navigation information may include historical paths that pass through historical initial positions and historical target positions.

[0085] In this embodiment, after determining the vehicle's initial historical position at a given historical moment, historical navigation information of the corresponding historical target position is obtained. Optionally, based on the determined initial historical position, this embodiment can determine the corresponding historical target position along the vehicle's historical driving direction at a target distance from the determined initial historical position. The historical navigation information of the determined target position can be obtained from the navigation app; for example, the historical path passing through the initial historical position and the target position can be obtained. This achieves the goal of determining the vehicle's historical navigation information and improves the accuracy of data positioning.

[0086] In this embodiment, the traversal results described above can be used to indicate whether there are paths that pass through the same area in the current path and historical paths.

[0087] In this embodiment, after obtaining historical navigation information of the historical target location corresponding to the historical initial location, the current path and the historical paths in the historical navigation information are traversed to obtain traversal results. Optionally, based on the obtained historical navigation information, this embodiment can extract historical paths from the historical navigation information. Traversing the extracted current path and the historical path yields traversal results, thereby achieving the goal of determining whether there are paths passing through the same area in the current path and historical paths, and realizing the technical effect of improving the efficiency of road determination.

[0088] In this embodiment, after traversing the current path and historical paths in the historical navigation information to obtain the traversal results, at least one target road is determined based on the traversal results. Optionally, this embodiment, based on the obtained traversal results, performs content judgment on the obtained traversal results to determine whether to delete paths that pass through the same area from the current path. Historical roads traversed by the historical path and current roads traversed by the deleted current path can be determined as target roads; or, historical roads traversed by the historical path and current roads traversed by the current path that were not deleted can be determined as target roads. This achieves the purpose of determining target roads and realizes the technical effect of improving the accuracy of the determined road data.

[0089] The following section further explains the method described above for traversing the current path and historical paths to obtain traversal results in this embodiment.

[0090] As an optional implementation method, the current path and historical paths are traversed to obtain traversal results, including: traversing the current main path, current sub-path, historical main path and historical sub-path to obtain traversal results.

[0091] In this embodiment, the current path may include the current main path where the current initial position is located, and the current sub-path connected to the current main path. For example, the current main path can be represented by the main path, and the current sub-path can be represented by the sub-path. This is only an example and is not a specific limitation.

[0092] In this embodiment, the historical path may include the main historical path at the initial historical position and the historical sub-paths connected to the main historical path.

[0093] In this embodiment, after obtaining historical navigation information of the historical target location corresponding to the historical initial location, the current main path, current sub-path, historical main path, and historical sub-path are traversed to obtain traversal results. Optionally, based on the obtained historical navigation information, this embodiment can extract historical paths from the historical navigation information. By traversing the extracted current main path and current sub-path in the current path, and the extracted historical main path and historical sub-path in the historical path, traversal results can be obtained. This achieves the goal of determining whether there are paths passing through the same area in the current path and historical paths, thus realizing the technical effect of improving the efficiency of road determination.

[0094] The method for determining at least one target road based on traversal results in this embodiment will be further explained below.

[0095] As an optional implementation method, determining at least one target road based on the traversal result includes: in response to the traversal result indicating that there are paths passing through the same area in the current path and the historical path, deleting the paths passing through the same area from the current path; and determining the historical paths traversed by the historical path and the current paths traversed by the deleted current path as the target roads.

[0096] In this embodiment, after traversing the current path and historical paths in the historical navigation information to obtain the traversal results, in response to the traversal results indicating that there are paths passing through the same area in the current path and historical paths, the paths passing through the same area are deleted from the current path. Optionally, based on the obtained traversal results, this embodiment performs content judgment on the obtained traversal results. If it is determined that the traversal results indicate that there are paths passing through the same area in the current path and historical paths, then it can be determined to delete the paths passing through the same area from the current path. This achieves the purpose of deduplicating duplicate roads and realizes the technical effect of improving the accuracy of the determined road data.

