Map vector matching methods, apparatus, devices, storage media, and software products

Abstract

This disclosure relates to map vector matching methods, apparatus, devices, storage media, and program products. The method includes: acquiring a target vector and its corresponding at least one spatially related vector from a high-precision base map, and acquiring candidate matching vectors from an updated map; generating vector features of the vector to be processed based on its vector position, vector type, and relative relationship information with other vectors; the vector to be processed includes the target vector or any candidate matching vector; when the vector to be processed is the target vector, the other vectors are spatially related vectors, and the vector features are those of the target vector; when the vector to be processed is a candidate matching vector, the other vectors are candidate matching vectors other than the target vector, and the vector features are those of the candidate vector; performing vector matching based on the target vector features and the candidate vector features to determine the target matching vector of the target vector. This improves the uniqueness of vector representation and the accuracy of vector matching.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, and in particular to a map vector matching method, apparatus, device, storage medium, and program product. Background Technology

[0002] To meet the development needs of intelligent driving technology, electronic maps with high absolute positioning accuracy (referred to as high-precision maps) have emerged. During the development of high-precision maps, scenarios requiring vector matching arise, such as comparing high-precision maps from different manufacturers and updating different versions of high-precision maps from the same manufacturer.

[0003] Currently, vector matching schemes in high-definition maps primarily pair vectors based on whether their geometric types (or simply vector types) are consistent and whether the distance differences between vectors meet certain requirements. However, due to the large number of vectors in high-definition maps, the accuracy of vector matching pairs obtained by this method is relatively low. Summary of the Invention

[0004] To address the technical problem of low accuracy in vector matching in high-precision maps, this disclosure provides a map vector matching method, apparatus, device, storage medium, and program product.

[0005] Firstly, this disclosure provides a map vector matching method, including:

[0006] Obtain the target vector and at least one spatial correlation vector corresponding to the target vector in the high-precision base map, and obtain each candidate matching vector corresponding to the target vector in the updated map;

[0007] Based on the vector position, vector type, and relative relationship information between the vector to be processed and other vectors, vector features of the vector to be processed are generated; wherein, the vector to be processed includes the target vector or any of the candidate matching vectors; when the vector to be processed is the target vector, the other vectors include the spatially related vectors, and the vector features are target vector features; when the vector to be processed is the candidate matching vector, the other vectors include the candidate matching vectors other than the candidate matching vector, and the vector features are candidate vector features;

[0008] Vector matching is performed based on the target vector features and the candidate vector features, and a target matching vector that matches the target vector is determined from the candidate matching vectors.

[0009] Secondly, this disclosure also provides a map vector matching device, comprising:

[0010] The vector acquisition module is used to acquire the target vector in the high-precision base map and at least one spatially related vector corresponding to the target vector, and to acquire each candidate matching vector corresponding to the target vector in the updated map;

[0011] The vector feature generation module is used to generate vector features of the vector to be processed based on the vector position, vector type, and relative relationship information between the vector to be processed and other vectors; wherein, the vector to be processed includes the target vector or any of the candidate matching vectors; when the vector to be processed is the target vector, the other vectors include the spatially related vectors, and the vector features are target vector features; when the vector to be processed is the candidate matching vector, the other vectors include the candidate matching vectors other than the target matching vector, and the vector features are candidate vector features.

[0012] The target matching vector determination module is used to perform vector matching based on the target vector features and each of the candidate vector features, and to determine the target matching vector that matches the target vector from each of the candidate matching vectors.

[0013] Thirdly, this disclosure also provides an electronic device, including:

[0014] A memory and a processor, wherein the memory is used to store executable instructions of the processor;

[0015] The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the map vector matching method provided in any embodiment of this disclosure.

[0016] Fourthly, this disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the map vector matching method provided in any embodiment of this disclosure.

[0017] Fifthly, this disclosure also provides a computer program product for executing the map vector matching method provided in any embodiment of this disclosure.

[0018] Compared with the prior art, the map vector matching technical solution provided in this disclosure has at least the following advantages: To avoid the problem of vector matching errors caused by relying solely on the vector's own vector position and vector type attributes, vector features of each vector participating in vector matching (target vector in the high-precision base map and each candidate matching vector in the updated map) are constructed. In constructing the vector features of each vector, in addition to using the vector's own vector position and vector type attributes, relevant information that can characterize the relative relationship between the vector and other vectors in the same map (i.e., relative relationship information) is also incorporated, thereby obtaining vector features that can uniquely identify the vector, improving the uniqueness and accuracy of each vector's characterization. Then, the target vector features of the target vector and the candidate vector features of each candidate matching vector are used to perform vector matching, improving the accuracy of vector matching, thereby providing more accurate basic data for subsequent processes. Attached Figure Description

[0019] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 A schematic diagram of a vector matching error provided in an embodiment of this disclosure;

[0021] Figure 2 This is a schematic diagram of another vector matching error provided in an embodiment of the present disclosure;

[0022] Figure 3 A schematic flowchart of a map vector matching method provided in an embodiment of this disclosure;

[0023] Figure 4 A schematic diagram illustrating the principle of determining a vector within a target range, provided by an embodiment of this disclosure;

[0024] Figure 5 for Figure 3 The diagram shows the refinement process of S320 in the map vector matching method.

