Beidou positioning data correction method and correction system

Abstract

The present invention provides a Beidou positioning data correction method and correction system, the method comprising: constructing a neural tree structure based on a high-precision road network line, the neural tree structure being a multi-level tree structure, and storing the high-precision road network line in the neural tree structure; searching for the best matching road network line of the current Beidou positioning data in the neural tree structure; if the current Beidou positioning data needs to be corrected, the positioning data after correction is calculated by plane coordinates according to the best matching line, the current Beidou positioning data and the previous Beidou positioning data. The present invention utilizes a neural network structure to store high-precision road network data, improves data query efficiency, and adopts multi-threaded parallel search and correction calculation, which can solve the problem of real-time positioning correction.

Description

Technical Field

[0001] The present invention relates to the field of positioning data correction, and more specifically, to a Beidou positioning data correction method and correction system. Background Art

[0002] During the driving process of a vehicle, the driving route usually deviates, so it needs to be corrected, that is, the positioning data of the vehicle needs to be corrected.

[0003] At present, the common correction method is, for example, the patent with application number CN201810675702.8, named a grid-based Beidou GPS vehicle trajectory management system and method. Through each grid information after average quantization division and grid preprocessing, and with the grid center coordinates as the index, a hash table of the intermediate data of the road section is generated, and the trajectory data is finally corrected through related process processing.

[0004] The main disadvantages of using this method for correction are:

[0005] 1. Low sample data accuracy. Directly using the road network data of a certain area on Amap, the data stored itself has low accuracy. In order to achieve the matching speed, grid hash is used to perform full matching.

[0006] 2. Slow matching speed. Although the overall dilution is used to form a grid hash, the overall matching mode is full, and each point needs to be compared in turn, and the query efficiency is O(n). Summary of the invention

[0007] The present invention aims at the technical problems existing in the prior art and provides a Beidou positioning data correction method and correction system.

[0008] According to a first aspect of the present invention, a Beidou positioning data correction method is provided, comprising:

[0009] Based on the high-precision road network, a neural tree structure is constructed, wherein the neural tree structure is a multi-level tree structure, and the high-precision road network is stored in the neural tree structure;

[0010] Searching for the best matching network route for the current Beidou positioning data in the neural tree structure;

[0011] If the current Beidou positioning data needs to be corrected, the corrected positioning data is calculated using a plane coordinate method according to the optimal matching route, the current Beidou positioning data and the previous Beidou positioning data.

[0012] Based on the above technical solution, the present invention can also make the following improvements.

[0013] Optionally, constructing a neural tree structure based on high-precision road network data includes:

[0014] A neural tree structure is constructed according to the latitude and longitude of each data point in the high-precision road network in ascending or descending order.

[0015] Optionally, constructing a neural tree structure in ascending or descending order according to the longitude and latitude of each data point in the high-precision road network includes:

[0016] For any data point in the high-precision road network, let the longitude of any data point be x and the latitude be y, where x and y include multiple bits, x = [x1x2x3 ... xn], y = [y1y2y3 ... ym];

[0017] Based on the longitude x of any data point, a first neural tree structure is constructed, wherein the root node of the first neural tree structure is x1, the first bit is used as a parent node, and the second bit is used as a child node;

[0018] as well as,

[0019] Based on the latitude y of any data point, a second neural tree structure is constructed, wherein the root node of the second neural tree structure is y1, the first one is used as the parent node, and the second one is used as the child node.

[0020] Optionally, searching for optimal matching road network data of current Beidou positioning data in the neural tree structure includes:

[0021] According to a breadth-first or depth-first search algorithm, based on the current Beidou positioning data, searching for matching road network routes in the neural tree structure;

[0022] If a matching road network route is found, the route is used as the optimal matching road network route for the current Beidou positioning data;

[0023] If multiple matching road network routes are searched, the distance between the current Beidou positioning data and each matching road network route is calculated, and the road network route with the shortest distance is used as the optimal road network route for the current Beidou positioning data.

