Information processing methods, devices, equipment and program products

Abstract

This application provides an information processing method, apparatus, device, and program product. The method includes: acquiring multiple routes in a target area; wherein the routes are historical navigation routes provided by a navigation service, and the multiple historical navigation routes satisfy the coverage of the target area; vectorizing the multiple routes to obtain corresponding multiple vectorized routes; removing duplicates from the multiple vectorized routes to obtain a target route set; the target route set is used to verify the map service corresponding to the target area. This application can ensure the authenticity of the routes selected for verification in a specified area, and while ensuring coverage, it reduces a large amount of repetitive work in the verification stage, thereby ensuring the accuracy and efficiency of verification.

Description

Technical Field

[0001] This application relates to the field of map technology, and in particular to an information processing method, apparatus, device, and program product. Background Technology

[0002] To ensure map quality, large-scale verification of the entire road network in a given area is necessary. Currently, verification typically uses map-generated routes, but these routes lack authenticity, making it difficult to guarantee accuracy. Verification based on real-world trajectories can also be used, ensuring route authenticity: one approach is to randomly select real-world trajectories for the area as verification routes, but this cannot guarantee coverage, thus compromising accuracy; another approach is to use all provided real-world trajectories for the area as verification routes, which ensures coverage, but the presence of many duplicate routes leads to significant duplication of work during verification.

[0003] Therefore, the existing technology of selecting a designated area for the verification route cannot guarantee authenticity and coverage while reducing a large amount of repetitive work in the verification stage, thus failing to guarantee the accuracy and efficiency of the verification. Summary of the Invention

[0004] The main objective of this application is to provide an information processing method, apparatus, device, and program product that can select a designated area for verifying the authenticity of the route used, and while ensuring coverage, reduce a large amount of repetitive work in the verification stage, thereby ensuring the accuracy and efficiency of the verification.

[0005] In a first aspect, embodiments of this application provide an information processing method, including:

[0006] Obtain multiple routes within the target area; wherein, the routes are historical navigation routes provided by the navigation service, and the multiple historical navigation routes meet the coverage requirements of the target area;

[0007] The multiple routes are vectorized to obtain the corresponding multiple vectorized routes;

[0008] The multiple vectorized routes are deduplicated to obtain a target route set; the target route set is used to verify the map service corresponding to the target area.

[0009] Optionally, the multiple routes are vectorized to obtain corresponding multiple vectorized routes, including:

[0010] For each route, key points are extracted from the route, and these key points are used to represent the locations that serve as feature markers during the map navigation process;

[0011] Vectorize each key point on the route to obtain the vector features of each key point on the route;

[0012] Based on the vector features of each key point on the route, a vectorized route is obtained; wherein the vectorized route is composed of the vector features of consecutive key points.

[0013] Optionally, the multiple vectorized routes are deduplicated to obtain a target route set, including:

[0014] Extract sub-vectors from the multiple vectorized routes; the sub-vectors are determined by the vector features of two adjacent key points;

[0015] For each vectorized route, based on the sub-vectors and the covering set in the vectorized route, it is determined whether to retain the vectorized route; wherein, the initial covering set is empty, and the covering set is used to represent the set of covered sub-vectors;

[0016] If retained, the initial route set is updated according to the vectorized route, and the cover set is updated according to the sub-vectors in the vectorized route to determine whether the next vectorized route should be retained; wherein, the initial route set is empty.

[0017] Determine the target route set based on the initial route set after the last update.

[0018] Optionally, for each vectorized route, based on the vectorized route and the coverage set, determine whether to retain the vectorized route, including:

[0019] Divide the multiple vectorized routes into at least one initial set;

[0020] For each initial set, the vectorized routes in the initial set are sorted in descending order of the number of key points contained;

[0021] Based on the sorting results, the vectorized target routes of the corresponding order are retrieved from the initial set in sequence;

[0022] For each vectorized target route extracted sequentially, it is determined whether the vectorized target route should be retained based on the vectorized target route and the coverage set.

[0023] Optionally, determining whether to retain the vectorized target route based on the vectorized target route and the coverage rate includes:

[0024] Generate a sub-vector set from the sub-vectors in the vectorized target route;

[0025] Based on the intersection of the sub-vector set and the coverage set, and the sub-vector set, determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold. If it is less, then determine to retain the vectorized target route.

[0026] Based on the vectorized routes, update the initial route set, including:

[0027] The union of the initial route set and the set formed by the vectorized target routes is used as the updated initial route set;

[0028] Update the coverage set based on the sub-vectors in the vectorized route, including:

[0029] The union of the covering set and the subvector set is taken as the updated covering set.

[0030] Optionally, the method further includes:

[0031] The key points contained in the target route set are plotted on the map of the target area to determine whether there are any uncovered areas; and / or, by replanning the routes contained in the target route set, each trajectory point is obtained and plotted as a screen to determine whether there are any uncovered areas on the map of the target area.

[0032] If such a region exists, a strategy for updating the target route set is determined based on the number or range of the uncovered regions, in order to update the target route set.

[0033] Optionally, the method further includes:

[0034] Store the target route set;

[0035] The method further includes:

[0036] Based on the target route set, generate the road network corresponding to the target area;

[0037] The road network is used to support the verification of the map service corresponding to the target area.

[0038] Secondly, embodiments of this application provide an information processing apparatus, including:

[0039] The first processing module is used to obtain multiple routes in the target area; wherein, the routes are historical navigation routes provided by the navigation service, and the multiple historical navigation routes meet the coverage of the target area;

[0040] The second processing module is used to vectorize the multiple routes to obtain the corresponding multiple vectorized routes;

[0041] The third processing module is used to deduplicate the multiple vectorized routes to obtain a target route set; the target route set is used to verify the map service corresponding to the target area.

