Map update processing method and apparatus, electronic device, and storage medium

Abstract

The application provides a map updating processing method and device, electronic equipment and storage medium, and relates to the technical field of map data processing. The method comprises the following steps: acquiring map data and observation data of a same target region; wherein the map data comprises feature data of at least one map element, and the observation data comprises feature data of at least one observation element; according to the feature data of the map element, the feature data of the observation element and a pre-established multi-dimensional index system, calculating a comprehensive matching degree between any map element and any observation element, and combining the map element and the observation element with a comprehensive matching degree greater than a preset threshold into a candidate matching pair; and determining a target matching result based on all candidate matching pairs. The above method improves the accuracy of the target matching result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of map data processing, and particularly relates to a map updating processing method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Based on the requirement of high-precision map for unmanned driving, the absolute and relative coordinate precision of the high-precision map must be higher, and the information elements contained in the high-precision map must be richer and more detailed, and the high-precision map must provide the automatic driving system with high freshness, high precision and multi-dimensional road and additional information.

[0003] Since the more timely the map is updated, the better, in order to realize efficient updating of the map, the prior art generally directly uses the position for matching.

[0004] However, even if the two elements are of different types in reality, the prior art is likely to identify the two elements of different types and close positions as one element, and thus the matching result is low in accuracy, and the technical problem of being unable to effectively update the map. SUMMARY

[0005] The present application provides a map updating processing method and device, electronic equipment and a storage medium, to solve the problem of low accuracy of map updating caused by low accuracy of matching results.

[0006] According to a first aspect of the present application, a map updating processing method is provided, comprising:

[0007] According to the original area on the map to be updated in the obtained map updating request, map data and observation data of a same target area are obtained; wherein the target area is a sub-area obtained by dividing the original area, the map data comprises feature data of at least one map element, and the observation data comprises feature data of at least one observation element;

[0008] According to the feature data of the map element, the feature data of the observation element and a pre-established multi-dimensional index system, a comprehensive matching degree between any map element and any observation element is calculated, and the map element and the observation element with a comprehensive matching degree greater than a preset threshold are combined as a candidate matching pair;

[0009] Based on all the candidate matching pairs, a target matching result is determined to realize updating of the original area on the map to be updated; wherein the target matching result is a set of multiple candidate matching pairs as target matching pairs.

[0010] In a possible implementation, the calculating of the comprehensive matching degree between any one of the map elements and any one of the observation elements according to the characteristic data of the map elements, the characteristic data of the observation elements, and the pre-established multi-dimensional index system comprises:

[0011] identifying an index in the pre-established multi-dimensional index system; wherein the multi-dimensional index system comprises at least two indexes: an attribute index, a reliability index, and a spatial position index;

[0012] For any one of the map elements and any one of the observation elements, if the index in the multi-dimensional index system comprises the attribute index, attribute data of the map element is extracted from the characteristic data of the map element, attribute data of the observation element is extracted from the characteristic data of the observation element, and an attribute matching degree between the map element and the observation element is calculated according to the attribute data of the map element and the attribute data of the observation element;

[0013] If the index in the multi-dimensional index system comprises the spatial position index, spatial position data of the map element is extracted from the characteristic data of the map element, spatial position data of the observation element is extracted from the characteristic data of the observation element, and a spatial position matching degree between the map element and the observation element is calculated according to the spatial position data of the map element and the spatial position data of the observation element;

[0014] If the index in the multi-dimensional index system comprises the reliability index, reliability data of the observation element is extracted from the characteristic data of the observation element, and a reliability matching degree between the map element and the observation element is calculated according to the reliability data of the observation element;

[0015] The comprehensive matching degree between the map element and the observation element is calculated based on at least two of the attribute matching degree, the spatial position matching degree, and the reliability matching degree determined according to the index in the multi-dimensional index system.

[0016] In a possible implementation, when the attribute index comprises at least two sub-attribute indexes of type, width, color, height, size, shape, and color, the calculating of the attribute matching degree between the map element and the observation element according to the attribute data of the map element and the attribute data of the observation element comprises:

[0017] sub-attribute data of the map element on each sub-attribute index is extracted from the attribute data of the map element, and sub-attribute data of the observation element on each sub-attribute index is extracted from the attribute data of the observation element;

[0018] For each sub-attribute index, a sub-attribute matching degree between the map element and the observation element is calculated according to sub-attribute data of the map element on the sub-attribute index and sub-attribute data of the observation element on the sub-attribute index;

[0019] An attribute matching degree between the map element and the observation element is determined based on the sub-attribute matching degrees between the map element and the observation element on all sub-attribute indexes.

[0020] In a possible implementation, the determining the target matching result based on all the candidate matching pairs comprises:

[0021] Inference matching is performed based on a preset target search algorithm and all the candidate matching pairs to obtain a plurality of inference matching results, wherein the inference matching result is a set of the plurality of candidate matching pairs;

[0022] An evaluation score of each inference matching result is calculated, and an inference matching result with the highest evaluation score is determined as the target matching result.

[0023] In a possible implementation, the calculating the evaluation score of each inference matching result comprises:

[0024] For each candidate matching pair in any inference matching result, a position similarity of the candidate matching pair is calculated according to position data of the candidate matching pair, position data of other candidate matching pairs in the inference matching result, and a preset position similarity calculation formula;

[0025] For each inference matching result, an evaluation score of the inference matching result is determined based on position similarities of all candidate matching pairs in the inference matching result, comprehensive matching degrees of the candidate matching pairs, and a preset target function.

[0026] In a possible implementation, when the position similarity calculation formula comprises a horizontal position similarity calculation formula, a vertical position similarity calculation formula, and a longitudinal position similarity calculation formula, the calculating the position similarity of the candidate matching pair according to the position data of the candidate matching pair, the position data of other candidate matching pairs in the inference matching result, and the preset position similarity calculation formula comprises:

[0027] extracting first component position information, second component position information and third component position information of the candidate matching pair respectively from position data of the candidate matching pair; wherein the first component position information is position information of the candidate matching pair in a horizontal direction, the second component position information is position information of the candidate matching pair in a vertical direction, and the third component position information is position information of the candidate matching pair in a longitudinal direction;

[0028] extracting fourth component position information, fifth component position information and sixth component position information of the other candidate matching pair respectively from position data of the other candidate matching pair in the inference matching result; wherein the fourth component position information is position information of the other candidate matching pair in the horizontal direction, the fifth component position information is position information of the other candidate matching pair in the vertical direction, and the sixth component position information is position information of the other candidate matching pair in the longitudinal direction;

[0029] calculating horizontal position similarity of the candidate matching pair based on the first component position information of the candidate matching pair, the fourth component position information of the other candidate matching pair and the horizontal position similarity calculation formula;

[0030] calculating vertical position similarity of the candidate matching pair based on the second component position information of the candidate matching pair, the fifth component position information of the other candidate matching pair and the vertical position similarity calculation formula;

[0031] calculating vertical position similarity of the candidate matching pair based on the third component position information of the candidate matching pair, the sixth component position information of the other candidate matching pair and the vertical position similarity calculation formula;

[0032] determining position similarity of the candidate matching pair based on the horizontal position similarity, the vertical position similarity and the longitudinal position similarity of the candidate matching pair.