[0024] Optionally, searching for a matching road network route in the neural tree structure based on current Beidou positioning data according to a breadth-first or depth-first search algorithm includes:

[0025] Get the longitude and latitude of the current Beidou positioning data;

[0026] Based on the longitude of the current Beidou positioning data, searching for matching longitude data in the first neural tree structure;

[0027] Based on the latitude of the current Beidou positioning data, searching for matching latitude data in the second neural tree structure;

[0028] According to the search and matching accuracy data and latitude data, the road network route that the current Beidou positioning data searches and matches is obtained.

[0029] Optionally, the road network route with the shortest distance is used as the optimal road network route for the current Beidou positioning data, and further includes:

[0030] If there are multiple road network routes with the shortest distance, the best matching road network route of the previous Beidou positioning data will be used as the best road network route of the current Beidou positioning data.

[0031] Optionally, whether the current Beidou positioning data needs to be corrected is determined in the following manner:

[0032] If the distance between the current Beidou positioning data and its optimal matching road network line is greater than the set distance threshold, the current Beidou positioning data needs to be corrected; otherwise, the current Beidou positioning data does not need to be corrected.

[0033] Optionally, the calculating the corrected positioning data by plane coordinate method according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data includes:

[0034] According to the average driving speed and driving time from the previous Beidou positioning data to the current Beidou positioning data and the azimuth of the current Beidou positioning data, the positioning data after correction of the current Beidou positioning data is calculated by plane coordinate method, and the corrected positioning data is located on the optimal matching road network route.

[0035] Optionally, the calculation of the positioning data after the current Beidou positioning data is corrected by plane coordinates according to the average driving speed and driving time from the previous Beidou positioning data to the current Beidou positioning data and the azimuth of the current Beidou positioning data includes:

[0036]

[0037] Among them, G i (lat, lon) represents the positioning data after the current Beidou positioning data G1′(lat, lon) is corrected, P j (lat, lon) represents the current Beidou positioning data G i ′(lat, lon) belongs to the road network line, Indicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i Average driving speed of ′(lat, lon), Δt iIndicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i ′(lat, lon) travel time, A i Indicates the current Beidou positioning data G i ′(lat, lon) is the azimuth.

[0038] According to a second aspect of the present invention, a Beidou positioning data correction system is provided, comprising:

[0039] A construction module, used to construct a neural tree structure based on the high-precision road network routes, wherein the neural tree structure is a multi-level tree structure, and the high-precision road network routes are stored in the neural tree structure;

[0040] A search module, used to search the neural tree structure for the best matching network route of the current Beidou positioning data;

[0041] The correction module is used to calculate the corrected positioning data by plane coordinate method according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data if the current Beidou positioning data needs correction.

[0042] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the processor is used to implement the steps of a Beidou positioning data correction method when executing a computer management program stored in the memory.

[0043] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the Beidou positioning data correction method are implemented.

[0044] The present invention provides a Beidou positioning data correction method and correction system, which utilize a neural network structure to store high-precision road network data, thereby improving data query efficiency, and adopts multi-threaded parallel search and correction calculation to solve the problem of real-time positioning correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flow chart of a Beidou positioning data correction method provided by the present invention;

[0046] Figure 2 A schematic diagram of the road network data for a high-precision map;

[0047] Figure 3 Schematic diagram of neural tree structure;

[0048] Figure 4 Schematic diagram for neural tree search;

[0049] Figure 5 This is a schematic diagram of correcting the current Beidou positioning data;

[0050] Figure 6 A schematic diagram of the structure of a Beidou positioning data correction system provided by the present invention;

[0051] Figure 7 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0052] Figure 8 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0053] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0054] Embodiment 1

[0055] A Beidou positioning data correction method, see Figure 1 , the correction method mainly includes the following steps:

[0056] S1, based on the high-precision road network routes, construct a neural tree structure, the neural tree structure is a multi-level tree structure, and the high-precision road network routes are stored in the neural tree structure.