[0042] Thirdly, embodiments of this application provide an electronic device, including:

[0043] At least one processor; and

[0044] A memory that is communicatively connected to the at least one processor;

[0045] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform the method described in any of the above aspects.

[0046] Fourthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the methods described in any of the above aspects.

[0047] The information processing method, apparatus, device, and program product provided in this application can acquire multiple routes in a target area. These routes are historical navigation routes provided by a navigation service, and the multiple historical navigation routes satisfy the coverage requirements of the target area. Further, the multiple routes are vectorized to obtain corresponding vectorized routes. Further, the multiple vectorized routes are deduplicated to obtain a target route set. The target route set is used to verify the map service corresponding to the target area. This application can acquire historical navigation routes provided by a navigation service that satisfy the coverage requirements of the target area, and then select a set of use cases for verifying the map service from the historical navigation routes, i.e., the target route set. This makes the target route set selected in this way have verification capability, thereby making the verification effective. Furthermore, based on the historical navigation routes, vectorization processing is performed so that the routes consist of vectors of consecutive points. To ensure route coverage while reducing duplication, and thus reducing the large amount of repetitive work in the verification stage, all provided routes can be vectorized and deduplicated to obtain the target route set, which is used to verify the map service of the target area. Therefore, this application makes the verification effective by processing historical navigation routes that have authenticity and meet the target area coverage. By vectorizing the full set of historical navigation routes and then deduplicating the vectorized routes, the coverage can be guaranteed while reducing a lot of repetitive work in the verification stage, thereby ensuring the accuracy and efficiency of the verification. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application;

[0050] Figure 2 A flowchart illustrating an information processing method provided in an embodiment of this application;

[0051] Figure 3 A flowchart illustrating another information processing method provided in an embodiment of this application;

[0052] Figure 4 This is a schematic diagram illustrating another application scenario provided by an embodiment of this application;

[0053] Figure 5 This is a schematic diagram illustrating another application scenario provided by an embodiment of this application;

[0054] Figure 6 This is a schematic diagram of the structure of an information processing device provided in an embodiment of this application;

[0055] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0056] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0057] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0058] First, let me explain the terms used in this application:

[0059] MapReduce: A framework for parallel computing of big data, consisting of two phases: Map and Reduce. The Map phase breaks down the problem and processes each part separately, while the Reduce phase aggregates all the results processed in the Map phase.

[0060] Navigation points: also known as key points, are points that serve as milestones in the map navigation process. The lines connecting navigation points form the navigation route.

[0061] Regarding set representation:

[0062] Edge: A vector line connecting points in a graph structure. For example, in the graph A→B→C, the two edges are A→B and B→C. The arrow of each edge points from the starting point to the ending point, indicating the direction of the edge.

[0063] Adjacency list: A data structure for storing graph structures. For each vertex in the graph, an index is created to quickly find a specific table structure based on that vertex. This table structure stores the endpoints of edges that originate from that vertex.

[0064] To ensure map quality, large-scale verification of the entire road network in a given area is necessary. Currently, verification is generally performed using map-generated routes (e.g., map rendering, data loading), but these generated routes lack realism, making it difficult to guarantee verification accuracy. Verification based on real-world trajectories can also be used, ensuring route authenticity: one approach is to randomly select real-world trajectories for the area as verification routes, but this cannot guarantee coverage, thus compromising accuracy; another approach is to use all provided real-world trajectories for the area as verification routes, which guarantees coverage, but the presence of many duplicate routes leads to significant duplication of work during verification.

[0065] Therefore, the existing technology of selecting a designated area for the verification route cannot guarantee authenticity and coverage while reducing a large amount of repetitive work in the verification stage, thus failing to guarantee the accuracy and efficiency of the verification.

[0066] In view of this, this application provides an information processing method. In order to enable the selected target route set to have verification capability and thus make the verification effective, the historical navigation routes of the target area provided by the navigation service can be obtained, and the obtained multiple historical navigation routes can cover all roads in the target area. Then, in order to ensure the coverage of the routes and reduce the duplication rate, thereby reducing a large amount of repetitive work in the verification stage, the full set of provided routes can be vectorized and deduplicated to obtain the target route set, which is used to verify the map service of the target area.

[0067] Therefore, by processing historical navigation routes that accurately meet the target area coverage requirements, the verification becomes effective. By vectorizing the entire set of historical navigation routes and then deduplicating the vectorized routes, coverage can be guaranteed while reducing a large amount of repetitive work in the verification phase, thereby ensuring the accuracy and efficiency of verifying or testing map services.

[0068] The following details how to select a set of test cases (i.e., the target route set) that is authentic, meets coverage requirements, and reduces a lot of repetitive work in the verification phase.

[0069] Figure 1 This is a schematic diagram illustrating an application scenario involved in an embodiment of this application. For example... Figure 1 As shown, the information processing method provided in this application embodiment can be applied to, for example... Figure 1 The application scenario shown includes a server and a terminal device. The terminal device can be an in-vehicle device or a user device, equipped with a map navigation system. Specifically, the server can obtain historical navigation routes provided by the navigation service, vectorize and deduplicate these routes, and select a test case set (target route set) to verify the map service for a specified area (the target area). This includes checking for errors in map rendering, map data loading, navigation prompts, or routes. The map navigation system can be installed on user devices or in-vehicle devices to provide users (including testers or verification personnel) with maps and navigation services for the specified area. It generates a road network from the target route set selected by the server, and uses the map navigation system to render maps and provide navigation services for each road in the network, thereby verifying the accuracy of the map service for the specified area.

[0070] In order to quickly select the target route set for verifying the map service, that is, to quickly select the minimum route set that is most likely to be complete in the specified area, the server can use multiple vectorized routes (here referring to the full set of vectorized routes that meet the coverage requirements) as the initial set, and initialize the initial route set to empty and the initial coverage set to empty.