[0033] In a possible implementation, before the map data and observation data of the same target region are acquired, the method further includes:

[0034] acquiring original map data and original observation data collected by a sensor of the original region;

[0035] dividing the original map data and the original observation data according to clustering results of point elements respectively to obtain map data and observation data of a plurality of target regions.

[0036] According to a second aspect of the present application, a map updating processing apparatus is provided, including:

[0037] The acquisition module is configured to acquire map data and observation data of a same target region according to an original region on a to-be-updated map in an acquired map update request, wherein the target region is a sub-region obtained by dividing the original region, the map data includes feature data of at least one map element, and the observation data includes feature data of at least one observation element.

[0038] The calculation module is configured to calculate a comprehensive matching degree between any map element and any observation element according to the feature data of the map element, the feature data of the observation element, and a pre-established multi-dimensional index system, and combine a map element and an observation element with a comprehensive matching degree greater than a preset threshold into a candidate matching pair.

[0039] The determination module is configured to determine a target matching result based on all the candidate matching pairs, so as to realize updating of the original region on the to-be-updated map, wherein the target matching result is a set of the candidate matching pairs as target matching pairs.

[0040] According to a third aspect of the present application, an electronic device is provided, including at least one processor and a memory.

[0041] The memory stores computer execution instructions.

[0042] The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the map update processing method according to the first aspect.

[0043] According to a fourth aspect of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the map update processing method according to the first aspect.

[0044] According to a fifth aspect of the present application, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the map update processing method according to the first aspect.

[0045] The application provides a map updating processing method. First, an original area on a to-be-updated map in a map updating request is obtained, and map data and observation data of a same target area are obtained; the target area is a sub-area obtained by dividing the original area, the map data comprises feature data of at least one map element, and the observation data comprises feature data of at least one observation element; then, according to the feature data of the map element, the feature data of the observation element and a pre-established multi-dimensional index system, a comprehensive matching degree between any map element and any observation element is calculated, and the map element and the observation element with the comprehensive matching degree greater than a preset threshold are combined as a candidate matching pair; finally, based on all the candidate matching pairs, a target matching result is determined to update the original area on the to-be-updated map.

[0046] Since the original area is large and is more likely to cause error matching, the sub-area in the original area divided by the application embodiment is obtained before the map data and the observation data are matched, so that the matching range of the map data and the observation data is reduced, and the matching accuracy is improved. In addition, the multi-dimensional index system is applied to accurately calculate the comprehensive matching degree between any map element and any observation element under multiple indexes, generate a candidate matching pair with high comprehensive matching degree, and improve the accuracy of the target matching result. Since each target area corresponds to a target matching result, the matching accuracy during map updating can be improved by the target matching results in different target areas.

[0047] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the application, nor is it used to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

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

[0049] Figure 1 A schematic diagram of an application scenario related to the embodiments of the application;

[0050] Figure 2 A flowchart of a map updating processing method provided by the embodiments of the application;

[0051] Figure 3 A schematic diagram of a division scenario provided by the embodiments of the application;

[0052] Figure 4 A flowchart of another map updating processing method provided by the embodiments of the application;

[0053] Figure 5 A flowchart of another map updating processing method provided by an embodiment of the present application is shown in FIG. 3.

[0054] Figure 6 A structure diagram of a map updating processing device provided by an embodiment of the present application is shown in FIG. 4.

[0055] Figure 7 A structure diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 5.

[0056] The specific embodiments of the present application have been shown in the above-described drawings, and will be described in more detail hereinafter. These drawings and the written description are not intended to restrict the scope of the present application in any way, but are merely intended to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0057] The exemplary embodiments will be described in detail herein below with reference to the drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application.

[0058] To facilitate understanding, the application scenarios of the embodiments of the present application are introduced first.

[0059] Figure 1 A structure diagram of an application scenario related to the embodiments of the present application is shown in FIG. 1. As shown in FIG. 1, the application scenario of the present embodiment is that a user uses a client to acquire map data from a data source 1 and observation data from a data source 2 through a data integration platform, and then performs a matching operation based on the map data and the observation data. Figure 1

[0060] However, the prior art generally directly uses positions to perform matching. Even if two elements are of different types in reality, they may be identified as one element because they are close to each other in position, and thus the matching result obtained has a low accuracy, which finally leads to the technical problem of low map updating accuracy.

[0061] To solve the above technical problem, the overall inventive concept of the present application is to provide a map updating method applied to the field of map data processing and having a high matching accuracy. The map data and the observation data of a same target region are obtained by dividing the data according to the characteristic data of the map data and the observation data, all possible matching pairs are listed, candidate matching pairs are filtered, a plurality of candidate matching results are output based on reasoning matching, and finally a target function is used to evaluate the candidate matching results to select an optimal matching result with a high accuracy.

[0062] ​The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes can not be described again in some examples. The embodiments of the present application will be described below with reference to the drawings.

[0063] Figure 2 A flowchart of a map updating processing method provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the method of the present embodiment includes the following steps. Figure 2

[0064] S201: Obtain map data and observation data of a same target region according to an original region on a map to be updated in a map updating request. The target region is a sub-region obtained by dividing the original region, the map data includes feature data of at least one map element, and the observation data includes feature data of at least one observation element.

