Classified storage method for urban and rural planning information data

Abstract

The invention relates to the technical field of big data, and discloses an urban and rural planning information data classified storage method, which comprises the following steps: acquiring urban and rural planning information data which is unstructured data; the urban and rural planning information data comprises traditional planning data, urban perception data and social network data; processing the urban and rural planning information data by adopting an improved decision tree model to realize feature classification of unstructured data; performing data anomaly identification on the classified urban and rural planning information data by adopting a decision tree classification algorithm, and outputting abnormal data; and performing block storage on the urban and rural planning information data after the abnormal data is removed. According to the block storage method based on the decision tree model, feature classification, anomaly recognition and block storage are carried out on urban and rural planning information data, the storage capacity of unstructured data is improved, the storage pressure of the unstructured data is reduced, and high-quality unstructured data storage is achieved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a classification storage method for urban and rural planning information data. Background Art

[0002] The promotion and application of mobile Internet and Internet of Things technologies have generated a large amount of data that reflects the characteristics of urban social and economic activities in real time, including power grid operation, road speed and traffic, and even the location and behavior of each person. These huge and complex urban perception big data can be used for urban and rural planning, construction and management, thus forming urban and rural planning information data. Urban and rural planning information data is characterized by complex types, huge volume and long time span.

[0003] Urban and rural planning information data is a kind of unstructured data. Unstructured data refers to data with irregular or incomplete data structure, no pre-defined data, and data that is not convenient to represent using the two-dimensional logical table of the database. In the context of the in-depth development of data processing technology, the amount of network data has increased significantly, and the data format and structure have also diversified, which has increased the difficulty of storing unstructured data. Solving the problem of unstructured data storage can significantly improve its management capabilities and application performance.

[0004] The existing method uses a compressed sensing model to achieve data storage and reduces storage space through an orthogonal matching pursuit algorithm. However, the data stored in this model contains a large amount of redundant data, which has a negative impact on data storage. At the same time, the cloud storage method has poor adaptability in actual application and low data compression accuracy. The distributed data storage method does not consider the unstructured characteristics of the data, and the search performance after data storage is poor. It can be seen that there is no efficient storage method for unstructured data in the existing technology. Summary of the invention

[0005] The present invention provides a classification storage method for urban and rural planning information data, constructs a block storage method based on a decision tree model, and improves the unstructured data storage capacity, reduces the unstructured data storage pressure, and realizes high-quality unstructured data storage by performing feature classification, anomaly identification, and block storage on urban and rural planning information data.

[0006] The present invention provides a classification storage method for urban and rural planning information data, comprising:

[0007] Acquire urban and rural planning information data, wherein the urban and rural planning information data is unstructured data; wherein the urban and rural planning information data includes traditional planning data, urban perception data, and social network data;

[0008] Using an improved decision tree model to process the urban and rural planning information data to achieve feature classification of unstructured data;

[0009] Using a decision tree classification algorithm to identify data anomalies on the classified urban and rural planning information data, and outputting the abnormal data;

[0010] The urban and rural planning information data after removing the abnormal data is stored in blocks.

[0011] Furthermore, the step of using an improved decision tree model to process the urban and rural planning information data to achieve feature classification of unstructured data includes:

[0012] A classification model is constructed using an improved decision tree algorithm to fuzzily classify the characteristics of the urban and rural planning information data;

[0013] The fuzzy directional classification of the urban and rural planning information data set is implemented in the form of finite set merging to obtain the classification index set Λ0; at the same time, the optimization classification is completed through the decision tree scheduling method of the urban and rural planning information data set, and the statistical characteristic information flow of the urban and rural planning information data classification is obtained in the fuzzy hierarchical distribution structure model;

[0014] Automatically classify the urban and rural planning information data features in N subspaces to obtain subsequences;

[0015] Implement finite data set classification for urban and rural planning information data, and classify the characteristics of urban and rural planning information data within a finite domain based on the irregular triangulated network model;

[0016] The coherent distribution source characteristics of the urban and rural planning information data set are extracted, the fuzzy expansion function of the urban and rural planning information data characteristics is obtained, and based on this, a decision tree bifurcation model of the main characteristics of the urban and rural planning information data is constructed to complete the classification of the urban and rural planning information data characteristics.

