Method, device and apparatus for generating multiple paths, and storage medium

Abstract

Embodiments of the present disclosure provide a multi-path generation method and device, equipment and a storage medium, relating to the field of artificial intelligence, in particular to the field of intelligent transportation. The specific implementation scheme is: in response to a path generation request, M recommended paths between a starting node and a destination node are generated, wherein the M recommended paths are generated through m path generation processes, in the i-th path generation process, n i recommended paths are generated based on a constructed search tree, and for each of the n i recommended paths, a passing cost of each road segment in the recommended path in the i+1-th path generation process is determined according to a penalty factor, the passing cost is associated with a recommended priority of the path, m>i>=1, M>n i >1. The present disclosure improves the diversity of recommended paths and the path generation efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent transportation in artificial intelligence, and more particularly to a method, apparatus, device, and storage medium for generating multiple paths. Background Technology

[0002] The continuous optimization of the transportation network provides users with a wealth of route options for driving. When users have travel needs, AI-based route generation systems can generate alternative routes from the user's set origin and destination.

[0003] Currently, path generation systems often rely on penalty models to generate multiple paths through multiple iterations. In each iteration, the penalty model generates a path from the starting point to the destination and penalizes the generated path by changing the weights of the road segments it passes through before proceeding to the next iteration, which generates another path from the starting point to the destination. However, when using penalty models to generate multiple paths, the time required is long, and the paths generated in multiple iterations are highly repetitive, resulting in poor path diversity. Summary of the Invention

[0004] This disclosure provides a method, apparatus, device, and storage medium for generating multiple paths.

[0005] According to a first aspect of this disclosure, a method for generating multiple paths is provided, comprising: in response to a path generation request, generating M recommended paths from a starting node to a destination node, wherein the starting node is a node in a traffic topology network mapped to the path origin in the path generation request, and the destination node is a node in the traffic topology network mapped to the path destination in the path generation request; wherein the M recommended paths are generated through m path generation processes, and in the i-th path generation process, n paths are generated based on a constructed search tree. i Recommended paths, and for this n i For each of the recommended paths, based on the penalty factor, the travel cost of each segment in the (i+1)th path generation process is determined. This travel cost is associated with the path's recommendation priority; where m ≥ i ≥ 1, M > n. i >1.

[0006] According to a second aspect of this disclosure, a multi-path generation apparatus is provided, comprising: a path generation unit, configured to generate M recommended paths from a starting node to a destination node in response to a path generation request, wherein the starting node is a node in a traffic topology network mapped to the path origin in the path generation request, and the destination node is a node in the traffic topology network mapped to the path end in the path generation request; wherein the M recommended paths are generated through m path generation processes, and in the i-th path generation process, n paths are generated based on a constructed search tree. i Recommended paths, and for this n i For each of the recommended paths, based on the penalty factor, the travel cost of each segment in the (i+1)th path generation process is determined. This travel cost is associated with the path's recommendation priority; where m ≥ i ≥ 1, M > n. i >1.

[0007] According to a third aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method provided in the first aspect.

[0008] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method provided according to the first aspect.

[0009] According to a fifth aspect of this disclosure, a computer program product is provided, comprising: a computer program stored in a readable storage medium, wherein at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the method of the first aspect.

[0010] The technology disclosed herein improves the diversity of recommended paths and the efficiency of path generation.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0013] Figure 1 This is a schematic diagram of the structure of a path generation system 100 provided in an embodiment of the present disclosure;

[0014] Figure 2 A flowchart illustrating a multi-path generation method 200 provided in this embodiment of the disclosure;

[0015] Figure 3 This is a schematic diagram of a search tree structure provided in an embodiment of the present disclosure;

[0016] Figure 4 A flowchart illustrating another multipath generation method 300 provided in this embodiment of the disclosure;

[0017] Figure 5 A schematic block diagram of a multipath generation apparatus 400 provided for embodiments of this disclosure;

[0018] Figure 6 A schematic block diagram of another multipath generation apparatus provided in an embodiment of this disclosure;

[0019] Figure 7 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0020] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] The multi-path generation method provided in this disclosure can be applied to any field that requires path generation, and is particularly suitable for intelligent transportation, deep learning, big data, and vehicle networking.

