Railway whole-line data integrated management system
By constructing railway node layout diagrams and data splicing technology, the problem of inconsistent coordinate systems for railways is solved, the data acquisition speed and accuracy are improved, and the requirements of one map on the whole road and the accuracy of overlapping line area data are realized.
Patent Information
- Application Number
- CN202411024903.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-22
AI Technical Summary
The coordinate systems of railway land use in various bureaus are unclear and inconsistent, resulting in a large number of maps, which cannot form a map of the whole road. There are problems with the data accuracy of railway lines in the map, especially when overlapping line areas, which cannot meet the entire road. The demand for a picture reduces the accuracy of railway data.
By constructing a railway node layout diagram, determining the railway node location and its data collection point, generating multiple data blocks, and splicing different data categories in the same data block to verify the accuracy of the data group to meet the needs of a map on the whole road. Improves data accuracy in overlapping line areas.
It improves the speed and accuracy of railway data collection, ensures the accuracy of the entire road data, and meets the needs of a map on the entire road.
Smart Images

Figure CN119006499A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of railway data management, and in particular to a comprehensive railway line data management system. Background Art
[0002] The railway land coordinate systems of various railway bureaus are unclear and non-uniform, resulting in a large number of maps, making it impossible to form a single map for the entire railway and difficult to establish business associations. There are problems with the data accuracy of the railway lines in the map, and a large amount of local coordinate system data cannot be accurately matched through algorithms and requires manual correction, so the timeliness of the data cannot be guaranteed. When it comes to overlapping line areas, there will be large deviations, which cannot meet the needs of a single map for the entire railway and greatly reduces the accuracy of the railway data. Summary of the invention
[0003] In order to solve the above technical problems, the present application provides a comprehensive management system for railway data of the entire line. By constructing a railway node layout diagram, the railway node locations and the corresponding data collection points are determined, the correlation between the railway nodes and the data collected by the data collection points is ensured, the data collection speed and accuracy are improved, and the data of the same railway node is generated into multiple data blocks according to the type of coordinate system. Different data categories in the same data block are spliced to obtain a data group and verify the accuracy of the data group, which meets the demand for a single map of the entire road and improves the accuracy of the data in the overlapping line area.
[0004] In some embodiments of the present application, a comprehensive railway line data management system is provided, including:
[0005] A construction module is used to construct a railway node layout diagram for the entire railway line structure, wherein the railway node layout diagram includes a plurality of data collection nodes and a plurality of railway nodes, and the railway nodes are interconnected;
[0006] A processing module, used for acquiring first data of a data collection node, grouping and splicing the first data to obtain a plurality of data groups, and associating the data groups with railway nodes;
[0007] The management module is used to generate an application evaluation value of the current data group according to the data group associated with the railway node and the actual data group, and determine whether to generate a correction instruction for the corresponding data group according to the application evaluation value.
[0008] In some embodiments of the present application, a railway node layout diagram is constructed for the entire railway line structure, including:
[0009] Obtain all GIS images of the railway, perform contour interception on all GIS images, and generate overlapping contour areas and railway foundation areas;
[0010] According to the preset node screening rules, the overlapping contour area is screened and the first railway node is determined, and the second railway node is determined according to the railway foundation area;
[0011] A railway node layout diagram is constructed according to the relative positions of the coincident contour area and the railway foundation area on the GIS image and the corresponding relationship between the first railway node and the second railway node and the coincident contour area and the railway foundation area.
[0012] In some embodiments of the present application, screening the overlapping contour area and determining the first railway node according to a preset node screening rule includes:
[0013] The area of the overlapping contour region is obtained, and the number of characteristic nodes corresponding to the overlapping contour region is set according to the average number of nodes in the overlapping contour region involved in all GIS images;
[0014] According to the number of characteristic nodes and the preset line distance principle, the overlapping contour area is divided to obtain multiple sub-areas;
[0015] Determine the first central node in each sub-region, analyze each first central node with the remaining characteristic nodes in the same sub-region, determine a node subset based on the first central node, and determine whether the first central node needs to be replaced according to the node subset;
[0016] If not necessary, the corresponding first central node is set as the first railway node. If necessary, the point in the node subset that satisfies the principle of being closest to each characteristic node in the same sub-region is set as the first central node.