[0071] Based on the vectorized routes in the initial set, repeat the following steps until the initial set is empty: Take the vectorized target route (which may refer to the first route) with the most key points from the initial set, and extract the sub-vectors from the vectorized target route to generate a sub-vector set. The sub-vectors are composed of the vector features of every two adjacent key points in the vectorized target route. Based on the intersection of the sub-vector set and the coverage set, determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold. If it is less, determine to retain the vectorized target route. That is, take the union of the initial route set and the set formed by the vectorized target route as the updated initial route set, and take the union of the coverage set and the sub-vector set as the updated coverage set.

[0072] The initial route set after the last update is used as the target route set.

[0073] Therefore, the information processing method provided in this application makes the verification effective by processing historical navigation routes that have authenticity and meet the target area coverage. By vectorizing the full set of historical navigation routes and then deduplicating the vectorized routes, the method can ensure coverage while reducing a lot of repetitive work in the verification stage, thereby ensuring the accuracy and efficiency of verifying or testing map services.

[0074] It should be noted that the above-described steps—selecting a set of use cases for verifying the map service from historical navigation routes provided by the acquired navigation service that meet the coverage of the target area—ensure that the selected target route set has verification capability, thereby making the verification effective; then, vectorizing the historical navigation routes so that the routes consist of vectors of consecutive points, and deduplicating the vectorized full set of provided routes to obtain the target route set—are merely illustrative. The process could also be achieved by splitting the data into more platforms and more modules; this application does not specifically limit this approach. The acquired navigation routes (including historical navigation routes) are all authorized by the user or the vehicle manufacturer.

[0075] The technical solutions of this application will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0076] For example, Figure 2 This is a flowchart illustrating an information processing method provided in an embodiment of this application. This embodiment can be applied to any device capable of information processing, such as a terminal. Figure 2 As shown, the information processing method may include:

[0077] S201. Obtain multiple routes in the target area.

[0078] The routes mentioned are historical navigation routes provided by the navigation service, and multiple historical navigation routes meet the coverage requirements of the target area.

[0079] In this embodiment, the server can select routes from the online database that meet the business requirements within the target area. These routes satisfy the coverage requirement of the target area; for example, these routes can completely cover the entire target area. The routes stored in the online database can be historical navigation routes provided by the navigation service of the map navigation system, ensuring authenticity and verifying the effectiveness of the map service, thus conforming to application scenarios such as map rendering and navigation services. It should be noted that these historical navigation routes are authorized, which will not be elaborated upon here.

[0080] S202. The multiple routes are vectorized to obtain the corresponding multiple vectorized routes.

[0081] The route deduplication process involves first vectorizing the routes, resulting in routes composed of directional, continuous points. Then, based on the vectorized routes, if there are overlapping sections, and the proportion of overlap is less than a preset threshold t, it indicates that the route contains a large number of uncovered sections, and this route is retained; otherwise, it is filtered out.

[0082] Optionally, the multiple routes are vectorized to obtain corresponding multiple vectorized routes, including:

[0083] For each route, key points are extracted from the route, and these key points are used to represent the locations that serve as feature markers during the map navigation process;

[0084] Vectorize each key point on the route to obtain the vector features of each key point on the route;

[0085] Based on the vector features of each key point on the route, a vectorized route is obtained; wherein the vectorized route is composed of the vector features of consecutive key points.

[0086] In this embodiment, to simplify the vectorized representation of the route, it is unnecessary to extract and quantize every point on the route. Instead, key points on each route, i.e., points that serve as feature markers (i.e., stage markers) during map navigation, can be extracted and vectorized to obtain vector features of each key point (e.g., used to represent directional locations). Stage-specific points include, for example, points (or locations) in complex scenarios such as those above an overpass and below a roundabout; or points in simple straight lanes that happen to lead onto an overpass, etc., which will not be listed here.

[0087] Specifically, key points are vectorized, and the vectors formed by consecutive key points constitute a vectorized route, which replaces the motion trajectory or the actual trajectory. This is because a unique vectorized route matching the actual trajectory is determined between two vector points on a route; that is, the vectorized route replaces the real route, and all routes are treated as vectors.

[0088] Since the vectorized route is composed of vectors of consecutive key points, the deduplication operation only needs to remove duplicates from the vectorized route. Simultaneously, the vector features are preserved during final storage, allowing for arbitrary extraction for map service verification without needing to reprocess the selected routes to achieve map service verification capabilities. In other words, deduplication based on vector features is used while simultaneously providing arbitrarily extracted routes for subsequent verification.

[0089] S203. Deduplicatively analyze the multiple vectorized routes to obtain a target route set; the target route set is used to verify the map service corresponding to the target area.

[0090] This section verifies map services, such as the accuracy of map rendering, data loading, and navigation services.

[0091] Taking a certain area as an example, the number of navigation routes obtained in a single day for that designated area may be in the tens of millions, and the total mileage that can be counted is about tens of thousands of kilometers. It can be seen that there are many overlapping points in the navigation routes. Therefore, in order to meet the coverage requirements and reduce redundant work, it is necessary to perform full deduplication.

[0092] In this embodiment, a test case set (i.e., a set of routes used to verify the map service) is selected from historical navigation routes provided by the navigation service that meet the coverage requirements of the target area. This provides verification and detection capabilities, ensuring the validity of the verification. Furthermore, to guarantee coverage, all historical navigation routes in the target area are processed in full. Simultaneously, to reduce the significant amount of repetitive work in the verification phase, all routes are deduplicated. Therefore, this method achieves the selection of a set of routes with verifiable authenticity and validity for a specified area, while ensuring coverage and reducing a large amount of repetitive work in the verification phase.