[0022] The executing entity of this disclosure can be an electronic device, and the path generation methods mentioned in this disclosure can all be executed by this electronic device or functional modules deployed therein. The electronic device can be any terminal device, such as a navigation device, mobile phone, computer, tablet, smart wearable, etc. Alternatively, the television device can be a smart vehicle, which can be a vehicle with autonomous driving capabilities. The smart vehicle provided in the embodiments of this disclosure can utilize various sensors, map databases, Global Positioning System (GPS), etc., to achieve autonomous driving. This disclosure does not limit the form of the smart vehicle; that is, any mobile device with autonomous driving capabilities is also within the scope of protection of this disclosure.

[0023] The aforementioned electronic device can also be a server. Executing the multi-path generation method provided in this disclosure via a server makes it easier to obtain the traffic topology network data required for path generation and provides better computing power for path generation. In this disclosure, the server can interact with the aforementioned terminal device or intelligent vehicle. For example, the server can obtain a path generation request input by a user through the terminal device or intelligent vehicle and generate a path based on the request. Alternatively, the server can push the generated recommended path to the terminal device or intelligent vehicle to display the recommended path to the user through the terminal device or intelligent vehicle.

[0024] The server can be implemented as a server or a server cluster. In some embodiments, the server can be implemented as a cloud server or a cloud server cluster, and at least one of cloud storage servers and cloud computing servers can be deployed in the cloud server cluster.

[0025] Among them, cloud computing servers are used to provide cloud computing services. Cloud computing, as a computing model, distributes computing tasks across a resource pool composed of a large number of computers, enabling various application systems to obtain computing power, storage space and information services as needed.

[0026] Cloud storage servers are used to provide cloud storage services. Cloud storage is an extension and development of the concept of cloud computing. It is a storage system that brings together a large number of different types of storage devices (also called storage nodes) in the network through application software or application interfaces to work together to provide data storage and business access functions to the outside world.

[0027] To address the issues of low path generation efficiency and poor diversity of generated paths, this disclosure provides a method for generating multiple paths. It introduces a search tree for path searching, generating multiple recommended paths based on the constructed search tree during each path generation process. By iteratively executing the path generation process multiple times, multiple recommended paths are obtained, enriching the diversity of paths and improving the efficiency of path generation.

[0028] Figure 1 This is a schematic diagram of a path generation system 100 provided in an embodiment of the present disclosure. The method provided in this embodiment can be applied to, for example... Figure 1 The path generation system 100 shown may include the aforementioned terminal device 110 and server 120, which are connected via wired or wireless means.

[0029] The terminal device 110 is equipped with a human-computer interaction module 111. The terminal device 110 receives the path generation request input by the user through the human-computer interaction module 111. The terminal device 110 can also display recommended paths to the user through the human-computer interaction interface 111.

[0030] Server 120 receives a path generation request sent by terminal device 110, generates a recommended path based on the path generation request, and then sends the recommended path to terminal device 110.

[0031] It should be noted that, Figure 1 The path generation system 100 may not include the server 120. When the path generation system does not include the server 120, the terminal device 110 executes the process executed by the server 120.

[0032] The technical solutions of this disclosure are described in detail below through specific embodiments.

[0033] Figure 2 This is a flowchart illustrating a multi-path generation method 200 provided in this disclosure embodiment. The execution entity of this disclosure embodiment can be the electronic device described in the above embodiments, for example... Figure 1 Server 120 in the middle. For example... Figure 2 As shown, the method 200 includes:

[0034] S210, in response to the path generation request, generates M recommended paths from the starting node to the destination node, where the starting node is the node mapped in the traffic topology network of the path in the path generation request, and the destination node is the node mapped in the traffic topology network of the path in the path generation request.

[0035] The traffic topology network in this embodiment is an abstract representation of a traffic network. Without considering shape and size, the traffic topology network is obtained by mapping the positional relationships of road segments and intersections within the traffic network. For example, intersections in the traffic network can be mapped as nodes, and road segments can be mapped as edges between nodes. Of course, some special locations in the traffic network can also be mapped as nodes, such as mapping the starting point for path planning as a starting node and the ending point for path planning as a destination node.