[0057] It can be understood that the data used by the embodiment of the present invention to correct the Beidou positioning data is high-precision road network data, wherein the data source is high-precision road network data collected by high-precision equipment. The high-precision road network data is cleaned and processed by tools to form professional and unified GIS data, and the road network points are formed by data import to form road network lines L j , j∈N, N is the number of road network lines, and the high-precision map road network line data diagram can be seen in Figure 2 shown.

[0058] Based on the acquired high-precision road network data, it is stored in a neural tree structure model. As an embodiment, based on the high-precision road network line data, a neural tree structure is constructed, including: constructing a neural tree structure in ascending or descending order according to the longitude and latitude of each data point in the high-precision road network line.

[0059] Among them, a neural tree structure is constructed according to the longitude and latitude of each data point in the high-precision road network in an ascending or descending mode, including: for any data point in the high-precision road network, the longitude of any data point is x, and the latitude is y, wherein x, y include multiple bits, x = [x1x2x3...xn], y = [y1y2y3...ym]; based on the longitude x of any data point, a first neural tree structure is constructed, the root node of the first neural tree structure is x1, the first bit is used as the parent node, and the last bit is used as the child node; and based on the latitude y of any data point, a second neural tree structure is constructed, the root node of the second neural tree structure is y1, the first bit is used as the parent node, and the last bit is used as the child node.

[0060] It can be understood that for high-precision road network data points, their coordinates include longitude coordinates and latitude coordinates. For each data point, its longitude can be expressed as x and its latitude can be expressed as y, where x and y include multiple bits, x = [x1x2x3...xn], y = [y1y2y3...ym], and the data coordinate form can be found in Table 1.

[0061] Table 1 High-precision road network data

[0062]

[0063] For all high-precision road network data points, a neural tree structure is constructed based on longitude (called the first neural tree structure), and a neural tree structure is constructed based on latitude (called the second neural tree structure). For specific construction methods, see Figure 3 The neural tree structure is as follows. For example, the longitude of a high-precision data point is in the form of 112.491322144001860, where 112 is the root node of the neural tree, and the other bits are the previous bit as the parent node and the next bit as the child node. Finally, the first neural tree structure is constructed. For nodes at the same level, the longitudes of different data points are stored in the nodes of the neural tree in ascending order from left to right or descending order from left to right. For the latitude of high-precision road network data, the same method is used to construct the second neural tree structure.

[0064] S2, searching the neural tree structure for the optimal matching network route of the current Beidou positioning data.

[0065] It is understandable that for the real-time Beidou positioning data of vehicle driving, it is first necessary to find out in the neural tree structure which road network route the Beidou positioning data belongs to, that is, the optimal matching road network route for the current Beidou positioning data.

[0066] When searching specifically, the optimal matching road network route data of the current Beidou positioning data is searched in the neural tree structure, including: searching for matching road network routes in the neural tree structure based on the current Beidou positioning data according to a breadth-first or depth-first search algorithm; if a matching road network route is found, the route is used as the optimal matching road network route for the current Beidou positioning data; if multiple matching road network routes are found, the distance between the current Beidou positioning data and each matching road network route is calculated, and the road network route with the smallest distance is used as the optimal road network route for the current Beidou positioning data.

[0067] It is understandable that when searching for matching road network data in the neural tree structure based on the current Beidou positioning data, the search can be performed according to a certain search algorithm, for example, the search can be performed according to a breadth-first search algorithm or a depth-first search algorithm.

[0068] Specifically, according to the breadth-first or depth-first search algorithm, based on the current Beidou positioning data, a matching road network route is searched in the neural tree structure, including: obtaining the longitude and latitude of the current Beidou positioning data; based on the longitude of the current Beidou positioning data, searching for matching longitude data in the first neural tree structure; based on the latitude of the current Beidou positioning data, searching for matching latitude data in the second neural tree structure; and obtaining the matching road network route for the current Beidou positioning data based on the searched matching accuracy data and latitude data.

