Map data processing method, device, computer equipment and storage medium

Abstract

The present invention relates to the technical field of data processing, and discloses a method, device, computer equipment and storage medium for processing map data, the method comprising: obtaining open map data and to-be-processed map data to be assigned road attributes; extracting the location information and road attributes of each first road from the open map data, and extracting the location information of each second road from the to-be-processed map data; determining the first road and the second road with matching positions according to the location information of the first road and the location information of the second road; assigning a value to the road attribute of the second road according to the road attribute of the first road that matches the second road. The present invention uses open map data to obtain road attributes, the road attribute has high accuracy, and the acquisition method is simple and efficient, and can simply, efficiently and accurately assign more complete road attributes to existing maps.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, computer equipment and storage medium for processing map data. Background Art

[0002] In order to meet the needs of urban planning, navigation and positioning, it is necessary to assign road attributes to existing road maps. The methods of obtaining road attributes mainly include obtaining road data through sensors such as images and radars, training road data using deep learning networks or other traditional methods, identifying road categories, identifying road feature backgrounds, and improving recognition accuracy through noise suppression and other methods to obtain road categories and attributes.

[0003] This type of solution has the following disadvantages: 1. It relies on sensors to provide data, and when processing large quantities of national road information, there will be problems with high data costs or difficulty in obtaining data; 2. In some special scenarios, the model is difficult to generalize, resulting in difficulty in correct identification, which ultimately leads to incorrect road attributes. Summary of the invention

[0004] In view of this, the present invention provides a method, apparatus, computer device and storage medium for processing map data, so as to efficiently and accurately assign road attributes to a map.

[0005] In a first aspect, the present invention provides a method for processing map data, comprising:

[0006] Obtaining open map data and unprocessed map data to be assigned road attributes;

[0007] Extracting the location information and road attributes of each first road from the open map data, and extracting the location information of each second road from the map data to be processed;

[0008] Determining a first road and a second road with matching positions according to the position information of the first road and the position information of the second road;

[0009] The road attributes of the second road are assigned values ​​according to the road attributes of the first road that matches the second road.

[0010] In some optional implementations, determining the first road and the second road with matching positions according to the position information of the first road and the position information of the second road includes:

[0011] generating a first position sequence corresponding to the first road according to the position information of the first road, and generating a second position sequence corresponding to the second road according to the position information of the second road;

[0012] Using the first position sequence as an observation sequence and the second position sequence as a state sequence, performing road matching to generate a first matching result; the first matching result includes a matching relationship between the first road and at least one of the second roads;

[0013] Using the first position sequence as a state sequence and the second position sequence as an observation sequence, performing road matching to generate a second matching result; the second matching result includes a matching relationship between the second road and at least one of the first roads;

[0014] A first road and a second road whose positions match are determined according to the first matching result and the second matching result.

[0015] In some optional implementations, the using the first position sequence as a state sequence and the second position sequence as an observation sequence to perform road matching to generate a second matching result includes:

[0016] Classify the first road according to its road attributes to determine the category to which the first road belongs;

[0017] According to the categories to which the first roads belong, a state set corresponding to each category is generated; the state set includes at least one first position sequence of the first roads belonging to the same category;

[0018] Road matching is performed respectively with the state sets of each category according to the second position sequence to generate sub-matching results corresponding to the corresponding category; and the sub-matching results are included in the second matching results.

[0019] In some optional implementations, determining the first road and the second road with matching positions according to the first matching result and the second matching result includes:

[0020] In a case where the sub-matching result corresponds to a target category, determining a partial matching result in the first matching result corresponding to a first road belonging to the target category;

[0021] A first road and a second road with matching positions are determined according to the sub-matching result and the partial matching result.

[0022] In some optional implementations, determining the first road and the second road with matching positions according to the first matching result and the second matching result includes:

[0023] Determining a first road and a second road having a valid matching relationship according to an intersection of the first matching result and the second matching result;

[0024] Determining a position matching degree between a first road and a second road having a valid matching relationship;

[0025] When the position matching degree satisfies the matching condition, it is determined that the first road and the second road having a valid matching relationship are positionally matched.

[0026] In some optional implementations, determining the position matching degree between the first road and the second road having a valid matching relationship includes:

[0027] Determine a first starting point and a first end point of a first pending road, and a second starting point and a second end point of a second pending road; the first pending road and the second pending road are respectively a first road and a second road having a valid matching relationship;

[0028] In the case where both the second starting point and the second end point are located between the first starting point and the first end point, setting the position matching degree between the first undetermined road and the second undetermined road to a position matching degree that satisfies a matching condition;

[0029] In the case where one of the second starting point and the second end point is located between the first starting point and the first end point, but the other of the second starting point and the second end point is not located between the first starting point and the first end point, if there is a third undetermined road that has a valid matching relationship with the second undetermined road and has the same road attributes as the first undetermined road, then determining whether the other of the second starting point and the second end point is located between the starting point and the end point of the third undetermined road;

[0030] In the case where the other of the second starting point and the second end point is located between the starting point and the end point of the third pending road, the position matching degree between the first pending road and the second pending road is set to a position matching degree that satisfies the matching conditions, and the position matching degree between the third pending road and the second pending road is set to a position matching degree that satisfies the matching conditions.