[0065] In the present embodiment, the map data and the observation data are both vector data. The observation data is also called reported data. The original region can refer to an entire road segment, the target region can refer to a part of the entire road segment, and the scene is a scene corresponding to the target region, which includes all map elements and observation elements in the target region. The specific steps of scene division are described below in S204-S205, which are not described here. Both the map elements and the observation elements are entity elements, which include point elements and line elements. The point elements or point-like elements include but are not limited to poles, signs, arrows, divergences, and convergences. The line elements or line-like elements can be a line. Before extracting the feature data of the line element, the feature data of the line element can be discretized, which is described in detail below in S403, which is not described here. Further, the feature data of the map elements and the feature data of the observation elements each include at least one of spatial position data, attribute data, and confidence data.

[0066] S202: Calculate a comprehensive matching degree between any map element and any observation element according to the feature data of the map elements, the feature data of the observation elements, and a pre-established multi-dimensional index system, and combine the map elements and the observation elements with a comprehensive matching degree greater than a preset threshold into a candidate matching pair. The multi-dimensional index system or matching degree evaluation index includes at least two indexes: attribute index, confidence index, and spatial position index.

[0067] ​It should be understood that the above multi-dimensional index system can also include other indexes in addition to the attribute index, the reliability index and the spatial position index. The above attribute index includes the following at least one sub-attribute index: type, width, color, height, size, shape and color. Since the feature data of the map element and the feature data of the observed element each include at least one of the spatial position data, the attribute data and the reliability data, the pre-established multi-dimensional index system can be established based on the attribute index, the reliability index and the spatial position index.

[0068] Since the element type is a point element and a line element, the embodiments of the present application can establish respective attribute indexes in the multi-dimensional index system for the point element and the line element, for example: the attribute index of the line element includes three sub-attribute indexes of type, width and color, and the attribute index of the point element includes five sub-attribute indexes of height, size, type, shape and color. The advantage of establishing respective attribute indexes for different types of elements is that the attribute matching degree between the map element and the observed element can be accurately evaluated, and then an accurate comprehensive matching degree is obtained.

[0069] In theory, one observed element in the report and each map element in the map can represent the same entity element in reality, so by calculating the comprehensive matching degree between the map element and the observed element, all possible matching pairs can be listed, providing a selection basis for subsequent screening of candidate matching pairs. The flow of S202 can be summarized as: inputting the feature data of the map element and the feature data of the observed element, then calculating the matching degree between them, then screening the matching pairs with high comprehensive matching degree, and finally outputting the candidate matching pairs. When screening, matching pairs with too low matching degree can be filtered out, for example: for two signs with very different sizes, the matching degree between them will be very low and will be filtered out.

[0070] The size of the comprehensive matching degree is used to represent the possibility of matching an observed element with a certain map element. In the embodiments of the present application, the matching degree can be described from three dimensions of the attribute index, the reliability index and the spatial position index.

[0071] Through the calculation of the comprehensive matching degree and the judgment of the preset threshold, candidate matching pairs with higher accuracy can be screened out. In actual application, different candidate matching pairs may have a mutual exclusion possibility even if the comprehensive matching degrees are all greater than the preset threshold, so it is necessary for the embodiments of the present application to perform the following S203.

[0072] S203: Based on all the candidate matching pairs, determining a target matching result to realize the update of the original area on the map to be updated. The target matching result is a set of multiple candidate matching pairs as target matching pairs.

[0073] The number of all candidate matching pairs is large, and there is a possibility of exclusivity between the candidate matching pairs. Therefore, in order to identify the target matching pair with high accuracy from the candidate matching pairs, the embodiment of the present application can determine the target matching result by providing an algorithm in this step, so that each target matching pair in the target matching result further improves the accuracy compared with all candidate matching pairs. Further, the algorithm type is not limited in the embodiment of the present application.

[0074] In the embodiment, S201 to S203 realize the processes of map data and observation data acquisition of the same target area, candidate matching pair generation based on a multi-dimensional index system, and target matching pair determination. On the one hand, by acquiring the map data and observation data of the same target area, the matching range is narrowed to improve the matching accuracy. On the other hand, by applying the multi-dimensional index system, the comprehensive matching degree between any map element and any observation element under multiple indexes can be accurately calculated, the candidate matching pair with high comprehensive matching degree is generated, and the accuracy of the target matching result is improved. Since each target area corresponds to a target matching result, the matching accuracy during map updating can be improved by the target matching results in different target areas.

[0075] In a possible implementation, before S201: acquiring the map data and observation data of the same target area, the method can further include the following S204-S205:

[0076] S204: acquiring original map data of an original area and original observation data collected by a sensor.

[0077] S205: dividing the original map data and the original observation data according to the clustering result of point elements to obtain the map data and the observation data of multiple target areas.

[0078] It should be understood that the original area is a large area, and the target area is a small area. The original observation data is also referred to as original reported data. The original map data is a summary of the map data of all target areas, and the original observation data is a summary of the observation data of all target areas. When performing the division operation, only the point elements are considered, and the types of the point elements do not need to be distinguished. Each point element can be used as a data point for clustering analysis without considering the type to obtain the clustering result. Since the original area is divided into scenes according to the clustering result of the point elements, the number of the divided scenes and the lengths of the road segments in the scenes are not limited in the embodiment of the present application.

[0079] The scene establishment can be realized through S204-S205. The scene establishment refers to dividing a large area into multiple small areas, and dividing the original map data and the original reported data of the large area into multiple small area map data and reported data. The specific process is: inputting all point elements, clustering and grouping the point elements according to spatial distance, dividing the scene according to the group, and outputting the divided scene. In the above process, the specific method is to first divide the original map data according to a preset rule, and then divide the original reported data according to the same division position. In this way, the original map data and the original reported data are divided by the same cutting line, and the map data and the reported data in the same cutting line form a scene. Since the map elements are sparsely distributed, the above preset rule can be determined by the density of the point elements.

[0080] The above map data is composed of a series of feature data of all map elements, and the feature data includes spatial position data. Therefore, the map elements can be clustered according to spatial distance, and each group composed of map elements corresponds to a scene.

[0081] The clustering and grouping mode realized by the point elements can divide the scene, and can make the corresponding point elements in the reported data and the point elements in the map data cut into one scene, thereby ensuring that the reported data can find the corresponding point elements in the same scene during matching. For example, there are 100 point elements, 50 of which are very close to each other, and the other 50 are also very close to each other, but the distance between the two groups is very large. At this time, they will be clustered into two categories, i.e., divided into two scenes. Or, when the distance between the two groups exceeds a preset distance value, they can also be divided into three scenes, as shown in FIG. 2B. The group of 50 point elements is taken as scene 1, the group of the other 50 point elements is taken as scene 3, and the group without point elements in the middle is taken as scene 2. In summary, the scene establishment can be realized through S204-S205, thereby narrowing the matching range and improving the matching accuracy. Figure 3

[0082] On the basis of the above embodiment, the technical scheme of the present application will be described in more detail in combination with several specific embodiments.