[0017] Furthermore, the step of using the improved decision tree algorithm to construct a classification model to perform fuzzy classification on the characteristics of the urban and rural planning data includes:

[0018] If the unstructured data contains n samples, S i,j (t) represents the learning factor of the two-dimensional decision tree classification model:

[0019]

[0020] Among them, s represents the proportion of urban and rural planning information data characteristics, Y i,j (t) represents the estimated conditional probability of the training data set;

[0021] Determine the relevance of fuzzy association parameters:

[0022]

[0023] Among them, a i(t), e (t) They respectively represent the statistical results of optimization detection of urban and rural planning information data and the energy consumption of urban and rural planning information data.

[0024] Furthermore, the step of using a decision tree classification algorithm to identify data anomalies on the classified urban and rural planning information data and outputting the abnormal data includes:

[0025] Construct a binary tree based on minimizing the Gini index, initialize a root node, and put all urban and rural planning information data into this node;

[0026] Select a feature to split so that the child node after the split can reduce the Gini index to the greatest extent. If the stopping condition is met, the split ends;

[0027] For each child node, repeat the previous step until the termination condition is met. When all nodes meet the termination condition, the algorithm ends;

[0028] Output an abnormal data detection report of the urban and rural planning information data.

[0029] Furthermore, the step of selecting a feature for splitting enables the child nodes after the splitting to reduce the Gini index to the greatest extent. If the stopping condition is met, the step of ending the splitting, the Gini index is expressed as:

[0030]

[0031] Among them, Gini(W,K) represents the Gini index, W1 and W2 represent the two parts of the training set data, S represents the training data set, Gini(W1) represents the Gini index of training set 1, and Gini(W2) represents the Gini index of training set 2.

[0032] Furthermore, the step of storing the urban and rural planning information data after removing the abnormal data in blocks includes:

[0033] Data and src represent the unstructured urban and rural planning information data to be input and its file name respectively, and the user terminal inputs the urban and rural planning information data into the stream;

[0034] The urban and rural planning information data is divided into blocks to obtain a set of urban and rural planning information data blocks B in each category = {b0, b1, ..., b m-1}, k urban and rural planning information data block sets F = {f0, f1, ..., f k-1}, and store the coarse unstructured data blocks on the nodes selected by the master node;

[0035] The coarse unstructured data blocks are encoded by using a Vandermonde matrix, and the coarse unstructured data blocks are subdivided;

[0036] The encoded unstructured data blocks are stored on the selected nodes, and new metadata is obtained based on different unstructured data blocks;

[0037] The above process is iterated until no new metadata is generated to complete the block storage of all urban and rural planning information data.

[0038] Furthermore, in the step of encoding the coarse unstructured data block by using the Vandermonde matrix and subdividing the coarse unstructured data block, the matrix equation in the encoding process is:

[0039]

[0040] Where V represents the Vandermonde matrix.

[0041] The present invention also provides a classified storage device for urban and rural planning information data, comprising:

[0042] An acquisition module, used to acquire urban and rural planning information data, wherein the urban and rural planning information data is unstructured data; wherein the urban and rural planning information data includes traditional planning data, urban perception data, and social network data;

[0043] A classification module, used to process the urban and rural planning information data using an improved decision tree model to achieve feature classification of unstructured data;

[0044] An identification module is used to identify data anomalies using a decision tree classification algorithm on the classified urban and rural planning information data, and output the abnormal data;

[0045] The storage module is used to store the urban and rural planning information data in blocks after removing the abnormal data.

[0046] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0047] The present invention also provides a computer-readable storage medium on which a computer program is stored, and the computer program implements the steps of the above method when executed by a processor.