[0093] Therefore, this application embodiment can obtain multiple routes in the target area; wherein, the routes are historical navigation routes provided by the navigation service, and the multiple historical navigation routes meet the coverage of the target area; further, the multiple routes are vectorized to obtain corresponding multiple vectorized routes; further, the multiple vectorized routes are deduplicated to obtain a target route set; the target route set is used to verify the map service corresponding to the target area.

[0094] This application obtains historical navigation routes provided by a navigation service that meet the coverage requirements of a target area. Then, it selects a set of use cases—the target route set—from these historical routes to verify the map service. This ensures the selected target route set has verification capability, thereby making the verification effective. Furthermore, it vectorizes the historical navigation routes, making them consist of vectors of consecutive points. To ensure route coverage while reducing duplication, thus minimizing repetitive work in the verification phase, all provided routes can be vectorized and deduplicated to obtain the target route set, which is then used to verify the map service for the target area. Therefore, this application ensures the effectiveness of verification by processing historical navigation routes that genuinely meet the target area coverage requirements. By vectorizing all provided historical navigation routes and then deduplicating the vectorized routes, it can guarantee coverage while reducing repetitive work in the verification phase, thereby ensuring the accuracy and efficiency of the verification.

[0095] At the same time, to save resources, the server can divide multiple vectorized routes (here referring to the full vectorized routes that meet the coverage requirements) into at least one initial set, and initialize the initial route set to empty and the coverage set to empty;

[0096] For each initial set, repeat the following steps until the initial set is empty: Extract the vectorized target route (which may refer to the first route) containing the most key points from the initial set, and extract sub-vectors from the vectorized target route to generate a sub-vector set. Each sub-vector is composed of the vector features of every two adjacent key points in the vectorized target route. Update the initial route set based on the sub-vector set. The updated initial route set contains the vectorized target routes remaining after the current deduplication process.

[0097] Based on the updated initial route sets corresponding to each initial set, a target route set is determined, and the vector features of each key point in the target route set are stored. Specifically, the updated initial route sets corresponding to each initial set are used as new initial sets, and the new initial route sets and new coverage sets are initialized to empty. For each vectorized route in the new initial set, the following steps are repeated until the new initial set is empty: The vectorized target route (which can be the second route) containing the most key points is extracted from the new initial set, and sub-vectors are extracted from the vectorized target route to generate a sub-vector set. Based on the sub-vector set, the new initial route set is updated. The updated new initial route set contains the vectorized target routes remaining after the current deduplication. The last updated new initial route set is used as the target route set.

[0098] Optionally, the method further includes:

[0099] The location information issued by the navigation service is analyzed to obtain the analysis results, which show that the overlapping parts of any two routes have the same key points.

[0100] Based on the analysis results, the characteristics of the overlapping routes corresponding to the two different routes are determined, wherein the overlapping routes contain overlapping sub-vectors.

[0101] Based on the aforementioned characteristics, duplicates are removed from the multiple vectorized routes to obtain the target route set.

[0102] In this embodiment, by observing the location information distributed by the navigation service, for any two routes, the overlapping navigation key points are consistent. This can be used as a deduplication condition for selecting different route sets, based on business requirements. Specifically, based on the characteristics of the navigation service, duplicate routes are defined as two different vectors that contain overlapping sub-vectors. Based on this navigation service characteristic, a deduplication strategy is determined to select the target dataset, ensuring that the selected route set conforms to the actual test application scenario, thereby guaranteeing the accuracy of the verification.

[0103] Optionally, the multiple vectorized routes are deduplicated to obtain a target route set, including:

[0104] Extract sub-vectors from the multiple vectorized routes; the sub-vectors are determined by the vector features of two adjacent key points;

[0105] For each vectorized route, based on the sub-vectors and the covering set in the vectorized route, it is determined whether to retain the vectorized route; wherein, the initial covering set is empty, and the covering set is used to represent the set of covered sub-vectors;

[0106] If retained, the initial route set is updated according to the vectorized route, and the cover set is updated according to the sub-vectors in the vectorized route to determine whether the next vectorized route should be retained; wherein, the initial route set is empty.

[0107] Determine the target route set based on the initial route set after the last update.

[0108] In this embodiment, after key points are vectorized, the vectors of every two adjacent key points on the route constitute a sub-vector of the route. A sub-vector set is generated for each route's corresponding sub-vectors. Then, based on this sub-vector set and the coverage set, the proportion of overlapping routes on the route is calculated, thereby determining whether to retain the vectorized route. If retained, the initial route set and coverage set are updated; if not retained, the initial route set is left unprocessed, i.e., the vectorized route is filtered out. Finally, the target route set is determined based on the last updated initial route set.

[0109] If multiple vectorized routes are not grouped, the initial route set after the last update is used as the target route set. If multiple vectorized routes are grouped, the union of the initial route sets after the last update for each group is used as a new initial set. Then, based on the sub-vectors of each vectorized route in the new initial set and the new overlay set (which is initialized to be empty), it is determined whether to retain the corresponding vectorized route, thereby determining the final target route set.

[0110] Therefore, by analyzing the coverage set of each vectorized route and the covered sub-vectors, the retention or rejection of that vectorized route can be determined. This deduplication method only needs to calculate all routes, unlike the massive computational cost of comparing vectorized routes pairwise (e.g., with tens of millions of routes, the computational cost is tens of millions multiplied by tens of millions). Thus, this deduplication method can quickly select the route set for validating the map service, i.e., test cases, while saving computational resources.

[0111] Optionally, for each vectorized route, based on the vectorized route and the coverage set, determine whether to retain the vectorized route, including:

[0112] Divide the multiple vectorized routes into at least one initial set;

[0113] For each initial set, the vectorized routes in the initial set are sorted in descending order of the number of key points contained;

[0114] Based on the sorting results, the vectorized target routes of the corresponding order are retrieved from the initial set in sequence;

[0115] For each vectorized target route extracted sequentially, it is determined whether the vectorized target route should be retained based on the vectorized target route and the coverage set.