[0025] Figure 6 for Figure 3 The diagram shows the refinement process of S330 in the map vector matching method.

[0026] Figure 7 This is a schematic diagram of the structure of a map vector matching device provided in an embodiment of the present disclosure;

[0027] Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0028] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0029] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0030] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0031] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0032] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0033] In the operation of high-precision maps, there are processes such as vector subtraction, vector evaluation, and vector updating. A fundamental operation in these processes is vector matching. Currently, the most common vector matching method is to pair vectors using their own attributes, such as vector type and location. However, due to the large number of vectors, the complexity of vector types, and the relatively clustered distribution of vectors in high-precision maps, the matching accuracy of the above-mentioned vector matching scheme is relatively low.

[0034] For example, Figure 1The image shows vectors (solid lines) contained in a high-precision base map (the original high-precision map that has not been updated) and vectors (dashed lines) contained in the corresponding updated map (a high-precision map created by mapping an area that already has a high-precision base map). In this example, a positioning error during the relocation process caused the updated map to shift by one lane relative to the high-precision base map. In this case, if vector matching is performed using a vector matching method from related technologies, "Ground Marker 2" in the updated map would be matched with "Ground Marker 1" in the high-precision base map as a single vector pair, resulting in a vector matching error.

[0035] For example, Figure 2 The example also shows the vectors contained in the high-precision base map and the corresponding vectors contained in the updated map. However, due to a certain positioning error, the updated map is slightly offset relative to the high-precision base map. In this case, if vector matching is performed according to the vector matching method in related technologies, it is easy for similar vectors to be mismatched, such as mismatching "card 1" in the updated map with "card 2" in the high-precision base map.

[0036] Based on the above, this disclosure provides a map vector matching method to construct vector features of corresponding vectors during the vector matching process of high-precision maps by utilizing the vector position and vector type attributes of each vector, as well as relevant information (i.e., relative relationship information) that can characterize the spatial relative relationship between the vector and other vectors in the same map. This improves the uniqueness and accuracy of vector characterization, and then uses these vector features to perform vector matching, thereby improving the accuracy of vector matching.

[0037] Figure 3 This is a flowchart illustrating a map vector matching method provided in an embodiment of the present disclosure, applicable to scenarios involving vector matching in high-precision maps. The map vector matching method can be executed by a map vector matching device, which can be implemented in software and / or hardware and integrated into an electronic device with computing capabilities. This electronic device can be, for example, a laptop computer, a desktop computer, or a server.

[0038] like Figure 3 As shown, the map vector matching method provided in this embodiment may include:

[0039] S310. Obtain the target vector and at least one spatial correlation vector corresponding to the target vector in the high-precision base map, and obtain each candidate matching vector corresponding to the target vector in the updated map.

[0040] The high-precision base map and the updated map are two high-precision maps within the same area that need to be compared / updated. The high-precision base map can be a baseline / reference map, and the updated map can be the map to be compared / updated. The target vector is the vector in the high-precision base map for which a matching vector is to be found. The spatially related vector is a vector in the high-precision base map that has a spatial correlation with the target vector, excluding the target vector. The candidate matching vector is a vector in the updated map.

[0041] Specifically, according to the above description, in the vector matching process of this disclosure embodiment, each vector needs to be described, that is, vector features need to be constructed. This construction process requires the use of vectors other than the vector to be processed (referred to as the vector to be processed). Therefore, before constructing the vector features, the electronic device needs to acquire the target vector in the high-precision base map and at least one spatially related vector in the high-precision base map. Simultaneously, the electronic device needs to locate a suitable position in the updated map based on the target vector and acquire at least two candidate matching vectors based on this location to ensure the reasonable construction of the vector features of the candidate matching vectors.

[0042] The aforementioned target vector, spatial correlation vector, and candidate matching vector can be obtained by directly reading the corresponding vectors from the high-precision base map and the updated map from the storage medium, or by pulling the corresponding vectors from the high-precision base map and the updated map from the network.

[0043] In some embodiments, the target vector and spatial correlation vector are extracted from the high-precision base map, and the candidate matching vector is extracted from the updated map. That is, S310 includes: obtaining the target vector in the high-precision base map, and determining the target range based on the vector position and preset distance of the target vector; obtaining vectors other than the target vector within the target range of the high-precision base map as spatial correlation vectors; and obtaining each vector within the target range of the updated map as each candidate matching vector.

[0044] The preset distance is a pre-determined distance value, such as 50m. For example, the preset distance is determined based on the range distance when at least two different vectors are contained within a defined range. In this example, the preset distance can be statistically determined by analyzing the vector distribution across multiple maps according to the rule that at least two different vectors are contained within a defined range. For instance, ranges can be defined in different areas of different maps, ensuring that at least two vectors are contained within each defined range. Then, the dimensions / range distances of these defined ranges are statistically analyzed, such as the radius of a circular range, the length and width of a rectangular range, etc., and the mean, median, etc., of these statistically analyzed dimensions are used as the preset distance. This ensures that the number of vectors extracted subsequently meets the requirements for vector feature construction. The target range is the range defined during this vector matching process.

