CN112579688B - Mining method, device, equipment and medium of spatial association rule - Google Patents
Mining method, device, equipment and medium of spatial association rule Download PDFInfo
- Publication number
- CN112579688B CN112579688B CN202011465851.5A CN202011465851A CN112579688B CN 112579688 B CN112579688 B CN 112579688B CN 202011465851 A CN202011465851 A CN 202011465851A CN 112579688 B CN112579688 B CN 112579688B
- Authority
- CN
- China
- Prior art keywords
- shoreline
- land
- change
- change information
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a mining method of a spatial association rule, a mining device of the spatial association rule, electronic equipment and a computer readable storage medium. The excavating method comprises the following steps: processing the land change information and the shoreline change information to generate a plurality of combined grid units and shoreline change strengths; establishing a model operation decision table based on the multiple combined grid units and the variation intensity of the shoreline; mining the model operation decision table to obtain a spatial association rule; the method for processing the land change information and the shoreline change information to generate a plurality of combined grid units and shoreline change strengths comprises the following steps: carrying out fan-shaped gridding division on the land change information to generate a plurality of sample grid units; a land change strength for each of the plurality of sample grid cells is determined.
Description
Technical Field
The present invention relates to the field of geographic information technologies, and in particular, to a method and an apparatus for mining spatial association rules, an electronic device, and a computer-readable storage medium.
Background
In view of the influence of the development of shipping on the space exploitation pattern, in the prior art, there is a research method of a coastal land exploitation space sequence model based on association rules, which obtains the arrangement order of land types in various land and sea directions by simplifying a coastal zone into adjacent lines perpendicular to a coastline (i.e., a shoreline). However, there are actually several limitations to be further improved in the above research methods in the prior art, which are as follows:
1) Firstly, because the existing method mainly focuses on the static state of the land utilization type, only focuses on excavating the sea-land direction land type sequence of the coastal region at a certain time point, and cannot reflect the dynamic states of land change, conversion and the like in time sequence;
2) Furthermore, the sample segmentation approach employed by the prior art method is to use the land type in the longitudinal through-area of the line from sea to land. Due to the complex and various bank line trends of the coastal zones, gaps and overlapping (overlapping) of lines perpendicular to the bank lines inevitably occur in the direction extending towards the inland, the overlapped parts need to spend a large amount of time for removing repeated samples, and the gaps among the lines lead the sample segmentation mode to be incapable of completely covering all the land in the area, so that the land type information is lost.
Disclosure of Invention
Technical problem to be solved
The invention provides a mining method of a spatial association rule, a mining device of the spatial association rule, electronic equipment and a computer readable storage medium, and aims to solve the technical problems that dynamic conditions such as time sequence land change and conversion cannot be reflected by a research method of a coastal land utilization spatial sequence model in the prior art, gaps and overlapping inevitably occur in the extending direction of a line to the inland, the processing efficiency is low, land type information is lost and the like.
(II) technical scheme
One aspect of the embodiments of the present invention provides a method for mining a spatial association rule, where the method includes: processing the land change information and the shoreline change information to generate a plurality of combined grid units and shoreline change strengths; establishing a model operation decision table based on the multiple combined grid units and the variation intensity of the shoreline; mining the model operation decision table to obtain a spatial association rule; wherein, in processing land change information and shoreline change information and generating a plurality of merging grid units and shoreline change strengths, the method comprises the following steps: carrying out fan-ring grid division on the land change information to generate a plurality of sample grid units; a land change strength for each of the plurality of sample grid cells is determined.
According to the embodiment of the invention, before processing the land change information and the shoreline change information, the method further comprises the following steps: generating land change information based on the land cover information; and generating the shoreline change information based on the quay shoreline information.
According to an embodiment of the present invention, in the fan-ring meshing the land change information to generate a plurality of sample grid cells, includes: vectorizing the regional shoreline of the land change information in a direction parallel to the shoreline to obtain vectorized data; generating a plurality of column buffers from the coastal regions to the inland at preset intervals based on the vectorized data; constructing a sector ring fitting the landform of the shoreline according to the plurality of column buffer areas; and rotationally dividing the fan ring to obtain a plurality of sample grid units.
According to an embodiment of the present invention, in determining the land change strength of each of a plurality of sample grid cells, comprises: obtaining a land change rate f of each sample grid cell according to the total area s0 of each sample grid cell and the land change area s1 in each sample grid cell, wherein the land change rate f comprises the following steps: f = s1/s0, f ∈ [0,1]; and according to the land change rate f, acquiring the land change strength of each sample grid unit by a natural breakpoint method.
According to the embodiment of the present invention, in processing the land change information and the shoreline change information to generate a plurality of merged grid cells and shoreline change strengths, the method further includes: merging the plurality of sample grid units according to a grid merging rule to generate a plurality of merged grid units; the grid merging rule is that when one sample grid unit and at least one other sample grid unit in the plurality of sample grid units are positioned in the same unit row, adjacent in spatial position and same in land change intensity, merging between the one sample grid unit and the at least one other sample grid unit is realized to generate one merged grid unit in the plurality of merged grid units; the merging grid cells are a sequence of samples in the same vertical shoreline direction.