[0083] Figure 4 Another map updating processing method provided by the embodiment of the present application is shown in the flowchart. On the basis of the embodiment shown in FIG. 2A, the embodiment focuses on the refinement of S202 in FIG. 2B. Figure 2 Figure 2 As shown in FIG. 2C, the method of the embodiment can include the following S401-S407. Figure 4

[0084] ​​​S401: Obtain the map data and observation data of the same target region according to the original region to be updated in the obtained map update request. The target region is a sub-region obtained by dividing the original region, the map data includes feature data of at least one map element, and the observation data includes feature data of at least one observation element. It should be understood that the specific implementation of S401 is similar to S201 in Figure 2

[0085] S402: Identify the indicators in the pre-established multi-dimensional indicator system; wherein the multi-dimensional indicator system includes at least two indicators: attribute indicators, reliability indicators, and spatial position indicators.

[0086] In the embodiments of the present application, the multi-dimensional indicator system can be adaptively established according to actual needs, so it can contain attribute indicators, reliability indicators and spatial position indicators, or the specific indicators used can be increased or decreased.

[0087] S403: For any map element and any observation element, if the indicators in the multi-dimensional indicator system include attribute indicators, the attribute data of the map element is extracted from the feature data of the map element, the attribute data of the observation element is extracted from the feature data of the observation element, and the attribute matching degree between the map element and the observation element is calculated according to the attribute data of the map element and the attribute data of the observation element.

[0088] Any map element and any observation element in the embodiments of the present application can form a matching pair. The matching pair is used to reflect the matching relationship between the map element and the observation element. The higher the attribute matching degree of the matching pair, the greater the possibility that the map element and the observation element are the same element entity.

[0089] The attribute matching degree can be understood as the attribute similarity, that is, the similarity of the map element and the observation element in each sub-attribute indicator dimension, such as the size of the label, the spatial position, and the distance between the observation element and the map element. The attribute similarity is the consistency of the observation element and the map element in the attribute indicators. The higher the consistency, the higher the score of the attribute matching degree. According to the consistency of the two elements, different scores are calculated, for example: if the color of the label is the same, mark 1 point, and if the color is different, mark 0 point.

[0090] In order to compare whether the continuous attributes are consistent, the embodiments of the present application can discretize the line element, for example, according to the national standard, the marking line width is discretized to 150mm, 200mm, 250mm, 300mm or 450mm, and the marking line width is marked as 1 point if it is the same, and 0 point if it is different.

[0091] ​S404: If the indexes in the multi-dimensional index system include the spatial position index, the spatial position data of the map element is extracted from the feature data of the map element, the spatial position data of the observation element is extracted from the feature data of the observation element, and the spatial position matching degree between the map element and the observation element is calculated according to the spatial position data of the map element and the spatial position data of the observation element.

[0092] It should be understood that the spatial position matching degree is also called a position score, which is used to describe the possibility of the spatial matching between the observation element and the map element, and the smaller the distance, the greater the possibility of matching. The embodiment of the present application can take the reciprocal of the distance as the position score.

[0093] S405: If the indexes in the multi-dimensional index system include the reliability index, the reliability data of the observation element is extracted from the feature data of the observation element, and the reliability matching degree between the map element and the observation element is calculated according to the reliability data of the observation element. It should be understood that the reliability matching degree is also called the existence reliability, which is used to reflect the possibility of the existence of the map element, which is reflected according to the number of historical observation data reporting. In the embodiment of the present application, the existence reliability is proportional to the number of reporting the map element, and the more the number of reporting, the greater the possibility of the existence of the map element, and the number of reporting the map element is determined by the reliability data of the observation element.

[0094] S406: Based on at least two of the attribute matching degree, the spatial position matching degree and the reliability matching degree determined by the indexes in the multi-dimensional index system, the comprehensive matching degree between the map element and the observation element is calculated, and the map element and the observation element with the comprehensive matching degree greater than a preset threshold are combined as a candidate matching pair.

[0095] Specifically, a corresponding dimension weight can be set for each matching degree. In order to distinguish the dimension weights, the following settings can be made, that is, the dimension weight corresponding to the attribute matching degree is determined as the first dimension weight, the dimension weight corresponding to the spatial position matching degree is determined as the second dimension weight, and the dimension weight corresponding to the reliability matching degree is determined as the third dimension weight.

[0096] When the multi-dimensional index system includes the attribute index, the reliability index and the spatial position index, the calculation method of the above-mentioned comprehensive matching degree can adopt a linear model, such as formula (1):

[0097]

[0098] wherein, e base is the map element, e reportmatchScore is a comprehensive matching degree between the map element and the observation element, θ1, θ2 and θ3 respectively represent a first dimension weight, a second dimension weight and a third dimension weight, and are used to represent the contribution of the attribute matching degree, the spatial position matching degree and the reliability matching degree to the comprehensive matching degree, disScore(e is an attribute matching degree between the map element and the observation element, and is used to reflect the score on the attribute index, wherein disScore(e

[0099] is a sub attribute matching degree between the map element and the observation element on the i-th sub attribute index, w i is a weight corresponding to the sub attribute matching degree, n is the number of sub attribute indexes, disScore(e base ,e report is a spatial position matching degree between the map element and the observation element, and is used to reflect the score on the spatial position index, disScore(e base ,e report is a reliability matching degree between the map element and the observation element, and is used to reflect the score on the reliability index.

[0100] Through the execution of the above-mentioned operations of S402 to S406, the present application can construct the candidate matching pair. Specifically, a matching pair composed of any map element and any observation element is generated, and then the comprehensive matching degree is calculated, and then the candidate matching pair with the comprehensive matching degree greater than the preset threshold is obtained through screening. The accuracy of the candidate matching pair is high, and the data preparation for generating the target matching result with high accuracy is good.

[0101] In a possible implementation manner, when the attribute index includes at least two sub attribute indexes in type, width, color, height, size, shape and color, S403: calculating the attribute matching degree between the map element and the observation element according to the attribute data of the map element and the attribute data of the observation element, includes:

[0102] S4031: extracting the sub attribute data of the map element on each sub attribute index from the attribute data of the map element, and extracting the sub attribute data of the observation element on each sub attribute index from the attribute data of the observation element.