[0031] In some optional embodiments, the method further comprises:

[0032] Acquire other road data; the other road data includes road attributes of at least one road;

[0033] The road attributes in the open map data are merged according to the road attributes in the other road data, and the merged road attributes are used as the road attributes of each first road in the open map data.

[0034] In a second aspect, the present invention provides a map data processing device, comprising:

[0035] An acquisition module, used for acquiring open map data and unprocessed map data to be assigned road attributes;

[0036] An information extraction module, used to extract the location information and road attributes of each first road from the open map data, and to extract the location information of each second road from the map data to be processed;

[0037] A matching module, configured to determine a first road and a second road whose positions match according to the position information of the first road and the position information of the second road;

[0038] The processing module is used to assign a road attribute to the second road according to the road attribute of the first road matching the second road.

[0039] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for processing map data of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for processing map data of the first aspect or any corresponding embodiment thereof.

[0041] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for processing map data of the first aspect or any corresponding embodiment thereof.

[0042] The present invention uses open map data to extract the road attributes of a first road, and determines the second road that matches the position of the first road in the map data to be processed by road matching, so that the road attributes of the first road can be assigned to the matching second road, thereby improving the road attributes of each second road in the map data to be processed. The method uses open map data to obtain road attributes, the road attributes have high accuracy, and the acquisition method is simple and efficient. It can simply, efficiently and accurately give more complete road attributes to existing maps, and can be widely used in scenarios such as the planning and use of urban maps. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 is a flowchart of a method for processing map data according to an embodiment of the present invention;

[0045] Figure 2 is a flowchart of another method for processing map data according to an embodiment of the present invention;

[0046] Figure 3 is a simple schematic diagram of a road in a map according to an embodiment of the present invention;

[0047] Figure 4 is another simple schematic diagram of a road in a map according to an embodiment of the present invention;

[0048] Figure 5 is a structural block diagram of a map data processing device according to an embodiment of the present invention;

[0049] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] According to an embodiment of the present invention, an embodiment of a method for processing map data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0052] In this embodiment, a method for processing map data is provided, which can be applied to computers, mobile terminals or servers, etc. Figure 1 is a flowchart of a method for processing map data according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps.

[0053] Step S101, obtaining open map data and map data to be processed and to which road attributes are to be assigned.

[0054] In this embodiment, for an existing map in which each road needs to be assigned road attributes, the map is used as a map to be processed. The map to be processed can be a map created by itself or a third-party map, which is not limited in this embodiment. Relevant data of the map to be processed, that is, the map data to be processed, can be extracted. The map to be processed can be a geometric topological map. Accordingly, the map data to be processed includes the topological information and shape of the road.

[0055] In addition, relevant data of open maps, namely open map data, is also obtained. Open maps refer to maps that are open to some or all users; for example, open maps may be open source OSM (Open Street Map) or other open source maps.

[0056] Take OSM as an example. OSM data is open source, allowing users to edit map data through simple online tools, which means that anyone can access, use and modify the data for free. This openness and editability not only improves the accuracy and real-time nature of map data, but also promotes the continuous updating and improvement of map data. Compared with other model recognition solutions that have more scenes that are difficult to recognize in images, the map data provided by OSM will be more accurate and easier to obtain.

[0057] Step S102: extracting the location information and road attributes of each first road from the open map data, and extracting the location information of each second road from the map data to be processed.

[0058] In this embodiment, the open map data includes relevant information of each road. For the convenience of description, the road in the open map data is referred to as a first road, and the information of the first road specifically includes location information and road attributes. In addition, the location information of each road extracted from the map data to be processed is also obtained. For the convenience of distinguishing description, the road in the map data to be processed is referred to as a second road.

[0059] Among them, the location information indicates the location of the road, and the location information includes at least the starting point and the end point of the road; in general, the road includes multiple track points, each track point has a location coordinate, and the location coordinates of the track points of the road can form a corresponding position sequence, which represents the location information of the road in the form of a sequence. The road attribute indicates the attribute information of the road; for example, the road attribute may include the road category, the road speed limit information, etc., which is specifically based on the content in the open map data.

[0060] Optionally, after the open map data is acquired, the open map data may be preprocessed to extract accurate location information and road attributes.

[0061] For example, data cleaning, geometric repair, coordinate conversion, projection transformation, etc. can be performed on the open map data to eliminate noise and outliers in the open map data and improve the quality and consistency of the open map data. For example, through coordinate transformation, the open map data can be converted to the same geographic coordinate system as the map data to be processed, so that the two data are consistent and the extracted location information format is unified, which is conducive to subsequent road matching.