[0036] It should be noted that a route generation request can be a request received by an electronic device from user input. For example, a user can input a start and end point in a human-computer interaction interface and select a route query control to input a route generation request. Alternatively, a route generation request can be a request received by an electronic device from other devices, such as... Figure 1The server 120 receives a path generation request sent by the terminal device 110. Of course, the terminal device 110 can obtain the path generation request based on the user's input or receive a path generation request sent by other devices. This disclosure does not limit this.

[0037] Regarding S210 above, it should be noted that the M recommended paths are generated through m path generation processes. The following explanation uses the i-th path generation process as an example to illustrate the iterative generation process of the M recommended paths. It should be understood that the i-th path generation process is any one of the m path generation processes.

[0038] During the i-th path generation process, based on the constructed search tree, n is generated. i A recommended path. During path generation, each node in the search tree corresponds to a node in the traffic topology network, combined with... Figure 3 As shown, the tree nodes at both ends of the search tree correspond to the starting node and the destination node in the traffic topology network, respectively. The tree nodes outside the two ends of the search tree correspond to the nodes between the starting node and the destination node in the traffic topology network. Electronic devices can generate n paths in one path generation process based on the search tree. i This disclosure improves the efficiency of path generation by generating one recommended path at a time, compared to the prior art which generates one recommended path at a time.

[0039] Continuing with the example above, in the i-th path generation process, for n i For each of the recommended paths, the travel cost of each segment in the recommended path is determined according to the penalty factor during the (i+1)th path generation process. This allows the electronic device to generate n paths during the (i+1)th path generation process based on this travel cost. i+1 A recommended path is generated. It should be noted that the travel cost represents the travel time, cost, and difficulty of the corresponding road segment; the travel cost can also be expressed as the weight of the road segment. Based on the travel costs of each road segment on the recommended path, the travel cost of the recommended path can be determined. Therefore, the travel cost of each road segment can be used to determine the travel cost of the recommended path generated in the next path generation process; that is, the travel cost is related to the recommendation priority of the path.

[0040] Based on the above iterative process, the electronic device can generate M recommended paths in m path generation processes. These M recommended paths can be the sum of the recommended paths generated in the m path generation processes, for example... Alternatively, the M recommended paths can be based on The recommended path is determined. This disclosure does not limit it.

[0041] In this embodiment of the disclosure: m≥i≥1, M>n i>1. Generally speaking, constructing a search tree can yield multiple meeting points, meaning that more than one recommended path can be generated during a single path generation process. Therefore, M > n. Of course, this disclosure does not exclude the cases where M = m or M < n.

[0042] In some embodiments, the electronic device may push the M recommended routes to the user, for example, by displaying the M recommended routes on the screen of a terminal device; or the electronic device may push the M recommended routes to other devices, for example... Figure 1 Server 120 pushes M recommended paths (such as...) to terminal device 110. Figure 1 The path marked by solid or dashed lines between the starting point and the ending point shown in the figure. Of course, the terminal device 110 can display the M recommended paths to the user through the display screen, which is not limited in this disclosure.

[0043] This disclosure provides a multi-path generation method applicable to intelligent transportation, deep learning, big data, and vehicle networking fields within the field of artificial intelligence, to improve the diversity of recommended paths and increase path generation efficiency.

[0044] In this embodiment of the disclosure, the communication cost of a road segment is determined according to the penalty factor. This can be simply described as penalizing the road segment according to the penalty factor. The two methods express the same content and can be used interchangeably.

[0045] In some embodiments, each of the M recommended paths may correspond to a set of penalty factors. The set of penalty factors corresponding to each recommended path may be the same or different, and this disclosure does not limit this.

[0046] In some embodiments, the penalty factor for each road segment in the recommended path can be different. During the i-th path generation process, the passage cost of each road segment in the recommended path during the (i+1)-th path generation process is determined based on the penalty factor. Specifically, this can be achieved by determining the passage cost of the corresponding road segment during the (i+1)-th path generation process based on the penalty factor corresponding to each road segment in the multiple road segments of each recommended path, thereby implementing fine-grained penalty for each road segment.