[0048] The beneficial effects of the present invention are:

[0049] The present invention uses an improved decision tree model to process urban and rural planning information data to achieve feature classification of unstructured data; a decision tree classification algorithm is used to identify data anomalies in the classified urban and rural planning information data, and the urban and rural planning information data after the abnormal data is removed is divided into blocks for storage; through the above process, the division accuracy of the unstructured data blocks is significantly improved, and it is guaranteed to the maximum extent that different unstructured data are processed accordingly, thereby improving the unstructured data storage capacity, reducing the unstructured data storage pressure, and achieving high-quality unstructured data storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The figure is a schematic diagram of a method flow according to an embodiment of the present invention.

[0051] Figure 2 FIG. 1 is a schematic diagram of a device structure according to an embodiment of the present invention.

[0052] Figure 3 The figure is a schematic diagram of the internal structure of a computer device according to an embodiment of the present invention.

[0053] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0055] like Figure 1 As shown, the present invention provides a classification storage method for urban and rural planning information data, comprising:

[0056] S1. Acquire urban and rural planning information data, where the urban and rural planning information data is unstructured data; wherein the urban and rural planning information data includes traditional planning data, urban perception data, and social network data;

[0057] The sources of urban and rural planning data are:

[0058] (1) Digitized traditional data and spatial information: such as digitized urban construction archives, vectorized urban historical maps, and information on population, industry, agriculture, and place name censuses. This type of data and information is collected and preserved by various functional departments.

[0059] (2) Urban planning and urban research information mainly utilizes data with geographic coordinates, geographic flow trajectory and flow rate. The new data generated in the Internet era mainly include microblogs with geographic coordinates, electronic map classification points of interest, real-time WeChat location, Dianping commercial outlets, bus and subway card swiping data, etc.

[0060] From the perspective of urban and rural planning big data classification, it includes traditional planning data (statistical yearbook data, remote sensing data, planning survey data, topographic maps, etc.), social network data (urban space theme evaluation, Weibo check-in data, spatiotemporal change data, mobile terminal behavior data, etc.), and urban perception data (open source maps, railway flight schedule data, bus card swiping data, mobile communication positioning data, smart infrastructure acquisition data). With the rapid growth of urban and rural planning big data and the increasing volume of data, the existing data storage methods face the risk of data reliability.

[0061] S2. Processing the urban and rural planning information data using an improved decision tree model to achieve feature classification of unstructured data;

[0062] Step S2 specifically includes:

[0063] S21, using an improved decision tree algorithm to construct a classification model to perform fuzzy classification on the characteristics of the urban and rural planning information data;

[0064] If the unstructured data contains n samples, S i,j (t) represents the learning factor of the two-dimensional decision tree classification model:

[0065]

[0066] Among them, s represents the proportion of urban and rural planning information data characteristics, Y i,j (t) represents the estimated conditional probability of the training data set;

[0067] Determine the relevance of fuzzy association parameters:

[0068]

[0069] Among them, a i (t), e (t) They respectively represent the statistical results of optimization detection of urban and rural planning information data and the energy consumption of urban and rural planning information data.

[0070] S22, implementing fuzzy directional classification of urban and rural planning information data sets in the form of finite set merging to obtain a classification index set Λ0; at the same time, completing optimization classification through a decision tree scheduling method of the urban and rural planning information data sets, and obtaining statistical characteristic information flow of urban and rural planning information data classification in the fuzzy hierarchical distribution structure model;

[0071] S23, automatically classifying the urban and rural planning information data features in the N subspaces to obtain subsequences;

[0072] X=Λ0[X a (0),X a (1),…,X a (N-1)]T

[0073] Use the following formula to describe the decision tree optimization classification nodes x1~x4:

[0074]

[0075] Among them, f θ (X,t),c θ (X,t),f x (X,t),c x (X, t) both represent resource matching sets of unstructured data features; d θ (t) and d x (t) represent the fuzzy hierarchical structure optimization coefficient and the hierarchical structure optimization coefficient respectively.

[0076] S24. Classify the urban and rural planning information data into a limited data set, and classify the characteristics of the urban and rural planning information data within a limited domain based on the irregular triangulated network model to obtain:

[0077]

[0078] Among them, ξ j Indicates the classification result of unstructured data features; d j (k) represents a finite set of feature distributions for unstructured data.

