Path planning method, device, electronic device, storage medium and program product

Abstract

The embodiments of the present application provide a path planning method, device, electronic device, storage medium and program product, which relate to the fields of navigation, Internet of Vehicles and map technology; and can be applied to related vehicle-mounted and map navigation scenarios. The method includes: obtaining starting point information and end point information, and determining the road section information corresponding to the starting point information and the end point information; based on the preset first index information, determining the candidate trajectory identifier corresponding to the road section information; based on the preset second index information, determining the candidate trajectory information corresponding to the candidate trajectory identifier; determining the target path information corresponding to the starting point information and the end point information in the candidate trajectory information; wherein the first index information and the second index information are established based on the thinned trajectory information, and the thinned trajectory information includes the key road section information retained after the thinning processing of the road section information matching the preset road network in the historical trajectory information. The implementation of the present application is conducive to improving the quality of path planning.

Description

Technical Field

[0001] The present application relates to the fields of navigation, vehicle networking and map technology. Specifically, the present application relates to a path planning method, device, electronic device, storage medium and program product. Background Art

[0002] With the rapid construction of roads and bridges and the rapid development of urban road planning, there are usually multiple travel routes for the same starting point and end point. Therefore, planning convenient travel routes for users has become a hot issue in the field of route planning.

[0003] In the prior art, due to the limitation of computer device memory and the large amount of historical trajectory data, if path planning is performed directly based on historical trajectory data, it is difficult to meet the memory and timeliness requirements of online services. Summary of the invention

[0004] The purpose of this application is to provide a path planning method, device, electronic device and storage medium that can meet the memory and timeliness requirements of online services. In order to achieve this purpose, the technical solutions provided in the embodiments of this application are as follows:

[0005] In one aspect, an embodiment of the present application provides a path planning method, the method comprising:

[0006] Acquire starting point information and end point information, and determine the road section information corresponding to the starting point information and end point information;

[0007] Based on the preset first index information, determining a candidate trajectory identifier corresponding to the road section information;

[0008] Based on the preset second index information, determining the candidate trajectory information corresponding to the candidate trajectory identifier;

[0009] Determining target path information corresponding to the starting point information and the end point information in the candidate trajectory information;

[0010] Among them, the first index information and the second index information are established based on the thinned trajectory information, the first index information represents the correspondence between each road section information and the candidate trajectory identifier, the second index information represents the correspondence between each candidate trajectory identifier and the candidate trajectory information, and the candidate trajectory information includes at least two road section information; the thinned trajectory information includes key road section information retained after thinning out the road section information matching the preset road network in the historical trajectory information.

[0011] In a feasible embodiment, the historical trajectory information is thinned out to obtain the thinned trajectory information, including:

[0012] Obtain some historical trajectory information of travel within a preset time period;

[0013] Determine a positioning point in the historical trajectory information based on at least one of time, distance, and trajectory landmarks;

[0014] Matching the positioning points in the historical trajectory information with the road section information in the preset road network to obtain matching trajectory information; wherein the preset road network is a topological map constructed with roads in the road map data as edges and intersections as nodes; the road section information in the preset road network includes information corresponding to each minimum segmentation unit in the topological map;

[0015] Based on a preset thinning strategy, the road section information included in the matching trajectory information is thinned to obtain thinned trajectory information retaining key road section information.

[0016] In a feasible embodiment, determining the positioning point in the historical trajectory information based on at least one of time, distance, and trajectory landmarks includes at least one of the following:

[0017] For each historical trajectory information, obtain the corresponding positioning point at a preset time interval;

[0018] For each historical trajectory information, the interval time for obtaining the positioning point is set based on the travel time of the historical trajectory information and the preset travel time, and the positioning point at the corresponding time is obtained once every interval time;

[0019] For each historical trajectory information, obtain the corresponding positioning point every preset distance;

[0020] For each historical track information, based on the entire length of the historical track information, a preset number of positioning points are obtained at equal intervals;

[0021] For each piece of historical trajectory information, a trajectory landmark is determined based on the attribute information of the historical trajectory information, and a corresponding positioning point is acquired based on the trajectory landmark; the attribute information represents the scene corresponding to the historical trajectory information.

[0022] In a feasible embodiment, matching the positioning point in the historical trajectory information with the road section information in the preset road network to obtain the matching trajectory information includes:

[0023] Position matching of the positioning points in the historical trajectory information with the road section information in the preset road network; the road section information includes the position information corresponding to each road section;

[0024] Perform the track segmentation operation on the historical track information that matches the road section information in the preset road network to obtain the matching track information:

[0025] The trajectory segmentation operation includes at least one of the following:

[0026] If the historical trajectory information includes at least two end point information, the historical trajectory information is divided based on the at least two end point information to obtain at least two segments of matching trajectory information;

[0027] If the historical trajectory information includes a stay point, the historical trajectory information is divided based on the stay point to obtain at least two segments of matching trajectory information; the stay point is a positioning point that stays at the same position for a preset time;

[0028] If the number of road section information included in the historical trajectory information is greater than a set number, the historical trajectory information is divided based on the set number to obtain at least two sections of matching trajectory information.

[0029] In a feasible embodiment, the thinning process based on the preset thinning strategy to obtain the thinned trajectory information retaining the key segment information includes at least one of the following:

[0030] Using the intersection information as a thinning factor, the matching trajectory information is thinned to obtain thinned trajectory information, so that the thinned trajectory information retains key section information corresponding to the intersection information;

[0031] Deleting the road section information that meets the preset target condition in the matching trajectory information to obtain the thinned trajectory information;

[0032] Among them, the preset target condition includes that the trajectory value corresponding to each road section information is less than the thinning target value; the thinning target value is the product of the average trajectory value corresponding to all road section information in the matching trajectory information and the thinning coefficient.

[0033] In a feasible embodiment, determining the target path information corresponding to the starting point information and the end point information in the candidate trajectory information includes:

[0034] Determine the number of historical adoptions corresponding to each candidate trajectory information;

[0035] Based on a preset number of candidate trajectory information with relatively large historical adoption times, target path information corresponding to the starting point information and the end point information is determined.

[0036] In a feasible embodiment, determining the target path information corresponding to the starting point information and the end point information in the candidate trajectory information includes:

[0037] Merging the candidate trajectory information including key road section information that is identical to a preset percentage or more;

[0038] Determining target path information corresponding to the starting point information and the end point information in the merged candidate trajectory information;

[0039] The merged processing includes at least one of the following:

[0040] For at least two candidate trajectory information with 100% identical key section information, only one candidate trajectory information is retained;

[0041] For at least two pieces of candidate trajectory information having the same key segment information exceeding a preset percentage, a new piece of candidate trajectory information is generated based on the union of the key segment information included in each piece of candidate trajectory information.

[0042] In a feasible embodiment, when the path planning method is applied to a terminal, obtaining the starting point information and the end point information includes:

[0043] In response to the route planning operation, obtaining the starting point information and the end point information input on the map interface;

[0044] After determining the target path information, the method further includes:

[0045] The target path information is displayed on the map interface.

[0046] In a feasible embodiment, if at least one of the starting point information and the end point information is dynamic information, at least one of the following is performed:

[0047] The steps of the path planning method are executed repeatedly at intervals of a preset loop duration until an instruction to exit the path planning is received;

[0048] Determine the distance between the starting point information and the end point information, and if it is detected that the change of the distance is greater than the preset distance, repeat the steps of the path planning method.

[0049] On the other hand, an embodiment of the present application provides a path planning device, the device comprising:

[0050] An acquisition module, used to acquire starting point information and end point information, and determine the road section information corresponding to the starting point information and end point information;

[0051] A first determination module, configured to determine a candidate trajectory identifier corresponding to the road section information based on preset first index information;

[0052] A second determination module, configured to determine the candidate trajectory information corresponding to the candidate trajectory identifier based on preset second index information;

[0053] A path determination module, used to determine target path information corresponding to the starting point information and the end point information in the candidate trajectory information;

[0054] Among them, the first index information and the second index information are established based on the thinned trajectory information, the first index information represents the correspondence between each road section information and the candidate trajectory identifier, the second index information represents the correspondence between each candidate trajectory identifier and the candidate trajectory information, and the candidate trajectory information includes at least two road section information; the thinned trajectory information includes key road section information retained after thinning out the road section information matching the preset road network in the historical trajectory information.

[0055] In a feasible embodiment, the path planning device further includes a preprocessing module, which is used to perform thinning processing on the historical trajectory information to obtain the thinned trajectory information, including:

[0056] Obtain some historical trajectory information of travel within a preset time period;

[0057] Determine a positioning point in the historical trajectory information based on at least one of time, distance, and trajectory landmarks;

[0058] Matching the positioning points in the historical trajectory information with the road section information in the preset road network to obtain matching trajectory information; wherein the preset road network is a topological map constructed with roads in the road map data as edges and intersections as nodes; the road section information in the preset road network includes information corresponding to each minimum segmentation unit in the topological map;

[0059] Based on a preset thinning strategy, the road section information included in the matching trajectory information is thinned to obtain thinned trajectory information retaining key road section information.

[0060] In a feasible embodiment, the preprocessing module is used to determine the positioning point in the historical trajectory information based on at least one of time, distance and trajectory landmarks, and is specifically used for at least one of the following:

[0061] For each historical trajectory information, obtain the corresponding positioning point at a preset time interval;

[0062] For each historical trajectory information, the interval time for obtaining the positioning point is set based on the travel time of the historical trajectory information and the preset travel time, and the positioning point at the corresponding time is obtained once every interval time;

[0063] For each historical trajectory information, obtain the corresponding positioning point every preset distance;

[0064] For each historical track information, based on the entire length of the historical track information, a preset number of positioning points are obtained at equal intervals;

[0065] For each piece of historical trajectory information, a trajectory landmark is determined based on the attribute information of the historical trajectory information, and a corresponding positioning point is acquired based on the trajectory landmark; the attribute information represents the scene corresponding to the historical trajectory information.

[0066] In a feasible embodiment, the preprocessing module is used to match the positioning points in the historical trajectory information with the road section information in the preset road network, and when the matching trajectory information is obtained, it is specifically used to:

[0067] Position matching of the positioning points in the historical trajectory information with the road section information in the preset road network; the road section information includes the position information corresponding to each road section;

[0068] Perform the track segmentation operation on the historical track information that matches the road section information in the preset road network to obtain the matching track information:

[0069] The trajectory segmentation operation includes at least one of the following:

[0070] If the historical trajectory information includes at least two end point information, the historical trajectory information is divided based on the at least two end point information to obtain at least two segments of matching trajectory information;

[0071] If the historical trajectory information includes a stay point, the historical trajectory information is divided based on the stay point to obtain at least two segments of matching trajectory information; the stay point is a positioning point that stays at the same position for a preset time;

[0072] If the number of road section information included in the historical trajectory information is greater than a set number, the historical trajectory information is divided based on the set number to obtain at least two sections of matching trajectory information.

[0073] In a feasible embodiment, when the preprocessing module is used to execute the preset thinning strategy to perform thinning processing on the road section information included in the matching trajectory information to obtain the thinned trajectory information retaining the key road section information, it is also used for at least one of the following:

[0074] Using the intersection information as a thinning factor, the matching trajectory information is thinned to obtain thinned trajectory information, so that the thinned trajectory information retains key section information corresponding to the intersection information;

[0075] Deleting the road section information that meets the preset target condition in the matching trajectory information to obtain the thinned trajectory information;

[0076] Among them, the preset target condition includes that the trajectory value corresponding to each road section information is less than the thinning target value; the thinning target value is the product of the average trajectory value corresponding to all road section information in the matching trajectory information and the thinning coefficient.

[0077] In a feasible embodiment, the path determination module is used to determine the target path information corresponding to the starting point information and the end point information in the candidate trajectory information, specifically for:

[0078] Determine the number of historical adoptions corresponding to each candidate trajectory information;

[0079] Based on a preset number of candidate trajectory information with relatively large historical adoption times, target path information corresponding to the starting point information and the end point information is determined.

[0080] In a feasible embodiment, the path determination module is used to determine the target path information corresponding to the starting point information and the end point information in the candidate trajectory information, specifically for:

[0081] Merging the candidate trajectory information including key road section information that is identical to a preset percentage or more;

[0082] Determining target path information corresponding to the starting point information and the end point information in the merged candidate trajectory information;

[0083] The merged processing includes at least one of the following:

[0084] For at least two candidate trajectory information with 100% identical key section information, only one candidate trajectory information is retained;

[0085] For at least two pieces of candidate trajectory information having the same key segment information exceeding a preset percentage, a new piece of candidate trajectory information is generated based on the union of the key segment information included in each piece of candidate trajectory information.

[0086] In a feasible embodiment, when the path planning method is applied to a terminal, the acquisition module is used to execute the acquisition of the starting point information and the end point information, specifically for:

[0087] In response to the route planning operation, obtaining the starting point information and the end point information input on the map interface;

[0088] After being used to determine the target path information, the path determination module is also used to:

[0089] The target path information is displayed on the map interface.

[0090] In a feasible embodiment, if at least one of the starting point information and the end point information is dynamic information, the device further includes an execution module, configured to execute at least one of the following:

[0091] The steps of the path planning method are executed repeatedly at intervals of a preset loop duration until an instruction to exit the path planning is received;

[0092] Determine the distance between the starting point information and the end point information, and if it is detected that the change of the distance is greater than the preset distance, repeat the steps of the path planning method.

[0093] In another aspect, the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is used to execute the method provided in any optional embodiment of the present application when running the computer program.

[0094] On the other hand, the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program runs in a processor, the processor is used to execute the method provided in any optional embodiment of the present application.

[0095] On the other hand, the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method provided in any optional embodiment of the present application.

[0096] The beneficial effects of the technical solution provided by this application are:

[0097] The path planning method provided by the embodiment of the present application, in the online service of path planning, after obtaining the starting point information and the end point information, the road section information corresponding to the starting point information and the end point information can be determined, that is, the determined road section information includes the starting point information and the end point information; then, the candidate trajectory identifier corresponding to the road section information can be determined based on the preset first index information, and the candidate trajectory information corresponding to the candidate trajectory identifier can be determined based on the preset second index information; so far, in order to meet the timeliness and real-time requirements of the online service, the present application pre-establishes a trajectory index (first index information and second index information), wherein the first index information represents the correspondence between each road section information and the candidate trajectory identifier, and the candidate trajectory identifier corresponding to the road section information corresponding to the starting point information and the end point information can be quickly screened out through the first index information; the second index information represents the correspondence between each candidate trajectory identifier and the candidate trajectory information, and the candidate trajectory information corresponding to the candidate trajectory identifier can be quickly screened out through the second index information (each candidate trajectory information includes at least two road section information), that is, the efficiency of querying the candidate trajectory information is improved through the trajectory index; then, the present application can determine the target path information corresponding to the starting point information and the end point information in the determined candidate trajectory information. Among them, the first index information and the second index information are both established based on the thinned trajectory information, and the thinned trajectory information includes the key section information retained after the thinning processing of the section information in the historical trajectory information that matches the preset road network. The thinning processing of the historical trajectory information in this application can effectively reduce the data storage volume of the historical trajectory information, and is also beneficial to reduce the subsequent calculation amount for determining the target path information, and at the same time, it is beneficial to improve the quality of path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0099] Figure 1 A schematic diagram of a flow chart of a path planning method provided in an embodiment of the present application;

[0100] Figure 2a A schematic diagram of a system processing flow provided in an example of the present application;

[0101] Figure 2b This is another schematic diagram of a system processing flow provided in an example of the present application;

[0102] Figure 3 A schematic diagram of a data structure of an inverted index provided in an example of the present application;

[0103] Figure 4 A schematic diagram of a data structure of a forward index provided in an example of the present application;

[0104] Figure 5 A schematic diagram of a trajectory processing flow provided in an example of the present application;

[0105] Figure 6 A schematic diagram of another trajectory processing flow provided in an example of the present application;

[0106] Figure 7 A schematic diagram of a scenario provided in an example of this application;

[0107] Figure 8 A schematic diagram of a process of ignoring minor intersections provided in an example of the present application;

[0108] Fig. 9 This is another scenario schematic diagram provided in an example of this application;

[0109] Fig.10 This is another scenario diagram provided in an example of the present application;

[0110] Fig.11 For Fig.10 Schematic diagram of the scene corresponding to route 1;

[0111] Fig.12 For Fig.10 Schematic diagram of the scene corresponding to middle route 2;

[0112] Fig.13 This is another scenario schematic diagram provided in an example of the present application;

[0113] Fig.14 A schematic diagram of an operating environment provided for an embodiment of the present application;

[0114] Fig.15 A schematic diagram of the structure of a path planning device provided in an embodiment of the present application;

[0115] Fig.16 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0116] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

[0117] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0118] The present application is to address the problems in existing path planning solutions, such as large storage volume of historical data, long query time, and inability to meet the timeliness requirements of online services. A path planning method, device, equipment, storage medium and program product are proposed. Based on the implementation of this solution, the problem of memory limitation can be effectively solved and the timeliness requirements of online services can be met.

[0119] The scheme of the embodiment of the present application involves an intelligent transportation system, such as in driving navigation, logistics transportation, food delivery, online car-hailing and other scenarios. Based on the scheme of the embodiment of the present application, the quality of path planning in each scenario can be improved. For example, in the driving navigation scenario, it is helpful to assist users to choose a suitable travel route faster and better. Among them, the intelligent transportation system (Intelligent Traffic System, ITS), also known as the intelligent transportation system (Intelligent Transportation System), is to effectively and comprehensively apply advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) to transportation, service control and vehicle manufacturing, strengthen the connection between vehicles, roads and users, and thus form a comprehensive transportation system that ensures safety, improves efficiency, improves the environment and saves energy.

[0120] The solution of the embodiment of the present application also involves artificial intelligence technology, such as mining historical trajectory information through artificial intelligence technology to achieve preprocessing of historical trajectory information. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science, which attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that the machines have the functions of perception, reasoning and decision-making. Artificial intelligence technology is a comprehensive discipline that involves a wide range of fields, including both hardware-level technology and software-level technology. Basic artificial intelligence technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, large path planning technology, operation / interaction systems, and mechatronics. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning, autonomous driving, and smart transportation.

[0121] Optionally, the data involved in the path planning method provided by the present application (such as the first index information, the second index information, the thinned trajectory information, the historical trajectory information, etc.) can be stored in the blockchain. The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain is essentially a decentralized database. It is a string of data blocks generated by cryptographic methods. Each data block contains a certain amount of processed data for verifying the validity of its information (anti-counterfeiting) and generating the next block. The blockchain may include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0122] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0123] Figure 1A flow chart of a path planning method provided by an embodiment of the present application is shown, and the method can be executed by any electronic device, such as a user terminal, which can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted device, etc. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0124] The following synchronous combination Figure 2a and Figure 2b , the path planning method provided in the embodiment of the present application is described.

[0125] Among them, Figure 2a As shown in FIG. 1 , what is implemented in the overall architecture of the system is big data analysis (analysis of large-scale data), such as data mining algorithms (Data Mining Algorithms) for visual data (such as map data with travel trajectory information that can be displayed in the user interface) to dig deep into the data and mine valuable historical trajectory information, and then use preset tools or strategies to analyze the historical trajectory information and determine N (N is greater than or equal to 1) target paths corresponding to the starting point and end point input by the current user. Among them, after successfully mining the historical trajectory information, the historical trajectory information can also be stored, such as storing it in a specific mode and establishing a corresponding database (such as a relational database) to provide data extraction, query, access and other operation interfaces for some subsequent intelligent service systems.

[0126] Specifically, Figure 2b As shown, the present application can establish first index information and second index information based on historical trajectory information, and then analyze candidate trajectory information corresponding to the starting point and end point currently input by the user based on the two pre-established index information, so as to determine the final N (N is greater than or equal to 1) target paths in the candidate trajectory information.

[0127] Specifically, Figure 1 As shown in , the path planning method provided in the embodiment of the present application may include the following steps S110 to S140.

[0128] Step S110: Acquire the starting point information and the end point information, and determine the road section information corresponding to the starting point information and the end point information.

[0129] The starting point information is the starting point information of the route. For example, for a driving scenario, the starting point information can be the location information corresponding to the starting point of the driving trip (such as GPS positioning information); for a food delivery scenario, the starting point information can be the location information of the merchant or the current location information of the rider. The end point information is the end point information of the route. For example, for a driving scenario, the end point information can be the location information corresponding to the destination of the driving trip; for a food delivery scenario, the end point information can be the location information specified by the ordering user.

[0130] Among them, the road section link is the smallest segmentation unit in the preset road network. Generally speaking, the road network of a country or region can be divided into hundreds of millions of road sections. The road section information may include the road section identification (also known as the road section number) linkid, the location information corresponding to the road section, the road section sequence, etc. The road section information corresponding to the starting point information and the end point information can be understood as including the starting point information and the end point information in the same road section information, or the starting point information and the end point information correspond to different road section information respectively; optionally, the beginning position and the end position of the road section do not necessarily correspond to the starting point information and the end point information. It can be understood that since the amount of historical trajectory information stored is relatively large, the road section information corresponding to the starting point information and the end point information may include multiple pieces.

[0131] Among them, the preset road network can be a topological map constructed based on road map data, in which roads are edges and intersections are nodes; therefore, road sections can be divided based on at least one of roads and intersections, and each road section corresponds to each segmentation unit.

[0132] Optionally, the starting point information and the end point information can be information of different states to adapt to different scenarios, such as static information or dynamic information. For example, in scenarios such as map navigation, food delivery, and logistics, the starting point information and the end point information can be static information; in a wedding car-following scenario, the starting point information can be the real-time positioning information of the first-ranked leading car, and the end point information can be the real-time positioning information of the current driving vehicle; in a location sharing scenario (at least two users enter the same map navigation page, can view the real-time location of other users to adjust the user's own direction of travel, and realize that all users are gathered at a certain location), the starting point information can be the user's own real-time positioning information, and the end point information can be the real-time positioning information of other users who enter the location sharing.

[0133] Step S120: Based on the preset first index information, determine the candidate trajectory identifier corresponding to the road section information.

[0134] The first index information represents the corresponding relationship between each road segment information and the candidate trajectory identifier, specifically, Figure 3 As shown, the first index information can record the index information in an inverted index data structure; wherein the inverted index (inverted index) determines the location of the record by the attribute value. In the embodiment of the present application, the first index information can be used to query the track identifier (preset track number) corresponding to each road section information based on the road section information (such as the road section identifier); Figure 3 As shown, the same road segment identifier can correspond to multiple track identifiers. When there are M road segment identifiers, there will be M track identifiers. It can be understood that the track identifier corresponding to the road segment information obtained through the first index information can constitute a candidate track identifier. Since the corresponding track identifier can include multiple ones, the concept of set can be used to understand the candidate track identifier.

[0135] Step S130: Determine the candidate trajectory information corresponding to the candidate trajectory identifier based on the preset second index information.

[0136] The second index information represents the corresponding relationship between each candidate trajectory identifier and the candidate trajectory information, such as Figure 4 As shown, the second index information can record the index information in a forward index data structure; wherein the forward index is obtained by querying the known identifier id. In the embodiment of the present application, through the second index information, the segment identifier (generally speaking, including at least two segment identifiers) included in the trajectory corresponding to each candidate trajectory identifier can be queried based on the trajectory identifier trajid, that is, the candidate trajectory information refers to the segment identifier sequence corresponding to each candidate trajectory. It can be understood that the total candidate trajectory information corresponding to the candidate trajectory identifier includes multiple candidate trajectories (such as when each candidate trajectory identifier corresponds to a candidate trajectory, when there are multiple candidate trajectory identifiers, there are correspondingly multiple candidate trajectories), so the concept of a set can be used to understand the candidate trajectory information.

[0137] Step S140: determining target path information corresponding to the starting point information and the end point information in the candidate trajectory information.

[0138] Specifically, target path information equal to the preset number can be determined in the candidate trajectory information. For example, in an online application, the user sets the display of 2 target path information each time, and then the road segment identification sequences corresponding to two candidate trajectories can be selected in the candidate trajectory information to respectively construct the corresponding target path information.

[0139] The first index information and the second index information are established based on the thinned trajectory information; the thinned trajectory information includes key section information retained after thinning out the section information matching the preset road network in the historical trajectory information.

[0140] Among them, thinning processing refers to the data processing process of minimizing the number of data points by adopting certain set rules while ensuring that the meaning of data representation remains unchanged. In the embodiment of the present application, since a trajectory may contain multiple road section information that is not very important or has a large repetitiveness, it is possible to obtain thinned trajectory information that only retains key road section information by thinning out several road section information that matches the preset road network in the historical trajectory information, so as to greatly reduce the amount of data required to be stored and reduce the amount of calculation in subsequent steps while ensuring that the difference in meaning represented by the obtained thinned trajectory information and the historical trajectory information is within an acceptable range.

[0141] The specific process of preprocessing the historical trajectory information in the embodiment of the present application is described below. Optionally, the preprocessing process can be a periodic, one-time or real-time implementation process, wherein periodicity refers to preprocessing the historical trajectory information once at a certain interval, and updating the pre-established data (such as the preset first index information and the preset second index information) used when the online service is updated; one-time refers to completing the preprocessing of the currently stored historical trajectory information once when the solution is launched, and the pre-established data used when the online service is no longer updated subsequently; real-time refers to the preprocessing of the historical trajectory information in real time as new historical trajectory information is continuously acquired over time, and the pre-established data used when the online service is updated in real time. The preprocessing process of the embodiment of the present application can be selected from the periodic, one-time and real-time implementation processes based on actual needs, and the present application does not limit this.

[0142] In a feasible embodiment, the historical trajectory information is thinned out to obtain the thinned trajectory information, including the following steps A1-A4:

[0143] Step A1: Obtain historical trajectory information for a preset time period;

[0144] Step A2: determining a positioning point in the historical trajectory information based on at least one of time, distance and trajectory landmarks;

[0145] Step A3: matching the positioning points in the acquired historical trajectory information with the road section information in the preset road network to obtain matching trajectory information;

[0146] Step A4: Based on a preset thinning strategy, the matching trajectory information is thinned to obtain thinned trajectory information.

[0147] Specifically, Figure 5 As shown, the embodiment of the present application can obtain multiple historical trajectory information of multiple users, and then access the positioning point (such as GPS point) of the historical trajectory information, and for each historical trajectory information, match the GPS point on the corresponding trajectory with the preset road network segment link to obtain matching trajectory information in which the positioning point and the segment information have a matching relationship.

[0148] Among them, considering the limitations of computer device memory, data processing volume, and the relevance of reference data to actual needs, the historical trajectory information that can be reached can be set based on time. Specifically, the historical trajectory information obtained can be the full amount of historical trajectory information generated after the platform is launched, that is, the preset time can be set from the moment the platform is launched to the current moment of path planning; in addition, considering that there are updates to road map data (such as changes in road imports and exports, the establishment of highways, etc.), in order to effectively improve the accuracy of the planned path, the historical trajectory information of a recent period can be screened for processing, such as setting the preset time period to the most recent year. If the time for path planning is January 1, 2022, the historical trajectory information stored in the time period from January 1, 2021 to December 31, 2021 can be obtained.

[0149] Among them, regarding the mining processing of positioning points in historical trajectory information, corresponding GPS points can be constructed according to the trajectory line, which can be implemented in at least one of the following ways:

[0150] (1) Constructing positioning points based on time points

[0151] For each historical track information, obtain the corresponding positioning point every preset time. Specifically, set to obtain the location information every preset time, and construct the positioning point on the historical track based on the obtained location information. For example, you can set to obtain the location information every 3 minutes, then the historical track that takes 30 minutes will correspond to 10 positioning points.

[0152] For each historical trajectory information, the interval time for obtaining the positioning point is set based on the travel time of the historical trajectory information and the preset time, and the positioning point of the corresponding time is obtained every the interval time. Specifically, the time point for obtaining the location information is set based on the time (travel time) taken to complete the entire trajectory. The longer the time taken, the longer the interval time for obtaining the location information; for example, for a historical trajectory that takes 50 minutes to complete, the location information can be obtained every 5 minutes; for a historical trajectory that takes 127 minutes to complete, the location information can be obtained every 10 minutes. When setting, the entire time consumption can be processed in sections. If it is less than or equal to the first time consumption (preset time consumption), the first interval time is set; if it is greater than the first time consumption but less than or equal to the second time consumption (preset time consumption), the second interval time is set; if it is greater than the second time consumption, the third interval time is set; wherein, the first time consumption is less than the second time consumption; accordingly, the first interval time is less than the second interval time, and the second interval time is less than the third interval time.

[0153] (2) Constructing positioning points based on distance

[0154] For each historical track information, the corresponding positioning point is obtained every preset distance. Specifically, it is set to obtain the position information every preset distance, and the positioning point on the historical track is constructed based on the obtained position information. For example, it can be set to obtain the position information every 10 kilometers, so the historical track of 177 kilometers will correspond to 18 positioning points (if the distance to the last positioning point is less than 10 kilometers, the end point will be taken as the last positioning point).

[0155] For each historical track information, based on the entire length of the historical track information, a preset number of positioning points are obtained at equal intervals. Specifically, a specific number of positioning points are created at equal intervals. For example, if only 10 (preset value) positioning points are obtained for a historical track, then for a historical track of 32 kilometers, location information can be obtained every 3.2 kilometers.

[0156] (3) Constructing positioning points based on trajectory landmarks

[0157] For each historical trajectory information, a trajectory landmark is determined based on the attribute information of the historical trajectory information, and a corresponding positioning point is obtained based on the trajectory landmark; the attribute information represents the scene corresponding to the historical trajectory.

[0158] For example, for a driving scenario, it is set to obtain location information every time the vehicle passes through an intersection, traffic light, electronic eye, etc., and construct a positioning point on the historical trajectory based on the obtained location information. That is, the trajectory landmarks may include intersections, traffic lights, electronic eyes, etc.

[0159] For example, for food delivery scenarios, it is set to obtain location information every time the location of a merchant with a delivery frequency higher than a set value and the location of the user who placed the order passes by, and construct a positioning point on the historical track based on the obtained location information. That is, the track landmarks can include the location of the merchant with a delivery frequency higher than the set value and the location of the user who placed the order.

[0160] For example, for logistics scenarios, it is set to obtain location information every time the name of the road is changed, such as when entering National Highway 2 from National Highway 1, and construct the positioning point on the historical track based on the obtained location information. That is, the track sign includes the name of the road.

[0161] Optionally, the processing of access trajectory GPS points can also be implemented using a pre-built AI model, and the collected historical trajectory information is input into the AI ​​model, which then completes the mining of positioning points.

[0162] In the embodiment of the present application, considering that the amount of original historical trajectory information is very large, if it is directly stored, the amount of trajectory data required to be stored is very large, and due to memory limitations, it is not conducive to sustainable development. Therefore, the embodiment of the present application proposes a method for matching trajectory information by thinning (that is, a preset thinning strategy), and only retains the key section information in the matching trajectory information.

[0163] Optionally, in step A4, based on a preset thinning strategy, thinning the road section information included in the matching trajectory information to obtain thinned trajectory information retaining key road section information includes at least one of the following steps A21-A22:

[0164] Step A21: using the intersection information as a thinning factor, performing thinning processing on the matching trajectory information to obtain thinned trajectory information, so that the thinned trajectory information retains key section information corresponding to the intersection information.

[0165] Specifically, when making a map road network, the road link may be interrupted by factors such as intersections, electronic eyes, traffic lights, and traffic signs. However, for path planning, the main factor affecting path planning is the intersection, and the interruption of the road link caused by factors such as electronic eyes, traffic lights, and traffic signs (that is, dividing a road section into two sections) does not affect path planning in actual travel. Therefore, the embodiment of the present application performs thinning processing on the matching trajectory information. In the road network topology, if Figure 7As shown, from section A to section C, it corresponds to the route A to B to C. At this time, deleting section B will not have any effect on the path planning. Therefore, the intersection information can be used as a thinning factor. If there are other sections (such as B) from section A to section C and they correspond to non-intersection information, section B can be deleted. For the matching trajectory information, the original sections A, B and C are thinned into thinned trajectory information including only key sections A and C. From section D to section F, it corresponds to the route D to E to F. Since section E corresponds to the intersection information, the results before and after the thinning process for the matching trajectory information remain unchanged (the section information corresponding to section E will not be deleted).

[0166] Step A22: deleting the road section information that meets the preset target condition in the matching trajectory information to obtain the thinned trajectory information.

[0167] Among them, the preset target condition includes that the trajectory value corresponding to each road section information is less than the thinning target value; the thinning target value is the product of the average trajectory value corresponding to all road section information in the matching trajectory information and the thinning coefficient.

[0168] Specifically, Figure 8 As shown, the embodiment of the present application provides a thinning strategy for ignoring minor intersections, which can retain key backbone road section information while ignoring minor intersections to effectively reduce the amount of data storage. Figure 8 To explain:

[0169] Number of trajectories < sum(link_1, link_2, ..., link_n) / n*alpha

[0170] ......Formula (1)

[0171] In formula (1), the number of trajectories is the trajectory value corresponding to each segment information, n is the number of segments included in each matching trajectory information, sum(link_1, link_2, ..., link_n) is the sum of the trajectory values ​​corresponding to all segments in the matching trajectory information, and alpha is the thinning coefficient.

[0172] The trajectory value refers to how many trajectory information the road section information corresponds to, which can be determined by a pre-established index. For example, in the first index information, the road section link_1 corresponds to 42 trajectory identifiers trajid.

[0173] like Figure 8 As shown, Figure 8 The road section 3 shown by the dotted line on the left is the object that needs to be deleted after processing in step A3. Assuming that the thinning coefficient is 0.2, Figure 8The segment information shown on the left side has a trajectory value of 1000 for segment 1, 999 for segment 2, and 1 for segment 3. The thinning target value is (1000+999+1) / 3*0.2=133 (rounded). It can be seen that only the trajectory value of segment 3 is less than the thinning target value. Therefore, the segment information corresponding to segment 3 is deleted from the matching trajectory information (that is, the segment information corresponding to segments 1 and 2 in the matching trajectory information is the key segment information).

[0174] like Figure 8 As shown, Figure 8 The result on the right indicates that there are no objects that need to be deleted. Assuming the thinning coefficient is 0.2, then for Figure 8 The section information shown on the right has a track value of 1000 for section 4, 700 for section 5, and 300 for section 6. The thinning target value is (1000+700+300) / 3*0.2=133 (rounded). It can be seen that the track values ​​of sections 4, 5, and 6 are all greater than the thinning target value, so there is no need to delete the section information included in the matching track information (that is, the section information included in the matching track information is all key section information).

[0175] Optionally, the thinning coefficient can be determined according to actual needs. The 0.2 in the above example is used for Figure 8 The information shown is for illustrative purposes only and is not intended to be limiting in this application.

[0176] It can be understood that step A21 and step A22 can be steps implemented in parallel, such as only implementing step A21 or only implementing step A22; or they can be steps implemented progressively, such as first implementing step A21 and then implementing step A22, or first implementing step A22 and then implementing step A21.

[0177] In the embodiments of the present application, Fig. 9 As shown, after the thinning process, for each matching trajectory information, only the key section information corresponding to the intersection information is retained, and the section information corresponding to the non-intersection information can be deleted or merged, so as to greatly simplify the historical trajectory information, reduce the storage volume of historical trajectory data, improve the efficiency of subsequent data query, and reduce the time consumption of data query.

[0178] In a possible embodiment, if Figure 6 As shown, in step A1, the positioning point in the acquired historical trajectory information is matched with the road section information in the preset road network to obtain the matching trajectory information, including the following steps A11-A12:

[0179] Step A11: Positionally match the positioning points in the historical trajectory information with the road section information in the preset road network; wherein the road section information includes the position information corresponding to each road section.

[0180] Specifically, the position matching of the positioning point and the road section information includes constructing a mapping relationship between the positioning point and the road section information, and the corresponding road section information can be found through the positioning point. The mapping relationship is established based on the position information represented by the positioning point and the position information included in the road section information.

[0181] Step A12: Perform a track segmentation operation on the historical track information that matches the road segment information in the preset road network to obtain matching track information. Specifically, Figure 6 As shown, after the GPS point is matched to the road section information of the road network, the trajectory can also be interrupted considering that the same trajectory may contain multiple trips.

[0182] The track segmentation operation includes at least one of the following steps A121-A123:

[0183] Step A121: if the historical trajectory information includes at least two end point information, the historical trajectory information is divided based on the at least two end point information to obtain at least two segments of matching trajectory information.

[0184] Specifically, in some scenarios, if two places need to be reached in the same travel trajectory, there are usually two end point information; for example, in the family's daily travel, the father drives to work, and for convenience he first sends his son to kindergarten, then sends his grandfather to the park for playing chess, and finally arrives at the company. At this time, the same travel trajectory will include three end points, the son's kindergarten, the grandfather's park, and the father's company. At this time, the travel trajectory can be divided into three travel trajectories, such as home-kindergarten, kindergarten-park, and park-company, and finally three matching trajectory information is obtained.

[0185] For example, in an online car-hailing scenario, when multiple users carpool, the same travel trajectory will correspond to multiple travel destinations and multiple travel orders. The historical trajectory information can be divided based on the destination information and / or order status, so that the same section of historical trajectory information that is matched with the road section information in the preset road network can be divided into at least two sections of matching trajectory information.

[0186] Optionally, for the online car-hailing scenario, if travel order 1 is from starting point A to end point B, and travel order 2 is from starting point C to end point D, since the road overlap rate of the two travel orders is higher than a preset percentage, the same online car-hailing vehicle can receive two travel orders at the same time (i.e., user carpooling), but for the travel trajectory of the same carpooling, only one historical trajectory information may be uploaded. Therefore, if there are two end point information (end point B and end point D) in the same historical trajectory information, the historical trajectory information can be divided into matching trajectory information 1 (corresponding to travel order 1, the travel trajectory is from position A to position B) and matching trajectory information 2 (corresponding to travel order 2, the travel trajectory is from position C to position D) based on the two end point information.

[0187] Step A122: If the historical trajectory information includes a stay point, the historical trajectory information is divided based on the stay point to obtain at least two segments of matching trajectory information; the stay point is a positioning point that stays at the same position for a preset time.

[0188] Specifically, the principle of implementing step A122 is to interrupt the trajectory based on the timestamp. For example, in the same travel trajectory, there is a point that has not changed for a long time. The actual scene may be waiting for someone or taking a rest. Therefore, when staying at the same location for a preset time, the positioning point can be regarded as a stay point, and the historical trajectory information can be divided based on the stay point to obtain at least two matching trajectory information segments.

[0189] Step A123: If the number of road segment information included in the historical trajectory information is greater than a set number, the historical trajectory information is divided based on the set number to obtain at least two segments of matching trajectory information.

[0190] Specifically, considering that some long-distance travel situations are not conducive to data analysis, for example, if long-distance historical trajectory information is used for route planning for short-distance travel, the resources consumed are too large; considering this problem, the embodiment of the present application can also control the number of road section information included in the matching trajectory information. For example, when it is detected that the historical trajectory information A includes 321 road section information, and the set number is 150, the historical trajectory information can be divided into matching trajectory information A1 (including the first 150 road section information), matching trajectory information A2 (including road section information ranked from 151st to 300th, a total of 150 road section information) and matching trajectory information A3 (including road section information ranked from 301st to 321st).

[0191] In the embodiment of the present application, the process of executing the trajectory interruption is as follows: Figure 5 In terms of the effect, further analysis of the same historical trajectory can deepen the mining of historical trajectory information and improve the accuracy of path planning based on historical trajectory information.

[0192] The following describes a specific process of determining target path information corresponding to the starting point information and the end point information in the candidate trajectory information in an embodiment of the present application.

[0193] In a possible embodiment, if Fig.10 , Fig.11 and Fig.12 As shown, in step S140, determining the target path information corresponding to the starting point information and the end point information in the candidate trajectory information includes the following steps B1-B2:

[0194] Step B1: Determine the number of historical adoptions corresponding to each candidate trajectory information.

[0195] Step B2: determining target path information corresponding to the starting point information and the end point information based on a preset number of candidate trajectory information with relatively large historical adoption times.

[0196] Specifically, Fig.10 As shown, there are Route 1 and Route 2 when planning the path. Fig.10 As shown in the results, when reaching the end point A, the distance of route 1 is shorter, so it is theoretically better to choose route 1 as the target path for planning. Fig.11 and Fig.12 Come and see, Fig.11 (corresponding to route 1) The parked vehicles on both sides occupy part of the road, making it difficult to pass each other; Fig.12 The vehicles parked on both sides (corresponding to Route 2) do not affect the normal driving of vehicles on the road. Relatively speaking, in actual street scenes, the time taken to reach the end point A from Route 2 is generally less than the time taken to reach the end point A from Route 1. In this regard, the embodiment of the present application can determine the final target path information in combination with the number of historical adoptions corresponding to each candidate trajectory information. For example, when the candidate trajectory information includes Route 1 and Route 2, the historical adoption times of Route 1 obtained are 741 times, and the historical adoption times of Route 2 are 6452 times. It is obvious that in the historical trajectory data, more users choose Route 2. Therefore, the candidate trajectory information with a larger number of historical adoptions can be selected to construct the final target path information, that is, the target path information corresponding to the starting point information and the end point information is determined based on the candidate trajectory information corresponding to Route 2.

[0197] The number of historical adoptions can be determined by the number of times the corresponding trajectory exists in the historical trajectory information.

[0198] Optionally, since the candidate trajectory information may include multiple pieces, that is, it may correspond to multiple candidate trajectories, when determining the final target path information, the preset number of candidate trajectory information to be used may be determined in combination with the number of target paths that need to be presented in the end. For example, if the current setting is to output N (preset number) pieces of target path information in the final path planning, and the candidate trajectory information includes K pieces, the candidate trajectory information may be sorted in descending order based on the number of historical adoptions corresponding to each candidate trajectory information (the number of historical adoptions is sorted from high to low), and the N candidate trajectory information in the top order is obtained to determine the final N pieces of target path information; wherein K is greater than or equal to N; that is, the N pieces of candidate trajectory information with the highest number of historical adoptions are selected from the M candidate trajectory information as the data basis for finally determining the target path information.

[0199] In the embodiment of the present application, by implementing steps B1 and B2, the historical adoption times contained in the historical trajectory information can be further mined, so as to further optimize the determined target path information based on the historical adoption times of the trajectory, improve the quality of the planned path, and improve the user experience.

[0200] In a feasible embodiment, determining the target path information corresponding to the starting point information and the end point information in the candidate trajectory information in step S140 includes the following steps C1-C2:

[0201] Step C1: merging the candidate trajectory information including key road section information that is identical to a preset percentage or more.

[0202] Step C2: determining the target path information corresponding to the starting point information and the end point information in the merged candidate trajectory information.

[0203] In an embodiment of the present application, in order to improve the quality of the planned path and reduce the amount of calculation, the candidate trajectory information can be merged, such as merging the same or similar candidate trajectories. Among them, whether the candidate trajectory information is the same and how large the percentage of the same can be determined based on the similarity calculation of the key section information. For example, when candidate trajectory information 1 and candidate trajectory information 2 include 10 key section information, if there are 5 key section information that are consistent between the two, then the two are 50% the same.

[0204] The merging process in step C1 includes at least one of the following steps C11-C12:

[0205] Step C11: For at least two candidate trajectory information whose key section information is 100% identical, only one candidate trajectory information is retained.

[0206] Step C12: for at least two candidate trajectory information whose key segment information is identical by more than a preset percentage, generate a new candidate trajectory information based on the union of the key segment information included in each candidate trajectory information.

[0207] If the key section information included in any two candidate trajectory information is exactly the same, the merge process can be to retain only one of the candidate trajectory information. For example, if candidate trajectory information 1 includes 27 key section information, and candidate trajectory information 2 includes 27 key section information, and all the key section information of the two are the same, then one of the candidate trajectory information can be deleted at will.

[0208] Among them, if the percentage of key section information included in any two candidate trajectory information is the same as that of a preset percentage, the merging can be to take the union of the key section information included in the two candidate trajectory information, and generate a candidate trajectory information corresponding to the two candidate trajectory information based on the union. For example, candidate trajectory information 1 includes 10 key section information, and candidate trajectory information 2 also includes 10 key section information, and there are 8 key section information that are consistent between the two, and the percentage of the same has reached a preset percentage, then the candidate trajectory information 1 and the candidate trajectory information 2 are finally merged to obtain a candidate trajectory information 3 including 12 key section information. In addition, when the number of key section information included in the compared candidate trajectory information is different, the similarity between the two can be determined based on the proportion of the same key section information of the candidate trajectory information with a smaller number of key section information in the candidate trajectory information with a larger number of key section information; for example, candidate trajectory information 3 includes 18 key section information, and candidate trajectory information 4 includes 16 key section information, and both have 14 key section information that are the same, then the similarity between candidate trajectory information 4 and candidate trajectory information 3 = 14 / 18*100% = 78% (rounded up). If the preset percentage is 70%, candidate trajectory 3 and candidate trajectory 4 can be merged, that is, the union of the key section information included in the two is taken, and the union includes 20 key section information.

[0209] In a feasible embodiment, if at least one of the starting point information and the end point information is dynamic information, the method provided in the embodiment of the present application further includes at least one of the following steps S150-S160:

[0210] Step S105: cyclically executing the steps of the path planning method at intervals of a preset cycle time until receiving an instruction to exit the path planning.

[0211] Specifically, since at least one of the starting point information and the end point information is dynamic information (i.e., the location information changes in real time), in order to ensure the accuracy, real-time and effectiveness of the planned path, the loop duration can be set, such as 10 seconds, and the above steps S110-S140 are repeated every ten seconds until an instruction to exit path planning is received.

[0212] Among them, the instruction to exit the path planning can be triggered by the user (i.e., the device passively receives it) or actively triggered by the device. For example, in a location sharing scenario, when it is detected that the distance between users in the location sharing is less than the set distance, the path planning function can be actively exited, and the above steps S110-S140 are no longer executed in a loop. For example, in a wedding car-following scenario, during the trip, you may temporarily stop at a certain place to take pictures. At this time, the distance between the vehicles is generally relatively small (the distance between the starting point and the end point). If the exit from the path planning is actively triggered, it may affect the following team after the shooting is completed (the shooting time is highly variable, and it is difficult to determine the time to follow the car again to configure the path planning information in advance). Therefore, the exit path planning instruction can be set to be triggered by the user (such as operating the exit path planning function, etc.).

[0213] Step S160: Determine the distance between the starting point information and the end point information. If it is detected that the change of the distance is greater than the preset distance, repeat the steps of the path planning method.

[0214] Specifically, since at least one of the starting point information and the end point information is dynamic information (i.e., the location information changes in real time), in order to ensure the accuracy, real-time and effectiveness of the planned path, a preset interval can be set. When it is detected that the change interval between the starting point information and the end point information is greater than the preset interval, the above steps S110-S140 are repeated.

[0215] Assuming that the preset spacing is 100 meters, the spacing between the starting point information and the end point information in the initial stage of path planning is 1000 meters. If during the movement, whether the starting point information or the end point information changes, causing the current spacing between the starting point information and the end point information to become 111 meters (the minimum unit for judging the change spacing is meter), repeat the above steps S110-S140.

[0216] A specific embodiment of applying the path planning method provided in the embodiment of the present application to a terminal is given below.

[0217] Specifically, the path planning method provided in the embodiment of the present application can be run on a terminal, and in some instances, it can be a path planning solution for certain navigation applications, taxi-hailing mini-programs, etc. Taking the navigation scenario as an example, an example of the embodiment of the present application being applied to a terminal is described.

[0218] The step S110 of acquiring the starting point information and the end point information includes: in response to the path planning operation, acquiring the starting point information and the end point information input on the map interface.

[0219] Specifically, the terminal includes a map interface for interacting with the user, on which map information is displayed. On the map information, the terminal can automatically locate the user's current location as the starting point information when running, and the user can also manually determine the starting point information; then, the user can determine the destination of the trip, that is, the end point information; after determining the starting point information and the end point information, the user can trigger the path planning control provided on the map interface, so that the terminal responds to the path planning operation initiated by the user when running, and actively obtains the starting point information and the end point information currently entered in the map interface.

[0220] After obtaining the starting point information and the end point information, the terminal will run the steps S110 to S140 in the above embodiment in the background to obtain the target path information corresponding to the starting point information and the end point information.

[0221] Specifically, Fig.14 As shown, after obtaining the starting point information and the end point information, the user terminal 20 can obtain the pre-stored historical trajectory data from the server 10 through the network 30 for path planning. The server 10 can request the database 40 to obtain the corresponding historical trajectory data and return it to the user terminal 20 through the network 30.

[0222] Optionally, after executing step S140, the method further includes the step of displaying the target path information on the map interface.

[0223] like Fig.13 As shown, when the target path information includes two, two target paths can be displayed on the map interface. For example, when the starting point is A and the end point is B, the map interface displays route 1 as a dotted line and route 2 as a double-dotted line.

[0224] A specific embodiment of applying the path planning method provided in the embodiment of the present application to a server is given below.

[0225] like Fig.14As shown, data can be transmitted between the user terminal 20 and the server 10 through the network 30. Specifically, when the user terminal 20 responds to the user's path planning needs, the acquired starting point information and end point information can be sent to the server 10 through the network 30, and the server 10 can obtain the corresponding historical trajectory information from the database 40 based on the starting point information and the end point information for path planning processing. Specifically, the road section information corresponding to the starting point information and the end point information is queried, and then in the relational database, a reverse index calculation is performed based on the road section information to obtain a candidate trajectory identifier corresponding to the road section information (the candidate trajectory identifier is obtained by querying the road section information in the first index information), and a forward index calculation is performed based on the candidate trajectory identifier to obtain the candidate trajectory information corresponding to the candidate trajectory identifier (the candidate trajectory information is obtained by querying the candidate trajectory identifier in the second index information, and the candidate trajectory information includes a road section identifier sequence formed by key road section information), and then the target path information corresponding to the starting point information and the end point information is finally determined in the server 10 based on the candidate trajectory information; the server 10 returns the target path information obtained by path planning based on the historical trajectory information to the user terminal 20 through the network 30, and the user terminal 20 can display the target path information on the map interface (such as Fig.13 shown).

[0226] Optionally, regardless of whether the path planning method is executed on a terminal or a server, the present application can provide a module for preprocessing the historical trajectory information; the preprocessing module is used to construct the second index information and the first index information offline, and the two index information constructed can also form a relational database accordingly. It can be understood that the second index information and the first index information are in a state of continuous updating as the historical trajectory data gradually increases.

[0227] In the path planning method provided in the embodiment of the present application, based on the massive historical travel trajectory data, the user's travel rules are mined, and two types of index information (first index information and second index information) are established by extracting the trajectories, so as to realize the query of real-time public long-distance route planning. In terms of driving navigation, logistics system, food delivery, vehicle-mounted system, online car-hailing, etc., the quality of path planning can be effectively improved while meeting the timeliness requirements of online services.

[0228] Optionally, in the embodiment of the present application, the storage of data does not necessarily need to rely on memory, that is, the data can be stored in Redis (Remote Dictionary Server) instead of in memory. Redis is a log-type, Key-Value database that supports the network and can be persistent based on memory, and provides interface APIs in multiple languages. The embodiment of the present application uses redis for data storage to enable multiple services to share stored data, saving service resources while solving the problem of memory limitations of computer devices.

[0229] Some possible application examples are given below for the path planning method given in the above embodiment.

[0230] Specifically, in some map application scenarios, users can browse the map and query the route from starting point A to end point B, as well as the corresponding estimated time and travel mode, etc. in the map program. For example, the user hopes to query the route from the south of Liede Bridge to Guangzhou Tower in the map program. At this time, the user can access the map program through the Web, or directly use the car map / mobile phone map. On the corresponding map interface, the user can enter the starting point information (it can be the place name Liede Bridge South, and the map program determines the location information of the place) and the end point information (it can be the place name Guangzhou Tower, and the map program determines the location information of the place), and then the background calls the offline preset index information to determine the target path information corresponding to the input starting point information and end point information, and displays the target path information on the map interface to feedback to the user the path planned by the path planning method provided in the embodiment of the present application. On this basis, users can trigger navigation based on the target path information displayed on the map interface. For example, when there is only one target path information at present, and the map interface only displays one travel route, the user can trigger the navigation control to perform real-time navigation based on the route; if the current target path information includes multiple routes, the user can trigger the navigation control after selecting one of the routes on the map interface to perform real-time navigation based on the route selected by the user. Users can switch routes during the navigation process.

[0231] Among them, when accessing the map through Wed, the user's terminal only needs to have a browser; when accessing through the car map / mobile phone map, the user's terminal needs to have the corresponding map application installed or obtain the corresponding map applet.

[0232] In the Internet of Vehicles scenario, the starting point information may refer to the current location of the user's driving vehicle (such as GPS positioning information), and the end point information may be the current location of the leading vehicle, that is, the starting point information and the end point information may also include non-fixed location information, which changes as the vehicle moves. At this time, the driving vehicle and the leading vehicle communicate through the Internet of Vehicles, that is, the on-board equipment on the driving vehicle effectively utilizes the dynamic information of the leading vehicle in the information network platform through wireless communication technology; optionally, the leading vehicle may not have the Internet of Vehicles function, but upload the location information of the leading vehicle to the information network platform in real time through the mobile phone map; and when the field vehicle has the Internet of Vehicles function, the leading vehicle can upload its location information to the information network platform in real time through the on-board equipment. In this scenario, the starting point information input by the user is the current location information of the driving vehicle (which can be determined by the real-time positioning function), and the end point information is the current location information of the leading vehicle. On this basis, the driving vehicle can upload the starting point information to the server through the Internet of Vehicles. Since the end point information changes in real time, the driving vehicle can only upload the association relationship with the leading vehicle, and the server actively retrieves the end point information corresponding to the leading vehicle according to the association relationship. Then, the server uses the path planning method provided in the embodiment of the present application to feedback the target path information to the driving vehicle (the target path information can be updated in real time, or updated after a specific interval, or updated after the distance between the driving vehicle and the leading vehicle exceeds a specific distance). The driving vehicle displays the target path information through the interactive interface of the on-board device, and then navigates based on the displayed target path information so that the driving vehicle follows the leading vehicle. Among them, if Fig.10 In the corresponding scenario, if the leading vehicle is at point A and the driving vehicle is at point B, there may be two candidate routes. At this time, the final target route can be recommended to the user based on the historical number of adoptions of each route, such as Fig.11 As shown, if the driving vehicle passes through route 1, it may be difficult to meet other vehicles. The driving vehicle needs to back up or wait on route 1, which results in an increase in the distance between the driving vehicle and the leading vehicle while the leading vehicle continues to move forward. Fig.12 As shown, although Route 2 requires a longer distance for driving a vehicle than Route 1, since the vehicle can easily pass through Route 2 (reflected by the historical adoption times of each route in this application), it is more conducive to the vehicle following the leading vehicle in the actual street. Therefore, Route 2 is determined as the target route to provide feedback to the user driving the vehicle.

[0233] In the specific implementation of this application, data related to user information, travel trajectory information, etc. are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0234] Based on the same principle as the above method embodiment, the present application embodiment also provides a path planning device, such as Fig.15 As shown in , the path planning device 100 may include a location information acquisition module 110 , a first determination module 120 , a second determination module 130 , and a path determination module 140 .

[0235] Among them, the acquisition module 110 is used to obtain the starting point information and the end point information, and determine the road section information corresponding to the starting point information and the end point information; the first determination module 120 is used to determine the candidate trajectory identifier corresponding to the road section information based on the preset first index information; the second determination module 130 is used to determine the candidate trajectory information corresponding to the candidate trajectory identifier based on the preset second index information; the path determination module 140 is used to determine the target path information corresponding to the starting point information and the end point information in the candidate trajectory information; wherein, the first index information and the second index information are established based on the thinned trajectory information; the first index information represents the correspondence between each road section information and the candidate trajectory identifier, the second index information represents the correspondence between each candidate trajectory identifier and the candidate trajectory information, and each candidate trajectory information includes at least two road section information; the thinned trajectory information includes the key road section information retained after the thinning processing of the road section information matching the preset road network in the historical trajectory information.

[0236] In a feasible embodiment, the path planning device 100 further includes a preprocessing module, which is used to perform thinning processing on the historical trajectory information to obtain the thinned trajectory information, including:

[0237] Obtain some historical trajectory information of travel within a preset time period;

[0238] Determine a positioning point in the historical trajectory information based on at least one of time, distance, and trajectory landmarks;

[0239] Matching the positioning points in the historical trajectory information with the road section information in the preset road network to obtain matching trajectory information; wherein the preset road network is a topological map constructed with roads in the road map data as edges and intersections as nodes; the road section information in the preset road network includes information corresponding to each minimum segmentation unit in the topological map;

[0240] Based on a preset thinning strategy, the road section information included in the matching trajectory information is thinned to obtain thinned trajectory information retaining key road section information.

[0241] In a feasible embodiment, the preprocessing module is used to determine the positioning point in the historical trajectory information based on at least one of time, distance and trajectory landmarks, and is specifically used for at least one of the following:

[0242] For each historical trajectory information, obtain the corresponding positioning point at a preset time interval;

[0243] For each historical trajectory information, the interval time for obtaining the positioning point is set based on the travel time of the historical trajectory information and the preset travel time, and the positioning point at the corresponding time is obtained once every interval time;

[0244] For each historical trajectory information, obtain the corresponding positioning point every preset distance;

[0245] For each historical track information, based on the entire length of the historical track information, a preset number of positioning points are obtained at equal intervals;

[0246] For each piece of historical trajectory information, a trajectory landmark is determined based on the attribute information of the historical trajectory information, and a corresponding positioning point is acquired based on the trajectory landmark; the attribute information represents the scene corresponding to the historical trajectory information.

[0247] In a feasible embodiment, the preprocessing module is used to match the positioning points in the historical trajectory information with the road section information in the preset road network, and when the matching trajectory information is obtained, it is specifically used to:

[0248] Position matching of the positioning points in the historical trajectory information with the road section information in the preset road network; the road section information includes the position information corresponding to each road section;

[0249] Perform the track segmentation operation on the historical track information that matches the road section information in the preset road network to obtain the matching track information:

[0250] The trajectory segmentation operation includes at least one of the following:

[0251] If the historical trajectory information includes at least two end point information, the historical trajectory information is divided based on the at least two end point information to obtain at least two segments of matching trajectory information;

[0252] If the historical trajectory information includes a stay point, the historical trajectory information is divided based on the stay point to obtain at least two segments of matching trajectory information; the stay point is a positioning point that stays at the same position for a preset time;

[0253] If the number of road section information included in the historical trajectory information is greater than a set number, the historical trajectory information is divided based on the set number to obtain at least two sections of matching trajectory information.

[0254] In a feasible embodiment, when the preprocessing module is used to execute the preset thinning strategy to perform thinning processing on the road section information included in the matching trajectory information to obtain the thinned trajectory information retaining the key road section information, it is also used for at least one of the following:

[0255] Using the intersection information as a thinning factor, the matching trajectory information is thinned to obtain thinned trajectory information, so that the thinned trajectory information retains key section information corresponding to the intersection information;

[0256] Deleting the road section information that meets the preset target condition in the matching trajectory information to obtain the thinned trajectory information;

[0257] Among them, the preset target condition includes that the trajectory value corresponding to each road section information is less than the thinning target value; the thinning target value is the product of the average trajectory value corresponding to all road section information in the matching trajectory information and the thinning coefficient.

[0258] In a feasible embodiment, the path determination module 140 is used to determine the target path information corresponding to the starting point information and the end point information in the candidate trajectory information, specifically for:

[0259] Determine the number of historical adoptions corresponding to each candidate trajectory information;

[0260] Based on a preset number of candidate trajectory information with relatively large historical adoption times, target path information corresponding to the starting point information and the end point information is determined.

[0261] In a feasible embodiment, the path determination module 140 is used to determine the target path information corresponding to the starting point information and the end point information in the candidate trajectory information, specifically for:

[0262] Merging the candidate trajectory information including key road section information that is identical to a preset percentage or more;

[0263] Determining target path information corresponding to the starting point information and the end point information in the merged candidate trajectory information;

[0264] The merged processing includes at least one of the following:

[0265] For at least two candidate trajectory information with 100% identical key section information, only one candidate trajectory information is retained;

[0266] For at least two pieces of candidate trajectory information having the same key segment information exceeding a preset percentage, a new piece of candidate trajectory information is generated based on the union of the key segment information included in each piece of candidate trajectory information.

[0267] In a feasible embodiment, when the path planning method is applied to a terminal, the acquisition module 110 is used to execute the acquisition of the starting point information and the end point information, specifically for:

[0268] In response to the route planning operation, obtaining the starting point information and the end point information input on the map interface;

[0269] After being used to determine the target path information, the path determination module 140 is further used to:

[0270] The target path information is displayed on the map interface.

[0271] In a feasible embodiment, if at least one of the starting point information and the end point information is dynamic information, the path planning device 100 further includes an execution module for executing at least one of the following:

[0272] The steps of the path planning method are executed repeatedly at intervals of a preset loop duration until an instruction to exit the path planning is received;

[0273] Determine the distance between the starting point information and the end point information, and if it is detected that the change of the distance is greater than the preset distance, repeat the steps of the path planning method.

[0274] The device of the embodiments of the present application can execute the method provided by the embodiments of the present application, and the implementation principles are similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0275] In an embodiment of the present application, an electronic device is provided, including a memory, a processor and a computer program stored in the memory, and the processor executes the above-mentioned computer program to implement the steps of the path planning method. Compared with the related art, it can be achieved that: in the online service of path planning, after the starting point information and the end point information are obtained, the road section information corresponding to the starting point information and the end point information can be determined, that is, the determined road section information includes the starting point information and the end point information; then, the candidate trajectory identifier corresponding to the road section information can be determined based on the preset first index information, and the candidate trajectory information corresponding to the candidate trajectory identifier can be determined based on the preset second index information; so far, in order to meet the timeliness and real-time requirements of the online service, the present application pre-establishes There is a trajectory index (first index information and second index information), wherein the first index information represents the correspondence between each road section information and the candidate trajectory identifier, and the first index information can be used to quickly screen out the candidate trajectory identifier corresponding to the road section information corresponding to the starting point information and the end point information; the second index information represents the correspondence between each candidate trajectory identifier and the candidate trajectory information, and the second index information can be used to quickly screen out the candidate trajectory information corresponding to the candidate trajectory identifier (each candidate trajectory information includes at least two road section information), that is, to improve the efficiency of querying the candidate trajectory information through the trajectory index; then, the present application can determine the target path information corresponding to the starting point information and the end point information in the determined candidate trajectory information. Among them, the first index information and the second index information are both established based on the thinned trajectory information, and the thinned trajectory information includes the key road section information retained after the thinning processing of the road section information matching the preset road network in the historical trajectory information, and the thinning processing of the historical trajectory information in the present application can effectively reduce the data storage volume of the historical trajectory information, and is also conducive to reducing the calculation amount of the subsequent determination of the target path information, and at the same time, it is conducive to improving the quality of path planning.

[0276] In an alternative embodiment, an electronic device is provided, such as Fig.16 As shown, Fig.16 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0277] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0278] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.16 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0279] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0280] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0281] Among them, electronic equipment includes but is not limited to: servers, user terminals, and vehicle-mounted equipment.

[0282] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0283] The embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0284] The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that shown or described in the drawings.

[0285] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0286] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A path planning method, characterized in that: include: Acquire starting point information and end point information, and determine the road section information corresponding to the starting point information and end point information; Based on the preset first index information, determining a candidate trajectory identifier corresponding to the road section information; Based on the preset second index information, determining the candidate trajectory information corresponding to the candidate trajectory identifier; Determining target path information corresponding to the starting point information and the end point information in the candidate trajectory information; The first index information and the second index information are established based on the thinned trajectory information, the first index information represents the correspondence between each road segment information and the candidate trajectory identifier, the second index information represents the correspondence between each candidate trajectory identifier and the candidate trajectory information, and each candidate trajectory information includes at least two road segment information; The thinned trajectory information includes key road section information retained after thinning out road section information matching a preset road network in the historical trajectory information.

2. The method according to claim 1, characterized in that The process of thinning the historical trajectory information to obtain the thinned trajectory information includes: Obtain some historical trajectory information of travel within a preset time period; Determine a positioning point in the historical trajectory information based on at least one of time, distance, and trajectory landmarks; Matching the positioning points in the historical trajectory information with the road section information in the preset road network to obtain matching trajectory information; wherein the preset road network is a topological map constructed with roads in the road map data as edges and intersections as nodes; the road section information in the preset road network includes information corresponding to each minimum segmentation unit in the topological map; Based on a preset thinning strategy, the road section information included in the matching trajectory information is thinned to obtain thinned trajectory information retaining key road section information.

3. The method according to claim 2, characterized in that The determining of the positioning point in the historical trajectory information based on at least one of time, distance and trajectory landmarks includes at least one of the following: For each historical trajectory information, obtain the corresponding positioning point at a preset time interval; For each historical trajectory information, the interval time for obtaining the positioning point is set based on the travel time of the historical trajectory information and the preset travel time, and the positioning point at the corresponding time is obtained once every interval time; For each historical trajectory information, obtain the corresponding positioning point every preset distance; For each historical track information, based on the entire length of the historical track information, a preset number of positioning points are obtained at equal intervals; For each historical trajectory information, determine a trajectory landmark based on the attribute information of the historical trajectory information, and obtain a corresponding positioning point based on the trajectory landmark; The attribute information represents the scene corresponding to the historical trajectory information.

4. The method according to claim 2, characterized in that The matching of the positioning points in the historical trajectory information with the road section information in the preset road network to obtain the matching trajectory information includes: Position matching of the positioning points in the historical trajectory information with the road section information in the preset road network; the road section information includes the position information corresponding to each road section; Perform the track segmentation operation on the historical track information that matches the road section information in the preset road network to obtain the matching track information: The trajectory segmentation operation includes at least one of the following: If the historical trajectory information includes at least two end point information, the historical trajectory information is divided based on the at least two end point information to obtain at least two segments of matching trajectory information; If the historical trajectory information includes a stay point, the historical trajectory information is divided based on the stay point to obtain at least two segments of matching trajectory information; the stay point is a positioning point that stays at the same position for a preset time; If the number of road section information included in the historical trajectory information is greater than a set number, the historical trajectory information is divided based on the set number to obtain at least two sections of matching trajectory information.

5. The method according to claim 2, characterized in that: The thinning process based on the preset thinning strategy to obtain the thinned trajectory information with the key segment information retained includes at least one of the following: Using the intersection information as a thinning factor, the matching trajectory information is thinned to obtain thinned trajectory information, so that the thinned trajectory information retains key section information corresponding to the intersection information; Deleting the road section information that meets the preset target condition in the matching trajectory information to obtain the thinned trajectory information; Among them, the preset target condition includes that the trajectory value corresponding to each road section information is less than the thinning target value; the thinning target value is the product of the average trajectory value corresponding to all road section information in the matching trajectory information and the thinning coefficient.

6. The method according to claim 1, characterized in that The determining of the target path information corresponding to the starting point information and the end point information in the candidate trajectory information includes: Determine the number of historical adoptions corresponding to each candidate trajectory information; Based on a preset number of candidate trajectory information with relatively large historical adoption times, target path information corresponding to the starting point information and the end point information is determined.

7. The method according to claim 1, characterized in that The determining of the target path information corresponding to the starting point information and the end point information in the candidate trajectory information includes: Merging the candidate trajectory information including key road section information that is identical to a preset percentage or more; Determining target path information corresponding to the starting point information and the end point information in the merged candidate trajectory information; The merged processing includes at least one of the following: For at least two candidate trajectory information with 100% identical key section information, only one candidate trajectory information is retained; For at least two pieces of candidate trajectory information having the same key segment information exceeding a preset percentage, a new piece of candidate trajectory information is generated based on the union of the key segment information included in each piece of candidate trajectory information.

8. The method according to claim 1, characterized in that: If at least one of the starting point information and the end point information is dynamic information, at least one of the following is performed: The steps of the path planning method are executed repeatedly at intervals of a preset loop duration until an instruction to exit the path planning is received; Determine the distance between the starting point information and the end point information, and if it is detected that the change of the distance is greater than the preset distance, repeat the steps of the path planning method.

9. A path planning device, characterized in that: include: An acquisition module, used to acquire starting point information and end point information, and determine the road section information corresponding to the starting point information and end point information; A first determination module, configured to determine a candidate trajectory identifier corresponding to the road section information based on preset first index information; A second determination module, configured to determine the candidate trajectory information corresponding to the candidate trajectory identifier based on preset second index information; A path determination module, used to determine target path information corresponding to the starting point information and the end point information in the candidate trajectory information; The first index information and the second index information are established based on the thinned trajectory information, the first index information represents the correspondence between each road segment information and the candidate trajectory identifier, the second index information represents the correspondence between each candidate trajectory identifier and the candidate trajectory information, and the candidate trajectory information includes at least two road segment information; The thinned trajectory information includes key road section information retained after thinning out road section information matching a preset road network in the historical trajectory information.

10. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to execute the method according to any one of claims 1 to 8 when running the computer program.

11. A computer-readable storage medium, characterized in that: The storage medium stores a computer program. When the computer program runs in a processor, the processor is configured to execute the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images