[0047] The penalty factor and the passage cost of a road segment can be positively correlated; for example, the larger the penalty factor value, the greater the passage cost after the penalty.

[0048] Furthermore, within a recommended path, the penalty factor for each segment can be determined based on its position within the path. For example, edge segments closer to the recommended path (such as incoming and / or outgoing edges) have larger penalty factors, while segments further away from the edge have smaller penalty factors. In this case, the probability of selecting such an edge segment is lower during the (i+1)th path generation process, resulting in a greater difference between the recommended path generated in the (i+1)th path generation process and the recommended path generated in the (i)th path generation process, thus enriching the diversity of recommended paths.

[0049] In some embodiments, during the i-th path generation process, the electronic device can construct a search tree from the starting node to the destination node. Combined with Figure 3 As shown, the search tree includes N i There are N meeting points. i ≥n i N i The meeting points are N points between the starting node and the destination node. i A path node is a node on a path, which is a node on the path formed between the starting node and the destination node.

[0050] Currently, electronic devices typically construct search trees based on a two-process unidirectional search. For example, in one search process, the electronic device searches from the starting node to the destination node, while in another search process, it searches from the destination node back to the starting node. The path is then obtained based on the meeting point between the two search processes. However, the electronic device needs to complete the path search between the starting and destination nodes in both search processes, resulting in a large search space and low search efficiency.

[0051] In this embodiment of the disclosure, the electronic device constructs a search tree from the starting node to the destination node based on a single-process bidirectional search. It should be noted that single-process bidirectional search is just one possible name, and this disclosure does not limit it. Other naming methods that employ similar techniques to this disclosure are also within the scope of protection of this disclosure. For example, combined with... Figure 3 As shown, in a search process, the electronic device starts from the starting node and the destination node respectively, and performs the search. When N forms the search tree... i When the two points meet, the search process ends, which means the search tree construction process is complete. Figure 3 Medium-thick line marking N i One path.

[0052] This disclosure uses a single-process example only and should not be construed as limiting the scope of this disclosure in any way. For example, electronic devices can also perform searches using two search processes: one search process starts from the starting node, and the other search process starts from the destination node. When N forms the search tree... i When two points of intersection are reached, the two search processes end, which means the process of building the search tree is completed.

[0053] Continuing with the above embodiments, during the i-th path generation process, the electronic device can construct a search tree from the starting node to the destination node, and then the electronic device will determine the path based on N. i The travel cost corresponding to each path is determined, and n is determined. i A recommended path. For example, for N... i For each of the N paths, the electronic device can sum the toll costs corresponding to multiple road segments of the path to obtain the toll cost of the path, and then sort the N paths in ascending order of toll cost. i Sort the n paths and select the first n. i Each path is used as n i One recommended path.

[0054] In some embodiments, the electronic device may terminate the iteration process in response to a first triggering event. The first triggering event includes, but is not limited to, at least one of the following:

[0055] i is greater than or equal to the preset number of iterations; the execution time is greater than or equal to the preset iteration time, with the start time of the execution time being the start time of the first path generation process and the end time of the execution time being the end time of the i-th path generation process; the total number of recommended paths generated in the previous i path generation processes is greater than or equal to the preset number of paths. For example, if the electronic device determines that i is greater than or equal to the preset number of iterations, it will stop executing the (i+1)-th path generation process.

[0056] As an example, the processing in any of the above embodiments can be implemented based on a waypoint model and a penalty model. For example, in the i-th path generation process, a search tree is constructed, and n... i A recommended path can be implemented by a waypoint model, which is trained based on the first network model; n is determined according to the penalty factor. i The communication cost of each segment of each recommended path in the (i+1)th path generation process can be implemented by a penalty model, which is trained based on the second network model.

[0057] As another example, the processing in any of the above embodiments can be implemented based on a path generation model, which can obtain M recommended paths based on the input starting node and destination node. This path generation model can be trained based on a third network model.