[0062] Step S103: determining the first road and the second road whose positions match each other according to the position information of the first road and the position information of the second road.

[0063] In this embodiment, the location information of the first road indicates the location of the first road, and the location information of the second road indicates the location of the second road. Therefore, based on the location information of the first road and the location information of the second road, the first road in the open map data and the second road in the map data to be processed can be position matched to determine the first road and the second road with matching locations.

[0064] For example, if the first road A and the second road B have the same location information, it can be determined that the locations of the first road A and the second road B match.

[0065] It can be understood that, generally, the open map data includes information of a plurality of first roads, and the map data to be processed includes information of a plurality of second roads, and it is necessary to determine whether each first road matches each corresponding second road.

[0066] Step S104, assigning a value to the road attribute of the second road according to the road attribute of the first road that matches the second road.

[0067] In this embodiment, after determining the first road that matches the position of the second road, the road attributes of the first road that matches the second road can be assigned to the second road, thereby updating or improving the road attributes of the second road.

[0068] For example, if the first road A matches the second road B, and the first road A is a highway, the road attribute "highway" can be assigned to the second road B, so that the road attribute of the second road B in the map data to be processed is also added with "highway" information to indicate that the second road B is a highway. When the updated map to be processed is used later, data processing can be performed based on more complete road attributes, providing reliable data support for urban planning, navigation applications, traffic analysis and other fields.

[0069] It can be understood that since the second road itself may have certain road attributes, when assigning road attributes to the second road, it is possible to first determine whether there are road attributes in the road attributes of the first road that matches the second road that the second road does not have; if so, assign these unassigned road attributes to the second road.

[0070] The map data processing method provided in this embodiment uses open map data to extract the road attributes of the first road, and determines the second road matching the position of the first road in the map data to be processed by road matching, so that the road attributes of the first road can be assigned to the matching second road, thereby improving the road attributes of each second road in the map data to be processed. The method uses open map data to obtain road attributes, the road attributes have high accuracy, and the acquisition method is simple and efficient. It can simply, efficiently and accurately give more complete road attributes to existing maps, and can be widely used in scenarios such as the planning and use of urban maps.

[0071] In this embodiment, a method for processing map data is provided, which can be applied to computers, mobile terminals or servers, etc. Figure 2 is a flowchart of a method for processing map data according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps.

[0072] Step S201, obtaining open map data and map data to be processed and to which road attributes are to be assigned.

[0073] For details, please see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0074] Optionally, the method further includes: acquiring other road data; the other road data includes road attributes of at least one road; fusing the road attributes in the open map data according to the road attributes in the other road data, and using the fused road attributes as the road attributes of each first road in the open map data.

[0075] In this embodiment, road data from other sources, i.e. other road data, may also be introduced. For example, the other road data may be traffic flow data, GPS trajectory data, remote sensing image data, etc., which include road attributes of one or more roads. Other road data may provide additional road attribute information, such as road congestion, vehicle speed, etc. Through the fusion and analysis of multi-source data, the road attributes of the first road may be updated, and the attribute characteristics of the road may be more comprehensively understood, thereby giving more comprehensive road attributes to the map data to be processed.

[0076] For example, remote sensing image data can provide rich surface information, including roads, buildings, vegetation, etc. By combining remote sensing image data with open map data such as OSM, road features (such as edges, textures, etc.) in remote sensing image data can be used to assist in extracting road attributes and improve the accuracy and completeness of extraction.

[0077] Step S202: extracting the location information and road attributes of each first road from the open map data, and extracting the location information of each second road from the map data to be processed.

[0078] For details, please see Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0079] Step S203: determining the first road and the second road whose positions match according to the position information of the first road and the position information of the second road.

[0080] Specifically, the above step S203 of "determining the first road and the second road with matching positions according to the position information of the first road and the position information of the second road" includes the following steps S2031 to S2034.

[0081] Step S2031: Generate a first position sequence corresponding to the first road according to the position information of the first road, and generate a second position sequence corresponding to the second road according to the position information of the second road.

[0082] In this embodiment, the position information of the first road and the position information of the second road can be expressed in the form of a sequence, that is, a position sequence, which is a sequence including multiple trajectory points (including a start point and an end point). For ease of description, the position sequence corresponding to the first road is referred to as a first position sequence, and the position sequence corresponding to the second road is referred to as a second position sequence.

[0083] Step S2032, using the first position sequence as an observation sequence and the second position sequence as a state sequence, performing road matching to generate a first matching result; the first matching result includes a matching relationship between the first road and at least one second road.

[0084] Step S2033, using the first position sequence as a state sequence and the second position sequence as an observation sequence, performing road matching to generate a second matching result; the second matching result includes a matching relationship between the second road and at least one first road.

