A data cleaning method, system and medium for national land space planning data

Abstract

The present application relates to the field of image processing technology, and specifically to a data cleaning method, system and medium for land space planning data, the method comprising: obtaining a set of terrain data points of land space geographic information; determining the local change neighboring difference of each terrain data point in the set of terrain data points based on the change of the surrounding terrain data points of each terrain data point in the set of terrain data points; determining the change distribution difference of each terrain data point based on the similarity between each terrain data point and the adjacent terrain data points in the set of terrain data points, combined with the local change neighboring difference of each terrain data point; obtaining terrain data points that need to be interpolated and cleaned based on the density of terrain data points in the set of terrain data points and mutation data points; interpolating and cleaning the terrain data points that need to be interpolated and cleaned based on the degree of confusion and change distribution difference of the local terrain data points. The present application aims to improve the accuracy of data cleaning.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and specifically to a data cleaning method, system and medium for national land space planning data. Background Art

[0002] In order to coordinate development deviations in different regions and effectively solve the problem of irrational use of land resources, it is necessary to plan the land resources in the national space.

[0003] At present, in the process of national land space planning, relevant planning and design personnel need to collect national land geographic environment data. Since national land geographic environment data may have defects such as data anomalies and sparseness, it is impossible to accurately reflect national land geographic space information in the process of national land space planning, which has a serious impact on the further planning of national land space. Therefore, it is necessary to clean the collected national land geographic environment data. Summary of the invention

[0004] In view of the above, in order to avoid defects such as data anomalies and data sparseness in national land geographic environment data, it is necessary to provide a data cleaning method, system and medium for national land space planning data, which improves the accuracy of data cleaning compared with traditional data cleaning methods, systems and media for national land space planning data:

[0005] In a first aspect, an embodiment of the present application provides a data cleaning method for land space planning data, the method comprising the following steps:

[0006] Get a set of terrain data points for national spatial geographic information;

[0007] Determine the local change neighboring difference of each terrain data point in the terrain data point set based on the change of the terrain data points around each terrain data point in the terrain data point set;

[0008] Based on the similarity between each terrain data point and the adjacent terrain data points in the terrain data point set, combined with the local change adjacent difference of each terrain data point, the change distribution difference of each terrain data point is determined;

[0009] Based on the density of terrain data points and mutation data points in the terrain data point set, terrain data points that need to be interpolated and cleaned are obtained in the terrain data point set;

[0010] Based on the degree of chaos and change distribution difference of local terrain data points, the reverse distance interpolation algorithm is used to interpolate and clean the terrain data points that need interpolation and cleaning.

[0011] Preferably, the process of determining the local change neighboring difference is:

[0012] Calculate the distance between any terrain data point in the terrain data point set and all terrain data points in the terrain data point set, arrange all terrain data points in the terrain data point set in ascending order according to the distance, and form a local terrain data point set centered on any terrain data point with a preset number of terrain data points;

[0013] For each local terrain data point set, taking the local terrain data point set as the center, respectively select a nearest local terrain data point set in multiple preset directions to form a neighboring terrain data point set of the local terrain data point set;

[0014] Calculate the average value of all data points in the local terrain data point set and its neighboring terrain data point set, and record it as the local neighboring mean;

[0015] Calculate the mean of all data point values ​​in the local terrain data point set, recorded as the central local mean;

[0016] Calculate the difference between the local neighborhood mean and the central local mean;

[0017] Count the range of values ​​of all data points in the local terrain data point set and its neighboring terrain data point set;

[0018] The forward fusion result of the difference and the range is used as the local change neighborhood difference of the central data point of the local terrain data point set.

[0019] Preferably, the process of determining the change distribution difference is:

[0020] Determine the terrain data distribution value of each terrain data point based on the similarity between each terrain data point and adjacent terrain data points in the terrain data point set;

[0021] The forward fusion result of the terrain data distribution value of each terrain data point and the local change neighboring difference is taken as the change distribution difference of each terrain data point.