[0069] It can be understood that the current Beidou positioning data of the vehicle is obtained, including its longitude data and latitude data, and the matching longitude data is searched in the first neural tree structure based on the longitude data; and the matching latitude data is searched in the second neural tree structure based on the latitude data. According to the matching longitude data and matching latitude data found, the road network line data matching the current Beidou positioning data is obtained. See Figure 4 , which is the data search process. When the current Beidou positioning data of multiple vehicles needs to be searched at the same time, a multi-threaded and multi-process parallel search method can be used to improve the efficiency of data search.

[0070] Among them, if the current Beidou positioning data can only find one matching road network route in the neural tree structure, then this road network route is the optimal matching road network route for the current Beidou positioning data.

[0071] If the current Beidou positioning data finds multiple matching road network routes in the neural tree structure, the distance between the current Beidou positioning data and each matching road network route is calculated. This can be understood as calculating the vertical distance from the current Beidou positioning data to each matching road network route, finding the road network route with the shortest distance, and taking the road network route with the shortest distance as the optimal matching road network route for the current Beidou positioning data.

[0072] It should be noted that if there are multiple road network routes with the shortest distance, that is, the distance from the current Beidou positioning data to multiple road network routes is equal and the shortest, then at this time, you can refer to the previous Beidou positioning data and take the optimal matching road network route of the previous Beidou positioning data as the optimal matching road network route of the current Beidou positioning data.

[0073] S3: If the current Beidou positioning data needs to be corrected, the corrected positioning data is calculated by plane coordinate method according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data.

[0074] It can be understood that after the optimal matching road network line of the current Beidou positioning data is found in the neural tree structure, it is determined whether the current Beidou positioning data needs to be corrected. As an embodiment, whether the current Beidou positioning data needs to be corrected is determined in the following way: if the distance between the current Beidou positioning data and its optimal matching road network line is greater than the set distance threshold, for example, the vertical distance between the current Beidou positioning data and its optimal matching road network line is greater than 20m, then the current Beidou positioning data needs to be corrected; if it is less than 20m, then within the error range, the current Beidou positioning data does not need to be corrected.

[0075] If the current Beidou positioning data needs to be corrected, the corrected positioning data is calculated by plane coordinate method according to the optimal matching route, the current Beidou positioning data and the previous Beidou positioning data, including: according to the average driving speed and driving time from the previous Beidou positioning data to the current Beidou positioning data and the azimuth of the current Beidou positioning data, the corrected positioning data of the current Beidou positioning data is calculated by plane coordinate method, and the corrected positioning data is located on the optimal matching road network route.

[0076] It is understandable that, see Figure 5 , for the current Beidou positioning data G i ', if the current Beidou positioning data needs to be corrected, then according to the previous Beidou positioning data G i-1 ' and the current Beidou positioning data G i 'The average speed of the vehicle, the previous Beidou positioning data G i-1 ' and the current Beidou positioning data G i 'Vehicle travel time Δt i , and the current Beidou positioning data G i 'Azimuth, calculate the current Beidou positioning data G i 'Positioning data after correction G i , that is, the current Beidou positioning data G i 'Correct to G i , complete the correction processing of the current Beidou positioning data.

[0077] Specifically, the corrected positioning data G can be calculated by using the average speed and azimuth angle of the previous unit time in the form of plane coordinates. i , which can be expressed as follows:

[0078]

[0079] Among them, G i (lat, lon) represents the current Beidou positioning data G i ′(lat, lon) Positioning data after correction, P j (lat, lon) represents the current Beidou positioning data G i ′(lat, lon) belongs to the road network line, Indicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i Average driving speed of ′(lat, lon), Δt i Indicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i ′(lat, lon) travel time, A i Indicates the current Beidou positioning data G i ′(lat, lon) is the azimuth.

[0080] Embodiment 2

[0081] A Beidou positioning data correction system, see Figure 6 The correction system includes a construction module 61, a search module 62 and a correction module 63, wherein:

[0082] A construction module 61 is used to construct a neural tree structure based on the high-precision road network route, wherein the neural tree structure is a multi-level tree structure, and the high-precision road network route is stored in the neural tree structure;

[0083] A search module 62, used to search the neural tree structure for the best matching network route of the current Beidou positioning data;

[0084] The correction module 63 is used to calculate the corrected positioning data in a plane coordinate manner according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data if the current Beidou positioning data needs correction.