According to the embodiment of the present invention, in processing the land change information and the shoreline change information to generate a plurality of merged grid cells and shoreline change strengths, the method further includes: according to the total regional shoreline length a0 and the regional shoreline change length a1 of the shoreline change information, acquiring a shoreline change rate d of the shoreline change information, wherein the method comprises the following steps: d = a1/a0, d ∈ [0,1]; and acquiring the shoreline change strength by a natural breakpoint method according to the shoreline change rate d.
According to an embodiment of the present invention, the model operation decision table is: { L m ，D n D n D n \8230; }, wherein L m Is shoreline variation intensity, m is grade number of shoreline variation intensity, D n The land change intensity is n, and the grade serial number of the land change intensity is n.
According to the embodiment of the invention, mining the model operation decision table to obtain the spatial association rule comprises the following steps: mining the model operation decision table through an Apriori algorithm to obtain a spatial association rule.
According to an embodiment of the invention, the excavation method further comprises: and judging a preset minimum support threshold and a preset minimum confidence threshold of the spatial association rule to determine that the spatial association rule is a strong association rule.
Another aspect of the embodiments of the present invention provides a mining apparatus for spatial association rules, so as to implement the foregoing method.
Another aspect of an embodiment of the present invention provides an electronic device, including one or more processors and a storage device; the storage device is used for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method described above.
Another aspect of the embodiments of the present invention provides a computer-readable storage medium having stored thereon executable instructions, which when executed by a processor, cause the processor to implement the above-mentioned method.
Another aspect of embodiments of the present invention provides a computer program comprising computer executable instructions for implementing a method as above when executed.
(III) advantageous effects
The invention provides a mining method of a spatial association rule, a mining device of the spatial association rule, electronic equipment and a computer readable storage medium. The excavation method comprises the following steps: processing the land change information and the shoreline change information to generate a plurality of combined grid units and shoreline change strengths; establishing a model operation decision table based on the multiple combined grid units and the variation intensity of the shoreline; mining the model operation decision table to obtain a spatial association rule; wherein, in processing land change information and shoreline change information and generating a plurality of merging grid units and shoreline change strengths, the method comprises the following steps: carrying out fan-ring grid division on the land change information to generate a plurality of sample grid units; a land change strength is determined for each of the plurality of sample grid cells. Therefore, by the mining method provided by the embodiment of the invention, an association rule model expressing the spatial relationship between the shoreline and the land change can be constructed, the spatial association of the port shoreline change, the land conversion and the development intensity spatial layout is mined, and the influence of the shipping development on the spatial development utilization mode is revealed.
Drawings
FIG. 1 is a flow diagram that schematically illustrates a mining method for spatial association rules, in accordance with an embodiment of the present invention;
FIG. 2 schematically illustrates a flow chart of generating a plurality of merged grid cells and shoreline variation strengths in an embodiment of the present invention;
FIG. 3 schematically illustrates a sample grid cell layout for fan-annular meshing according to an embodiment of the present invention;
FIG. 4 is a diagram schematically illustrating a merged grid cell layout corresponding to land variation strengths in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating the component architecture of a mining device for spatial association rules, in accordance with an embodiment of the present invention;
fig. 6 schematically shows a component architecture of an electronic device suitable for implementing the above method in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It is to be understood that such description is merely illustrative and not intended to limit the scope of the present invention. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.). In those instances where a convention analogous to "at least one of A, B, or C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.).
The mining method of the spatial association rule of the embodiment of the invention is to further acquire the changed land information by analyzing land utilization data of different time sequences in an overlapping manner on the basis of classifying the land types of the research area in a plurality of periods. By means of a space grid dividing method constructed through new research, sample units are cut, the land change rate of each sample grid unit is calculated, and the land development grade (namely land change strength) is determined according to the land change rate. Therefore, the development and construction of the bank vertical grid space association model can be realized, and finally, the association decision table reflecting the port shoreline change and land change strength is substituted into an Apriori algorithm to realize the mining of the space association rule.
The invention provides a mining method of a spatial association rule, a mining device of the spatial association rule, electronic equipment and a computer readable storage medium, and aims to solve the technical problems that dynamic conditions such as time sequence land change and conversion cannot be reflected by a research method of a coastal land utilization spatial sequence model in the prior art, gaps and overlapping inevitably occur in the extending direction of a line to the inland, the processing efficiency is low, land type information is lost and the like.
As shown in fig. 1, an aspect of the embodiment of the present invention provides a mining method for spatial association rules, where the mining method includes steps S101 to S103.
In step S101, land change information and shoreline change information are processed to generate a plurality of merged grid cells and shoreline change strengths;
in step S102, a model operation decision table is established based on the plurality of merged grid cells and the shoreline variation strength; and
in step S103, a model operation decision table is mined to obtain a spatial association rule.
As shown in fig. 2, in step S101: the steps of processing the land change information and the shoreline change information to generate a plurality of merged grid cells and shoreline change strengths comprise steps S110a-S120a.
In step S110a, performing fan-ring meshing on the land change information to generate a plurality of sample mesh cells;
in step S120a, the land change strength of each of the plurality of sample grid cells is determined.