[0097] In this embodiment, in response to the traversal result indicating that there are paths passing through the same area in the current path and historical paths, after deleting the paths passing through the same area from the current path, the historical roads traversed by the historical path and the current roads traversed by the deleted current path are determined as the target road. Optionally, this embodiment, based on deleting the paths passing through the same area from the current path, performs road traversal on the deleted current path to obtain the current roads traversed by the deleted current path, and performs road traversal on the historical path to obtain the historical roads traversed by the historical path. The obtained historical roads traversed by the historical path and the obtained current roads traversed by the deleted current path can be determined as the target road, thereby achieving the purpose of determining the target road and realizing the technical effect of improving the efficiency of road determination.

[0098] The following description further explains the method described above for matching at least one trajectory point of the target road network with the current driving route of the vehicle to obtain a matching result.

[0099] As an optional embodiment, at least one trajectory point includes the current trajectory point and a previous trajectory point located before the current trajectory point, wherein the current trajectory point is the last trajectory point among multiple trajectory points. Step S120 involves matching the target road network with at least one trajectory point of the vehicle's current driving route to obtain a matching result, including: determining at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road; determining at least one transition probability for the at least one first observation probability to transform into at least one second observation probability; fusing the at least one first observation probability, the at least one second observation probability, and the corresponding transition probability to obtain at least one fused probability for the previous trajectory point to transform into the current trajectory point; and, in response to the current trajectory point being the last trajectory point, matching the target road network with at least one trajectory point based on the at least one fused probability to obtain a matching result.

[0100] In this embodiment, the aforementioned at least one trajectory point may include the current trajectory point and the previous trajectory point located before the current trajectory point. The current trajectory point may be the last trajectory point among multiple trajectory points; this last trajectory point may also be referred to as the final trajectory point. This is merely an example and not a specific limitation.

[0101] In this embodiment, the first observation probability can be used to represent the probability that the previous trajectory point is located on the target road, and the second observation probability can be used to represent the probability that the current trajectory point is located on the target road.

[0102] In this embodiment, after constructing a target road network matching the vehicle based on the topology information of the target road, at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road are determined. Optionally, based on the constructed target road network matching the vehicle, this embodiment can determine the current trajectory point and the previous trajectory point located before the current trajectory point from at least one trajectory point of the vehicle's current driving route. Based on determining the current trajectory point and the previous trajectory point, at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road, can be determined. That is, the probability that the previous trajectory point is located on at least one target road and the probability that the current trajectory point is located on at least one target road can be determined, thereby achieving the purpose of determining the observation probability of trajectory points and roads, and realizing the technical effect of improving the reliability of trajectory point matching.

[0103] In this embodiment, the aforementioned transition probability can be used to represent the degree of likelihood of the first observation probability transitioning to the second observation probability.

[0104] In this embodiment, after determining at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road, at least one transition probability is determined to transform from the at least one first observation probability to the at least one second observation probability. Optionally, based on determining the at least one first observation probability and the at least one second observation probability, this embodiment calculates the probability of the at least one first observation probability transforming into the at least one second observation probability to obtain the at least one transition probability. This achieves the goal of determining the transition probability between two observations, thereby improving the reliability of trajectory point matching.

[0105] In this embodiment, after determining at least one transition probability from at least one first observation probability to at least one second observation probability, the at least one first observation probability, the at least one second observation probability, and the corresponding transition probability are fused to obtain at least one fused probability of the previous trajectory point transitioning to the current trajectory point. Optionally, this embodiment, based on determining at least one transition probability, fuses the determined at least one first observation probability, the at least one second observation probability, and the corresponding transition probability to obtain at least one fused probability of the previous trajectory point transitioning to the current trajectory point. This achieves the purpose of fusing and calculating the transition probabilities, and realizes the technical effect of improving the reliability of trajectory point matching.