[0045] Specifically, the electronic device can extract any vector from the high-precision base map as the target vector, or extract a vector from the high-precision base map as the target vector according to business requirements. Then, using the position of the target vector as the center, the target range is determined according to a preset distance and shape. For example, Figure 4 In this process, the electronic device can use "card 3" as the center and a preset distance as the radius to obtain a circular area as the target range.

[0046] Then, the electronic device extracts at least one vector other than the target vector from the vectors contained in the target range as a spatial correlation vector.

[0047] Subsequently, the electronic device locates the corresponding position from the updated map according to the vector position of the target vector, and forms the target range in the updated map with the located position as the center, according to the preset distance and the range shape, and extracts at least two vectors from the target range as candidate matching vectors.

[0048] S320. Based on the vector position, vector type, and relative relationship information between the vector to be processed and other vectors, generate vector features of the vector to be processed; wherein, the vector to be processed includes a target vector or any candidate matching vector; when the vector to be processed is a target vector, other vectors include spatially related vectors, and the vector features of the vector to be processed are target vector features; when the vector to be processed is a candidate matching vector, other vectors include candidate matching vectors other than the candidate matching vector, and the vector features of the vector to be processed are candidate vector features.

[0049] In this context, vector position refers to the coordinates of the vector, which can be the coordinates of the vector's center or a node within the vector. Vector type refers to the geometric type of the vector, such as point, line, or area. Other vectors are vectors other than the vector to be processed. Vector features are the descriptive information of the vector to be processed. Relative relationship information refers to the representation of spatial relative relationships, such as relative distance or relative orientation.

[0050] Specifically, the construction process for the vector features of the target vector and each candidate matching vector is the same. Therefore, the electronic device can use the target vector or any candidate matching vector as the vector to be processed. Then, it acquires the vector position, vector type, and relative relationship information between the vector to be processed and other vectors, and combines the vector position, vector type, and relative relationship information to form the vector features of the vector to be processed.

[0051] Given that the combination of attributes such as vector position and vector type can distinguish vectors to a certain extent, and that the spatial relative relationship between a vector and other vectors in its space has more differentiated characteristics, the present invention utilizes the vector's own attributes and its spatial relative relationship with other vectors to construct vector features, which can greatly improve the uniqueness of vector representation and the accuracy of vector differentiation, thereby greatly improving the accuracy of vector matching using these vector features.

[0052] In one example, when the vector to be processed is a target vector, S320 can be implemented as follows: based on the target vector's vector position, vector type, and the relative relationship information between the target vector and spatially related vectors, generate the target vector's vector features (i.e., target vector features).

[0053] In another example, when the vector to be processed is a candidate matching vector, S320 can be implemented as follows: for each candidate matching vector, based on the vector position, vector type, and relative relationship information between the candidate matching vector and other candidate matching vectors, the vector features (i.e., candidate vector features) of the candidate matching vector are generated.

[0054] S330. Perform vector matching based on the target vector features and the features of each candidate vector, and determine the target matching vector that matches the target vector from each candidate matching vector.

[0055] Specifically, the electronic device can perform vector matching between the target vector feature and each candidate vector feature to obtain the corresponding matching degree. Then, each matching degree is compared with a matching degree threshold (a pre-set empirical value). If all matching degrees are not greater than the matching degree threshold, it is determined that the target vector within the target range has no paired target matching vector. If there is a matching degree greater than the matching degree threshold, the candidate matching vector corresponding to the candidate vector feature with that matching degree is determined as the target matching vector of the target vector. If there are multiple candidate vector features with matching degrees greater than the matching degree threshold, the candidate matching vector corresponding to the candidate vector feature with the highest matching degree can be determined as the target matching vector of the target vector, or a candidate matching vector corresponding to a candidate vector feature can be randomly selected from among them.

[0056] Once the electronic device has determined the target matching vector of the target vector, it can execute subsequent processes according to business requirements. For example, it can adjust the target matching vector to achieve alignment between the target vector and the target matching vector; or it can calculate the vector error between the target vector and the target matching vector to evaluate the accuracy of the target matching vector, and so on.

[0057] This disclosure provides a map vector matching method, which includes: acquiring a target vector and at least one spatially related vector corresponding to the target vector in a high-precision base map, and acquiring candidate matching vectors corresponding to the target vector in an updated map; generating vector features of the vector to be processed (corresponding to target vector features or candidate vector features) based on the vector position, vector type, and relative relationship information between the vector to be processed and other vectors; performing vector matching based on the target vector features and each candidate vector feature, and determining the target matching vector that matches the target vector from each candidate matching vector. Thus, by adding the relative relationship information of the spatial relationships between other vectors in the same map and the vector to be processed to the vector feature construction process of the vector to be processed, the uniqueness and accuracy of the representation of each vector to be processed are improved, thereby solving the problem of vector matching errors caused by relying solely on the vector's own vector position and vector type attributes, improving the accuracy of vector matching, and providing more accurate basic data for subsequent processes.