The land change information is land change data corresponding to different time, such as land data of a certain coast and related land areas, and land type change data between 2010 and 2020. The land type may relate to developed land, undeveloped land, and the like. For example, a land area in which the land type has not changed in 2010-2020 is an undeveloped land and conversely is a developed land. For the problem that the development site also relates to development strength, the following is referred to.
The land line change information is land line change data corresponding to different times in the land change information, and for example, land line type change data between 2010 and 2020 with respect to the land line data of the certain coast. The shoreline type can design developed shorelines, undeveloped shorelines, and the like. For example, a shoreline in which the type of the shoreline has not changed in 2010-2020 is an undeveloped shoreline, and conversely is a developed shoreline. The developed shoreline and the undeveloped shoreline can comprehensively reflect the development strength of the shoreline, the shoreline development strength can be reflected by a shoreline change rate, the shoreline change rate can be determined by corresponding to the relationship between the developed shoreline and the undeveloped shoreline in a certain time period, and the longer the shoreline change rate is, the longer the developed shoreline is, the higher the shoreline development strength is.
And the merging grid unit is formed by merging the sample grid units according to the corresponding land change information. As shown in fig. 3, the sample grid cell is a unit land area, that is, the target land area is equally divided as much as possible according to the area proportion, wherein the unit land area is the sample grid cell. Accordingly, the merged CELL is 1 sample CELL or a land area formed by merging at least 2 sample CELLs having the same land variation information.
The sample grid cell can realize division according to a fan-shaped annular sample division rule based on relevant data in the land change information. In addition, compared with a simple linear sample unit extraction mode perpendicular to a coastline in the prior art, the sea-land grid sample division method formed by fan-ring segmentation can be closely attached to the geometric shape characteristics of the coastline (especially a wharf area). Moreover, as shown in fig. 3, the grid-shaped sample grid cells are mutually embedded in the adjacent structures, so that overlapping or gaps are not generated, the work of manually removing overlapped samples is omitted, and the land information is ensured not to be lost due to the inherent gaps of the linear samples.
Furthermore, the sample grid cells subjected to preliminary grid division are merged, so that the merged grid cells ensure that the samples have good integrity and are not too broken, the data redundancy of the samples is reduced, and the operation efficiency in mining the association rules is improved.
Therefore, according to the merged grid unit and the corresponding land line variation strength, an association decision table of the vertical land line variation strength and land development strength sequence association model, namely a model operation decision table, can be determined and established. And mining the model operation decision table by using a corresponding algorithm as a mining protocol to obtain a spatial association rule between the corresponding land-sea land utilization mode and the development intensity, namely the spatial association rule.
Compared with the prior art, the method disclosed by the embodiment of the invention has the advantages that on the basis of calculating the land change rate by superposing the multi-time-sequence land information, the change condition and the intensity of the land in the sea-land direction of the coastal zone in a certain period can be better reflected compared with the method of emphasizing excavation of the land type sequence in the sea-land direction of the coastal zone in a certain period. Moreover, according to a quantitative analysis mode, the mining result of the association rule can objectively reflect the land-to-sea development strength sequence.
The method provided by the embodiment of the invention aims to excavate the correlation between the quayside change of the wharf and the land development intensity sequence in the vertical direction of the quayside change, and further discloses the influence of the development of the port on the urban expansion space structure. The comprehensive driving effect of the port on the city is exerted to the maximum extent, and model method reference is provided for optimizing the industrial structure and achieving the maximum benefit. Meanwhile, reference can be provided for the research of the space incidence relation and the space structure of other areas, such as the function partition mode research of the coastal zone and the like, so that the whole planning and the scientific utilization of the development of the coastal zone are facilitated, and the sea-land overall planning and the sustainable development are realized.
As shown in fig. 1, according to an embodiment of the present invention, at step S101: before the land change information and the shoreline change information are processed, the method further comprises the following steps: generating land change information based on the land cover information; and generating the shoreline change information based on the quay shoreline information.
The land cover information refers to relevant data of natural and artificial vegetation, buildings and other ground surface covers which can be obtained directly or through remote sensing technology observation. The wharf shoreline information refers to intersection line data between a vertical plane and a horizontal plane on the side, close to a ship, of a wharf building and the like, and can be understood as coastal length data of the ship. The land cover information and the wharf shoreline information of different time sequences are based on the remote sensing extraction technology, so that the extraction of the land change information and the shoreline change information can be directly realized, and the repeated description is omitted.
As shown in fig. 2, according to the embodiment of the present invention, at step S110a: performing fan-ring meshing on the land change information to generate a plurality of sample grid cells, including: vectorizing the regional shoreline of the land change information in a direction parallel to the shoreline to obtain vectorized data; generating a plurality of column buffers from the coastal regions to the inland at preset intervals based on the vectorized data; constructing a sector ring fitting the landform of the shoreline according to the plurality of row buffer areas; and rotationally dividing the fan ring to obtain a plurality of sample grid units.