[0103] S4032: for each sub attribute index, calculating the sub attribute matching degree between the map element and the observation element according to the sub attribute data of the map element on the sub attribute index and the sub attribute data of the observation element on the sub attribute index.

[0104] S4033: Determine the attribute matching degree between the map element and the observation element based on the sub-attribute matching degrees between the map element and the observation element on all sub-attribute indicators.

[0105] As can be seen from the description of S4031-S4033, the embodiments of the present application can calculate the sub-attribute matching degrees of the map element and the observation element on each sub-attribute indicator, and then determine the attribute matching degree between the map element and the observation element according to the formula (1) based on the formula (1). The attribute matching degree between the map element and the observation element is determined, which provides a data basis for calculating the comprehensive matching degree.

[0106] Figure 5 The flowchart of another map updating processing method provided by the embodiments of the present application is shown. Based on the embodiments shown in the above Figure 2 or Figure 3 The embodiments of the present application make more detailed description on the specific implementation of S203 or S407.

[0107] As Figure 5 shown, the method of the embodiments includes the following S501-S504, wherein:

[0108] S501: Obtain the map data and the observation data of the same target region according to the original region on the map to be updated in the obtained map updating request. The target region is a sub-region obtained by dividing the original region, the map data includes the feature data of at least one map element, and the observation data includes the feature data of at least one observation element.

[0109] S502: Calculate the comprehensive matching degree between any map element and any observation element according to the feature data of the map element, the feature data of the observation element, and the pre-established multi-dimensional index system, and combine the map element and the observation element with the comprehensive matching degree greater than the preset threshold value into a candidate matching pair. The multi-dimensional index system includes at least two indicators: attribute indicator, confidence indicator, and spatial position indicator.

[0110] S503: Perform reasoning matching based on the preset target search algorithm and all candidate matching pairs to obtain a plurality of reasoning matching results. The reasoning matching result is a set of a plurality of candidate matching pairs. The reasoning matching result is referred to as a matching result.

[0111] S504: Calculate the evaluation score of each reasoning matching result, and determine the reasoning matching result with the highest evaluation score as the target matching result.

[0112] The preset target search algorithm can be a greedy algorithm or other algorithms, and the specific type of the algorithm is not limited in the embodiments of the present application.

[0113] It should be understood that the principle of reasoning matching in S503 is to first assume that a certain candidate matching pair Pair-A is correct, to find the next candidate matching pair with the horizontal and vertical distance of the candidate matching pair as the reference, to find the next candidate matching pair with the found candidate matching pair as the reference, and to repeat the process until all candidate matching pairs are found. Thus, a matching result starting from Pair-A can be obtained. In turn, starting from the remaining candidate matching pairs, multiple matching results can be found, and if starting from N candidate matching pairs, at most N matching results can be obtained. Then, the matching results are evaluated by the evaluation function, and a matching result with the highest score is selected as the target matching result. For example, assuming that Pair-A is correct, the horizontal and vertical distance of Pair-A is (d1, d2), a buffer is added to or subtracted from the distance to obtain (d1±buffer, d1±buffer), and the interval is the horizontal and vertical distance interval that the next candidate matching pair Pair-B should satisfy. The buffer reflects the worst relative accuracy and is a priori value set by a person. After Pair-B is found, the horizontal and vertical distance (d3, d4) of Pair-B is used as the reference to find Pair-C, and the process is repeated to obtain a matching result starting from Pair-A.

[0114] The relative accuracy error refers to the difference in distance between two candidate matching pairs, including horizontal and vertical directions. For example, the accuracy error of Pair-A and Pair-B is (d3-d1, d4-d2).

[0115] The target of reasoning matching is to find a group of candidate matching pairs with small relative accuracy errors and high matching degrees, so as to obtain a target matching result with good accuracy. The specific method is as follows: (1) selecting a candidate matching pair (assuming to be candidate matching pair A) as the starting point; (2) selecting a candidate matching pair that satisfies one of the reference relationships (the best each time) from the remaining candidate matching pairs; (3) repeating the previous step until all candidate matching pairs are traversed, and a matching result starting from candidate matching pair A is obtained; (4) jumping to (1), selecting the remaining candidate matching pairs in turn as the starting point, and repeating steps 2 and 3 until all candidate matching pairs are traversed as the starting point.

[0116] In selecting the next candidate matching pair, the strategy is to find a matching pair that can increase the position similarity and the comprehensive matching degree (i.e., the value of the target function). The target function is composed of the comprehensive matching degree and the position similarity, and represents the consistency of the position relationship between the internal matching pairs of the candidate matching result, and is used to evaluate the candidate matching result.

[0117] By performing the operations of S503-S504 described above, the application can generate inference matching results, and then select a target matching result with higher accuracy from the inference matching results. Whether it is an inference matching result or a target matching result, the structure is composed of multiple candidate matching pairs, and one candidate matching result represents a matching scheme.

[0118] In a possible implementation, S504: calculating an evaluation score of each inference matching result, including S5041-S5042 as follows:

[0119] S5041: for each candidate matching pair in any inference matching result, calculating a position similarity of the candidate matching pair according to position data of the candidate matching pair, position data of other candidate matching pairs in the inference matching result, and a preset position similarity calculation formula.

[0120] Since the position can be a position in multiple dimensions such as horizontal, vertical, and perpendicular, the preset position similarity calculation formula can include a horizontal position similarity calculation formula, a vertical position similarity calculation formula, and a perpendicular position similarity calculation formula, and the specific execution steps of S4041 are S1-S6 as described below, which are not described in detail here. The preset position similarity calculation formula is a modeling result of the position similarity, and the formula can accurately evaluate the similarity of the position relationship of each candidate matching pair in the inference matching result.

[0121] S5042: for each inference matching result, determining an evaluation score of the inference matching result based on the position similarity of all candidate matching pairs in the inference matching result, the comprehensive matching degree of the candidate matching pair, and a preset target function. The application embodiment models the target function in advance before applying the target function to obtain a preset target function, such as formula (2):

[0122]

[0123] wherein J(x) is an evaluation score of a certain inference matching result, x i is the i th candidate matching pair in the inference matching result, N is the number of candidate matching pairs in the inference matching result, w i is the weight of the candidate matching pair x i , attScore(x i ) is the comprehensive matching degree of the candidate matching pair x i , and posScore(x i ) is the position similarity of the candidate matching pair x i .