[0079] S25. Extract the coherent distribution source characteristics of the urban and rural planning information data set, obtain the fuzzy expansion function of the urban and rural planning information data characteristics, and use this to construct a main feature decision tree bifurcation model of the urban and rural planning information data to complete the classification of urban and rural planning information data characteristics.

[0080] The fuzzy expansion function is:

[0081]

[0082] The following is the optimal solution for clustering:

[0083]

[0084] Based on the above process, the classification of urban and rural planning information data characteristics is completed.

[0085] S3, using a decision tree classification algorithm to identify data anomalies on the classified urban and rural planning information data, and outputting the abnormal data;

[0086] Step S3 specifically includes:

[0087] S31. Construct a binary tree based on minimization of the Gini index, initialize a root node, and put all urban and rural planning information data into this node;

[0088] S32, select a feature to split so that the child node after the split can reduce the Gini index to the greatest extent. If the stop condition is met, the splitting is terminated;

[0089] The Gini index is expressed as:

[0090]

[0091] Among them, Gini(W,K) represents the Gini index, W1 and W2 represent the two parts of the training set data, S represents the training data set, Gini(W1) represents the Gini index of training set 1, and Gini(W2) represents the Gini index of training set 2.

[0092] S33, for each child node, repeat the previous step until the termination condition is met. When all nodes meet the termination condition, the algorithm ends;

[0093] As described in steps S31-S33 above, the detection and identification of abnormal data of urban and rural planning information data can be regarded as a second-class problem. Among them, the decision tree is a commonly used classification method. First, the decision tree algorithm is organized and can clearly give the basis and conditions for classification, making the results easy to understand and accept. Secondly, the decision tree algorithm combines qualitative and quantitative analysis methods at the same time, taking into account the specific numerical characteristics of the data and incorporating relevant business logic and empirical knowledge. This makes the decision tree more comprehensive and accurate when dealing with practical problems. Furthermore, the decision tree algorithm has a wide range of applicability and can be applied to many different types of data and problems without a large number of adjustments or modifications to the algorithm itself. In the structure of the decision tree model, it usually includes a root node, several internal nodes and several leaf nodes. The root node is the starting point of the entire decision tree, and all data are classified from here. The internal node is the intermediate node in the decision tree, representing a condition or decision point in the classification process. The leaf node is the end node of the decision tree, corresponding to the final classification result. In the scenario of anomaly identification of urban and rural planning information data, leaf nodes can represent normal or abnormal classification results, while internal nodes represent the features or conditions used to distinguish these two types of data.

[0094] The present invention adopts a decision tree classification algorithm to detect and identify abnormalities in urban and rural planning information data, and adopts a top-down exhaustive method to construct a binary tree for classification. Based on the minimization of the Gini index, a binary tree is constructed. On this basis, a feature-based adaptive segmentation algorithm is proposed. The segmentation process continues until a certain termination condition, for example: the correct recognition rate of the training sample reaches a preset threshold, or all features have been used up, such as the above steps S31-S33.

[0095] S34: Output an abnormal data detection report of the urban and rural planning information data.

[0096] The above-mentioned anomaly recognition model based on the decision tree classification algorithm is used to identify anomalies in urban and rural planning information data, and the model is used to output the final recognition result, namely the anomaly data detection report, which lists in detail the information related to the abnormal data detected in the urban and rural planning information data, including the type of abnormal data, the time of occurrence, the scope of impact, and the possible causes.

[0097] S4. The urban and rural planning information data after the abnormal data is removed is stored in blocks.

[0098] Step S4 specifically includes:

[0099] S41, using data and src to represent the unstructured urban and rural planning information data to be input and its file name respectively, and using the user terminal to input the urban and rural planning information data into the stream;

[0100] S42, urban and rural planning information data blocks are divided to obtain urban and rural planning information data block sets B in each category = {b0, b1, ..., b m-1}, k urban and rural planning information data block sets F = {f0, f1, ..., f k-1}, and store the coarse unstructured data blocks on the nodes selected by the master node;

[0101] S43, encoding the coarse unstructured data block by using a Vandermonde matrix, and subdividing the coarse unstructured data block;

[0102] The matrix equation during the encoding process is:

[0103]

[0104] Where V represents the Vandermonde matrix.