[0017] In some embodiments of the present application, obtaining first data of a data collection node includes:
[0018] Determining a first distance of each first railway node according to the regional scope of each first railway node;
[0019] According to the first position coordinate of the first railway node as the origin and the first distance as the radius, the first data collection nodes belonging to the current first railway node are screened out, and the second position coordinate corresponding to each first data collection node is obtained;
[0020] Calculating a relative distance between the first position coordinate and the second position coordinate, and determining a correlation between the current first data collection node and the corresponding first railway node based on a ratio of the relative distance to the first distance;
[0021] The data of the first data collection node whose correlation is greater than a preset correlation threshold is obtained, and the data is preprocessed and standardized to generate first data.
[0022] In some embodiments of the present application, preprocessing and standardizing the data to generate first data includes:
[0023] Preprocessing the data, including unification, removal of outliers, filling of missing values, and data cleaning;
[0024] The preprocessed data is standardized, wherein the standardization includes classifying the data according to data categories to obtain multi-category data, and standardizing the data of the same category;
[0025]
[0026] Among them, x'( i ) is the i-th data x( i ), where n is the number of data in the same data category;
[0027] The first data is generated according to a plurality of standardized data of different data categories.
[0028] In some embodiments of the present application, the first data is grouped and concatenated to obtain multiple data groups, including:
[0029] Dividing the first data into a plurality of data blocks according to the type of the coordinate system of the first data;
[0030] Extract characteristic factors from the first data of the same data category according to the correlation coefficient set to obtain characteristic factors corresponding to multiple data categories;
[0031] The characteristic factor is:
[0032] ∝xM T =eM' (i)
[0033] Among them, xM T is the characteristic factor in the Mth data category, eM' (i) is the correlation coefficient corresponding to the i-th standardized data in the M-th data category, ∝ is a screening formula, wherein the screening formula is used to screen out the standardized data whose correlation coefficient is greater than a preset correlation coefficient threshold;
[0034] The characteristic factors of different data categories in the same data block are spliced to generate multiple initial data groups;
[0035] Generate the splicing credibility of the initial data group according to the correlation coefficient of the characteristic factors involved in the initial data group;
[0036] An initial data group whose splicing credibility is greater than a preset credibility threshold is set as a data group, and the data group is associated with the first railway node.
[0037] In some embodiments of the present application, generating an application evaluation value of the current data group includes:
[0038] Generate a credibility mean value according to the splicing credibility of the data group corresponding to the first railway node, and set the number of collection groups of the actual data group according to the credibility mean value;
[0039] Generate an application evaluation value A of the current data group according to the data deviation value of the same data category between the actual data group and the corresponding data group, the correlation coefficient corresponding to the data category, and the splicing credibility of the data group;
[0040]
[0041] Wherein, h is the data category in the actual data group and the corresponding data group, S1i is the i-th data category in the actual data group, S2i is the i-th data category in the data group, S1i-S2i is the data deviation value of the same data category in the actual data group and the corresponding data group, e' (i) is the correlation coefficient corresponding to the i-th data category, where i = 1, 2, …h.
[0042] In some embodiments of the present application, judging whether to generate a correction instruction for a corresponding data group according to the application evaluation value includes:
[0043] Presetting a first preset application evaluation value threshold and a second preset application evaluation value threshold, wherein the first preset application evaluation value threshold is smaller than the second preset application evaluation value threshold;
[0044] When the application evaluation value is less than the first preset application evaluation value threshold, a secondary correction instruction is generated for the current data group, wherein the secondary correction instruction is to redetermine the first railway node associated with the current data group, reacquire the first data of the data acquisition node, and group and splice the first data;
[0045] When the application evaluation value is between the first preset application evaluation value threshold and the second preset application evaluation value threshold, a first-level correction instruction is generated for the current data group, wherein the first-level correction instruction is to fine-tune the splicing factor of the current data group;
[0046] When the application evaluation value is greater than the second preset application evaluation value threshold, no correction instruction is generated.