[0085] The purpose of position matching the first road and the second road is to assign the road attribute of the first road to the second road, thereby updating or improving the road attribute of the second road. Therefore, when performing position matching, it is mainly to determine which first roads or roads each second road is position matched with. However, since the position information of the first road in the open map data and the position information of the second road in the map data to be processed can be expressed as a position sequence, in this embodiment, the first road and the second road are matched twice by a positive and negative matching method to improve the accuracy of the final matching.

[0086] Specifically, in order to determine which first roads or roads have a position match with the second road, as shown in the above step S2033, the second road in the map data to be processed can be used as the collected observation value, that is, the second position sequence corresponding to the second road can be used as the observation sequence, and the first road in the open map data can be used as the actual state value, that is, the first position sequence corresponding to the first road can be used as the state sequence. By determining which actual state sequence matches the collected observation sequence, the matching of the two roads can be achieved.

[0087] Among them, the observation sequence of each second road in the map data to be processed (i.e., the second position sequence) can form an observation set, and the state sequence of each first road in the open map data (i.e., the first position sequence) can form a state set. It can be determined which state sequence or states in the state set each observation sequence in the observation set matches.

[0088] For example, the HMM (Hidden Markov Model) algorithm can be used for road matching. Taking step S2033 as an example, the HMM can be constructed based on the observation sequence and the known state set; at this time, the state set corresponds to each first road in the open map data such as OSM, and the observation set corresponds to the second road of the to-be-processed map data to be processed. The state transition probability matrix A is the link probability between the road sections, the observation probability matrix B represents the probability of generating a map on the specified road section, and the initial state probability vector Q represents the probability of the starting position road section.

[0089] The most likely hidden state sequence, i.e., the most likely road segment sequence, is solved by using the HMM decoding algorithm (e.g., the Viterbi algorithm). The most likely road segment sequence is the state sequence (i.e., the first position sequence) that best matches the observation sequence (i.e., the second position sequence), and is also the real path inferred from the trajectory points. Finally, it is determined which first roads or roads the second road matches, thereby generating the corresponding matching result, i.e., the second matching result.

[0090] It can be understood that if the second road does not match any of the first roads, the second road matching fails, and there is no matching relationship related to the second road in the second matching result.

[0091] In addition, contrary to the above step S2033, as shown in the above step S2032, the first position sequence can also be used as an observation sequence and the second position sequence can be used as a state sequence, that is, the first road in the open map data is used as the collected observation value, and the second road in the map data to be processed is used as the actual state value, based on which secondary matching is performed, for example, based on HMM, etc., it is determined that the first road has a matching relationship with which one or more second roads, thereby generating a corresponding first matching result.

[0092] It can be understood that the above-mentioned step S2032 and step S2033 can be executed in parallel or sequentially, and this embodiment does not limit the execution order of the two.

[0093] Step S2034: Determine a first road and a second road whose positions match according to the first matching result and the second matching result.

[0094] As described above, the first matching result and the second matching result both include the matching relationship between the first road and the second road. The first matching result and the second matching result can be mutually verified to ultimately determine a more accurate matching result and determine the first road and the second road with matching positions.

[0095] Among them, the matching relationship between the first road and the second road in the first matching result and the second matching result can be expressed in the form of a road matching pair, and then based on the matching relationship contained in the intersection of the first matching result and the second matching result, the first road and the second road with matching positions are determined.

[0096] For example, in the first matching result, the first road A has a matching relationship with the second road B, the second road C, and the second road D, which can be represented as three matching pairs (A, B), (A, C), and (A, D); while in the second matching result, the second road B has a matching relationship with the first road A, and the second road C has a matching relationship with the first road A, and the second road E has a matching relationship with the first road A, so there are matching pairs (A, B), (A, C), and (A, E) in the second matching result. It can be seen that the intersection of the two is (A, B), (A, C), so it is finally determined that the first road A has a position match with the second road B and the second road C.

[0097] In some optional implementations, the above step S2033 "using the first position sequence as a state sequence and the second position sequence as an observation sequence to perform road matching and generate a second matching result" may include steps A1 to A3.

[0098] Step A1, classifying the first road according to its road attributes to determine the category to which the first road belongs.

[0099] Step A2: generating a state set corresponding to each category according to the category to which each first road belongs; the state set includes at least one first position sequence of the first roads belonging to the same category.

[0100] Step A3: performing road matching with the state sets of each category according to the second position sequence, and generating sub-matching results corresponding to the corresponding categories; the sub-matching results are included in the second matching results.

[0101] In this embodiment, when the open map data is used as the real state value, since each first road in the open map data has a corresponding road attribute, the first roads are classified according to the road attributes of each first road, so that the first roads in the open map data are divided into multiple categories, each category corresponding to a road attribute.

[0102] For example, the first road may be divided into multiple categories such as tunnels, highways, urban expressways, roundabouts, toll booths, etc., or other classification methods may be used, which are not limited in this embodiment.