[0058] Figure 4 This is a flowchart illustrating another multi-path generation method 300 provided in an embodiment of this disclosure. Figure 4 As shown, the method 300 includes some or all of the following processes S310 to S340.

[0059] S310, Get path generation request.

[0060] S320, after m path generation processes, generates a path from the starting node to the destination node. One recommended path.

[0061] S330, Based on the first ratio, determine whether the target area is a sparse road area. The target area includes the starting node and the destination node. The first ratio is the ratio of the number of times the effective path generation process is performed to m.

[0062] When the target area is a sparsely roaded area, execute S340 and S350 in sequence; when the target area is not a sparsely roaded area, execute S350.

[0063] S340, corrected merge parameters.

[0064] S350, based on the merging parameters, The recommended paths are merged to obtain M recommended paths.

[0065] S360 identifies glitch regions in M ​​recommended paths and corrects these glitch regions.

[0066] S370, push M recommended paths.

[0067] Among them, S310, S320 and S370 and Figure 2 The processes in the illustrated embodiments have the same or similar implementation methods and technical effects, which will not be repeated here.

[0068] In S330 above, the target region can be the region where path searching is performed. For each path generation process in the above m path generation processes, determine whether it is a valid path generation process. Taking the i-th path generation process as an example, if n i The recommended path with the highest priority among the recommended paths, excluding those generated during the first i-1 recommendation path generation processes. In other words, n iIf the recommended path with the highest priority among the recommended paths was not generated in the first i-1 recommended path generation processes, then the i-th path generation process is determined to be a valid path generation process; if n i The recommended path with the highest priority among the recommended paths is the recommended path generated in the first i-1 recommended path generation processes, and the i-th path generation process is determined to be an invalid path generation process. Based on this, the electronic device uses the ratio of the number of valid path generation processes to m in the m path generation processes as the first ratio. When the first ratio is greater than or equal to a preset ratio (e.g., 30%, 40%, 50%, etc.), the electronic device can determine that there are fewer paths in the target area, that is, the target area is a sparse road area; conversely, when the first ratio is less than the preset ratio, the electronic device can determine that there are more paths in the target area, that is, the target area is not a sparse road area.

[0069] Furthermore, when the target area is a sparsely roaded region, compared to non-sparsely roaded regions, it is necessary to minimize the merging of iteratively generated recommended paths to enrich the diversity of recommended paths. Based on this, the electronic device in S340 needs to correct the merging parameters when the target path is a sparsely roaded region, so that more recommended paths can be retained when merging paths based on the corrected merging parameters.

[0070] Regarding the S360 mentioned above, it should be noted that any recommended path may contain spurious areas (or bad cases). For example, if there are two sampling points in the recommended path with time series shorter than the preset time, and both sampling points are located at the same node in the traffic topology network, it indicates that there may be abnormal road segments such as detours or congestion in the recommended path. The area composed of these abnormal road segments is the spurious area. Correcting these spurious areas makes the recommended path more reasonable.

[0071] The above text combined Figures 2 to 4 The present disclosure describes in detail the method embodiments, which are illustrated below in conjunction with... Figures 5 to 6 The present disclosure provides a detailed description of the apparatus embodiments. It should be understood that the apparatus embodiments correspond to the method embodiments, and similar descriptions can be found in the method embodiments.

[0072] Figure 5 This is a schematic block diagram of a multipath generation apparatus 400 provided for embodiments of this disclosure. Figure 5 As shown, the multipath generation apparatus 400 includes:

[0073] The path generation unit 410 is configured to generate M recommended paths from the starting node to the destination node in response to a path generation request. The starting node is the node in the traffic topology network that maps the path start point in the path generation request to the node in the traffic topology network, and the destination node is the node in the traffic topology network that maps the path end point in the path generation request to the node in the path generation request.

[0074] The M recommended paths are generated through m path generation processes. In the i-th path generation process, n paths are generated based on the constructed search tree. i Recommended paths, and for this n i For each of the recommended paths, based on the penalty factor, the travel cost of each segment in the (i+1)th path generation process is determined. This travel cost is associated with the path's recommendation priority; where m ≥ i ≥ 1, M > n. i >1.