[0022] Preferably, the process of determining the terrain data distribution value is:

[0023] For each set of local terrain data points, calculate the distance between each data point in the set of local terrain data points and the central data point;

[0024] The distance between two data points is used as the input of the Gaussian function to obtain the distance scale between the two data points. The difference between the value of each data point in the local terrain data point set and the value of the central data point is positively combined with the result of the distance scale corresponding to each data point, and recorded as the change distance between each data point and the central data point.

[0025] The average value of the corresponding change distances of all data points in the local terrain data point set is recorded as the terrain data distribution value of the central data point of the local terrain data point set.

[0026] Preferably, the process of determining the terrain data points that need interpolation cleaning is:

[0027] Arrange all data points in the local terrain data point set and its neighboring terrain data point set in the horizontal and vertical directions respectively to obtain each horizontal change data point sequence and each vertical change data point sequence;

[0028] A mutation point detection algorithm is used to obtain mutation data points in each horizontal change data point sequence and each vertical change data point sequence, and the values ​​of the mutation data points are assigned to preset values;

[0029] For each level change data point sequence, calculate the distance between any two adjacent data points in the level change data point sequence in the terrain data point set, and record it as the local distance;

[0030] Determine a horizontal interval threshold of the horizontal change data point sequence based on the local distance between any two adjacent data points in the horizontal change data point sequence;

[0031] When the local distance between two adjacent data points in the horizontal variation data point sequence is greater than or equal to the horizontal interval threshold, it is determined that a data point needs to be interpolated and supplemented between the two adjacent data points;

[0032] The data point at the middle position of the two adjacent data points and the data point whose value in the horizontal change data point sequence is the preset value are used as the terrain data points that need to be interpolated and cleaned;

[0033] For each vertical change data point sequence, the terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence are obtained by using the calculation method of the terrain data points that need to be interpolated and cleaned in the vertical change data point sequence.

[0034] Preferably, the horizontal interval threshold is: the mean value of all the local distances corresponding to the horizontal change data point sequence.

[0035] Preferably, the process of performing interpolation cleaning on the terrain data points that need interpolation cleaning is:

[0036] Based on the proportion of terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence, the degree of confusion of the data point values, and the difference in the change distribution of the data points, the dynamic power parameter of the reverse distance interpolation algorithm is determined;

[0037] The horizontal change data point sequence and the dynamic power parameter are used as the input of the reverse distance interpolation algorithm to interpolate and fill the terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence;

[0038] For the vertically changing data point sequence, the method of interpolating and filling the horizontally changing data point sequence is adopted to interpolate and fill the vertically changing data point sequence.

[0039] Preferably, the dynamic power parameter is determined as follows:

[0040] The ratio of the number of terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence to the total number of data points is recorded as the local vacancy value;

[0041] Calculate the degree of confusion of the values ​​of all data points in the horizontal change data point sequence, perform forward fusion on the degree of confusion and the mean of the difference of the change distribution of all data points in the horizontal change data point sequence, and record the normalized result of the forward fusion as the local information density;

[0042] When the local vacancy value is greater than or equal to the preset local vacancy value threshold, the initial power parameter value of the reverse distance interpolation algorithm is the first preset value; otherwise, the initial power parameter value is the second preset value;

[0043] The product of the initial power parameter and the local information density is used as the dynamic power parameter of the reverse distance interpolation algorithm.

[0044] In the second aspect, an embodiment of the present application also provides a data cleaning system for national land space planning data, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above methods are implemented.

[0045] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements a data cleaning method for national land space planning data as described in the first aspect.

[0046] This application has at least the following beneficial effects:

[0047] The present application divides the terrain data points into multiple local terrain data point sets, and analyzes the changes in the values ​​of the data points around a certain terrain data point based on the changes in the values ​​of the data points in each local terrain data point set compared with the surrounding local terrain data point sets, and the overall change trend of the values ​​of the data points within each local terrain data point set, thereby improving the accuracy of the analysis of the changes in the values ​​of the local data points;

[0048] Furthermore, the positions of the terrain data points to be interpolated and cleaned are obtained in combination with the density and value changes of the terrain data points, thereby improving the accuracy of obtaining the positions of the terrain data points to be interpolated and cleaned;