[0105] S44, storing the encoded unstructured data blocks on the selected node, and obtaining new metadata based on different unstructured data blocks;

[0106] S45. Iterate the above process until no new metadata is generated to complete the block storage of all urban and rural planning information data.

[0107] As described in the above steps S41-S45, the urban and rural planning information data after feature classification is divided into a number of unstructured data blocks, and the specifications of different data blocks are consistent. m-1} represents the set of unstructured data blocks in each category. The Reed-Solution code block algorithm is used to perform secondary block division on different unstructured data blocks to obtain k unstructured data block sets F = {f0, f1, ..., fk-1}, the specifications of each data block are consistent, where m-1 and k-1 represent the number of unstructured data blocks before and after the Reed code segmentation. In order to improve the coding efficiency, the Vandermonde matrix is ​​used for coding to obtain the check block set B = {b0, b1, ..., b m-k-1}, where there are mk check blocks in total. After the Vandermonde matrix encoding process, the encoded nonlinear data is stored to prevent the master node from generating significant redundant nonlinear data. The selected node only stores a single unstructured data block. According to the relationship between the two, the metadata of the unstructured data stored in blocks is obtained. After the storage of the unstructured data blocks in each node is completed, the metadata will be directly updated to different nodes.

[0108] The present invention uses an improved decision tree model to process urban and rural planning information data to achieve feature classification of unstructured data; a decision tree classification algorithm is used to identify data anomalies in the classified urban and rural planning information data, and the urban and rural planning information data after the abnormal data is removed is divided into blocks for storage; through the above process, the division accuracy of the unstructured data blocks is significantly improved, and it is guaranteed to the maximum extent that different unstructured data are processed accordingly, thereby improving the unstructured data storage capacity, reducing the unstructured data storage pressure, and achieving high-quality unstructured data storage.

[0109] like Figure 2 As shown, the present invention also provides a classification storage device for urban and rural planning information data, comprising:

[0110] Acquisition module 1, used to acquire urban and rural planning information data, wherein the urban and rural planning information data is unstructured data; wherein the urban and rural planning information data includes traditional planning data, urban perception data, and social network data;

[0111] Classification module 2, used for processing the urban and rural planning information data using an improved decision tree model to achieve feature classification of unstructured data;

[0112] Identification module 3, used to identify data anomalies using a decision tree classification algorithm on the classified urban and rural planning information data, and output the abnormal data;

[0113] The storage module 4 is used to store the urban and rural planning information data after removing the abnormal data in blocks.

[0114] In one embodiment, the classification module 2 comprises:

[0115] A fuzzy classification unit, used to construct a classification model using an improved decision tree algorithm to perform fuzzy classification on the characteristics of the urban and rural planning information data;

[0116] The directional classification unit is used to implement the fuzzy directional classification of the urban and rural planning information data set in the form of finite set merging to obtain the classification index set Λ0; at the same time, the optimization classification is completed through the decision tree scheduling method of the urban and rural planning information data set, and the statistical characteristic information flow of the urban and rural planning information data classification is obtained in the fuzzy hierarchical distribution structure model;

[0117] A subsequence unit is used to automatically classify and process the urban and rural planning information data features in N subspaces to obtain subsequences;

[0118] Dataset classification is used to implement limited data set classification of urban and rural planning information data, and classify the characteristics of urban and rural planning information data within a limited domain based on the irregular triangulated network model;

[0119] The feature classification unit is used to extract the coherent distribution source features of the urban and rural planning information data set, obtain the fuzzy expansion function of the urban and rural planning information data features, and use this to construct a main feature decision tree bifurcation model of the urban and rural planning information data to complete the feature classification of the urban and rural planning information data.