[0124] As can be known from the description of S5041-S5042, the position similarity can measure the consistency of the relative positions between the candidate matching pairs in the reasoning matching result, and the target function can evaluate the advantages and disadvantages of the reasoning matching result. Since a reasoning matching result is composed of multiple candidate matching pairs, and the relative accuracy between the multiple candidate matching pairs and the size of the comprehensive matching degree of the candidate matching pairs can both determine the advantages and disadvantages of the reasoning matching result, when modeling the target function, the position similarity of all candidate matching pairs and the comprehensive matching degree of all candidate matching pairs are used as the scoring basis. The target function evaluates each reasoning matching result in the same scene, scores each reasoning matching result, and finally outputs the reasoning matching result with the highest evaluation score, which is used as the target matching result. The purpose is to realize the evaluation and selection of the reasoning matching result.

[0125] In a possible implementation, S5041: calculating the position similarity of the candidate matching pair includes the following S1-S6.

[0126] S1: extracting the first component position information, the second component position information, and the third component position information of the candidate matching pair from the position data of the candidate matching pair, respectively; wherein the first component position information is the position information of the candidate matching pair in the horizontal direction, the second component position information is the position information of the candidate matching pair in the vertical direction, and the third component position information is the position information of the candidate matching pair in the perpendicular direction.

[0127] In the embodiment of the present application, the horizontal distance generally refers to the distance from the marking line to the driving track in the direction perpendicular to the driving direction. In the embodiment of the present application, the position information of the candidate matching pair in the horizontal direction can be understood as the horizontal distance, which in the embodiment can refer to the distance between the candidate matching pair and the marking line. The vertical distance generally refers to the length of the driving track in the direction parallel to the driving direction. In the embodiment of the present application, the position information of the candidate matching pair in the vertical direction can be understood as the vertical distance, which in the embodiment of the present application refers to the distance between the candidate matching pair and the fixed point in the direction parallel to the driving direction.

[0128] S2: extracting the fourth component position information, the fifth component position information, and the sixth component position information of the other candidate matching pair from the position data of the other candidate matching pair in the reasoning matching result, respectively; wherein the fourth component position information is the position information of the other candidate matching pair in the horizontal direction, the fifth component position information is the position information of the other candidate matching pair in the vertical direction, and the sixth component position information is the position information of the other candidate matching pair in the perpendicular direction.

[0129] S3: calculating the horizontal position similarity of the candidate matching pair based on the first component position information of the candidate matching pair, the fourth component position information of the other candidate matching pair, and the horizontal position similarity calculation formula.

[0130] In the same inference matching result, the formula for calculating the lateral positional similarity between a candidate matching pair and any other candidate matching pair is shown in equation (3):

[0131]

[0132] Where, ψ(x) i ,x j x represents the lateral positional similarity between a candidate matching pair and any other candidate matching pair. i For candidate matching pairs, x j For other candidate matching pairs in the same inference matching result, d i The first component position information of the candidate matching pair, or the lateral distance of the candidate matching pair, d j This refers to the fourth component positional information of other candidate matching pairs, or the lateral distance between other candidate matching pairs. Therefore, it can be seen that the candidate matching pair and some other candidate matching pair x... j Horizontal position similarity between and |d i -d j |Inversely proportional.

[0133] Since there are multiple candidate matching pairs in the same reasoning matching result, the horizontal positional similarity of a candidate matching pair is related to the horizontal positional similarity between all other candidate matching pairs when calculating. Therefore, the horizontal positional similarity of a candidate matching pair is given by equation (4):

[0134]

[0135] Where x is a candidate matching pair, x j Let N be the j-th candidate match in the same inference matching result, and N be the number of candidate match pairs in the same inference matching result. S4: Calculate the vertical position similarity of candidate matching pairs based on the second component position information of candidate matching pairs, the fifth component position information of other candidate matching pairs, and the vertical position similarity calculation formula.

[0136] S5: Calculate the vertical position similarity of candidate matching pairs based on the position information of the third component of candidate matching pairs, the position information of the sixth component of other candidate matching pairs, and the formula for calculating vertical position similarity.

[0137] It should be understood that the longitudinal position similarity calculation formula in S4 and the vertical position similarity calculation formula in S5 can be consistent with the transverse position similarity calculation formula in S3 or not. The form of each formula can be customized according to actual needs. Therefore, the specific form of the transverse position similarity calculation formula, the longitudinal position similarity calculation formula, and the vertical position similarity calculation formula is not limited in the embodiments of the present application.

[0138] S6: Based on the transverse position similarity, the longitudinal position similarity and the vertical position similarity of the candidate matching pair, the position similarity of the candidate matching pair is determined. When considering the transverse, longitudinal and vertical directions, the position similarity of the candidate matching pair is formula (5):

[0139]

[0140] wherein i is the i-th in the three dimensions of transverse, longitudinal or vertical direction; w i is the weight of the candidate matching pair in the transverse, longitudinal or vertical direction, is the transverse, longitudinal or vertical position similarity of the candidate matching pair.

[0141] As can be seen from the description of S1-S6, the transverse position similarity is used to measure the consistency between the matching pairs in the transverse position, and the longitudinal position similarity is used to measure the consistency between the matching pairs in the longitudinal position, and the vertical position similarity is used to measure the consistency between the matching pairs in the vertical position. From the transverse, longitudinal and vertical multi-dimensional angles, the consistency between the matching pairs in the three-dimensional space can be measured.

[0142] The embodiments of the present application define the comprehensive matching degree calculation method between elements in the multi-dimensional index system, the candidate matching result comprehensive evaluation method, and design a reasoning matching method based on the greedy algorithm, and then obtain the target matching result with high accuracy. On this basis, the target matching result can be used to find the map changes and update the high-precision map. Through the accurate evaluation and fast search algorithm of the candidate matching result, the embodiments of the present application can update the map more efficiently under the condition of ensuring the accuracy of map recognition.