[0116] In this embodiment, if the number of routes to be processed does not reach a predetermined level, deduplication is performed on the vectorized routes. Compared to deduplication by comparing routes pairwise, this saves computational resources, improves processing efficiency, and ensures the accuracy of the processing results. Furthermore, since this deduplication algorithm itself has divide-and-conquer properties (parallel processing does not affect the final result), if the number of routes to be processed is large, parallel processing can be achieved through MapReduce, greatly improving processing efficiency. For example, tens of millions of online data points can be processed within hourly time units.

[0117] Specifically, if the number of routes is small, all vectorized routes can be used as an initial set, and the updated initial route set obtained through this step is the target route set. If the number of routes is large, they can be divided into multiple initial sets, and the same deduplication process can be performed on each initial set. Then, the deduplication results of each initial set are merged as a new initial set, and the same processing steps are performed again to obtain the final target route set.

[0118] In the deduplication process for each initial set, target routes are selected in a sorted order. This process prioritizes longer routes while removing as many shorter routes as possible, resulting in a smaller but more comprehensive set of target routes. These routes are then used as test cases in subsequent verification processes, reducing redundant work. Furthermore, storing the route sets as vectors (vector features) also reduces memory usage. Specifically, the route with the most key points is selected first. If this route is chosen, the initial route set will contain the longest routes with the most key points. For example, the sorted route A→B→C might be selected first, rather than two routes, A→B and B→C.

[0119] Optionally, determining whether to retain the vectorized target route based on the vectorized target route and the coverage rate includes:

[0120] Generate a sub-vector set from the sub-vectors in the vectorized target route;

[0121] Based on the intersection of the sub-vector set and the coverage set, and the sub-vector set, determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold. If it is less, then determine to retain the vectorized target route.

[0122] Optionally, the initial route set is updated based on the vectorized routes, including:

[0123] The union of the initial route set and the set formed by the vectorized target routes is used as the updated initial route set;

[0124] Optionally, the coverage set is updated based on the sub-vectors in the vectorized route, including:

[0125] The union of the covering set and the subvector set is taken as the updated covering set.

[0126] In this embodiment, ideally, the entire route set should not contain any overlapping routes. In practice, the repetition rate of routes is calculated (i.e., the proportion of sub-vectors overlapping with other routes in the vector), and only routes with a repetition rate less than a preset repetition threshold are selected. The specific steps for deduplicating the multiple vectorized routes to obtain the target route set can be as follows:

[0127] Step a: Divide the multiple vectorized routes into at least one initial set, and initialize the initial route set to empty.

[0128] Step b: For each initial set, repeat the following steps until the initial set is empty: Take the vectorized target route (which can be the first route) containing the most key points from the initial set, and extract the sub-vectors from the vectorized target route to generate a sub-vector set. The sub-vectors are composed of the vector features of every two adjacent key points in the vectorized target route. Based on the intersection of the sub-vector set and the coverage set, determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold. If it is less, determine to retain the vectorized target route, and take the union of the initial route set and the set formed by the vectorized target routes as the updated initial route set. The updated initial route set contains the vectorized target routes retained after the current deduplication. Take the union of the coverage set and the sub-vector set as the updated coverage set. The initial coverage set is empty, and the initial route set is empty.

[0129] Step c: Determine the target route set based on the updated initial route set corresponding to each initial set, and store the vector features of each key point in the target route set.

[0130] Specifically, in scenario 1: if the initial set is one, then the updated initial route set is the target route set.

[0131] Multiple vectorized routes are used as an initial set, and the vectorized routes in this initial set are sorted in descending order of the number of key points they contain;

[0132] Based on the sorting results, the vectorized target routes of the corresponding order are retrieved from the initial set in sequence;

[0133] For each vectorized target route extracted sequentially, repeat the following steps until the last vectorized target route is extracted: Generate a sub-vector set from the sub-vectors in the vectorized target route; determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold based on the intersection of the sub-vector set and the coverage set, and the sub-vector set itself; if less, retain the vectorized target route; use the union of the initial route set and the set formed by the vectorized target routes as the updated initial route set, which includes the vectorized target routes retained after the current deduplication; use the union of the coverage set and the sub-vector set as the updated coverage set.

[0134] Use the initial route set after the last update to determine the target route set.

[0135] An exemplary standard route production process: Step 1. Select routes that meet the business requirements from all target areas in the online database, vectorize the key points of all routes, and use all vectorized routes as the initial set S.

[0136] Step 2. Set the initial route set T = {}, the coverage set (or coverage set) G = {}, and the repetition threshold t.

[0137] Step 3. Extract the route s with the most key navigation points (i.e., navigation points or key points) from S, extract the sub-vectors formed by all adjacent navigation points in s, and generate a set (i.e., a sub-vector set) s. G ={(k i k i+1 )|i=1...(|s G |-1)}.

[0138] Step 4. Calculate the intersection of the sub-vector set and the existing covered set G, let set s′. G =s G ∩G.

[0139] Step 5. If satisfied This indicates that s is a route containing many uncovered routes. In this case, execute T = T∪{s} and G = G∪{s}. G}. Otherwise, skip directly. Where, |s′ G | represents s′ G Size of the set; |s G | indicates s G The size of the set.

[0140] Step 6. Repeat steps 3-5 for all elements in S until all routes have been processed. The resulting set T is the minimum repeating maximum coverage set (referring to the target route set).