[0075] In some embodiments, the device 400 further includes a push unit 420 for pushing the M recommended paths.

[0076] exist Figure 5 Based on the illustrated embodiment, Figure 6 A schematic block diagram of another multipath generation apparatus provided in an embodiment of this disclosure. The following is in conjunction with... Figure 6 As shown, the device 400 will be described as follows:

[0077] In some embodiments, the apparatus 400 further includes a first iterative processing unit 430, which includes a first iterative processing module 431; the first iterative processing module 431 is used to determine the passage cost of the road segment in the (i+1)th path generation process based on the penalty factor corresponding to each road segment in the plurality of road segments.

[0078] In some embodiments, the first iterative processing unit 430 further includes a second iterative processing module 432; the second iterative processing module 432 is used to determine the penalty factors corresponding to the multiple road segments of the recommended path according to the positions of the multiple road segments in the recommended path.

[0079] In some embodiments, the device 400 includes a second iteration processing unit 440, which includes a third iteration processing module 441 and a fourth iteration processing module 442; the third iteration processing module 441 is used to construct a search tree from the starting node to the destination node, the search tree including N i There are N meeting points. i ≥n i The N i The meeting points are N points between the starting node and the destination node. i A path node on a path; the fourth iteration processing module 442 is used to process the N... i The travel cost corresponding to each of the n paths determines the n... i One recommended path.

[0080] In some embodiments, the third iteration processing module 441 is specifically configured to: construct the search tree starting from the starting node and the target node respectively, and in the N forming the search tree i The search tree construction process ends when there are 10 encounter points.

[0081] In some embodiments, the fourth iteration processing module 442 includes a first iteration processing submodule 4421 and a second iteration processing submodule 4422: the first iteration processing submodule 4421 is used for the N i For each of the N paths, the toll costs corresponding to the multiple road segments of that path are summed to obtain the toll cost of that path; the second iterative processing submodule 4422 is used to process the N paths in ascending order of toll cost. i Sort the n paths and select the first n. i The n paths are used as the n i One recommended path.

[0082] In some embodiments, the apparatus 400 further includes: a third iteration processing unit 450, configured to stop executing the (i+1)th path generation process in response to a first triggering event; wherein the first triggering event includes at least one of the following:

[0083] i is greater than or equal to the preset number of iterations;

[0084] The execution time is greater than or equal to the preset iteration time. The start time of this execution time is the start time of the first path generation process, and the end time of this execution time is the end time of the i-th path generation process.

[0085] The total number of recommended paths generated in the previous i path generation processes is greater than or equal to the preset number of paths.

[0086] In some embodiments, the path generation unit 410 includes a first path generation module 411; the first path generation module 411 is configured to, based on merging parameters, process the path generated in m path generation processes. The recommended paths are merged to obtain the M recommended paths.

[0087] In some embodiments, the path generation unit 410 further includes a second path generation module 412, which includes a first path generation submodule 4121 and a second path generation submodule 4122. The first path generation submodule 4121 is used to determine whether the target area is a sparse road area based on a first ratio. The target area includes the starting node and the destination node. The first ratio is the ratio of the number of effective path generation processes to m. The second path generation submodule 4122 is used to correct the merging parameter when the target area is a sparse road area.

[0088] In some embodiments, the second path generation module 412 includes a third path generation submodule 4123: the third path generation submodule 4123 is used for if n i The recommended path with the highest priority among the recommended paths, and the recommended path that was not generated in the first i-1 recommended path generation processes, is determined to be a valid path generation process.

[0089] In some embodiments, the path generation unit 410 further includes a third path generation module 413; the third path generation module 413 is used to identify burr regions in the M recommended paths and correct the burr regions.

[0090] The above Figure 5 and Figure 6 The apparatus provided in the embodiments can execute the technical solutions on the intelligent vehicle side of the above method embodiments. Its implementation principle and technical effects are similar, and will not be repeated here.

[0091] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0092] According to embodiments of this disclosure, this disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, at least one processor of an electronic device being able to read the computer program from the readable storage medium, and the at least one processor executing the computer program causing the electronic device to perform the scheme provided in any of the above embodiments.