[0047] In some embodiments of the present application, the number of collection groups of the actual data group is set according to the credibility mean, including:
[0048] Presetting a first preset credibility mean interval, a second preset credibility mean interval, a third preset credibility mean interval and a fourth preset credibility mean interval;
[0049] When the credibility mean is within the first preset credibility mean interval, the number of collection groups of the actual data group is set to be the fourth preset number of collection groups;
[0050] When the credibility mean is within the second preset credibility mean interval, the number of collection groups of the actual data group is set to be the third preset number of collection groups;
[0051] When the credibility mean is within the third preset credibility mean interval, the number of collection groups of the actual data group is set to the second preset number of collection groups;
[0052] When the credibility mean is in the fourth preset credibility mean interval, the number of collection groups of the actual data groups is set to the first preset number of collection groups.
[0053] Compared with the prior art, the railway line data integrated management system of the embodiment of the present application has the following beneficial effects:
[0054] By constructing a railway node layout diagram, determining the location of railway nodes and the corresponding data collection points, ensuring the correlation of data collected by railway nodes and data collection points, improving data collection speed and accuracy, generating multiple data blocks for the data of the same railway node according to the type of coordinate system, and splicing different data categories in the same data block to obtain data groups and verify the accuracy of the data groups, the demand for one map for the entire railway is met and the accuracy of data in overlapping line areas is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 It is a schematic diagram of a comprehensive railway line data management system in the preferred embodiment of the present application. DETAILED DESCRIPTION
[0056] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.
[0057] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.
[0058] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.
[0059] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0060] like Figure 1 As shown, a railway line data integrated management system according to a preferred embodiment of the present application includes:
[0061] A construction module is used to construct a railway node layout diagram for the entire railway line structure, wherein the railway node layout diagram includes a plurality of data collection nodes and a plurality of railway nodes, and the railway nodes are interconnected;
[0062] A processing module, used for acquiring first data of a data collection node, grouping and splicing the first data to obtain a plurality of data groups, and associating the data groups with railway nodes;
[0063] The management module is used to generate an application evaluation value of the current data group according to the data group associated with the railway node and the actual data group, and determine whether to generate a correction instruction for the corresponding data group according to the application evaluation value.
[0064] In some embodiments of the present application, a railway node layout diagram is constructed for the entire railway line structure, including:
[0065] Obtain all GIS images of the railway, perform contour interception on all GIS images, and generate overlapping contour areas and railway foundation areas;
[0066] According to the preset node screening rules, the overlapping contour area is screened and the first railway node is determined, and the second railway node is determined according to the railway foundation area;
[0067] A railway node layout diagram is constructed according to the relative positions of the coincident contour area and the railway foundation area on the GIS image and the corresponding relationship between the first railway node and the second railway node and the coincident contour area and the railway foundation area.
[0068] In some embodiments of the present application, screening the overlapping contour area and determining the first railway node according to a preset node screening rule includes:
[0069] The area of the overlapping contour region is obtained, and the number of characteristic nodes corresponding to the overlapping contour region is set according to the average number of nodes in the overlapping contour region involved in all GIS images;
[0070] According to the number of characteristic nodes and the preset line distance principle, the overlapping contour area is divided to obtain multiple sub-areas;
[0071] Determine the first central node in each sub-region, analyze each first central node with the remaining characteristic nodes in the same sub-region, determine a node subset based on the first central node, and determine whether the first central node needs to be replaced according to the node subset;
[0072] If not necessary, the corresponding first central node is set as the first railway node. If necessary, the point in the node subset that satisfies the principle of being closest to each characteristic node in the same sub-region is set as the first central node.
[0073] In this embodiment, the number of characteristic nodes is the actual number of nodes in the overlapping contour area, the actual number of nodes is the number of stations and section land, and the preset line distance principle is set according to the distance between adjacent nodes in the GIS image. The area is reasonably divided according to the distance between adjacent nodes and the number of characteristic nodes, laying the foundation for the subsequent determination of the central node.
[0074] In this embodiment, the first central node refers to the node closest to each characteristic node of the current sub-region, and the node subset is specifically the characteristic nodes of the same sub-region.
[0075] In this embodiment, by dividing into multiple sub-areas and the corresponding first central node, the point closest to each feature node in the same sub-area is generated, thereby determining the first railway node, laying the foundation for the subsequent acquisition of the first data and data splicing and grouping, and ensuring the accuracy of the relative position relationship of the original node data in the summary map.
[0076] In some embodiments of the present application, obtaining first data of a data collection node includes:
[0077] Determining a first distance of each first railway node according to the regional scope of each first railway node;
[0078] According to the first position coordinate of the first railway node as the origin and the first distance as the radius, the first data collection nodes belonging to the current first railway node are screened out, and the second position coordinate corresponding to each first data collection node is obtained;
[0079] Calculating a relative distance between the first position coordinate and the second position coordinate, and determining a correlation between the current first data collection node and the corresponding first railway node based on a ratio of the relative distance to the first distance;
[0080] The data of the first data collection node whose correlation is greater than a preset correlation threshold is obtained, and the data is preprocessed and standardized to generate first data.
[0081] In this embodiment, the data collection node is determined according to the railway node, which lays the foundation for the subsequent acquisition of the first data of the corresponding data collection node, ensures the relevance of the first data to the corresponding railway node, greatly reduces the tediousness of data processing, and quickly collects the relevant data of the corresponding railway node, laying the foundation for the subsequent grouping and splicing of the corresponding railway node data.
[0082] In some embodiments of the present application, preprocessing and standardizing the data to generate first data includes:
[0083] Preprocessing the data, including unification, removal of outliers, filling of missing values, and data cleaning;
[0084] The preprocessed data is standardized, wherein the standardization includes classifying the data according to data categories to obtain multi-category data, and standardizing the data of the same category;
[0085]
[0086] Among them, x'( i ) is the i-th data x( i ), where n is the number of data in the same data category;
[0087] The first data is generated according to a plurality of standardized data of different data categories.
[0088] In this embodiment, unification is the process of uniformly processing the data to ensure that the data has a similar scale and distribution. Missing values are abnormal losses in the data, and outliers are data in the data set that are significantly different from other data. Data cleaning is the process of identifying and correcting erroneous, inconsistent, or incomplete data in the data set.
[0089] In this embodiment, the data categories determined by classification of historical map data include terrain data, road network data, location data, etc.
[0090] In this embodiment, the data is processed uniformly through preprocessing and standardization, which improves the quality and credibility of the data, lays a data foundation for subsequent grouping and splicing of the data, ensures data accuracy, and improves the accuracy of map route data.
[0091] In some embodiments of the present application, the first data is grouped and concatenated to obtain multiple data groups, including:
[0092] Dividing the first data into a plurality of data blocks according to the type of the coordinate system of the first data;
[0093] Extract characteristic factors from the first data of the same data category according to the correlation coefficient set to obtain characteristic factors corresponding to multiple data categories;
[0094] The characteristic factor is:
[0095] ∝xM T =eM' (i)
[0096] Among them, xM T is the characteristic factor in the Mth data category, eM' (i) is the correlation coefficient corresponding to the i-th standardized data in the M-th data category, ∝ is a screening formula, wherein the screening formula is used to screen out the standardized data whose correlation coefficient is greater than a preset correlation coefficient threshold;
[0097] The characteristic factors of different data categories in the same data block are spliced to generate multiple initial data groups;
[0098] Generate the splicing credibility of the initial data group according to the correlation coefficient of the characteristic factors involved in the initial data group;
[0099] An initial data group whose splicing credibility is greater than a preset credibility threshold is set as a data group, and the data group is associated with the first railway node.