[0106] In this embodiment, after fusing at least one first observation probability, at least one second observation probability, and the corresponding transition probability to obtain at least one fused probability of the previous trajectory point transforming into the current trajectory point, in response to the current trajectory point being the last trajectory point, the target road network is matched with at least one trajectory point based on the at least one fused probability to obtain a matching result. Optionally, this embodiment, based on obtaining the at least one fused probability of the previous trajectory point transforming into the current trajectory point, determines whether the current trajectory point is the last trajectory point, and obtains a determination result, wherein the determination result can be used to represent the relationship between the current trajectory point and the last trajectory point. If the obtained determination result indicates that the current trajectory point is the last trajectory point, then based on the obtained at least one fused probability, the constructed target road network is matched with at least one trajectory point to obtain a matching result, thereby achieving the purpose of ensuring the accuracy of the target road network and realizing the technical effect of improving the accuracy of route matching.

[0107] The following further explains the method of responding to the current trajectory point as the last trajectory point, matching at least one trajectory point with the target road network based on at least one fusion probability to obtain the matching result in the above embodiment.

[0108] As an optional embodiment, in response to the current trajectory point being the last trajectory point, the target road network is matched with at least one trajectory point based on at least one fusion probability to obtain a matching result, including: in response to the current trajectory point being the last trajectory point, determining a target fusion probability from multiple fusion probabilities; and using the first observation probability and the second observation probability corresponding to the target fusion probability to match the target road network with at least one trajectory point to obtain a matching result.

[0109] In this embodiment, the target fusion probability can be greater than any of the multiple fusion probabilities other than the target fusion probability. For example, the target fusion probability can also be referred to as the maximum fusion probability.

[0110] In this embodiment, after fusing at least one first observation probability, at least one second observation probability, and the corresponding transition probability to obtain at least one fused probability of the previous trajectory point transitioning to the current trajectory point, in response to the current trajectory point being the last trajectory point, a target fused probability is determined from multiple fused probabilities. Optionally, based on obtaining at least one fused probability of the previous trajectory point transitioning to the current trajectory point, this embodiment determines whether the current trajectory point is the last trajectory point, and a determination result can be obtained. If the determination result indicates that the current trajectory point is the last trajectory point, the multiple fused probabilities are sorted, and the target fused probability can be determined from the sorted multiple fused probabilities, thereby achieving the purpose of determining the maximum fused probability and realizing the technical effect of improving the accuracy of route matching.

[0111] In this embodiment, in response to the current trajectory point being the last trajectory point, after determining the target fusion probability from multiple fusion probabilities, the first observation probability and the second observation probability corresponding to the target fusion probability are used to match the target road network with at least one trajectory point to obtain a matching result. Optionally, this embodiment, based on determining the target fusion probability from multiple fusion probabilities, can determine the first observation probability and the second observation probability corresponding to the target fusion probability. Using the determined first observation probability and the second observation probability, the target road network is matched with at least one trajectory point to obtain a matching result, thereby achieving the purpose of determining the degree of matching between the trajectory point and the target road network, and thus achieving the technical effect of improving the accuracy of route matching.

[0112] In this embodiment of the invention, when matching a vehicle's route, the vehicle's current initial position at the current moment can be determined, and the current navigation information of the current target position corresponding to the current initial position can be obtained. Based on the current path in the obtained current navigation information, at least one target road can be determined. Based on the topology information of the determined target road, a target road network matching the vehicle can be constructed, and the constructed target road network can be matched with at least one trajectory point of the vehicle's current driving route to obtain a matching result. Since in this embodiment, based on the determined target road, a target road network matching the vehicle can be constructed according to the topology information of the target road, and at least one trajectory point of the vehicle's current driving route can be matched within the constructed target road network to obtain the degree of matching between the trajectory point and the target road network, the accuracy of the target road network can be guaranteed, thereby solving the technical problem of low route matching accuracy and achieving the technical effect of improving route matching accuracy.

[0113] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0114] In actual driving, a user's route may differ each time they drive. For example, in a scenario involving going up and down a bridge, if a user goes up the bridge one moment and down the bridge the next, it's easy to align the up bridge step with the down bridge step, resulting in an incorrect map and causing low route matching accuracy.