[0103] For the first roads of each category, the first position sequences (state sequences in this case) of these first roads can be taken as a set to form a corresponding state set; ultimately, a state set corresponding to each category can be generated, and each state set includes the first position sequence of the first roads of the corresponding category.

[0104] When performing road matching, the second position sequence as the observation sequence is road matched with each category of state set, so as to determine whether the second position sequence matches the state sequence in each state set (i.e., the first position sequence), and finally determine which state sequence or states in which state sets the second position sequence matches, thereby generating a corresponding matching result. For the convenience of distinguishing descriptions, this matching result is referred to as a "sub-matching result".

[0105] Under normal circumstances, the second position sequence only has a matching relationship with the state sequence in one category of state set, that is, only a sub-matching result of one category is generated, and the matching results of other categories are empty; if there are multiple other roads near a second road, the second position sequence of the second road may match the state sequences of multiple categories, thereby generating sub-matching results corresponding to multiple categories.

[0106] In this embodiment, when the first position sequence is used as the state sequence, each first position sequence is classified based on the road attribute of the first road, and state sets of different categories are generated. The second road sequence is matched with the state sets of each category, which can improve the matching effect and effectively avoid misjudgment.

[0107] Optionally, the above step S2034 "determining the first road and the second road with matching positions according to the first matching result and the second matching result" may include steps B1 and B2.

[0108] Step B1: when the sub-matching result corresponds to the target category, determine a partial matching result in the first matching result that corresponds to the first road belonging to the target category.

[0109] Step B2: Determine the first road and the second road with matching positions according to the sub-matching result and the partial matching result.

[0110] In this embodiment, for a second road, its sub-matching result corresponds to a corresponding category. For ease of description, the category corresponding to the sub-matching result is called a target category; it can be understood that the target category is one of the categories. When performing road matching on the second road, it can be matched with the complete first matching result. Alternatively, it is also possible to exchange the partial matching results corresponding to the first road belonging to the target category from the first matching result, and then only perform road matching with this partial matching result (a part of the data in the first matching result). This can not only reduce the amount of data during road matching and improve matching efficiency, but also reduce the influence of other categories of first roads, and further improve the accuracy of matching.

[0111] Optionally, the above step S2034 "determining the first road and the second road with matching positions according to the first matching result and the second matching result" may include steps C1 to C3.

[0112] Step C1, determining a first road and a second road having a valid matching relationship according to the intersection of the first matching result and the second matching result.

[0113] Step C2, determining the position matching degree between the first road and the second road having a valid matching relationship.

[0114] Step C3: when the position matching degree satisfies the matching condition, determining that the first road and the second road having a valid matching relationship are positionally matched.

[0115] In this embodiment, the intersection of the first matching result and the second matching result represents a matching relationship that meets both the first matching result and the second matching result. This matching relationship has a high confidence level. For ease of description, this matching relationship is referred to as an effective matching relationship. Among them, for the first road and the second road with an effective matching relationship, it can be directly determined that the positions of the two roads match, but due to different ways of dividing roads in different maps, it may lead to misjudgment. Therefore, this embodiment further determines the matching degree between the roads, that is, the position matching degree.

[0116] Specifically, for a first road and a second road having a valid matching relationship, whether the positions of the two roads match can be determined based on their position information, which is represented by the position matching degree in this embodiment; for example, the degree of position overlap of the two roads can be used as the position matching degree.

[0117] A matching condition may be pre-set, and if the position matching degree between the first road and the second road having a valid matching relationship satisfies the matching condition, then the positions of the two roads may be considered to be matched. For example, the higher the position matching degree, the more matched the two roads are, so a matching degree threshold may be set, and if the position matching degree exceeds the matching degree threshold, then it may be determined that the positions of the two roads are matched.

[0118] Figure 3 A simple schematic diagram of roads in the open map and the map to be processed is shown, Figure 3 As shown, the open map includes three first roads, namely, first road AB, first road BC, and first road CD, and the map to be processed includes three second roads, namely, second road EF, second road FG, and second road GH. Among them, A, B, C, and D are track points in the open map, and E, F, G, and H are track points in the map to be processed, and point A and point E are at the same position.

[0119] If the first matching result indicates that the first road AB has a matching relationship with the second road EF and the second road FG, the second matching result indicates that the second road EF has a matching relationship with the first road AB, and the second road FG has a matching relationship with the first road AB and the first road BC. Based on the intersection of the two matching results, it can be determined that the first road AB has a valid matching relationship with the second road EF and the second road FG. Figure 3 As shown, the position deviation between the first road AB and the second road FG is large, and the position matching degree between the two is small, so the effective matching relationship is ignored, and finally the position matching between the first road AB and the second road EF is determined, and the road attributes of the first road AB can be assigned to the second road EF later.

[0120] It can be understood that if road matching is performed based on the classified matching results as shown in the above steps B1 to B2, then in step C1, the first matching result is specifically a partial matching result corresponding to the target category, and the second matching result is a sub-matching result corresponding to the target category.