[0058] In some embodiments, such as Figure 5 As shown, Figure 3 The diagram illustrates the refinement process of S320 in the map vector matching method. (Refer to...) Figure 5 S320 "Generates vector features of the vector to be processed based on the vector position, vector type, and relative relationship information between the vector to be processed and other vectors", including:

[0059] S521. Based on the vector position and vector type of the vector to be processed, determine the local vector ID field.

[0060] Among them, the local vector ID field refers to the ID field that uses the attribute information of the vector to be processed itself to represent it.

[0061] Specifically, the electronic device constructs vector features by using the vector position and vector type of the vector to be processed as a field (i.e., the local vector ID field).

[0062] In some embodiments, since vector position and vector type are information that characterizes the intrinsic attributes of the vector to be processed, and contain more vector identification information, the local vector ID field can be used as the first field of the vector feature. For example, the local vector ID field is "vector position + vector type".

[0063] S522. Determine the relative vector ID field based on the relative distance and relative orientation between the vector to be processed and other vectors.

[0064] Among them, the relative vector ID field refers to the ID field characterized by using the relative relationship information between other vectors and the vector to be processed.

[0065] Specifically, the electronic device calculates the relative distance and relative orientation between the vector to be processed and the other vectors, based on the vector position and orientation of the vector to be processed, and the vector positions and orientations of the other vectors. Then, the relative distance and relative orientation corresponding to the other vector are used as the relative vector ID field. For example, the relative vector ID field is "relative distance + relative orientation".

[0066] S523. Combine the local vector ID field and the relative vector ID field to generate vector features.

[0067] Specifically, the electronic device concatenates the aforementioned local vector ID field and the aforementioned relative vector ID field to obtain the vector characteristics of the vector to be processed. For example, the vector characteristics can be represented as "vector position + vector type_relative distance + relative orientation".

[0068] The map vector matching method provided in the above embodiments of this disclosure can determine the local vector ID field based on the vector position and vector type of the vector to be processed; determine the relative vector ID field based on the relative distance and relative orientation between the vector to be processed and other vectors; and combine the local vector ID field and the relative vector ID field to generate vector features. This realizes the arrangement of vector position, vector type, relative distance, and relative orientation into vector features by field, thereby preserving the above information more completely and providing a more complete data foundation for subsequent vector matching.

[0069] In some embodiments, when there are multiple other vectors, the number of relative vector ID fields is the same as the number of other vectors. Therefore, determining the relative vector ID field based on the relative distance and relative orientation between the vector to be processed and other vectors includes: determining the relative vector ID field corresponding to each other vector based on the relative distance and relative orientation between the vector to be processed and each other vector. The electronic device uses the relative distance and relative orientation corresponding to each other vector as the relative vector ID field of the corresponding other vector.

[0070] Based on the above embodiments, the above-mentioned combination of the local vector ID field and the relative vector ID field to generate vector features includes: arranging each relative vector ID field in ascending order according to the relative distance corresponding to each other vector, and combining the local vector ID field and the sorted relative vector ID fields to generate vector features.

[0071] Specifically, considering that the number of vectors contained within the target range of the high-precision base map and the number of vectors contained within the target range of the updated map may be inconsistent, resulting in a discrepancy in the number of fields in the target vector features of the target vector and the candidate vector features of the candidate matching vector, which may cause inconvenience and some meaningless calculations in the subsequent vector matching process, as well as the problem that too many vectors in the target range result in a large amount of computation in the vector matching process, this embodiment of the disclosure can truncate all relative vector ID fields to a certain extent, thereby reducing the computational dimensionality and computational load, and thus improving the computational efficiency of vector matching. At the same time, in order to ensure the accuracy of vector matching, this embodiment takes into account that other vectors with smaller relative distances have a greater interference with the matching of the target vector and need to be taken into account more, so the relative vector ID fields can be truncated after being arranged in ascending order according to their corresponding relative distances.

[0072] In practice, the electronic device sorts the relative vector ID fields of each other vector in ascending order according to their relative distances, resulting in sorted relative vector ID fields. Then, the electronic device concatenates its own vector ID field with the sorted relative vector ID fields to generate a vector feature. For example, under the assumption that relative distance 1 < relative distance 2 < ... < relative distance n, the vector feature can be represented as "vector position + vector type_relative distance 1 + relative orientation 1_relative distance 2 + relative orientation 2_..._relative distance n + relative orientation n".

[0073] In some embodiments, such as Figure 6 As shown, Figure 3 The diagram illustrates the refinement process of S330 in the map vector matching method. (Refer to...) Figure 6 S330 "Perform vector matching based on target vector features and candidate vector features, and determine the target matching vector that matches the target vector from the candidate matching vectors", includes:

[0074] S631. Perform vector matching processing as follows (S6311 to S6313) for each candidate vector feature to obtain the total matching degree corresponding to each candidate vector feature.

[0075] The overall matching degree is the degree of matching between the candidate matching vector and the target vector.

[0076] Specifically, the electronic device can perform vector matching between the target vector and each candidate matching vector to find the best matching candidate vector. Therefore, the electronic device can perform the same vector matching process for each candidate matching vector.