[0115] However, this invention proposes a vehicle route matching method. Based on the current path in the acquired current navigation information, at least one target road for the vehicle is determined. A target road network is constructed according to the topology information of the target road. The trajectory points of the vehicle are matched with the constructed target road network to obtain the matching result. This achieves the goal of ensuring the accuracy of the target road network, thereby solving the technical problem of low route matching accuracy and improving the technical effect of route matching accuracy.

[0116] In this embodiment, by executing a method for distinguishing different roads by memorizing multiple driving routes, the trajectory points of the vehicle can be matched with the constructed target road network. For example, Figure 2(a) is a flowchart of a method for distinguishing different roads by memorizing multiple driving routes according to an embodiment of the present invention. As shown in Figure 2(a), the method may include the following steps:

[0117] Step S201: Extract the current road and historical roads from the v2 navigation information.

[0118] In the technical solution provided by step S201 of the present invention, the v2 navigation information may include a main path and a sub path. The main path may represent the path where the vehicle is located, and the sub path may provide information about other paths connected to the main path.

[0119] In this embodiment, the aforementioned v2 navigation information can be a v2 path, which can be used to provide road structure and topology data near the vehicle's trajectory. All v2 paths are traversed; a path may have multiple points. Adjacent points in a path construct a road, and the road direction can be from the previous point to the next point.

[0120] After extracting the current road and historical roads from the v2 navigation information, step S202 is performed to remove duplicates from the current road and historical roads to obtain the road network.

[0121] In the technical solution provided by step S202 of the present invention, if there are identical roads passing through the same area in the current road and historical roads, then under the topological information of the target road, the current road and historical roads are deduplicated, the deduplicated current road and the deduplicated historical roads are spliced ​​together, and the topological relationship is completed, so as to obtain a local road network covering the entire trajectory.

[0122] In this embodiment, topological relationships can be constructed for all roads. Roads separated from the original path can have predecessor-successor relationships constructed based on their point sequences. For roads within different routes, their predecessor-successor relationships with other roads can be determined through their spatial location and direction.

[0123] After deduplicating the current and historical roads, proceed to step S203 to calculate the observation probability between the trajectory point and the target road, and use v2 main path weighting.

[0124] In the technical solution provided in step S203 of the present invention, a Hidden Markov Model can be used to calculate the observation probability of each trajectory point and its surrounding roads. By combining the historical predecessor and successor paths corresponding to the surrounding roads, and the calculated observation probability of each trajectory point and its surrounding roads, it is possible to determine which road the trajectory point belongs to. The observation probability can be determined by a combination of information such as the perpendicular distance, projected distance, and direction between the trajectory point and the road.

[0125] In this embodiment, the trajectory observation effect of the vehicle obtained by using v2 main path weighting can be shown in Figure 2(b). For example, Figure 2(b) is a schematic diagram of the trajectory observation effect of a vehicle according to an embodiment of the present invention. In the case of a fork in the road, the trajectory (the directed line formed by the dashed lines shown in Figure 2(b)) passes through the middle of the fork. Although matching the roads on both sides of the fork (the directed lines formed by the solid lines shown in Figure 2(b)) is reasonable, the vehicle route matching method in this application will give a higher observation probability to the road formed by the main path of the route (the directed line formed by the dotted lines shown in Figure 2(b)).

[0126] After calculating the observation probability between the trajectory point and the target road and weighting it using the v2 main path, proceed to step S204 to traverse the trajectory points and perform state transitions.

[0127] In the technical solution provided in step S204 of the present invention, the transition probability between roads can be given by the connectivity between roads. If roads are directly connected, the transition probability between roads can be 1; if roads are not connected, the transition probability between roads can be 0; if roads are indirectly connected, the transition probability between roads can be a value between 0 and 1.

[0128] In this embodiment, starting from the second trajectory, the trajectory is traversed, the maximum fusion probability of transitioning from the previous trajectory point to the current trajectory point is calculated, and the state from the previous trajectory point from which the transition occurs is recorded. The fusion probability can be obtained by fusing the observation probability of the previous trajectory point, the observation probability of the current trajectory point, and the transition probability of the observation probabilities of the previous and current trajectory points.