[0100] In this embodiment, the correlation coefficient set refers to the correlation coefficients generated by the degree of influence of historical map data on the corresponding position accuracy. When the historical map data fluctuates and causes changes in the position accuracy, the correlation coefficient is generated based on the degree of change. The greater the degree of change, that is, the greater the degree of influence, the greater the correlation coefficient.
[0101] In this embodiment, for characteristic factors in the same data category, such as altitude data in the terrain data category, if the historical correlation coefficient of the altitude data is greater than a preset correlation coefficient threshold, the altitude data is set as the characteristic factor in the terrain data category.
[0102] In this embodiment, the coordinate system corresponding to the data block definition is converted into the same coordinate system. Based on the Tiandi Map image data, the data blocks corresponding to different data categories are spliced to form the station and section land use data of a certain railway bureau. The station and section land use data of multiple railway bureaus are merged into the final result data. The corresponding actual data group is set in the second railway node. After the data group is associated with the first railway node, the corresponding data group is set on the railway node layout diagram, forming a map of the entire railway while ensuring the accuracy of the data.
[0103] In some embodiments of the present application, generating an application evaluation value of the current data group includes:
[0104] Generate a credibility mean value according to the splicing credibility of the data group corresponding to the first railway node, and set the number of collection groups of the actual data group according to the credibility mean value;
[0105] Generate an application evaluation value A of the current data group according to the data deviation value of the same data category between the actual data group and the corresponding data group, the correlation coefficient corresponding to the data category, and the splicing credibility of the data group;
[0106]
[0107] Wherein, h is the data category in the actual data group and the corresponding data group, S1i is the i-th data category in the actual data group, S2i is the i-th data category in the data group, S1i-S2i is the data deviation value of the same data category in the actual data group and the corresponding data group, e' (i) is the correlation coefficient corresponding to the i-th data category, where i = 1, 2, …h.
[0108] In some embodiments of the present application, judging whether to generate a correction instruction for a corresponding data group according to the application evaluation value includes:
[0109] Presetting a first preset application evaluation value threshold and a second preset application evaluation value threshold, wherein the first preset application evaluation value threshold is smaller than the second preset application evaluation value threshold;
[0110] When the application evaluation value is less than the first preset application evaluation value threshold, a secondary correction instruction is generated for the current data group, wherein the secondary correction instruction is to redetermine the first railway node associated with the current data group, reacquire the first data of the data acquisition node, and group and splice the first data;
[0111] When the application evaluation value is between the first preset application evaluation value threshold and the second preset application evaluation value threshold, a first-level correction instruction is generated for the current data group, wherein the first-level correction instruction is to fine-tune the splicing factor of the current data group;
[0112] When the application evaluation value is greater than the second preset application evaluation value threshold, no correction instruction is generated.
[0113] In this embodiment, the first preset application evaluation value threshold and the second preset application evaluation value threshold are set in advance. The splicing factor is the characteristic factor of different data categories in the same data block involved in the current data group. The characteristic factor is replaced or adjusted to improve the accuracy of the entire data group.
[0114] In some embodiments of the present application, the number of collection groups of the actual data group is set according to the credibility mean, including:
[0115] Presetting a first preset credibility mean interval, a second preset credibility mean interval, a third preset credibility mean interval and a fourth preset credibility mean interval;
[0116] When the credibility mean is within the first preset credibility mean interval, the number of collection groups of the actual data group is set to be the fourth preset number of collection groups;
[0117] When the credibility mean is within the second preset credibility mean interval, the number of collection groups of the actual data group is set to be the third preset number of collection groups;
[0118] When the credibility mean is within the third preset credibility mean interval, the number of collection groups of the actual data group is set to the second preset number of collection groups;
[0119] When the credibility mean is in the fourth preset credibility mean interval, the number of collection groups of the actual data groups is set to the first preset number of collection groups.