[0121] Optionally, the above step C2 of “determining the position matching degree between the first road and the second road having a valid matching relationship” specifically includes steps C21 to C24.

[0122] Step C21, determining the first starting point and the first end point of the first pending road, and the second starting point and the second end point of the second pending road; the first pending road and the second pending road are respectively the first road and the second road having a valid matching relationship.

[0123] Step C22, when the second starting point and the second end point are both located between the first starting point and the first end point, setting the position matching degree between the first undetermined road and the second undetermined road to a position matching degree that satisfies the matching condition.

[0124] Step C23, when one of the second starting point and the second end point is located between the first starting point and the first end point, but the other of the second starting point and the second end point is not located between the first starting point and the first end point, if there is a third pending road that has a valid matching relationship with the second pending road and has the same road attributes as the first pending road, then determine whether the other of the second starting point and the second end point is located between the starting point and the end point of the third pending road.

[0125] Step C24, when the other of the second starting point and the second end point is located between the starting point and the end point of the third pending road, the position matching degree between the first pending road and the second pending road is set to the position matching degree that satisfies the matching condition, and the position matching degree between the third pending road and the second pending road is set to the position matching degree that satisfies the matching condition.

[0126] In this embodiment, for the convenience of subsequent description, the first road and the second road with a valid matching relationship are respectively referred to as the first pending road and the second pending road. The first pending road and the second pending road both have a starting point and an end point. In this embodiment, the position matching degree is determined by judging the position relationship between the starting point and the end point between the first pending road and the second pending road, and the position matching between the first pending road and the second pending road is determined.

[0127] Continue with Figure 3 Take the map shown in the figure as an example, and then Figure 4 As shown, the open map includes two types of roads, namely tunnels and highways, wherein the first road AB is a tunnel, and the first roads BC and CD are both highways. Since the purpose of determining the first road and the second road that match the positions is to assign road attributes to the second road, the first road that matches the second road needs to have unique road attributes to avoid assignment errors.

[0128] There are only two types of position matching degrees, one is the position matching degree that meets the matching condition, for example, 1, and the other is the position matching degree that does not meet the matching condition, for example, 0. Alternatively, the position matching degree can also be directly represented by a Boolean value, for example, the position matching degree that meets the matching condition is true, and the position matching degree that does not meet the matching condition is false. Based on the Boolean value, the first road and the second road having the effective matching relationship can also be directly determined to match each other.

[0129] like Figure 4 As shown, if there is a valid matching relationship between the first road AB and the second road EF and the second road FG, the first road AB is used as the first undetermined road, with the first starting point A and the first end point B. Similarly, the second road EF is used as the second undetermined road, with the second starting point E and the second end point F. Figure 4 As shown, the second starting point E and the second end point F are both located between the first starting point A and the first end point B, so the position matching degree between the first road AB and the second road EF is marked as satisfying the matching condition, and then it can be determined that the positions of the first road AB and the second road EF match, and subsequently the road attribute "tunnel" of the first road AB is assigned to the second road EF, so that the second road EF can also be determined as a tunnel in the map to be processed.

[0130] However, if the second pending road is not completely within a first pending road, that is, the second starting point is between the first starting point and the first end point, but the second end point is not between the first starting point and the first end point, or the second end point is between the first starting point and the first end point, but the second starting point is not between the first starting point and the first end point, then further determine whether there is a first road in the open map, the first road has a valid matching relationship with the second pending road, and the first road and the first pending road also have the same road attributes, then the first road is used as the third pending road for subsequent processing. If there is no third pending road, the positions of the first pending road and the second pending road do not match, or in other words, the position matching degree between the two is a position matching degree that does not meet the matching conditions.

[0131] like Figure 4 As shown, if there is a valid matching relationship between the first road AB and the second road FG, the second end point G at this time is not between the first starting point A and the first end point B, even if the second road FG and the first road BC have a valid matching relationship, but because the attributes of the first road AB and the first road BC are inconsistent, there is no third pending road that meets the conditions, that is, the second road FG does not match any first road position, and the road attributes of the second road FG are not assigned subsequently.

[0132] For the second road GH, if there is a valid mapping relationship between it and the first road BC, although the second end point H at this time is not between the first roads BC, that is, not between the first starting point B and the first end point C, there is also a valid mapping relationship between the second road GH and the first road CD, and the first road CD and the first road BC (the first pending road at this time) have the same road attributes, so the first road CD can be used as the third pending road.

[0133] It can be understood that when judging whether a first road can be used as a third pending road, if there are other first roads between the first road and the first pending road, these other first roads also need to have the same road attributes as the first pending road, otherwise the first road will not be determined as the third pending road.

[0134] Among them, since the second end point H is located between the starting point C and the end point D of the first road CD, it can be determined that although the second road GH crosses multiple first roads, these first roads have the same road attribute, and the second road GH can be assigned a value later. Therefore, it can be determined that the second road GH is positionally matched with the first road BC and the first road CD, and the corresponding position matching degrees also meet the matching conditions. Afterwards, the road attribute of the second road GH can be set to "highway".