[0049] Furthermore, the power parameter in the traditional reverse distance interpolation algorithm is optimized, and the power parameter is dynamically adjusted based on the changes in the values ​​of data points in the local area, which improves the accuracy of interpolation of abnormal data and missing data in terrain data, thereby improving the accuracy of data cleaning. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A flowchart of the steps of a data cleaning method for land space planning data provided by an embodiment of the present application;

[0052] Figure 2 It is a schematic diagram of the process of determining the distribution value of terrain data;

[0053] Figure 3 A schematic diagram of the process of determining terrain data points that need to be interpolated and cleaned;

[0054] Figure 4 Schematic diagram of the process of determining dynamic power parameters. DETAILED DESCRIPTION

[0055] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It should be understood that, unless otherwise specified, " / " means or.

[0057] It should also be noted that the terms "first" and "second" in this application are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of this application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0058] The following is a detailed description of a specific solution of a data cleaning method, system and medium for national land space planning data provided by the present application in conjunction with the accompanying drawings.

[0059] See also Figure 1 , which shows a flowchart of a data cleaning method for land space planning data provided by an embodiment of the present application, the method comprising the following steps:

[0060] Step 1: Obtain a set of terrain data points of national land space geographic information.

[0061] In the process of national land space planning, natural topography is an important reference. Therefore, in order to analyze and plan the national land space reasonably, it is necessary to first obtain local topographic data information. The Digital Elevation Model (DEM) uses limited terrain elevation data to achieve digital representation of mountain topography and surface morphology. Before establishing a digital elevation model, it is necessary to obtain topographic data. This application uses a set of terrain data points obtained by an earth observation laser altimeter satellite for calculation and analysis.

[0062] Step 2: determining the local change neighboring difference of each terrain data point in the terrain data point set based on the change of the terrain data points around each terrain data point in the terrain data point set.

[0063] During the operation of the Earth observation laser altimeter satellite, the laser beam will be disturbed by the state of the atmospheric cloud layer, resulting in the deviation of the values ​​of some terrain data points in the acquired terrain data point set from the actual values, which is inconsistent with the trend of local terrain data changes and cannot accurately reflect the real changes in the local terrain state. Therefore, it is necessary to analyze and extract the terrain data points with abnormal changes in the terrain data point set.

[0064] The terrain changes in small local areas are consistent, so the terrain data point set is first divided to obtain each local terrain data point set. The specific process is as follows:

[0065] The distance between any terrain data point in the terrain data point set and all terrain data points in the terrain data point set is calculated, all terrain data points in the terrain data point set are arranged from small to large according to the distance, and a preset number of terrain data points are used to form a local terrain data point set centered on any terrain data point.

[0066] In one embodiment of the present application, the distance is Euclidean distance. As other implementation methods, on the basis of being able to measure the distance between two terrain data points, the implementer may adopt other existing technologies to obtain the distance between two terrain data points, such as Manhattan distance, Minkowski distance, etc., and the present application does not impose any special restrictions.

[0067] In an embodiment of the present application, the value of the preset number is 11. The value of the preset number is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0068] For each local terrain data point set, with the local terrain data point set as the center, a nearest local terrain data point set is taken in multiple preset directions to form a neighboring terrain data point set of the local terrain data point set. Among them, the intersection between the local terrain data point sets taken in any two directions of the local terrain data point set is an empty set, reflecting the state of non-intersecting position areas in the local terrain.

[0069] In an embodiment of the present application, the preset directions are four directions: up, down, left, and right. The preset directions are preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0070] The process of determining the local variation neighborhood difference of each terrain data point is:

[0071] Calculate the average value of all data points in the local terrain data point set and its neighboring terrain data point set, and record it as the local neighboring mean;

[0072] Calculate the mean of all data point values ​​in the local terrain data point set, recorded as the central local mean;

[0073] Calculate the difference between the local neighborhood mean and the central local mean;

[0074] Count the range of values ​​of all data points in the local terrain data point set and its neighboring terrain data point set;

[0075] The forward fusion result of the difference and the range is used as the local change neighborhood difference of the central data point of the local terrain data point set.