In the embodiment of the invention, in order to construct the spatial association rule model, the researched land area needs to be subjected to grid division based on the land change information. Therefore, division is mainly completed by constructing fan-shaped annular grids conforming to the shape of the coastal zone in accordance with the sea-land distribution condition of the coastal terrain. As shown in fig. 3, the illustrated region is a research region of the embodiment of the present invention, and corresponds to a land region a of land change information. On the basis of vectorization of regional coastlines in the direction of a parallel coastline s (which is an interface line between land and sea), a plurality of buffer areas are generated from coastal areas to inland at preset intervals r, and each buffer area is a row of land areas a, namely a row of buffer areas L. Then, the two ends of the coast of each land area a are perpendicular to the edges of the coastline s to form two radii of a sector ring, the shore line between the two radii is an inner arc of the sector ring, and the outer edge of the outermost peripheral column buffer area L is an outer arc, thereby forming a sector ring conforming to the coastal topography. And finally, making the extension lines of the two semi-radial ocean directions and intersecting, taking the intersection point as a circle center, taking the two radiuses as a starting point and a stopping edge, and rotationally dividing according to a preset degree interval (for example, the preset degree interval is 1.5 degrees), so as to obtain a sample grid unit cell formed by the intersection of the sea-land vertical line and each buffer area. The grid sample unit segmentation method can effectively reserve the space trend of the coastline, can reflect the space adjacency relation of the land development strength, and provides a space with quantitative land development strength for the construction of a space association model of a subsequent sample grid unit.
As shown in fig. 2, in determining the land change strength of each of a plurality of sample grid cells according to an embodiment of the present invention, the method includes: obtaining a land change rate f of each sample grid cell according to the total area s0 of each sample grid cell and the land change area s1 in each sample grid cell, wherein the land change rate f comprises the following steps: f = s1/s0, f ∈ [0,1]; and acquiring the land change strength of each sample grid unit by a natural breakpoint method according to the land change rate f.
The land change strength is obtained according to the change of the variables in the sample grid cell, and the land change strength can determine the grading of the corresponding sample grid cell. Specifically, as shown in fig. 3, after the grid division of the target land area a is implemented, the land utilization type data of two different periods are correspondingly superimposed and analyzed to obtain land change information, and then the land change information is superimposed on the sample grid cell, and the sample grid cell is associated with the land change information therein. And taking the total area s0 of a single sample grid cell as a denominator and the changed land area s1 in the sample grid cell as a numerator, and acquiring the land change rate f of the sample grid cell, wherein f = s1/s0, and f belongs to [0,1]. Finally, the natural breakpoint method is used to determine the land change rate f, and the land change strength of the sample grid unit can be divided into four grades, namely weak (the change rate is less than 16.93%), medium (the change rate is more than or equal to 16.93% ≦ 38.26%), strong (the change rate is more than or equal to 38.26% ≦ 62.88%) and strong (the change rate is more than or equal to 62.88%), and accordingly, reference can be made to the content shown in fig. 4. Wherein, due to the difference of different research areas A, the grading value of the concrete land change intensity can be adjusted according to the actual condition. It should be noted that the natural breakpoint method is based on natural breakpoints inherent in data, and sets boundaries at positions where data values have relatively large differences, so as to identify hierarchical or hierarchical intervals of the data. The natural breakpoint method can be used for grading different land change rates most appropriately, so that the difference between all levels is maximized, and the strength of land utilization change, namely the land development degree, is objectively distinguished.
According to an embodiment of the present invention, in step S101: in processing land change information and bank line change information to generate a plurality of merged grid units and bank line change strengths, the method further comprises: step S130a.
In step S130a, merging the plurality of sample grid cells according to a grid merging rule to generate a plurality of merged grid cells; the grid merging rule is that when one sample grid unit and at least one other sample grid unit in the plurality of sample grid units are positioned in the same unit row, adjacent in spatial position and same in land change intensity, merging between the one sample grid unit and the at least one other sample grid unit is realized to generate one merged grid unit in the plurality of merged grid units; the merging grid cells are a plurality of sample sequences in the same vertical shoreline direction.
As shown in fig. 3 and 4, in order to merge the sample grid CELLs in the vertical shoreline direction to form a merged grid CELL, the merged grid CELL group is formed as a sequence of a model operation decision table for association rule mining, and meanwhile, in order to reduce data redundancy and maintain the validity of the sample information, the sample grid CELLs in the same row H in the vertical shoreline direction with the same land variation intensity level need to be merged. Specifically, the method can be performed according to the following grid merging rules:
(1) the method comprises the following steps One sample grid unit and at least one other sample grid unit in the plurality of sample grid units to be combined are positioned in the same row H and adjacent to each other in spatial position;
(2) the levels of the land change strengths of the sample grid units to be combined are the same;
the number of sample grid CELLs that can be merged is not limited, that is, if 3 or more consecutive sample grid CELLs adjacent to each other appear, all of the CELLs can be merged into one merged grid CELL as long as the two merging conditions are met. Fig. 4 is a schematic diagram showing the distribution of land variation intensity after merging.
And finally, taking at least one merged grid CELL on the same vertical shoreline in the direction from the sea to the land as a group of merged grid CELL sequences, and constructing a model related to the vertical shoreline variation intensity and the land development intensity sequence, namely a model operation decision table.
According to an embodiment of the present invention, in step S101: the step S110b and the step S120b are further included in processing the land change information and the shoreline change information to generate a plurality of merged grid cells and shoreline change strengths.