[0143] In summary, the overall process of the embodiment of the present application has four steps: scene establishment, generating matching pairs, reasoning matching, and evaluating the optimal. The specific process of scene establishment is shown in S204-S205, the specific process of generating matching pairs is shown in S402-S406, the specific process of reasoning matching is shown in S503, and the specific process of evaluating the optimal is shown in S504. In the process of generating matching pairs, the modeling of the matching degree evaluation index and the operation of attribute discretization can more accurately calculate the comprehensive matching degree between the map elements and the observation elements. In the process of reasoning matching, through the efficient search algorithm and the modeling of the problem, the accuracy of the matching can be improved under the premise of ensuring the search efficiency. In the process of evaluating the optimal, the relative position relationship similarity between the candidate matching pairs in the reasoning matching result can be more accurately evaluated through the modeling of the position similarity.

[0144] Figure 6 A structure diagram of a map update processing device provided by the embodiment of the present application is shown. The device of the embodiment can be in the form of software and / or hardware. As shown in the figure, the map update processing device provided by the embodiment includes an acquisition module 61, a calculation module 62, and a determination module 63. Figure 6

[0145] The acquisition module 61 is configured to acquire the map data and the observation data of the same target region according to the original region on the map to be updated in the acquired map update request, wherein the target region is a sub-region obtained by dividing the original region, the map data includes the feature data of at least one map element, and the observation data includes the feature data of at least one observation element.

[0146] The calculation module 62 is configured to calculate the comprehensive matching degree between any map element and any observation element according to the feature data of the map element, the feature data of the observation element, and the pre-established multi-dimensional index system, and combine the map element and the observation element with the comprehensive matching degree greater than a preset threshold into a candidate matching pair.

[0147] The determination module 63 is configured to determine a target matching result based on all the candidate matching pairs, so as to realize the update of the original region on the map to be updated, wherein the target matching result is a set of the target matching pairs of the plurality of candidate matching pairs.

[0148] In a possible implementation manner, the calculation module 62 includes an identification unit and a calculation unit, wherein:

[0149] The identification unit is configured to identify the indexes in the pre-established multi-dimensional index system, wherein the multi-dimensional index system includes at least two indexes: an attribute index, a confidence index, and a spatial position index.

[0150] ​The computing unit is configured to, for any map element and any observation element, if the indexes in the multi-dimensional index system include attribute indexes, extract attribute data of the map element from the feature data of the map element, extract attribute data of the observation element from the feature data of the observation element, and calculate an attribute matching degree between the map element and the observation element according to the attribute data of the map element and the attribute data of the observation element.

[0151] The computing unit is further configured to, if the indexes in the multi-dimensional index system include spatial position indexes, extract spatial position data of the map element from the feature data of the map element, extract spatial position data of the observation element from the feature data of the observation element, and calculate a spatial position matching degree between the map element and the observation element according to the spatial position data of the map element and the spatial position data of the observation element.

[0152] The computing unit is further configured to, if the indexes in the multi-dimensional index system include reliability indexes, extract reliability data of the observation element from the feature data of the observation element, and calculate a reliability matching degree between the map element and the observation element according to the reliability data of the observation element.

[0153] The computing unit is further configured to calculate a comprehensive matching degree between the map element and the observation element based on at least two of the attribute matching degree, the spatial position matching degree and the reliability matching degree determined according to the indexes in the multi-dimensional index system.

[0154] In a possible implementation, when the attribute indexes include at least two sub-attribute indexes of type, width, color, height, size, shape and color, the computing unit is further configured to:

[0155] extract sub-attribute data of the map element on each sub-attribute index from the attribute data of the map element, and extract sub-attribute data of the observation element on each sub-attribute index from the attribute data of the observation element.

[0156] calculate, for each sub-attribute index, a sub-attribute matching degree between the map element and the observation element according to the sub-attribute data of the map element on the sub-attribute index and the sub-attribute data of the observation element on the sub-attribute index.

[0157] determine the attribute matching degree between the map element and the observation element based on the sub-attribute matching degrees between the map element and the observation element on all the sub-attribute indexes.

[0158] In a possible implementation, the determining module 63 includes an inference matching unit and a calculation determining unit, and wherein:

[0159] The inference matching unit is configured to perform inference matching based on a preset target search algorithm and all candidate matching pairs to obtain a plurality of inference matching results; wherein the inference matching result is a set of the plurality of candidate matching pairs.

[0160] The computing and determining unit is configured to calculate an evaluation score of each inference matching result, and determine the inference matching result with the highest evaluation score as the target matching result.

[0161] In a possible implementation, the computing and determining unit is further configured to:

[0162] For each candidate matching pair in any inference matching result, the position similarity of the candidate matching pair is calculated according to the position data of the candidate matching pair, the position data of other candidate matching pairs in the inference matching result, and a preset position similarity calculation formula.

[0163] For each inference matching result, the evaluation score of the inference matching result is determined based on the position similarity of all candidate matching pairs in the inference matching result, the comprehensive matching degree of the candidate matching pairs, and a preset target function.

[0164] When the position similarity calculation formula includes a horizontal position similarity calculation formula, a vertical position similarity calculation formula, and a vertical position similarity calculation formula, the computing and determining unit is further configured to:

[0165] The first component position information, the second component position information, and the third component position information of the candidate matching pair are extracted from the position data of the candidate matching pair, respectively; the first component position information is the position information of the candidate matching pair in the horizontal direction, the second component position information is the position information of the candidate matching pair in the vertical direction, and the third component position information is the position information of the candidate matching pair in the vertical direction.

[0166] The fourth component position information, the fifth component position information, and the sixth component position information of the other candidate matching pairs are extracted from the position data of the other candidate matching pairs in the inference matching result, respectively; the fourth component position information is the position information of the other candidate matching pairs in the horizontal direction, the fifth component position information is the position information of the other candidate matching pairs in the vertical direction, and the sixth component position information is the position information of the other candidate matching pairs in the vertical direction.

[0167] The horizontal position similarity of the candidate matching pair is calculated based on the first component position information of the candidate matching pair, the fourth component position information of the other candidate matching pairs, and the horizontal position similarity calculation formula.

[0168] The vertical position similarity of the candidate matching pair is calculated based on the second component position information of the candidate matching pair, the fifth component position information of the other candidate matching pairs, and the vertical position similarity calculation formula.

[0169] The vertical position similarity of the candidate matching pair is calculated based on the third component position information of the candidate matching pair, the sixth component position information of other candidate matching pairs, and a vertical position similarity calculation formula.

[0170] The position similarity of the candidate matching pair is determined based on the horizontal position similarity, the vertical position similarity, and the vertical position similarity of the candidate matching pair.