[0077] S6311. Based on the differences in vector position and vector type, determine the matching degree of the local vector ID field between the local vector ID field in the target vector feature and the local vector ID field in the candidate vector feature.

[0078] Among them, the local field matching degree refers to the degree of matching between the information contained in the local vector ID field of two vectors.

[0079] Specifically, since the dimensions of the local vector ID field in the target vector feature and the candidate vector feature are the same, the electronic device can directly calculate the matching degree between the local vector ID field in the target vector feature and the local vector ID field in the candidate vector feature, that is, the local field matching degree.

[0080] For example, an electronic device can calculate the distance difference between the vector position in the local vector ID field of the target vector feature and the vector position in the local vector ID field of the candidate vector feature, and normalize this distance difference to the corresponding matching degree value according to a pre-set distance threshold, so as to ensure that the matching degree calculated in different dimensions can be used for the overall matching calculation. Similarly, the electronic device can compare whether the vector types in the two local vector ID fields are consistent, and normalize the result of whether they are consistent to the corresponding matching degree value.

[0081] S6312. Based on the differences in relative distance and relative orientation, determine the relative field matching degree between each relative vector ID field in the target vector feature and each relative vector ID field in the candidate vector feature.

[0082] Among them, relative field matching degree refers to the degree of matching between the information contained in the relative vector ID fields of two vectors.

[0083] Specifically, according to the above-mentioned method for calculating the matching degree of the local field, the electronic device can calculate the matching degree between the relative vector ID field in the target vector feature and the candidate vector feature.

[0084] In some embodiments, the vector correspondence between the high-precision base map and the updated map is relatively good, such as when the repositioning accuracy of the high-precision base map and the updated map is high or the relative vector relationships within the target area are relatively simple. In this case, there is a good field correspondence between the fields in the target vector features and the candidate vector features. For example, two relative vector ID fields with the same arrangement order correspond to the same vector. In this way, the electronic device can directly match a certain relative vector ID field in the target vector features with the corresponding relative vector ID fields in the candidate vector features and calculate their matching degree.

[0085] In other embodiments, the vector correspondence between the high-precision base map and the updated map is poor, or the vector correspondence is unclear. In this case, the electronic device can perform combination and calculation of the relative vector ID fields in a traversal manner to obtain the matching degree of the corresponding relative vector ID field combination. That is, S6312 includes: traversing each relative vector ID field in the target vector feature, and determining the relative field matching degree between the relative vector ID field in the traversed target vector feature and each relative vector ID field in the candidate vector feature based on the difference in relative distance and the difference in relative orientation.

[0086] Specifically, given the unclear correspondence between the relative vector ID fields, in order to improve the accuracy of the subsequent overall matching degree calculation, this embodiment performs mutual combination and relative field matching degree calculation on each relative vector ID field in the target vector feature and each relative vector ID field in the candidate vector feature. For example, the target vector feature includes four relative vector ID fields numbered 1, 2, 3, and 4, and the candidate vector feature includes four relative vector ID fields numbered A, B, C, and D. Then, the electronic device calculates the relative field matching degree of the relative vector ID field combinations of 1-A, 1-B, 1-C, 1-D, 2-A, 2-B, 2-C, 2-D, 3-A, 3-B, 3-C, 3-D, 4-A, 4-B, 4-C, and 4-D, respectively.

[0087] When the number of relative vector ID fields in the target vector features and candidate vector features is inconsistent, the relative field matching degree of the combination with missing relative vector ID fields can be set to 0 and participate in the subsequent calculation of the total matching degree to further improve the accuracy of the total matching degree.

[0088] S6313. The matching degree of the local field and the matching degree of each relative field are weighted and summed using the weights of each target to obtain the total matching degree between the target vector features and the candidate vector features.

[0089] The target weight is a predetermined weighting weight, which can be set by human experience or calculated according to some rules. This implementation scheme can be found in the relevant description of the following embodiments.

[0090] Specifically, the electronic device uses the target weights corresponding to the local field matching degree and the relative field matching degree to perform a weighted summation calculation to obtain the total matching degree between the target vector feature and the candidate vector feature.

[0091] For the implementation of calculating the matching degree between two relative vector ID fields corresponding to the arrangement order, the electronic device can directly perform a weighted summation of the matching degree of the local field and the matching degree of each relative field to obtain a total matching degree corresponding to the candidate vector feature.

[0092] For the above implementation method of traversing the relative vector ID field in the target vector feature to calculate its relative field matching degree with each relative vector ID field in the candidate vector feature, S6313 includes: arranging and combining each relative vector ID field in the target vector feature and each relative vector ID field in the candidate vector feature to obtain multiple field combinations; using each target weight, performing weighted summation on the matching degree of the current field and the matching degree of each relative field corresponding to each field combination to obtain the initial matching degree corresponding to the corresponding field combination; and determining the maximum value among the initial matching degrees as the total matching degree between the target vector feature and the candidate vector feature.

[0093] Specifically, continuing with the example of the target vector features including four relative vector ID fields numbered 1, 2, 3, and 4, and the candidate vector features including four relative vector ID fields numbered A, B, C, and D, the electronic device can use the relative vector ID fields contained in the target vector features as a basis, and according to the rule that the selected relative vector ID fields cannot be recombined, arrange and combine the relative field matching degrees of the obtained relative vector ID field combinations to obtain multiple combinations of relative field matching degrees. For example, the electronic device can obtain a combination of relative field matching degrees of 1-A, 2-C, 3-D, and 4-B, or a combination of relative field matching degrees of 1-A, 2-D, 3-B, and 4-C, and so on.

[0094] Then, the electronic device uses the target weights to perform a weighted summation of the matching degree of its own field and the matching degree of each of the above relative fields, to obtain the overall matching degree (called the initial matching degree) corresponding to the corresponding relative field matching degree combination. In this way, the electronic device can obtain multiple initial matching degrees, and the number of these initial matching degrees is consistent with the number of relative field matching degree combinations.

[0095] Subsequently, considering that the vectors corresponding to the relative vector ID fields in the combination of relative field matching degrees corresponding to the largest initial matching degree have a better vector correspondence, the electronic device selects the initial matching degree with the largest value from these initial matching degrees as the total matching degree between the candidate vector feature and the target vector feature. This can improve the accuracy of the calculation of the total matching degree to a greater extent, providing more accurate basic data for subsequent vector matching, thereby further improving the accuracy of vector matching.

[0096] In some embodiments, prior to S6313, the process of obtaining target weights includes: determining the target weight of the local vector ID field and the target weight of each relative vector ID field in the target vector features based on the relative distance between target vectors, the relative distance between the target vector and each spatially related vector, and the constraint that the sum of each target weight is 1.

[0097] Specifically, considering that the greater the relative distance between other vectors, the less effective they are in representing the accuracy of the target vector, this embodiment sets the target weights according to relative distance, with a numerical relationship where the greater the relative distance, the smaller the target weight. Simultaneously, the sum of all target weights needs to be constrained to 1. In this way, the electronic device can obtain the target weight corresponding to each field (including the local vector ID field and the relative vector ID field). This improves the compatibility between the target weights and each vector, thereby further enhancing the accuracy of the overall matching degree.

[0098] S632. The candidate matching vector corresponding to the maximum value among the total matching degrees is determined as the target matching vector.

[0099] Specifically, the electronic device compares the total matching degree corresponding to each candidate matching vector, determines the total matching degree with the largest value, and determines the candidate matching vector corresponding to the largest total matching degree as the target matching vector that best matches the target vector.

[0100] The map vector matching method provided in the above embodiments of this disclosure can determine the local field matching degree between the local vector ID field in the target vector feature and the local vector ID field in the candidate vector feature; determine the relative field matching degree between each relative vector ID field in the target vector feature and each relative vector ID field in the candidate vector feature; perform weighted summation processing on the local field matching degree and each relative field matching degree using each target weight to obtain the total matching degree between the target vector feature and the candidate vector feature; realize field-by-field matching between the target vector feature and the candidate vector feature, improve the accuracy of vector feature matching, and thus further improve the accuracy of subsequent vector matching.

[0101] Figure 7 This is a schematic diagram of a map vector matching device provided in an embodiment of the present disclosure. The device can be implemented in software and / or hardware and can be integrated into any electronic device with a certain computing power.

[0102] like Figure 7 As shown, the map vector matching device 700 provided in this embodiment may include:

[0103] The vector acquisition module 710 is used to acquire the target vector and at least one spatially related vector corresponding to the target vector in the high-precision base map, and to acquire each candidate matching vector corresponding to the target vector in the updated map;

[0104] The vector feature generation module 720 is used to generate vector features of the vector to be processed based on the vector position, vector type, and relative relationship information between the vector to be processed and other vectors. The vector to be processed includes a target vector or any candidate matching vector. When the vector to be processed is a target vector, the other vectors include spatially related vectors, and the vector features are those of the target vector. When the vector to be processed is a candidate matching vector, the other vectors include candidate matching vectors other than the target vector, and the vector features are those of the candidate vector.

[0105] The target matching vector determination module 730 is used to perform vector matching based on the target vector features and the features of each candidate vector, and to determine the target matching vector that matches the target vector from each candidate matching vector.

[0106] The map vector matching apparatus provided in this embodiment can acquire a target vector and at least one spatially related vector corresponding to the target vector in a high-precision base map, and acquire candidate matching vectors corresponding to the target vector in the updated map; based on the vector position, vector type, and relative relationship information between the vector to be processed (target vector or any candidate matching vector) and other vectors, it generates vector features of the vector to be processed (corresponding to target vector features or candidate vector features); based on the target vector features and each candidate vector feature, it performs vector matching, and determines the target matching vector that matches the target vector from each candidate matching vector. Thus, by adding the relative relationship information of the spatial relationships between other vectors in the same map and the vector to be processed to the vector feature construction process of the vector to be processed, the uniqueness and accuracy of the representation of each vector to be processed are improved, thereby solving the problem of vector matching errors caused by relying solely on the vector's own vector position and vector type attributes, improving the accuracy of vector matching, and providing more accurate basic data for subsequent processes.

[0107] In some embodiments, the vector feature generation module 720 includes:

[0108] The local vector ID field determination submodule is used to determine the local vector ID field based on the vector position and vector type of the vector to be processed;

[0109] The relative vector ID field determination submodule is used to determine the relative vector ID field based on the relative distance and relative orientation between the vector to be processed and other vectors;

[0110] The vector feature generation submodule is used to combine the local vector ID field and the relative vector ID field to generate vector features.

[0111] In some embodiments, when there are multiple other vectors, the number of relative vector ID fields is the same as the number of other vectors;

[0112] Accordingly, the relative vector ID field determines the specific uses of the submodule:

[0113] Based on the relative distance and relative orientation between the vector to be processed and each other vector, determine the relative vector ID field corresponding to each other vector;

[0114] Accordingly, the vector feature generation submodule is specifically used for:

[0115] The relative vector ID fields are sorted in ascending order according to their relative distance to each other vector, and the local vector ID field and the sorted relative vector ID fields are combined to generate vector features.

[0116] In some embodiments, the target matching vector determination module 730 includes:

[0117] The total matching degree acquisition submodule is used to perform the following vector matching processing for each candidate vector feature:

[0118] Based on the differences in vector position and vector type, determine the matching degree of the local field between the local vector ID field in the target vector feature and the local vector ID field in the candidate vector feature;

[0119] Based on the differences in relative distance and relative orientation, the relative field matching degree between each relative vector ID field in the target vector feature and each relative vector ID field in the candidate vector feature is determined;

[0120] The matching degree of the local field and the matching degree of each relative field are weighted and summed using the weights of each target to obtain the total matching degree between the target vector features and the candidate vector features.

[0121] The target matching vector determination submodule is used to determine the candidate matching vector corresponding to the maximum value among the total matching degrees as the target matching vector.

[0122] Furthermore, the total matching degree acquisition submodule is specifically used for:

[0123] Traverse each relative vector ID field in the target vector feature, and determine the relative field matching degree between the relative vector ID field in the traversed target vector feature and each relative vector ID field in the candidate vector feature based on the difference in relative distance and relative orientation.

[0124] The relative vector ID fields in the target vector features and the relative vector ID fields in the candidate vector features are arranged and combined to obtain multiple field combinations;

[0125] By using the target weights, the matching degree of the local field and the matching degree of each relative field corresponding to each field combination are weighted and summed to obtain the initial matching degree of the corresponding field combination.

[0126] The maximum value among the initial matching degrees is determined as the total matching degree between the target vector feature and the candidate vector feature.

[0127] In some embodiments, the target matching vector determination module 730 further includes a target weight determination submodule, used for:

[0128] Before using the weighted summation of the matching degree of the local field and the matching degree of each relative field to obtain the total matching degree between the target vector features and the candidate vector features, the target weight of the local vector ID field and the target weight of the corresponding relative vector ID field in the target vector features are determined based on the relative distance between target vectors, the relative distance between the target vector and each spatially related vector, and the constraint that the sum of each target weight is 1.

[0129] In some embodiments, the vector acquisition module 710 is specifically used for:

[0130] Obtain the target vector in the high-precision base map, and determine the target range based on the vector position of the target vector and a preset distance; wherein, the preset distance is determined based on the range distance when the defined range contains at least two different vectors;

[0131] Obtain vectors within the target area of ​​the high-precision base map, excluding the target vector, as spatial correlation vectors;

[0132] Obtain each vector within the target area of ​​the updated map as a candidate matching vector.

[0133] The map vector matching apparatus provided in this disclosure can execute any of the map vector matching methods provided in this disclosure, and has the corresponding functional modules and beneficial effects for executing the method. Content not described in detail in the apparatus embodiments of this disclosure can be referred to the description in any method embodiment of this disclosure.

[0134] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. It is used to exemplarily illustrate an electronic device that implements the map vector matching method in any embodiment of the present disclosure and should not be construed as a specific limitation on the embodiments of the present disclosure.

[0135] like Figure 8As shown, the electronic device 800 may include a processor (e.g., a central processing unit, a graphics processor, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device 800. The processor 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0136] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data. Although an electronic device 800 with various devices is shown, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0137] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the map vector matching method provided in any of the embodiments of this disclosure. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processor 801, it can perform the functions defined in the map vector matching method provided in any embodiment of this disclosure.

[0138] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0139] In some implementations, the client and server can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0140] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0141] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the map vector matching method provided in any embodiment of this disclosure.

[0142] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on a computer, partially on a computer, as a standalone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0144] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0145] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0146] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0147] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0148] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0149] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A map vector matching method, characterized in that, include: Obtain the target vector and at least one spatial correlation vector corresponding to the target vector in the high-precision base map, and obtain each candidate matching vector corresponding to the target vector in the updated map; Based on the vector position and vector type of the vector to be processed, a local vector ID field is determined; based on the relative distance and relative orientation between the vector to be processed and other vectors, a relative vector ID field is determined; the local vector ID field and the relative vector ID field are combined to generate the vector features of the vector to be processed; wherein, the vector to be processed includes the target vector or any of the candidate matching vectors; when the vector to be processed is the target vector, the other vectors include the spatially related vectors, and the vector features are target vector features; when the vector to be processed is the candidate matching vector, the other vectors include the candidate matching vectors other than the candidate matching vector, and the vector features are candidate vector features; Vector matching is performed based on the target vector features and the candidate vector features, and a target matching vector that matches the target vector is determined from the candidate matching vectors.

2. The method according to claim 1, wherein, When there are multiple other vectors, the number of relative vector ID fields is the same as the number of other vectors; The determination of the relative vector ID field based on the relative distance and relative orientation between the vector to be processed and the other vectors includes: Based on the relative distance and relative orientation between the vector to be processed and each of the other vectors, determine the relative vector ID field corresponding to each of the other vectors; The process of combining the local vector ID field and the relative vector ID field to generate the vector feature includes: The relative vector ID fields are arranged in ascending order according to the relative distances corresponding to each of the other vectors, and the local vector ID field and the sorted relative vector ID fields are combined to generate the vector feature.

3. The method according to claim 1, wherein, The step of performing vector matching based on the target vector features and each of the candidate vector features, and determining the target matching vector that matches the target vector from the candidate matching vectors, includes: For each of the candidate vector features, the following vector matching process is performed: Based on the differences in vector position and vector type, determine the local field matching degree between the local vector ID field in the target vector feature and the local vector ID field in the candidate vector feature; Based on the differences in relative distance and relative orientation, the relative field matching degree between each relative vector ID field in the target vector feature and each relative vector ID field in the candidate vector feature is determined; The matching degree of the local field and the matching degree of each relative field are weighted and summed using the target weights to obtain the total matching degree between the target vector feature and the candidate vector feature. The candidate matching vector corresponding to the maximum value among the total matching degrees is determined as the target matching vector.

4. The method according to claim 3, wherein, The determination of the relative field matching degree between each relative vector ID field in the target vector feature and each relative vector ID field in the candidate vector feature, based on the difference in relative distance and the difference in relative orientation, includes: Traverse each relative vector ID field in the target vector feature, and determine the relative field matching degree between the relative vector ID field in the traversed target vector feature and each relative vector ID field in the candidate vector feature based on the difference in relative distance and the difference in relative orientation; The step of using the weighted summation of the matching degree of the local field and the matching degree of the relative field based on the target weights to obtain the total matching degree between the target vector features and the candidate vector features includes: The relative vector ID fields in the target vector features and the relative vector ID fields in the candidate vector features are arranged and combined to obtain multiple field combinations; Using the target weights, the matching degree of the local field and the relative field matching degree corresponding to each field combination are weighted and summed to obtain the initial matching degree corresponding to the corresponding field combination. The maximum value among the initial matching degrees is determined as the total matching degree between the target vector feature and the candidate vector feature.

5. The method according to claim 3, wherein, Before performing a weighted summation of the matching degree of the local field and the matching degree of each relative field using the target weights to obtain the total matching degree between the target vector feature and the candidate vector feature, the method further includes: Based on the relative distance between the target vectors, the relative distance between the target vector and each of the spatially related vectors, and the constraint that the sum of each target weight is 1, the target weight of the local vector ID field and the target weight of each of the relative vector ID fields in the target vector feature are determined.

6. The method according to claim 1, wherein, The step of obtaining the target vector in the high-precision base map and at least one spatial correlation vector corresponding to the target vector, and obtaining each candidate matching vector corresponding to the target vector in the updated map, includes: The target vector in the high-precision base map is obtained, and the target range is determined based on the vector position of the target vector and a preset distance; wherein, the preset distance is determined based on the range distance when the defined range contains at least two different vectors; Obtain the vectors within the target range of the high-precision base map, excluding the target vector, as the spatial correlation vector; Obtain each vector within the target range of the updated map as a candidate matching vector.

7. A map vector matching device, characterized in that, include: The vector acquisition module is used to acquire the target vector in the high-precision base map and at least one spatially related vector corresponding to the target vector, and to acquire each candidate matching vector corresponding to the target vector in the updated map; The vector feature generation module is used to determine a local vector ID field based on the vector position and vector type of the vector to be processed; determine a relative vector ID field based on the relative distance and relative orientation between the vector to be processed and other vectors; and combine the local vector ID field and the relative vector ID field to generate vector features of the vector to be processed; wherein, the vector to be processed includes the target vector or any of the candidate matching vectors; when the vector to be processed is the target vector, the other vectors include the spatially related vectors, and the vector features are target vector features; when the vector to be processed is the candidate matching vector, the other vectors include the candidate matching vectors other than the candidate matching vector, and the vector features are candidate vector features; The target matching vector determination module is used to perform vector matching based on the target vector features and each of the candidate vector features, and to determine the target matching vector that matches the target vector from each of the candidate matching vectors.

8. An electronic device, characterized in that, include: A memory and a processor, wherein the memory is used to store executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the map vector matching method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the map vector matching method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product is used to execute the map vector matching method according to any one of claims 1 to 6.

Images