[0093] Figure 7 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The electronic device may also represent a vehicle with autonomous driving capabilities, such as an intelligent vehicle. The electronic device may also represent a server. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0094] like Figure 7As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0095] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0096] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 executes the multipath generation method described in the embodiments above. For example, in some embodiments, the multipath generation method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the multipath generation method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to execute the multipath generation method by any other suitable means (e.g., by means of firmware).

[0097] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0099] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0100] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0101] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0102] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0103] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0104] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for generating multiple paths, comprising: In response to a path generation request, M recommended paths are generated from the starting node to the destination node, where the starting node is the node mapped in the traffic topology network of the path in the path generation request, and the destination node is the node mapped in the traffic topology network of the path ending point of the path in the path generation request. The M recommended paths are generated through m path generation processes. In the i-th path generation process, n paths are generated based on the constructed search tree. i Recommended paths, and for the n i For each of the recommended paths, the travel cost of each segment in the recommended path during the (i+1)th path generation process is determined according to a penalty factor, and the travel cost is associated with the recommendation priority of the path; where m≥i≥1, M>n i >1.

2. The method according to claim 1, wherein, The n i Each recommended path includes multiple road segments, and each of the multiple road segments corresponds to multiple penalty factors. The step of determining the travel cost of each road segment in the recommended path during the (i+1)th path generation process based on the penalty factor includes: Based on the penalty factor corresponding to each of the multiple road segments, the passage cost of the road segment in the (i+1)th path generation process is determined.

3. The method according to claim 2, wherein, The method further includes: Based on the positions of multiple road segments in the recommended path, the penalty factors corresponding to each of the multiple road segments in the recommended path are determined.

4. The method according to any one of claims 1 to 3, wherein, The constructed search tree generates n i The recommended paths include: Construct a search tree from the starting node to the destination node, the search tree comprising N i There are N meeting points. i ≥n i The N i The meeting points are N points between the starting node and the destination node. i A path node on a path; According to the N i The travel cost corresponding to each path is used to determine the n... i One recommended path.

5. The method according to claim 4, wherein, The construction of the search tree from the starting node to the destination node includes: Starting from the starting node and the destination node respectively, construct the search tree, and in the N nodes forming the search tree... i The search tree construction process ends when there are 10 encounter points.

6. The method according to claim 4, wherein, The N i Each path includes multiple road segments; According to the N i The travel cost corresponding to each path is determined, and n is determined. i The recommended paths include: For the N i For each path in the given path, the toll costs corresponding to multiple road segments of the path are summed to obtain the toll cost of the path. According to the order of passage cost from smallest to largest, the N... i Sort the n paths and select the first n. i The path is used as n i One recommended path.

7. The method according to any one of claims 1 to 3, wherein, The method further includes: In response to the first triggering event, the (i+1)th path generation process is stopped; where, The first triggering event includes at least one of the following: i is greater than or equal to the preset number of iterations; The execution time is greater than or equal to the preset iteration time, the start time of the execution time is the start time of the first path generation process, and the end time of the execution time is the end time of the i-th path generation process. The total number of recommended paths generated in the previous i path generation processes is greater than or equal to the preset number of paths.

8. The method according to any one of claims 1 to 3, wherein, The generation of M recommended paths from the starting node to the destination node includes: Based on the merging parameters, the path generation process generated m times... The recommended paths are merged to obtain the M recommended paths.

9. The method according to claim 8, wherein, The method further includes: Based on the first ratio, it is determined whether the target area is a sparse road area. The target area includes the starting node and the destination node. The first ratio is the ratio of the number of times the effective path generation process is performed to m. When the target area is a sparsely roaded area, the merging parameters are adjusted.

10. The method according to claim 9, wherein, The method further includes: If n i The recommended path with the highest priority among the recommended paths, and the recommended path not generated in the first i-1 recommended path generation processes, are determined to be a valid path generation process.

11. The method according to any one of claims 1 to 3, wherein, The method further includes: The M recommended paths are subjected to burr region identification, and the burr regions are corrected.