[0129] For example, by combining the first observation probability that the previous trajectory point A belongs to each target road, the second observation probability that the current trajectory point B belongs to each target road, and the transition probability of each target road to which the previous trajectory point A belongs to each target road to which the current trajectory point B belongs, we can obtain the maximum fusion probability of the previous trajectory point A transferring to the current trajectory point B. This is only an example and is not specifically limited.

[0130] After traversing the trajectory points and the state transitions, proceed to step S205, starting from the state with the highest fusion probability at the tail, and backtrack to obtain the matching states of all trajectory points.

[0131] In the technical solution provided by step S205 of the present invention, after traversing all trajectory points, backtracking is performed in the road network starting from the observation probability corresponding to the maximum fusion probability of the last trajectory point. This allows the matching status of each trajectory point with the road network to be obtained, that is, the degree of matching between the trajectory point and the target road network can be obtained. The aforementioned observation probability may include the first observation probability and the second observation probability corresponding to the target fusion probability, and the aforementioned backtracking may be path backtracking.

[0132] In this embodiment, the matching effect between the vehicle's trajectory points and the road network can be shown in Figure 2(c). Figure 2(c) is a schematic diagram of the matching effect between the vehicle's trajectory points and the road network according to an embodiment of the present invention. The intersecting thick black solid lines can be used to represent the road network, the black-bordered diamonds can be used to represent the vehicle's trajectory points, the thick black dashed lines can be used to represent the main road attribute, and the thin black solid lines can be used to represent the association between the trajectory points and the road network.

[0133] In this embodiment, the vehicle can upload its current initial location to the server, allowing the server to obtain the current navigation information of the current target location corresponding to the current initial location. Based on the current path in the current navigation information, at least one target road can be determined. Based on the topology information of the target road, a target road network matching the vehicle can be constructed, and at least one trajectory point of the target road network and the vehicle's current driving route can be matched to obtain a matching result, which is then sent to the vehicle. Figure 2(d) is a schematic diagram of data interaction between a vehicle and a server according to an embodiment of the present invention. As shown in Figure 2(d), the vehicle 230 can upload its current initial location to the server 231, and the server 231 can send the obtained matching result to the vehicle 230.

[0134] In this embodiment, based on the determination of the target road, a target road network matching the vehicle can be constructed according to the topology information of the target road. In the constructed target road network, at least one trajectory point of the vehicle's current driving route is matched to obtain the degree of matching between the trajectory point and the target road network. This achieves the goal of ensuring the accuracy of the target road network, thereby solving the technical problem of low route matching accuracy and achieving the technical effect of improving the accuracy of route matching.

[0135] According to another aspect of the present invention, corresponding to the embodiments of the above-described vehicle route matching method, this specification also provides a vehicle route matching device. Figure 3 This is a structural block diagram of a vehicle route matching device according to an embodiment of the present invention, such as... Figure 3 As shown, the route matching device 300 for the vehicle may include: a first determining unit 302, an acquiring unit 304, a second determining unit 306, a constructing unit 308, and a matching unit 310.

[0136] The first determining unit 302 is used to determine the current initial position of the vehicle at the current moment.

[0137] The acquisition unit 304 is used to acquire the current navigation information of the current target position corresponding to the current initial position. The current target position is located in the driving direction of the vehicle, and the current target position maintains a target distance from the current initial position. The current navigation information includes the current path passing through the current initial position and the current target position.

[0138] The second determining unit 306 is used to determine at least one target road based on the current path in the current navigation information, wherein the target road is used to represent a road that the vehicle can drive on.

[0139] Construction unit 308 is used to construct a target road network that matches vehicles based on the topology information of the target road, wherein the topology information is used to represent the predecessor and / or successor information of the target road.

[0140] The matching unit 310 is used to match at least one trajectory point of the target road network with the current driving route of the vehicle to obtain a matching result, so as to determine the road under the current driving route in the target road network, wherein the current driving route includes the current initial position, and the matching result is used to indicate the degree of matching between the trajectory point and the target road network.