[0135] Step S204: assigning a value to the road attribute of the second road according to the road attribute of the first road that matches the second road.

[0136] For details, please see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0137] The map data processing method provided in this embodiment can obtain a high-confidence matching relationship more accurately by performing a secondary matching of the first road and the second road in a positive and negative matching manner, thereby improving the accuracy of position matching. The method has good flexibility and scalability, and the algorithm can be optimized and expanded according to needs. On the basis of selecting a valid matching relationship based on the intersection, further determining whether the road is positionally matched based on the position matching degree can further improve the accuracy of matching; and, based on the position relationship between the starting point and the end point of the first road and the second road, it can be simply, conveniently and accurately determined whether the first road and the second road are positionally matched, and the determined road attributes are unique, ensuring the accuracy of the subsequent assignment of road attributes to the second road.

[0138] In this embodiment, a map data processing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0139] This embodiment provides a map data processing device, such as Figure 5 As shown, including:

[0140] An acquisition module 501 is used to acquire open map data and to-be-processed map data to be assigned road attributes;

[0141] An information extraction module 502, for extracting the location information and road attributes of each first road from the open map data, and extracting the location information of each second road from the map data to be processed;

[0142] A matching module 503, configured to determine a first road and a second road whose positions match according to the position information of the first road and the position information of the second road;

[0143] The processing module 504 is used to assign a road attribute to the second road according to the road attribute of the first road matching the second road.

[0144] In some optional implementations, the matching module 503 determines the first road and the second road with matching positions according to the position information of the first road and the position information of the second road, including:

[0145] generating a first position sequence corresponding to the first road according to the position information of the first road, and generating a second position sequence corresponding to the second road according to the position information of the second road;

[0146] Using the first position sequence as an observation sequence and the second position sequence as a state sequence, performing road matching to generate a first matching result; the first matching result includes a matching relationship between the first road and at least one of the second roads;

[0147] Using the first position sequence as a state sequence and the second position sequence as an observation sequence, performing road matching to generate a second matching result; the second matching result includes a matching relationship between the second road and at least one of the first roads;

[0148] A first road and a second road whose positions match are determined according to the first matching result and the second matching result.

[0149] In some optional implementations, the matching module 503 uses the first position sequence as a state sequence and the second position sequence as an observation sequence to perform road matching to generate a second matching result, including:

[0150] Classify the first road according to its road attributes to determine the category to which the first road belongs;

[0151] According to the categories to which the first roads belong, a state set corresponding to each category is generated; the state set includes at least one first position sequence of the first roads belonging to the same category;

[0152] Road matching is performed respectively with the state sets of each category according to the second position sequence to generate sub-matching results corresponding to the corresponding category; and the sub-matching results are included in the second matching results.

[0153] In some optional implementations, the matching module 503 determines the first road and the second road with matching positions according to the first matching result and the second matching result, including:

[0154] In a case where the sub-matching result corresponds to a target category, determining a partial matching result in the first matching result corresponding to a first road belonging to the target category;

[0155] A first road and a second road with matching positions are determined according to the sub-matching result and the partial matching result.

[0156] In some optional implementations, the matching module 503 determines the first road and the second road with matching positions according to the first matching result and the second matching result, including:

[0157] Determining a first road and a second road having a valid matching relationship according to an intersection of the first matching result and the second matching result;

[0158] Determining a position matching degree between a first road and a second road having a valid matching relationship;

[0159] When the position matching degree satisfies the matching condition, it is determined that the first road and the second road having a valid matching relationship are positionally matched.

[0160] In some optional implementations, the matching module 503 determines the position matching degree between the first road and the second road having a valid matching relationship, including:

[0161] Determine a first starting point and a first end point of a first pending road, and a second starting point and a second end point of a second pending road; the first pending road and the second pending road are respectively a first road and a second road having a valid matching relationship;

[0162] In the case where both the second starting point and the second end point are located between the first starting point and the first end point, setting the position matching degree between the first undetermined road and the second undetermined road to a position matching degree that satisfies a matching condition;

[0163] In the case where one of the second starting point and the second end point is located between the first starting point and the first end point, but the other of the second starting point and the second end point is not located between the first starting point and the first end point, if there is a third undetermined road that has a valid matching relationship with the second undetermined road and has the same road attributes as the first undetermined road, then determining whether the other of the second starting point and the second end point is located between the starting point and the end point of the third undetermined road;

[0164] In the case where the other of the second starting point and the second end point is located between the starting point and the end point of the third pending road, the position matching degree between the first pending road and the second pending road is set to a position matching degree that satisfies the matching conditions, and the position matching degree between the third pending road and the second pending road is set to a position matching degree that satisfies the matching conditions.