12. A multipath generation apparatus, comprising: A path generation unit is configured to generate M recommended paths from a starting node to a destination node in response to a path generation request. The starting node is the node in the traffic topology network that maps the path start point in the path generation request to the node in the traffic topology network, and the destination node is the node in the traffic topology network that maps the path end point in the path generation request to the node in the traffic topology network. The M recommended paths are generated through m path generation processes. In the i-th path generation process, n paths are generated based on the constructed search tree. i Recommended paths, and for the n i For each of the recommended paths, the travel cost of each segment in the recommended path during the (i+1)th path generation process is determined according to a penalty factor, and the travel cost is associated with the recommendation priority of the path; where m≥i≥1, M>n i >1.

13. The apparatus according to claim 12, wherein, The n i Each recommended path contains multiple road segments, and each road segment corresponds to multiple penalty factors; the device further includes a first iterative processing unit, which includes a first iterative processing module. The first iterative processing module is used to determine the passage cost of the road segment in the (i+1)th path generation process based on the penalty factor corresponding to each of the plurality of road segments.

14. The apparatus according to claim 13, wherein, The first iterative processing unit further includes a second iterative processing module; The second iterative processing module is used to determine the penalty factors corresponding to the multiple road segments of the recommended path based on their positions in the recommended path.

15. The apparatus according to any one of claims 12 to 14, wherein, The device includes a second iterative processing unit, which includes a third iterative processing module and a fourth iterative processing module. The third iterative processing module is used to construct a search tree from the starting node to the destination node, the search tree including N i There are N meeting points. i ≥n i The N i The meeting points are N points between the starting node and the destination node. i A path node on a path; The fourth iteration processing module is used to process N according to N i The travel cost corresponding to each path is used to determine the n... i One recommended path.

16. The apparatus according to claim 15, wherein, The third iterative processing module is specifically used for: Starting from the starting node and the destination node respectively, construct the search tree, and in the N nodes forming the search tree... i The search tree construction process ends when there are 10 encounter points.

17. The apparatus according to claim 15, wherein, The fourth iteration processing module includes a first iteration processing submodule and a second iteration processing submodule: The first iterative processing submodule is used for the N i For each path in the given path, the toll costs corresponding to multiple road segments of the path are summed to obtain the toll cost of the path. The second iterative processing submodule is used to process the N in ascending order of passage cost. i Sort the n paths and select the first n. i The path is used as n i One recommended path.

18. The apparatus according to any one of claims 12 to 14, wherein, The device further includes: The third iteration processing unit is used to stop the execution of the (i+1)th path generation process in response to the first triggering event; wherein... The first triggering event includes at least one of the following: i is greater than or equal to the preset number of iterations; The execution time is greater than or equal to the preset iteration time, the start time of the execution time is the start time of the first path generation process, and the end time of the execution time is the end time of the i-th path generation process. The total number of recommended paths generated in the previous i path generation processes is greater than or equal to the preset number of paths.

19. The apparatus according to any one of claims 12 to 14, wherein, The path generation unit includes a first path generation module; The first path generation module is used to generate the path in m path generation processes based on the merging parameters. The recommended paths are merged to obtain the M recommended paths.

20. The apparatus according to claim 19, wherein, The path generation unit further includes a second path generation module, which includes a first path generation submodule and a second path generation submodule. The first path generation submodule is used to determine whether the target area is a sparse road area based on a first ratio. The target area includes the starting node and the destination node. The first ratio is the ratio of the number of times the effective path generation process is performed to m. The second path generation submodule is used to correct the merging parameters when the target area is a sparsely roaded area.

21. The apparatus according to claim 20, wherein, The second path generation module includes a third path generation submodule: The third path generation submodule is used if n i The recommended path with the highest priority among the recommended paths, and the recommended path not generated in the first i-1 recommended path generation processes, are determined to be a valid path generation process.

22. The apparatus according to any one of claims 12 to 14, wherein, The path generation unit further includes a third path generation module; The third path generation module is used to identify burr regions in the M recommended paths and correct the burr regions.

23. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 11.

25. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images