[0141] Optionally, the construction unit 308 may include: a first determining module, used to determine the historical initial position of the vehicle at a historical moment; a first obtaining module, used to obtain historical navigation information of the historical target position corresponding to the historical initial position, wherein the historical target position is located in the historical driving direction of the vehicle, and the historical target position maintains a target distance from the historical initial position, and the historical navigation information includes a historical path passing through the historical initial position and the historical target position; and a construction module, used to construct a target road network based on topology information, the current path, and the historical path in the historical navigation information.

[0142] Optionally, the construction module may include: a first determining submodule, used to determine the current roads traversed by the current path and the historical roads traversed by the historical path; and a splicing submodule, used to splice the current roads and historical roads with topology information to obtain the target road network.

[0143] Optionally, the second determining unit 306 may include: a second determining module, used to determine the historical initial position of the vehicle at a historical time; a second obtaining module, used to obtain historical navigation information of the historical target position corresponding to the historical initial position, wherein the historical target position is located in the historical driving direction of the vehicle, and the historical target position maintains a target distance from the historical initial position, and the historical navigation information includes a historical path passing through the historical initial position and the historical target position; a traversal module, used to traverse the current path and the historical paths in the historical navigation information to obtain a traversal result, wherein the traversal result is used to indicate whether there is a path passing through the same area in the current path and the historical path; and a third determining module, used to determine at least one target road based on the traversal result.

[0144] Optionally, the current path includes the current main path where the current initial position is located, and the current sub-path connected to the current main path; the historical path includes the historical main path where the historical initial position is located, and the historical sub-path connected to the historical main path; the traversal module may include: a traversal sub-module, used to traverse the current main path, the current sub-path, the historical main path, and the historical sub-path to obtain the traversal result.

[0145] Optionally, the third determining module may include: a deletion submodule, used to delete paths that pass through the same area from the current path in response to the traversal result indicating that there are paths that pass through the same area in the current path and the historical path; and a second determining submodule, used to determine the historical roads traversed by the historical path and the current roads traversed by the deleted current path as the target road.

[0146] Optionally, at least one trajectory point includes the current trajectory point and a previous trajectory point preceding the current trajectory point, wherein the current trajectory point is the last trajectory point among multiple trajectory points. The matching unit 310 may include: a fourth determining module, used to determine at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road, wherein the first observation probability is used to represent the probability that the previous trajectory point is located on the target road, and the second observation probability is used to represent the probability that the current trajectory point is located on the target road; a fifth determining module, used to determine at least one transition probability from at least one first observation probability to at least one second observation probability, wherein the transition probability is used to represent the probability that the first observation probability will transition to the second observation probability; a fusion module, used to fuse the at least one first observation probability, the at least one second observation probability, and the corresponding transition probability to obtain at least one fused probability from the previous trajectory point to the current trajectory point; and a matching module, used to match the at least one trajectory point with the target road network based on the at least one fused probability in response to the current trajectory point being the last trajectory point, to obtain a matching result.

[0147] Optionally, the matching module may include: a third determining submodule, used to determine a target fusion probability from multiple fusion probabilities in response to the current trajectory point being the last trajectory point, wherein the target fusion probability is greater than the probabilities other than the target fusion probability among the multiple fusion probabilities; and a matching submodule, used to match the target road network with at least one trajectory point using the first observation probability and the second observation probability corresponding to the target fusion probability, to obtain a matching result.

[0148] In this embodiment, the vehicle route matching device includes the following units: a first determining unit, used to determine the current initial position of the vehicle at the current moment; an acquiring unit, used to acquire the current navigation information of the current target position corresponding to the current initial position, wherein the current target position is located in the vehicle's driving direction, and the current target position maintains a target distance from the current initial position, and the current navigation information includes the current path passing through the current initial position and the current target position; a second determining unit, used to determine at least one target road based on the current path in the current navigation information, wherein the target road represents a road that the vehicle can drive; and a constructing unit, used to... Based on the topology information of the target road, a target road network matching the vehicle is constructed. The topology information is used to represent the predecessor and / or successor information of the target road. A matching unit is used to match the target road network with at least one trajectory point of the vehicle's current driving route to obtain a matching result, so as to determine the road under the current driving route in the target road network. The current driving route includes the current initial position. The matching result is used to represent the degree of matching between the trajectory point and the target road network. This achieves the goal of ensuring the accuracy of the target road network, thereby solving the technical problem of low route matching accuracy and thus realizing the technical effect of improving the accuracy of route matching.