In step S110b, a land line change rate d of the land line change information is obtained according to the total regional land line length a0 and the regional land line change length a1 of the land line change information, which includes: d = a1/a0, d ∈ [0,1];
in step S120b, the shoreline variation intensity is obtained by the natural breakpoint method according to the shoreline variation rate d.
The grade of the corresponding shoreline can be determined according to the acquisition of the shoreline change information in the total length of the shoreline. Specifically, as shown in fig. 3 and 4, land utilization data of different time sequences are analyzed in a superposition manner to obtain land line change information of a change time sequence, and a quotient of a change length a1 of each changed region land line and a total length a0 of the region land line is used to obtain a land line change rate d, d = a1/a0, and d belongs to [0,1]. And then, determining the variation intensity of the shoreline according to the change rate d of the shoreline by a natural breakpoint method, wherein the variation intensity of the shoreline can be classified into four grades of weak variation (the variation rate is more than or equal to 0% and less than or equal to 17.35%), medium variation (the variation rate is more than 17.35% and less than or equal to 32.14%), strong variation (the variation rate is more than 32.14% and less than or equal to 55.6%) and strong variation (the variation rate is more than or equal to 55.6%). Due to the difference of different shorelines Sde, the grading value of the specific shoreline variation intensity can be adjusted according to the actual situation. It should be noted that direct classification of the shoreline change rate of the shoreline s can be realized by the natural breakpoint method, so that the shoreline development strength of the shoreline of the corresponding area a, that is, the magnitude of the shoreline development degree, is objectively defined.
According to the embodiment of the invention, the model operation decision table is: { L m ，D n D n D n \8230; }, wherein L m Is the shoreline variation intensity, m is the grade number of the shoreline variation intensity, D n The land change intensity is n, and the grade serial number of the land change intensity is n.
In particular, wherein the shoreline varies in intensity L m Representing the percentage of the ratio of the length of the change through the code head shoreline within a line interval to the total length of the shoreline. m represents the serial number of the grade of the variation intensity of the shore line, can be respectively 1 grade, 2 grade, 3 grade and 4 grade, and respectively represents weak grade, medium grade, strong grade and extremely strong grade, namely the value of m is one of {1,2,3,4 }. n represents the grade serial numbers of the land change strength D, and is respectively 1,2,3 and 4 grades, namely weak, medium, strong and extremely strong grades, namely the value of n is also one of {1,2,3,4 }. For example, if the shoreline change level is "strong" in the same sample strip direction, and the shoreline is "strong", "medium", or "extremely strong" in the order corresponding to the land development intensity from the sea to the land direction, the data form of the shoreline substituted into the mining algorithm is { L } 3 ，D 3 D 2 D 4 }. Wherein, L is 3 And D 3 D 2 D 4 Viewed as one term each, then the sample { L } 3 ，D 3 D 2 D 4 The method can be regarded as a 2-term set, all samples are substituted into the mining algorithm in a two-term set mode, effective information contained in data cannot be lost, meanwhile, the algorithm can be further simplified, and data mining efficiency is improved.
According to the embodiment of the invention, mining the model operation decision table to obtain the spatial association rule comprises the following steps: and mining the model operation decision table through an Apriori algorithm to obtain a spatial association rule.
The Apriori algorithm is a multi-iteration association rule mining method for searching layer by layer, and a larger set is formed by combining item sets meeting the minimum support degree from a single element item set. Multiple iterations are needed in the mining process of the model operation decision table through an Apriori algorithm, and all items in the database are obtained in the first iteration to form a candidate item set C 1 Then according to the minimum support degree at C 1 Find out the conforming conditionsThe items of (A) form a frequent item set L 1 . After k iterations, the k iteration is performed by a frequent (k-1) item set L k-1 Generating a set of candidate k-terms C by performing self-join k Then traversing the database to obtain C k The support degree of each item set, and finally, a frequent k item set L is selected according to the minimum support degree k Therefore, the spatial association rule of the invention can be mined.
Since the prior art fails to determine the specific gravity of different land types on a single vertical shoreline strip, land types with very little specific gravity in a partial sequence may still be present in the mining results of the association rules. Although the relative sequential position of the land types occupying a very small proportion on the sequence is an objective fact, due to the very small proportion, whether the land types have correlation between adjacent classes on the same sequence or not and whether the research on the land types of the regions is meaningful or not need to be judged subsequently.
Specifically, mining of the spatial association rule refers to a process of acquiring a meaningful land change association relationship from a large land change data set, namely identifying a frequently occurring attribute value set (also called a Frequent Item set) from the data set, and then creating and describing the spatial association rule by using the obtained Frequent set. The key point of the mining technology is to acquire an item set which is not less than the minimum support degree in a data set and then acquire frequent item set generation rules. Only the spatial association rule exceeding the preset support degree and confidence degree threshold value is the strong association rule, otherwise, the strong association rule is removed in the stage of pruning branches, and the mined spatial association rule has no practical significance. The item set with the support degree greater than the minimum support degree is called a frequent item set, and otherwise, the item set is a non-frequent item set.