[0120] In this embodiment, when the mean credibility value is larger, it means that the splicing credibility of the current data group is higher, that is, the accuracy is higher, and the number of actual data groups collected can be reduced. When the mean credibility value is smaller, it means that the splicing credibility of the current data group is lower, that is, the accuracy is lower, and the number of actual data groups collected needs to be increased, thereby improving the accuracy of the application evaluation value of the current data group and ensuring the accuracy of the current data and the overlapping area position in the map.
[0121] In summary, the present invention discloses a comprehensive management system for railway line data, including: a construction module, for constructing a railway node layout diagram for the entire railway line structure, the railway node layout diagram includes a number of data acquisition nodes and a number of railway nodes, and the railway nodes are interconnected; a processing module, for obtaining the first data of the data acquisition node, grouping and splicing the first data, obtaining multiple data groups, and associating the data groups with the railway nodes; a management module, for generating an application evaluation value of the current data group according to the data group associated with the railway node and the actual data group, and judging whether to generate a correction instruction for the corresponding data group according to the application evaluation value. The present application constructs a railway node layout diagram, determines the railway node position and the corresponding data acquisition point, ensures the correlation between the railway node and the data acquisition point data collected, improves the data acquisition speed and accuracy, generates multiple data blocks according to the type of coordinate system for the data of the same railway node, splices different data categories in the same data block, obtains the data group and verifies the accuracy of the data group, meets the demand for a single map of the entire road and improves the accuracy of the data in the overlapping line area.
[0122] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.
Claims
1. A comprehensive railway data management system, characterized in that: include: A construction module is used to construct a railway node layout diagram for the entire railway line structure, wherein the railway node layout diagram includes a plurality of data collection nodes and a plurality of railway nodes, and the railway nodes are interconnected; A processing module, used for acquiring first data of a data collection node, grouping and splicing the first data to obtain a plurality of data groups, and associating the data groups with railway nodes; The management module is used to generate an application evaluation value of the current data group according to the data group associated with the railway node and the actual data group, and determine whether to generate a correction instruction for the corresponding data group according to the application evaluation value.
2. The railway line data integrated management system according to claim 1, characterized in that: For the entire railway structure, a railway node layout diagram is constructed, including: Obtain all GIS images of the railway, perform contour interception on all GIS images, and generate overlapping contour areas and railway foundation areas; According to the preset node screening rules, the overlapping contour area is screened and the first railway node is determined, and the second railway node is determined according to the railway foundation area; A railway node layout diagram is constructed according to the relative positions of the coincident contour area and the railway foundation area on the GIS image and the correspondence between the first railway node and the second railway node and the coincident contour area and the railway foundation area.
3. The railway line data integrated management system as claimed in claim 2, characterized in that: According to the preset node screening rules, the overlapping contour area is screened and the first railway node is determined, including: The area of the overlapping contour region is obtained, and the number of characteristic nodes corresponding to the overlapping contour region is set according to the average number of nodes in the overlapping contour region involved in all GIS images; According to the number of characteristic nodes and the preset line distance principle, the overlapping contour area is divided to obtain multiple sub-areas; Determine the first central node in each sub-region, analyze each first central node with the remaining characteristic nodes in the same sub-region, determine a node subset based on the first central node, and determine whether the first central node needs to be replaced according to the node subset; If not necessary, the corresponding first central node is set as the first railway node. If necessary, the point in the node subset that satisfies the principle of being closest to each characteristic node in the same sub-region is set as the first central node.
4. The railway line data integrated management system as claimed in claim 3, characterized in that: Acquiring first data of a data collection node includes: Determining a first distance of each first railway node according to the regional scope of each first railway node; According to the first position coordinate of the first railway node as the origin and the first distance as the radius, the first data collection nodes belonging to the current first railway node are screened out, and the second position coordinate corresponding to each first data collection node is obtained; Calculating a relative distance between the first position coordinate and the second position coordinate, and determining a correlation between the current first data collection node and the corresponding first railway node based on a ratio of the relative distance to the first distance; The data of the first data collection node whose correlation is greater than a preset correlation threshold is obtained, and the data is preprocessed and standardized to generate first data.