[0149] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, the device where the storage medium is located executes any of the methods described above.

[0150] According to another aspect of the present invention, a computer program product is also provided, the computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of any one of the above.

[0151] According to another aspect of the present invention, a vehicle is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program, when running, performs the method described above.

[0152] Figure 4 This is a structural block diagram of a vehicle according to an embodiment of the present invention, such as... Figure 4 As shown, the components of the vehicle 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.

[0153] Vehicle 400 may also include access device 440, which enables vehicle 400 to communicate via one or more networks 460. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. Access device 440 may include one or more of any type of wired or wireless network interface (e.g., network interface controller (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0154] In one embodiment of this disclosure, the aforementioned components of vehicle 400 and Figure 4 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 4 The vehicle structure diagram shown is for illustrative purposes only and is not intended to limit the scope of this disclosure. Those skilled in the art can add or replace other components as needed.

[0155] It should be noted that the sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0156] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0157] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed can be through some interfaces; the indirect coupling or communication connection of units or modules can be electrical or other forms.

[0158] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0159] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0160] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0161] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for matching routes for vehicles, characterized in that, include: Determine the vehicle's current initial position at the current moment; Obtain current navigation information of the current target position corresponding to the current initial position, wherein the current target position is located in the driving direction of the vehicle, and the current target position maintains a target distance from the current initial position, and the current navigation information includes the current path passing through the current initial position and the current target position; Based on the current path in the current navigation information, at least one target road is determined, wherein the target road is used to represent a road that the vehicle can drive on; Based on the topology information of the target road, a target road network matching the vehicle is constructed, wherein the topology information is used to represent the predecessor and / or successor information of the target road; The target road network is matched with at least one trajectory point of the vehicle's current driving route to obtain a matching result, so as to determine the road under the current driving route in the target road network, wherein the current driving route includes the current initial position, and the matching result is used to indicate the degree of matching between the trajectory point and the target road network; The method of determining at least one target road based on the current path in the current navigation information includes: determining the historical initial position of the vehicle at a historical time; determining the historical target position corresponding to the historical initial position at a target distance from the historical initial position along the historical driving direction of the vehicle; obtaining the historical navigation information of the historical target position, wherein the historical navigation information includes the historical path passing through the historical initial position and the historical target position; and determining at least one target road based on the current path and the historical path.

2. The method according to claim 1, characterized in that, Based on the topology information of the target road, a target road network matching the vehicle is constructed, including: Determine the initial historical position of the vehicle at a given historical moment; Obtain historical navigation information of the historical target location corresponding to the historical initial location, wherein the historical target location is located in the historical driving direction of the vehicle, and the historical target location and the historical initial location maintain the target distance, and the historical navigation information includes a historical path passing through the historical initial location and the historical target location; The target road network is constructed based on the topology information, the current path, and the historical path in the historical navigation information.

3. The method according to claim 2, characterized in that, Constructing the target road network based on the topology information, the current path, and the historical path in the historical navigation information includes: Determine the current roads traversed by the current path and the historical roads traversed by the historical path; Based on the topology information, the current roads and the historical roads are spliced ​​together to obtain the target road network.

4. The method according to claim 1, characterized in that, Based on the current path and the historical path, at least one of the target roads is determined, including: The current path and the historical path are traversed to obtain the traversal result, wherein the traversal result is used to indicate whether there is a path that passes through the same area in the current path and the historical path; Based on the traversal results, it is determined whether to delete the path that passes through the same area from the current path, or to keep the current path. The target road is determined by the historical roads traversed by the historical path and the current roads traversed by the current path after deletion, or by the historical roads traversed by the historical path and the current roads traversed by the current path that are retained.