The support S refers to the probability of the simultaneous occurrence of the item sets A and B in all the transactions, and the expression is as follows:
Support(A＝＞B)＝P(A∪B)
the credibility C refers to the proportion of the transaction A in B on the premise that A occurs, and the expression is as follows:
Confidence(A＝＞B)＝P(B|A)
because the proportion of different land types on a single vertical shoreline strip cannot be accurately calculated in the prior art, for the land types with extremely small proportion of partial occupied area, whether the sequence relation of the land types presented by the strip is real and objective or not needs to be deduced or further verified, and whether the actual significance of the extracted partial association rules is questioned or not is still questioned;
according to an embodiment of the invention, the excavation method further comprises: and judging a preset minimum support threshold and a preset minimum confidence threshold of the spatial association rule to determine that the spatial association rule is a strong association rule.
In the embodiment of the invention, the constructed model operation decision table is mined by an Apriori algorithm, and finally, the rule which accords with the support degree and the confidence coefficient threshold set by a user is a strong association rule. When the minimum support threshold is set to 2% to 5% and the minimum confidence is set to 20% to 25%, it is possible to effectively determine whether the mined spatial association rule is a strong association rule. The specific values of the minimum support threshold and the preset minimum confidence threshold are adjusted according to actual conditions due to differences of different research areas. Therefore, whether the mined spatial association rule has practical significance can be directly judged, and the effectiveness of the spatial association rule is further improved.
As shown in fig. 5, another aspect of the embodiment of the present invention provides a mining apparatus 500 for spatial association rules to implement the foregoing method. The mining device 500 may include an information processing module 510, a model building module 520, and a rule mining module 530. The information processing module 510 is configured to process the land change information and the shoreline change information to generate a plurality of merged grid units and shoreline change strengths; the model building module 520 is configured to build a model operation decision table based on the multiple merged grid units and the shoreline variation strength; and a rule mining module 530 is used for mining the model operation decision table to obtain the spatial association rule.
It should be noted that the excavating device 500 according to the embodiment of the present invention is used to implement the above-mentioned method, and is not described herein again.
In summary, the mining method for the spatial association rule according to the embodiment of the present invention can at least achieve the following technical effects:
(1) In order to reflect the strength characteristics of the time sequence change of the land development, the land development strength is graded on the basis of calculating the land change rate by superposing the multi-time sequence land information. Compared with the prior art which focuses on digging the sea-land direction land type sequence of the coastal region in a certain period, the method can better reflect the change condition and intensity of the sea-land direction land of the coastal region in a certain period.
(2) The method can better adapt to an Apriori association rule algorithm and realize association rule mining of the landform characteristics of the wharf area. Based on the sea-land grid sample division formed by fan-ring-shaped division, compared with a simple linear sample extraction method perpendicular to the coastline in the prior art, the sample division method taking the fan-ring-shaped as the basic unit can be closely attached to the geometrical shape characteristics of the coastline (especially a wharf area). The grid-shaped unit neighborhood structures are mutually embedded, so that overlapping or gaps cannot be generated, the work of manually removing overlapped samples is omitted, and the land information cannot be lost due to the inherent gaps of the linear samples.
(3) In addition, the adjacent sample grid units in the same vertical shoreline direction and with the same land development strength are combined, so that the samples are ensured to have good integrity and are not too broken, the data redundancy of the samples is reduced, and the operation efficiency in mining the association rules is improved.
(4) The land utilization change rate of the grid cells is determined by making a quotient of the changed land area in the sample grid cells and the total area of the sample grid cells (namely, quantitative analysis is realized), so that the mining result of the spatial association rule can objectively reflect the land-sea development intensity sequence. In the prior art, the proportion of different land types on a single vertical shoreline strip cannot be determined, and the direct judgment on whether the excavated spatial association rule has practical significance can be realized, so that the effectiveness of the spatial association rule is further improved.
(5) Finally, the spatial association rule can reflect the correlation between the variation of the digging wharf shoreline and the land development intensity sequence vertically, further reveals the influence of the development of the port on the urban expansion space structure, gives full play to the comprehensive driving effect of the port on the city to the greatest extent, and provides a model method reference for optimizing the industrial structure and realizing the maximum benefit. Meanwhile, reference can be provided for the research of the space incidence relation and the space structure of other areas, for example, the research of a functional partition mode of the coastal zone and the like, and the method is favorable for the overall planning and scientific utilization of the development of the coastal zone and the overall planning and sustainable development of sea and land.
As shown in fig. 6, another aspect of the present invention provides an electronic device 600, including: one or more processors and storage for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the above-described method. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, an electronic device 600 according to an embodiment of the present invention includes a processor 601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. Processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 601 may also include on-board memory for caching purposes. Processor 601 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the present invention.
In the RAM 603, various programs and data necessary for the operation of the apparatus 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of the method flow according to the embodiments of the present invention by executing programs in the ROM 602 and/or RAM 603. It is to be noted that the programs may also be stored in one or more memories other than the ROM 602 and RAM 603. The processor 601 may also perform various operations of method flows according to embodiments of the present invention by executing programs stored in the one or more memories.