[0076] It needs to be understood that: difference refers to the difference between the two, such as the absolute value relationship of the difference, the ratio relationship, etc., which can be set by the implementer according to the actual situation; positive fusion refers to combining multiple independent variables together to enhance the overall effect, such as multiplication relationship, addition relationship, etc., which can be limited by the implementer according to the actual situation.

[0077] In one embodiment of the present application, the difference and the range are respectively taken as the exponents of an exponential function with a natural constant as the base, denoted as a difference exponential function and a range exponential function, and the sum of the difference exponential function and the range exponential function is taken as the local change neighborhood difference of the central data point of the local terrain data point set; wherein the difference is the absolute value of the difference.

[0078] In another embodiment of the present application, the sum of the central local mean and a preset tuning parameter constant greater than 0 is calculated, the ratio of the local neighborhood mean to the sum is calculated, and the product of the ratio and the range is used as the local change neighborhood difference of the central data point of the local terrain data point set; wherein, the purpose of the tuning parameter constant is to avoid the denominator being 0, the value of the tuning parameter constant is 1, the value of the tuning parameter constant is preset artificially, and the implementer can set it by himself, and the present application does not impose any special restrictions.

[0079] It should be noted that if the change in the values ​​of data points in the local terrain data point set is more obvious than that in the surrounding local terrain data point sets, the difference and the range are larger, and the local change adjacent difference is relatively larger.

[0080] Step 3: Based on the similarity between each terrain data point and the adjacent terrain data points in the terrain data point set, combined with the local change adjacent difference of each terrain data point, the change distribution difference of each terrain data point is determined.

[0081] The process of determining the difference in the distribution of the change of each terrain data point is as follows:

[0082] The data points in each local terrain data point set reflect the changing characteristics of the local terrain. Therefore, it is necessary to calculate the distribution characteristics of the data points in the local terrain data point set and characterize the fluctuation characteristics of the terrain data.

[0083] For each set of local terrain data points, the distance between each data point in the set of local terrain data points and the central data point is calculated. Considering that the closer the distance between two data points in the set of local terrain data points, the closer the data changes between the two data points are, the distance between the two data points is used as the input of the Gaussian function to obtain the distance scale between the two data points, and the difference between the value of each data point in the set of local terrain data points and the value of the central data point is forward combined with the result of the distance scale corresponding to each data point, and recorded as the change distance between each data point and the central data point.

[0084] The average value of the corresponding change distances of all data points in the local terrain data point set is recorded as the terrain data distribution value of the central data point of the local terrain data point set.

[0085] It should be understood that positive combination refers to combining multiple independent variables in a way that enhances the overall effect, such as additive relationship, multiplicative relationship, etc., and implementers can define it according to actual conditions.

[0086] In one embodiment of the present application, the difference between the value of each data point in the local terrain data point set and the value of the central data point is multiplied by the distance scale corresponding to each data point, and the result is recorded as the change distance between each data point and the central data point.

[0087] In another embodiment of the present application, the difference between the value of each data point in the local terrain data point set and the value of the central data point is added to the corresponding distance scale of each data point, and the result is recorded as the change distance between each data point and the central data point.

[0088] Combine the terrain data distribution values ​​and local change neighboring differences of each terrain data point in the terrain data point set to determine the change distribution difference of each terrain data point. The specific process is as follows:

[0089] The forward fusion result of the terrain data distribution value of each terrain data point and the local change neighboring difference is taken as the change distribution difference of each terrain data point.

[0090] In one embodiment of the present application, the positive product of the terrain data distribution value of each terrain data point and the local change neighboring difference is used as the change distribution difference of each terrain data point.

[0091] In another embodiment of the present application, the terrain data distribution value and the local change neighboring difference of each terrain data point are respectively used as the exponents of an exponential function with a natural constant as the base, denoted as the first exponential function and the second exponential function, and the sum of the first exponential function and the second exponential function is used as the change distribution difference of each terrain data point.

[0092] It should be noted that: if the change in the values ​​of the data points in the local terrain data point set is closer to that in the surrounding local terrain data point set, the local change neighborhood difference will be relatively small. At the same time, if the overall change trend of the values ​​of the data points within the local terrain data point set is closer, the terrain data distribution value will be relatively small. At this time, the change distribution difference is relatively small. On the contrary, if there are data points with abnormal value changes in the local terrain data point set, the change distribution difference will be relatively large. The change distribution difference can reflect the change in the values ​​of the data points around the central data point of the local terrain data point set. The schematic diagram of the process of determining the terrain data distribution value is shown in the figure. Figure 2 shown.

[0093] Step 4: based on the density of the terrain data points and the mutation data points in the terrain data point set, obtain the terrain data points in the terrain data point set that need to be interpolated and cleaned.

[0094] The process of determining the terrain data points that need interpolation cleaning is as follows:

[0095] Generally, the actual terrain structure changes are continuous, so the values ​​of terrain data points in the local area also have the characteristics of continuous change. The local terrain data point set and all data points in its neighboring terrain data point set are arranged horizontally and vertically to obtain the horizontal change data point sequence and the vertical change data point sequence.

[0096] A mutation point detection algorithm is used to obtain mutation data points in each horizontal change data point sequence and each vertical change data point sequence, and the numerical value of the mutation data point is assigned to a preset value.

[0097] In an embodiment of the present application, the preset value is 0. The preset value is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0098] In one embodiment of the present application, a Bayesian mutation point detection algorithm is used to obtain mutation data points in a sequence. As other implementation methods, on the basis of being able to obtain mutation data points in a sequence, the implementer may use other existing technologies to obtain mutation data points in a sequence, such as the Pettitt mutation point detection algorithm, the Mann-Kendall mutation point detection algorithm, etc., and the present application does not impose any special restrictions.

[0099] In the horizontal change data point sequence and the vertical change data point sequence, there are missing data points in the sequence due to the removal of abnormal data points. At the same time, due to the accuracy of the terrain data sensing equipment during the data collection process, the collected local terrain data is relatively sparse and cannot accurately reflect the local terrain changes. Therefore, it is necessary to interpolate the local terrain data points.

[0100] For each level change data point sequence, calculate the distance between any two adjacent data points in the level change data point sequence in the terrain data point set, and record it as the local distance;

[0101] The mean value of all the local distances corresponding to the level change data point sequence is recorded as the level interval threshold of the level change data point sequence;

[0102] When the local distance between two adjacent data points in the horizontal change data point sequence is greater than or equal to the horizontal interval threshold, it indicates that the data points in the horizontal change data point sequence are sparsely distributed, and it is determined that a data point needs to be interpolated between the two adjacent data points;

[0103] The data point at the middle position of the two adjacent data points and the data point with the value of the preset value in the horizontal change data point sequence are taken as the terrain data points that need to be interpolated and cleaned.

[0104] For each vertical change data point sequence, the calculation method of the terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence is adopted to obtain the terrain data points that need to be interpolated and cleaned in each vertical change data point sequence. The flowchart for determining the terrain data points that need to be interpolated and cleaned is shown in the figure. Figure 3 shown.

[0105] Step 5: Based on the degree of disorder and the difference in change distribution of local terrain data points, the terrain data points that need to be interpolated and cleaned are interpolated and cleaned using a reverse distance interpolation algorithm.

[0106] The process of interpolation cleaning of terrain data points that need interpolation cleaning is as follows:

[0107] Inverse Distance Weighted (IDW) is a classic spatial interpolation algorithm commonly used in geographic data information processing. In this algorithm, the setting of the power parameter greatly affects the accuracy of the numerical interpolation results.

[0108] This application optimizes the power parameter in the traditional reverse distance interpolation algorithm, and dynamically adjusts the power parameter based on the changes in the values ​​of local area data points, so as to achieve the purpose of accurate interpolation and cleaning of geographic data information.

[0109] The ratio of the number of terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence to the total number of data points is recorded as the local vacancy value;

[0110] Calculate the degree of confusion of the values ​​of all data points in the horizontal change data point sequence, perform forward fusion on the degree of confusion and the mean of the difference of the change distribution of all data points in the horizontal change data point sequence, and record the normalized result of the forward fusion as the local information density;

[0111] The degree of chaos can be represented by statistics such as variance, standard deviation or information entropy that can describe the degree of irregularity in the distribution of data point values; in one embodiment of the present application, the degree of chaos is information entropy.

[0112] When the local vacancy value is greater than or equal to the preset local vacancy value threshold, the initial power parameter value of the reverse distance interpolation algorithm is the first preset value; otherwise, the initial power parameter value is the second preset value; in one embodiment of the present application, the first preset value and the second preset value are 1 and 2 respectively, and the values ​​of the first preset value and the second preset value are preset manually and can be set by the implementer, and the present application does not impose any special restrictions;

[0113] The product of the initial power parameter and the local information density is used as the dynamic power parameter of the reverse distance interpolation algorithm; the flow chart of determining the dynamic power parameter is as follows: Figure 4 As shown;

[0114] The horizontal change data point sequence and the dynamic power parameter are used as the input of the reverse distance interpolation algorithm to interpolate and fill the terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence;

[0115] For the vertically changing data point sequence, the method of interpolating and filling the horizontally changing data point sequence is adopted to interpolate and fill the vertically changing data point sequence.

[0116] At this point, the interpolation cleaning of abnormal terrain data points in the terrain data point set can be achieved.

[0117] Based on the same inventive concept as the above method, an embodiment of the present application also provides a data cleaning system for national land space planning data, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned data cleaning methods for national land space planning data.

[0118] Based on the same concept as the method embodiment of the present application, a computer-readable storage medium is proposed, and the computer-readable storage medium stores a computer program. When the computer program is executed by the processor, it implements a data cleaning method for national land space planning data as described in the first aspect. Its specific functions and technical effects can be found in the method embodiment part, which will not be repeated here.

[0119] In summary, the present application divides the terrain data points into multiple local terrain data point sets, and analyzes the changes in the values ​​of the data points around a certain terrain data point based on the changes in the values ​​of the data points in each local terrain data point set compared with the surrounding local terrain data point sets, and the overall change trend of the values ​​of the data points within each local terrain data point set, thereby improving the accuracy of the analysis of the changes in the values ​​of the local data points;

[0120] Furthermore, the positions of the terrain data points to be interpolated and cleaned are obtained in combination with the density and value changes of the terrain data points, thereby improving the accuracy of obtaining the positions of the terrain data points to be interpolated and cleaned;

[0121] Furthermore, the power parameter in the traditional reverse distance interpolation algorithm is optimized, and the power parameter is dynamically adjusted based on the changes in the values ​​of data points in the local area, which improves the accuracy of interpolation of abnormal data and missing data in terrain data, thereby improving the accuracy of data cleaning.

[0122] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0123] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. A data cleaning method for national land space planning data, characterized in that: The method comprises the following steps: Get a set of terrain data points for national spatial geographic information; Determine the local change neighboring difference of each terrain data point in the terrain data point set based on the change of the terrain data points around each terrain data point in the terrain data point set; Based on the similarity between each terrain data point and the adjacent terrain data points in the terrain data point set, combined with the local change adjacent difference of each terrain data point, the change distribution difference of each terrain data point is determined; Based on the density of terrain data points and mutation data points in the terrain data point set, terrain data points that need to be interpolated and cleaned are obtained in the terrain data point set; Based on the degree of confusion and distribution difference of local terrain data points, the reverse distance interpolation algorithm is used to interpolate and clean the terrain data points that need to be interpolated and cleaned; The process of determining the terrain data points that need interpolation cleaning is as follows: Arrange all data points in the local terrain data point set and its neighboring terrain data point set in the horizontal and vertical directions respectively to obtain each horizontal change data point sequence and each vertical change data point sequence; A mutation point detection algorithm is used to obtain mutation data points in each horizontal change data point sequence and each vertical change data point sequence, and the values ​​of the mutation data points are assigned to preset values; For each level change data point sequence, calculate the distance between any two adjacent data points in the level change data point sequence in the terrain data point set, and record it as the local distance; Determine a horizontal interval threshold of the horizontal change data point sequence based on the local distance between any two adjacent data points in the horizontal change data point sequence; When the local distance between two adjacent data points in the horizontal variation data point sequence is greater than or equal to the horizontal interval threshold, it is determined that a data point needs to be interpolated and supplemented between the two adjacent data points; The data point at the middle position of the two adjacent data points and the data point whose value in the horizontal change data point sequence is the preset value are used as the terrain data points that need to be interpolated and cleaned; For each vertical change data point sequence, a calculation method for terrain data points that need to be interpolated and cleaned in a horizontal change data point sequence is adopted to obtain terrain data points that need to be interpolated and cleaned in each vertical change data point sequence; The process of interpolating and cleaning the terrain data points that need interpolation and cleaning is as follows: Based on the proportion of terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence, the degree of confusion of the data point values, and the difference in the change distribution of the data points, the dynamic power parameter of the reverse distance interpolation algorithm is determined; The horizontal change data point sequence and the dynamic power parameter are used as the input of the reverse distance interpolation algorithm to interpolate and fill the terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence; For the vertically changing data point sequence, the method of interpolating and filling the horizontally changing data point sequence is adopted to interpolate and fill the vertically changing data point sequence; The determination process of the dynamic power parameter is: The ratio of the number of terrain data points that need to be interpolated and cleaned in the horizontal change data point sequence to the total number of data points is recorded as the local vacancy value; Calculate the degree of confusion of the values ​​of all data points in the level change data point sequence, perform forward fusion on the degree of confusion and the mean of the difference of the change distribution of all data points in the level change data point sequence, and record the normalized result of forward fusion as the local information density; forward fusion refers to combining multiple independent variables in a way that enhances the overall effect; When the local vacancy value is greater than or equal to the preset local vacancy value threshold, the initial power parameter value of the reverse distance interpolation algorithm is the first preset value; otherwise, the initial power parameter value is the second preset value; The product of the initial power parameter and the local information density is used as the dynamic power parameter of the reverse distance interpolation algorithm.

2. A data cleaning method for national land space planning data according to claim 1, characterized in that: The process of determining the local variation neighboring difference is as follows: Calculate the distance between any terrain data point in the terrain data point set and all terrain data points in the terrain data point set, arrange all terrain data points in the terrain data point set in ascending order according to the distance, and form a local terrain data point set centered on any terrain data point with a preset number of terrain data points; For each local terrain data point set, taking the local terrain data point set as the center, respectively select a nearest local terrain data point set in multiple preset directions to form a neighboring terrain data point set of the local terrain data point set; Calculate the average value of all data points in the local terrain data point set and its neighboring terrain data point set, and record it as the local neighboring mean; Calculate the mean of all data point values ​​in the local terrain data point set, recorded as the central local mean; Calculate the difference between the local neighborhood mean and the central local mean; Count the range of values ​​of all data points in the local terrain data point set and its neighboring terrain data point set; The forward fusion result of the difference and the range is used as the local change neighborhood difference of the central data point of the local terrain data point set.

3. A data cleaning method for land space planning data according to claim 2, characterized in that: The process of determining the change distribution difference is as follows: Determine the terrain data distribution value of each terrain data point based on the similarity between each terrain data point and adjacent terrain data points in the terrain data point set; The forward fusion result of the terrain data distribution value of each terrain data point and the local change neighboring difference is taken as the change distribution difference of each terrain data point.

4. A data cleaning method for national land space planning data as claimed in claim 3, characterized in that: The process of determining the distribution value of the terrain data is as follows: For each set of local terrain data points, calculate the distance between each data point in the set of local terrain data points and the central data point; The distance between two data points is used as the input of the Gaussian function to obtain the distance scale between the two data points. The difference between the value of each data point in the local terrain data point set and the value of the central data point is positively combined with the result of the distance scale corresponding to each data point, and recorded as the change distance between each data point and the central data point; positive combination refers to combining multiple independent variables in a way that enhances the overall effect; The average value of the corresponding change distances of all data points in the local terrain data point set is recorded as the terrain data distribution value of the central data point of the local terrain data point set.

5. The data cleaning method for national land space planning data according to claim 1, characterized in that: The horizontal interval threshold is: the mean value of all the local distances corresponding to the horizontal change data point sequence.

6. A data cleaning system for national land space planning data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, it implements the steps of a data cleaning method for national land space planning data as described in any one of claims 1-5.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements a data cleaning method for national land space planning data as described in any one of claims 1 to 5.

Images