[0120] In one embodiment, the fuzzy classification unit includes:

[0121] If the unstructured data contains n samples, S i,j (t) represents the learning factor of the two-dimensional decision tree classification model:

[0122]

[0123] Among them, s represents the proportion of urban and rural planning information data characteristics, Y i,j (t) represents the estimated conditional probability of the training data set;

[0124] Determine the relevance of fuzzy association parameters:

[0125]

[0126] Among them, a i (t), e (t) They respectively represent the statistical results of optimization detection of urban and rural planning information data and the energy consumption of urban and rural planning information data.

[0127] In one embodiment, the identification module 3 includes:

[0128] An initialization unit is used to construct a binary tree based on minimization of the Gini index and initialize a root node to put all urban and rural planning information data into this node;

[0129] The selection unit is used to select a feature for splitting so that the child node after the split can reduce the Gini index to the greatest extent. If the stop condition is met, the splitting is terminated;

[0130] The repeating unit is used to repeat the previous step for each child node until the termination condition is met. When all nodes meet the stopping condition, the algorithm ends;

[0131] An output unit is used to output an abnormal data detection report of the urban and rural planning information data.

[0132] In one embodiment, in the selection unit, the Gini index is expressed as:

[0133]

[0134] Among them, Gini(W,K) represents the Gini index, W1 and W2 represent the two parts of the training set data, S represents the training data set, Gini(W1) represents the Gini index of training set 1, and Gini(W2) represents the Gini index of training set 2.

[0135] In one embodiment, the storage module 4 includes:

[0136] The input unit is used to represent the unstructured urban and rural planning information data to be input and its file name with data and src respectively, and input the urban and rural planning information data into the stream by using the user terminal;

[0137] The block division unit is used for dividing the urban and rural planning information data into blocks to obtain the urban and rural planning information data block set B in each category = {b0, b1, ..., b m-1}, k urban and rural planning information data block sets F = {f0, f1, ..., f k-1}, and store the coarse unstructured data blocks on the nodes selected by the master node;

[0138] A coding unit, used for coding the coarse unstructured data block by using a Vandermonde matrix, and subdividing the coarse unstructured data block;

[0139] A storage unit, used for storing the encoded unstructured data blocks on the selected node, and obtaining new metadata based on different unstructured data blocks;

[0140] The iteration unit is used to iterate the above process until no new metadata is generated, so as to complete the block storage of all urban and rural planning information data.

[0141] In one embodiment, in the encoding unit, the matrix equation in the encoding process is:

[0142]

[0143] Where V represents the Vandermonde matrix.

[0144] The above modules and units are used to execute the corresponding steps in the above-mentioned classification storage method of urban and rural planning information data. The specific implementation method thereof is described in the above-mentioned method embodiment and will not be repeated here.

[0145] like Figure 3 As shown, the present invention also provides a computer device, which can be a server, and its internal structure can be as shown in Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required for the process of the classified storage method of urban and rural planning information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the classified storage method of urban and rural planning information data is implemented.

[0146] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0147] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any one of the above-mentioned classification storage methods for urban and rural planning information data is implemented.

[0148] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0149] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0150] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A classification storage method for urban and rural planning information data, characterized in that: include: Acquire urban and rural planning information data, wherein the urban and rural planning information data is unstructured data; wherein the urban and rural planning information data includes traditional planning data, urban perception data, and social network data; Using an improved decision tree model to process the urban and rural planning information data to achieve feature classification of unstructured data; Using a decision tree classification algorithm to identify data anomalies on the classified urban and rural planning information data, and outputting the abnormal data; The urban and rural planning information data after removing the abnormal data is stored in blocks.

2. The classification storage method of urban and rural planning information data according to claim 1 is characterized in that: The step of using the improved decision tree model to process the urban and rural planning information data to achieve feature classification of unstructured data includes: A classification model is constructed using an improved decision tree algorithm to fuzzily classify the characteristics of the urban and rural planning information data; The fuzzy directional classification of the urban and rural planning information data set is implemented in the form of finite set merging to obtain the classification index set Λ0; at the same time, the optimization classification is completed through the decision tree scheduling method of the urban and rural planning information data set, and the statistical characteristic information flow of the urban and rural planning information data classification is obtained in the fuzzy hierarchical distribution structure model; Automatically classify the urban and rural planning information data features in N subspaces to obtain subsequences; Implement finite data set classification for urban and rural planning information data, and classify the characteristics of urban and rural planning information data within a finite domain based on the irregular triangulated network model; The coherent distribution source characteristics of the urban and rural planning information data set are extracted, the fuzzy expansion function of the urban and rural planning information data characteristics is obtained, and based on this, a decision tree bifurcation model of the main characteristics of the urban and rural planning information data is constructed to complete the classification of the urban and rural planning information data characteristics.