5. The railway line data integrated management system as claimed in claim 4, characterized in that: Preprocessing and standardizing the data to generate first data includes: Preprocessing the data, including unification, removal of outliers, filling of missing values, and data cleaning; The preprocessed data is standardized, wherein the standardization includes classifying the data according to data categories to obtain multi-category data, and standardizing the data of the same category; Among them, x' (i) is the i-th data x in the same data category (i) The standardized data, n is the number of data in the same data category; The first data is generated according to a plurality of standardized data of different data categories.
6. The railway line data integrated management system as claimed in claim 5, characterized in that: The first data is grouped and concatenated to obtain multiple data groups, including: Dividing the first data into a plurality of data blocks according to the type of the coordinate system of the first data; Extract characteristic factors from the first data of the same data category according to the correlation coefficient set to obtain characteristic factors corresponding to multiple data categories; The characteristic factor is: ∝xM T =eM' (i) Among them, xM T is the characteristic factor in the Mth data category, eM' (i) is the correlation coefficient corresponding to the i-th standardized data in the M-th data category, ∝ is a screening formula, wherein the screening formula is used to screen out the standardized data whose correlation coefficient is greater than a preset correlation coefficient threshold; The characteristic factors of different data categories in the same data block are spliced to generate multiple initial data groups; Generate the splicing credibility of the initial data group according to the correlation coefficient of the characteristic factors involved in the initial data group; An initial data group whose splicing credibility is greater than a preset credibility threshold is set as a data group, and the data group is associated with the first railway node.
7. The railway line data integrated management system as claimed in claim 6, characterized in that: Generate application evaluation values for the current data group, including: Generate a credibility mean value according to the splicing credibility of the data group corresponding to the first railway node, and set the number of collection groups of the actual data group according to the credibility mean value; Generate an application evaluation value A of the current data group according to the data deviation value of the same data category between the actual data group and the corresponding data group, the correlation coefficient corresponding to the data category, and the splicing credibility of the data group; Wherein, h is the data category in the actual data group and the corresponding data group, S1i is the i-th data category in the actual data group, S2i is the i-th data category in the data group, S1i-S2i is the data deviation value of the same data category in the actual data group and the corresponding data group, e' (i) is the correlation coefficient corresponding to the i-th data category, where i = 1, 2, …h.
8. The railway line data integrated management system as claimed in claim 7, characterized in that: Determining whether to generate a correction instruction for a corresponding data group according to the application evaluation value includes: Presetting a first preset application evaluation value threshold and a second preset application evaluation value threshold, wherein the first preset application evaluation value threshold is smaller than the second preset application evaluation value threshold; When the application evaluation value is less than the first preset application evaluation value threshold, a secondary correction instruction is generated for the current data group, wherein the secondary correction instruction is to redetermine the first railway node associated with the current data group, reacquire the first data of the data acquisition node, and group and splice the first data; When the application evaluation value is between the first preset application evaluation value threshold and the second preset application evaluation value threshold, a first-level correction instruction is generated for the current data group, wherein the first-level correction instruction is to fine-tune the splicing factor of the current data group; When the application evaluation value is greater than the second preset application evaluation value threshold, no correction instruction is generated.
9. The railway line data integrated management system as claimed in claim 7, characterized in that: The number of collection groups of the actual data group is set according to the credibility mean, including: Presetting a first preset credibility mean interval, a second preset credibility mean interval, a third preset credibility mean interval and a fourth preset credibility mean interval; When the credibility mean is within the first preset credibility mean interval, the number of collection groups of the actual data group is set to be the fourth preset number of collection groups; When the credibility mean is within the second preset credibility mean interval, the number of collection groups of the actual data group is set to be the third preset number of collection groups; When the credibility mean is within the third preset credibility mean interval, the number of collection groups of the actual data group is set to the second preset number of collection groups; When the credibility mean is in the fourth preset credibility mean interval, the number of collection groups of the actual data groups is set to the first preset number of collection groups.