[0085] It can be understood that the Beidou positioning data correction system provided by the present invention corresponds to the Beidou positioning data correction method provided by the aforementioned embodiments. The relevant technical features of the Beidou positioning data correction system can refer to the relevant technical features of the Beidou positioning data correction method, which will not be repeated here.

[0086] Embodiment 3

[0087] See also Figure 7 , Figure 7 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 7 As shown, an embodiment of the present invention provides an electronic device 700, including a memory 710, a processor 720, and a computer program 711 stored in the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 711, the steps of the Beidou positioning data correction method of embodiment 1 are implemented.

[0088] Embodiment 4

[0089] See also Figure 8 , Figure 8 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 8 As shown, this embodiment provides a computer-readable storage medium 800 on which a computer program 811 is stored. When the computer program 811 is executed by a processor, the steps of the Beidou positioning data correction method of embodiment 1 are implemented.

[0090] The Beidou positioning data correction method and correction system provided by the embodiment of the present invention have the following advantages:

[0091] (1) The use of neural network structures to store high-precision road network data improves data query efficiency, and the use of multi-threaded parallel search and correction calculations can solve the problem of real-time positioning and correction;

[0092] (2) During the data search process, when multiple matching road network routes are found, the optimal matching road network route is obtained through a certain method, thereby improving the accuracy of the correction data basis;

[0093] (3) Data correction is performed based on high-precision road network data collected by high-precision equipment. Due to the high accuracy of high-precision road network data, the data correction accuracy of the present invention is significantly improved, and after correction, there is a good improvement in turning jump points.

[0094] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0100] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A Beidou positioning data correction method, characterized in that: include: Based on the high-precision road network, a neural tree structure is constructed, wherein the neural tree structure is a multi-level tree structure, and the high-precision road network is stored in the neural tree structure; Searching for the best matching network route for the current Beidou positioning data in the neural tree structure; If the current Beidou positioning data needs to be corrected, the corrected positioning data is calculated by plane coordinate method according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data; The neural tree structure is constructed based on high-precision road network data, including: Construct a neural tree structure in ascending or descending order according to the longitude and latitude of each data point in the high-precision road network; The method of constructing a neural tree structure in ascending or descending order according to the longitude and latitude of each data point in the high-precision road network includes: For any data point in the high-precision road network, let the longitude of any data point be x and the latitude be y, where x and y include multiple bits, x = [x1x2x3 ... xn], y = [y1y2y3 ... ym]; Based on the longitude x of any data point, a first neural tree structure is constructed, wherein the root node of the first neural tree structure is x1, the first bit is used as a parent node, and the second bit is used as a child node; as well as, Based on the latitude y of any data point, a second neural tree structure is constructed, wherein the root node of the second neural tree structure is y1, the first one is used as a parent node, and the second one is used as a child node; The calculating the corrected positioning data by plane coordinate method according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data includes: According to the average driving speed and driving time from the previous Beidou positioning data to the current Beidou positioning data and the azimuth of the current Beidou positioning data, the positioning data after the correction of the current Beidou positioning data is calculated by plane coordinates, and the positioning data after the correction is located on the optimal matching road network route; The method of calculating the positioning data after the correction of the current Beidou positioning data by plane coordinates according to the average driving speed and driving time from the previous Beidou positioning data to the current Beidou positioning data and the azimuth of the current Beidou positioning data includes: Among them, G i (lat, lon) represents the current Beidou positioning data G i ′(lat, lon) Positioning data after correction, P j (lat, lon) represents the current Beidou positioning data G i ′(lat, lon) belongs to the road network line, Indicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i Average driving speed of ′(lat, lon), Δt i Indicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i ′(lat, lon) travel time, A i Indicates the current Beidou positioning data G i ′(lat, lon) is the azimuth.

2. The Beidou positioning data correction method according to claim 1, characterized in that: The step of searching the neural tree structure for optimal matching road network data of the current Beidou positioning data includes: According to a breadth-first or depth-first search algorithm, based on the current Beidou positioning data, searching for matching road network routes in the neural tree structure; If a matching road network route is found, the road network route is used as the optimal matching road network route for the current Beidou positioning data; If multiple matching road network routes are searched, the distance between the current Beidou positioning data and each matching road network route is calculated, and the road network route with the shortest distance is used as the optimal road network route for the current Beidou positioning data.

3. The Beidou positioning data correction method according to claim 2, characterized in that: The method of searching for a matching road network route in the neural tree structure based on the current Beidou positioning data according to a breadth-first or depth-first search algorithm includes: Get the longitude and latitude of the current Beidou positioning data; Based on the longitude of the current Beidou positioning data, searching for matching longitude data in the first neural tree structure; Based on the latitude of the current Beidou positioning data, searching for matching latitude data in the second neural tree structure; According to the search and matching accuracy data and latitude data, the road network route that the current Beidou positioning data searches and matches is obtained.

4. The Beidou positioning data correction method according to claim 2, characterized in that: The road network with the shortest distance is used as the optimal road network for the current Beidou positioning data, and also includes: If there are multiple road network routes with the shortest distance, the best matching road network route of the previous Beidou positioning data will be used as the best road network route of the current Beidou positioning data.

5. The Beidou positioning data correction method according to claim 1, characterized in that: Determine whether the current Beidou positioning data needs to be corrected by the following method: If the distance between the current Beidou positioning data and its optimal matching road network line is greater than the set distance threshold, the current Beidou positioning data needs to be corrected; otherwise, the current Beidou positioning data does not need to be corrected.

6. A Beidou positioning data correction system, characterized in that: include: A construction module, used to construct a neural tree structure based on the high-precision road network routes, wherein the neural tree structure is a multi-level tree structure, and the high-precision road network routes are stored in the neural tree structure; A search module, used to search the neural tree structure for the best matching network route of the current Beidou positioning data; A correction module, for calculating the corrected positioning data by plane coordinates according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data if the current Beidou positioning data needs correction; The neural tree structure is constructed based on high-precision road network data, including: Construct a neural tree structure in ascending or descending order according to the longitude and latitude of each data point in the high-precision road network; The method of constructing a neural tree structure in ascending or descending order according to the longitude and latitude of each data point in the high-precision road network includes: For any data point in the high-precision road network, let the longitude of any data point be x and the latitude be y, where x and y include multiple bits, x = [x1x2x3 ... xn], y = [y1y2y3 ... ym]; Based on the longitude x of any data point, a first neural tree structure is constructed, wherein the root node of the first neural tree structure is x1, the first bit is used as a parent node, and the second bit is used as a child node; as well as, Based on the latitude y of any data point, a second neural tree structure is constructed, wherein the root node of the second neural tree structure is y1, the first one is used as a parent node, and the second one is used as a child node; The calculating the corrected positioning data by plane coordinate method according to the optimal matching line, the current Beidou positioning data and the previous Beidou positioning data includes: According to the average driving speed and driving time from the previous Beidou positioning data to the current Beidou positioning data and the azimuth of the current Beidou positioning data, the positioning data after the correction of the current Beidou positioning data is calculated by plane coordinates, and the positioning data after the correction is located on the optimal matching road network route; The method of calculating the positioning data after the correction of the current Beidou positioning data by plane coordinates according to the average driving speed and driving time from the previous Beidou positioning data to the current Beidou positioning data and the azimuth of the current Beidou positioning data includes: Among them, G i (lat, lon) represents the current Beidou positioning data G i ′(lat, lon) Positioning data after correction, P j (lat, lon) represents the current Beidou positioning data G i ′(lat, lon) belongs to the road network line, Indicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i Average driving speed of ′(lat, lon), Δt i Indicates the previous Beidou positioning data G i-1 ′(lat, lon) to the current Beidou positioning data G i ′(lat, lon) travel time, A i Indicates the current Beidou positioning data G i ′(lat, lon) is the azimuth.

Images