[0141] Specifically, the process of using set representation is as follows:

[0142] 01. The set of all covers G is a data structure stored using an adjacency list to store all sub-vectors of the route set;

[0143] 02. For a route with M key points, its subvector set is:

[0144] s G =(A1,A2),(A2,A3),...,(A M-1 A M )

[0145] 03. Regarding s G Each vector (A) x A x+1 Verify that it exists in the covering set G:

[0146] 031. Verify if A exists in the adjacency list. x If the index of the vector does not exist, it means that the vector definitely does not exist.

[0147] 032. If an index exists, then use the index to check if table A exists in the corresponding table structure. x+1 If the vector exists, it means that the vector already exists in the covering set; otherwise, it does not exist.

[0148] 04. The above method can be used to quickly determine s G The size of the intersection with G |s′ G |, if satisfied Then all vectors are added to the covering set G. At this point, for s G Each vector (A) x A x+1 ):

[0149] 041. If A does not exist in the adjacency list x If the index is used, a new table structure will be created, with the initial element being A. x+1 and add A x Indexes to this table structure are added to the adjacent table.

[0150] 042. Otherwise, find A based on the index. x The corresponding table structure, if A x+1 If it does not exist in the list, then A will be... x+1 Add to the list.

[0151] Result set verification

[0152] Whether the route set obtained after deduplication based on navigation key points meets the initial expectations is verified by using both navigation key points and actual route trajectories to confirm the completeness of the road network data.

[0153] Scenario 2: If there are multiple initial sets, then the updated initial route sets corresponding to each initial set are used to determine the target route set:

[0154] Step d: Divide the multiple vectorized routes into multiple initial sets, and execute step b above;

[0155] Step e: Take the updated initial route set corresponding to each initial set as the new initial set, and perform deduplication according to step b above. That is, for each vectorized route in the new initial set (which can be the second route), repeat the following steps until the new initial set is empty: Take the vectorized target route with the most key points from the new initial set, and extract the sub-vectors in the vectorized target route to generate a sub-vector set. The sub-vectors are composed of the vector features of every two adjacent key points in the vectorized target route. Based on the intersection of the sub-vector set and the new coverage set and the sub-vector set, determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold. If it is less, determine to retain the vectorized target route, and take the union of the new initial route set and the set formed by the vectorized target routes as the updated new initial route set. The updated new initial route set contains the vectorized target routes left after the current deduplication. Take the union of the new coverage set and the sub-vector set as the updated new coverage set. The newly initialized coverage set is empty, and the newly initialized initial route set is empty.

[0156] Specifically, for massive amounts of online data, MapReduce capabilities can be used to quickly and distributedly filter batches of data to obtain the minimum set of routes with an overlap rate below a specified threshold. For an example, see [link to example]. Figure 3 As shown, the vectorized route (i.e., S) is first divided into N equal groups: S1, S2, ..., S N Each of these serves as one of N Map stages (Map1, Map2, ..., Map3). N The input is the Map phase. Then, each Map phase outputs results using a standard route production process. The union of all Map phase results is then used as the input for the Reduce phase. Finally, the Reduce phase is run to obtain the final set of routes.

[0157] Therefore, the purpose of deduplication is achieved by using set intersection and union calculation. The processing logic is simple, and it can quickly select the smallest set of routes that is most likely to be complete in the specified area, ensuring the coverage after deduplication, while reducing the amount of repetitive work in the verification stage.

[0158] Optionally, the method further includes:

[0159] The key points contained in the target route set are plotted on the map of the target area to determine whether there are any uncovered areas; and / or, by replanning the routes contained in the target route set, each trajectory point is obtained and plotted as a screen to determine whether there are any uncovered areas on the map of the target area.

[0160] If such a region exists, a strategy for updating the target route set is determined based on the number or range of the uncovered regions, in order to update the target route set.

[0161] In this embodiment of the application, the completeness of the road network data is verified (or validated) by using two dimensions: navigation key points and actual route trajectory, to determine whether the route set obtained after deduplication based on navigation key points meets the initial expectations.

[0162] Specifically, if the range of the gap (i.e. the uncovered area) is relatively small or the number of gaps is relatively small, the strategy that can be used is to obtain a route containing each target key point from the multiple routes or to obtain a vectorized route containing each target key point from the multiple vectorized routes; and to update the target route set based on the route containing each target key point or the vectorized route containing each target key point.

[0163] If the range of the gap is large or the number of gaps is large, a new target route set can be obtained by repeating the above-described process for determining the target route set, thus updating the target route set.

[0164] For example, see Figure 4 As shown, the key points contained in the target route set are plotted on the map of the target area to determine if there are any uncovered areas. This is used to verify the accuracy of the deduplication algorithm and to determine whether the target dataset is the set of routes in the target area that can cover all navigation points to the maximum extent and has the fewest duplicate routes. Navigation key points are plotted on the target area using the map open API, and the map is visually inspected for any obvious gaps. For example, the key points are plotted on the current map 10 of the target area for comparison (combined with...). Figure 4 As shown in the image (key points are plotted on map 10), check for any obvious gaps, i.e., any obvious uncovered areas.

[0165] See Figure 5As shown, by replanning the routes contained in the target route set, obtaining each trajectory point, and plotting each trajectory point on a screen, it is determined whether there are uncovered areas on the map of the target area. This is used to verify the accuracy of the deduplication algorithm, and further determine whether the target dataset is a set of routes in the target area that can maximize the coverage of all navigation points and minimize the number of repeated routes. Using navigation services, the selected routes are replanned to obtain real trajectory points, and these trajectory points are visually plotted on a screen to quickly check for any obvious gaps. Combined with... Figure 5 As shown, for example, the road network is compared to the current map 10 covering the target area (in conjunction with...). Figure 5 As shown in the image (the road network is covered on map 10), check if there are any obvious gaps, i.e., if there are any obvious uncovered areas.

[0166] It should be noted that, Figure 4 and Figure 5 This is merely an example; no restrictions are placed on the generated images, which need to be determined based on the actual scenario.

[0167] Therefore, the coverage of the obtained target route set can be checked by drawing it. This verification and updating method can improve the coverage of the target route set, thereby improving the accuracy of subsequent map or navigation testing or verification.

[0168] Optionally, the method further includes:

[0169] Store the target route set.

[0170] In this embodiment, the final selected route set is stored. During subsequent verification, this route set can be used either immediately or stored later, offering flexibility.

[0171] Optionally, the method further includes:

[0172] Based on the target route set, generate the road network corresponding to the target area;

[0173] The road network is used to support the verification of the map service corresponding to the target area.

[0174] In practical applications, based on the generated road network, real road segments are verified or validated through navigation services. During this process, testers can use the navigation function to test whether the map rendering is incorrect, whether the loading is incorrect, whether the navigation effect is unstable or has errors, etc., thus accurately testing or validating the map service.

[0175] In this embodiment of the application, a definition of repeated online user navigation routes is established based on the characteristics of navigation services (repeated routes have the same key points). Based on the definition of repeated navigation routes, a method is proposed to construct a specified area that satisfies the maximum route coverage while having the minimum repetition rate. Moreover, this method itself can be parallelized through MapReduce, which greatly improves processing efficiency.

[0176] Therefore, this application makes the verification effective by processing historical navigation routes that have real coverage of the target area. By vectorizing the full set of historical navigation routes and then deduplicating the vectorized routes, the coverage can be guaranteed while reducing a lot of repetitive work in the verification stage, thereby ensuring the accuracy and efficiency of the verification or testing map service.

[0177] Corresponding to the above information processing method, embodiments of this application provide an information processing apparatus. Figure 6 This is a schematic diagram of the structure of an information processing device provided in an embodiment of this application. The device includes:

[0178] The first processing module 601 is used to obtain multiple routes in the target area; wherein, the routes are historical navigation routes provided by the navigation service, and the multiple historical navigation routes meet the coverage of the target area;

[0179] The second processing module 602 is used to perform vectorization processing on the multiple routes to obtain the corresponding multiple vectorized routes;

[0180] The third processing module 603 is used to deduplicate the multiple vectorized routes to obtain a target route set; the target route set is used to verify the map service corresponding to the target area.

[0181] The information processing apparatus provided in this application embodiment can be used to perform the above-described... Figures 1 to 5 The technical solutions of the embodiments shown are similar in principle and in effect, and will not be described again here.

[0182] Optional, the first processing module is specifically used for:

[0183] For each route, key points are extracted from the route, and these key points are used to represent the locations that serve as feature markers during the map navigation process;

[0184] Vectorize each key point on the route to obtain the vector features of each key point on the route;

[0185] Based on the vector features of each key point on the route, a vectorized route is obtained; wherein the vectorized route is composed of the vector features of consecutive key points.

[0186] Optionally, the device further includes: a third processing module, further configured to:

[0187] The location information issued by the navigation service is analyzed to obtain the analysis results, which show that the overlapping parts of any two routes have the same key points.

[0188] Based on the analysis results, the characteristics of the overlapping routes corresponding to the two different routes are determined, wherein the overlapping routes contain overlapping sub-vectors.

[0189] Based on the aforementioned characteristics, duplicates are removed from the multiple vectorized routes to obtain the target route set.

[0190] Optionally, the third processing module includes: a first processing unit, a second processing unit, a third processing unit, and a fourth processing unit;

[0191] The first processing unit is used to extract sub-vectors from the multiple vectorized routes; the sub-vectors are determined by the vector features of two adjacent key points;

[0192] The second processing unit is used to determine whether to retain the vectorized route for each vectorized route based on the sub-vectors and the covering set in the vectorized route; wherein, the initial covering set is empty, and the covering set is used to represent the set of covered sub-vectors;

[0193] The third processing unit is used to update the initial route set according to the vectorized route when it is determined to retain a route, and to update the coverage set according to the sub-vectors in the vectorized route, in order to determine whether the next vectorized route should be retained; wherein, the initial route set is empty.

[0194] The fourth processing unit is used to determine the target route set based on the initial route set after the last update.

[0195] Optionally, the second processing unit is specifically used for:

[0196] Divide the multiple vectorized routes into at least one initial set;

[0197] For each initial set, the vectorized routes in the initial set are sorted in descending order of the number of key points contained;

[0198] Based on the sorting results, the vectorized target routes of the corresponding order are retrieved from the initial set in sequence;

[0199] For each vectorized target route extracted sequentially, it is determined whether the vectorized target route should be retained based on the vectorized target route and the coverage set.

[0200] Optionally, the second processing unit is specifically used for:

[0201] Generate a sub-vector set from the sub-vectors in the vectorized target route;

[0202] Based on the intersection of the sub-vector set and the coverage set, and the sub-vector set, determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold. If it is less, then determine to retain the vectorized target route.

[0203] The third processing unit is specifically used for:

[0204] The union of the initial route set and the set formed by the vectorized target routes is used as the updated initial route set;

[0205] The third processing unit is also specifically used for:

[0206] The union of the covering set and the subvector set is taken as the updated covering set.

[0207] Optionally, the device further includes: a fifth processing module, used for:

[0208] The key points contained in the target route set are plotted on the map of the target area to determine whether there are any uncovered areas; and / or, by replanning the routes contained in the target route set, each trajectory point is obtained and plotted as a screen to determine whether there are any uncovered areas on the map of the target area.

[0209] If such a region exists, a strategy for updating the target route set is determined based on the number or range of the uncovered regions, in order to update the target route set.

[0210] Optionally, the device further includes: a storage module, used for:

[0211] Store the target route set.