[0165] In some optional implementations, the acquisition module 501 is further used to: acquire other road data; the other road data includes road attributes of at least one road;

[0166] The processing module 504 is further configured to fuse the road attributes in the open map data according to the road attributes in the other road data, and use the fused road attributes as the road attributes of each first road in the open map data.

[0167] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0168] The map data processing device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, including a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0169] The embodiment of the present invention also provides a computer device having the above Figure 5 The map data processing device shown.

[0170] See also Figure 6 , Figure 6is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0171] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0172] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0173] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0174] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0175] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0176] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0177] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0178] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations should all be included in the protection scope of the present invention.

Claims

1. A method for processing map data, characterized in that: The method comprises: Obtaining open map data and unprocessed map data to be assigned road attributes; Extracting the location information and road attributes of each first road from the open map data, and extracting the location information of each second road from the map data to be processed; Determine a first road and a second road with matching positions according to the position information of the first road and the position information of the second road; The road attributes of the second road are assigned values ​​according to the road attributes of the first road that matches the second road.

2. The method according to claim 1, characterized in that The determining the first road and the second road with matching positions according to the position information of the first road and the position information of the second road comprises: generating a first position sequence corresponding to the first road according to the position information of the first road, and generating a second position sequence corresponding to the second road according to the position information of the second road; Using the first position sequence as an observation sequence and the second position sequence as a state sequence, performing road matching to generate a first matching result; the first matching result includes a matching relationship between the first road and at least one of the second roads; Using the first position sequence as a state sequence and the second position sequence as an observation sequence, performing road matching to generate a second matching result; the second matching result includes a matching relationship between the second road and at least one of the first roads; A first road and a second road whose positions match are determined according to the first matching result and the second matching result.

3. The method according to claim 2, characterized in that The step of using the first position sequence as a state sequence and the second position sequence as an observation sequence to perform road matching and generate a second matching result includes: Classify the first road according to its road attributes to determine the category to which the first road belongs; According to the categories to which the first roads belong, a state set corresponding to each category is generated; the state set includes at least one first position sequence of the first roads belonging to the same category; Road matching is performed respectively with the state sets of each category according to the second position sequence to generate sub-matching results corresponding to the corresponding category; and the sub-matching results are included in the second matching results.

4. The method according to claim 3, characterized in that The determining, according to the first matching result and the second matching result, of the first road and the second road whose positions are matched comprises: In a case where the sub-matching result corresponds to a target category, determining a partial matching result in the first matching result corresponding to a first road belonging to the target category; A first road and a second road with matching positions are determined according to the sub-matching result and the partial matching result.

5. The method according to any one of claims 2 to 4, characterized in that The determining, according to the first matching result and the second matching result, of the first road and the second road whose positions are matched comprises: Determining a first road and a second road having a valid matching relationship according to an intersection of the first matching result and the second matching result; Determining a position matching degree between a first road and a second road having a valid matching relationship; When the position matching degree satisfies the matching condition, it is determined that the first road and the second road having a valid matching relationship are positionally matched.

6. The method according to claim 5, characterized in that The determining of the position matching degree between the first road and the second road having a valid matching relationship includes: Determine a first starting point and a first end point of a first pending road, and a second starting point and a second end point of a second pending road; the first pending road and the second pending road are respectively a first road and a second road having a valid matching relationship; In the case where both the second starting point and the second end point are located between the first starting point and the first end point, setting the position matching degree between the first undetermined road and the second undetermined road to a position matching degree that satisfies a matching condition; In the case where one of the second starting point and the second end point is located between the first starting point and the first end point, but the other of the second starting point and the second end point is not located between the first starting point and the first end point, if there is a third undetermined road that has a valid matching relationship with the second undetermined road and has the same road attributes as the first undetermined road, then determining whether the other of the second starting point and the second end point is located between the starting point and the end point of the third undetermined road; In the case where the other of the second starting point and the second end point is located between the starting point and the end point of the third pending road, the position matching degree between the first pending road and the second pending road is set to a position matching degree that satisfies the matching conditions, and the position matching degree between the third pending road and the second pending road is set to a position matching degree that satisfies the matching conditions.

7. The method according to claim 1, characterized in that Also includes: Acquire other road data; the other road data includes road attributes of at least one road; The road attributes in the open map data are merged according to the road attributes in the other road data, and the merged road attributes are used as the road attributes of each first road in the open map data.

8. A map data processing device, characterized in that: The device comprises: An acquisition module, used for acquiring open map data and unprocessed map data to be assigned road attributes; An information extraction module, used to extract the location information and road attributes of each first road from the open map data, and to extract the location information of each second road from the map data to be processed; A matching module, configured to determine a first road and a second road whose positions match according to the position information of the first road and the position information of the second road; The processing module is used to assign a road attribute to the second road according to the road attribute of the first road matching the second road.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the map data processing method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the map data processing method according to any one of claims 1 to 7.

Images