3. The classification storage method of urban and rural planning information data according to claim 2 is characterized in that: The step of using the improved decision tree algorithm to construct a classification model to perform fuzzy classification on the characteristics of the urban and rural planning data includes: If the unstructured data contains n samples, S i,j (t) represents the learning factor of the two-dimensional decision tree classification model: Among them, s represents the proportion of urban and rural planning information data characteristics, Y i,j (t) represents the estimated conditional probability of the training data set; Determine the relevance of fuzzy association parameters: Among them, a i (t), e (t) They respectively represent the statistical results of optimization detection of urban and rural planning information data and the energy consumption of urban and rural planning information data.

4. The classification storage method of urban and rural planning information data according to claim 1 is characterized in that: The step of using a decision tree classification algorithm to identify data anomalies on the classified urban and rural planning information data and outputting the abnormal data includes: Construct a binary tree based on minimizing the Gini index, initialize a root node, and put all urban and rural planning information data into this node; Select a feature to split so that the child node after the split can reduce the Gini index to the greatest extent. If the stopping condition is met, the split ends; For each child node, repeat the previous step until the termination condition is met. When all nodes meet the termination condition, the algorithm ends; Output an abnormal data detection report of the urban and rural planning information data.

5. The classification storage method of urban and rural planning information data according to claim 4 is characterized in that: The step of selecting a feature for splitting is to make the child nodes after splitting reduce the Gini index to the greatest extent. If the stop condition is met, the step of ending the splitting is completed. The Gini index is expressed as: Among them, Gini(W,K) represents the Gini index, W1 and W2 represent the two parts of the training set data, S represents the training data set, Gini(W1) represents the Gini index of training set 1, and Gini(W2) represents the Gini index of training set 2.

6. The classification storage method of urban and rural planning information data according to claim 1 is characterized in that: The step of storing the urban and rural planning information data after removing the abnormal data in blocks comprises: Data and src represent the unstructured urban and rural planning information data to be input and its file name respectively, and the user terminal inputs the urban and rural planning information data into the stream; The urban and rural planning information data is divided into blocks to obtain a set of urban and rural planning information data blocks B in each category = {b0, b1, ..., b m-1 }, k urban and rural planning information data block sets F = {f0, f1, ..., f k-1 }, and store the coarse unstructured data blocks on the nodes selected by the master node; The coarse unstructured data blocks are encoded by using a Vandermonde matrix, and the coarse unstructured data blocks are subdivided; The encoded unstructured data blocks are stored on the selected nodes, and new metadata is obtained based on different unstructured data blocks; The above process is iterated until no new metadata is generated to complete the block storage of all urban and rural planning information data.

7. The classified storage method of urban and rural planning information data according to claim 6 is characterized in that: In the step of encoding the coarse unstructured data block by using the Vandermonde matrix and subdividing the coarse unstructured data block, the matrix equation in the encoding process is: Where V represents the Vandermonde matrix.

8. A classified storage device for urban and rural planning information data, characterized in that: include: An acquisition module, used to acquire urban and rural planning information data, wherein the urban and rural planning information data is unstructured data; wherein the urban and rural planning information data includes traditional planning data, urban perception data, and social network data; A classification module, used to process the urban and rural planning information data using an improved decision tree model to achieve feature classification of unstructured data; An identification module is used to identify data anomalies using a decision tree classification algorithm on the classified urban and rural planning information data, and output the abnormal data; The storage module is used to store the urban and rural planning information data in blocks after removing the abnormal data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images