5. The method according to claim 4, characterized in that, The current path includes the current main path where the current initial position is located, and the current sub-path connected to the current main path. The historical path includes the historical main path where the historical initial position is located, and the historical sub-path connected to the historical main path. Traversing the current path and the historical paths in the historical navigation information yields a traversal result, including: The current main path, the current sub-path, the historical main path, and the historical sub-path are traversed to obtain the traversal result.

6. The method according to claim 4, characterized in that, Based on the traversal results, determining whether to delete the path that passes through the same region from the current path, or to keep the current path, includes: In response to the traversal result indicating that there exists a path that passes through the same region in the current path and the historical path, the path that passes through the same region is deleted from the current path; In response to the traversal result indicating that no path passes through the same region in the current path and the historical path, the current path is maintained.

7. The method according to claim 1, characterized in that, At least one of the trajectory points includes a current trajectory point and a previous trajectory point preceding the current trajectory point, wherein the current trajectory point is the last trajectory point among the plurality of trajectory points. The matching of at least one trajectory point of the vehicle's current driving route with the target road network yields a matching result, including: Determine at least one first observation probability between the previous trajectory point and at least one target road, and at least one second observation probability between the current trajectory point and at least one target road, wherein the first observation probability is used to represent the probability that the previous trajectory point is located on the target road, and the second observation probability is used to represent the probability that the current trajectory point is located on the target road; Determine at least one transition probability for at least one of the first observation probabilities to transform into at least one of the second observation probabilities, wherein the transition probability is used to represent the degree of probability of the first observation probability transforming into the second observation probability; At least one first observation probability, at least one second observation probability, and the corresponding transition probability are fused to obtain at least one fused probability of the previous trajectory point transitioning to the current trajectory point; In response to the current trajectory point being the last trajectory point, at least one of the trajectory points is matched with the target road network based on at least one of the fusion probabilities to obtain the matching result.

8. The method according to claim 7, characterized in that, In response to the current trajectory point being the last trajectory point, based on at least one of the fusion probabilities, at least one of the trajectory points is matched with the target road network to obtain the matching result, including: In response to the current trajectory point being the last trajectory point, a target fusion probability is determined from a plurality of fusion probabilities, wherein the target fusion probability is greater than any of the probabilities other than the target fusion probability among the plurality of fusion probabilities; Using the first observation probability and the second observation probability corresponding to the target fusion probability, at least one of the trajectory points is matched with the target road network to obtain the matching result.

9. A route matching device for vehicles, characterized in that, include: The first determining unit is used to determine the current initial position of the vehicle at the current moment; The acquisition unit is used to acquire the current navigation information of the current target position corresponding to the current initial position, wherein the current target position maintains a target distance from the current initial position in the direction of vehicle travel, and the current navigation information includes the current path passing through the current initial position and the current target position; The second determining unit is configured to determine at least one target road based on the current path in the current navigation information, wherein the target road is used to represent a road that the vehicle can drive on; A construction unit is configured to construct a target road network matching the vehicle based on the topology information of the target road, wherein the topology information is used to represent the predecessor and / or successor information of the target road; A matching unit is configured to match the target road network with at least one trajectory point of the vehicle's current driving route to obtain a matching result, so as to determine the road in the target road network that is under the current driving route, wherein the current driving route includes the current initial position, and the matching result is used to indicate the degree of matching between the trajectory point and the target road network; The second determining unit is configured to determine at least one target road based on the current path in the current navigation information by performing the following steps: determining the historical initial position of the vehicle at a historical time; determining the historical target position corresponding to the historical initial position at a target distance from the historical initial position along the historical driving direction of the vehicle; obtaining the historical navigation information of the historical target position, wherein the historical navigation information includes a historical path passing through the historical initial position and the historical target position; and determining at least one target road based on the current path and the historical path.

10. A processor, characterized in that, The processor is used to run a program, wherein the program, when run by the processor, executes the route matching method for the vehicle according to any one of claims 1 to 8.

11. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the route matching method for the vehicle according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the route matching method for the vehicle according to any one of claims 1 to 8.

Images