[0212] Optionally, the device further includes: a sixth processing module, used for:

[0213] Based on the target route set, generate the road network corresponding to the target area;

[0214] The road network is used to support the verification of the map service corresponding to the target area.

[0215] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device in this embodiment may include:

[0216] At least one processor 701; and

[0217] Memory 702 communicatively connected to the at least one processor;

[0218] The memory 702 stores instructions that can be executed by the at least one processor 701 to cause the electronic device to perform the method as described in any of the above embodiments.

[0219] Optionally, the memory 702 can be either standalone or integrated with the processor 701. Optionally, the memory 702 can be connected to the processor 701 via bus 703.

[0220] The implementation principle and technical effects of the electronic device provided in this embodiment can be found in the foregoing embodiments, and will not be repeated here.

[0221] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method described in any of the foregoing embodiments.

[0222] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the methods described in any of the foregoing embodiments.

[0223] The technical solution of this application involves the collection, storage, use, processing, transmission, provision, and disclosure of various information of users and merchants, which all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0224] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0225] The integrated modules implemented as software functional modules described above can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application.

[0226] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor. The memory may include high-speed RAM, and may also include non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk, or optical disc, etc.

[0227] The aforementioned storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0228] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0229] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0230] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0231] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0232] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An information processing method, characterized in that, The method includes: Obtain multiple routes within the target area; wherein, the routes are historical navigation routes provided by the navigation service, and the multiple historical navigation routes meet the coverage requirements of the target area; The multiple routes are vectorized to obtain corresponding vectorized routes; the vectorized routes are composed of vector features of continuous key points, which are used to represent the positions marked as features in the map navigation process; Based on the sub-vectors and coverage set in the vectorized routes, duplicates are removed from the multiple vectorized routes to obtain a target route set. The repetition of each route in the target route set is less than a preset repetition threshold, and the coverage rate of the sub-vectors of each route in the coverage set is less than a preset coverage rate threshold, which is used to verify the map service corresponding to the target area. The sub-vectors are determined by the vector features of two adjacent key points, and the coverage set is used to represent the set of covered sub-vectors, and the initial coverage set is empty.

2. The method according to claim 1, characterized in that, The multiple routes are vectorized to obtain corresponding vectorized routes, including: For each route, extract the key points along that route; Vectorize each key point on the route to obtain the vector features of each key point on the route; Based on the vector features of each key point on the route, the vectorized route is obtained.

3. The method according to claim 1 or 2, characterized in that, Based on the sub-vectors and coverage set in the vectorized routes, duplicates are removed from the multiple vectorized routes to obtain the target route set, including: Extract sub-vectors from the multiple vectorized routes; For each vectorized route, determine whether to retain the vectorized route based on the sub-vectors and coverage set in the vectorized route; If retained, the initial route set is updated according to the vectorized route, and the cover set is updated according to the sub-vectors in the vectorized route to determine whether the next vectorized route should be retained; wherein, the initial route set is empty. Determine the target route set based on the initial route set after the last update.

4. The method according to claim 3, characterized in that, For each vectorized route, based on the vectorized route and the coverage set, determine whether to retain the vectorized route, including: Divide the multiple vectorized routes into at least one initial set; For each initial set, the vectorized routes in the initial set are sorted in descending order of the number of key points contained; Based on the sorting results, the vectorized target routes of the corresponding order are retrieved from the initial set in sequence; For each vectorized target route extracted sequentially, it is determined whether the vectorized target route should be retained based on the vectorized target route and the coverage set.

5. The method according to claim 4, characterized in that, Determining whether to retain the vectorized target route based on the vectorized target route and the coverage rate includes: Generate a sub-vector set from the sub-vectors in the vectorized target route; Based on the intersection of the sub-vector set and the coverage set, and the sub-vector set, determine whether the coverage rate of the sub-vectors corresponding to the vectorized target route is less than a preset threshold. If it is less, then determine to retain the vectorized target route. Based on the vectorized routes, update the initial route set, including: The union of the initial route set and the set formed by the vectorized target routes is used as the updated initial route set; Update the coverage set based on the sub-vectors in the vectorized route, including: The union of the covering set and the subvector set is taken as the updated covering set.

6. The method according to claim 1 or 2, characterized in that, The method further includes: The key points contained in the target route set are plotted on the map of the target area to determine whether there are any uncovered areas; and / or, by replanning the routes contained in the target route set, each trajectory point is obtained and plotted as a screen to determine whether there are any uncovered areas on the map of the target area. If such a region exists, a strategy for updating the target route set is determined based on the number or range of the uncovered regions, in order to update the target route set.

7. The method according to claim 1 or 2, characterized in that, The method further includes: Store the target route set; The method further includes: Based on the target route set, generate the road network corresponding to the target area; The road network is used to support the verification of the map service corresponding to the target area.

8. An information processing device, characterized in that, include: The first processing module is used to obtain multiple routes in the target area; wherein, the routes are historical navigation routes provided by the navigation service, and the multiple historical navigation routes meet the coverage of the target area; The second processing module is used to vectorize the multiple routes to obtain corresponding multiple vectorized routes; the vectorized routes are composed of vector features of continuous key points, and the key points are used to represent the positions used as feature markers in the map navigation process; The third processing module is used to deduplicate the multiple vectorized routes based on the sub-vectors and coverage set in the vectorized routes to obtain a target route set. The repetition degree of each route in the target route set is less than a preset repetition threshold, and the coverage rate of the sub-vectors of each route in the coverage set is lower than a preset coverage rate threshold, which is used to verify the map service corresponding to the target area. The sub-vectors are determined by the vector features of two adjacent key points, and the coverage set is used to represent the set of covered sub-vectors, and the initial coverage set is empty.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory that is communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform the method according to any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images