According to an embodiment of the present invention, the method flow according to an embodiment of the present invention may be implemented as a computer software program. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable storage medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program, when executed by the processor 601, performs the above-described functions defined in the system of the embodiment of the present invention. The above described systems, devices, apparatuses, modules, units, etc. may be implemented by computer program modules according to embodiments of the present invention.
Another aspect of embodiments of the present invention provides a computer-readable storage medium storing computer-executable instructions for implementing the method as described above when executed.
The computer-readable storage medium of the present invention may be contained in the apparatus/device/system described in the above-described embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement a method according to an embodiment of the invention.
According to embodiments of the present invention, the computer readable storage medium may be a non-volatile computer readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present invention, a computer-readable storage medium may include the above-described ROM 602 and/or RAM 603 and/or one or more memories other than the ROM 602 and RAM 603.
Another aspect of embodiments of the present invention provides a computer program comprising computer executable instructions for implementing a method as described above when executed.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be appreciated by a person skilled in the art that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present invention are possible, even if such combinations or combinations are not explicitly recited in the present invention. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present invention may be made without departing from the spirit and teachings of the invention. All such combinations and/or associations are within the scope of the present invention.
So far, the embodiments of the present invention have been described in detail with reference to the accompanying drawings.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only examples of the present invention, and should not be construed as limiting the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A mining method of spatial association rules is characterized by comprising the following steps:
processing the land change information and the shoreline change information to generate a plurality of combined grid units and shoreline change strengths;
establishing a model operation decision table based on the plurality of combined grid units and the variation intensity of the shoreline; and
mining the model operation decision table to obtain the spatial association rule;
wherein, in the processing of the land change information and the shoreline change information to generate a plurality of merged grid units and shoreline change strengths, the method comprises the following steps:
performing fan-ring grid division on the land change information to generate a plurality of sample grid units;
determining a land change strength for each of the plurality of sample grid cells;
wherein, in the fanning a circular grid of the land change information to generate a plurality of sample grid cells, comprising:
vectorizing the regional shoreline of the land change information in a direction parallel to the shoreline to obtain vectorized data;
generating a plurality of column buffer areas from the coastal areas to the inland at preset intervals based on the vectorized data, wherein each column buffer area is a column of the land area corresponding to the land change information;
according to a plurality of buffer areas of being listed as, construct the fan ring shape of laminating shoreline topography, wherein include: constructing a sector ring shape fitting the landform of the shoreline by using two ends of the shoreline of each land area to be vertical to the edges of the shoreline to form two radii of the sector ring shape, using the shoreline between the two radii as an inner arc of the sector ring shape and using the outer edge of the outermost peripheral row buffer zone as an outer arc;
rotationally dividing the fan-shaped ring to obtain the plurality of sample grid cells, wherein the step of rotationally dividing the fan-shaped ring comprises the following steps: and making extension lines of the two semi-radial ocean directions intersect, taking the intersection point as a circle center, taking the two radiuses as a starting edge and a stopping edge, and rotationally dividing according to a preset degree interval to obtain a sample grid unit formed by the intersection of the ocean-land vertical line and each buffer area.
2. The excavation method of claim 1, further comprising, prior to processing the land change information and the shoreline change information:
generating the land change information based on land cover information; and
and generating the shoreline change information based on the wharf shoreline information.
3. The excavation method of claim 1, including, in determining the land change strength of each of the plurality of sample grid cells:
obtaining a land change rate f of each sample grid cell according to the total area s0 of each sample grid cell and the land change area s1 in each sample grid cell, wherein the method comprises the following steps: f = s1/s0, f ∈ [0,1];
and acquiring the land change strength of each sample grid unit by a natural breakpoint method according to the land change rate f.
4. The mining method of claim 3, wherein in the processing land change information and shoreline change information to generate a plurality of merged grid cells and shoreline change strengths, further comprising:
merging the plurality of sample grid units according to a grid merging rule to generate a plurality of merged grid units;
wherein the grid merging rule is to implement merging between one sample grid cell and at least one other sample grid cell when the one sample grid cell and the at least one other sample grid cell are located in the same cell row, adjacent in spatial position, and same in land variation strength, so as to generate one merged grid cell of the multiple merged grid cells;
the merged grid cells are a sequence of samples in the same vertical shoreline direction.
5. The mining method of claim 2, wherein in the processing the land change information and the shoreline change information to generate the plurality of merged grid cells and the shoreline change strengths, further comprising:
according to the total length a0 of the regional shoreline and the change length a1 of the regional shoreline of the shoreline change information, obtaining the shoreline change rate d of the shoreline change information, wherein the shoreline change rate d comprises: d = a1/a0, d ∈ [0,1];
and acquiring the shoreline change strength by a natural breakpoint method according to the shoreline change rate d.
6. Excavation according to claim 1The method is characterized in that the model operation decision table is as follows: { L m ，D n D n D n \8230; }, wherein L m Is the shoreline variation intensity, m is the grade serial number of the shoreline variation intensity, D n The land change intensity is n, and the grade serial number of the land change intensity is n.
7. The mining method according to claim 1, wherein the mining the model operation decision table to obtain the spatial association rule comprises:
and mining the model operation decision table through an Apriori algorithm to obtain the spatial association rule.