[0171] The map updating processing device provided in the embodiment can be used to execute the map updating processing method provided in any of the above method embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0172] In the technical solution of the present application, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0173] According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

[0174] Figure 7 A structural schematic diagram of an electronic device provided in the embodiment of the present application is shown in FIG. 7. The electronic device includes a receiver 70, a transmitter 71, at least one processor 72, and a memory 73. The electronic device composed of the above components can be used to implement the above several specific embodiments of the present application, and will not be described here.

[0175] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions. When the processor executes the computer execution instructions, each step in the method in the above embodiment is implemented.

[0176] The embodiment of the present application further provides a computer program product, which includes a computer program. When the processor executes the computer program, each step in the method in the above embodiment is implemented.

[0177] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on a chip systems (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0178] Program code for carrying out methods of the present application can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, or entirely on a remote machine or electronic device.

[0179] In the context of the present application, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer-readable storage medium can include one or more lines of electrical conductors, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0180] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0181] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0182] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the spirit and scope of the technology disclosed herein. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed herein are achieved. The present disclosure is not limited in this regard.

[0183] The specific embodiments described herein have been chosen for purposes of illustration and example only. Those of ordinary skill in the art will appreciate that other embodiments and modifications are possible so long as the principles of the application are maintained. The scope of the application is defined by the appended claims and their equivalents.

Claims

1. A map update processing method characterized by comprising: The method comprises: obtaining original map data of an original area and original observation data collected by a sensor; dividing the original map data and the original observation data according to the density of point elements to obtain map data and observation data of a plurality of target areas; obtaining the map data and the observation data of the same target area according to an original area on a map to be updated in a map update request; wherein the target area is a sub-area obtained by dividing the original area, the map data comprises feature data of at least one map element, and the observation data comprises feature data of at least one observation element; calculating a comprehensive matching degree between any map element and any observation element according to the feature data of the map element, the feature data of the observation element, and a pre-established multi-dimensional index system, and combining a map element and an observation element with a comprehensive matching degree greater than a preset threshold into a candidate matching pair; the multi-dimensional index system comprises at least two indexes: an attribute index, a reliability index, and a spatial position index; determining a target matching result based on all the candidate matching pairs to update the original area on the map to be updated; wherein the target matching result is a set of the candidate matching pairs as target matching pairs.

2. The method of claim 1, wherein, The method of calculating a comprehensive matching degree between any map element and any observation element according to the feature data of the map element, the feature data of the observation element, and a pre-established multi-dimensional index system comprises: identifying indexes in the pre-established multi-dimensional index system; for any map element and any observation element, if the indexes in the multi-dimensional index system comprise the attribute index, extracting attribute data of a map element from the feature data of the map element, extracting attribute data of an observation element from the feature data of the observation element, and calculating an attribute matching degree between the map element and the observation element according to the attribute data of the map element and the attribute data of the observation element; if the indexes in the multi-dimensional index system comprise the spatial position index, extracting spatial position data of a map element from the feature data of the map element, extracting spatial position data of an observation element from the feature data of the observation element, and calculating a spatial position matching degree between the map element and the observation element according to the spatial position data of the map element and the spatial position data of the observation element; if the indexes in the multi-dimensional index system comprise the reliability index, extracting reliability data of an observation element from the feature data of the observation element, and calculating a reliability matching degree between the map element and the observation element according to the reliability data of the observation element; calculating a comprehensive matching degree between the map element and the observation element based on at least two of the attribute matching degree, the spatial position matching degree, and the reliability matching degree determined based on the indexes in the multi-dimensional index system.

3. The method of claim 2, wherein, When the attribute indicators include at least two sub-attribute indicators of type, width, height, size, shape and color, the calculation of the attribute matching degree between the map element and the observation element according to the attribute data of the map element and the attribute data of the observation element comprises: extracting the sub-attribute data of the map element on each sub-attribute indicator from the attribute data of the map element, and extracting the sub-attribute data of the observation element on each sub-attribute indicator from the attribute data of the observation element; for each sub-attribute indicator, calculating the sub-attribute matching degree between the map element and the observation element according to the sub-attribute data of the map element on the sub-attribute indicator and the sub-attribute data of the observation element on the sub-attribute indicator; determining the attribute matching degree between the map element and the observation element based on the sub-attribute matching degrees between the map element and the observation element on all sub-attribute indicators.

4. The method of claim 1, wherein, The determination of the target matching result based on all the candidate matching pairs comprises: performing inference matching based on a preset target search algorithm and all the candidate matching pairs to obtain a plurality of inference matching results; wherein the inference matching result is a set of a plurality of the candidate matching pairs; calculating the evaluation score of each inference matching result, and determining the inference matching result with the highest evaluation score as the target matching result.

5. The method of claim 4, wherein, The calculation of the evaluation score of each inference matching result comprises: for each candidate matching pair in any inference matching result, calculating the position similarity of the candidate matching pair according to the position data of the candidate matching pair, the position data of other candidate matching pairs in the inference matching result, and a preset position similarity calculation formula; for each inference matching result, determining the evaluation score of each inference matching result based on the position similarity of all the candidate matching pairs in the inference matching result, the comprehensive matching degree of the candidate matching pairs, and a preset target function.

6. A map update processing apparatus characterized by comprising: comprise: an acquisition module configured to acquire original map data of an original region and original observation data collected by a sensor; dividing the original map data and the original observation data according to the density of point elements to obtain map data and observation data of a plurality of target regions; acquiring the map data and the observation data of the same target region according to an original region on a map to be updated in a map update request; wherein the target region is a sub-region obtained by cutting the original region, the map data comprises feature data of at least one map element, and the observation data comprises feature data of at least one observation element; a calculation module configured to calculate a comprehensive matching degree between any map element and any observation element according to the feature data of the map element, the feature data of the observation element and a pre-established multi-dimensional index system, and combine the map element and the observation element with a comprehensive matching degree greater than a preset threshold into a candidate matching pair; the multi-dimensional index system comprises at least two indicators: an attribute indicator, a confidence indicator and a spatial position indicator. A determining module is configured to determine a target matching result based on all the candidate matching pairs, so as to realize updating of the original area on the to-be-updated map; wherein the target matching result is a set of target matching pairs including the plurality of candidate matching pairs.

7. An electronic device, comprising: Comprising: at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the map updating processing method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by the processor to implement the map updating processing method according to any one of claims 1 to 5.

9. A computer program product comprising a computer program which, when executed by a processor, implements the map updating processing method according to any one of claims 1 to 5.

Images