8. The excavation method according to claim 1, further comprising:
and judging a preset minimum support degree threshold value and a preset minimum confidence degree threshold value on the spatial association rule to determine that the spatial association rule is a strong association rule.
9. A mining device for spatial association rules to implement the method of any one of claims 1 to 8.
10. An electronic device, comprising:
one or more processors;
a storage device to store one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-8.
11. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011465851.5A CN112579688B (en) | 2020-12-11 | 2020-12-11 | Mining method, device, equipment and medium of spatial association rule |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011465851.5A CN112579688B (en) | 2020-12-11 | 2020-12-11 | Mining method, device, equipment and medium of spatial association rule |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112579688A CN112579688A (en) | 2021-03-30 |
| CN112579688B true CN112579688B (en) | 2022-10-18 |
Family
ID=75132209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011465851.5A Active CN112579688B (en) | 2020-12-11 | 2020-12-11 | Mining method, device, equipment and medium of spatial association rule |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112579688B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107229919A (en) * | 2017-06-05 | 2017-10-03 | 深圳先进技术研究院 | It is a kind of to be used for the ecological key element processing method and system of complicated ecological littoral zone |
| CN107679703A (en) * | 2017-09-08 | 2018-02-09 | 天津大学 | A kind of coastal ecological safety evaluation method |
| CN108550174A (en) * | 2018-03-08 | 2018-09-18 | 中国地质大学（武汉） | A kind of coastline Super-resolution Mapping and system based on half global optimization |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095591B (en) * | 2015-08-11 | 2017-12-15 | 武汉大学 | A kind of multiple dimensioned urban sprawl correlation rule extracting method |
| CA3001119C (en) * | 2015-11-09 | 2020-09-29 | Landmark Graphics Corporation | Modelling complex geological sequences using geologic rules and paleographic maps |
| CN111339427B (en) * | 2020-03-23 | 2022-12-20 | 卓尔智联(武汉)研究院有限公司 | Book information recommendation method, device and system and storage medium |
-
2020
- 2020-12-11 CN CN202011465851.5A patent/CN112579688B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107229919A (en) * | 2017-06-05 | 2017-10-03 | 深圳先进技术研究院 | It is a kind of to be used for the ecological key element processing method and system of complicated ecological littoral zone |
| CN107679703A (en) * | 2017-09-08 | 2018-02-09 | 天津大学 | A kind of coastal ecological safety evaluation method |
| CN108550174A (en) * | 2018-03-08 | 2018-09-18 | 中国地质大学（武汉） | A kind of coastline Super-resolution Mapping and system based on half global optimization |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112579688A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gandini et al. | Climate change risk assessment: A holistic multi-stakeholder methodology for the sustainable development of cities | |
| Lamelas et al. | Doline probability map using logistic regression and GIS technology in the central Ebro Basin (Spain) | |
| Chazal et al. | Gromov-Hausdorff approximation of filament structure using Reeb-type graph | |
| CN104635262B (en) | A kind of positive reversed fault isopleth automatic generation method based on extended rectangular grid | |
| CN104156525A (en) | Method for improving storm surge disaster risk predication accuracy | |
| CN111582572A (en) | Ecological protection, restoration and planning zoning method for lakes and grasses in mountain and water forest fields | |
| CN111461046B (en) | Automatic coast erosion and siltation identification method and device based on shoreline data | |
| Choi et al. | Computation of tsunamis in the East (Japan) Sea using dynamically interfaced nested model | |
| Chang et al. | Selection of pulse-like ground motions with strong velocity-pulses using moving-average filtering | |
| Wang et al. | Hazard assessment of storm surges and concomitant waves in Shandong Peninsula based on long-term numerical simulations | |
| CN112579688B (en) | Mining method, device, equipment and medium of spatial association rule | |
| Zhang et al. | Landslide susceptibility mapping using novel hybrid model based on different mapping units | |
| KR20140093830A (en) | Three-dimensional virtual reality fluid simulation system and method for river of flooding | |
| Debese et al. | Extraction of sandy bedforms features through geodesic morphometry | |
| Chen et al. | Computational morphology of debris and alluvial fans on irregular terrain using the visibility polygon | |
| CN112231423A (en) | Fault structure automatic recovery method and device based on geological map | |
| Jones | Solid modelling of earth masses for applications in geotechnical engineering | |
| Abramov et al. | Digital technologies development for maritime activities oceanographic support in Arctic and Subarctic | |
| Susiloningtyas et al. | Dynamic System Model of Land Use Affected by Sea Level Rise in the Coastal Area of Bengkulu City, Indonesia | |
| Gao et al. | Mathematical Interpolation and Correction of Three-Dimensional Modelling of High-Speed Railway. | |
| JP3860138B2 (en) | Debris flow warning area generation device and program thereof | |
| Yan et al. | Association mining of coastline change and land use patterns to enhance conservation | |
| Flanagin et al. | Hydraulic splines: A hybrid approach to modeling river channel geometries | |
| CN116467790B (en) | Discrimination method for optimizing plane layout of breakwater in half-shelter harbor area | |
| Igigabel et al. | Guidelines for Analysing Coastal Flood Protection Systems After a Submersion. Water 2022, 14, 15 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |