A monitoring statistical analysis method and device based on parallel clustering

Abstract

The present application relates to a monitoring statistical analysis method and device based on parallel clustering, which obtains the attribute weight set of the monitoring data by setting the weight of the attribute of the monitoring data in the original monitoring data set, obtains multiple monitoring data layers by stratifying the original data set according to the correlation coefficient between the attribute weight sets, obtains multiple first monitoring data cluster centers by performing parallel clustering on each layer, obtains multiple second monitoring data cluster centers by dividing the original data set according to the distance between the monitoring data in the original data set and the first monitoring data cluster center, obtains multiple third monitoring data cluster centers by performing parallel clustering on multiple second monitoring data cluster centers, obtains multiple best monitoring data clusters and best cluster centers by dividing the original data set according to the distance between the original data set and the third monitoring data cluster center, and constructs a model based on the best monitoring data cluster and the best cluster center for statistical analysis. This method can quickly screen the best cluster center in the face of massive data and improve the efficiency of statistical analysis.

Description

Technical Field

[0001] The present application relates to the technical field of data mining, and in particular to a monitoring statistical analysis method and device based on parallel clustering. Background Art

[0002] With the rapid growth of various statistical analysis data, data sources are becoming more diverse, data features are becoming more typical, and data statistical analysis related research has entered the era of big data. How to efficiently organize data sources, extract data features, and mine the information contained in the data from massive data has become one of the hot topics in the current research on statistical analysis of supervisory data.

[0003] For the statistical analysis of massive data, the existing clustering analysis algorithms have low computational efficiency. How to efficiently organize data sources and extract data features to mine the information contained in the massive data is an urgent problem that needs to be solved. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide a supervisory statistical analysis method and device based on parallel clustering, so as to improve the clustering calculation efficiency for large-scale data.

[0005] A supervisory statistical analysis method based on parallel clustering, the method comprising:

[0006] Acquire an original monitoring data set; the original monitoring data set includes a plurality of monitoring data; the monitoring data includes a monitoring object and attributes of the monitoring object; the attributes include a location attribute, a responsibility attribute, a domain attribute, a monitoring item attribute, and a problem attribute of the monitored object;

[0007] Setting weights for multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, calculating correlation coefficients between the attribute weight sets, and stratifying the monitoring data in the original monitoring data set according to the correlation coefficients to obtain multiple monitoring data layers;

[0008] Performing parallel clustering on the monitoring data in each monitoring data layer to obtain a plurality of first monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers;

[0009] Performing parallel clustering on the multiple second monitoring data cluster centers to obtain multiple third monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each of the third monitoring data cluster centers, and obtaining multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters;

[0010] A statistical analysis model is constructed based on the optimal monitoring data cluster and the optimal cluster center to perform statistical analysis on the monitoring data.

[0011] In one embodiment, weights are set for the multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, correlation coefficients between the attribute weight sets are calculated, and the monitoring data in the original monitoring data set are layered according to the correlation coefficients to obtain multiple monitoring data layers, including:

[0012] The weights of the multiple attributes of each monitoring data are set to obtain the attribute weight set of each monitoring data:

[0013] M n ={m n1 , m n2 , ..., m nl}

[0014] Among them, M n Denotes the original supervision data set M = {M1, M2, ..., M N}, the nth monitoring data, m nl Indicates M n The lth attribute of ;

[0015] The correlation coefficient between the attribute weight sets is calculated as:

[0016] ρ=Σ l (m i -m j )

[0017] Among them, ρ is the correlation coefficient, m i M is the monitoring data i The attribute weight, m j M is the monitoring data j The attribute weight of

[0018] The monitoring data in the original monitoring data set are layered according to the correlation coefficient to obtain multiple monitoring data layers:

[0019] C={C1,C2,...,C m}

[0020] Among them, m represents the number of monitoring data in the monitoring data layer.

[0021] In one embodiment, the monitoring data in each monitoring data layer are clustered in parallel to obtain a plurality of first monitoring data cluster centers, including:

[0022] For each monitoring data layer, the monitoring data C = {C1, C2, ..., C m} perform parallel clustering, and use the K-means algorithm to divide the monitoring data sets in each monitoring data layer into multiple first monitoring data clusters R = {R1, R2, ..., R k};

[0023] The cluster center of each first supervisory data cluster is calculated to obtain a plurality of first supervisory data cluster centers.

[0024] In one embodiment, the original monitoring data set is divided according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers, including:

[0025] Dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and the center of the first monitoring data cluster to obtain a corresponding plurality of second monitoring data sets;

[0026] The cluster center of each second supervision data set is calculated to obtain multiple second supervision data cluster centers.

[0027] A supervisory statistical analysis device based on parallel clustering, the device comprising:

[0028] An acquisition module is used to acquire an original monitoring data set; the original monitoring data set includes a plurality of monitoring data; the monitoring data includes a monitoring object and attributes of the monitoring object; the attributes include a location attribute, a responsibility attribute, a domain attribute, a monitoring item attribute, and a problem attribute of the monitored object;

[0029] A stratification module, used to set weights for multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, calculate the correlation coefficient between the attribute weight sets, and stratify the monitoring data in the original monitoring data set according to the correlation coefficient to obtain multiple monitoring data layers;

[0030] A first partitioning module is used to perform parallel clustering on the monitoring data in each monitoring data layer to obtain a plurality of first monitoring data cluster centers, and to partition the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers;

[0031] A second partitioning module is used to perform parallel clustering on the multiple second monitoring data cluster centers to obtain multiple third monitoring data cluster centers, and to partition the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each of the third monitoring data cluster centers to obtain multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters;

[0032] The statistical analysis module is used to construct a statistical analysis model based on the optimal monitoring data cluster and the optimal cluster center to perform statistical analysis on the monitoring data.

[0033] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Acquire an original monitoring data set; the original monitoring data set includes a plurality of monitoring data; the monitoring data includes a monitoring object and attributes of the monitoring object; the attributes include a location attribute, a responsibility attribute, a domain attribute, a monitoring item attribute, and a problem attribute of the monitored object;

[0035] Setting weights for multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, calculating correlation coefficients between the attribute weight sets, and stratifying the monitoring data in the original monitoring data set according to the correlation coefficients to obtain multiple monitoring data layers;

[0036] Performing parallel clustering on the monitoring data in each monitoring data layer to obtain a plurality of first monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers;

[0037] Performing parallel clustering on the multiple second monitoring data cluster centers to obtain multiple third monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each of the third monitoring data cluster centers, and obtaining multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters;

[0038] A statistical analysis model is constructed based on the optimal monitoring data cluster and the optimal cluster center to perform statistical analysis on the monitoring data.

[0039] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0040] Obtaining an original monitoring data set; the original monitoring data set includes a plurality of monitoring data; the monitoring data includes a monitoring object and attributes of the monitoring object; the attributes include a location attribute, a responsibility attribute, a domain attribute, a monitoring item attribute, and a problem attribute of the monitored object;

[0041] Setting weights for multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, calculating correlation coefficients between the attribute weight sets, and stratifying the monitoring data in the original monitoring data set according to the correlation coefficients to obtain multiple monitoring data layers;

[0042] Performing parallel clustering on the monitoring data in each monitoring data layer to obtain a plurality of first monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers;

[0043] Performing parallel clustering on the multiple second monitoring data cluster centers to obtain multiple third monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each of the third monitoring data cluster centers, and obtaining multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters;

[0044] A statistical analysis model is constructed based on the optimal monitoring data cluster and the optimal cluster center to perform statistical analysis on the monitoring data.

[0045] The above-mentioned monitoring statistical analysis method and device based on parallel clustering first obtains the original monitoring data set. It can be understood that the original monitoring data set is obtained by extracting the information of the monitored object through the monitoring system. The original monitoring data set includes the monitored object and the location attribute, responsibility attribute, field attribute, monitoring project attribute, and problem attribute of the monitored object. That is, the location, responsibility, field, monitoring project and corresponding problems of the monitored object are used as monitoring data samples, and then weights are set for multiple attributes of each monitoring data to obtain an attribute weight set of each monitoring data, and the correlation coefficient between the attribute weight sets is calculated. The monitoring data in the original monitoring data set is stratified according to the correlation coefficient to obtain multiple monitoring data. The monitoring data layer is divided according to the data attributes to generate different levels. The data in the same level have a high degree of similarity, which is used as the basis for clustering. Then, the monitoring data in each monitoring data layer is clustered in parallel to obtain multiple first monitoring data cluster centers. The original monitoring data set is divided according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain multiple second monitoring data cluster centers. The multiple second monitoring data cluster centers are clustered in parallel to obtain multiple third monitoring data cluster centers. The original monitoring data set is divided according to the distance between each monitoring data in the original monitoring data set and each of the third cluster centers to obtain multiple optimal monitoring data clusters and optimal monitoring data cluster corresponding centers. The best cluster center, it can be understood that the hierarchical processing of the original monitoring data set is a preliminary division. Through the first parallel clustering, multiple first monitoring data cluster centers with multiple levels are obtained, and the monitoring data in the original monitoring data set are redistributed to their respective first monitoring data cluster centers. It can be known that since the number of first monitoring data cluster centers in a level is greater than 1, the total number of first monitoring data cluster centers is greater than the number of levels. Therefore, the division of the original data set by the first monitoring data cluster center is a more fine-grained division. In this process, the monitoring data in each level complement each other, avoiding repeated clustering of the data set and wasting computing resources. The object of the second parallel clustering is the original data set. After the second division, multiple second monitoring data cluster centers are updated, and multiple second monitoring data cluster centers are clustered in parallel to extract the correlation between multiple second monitoring data cluster centers. Then, the number of third monitoring data cluster centers is smaller than the number of second monitoring data cluster centers. Correspondingly, the division of the original data set is further divided on the basis of the fine-grained division obtained by the first parallel clustering to make the distribution of monitoring data more compact. Finally, a statistical analysis model is constructed according to the best monitoring data cluster and the best cluster center to perform statistical analysis on the monitoring data. The present invention is based on data feature extraction of massive monitoring data, adopts a parallel clustering method, and performs cluster analysis on the monitoring data in layers and step by step, and the layers complement each other.In the face of massive data, the best cluster center can be quickly screened out, thereby improving the efficiency of monitoring statistical analysis and assisting in improving monitoring capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a flow chart of a monitoring statistical analysis method based on parallel clustering in one embodiment;

[0047] Figure 2 is a structural block diagram of a monitoring statistical analysis device based on parallel clustering in one embodiment;

[0048] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] In one embodiment, Figure 1 As shown, a monitoring statistical analysis method based on parallel clustering is provided, comprising the following steps:

[0051] Step 102, obtaining the original supervision data set.

[0052] The original supervision data set includes multiple supervision data. The supervision data includes supervision objects and attributes of supervision objects. The attributes include location attributes, responsibility attributes, field attributes, supervision project attributes, and problem attributes.

[0053] The original monitoring data set is obtained by extracting information of the monitored object through the monitoring system. The original monitoring data set includes the monitored object and its location attributes, responsibility attributes, field attributes, monitoring item attributes, and problem attributes, that is, the location, responsibility, field, monitoring item and corresponding problems found of the monitored object.

[0054] Step 104, weights are set for multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, correlation coefficients between attribute weight sets are calculated, and the monitoring data in the original monitoring data set are stratified according to the correlation coefficients to obtain multiple monitoring data layers.

[0055] Weights are set for multiple attributes of each monitoring data, and the correlation coefficients between attribute weight sets are calculated. The monitoring data in the original monitoring data set are stratified according to the correlation coefficients. That is to say, starting from the monitoring data with relatively rich and clear data features, the data features are extracted for hierarchical division, so that the monitoring data in the same layer are more similar, and the monitoring data in different layers are less similar.

[0056] Step 106, clustering the monitoring data in each monitoring data layer in parallel to obtain multiple first monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain multiple second monitoring data cluster centers.

[0057] It can be understood that the hierarchical processing of the original monitoring data set in step 104 is a preliminary division. Through the first parallel clustering, multiple first monitoring data cluster centers of multiple levels are obtained, and the monitoring data in the original monitoring data set are redistributed to their respective first monitoring data cluster centers. It can be seen that since the number of first monitoring data cluster centers in a level is greater than 1, the total number of first monitoring data cluster centers is greater than the number of levels. Therefore, the division of the original data set by the first monitoring data cluster centers is a more fine-grained division. In this process, the monitoring data in each level complement each other, avoiding repeated clustering of the data set and wasting computing resources.

[0058] Step 108, clustering the multiple second monitoring data cluster centers in parallel to obtain multiple third monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each third monitoring data cluster center, and obtaining multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters.

[0059] The object of the second parallel clustering is the multiple second monitoring data cluster centers updated after the second division of the original data set. The multiple second monitoring data cluster centers are clustered in parallel to extract the correlation between the multiple second monitoring data cluster centers. Then the number of third monitoring data cluster centers obtained is smaller than the number of second monitoring data cluster centers. Correspondingly, the division of the original data set is further divided on the basis of the fine-grained division obtained by the first parallel clustering, which makes the distribution of monitoring data more compact.

[0060] Step 110, constructing a statistical analysis model based on the best monitoring data cluster and the best cluster center, and performing statistical analysis on the monitoring data.

[0061] A data statistical analysis model is constructed based on the best monitoring data cluster and the best cluster center. The model can be used to establish a monitoring statistical analysis system on the Hadoop platform to perform statistical analysis of monitoring data.

[0062] In the above-mentioned monitoring statistical analysis method based on parallel clustering, weights are set for multiple attributes of each monitoring data in the original monitoring data set to obtain an attribute weight set for each monitoring data, the correlation coefficient between the attribute weight sets is calculated, the monitoring data in the original monitoring data set is stratified according to the correlation coefficient to obtain multiple monitoring data layers, the monitoring data in each monitoring data layer are clustered in parallel to obtain multiple first monitoring data cluster centers, the original monitoring data set is divided according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain multiple second monitoring data cluster centers, the multiple second monitoring data cluster centers are clustered in parallel to obtain multiple third monitoring data cluster centers, the original monitoring data set is divided according to the distance between each monitoring data in the original monitoring data set and each third monitoring data cluster center to obtain multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters, and finally a statistical analysis model is constructed based on the optimal monitoring data clusters and the optimal cluster centers to perform statistical analysis of the monitoring data. This method is based on the data feature extraction of massive monitoring data. It adopts a parallel clustering method to perform cluster analysis on the monitoring data in layers. The layers complement each other. In the face of massive data, the best cluster center can be quickly screened out, thereby improving the efficiency of monitoring statistical analysis and assisting in improving monitoring capabilities.

[0063] In one embodiment, weights are set for multiple attributes of each monitoring data, and the attribute weight set of each monitoring data is obtained as follows:

[0064] M n ={m n1 , m n2 , ..., m nl}

[0065] Among them, M n Denotes the original supervision data set M = {M1, M2, ..., M N}, the nth monitoring data, m nl Indicates M n The lth attribute of ;

[0066] The correlation coefficient between the attribute weight sets is calculated as:

[0067] ρ=Σ l (m i -m j )

[0068] Among them, ρ is the correlation coefficient, m i M is the monitoring data i The attribute weight, m j M is the monitoring data j The attribute weight of

[0069] The monitoring data in the original monitoring data set are stratified according to the correlation coefficient to obtain multiple monitoring data layers:

[0070] C={C1,C2,...,C m}

[0071] Among them, m represents the number of monitoring data in the monitoring data layer.

[0072] In one embodiment, for each monitoring data layer, the monitoring data C={C1, C2, . . . , C m} perform parallel clustering, and use the K-means algorithm to divide the monitoring data sets in each monitoring data layer into multiple first monitoring data clusters R = {R1, R2, ..., R k}, calculate the cluster center of each first monitoring data cluster to obtain multiple first monitoring data cluster centers, divide the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and the first monitoring data cluster center to obtain multiple corresponding second monitoring data sets, and calculate the cluster center of each second monitoring data set to obtain multiple second monitoring data cluster centers.

[0073] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0074] In one embodiment, Figure 2 As shown, a monitoring statistical analysis device based on parallel clustering is provided, comprising: an acquisition module, a stratification module, a first division module and a second division module, wherein:

[0075] An acquisition module is used to acquire an original monitoring data set; the original monitoring data set includes a plurality of monitoring data; the monitoring data includes a monitoring object and attributes of the monitoring object; the attributes include location attributes, responsibility attributes, domain attributes, monitoring item attributes, and problem attributes of the monitored object;

[0076] A stratification module is used to set weights for multiple attributes of each monitoring data, obtain an attribute weight set for each monitoring data, calculate the correlation coefficient between the attribute weight sets, and stratify the monitoring data in the original monitoring data set according to the correlation coefficient to obtain multiple monitoring data layers;

[0077] The first partitioning module is used to perform parallel clustering on the monitoring data in each monitoring data layer to obtain a plurality of first monitoring data cluster centers, and to partition the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers;

[0078] A second partitioning module is used to perform parallel clustering on the multiple second monitoring data cluster centers to obtain multiple third monitoring data cluster centers, and to partition the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each of the third monitoring data cluster centers to obtain multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters;

[0079] The statistical analysis module is used to construct a statistical analysis model based on the best monitoring data cluster and the best cluster center to perform statistical analysis of the monitoring data.

[0080] For the specific definition of a monitoring statistical analysis device based on parallel clustering, please refer to the definition of a monitoring statistical analysis method based on parallel clustering above, which will not be repeated here. Each module in the above-mentioned monitoring statistical analysis device based on parallel clustering can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0081] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. 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, a monitoring statistical analysis method based on parallel clustering is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0082] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0083] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the above embodiment when executing the computer program.

[0084] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the above embodiment are implemented.

[0085] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant 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 used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), 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).

[0086] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A monitoring statistical analysis method based on parallel clustering, characterized in that: The method comprises: Obtaining an original monitoring data set; the original monitoring data set includes a plurality of monitoring data; the monitoring data includes a monitored object and attributes of the monitored object; the attributes include a location attribute, a responsibility attribute, a domain attribute, a monitoring item attribute, and a problem attribute of the monitored object; Setting weights for multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, calculating correlation coefficients between the attribute weight sets, and stratifying the monitoring data in the original monitoring data set according to the correlation coefficients to obtain multiple monitoring data layers; Performing parallel clustering on the monitoring data in each monitoring data layer to obtain a plurality of first monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers; Performing parallel clustering on the multiple second monitoring data cluster centers to obtain multiple third monitoring data cluster centers, dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each of the third monitoring data cluster centers, and obtaining multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters; Constructing a statistical analysis model based on the optimal monitoring data cluster and the optimal cluster center to perform statistical analysis of the monitoring data 2. The method according to claim 1, characterized in that: The weighting of the multiple attributes of each monitoring data is set to obtain an attribute weight set of each monitoring data, the correlation coefficient between the attribute weight sets is calculated, and the monitoring data in the original monitoring data set is layered according to the correlation coefficient to obtain multiple monitoring data layers, including: The weights of the multiple attributes of each monitoring data are set to obtain the attribute weight set of each monitoring data: in, Represents the original supervision dataset The n Monitoring data, express No. l Attributes; The correlation coefficient between the attribute weight sets is calculated as: p=∑ l (m i -m j ) in, is the correlation coefficient, To monitor data The attribute weight of To monitor data The attribute weight of The monitoring data in the original monitoring data set are layered according to the correlation coefficient to obtain multiple monitoring data layers: C={C1,C2,…,C m } in, m Indicates the number of monitoring data in the monitoring data layer.

3. The method according to claim 1, characterized in that: Perform parallel clustering on the monitoring data in each monitoring data layer to obtain multiple first monitoring data cluster centers, including: For each monitoring data layer, the monitoring data C={C1,C2,…,C m } perform parallel clustering, and use the K-means algorithm to divide the monitoring data sets in each monitoring data layer into multiple first monitoring data clusters R = {R1, R2, …, R k }; The cluster center of each first supervisory data cluster is calculated to obtain a plurality of first supervisory data cluster centers.

4. The method according to claim 1, characterized in that: The original monitoring data set is divided according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers, including: Dividing the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and the center of the first monitoring data cluster to obtain a corresponding plurality of second monitoring data sets; The cluster center of each second supervision data set is calculated to obtain multiple second supervision data cluster centers.

5. A monitoring statistical analysis device based on parallel clustering, characterized in that: The device comprises: An acquisition module is used to acquire an original monitoring data set; the original monitoring data set includes a plurality of monitoring data; the monitoring data includes a monitored object and attributes of the monitored object; the attributes include a location attribute, a responsibility attribute, a domain attribute, a monitoring item attribute, and a problem attribute of the monitored object; A stratification module, used to set weights for multiple attributes of each monitoring data to obtain an attribute weight set for each monitoring data, calculate the correlation coefficient between the attribute weight sets, and stratify the monitoring data in the original monitoring data set according to the correlation coefficient to obtain multiple monitoring data layers; A first partitioning module is used to perform parallel clustering on the monitoring data in each monitoring data layer to obtain a plurality of first monitoring data cluster centers, and to partition the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each first monitoring data cluster center to obtain a plurality of second monitoring data cluster centers; A second partitioning module is used to perform parallel clustering on the multiple second monitoring data cluster centers to obtain multiple third monitoring data cluster centers, and to partition the original monitoring data set according to the distance between each monitoring data in the original monitoring data set and each of the third monitoring data cluster centers to obtain multiple optimal monitoring data clusters and optimal cluster centers corresponding to the optimal monitoring data clusters; The statistical analysis module is used to construct a statistical analysis model based on the optimal monitoring data cluster and the optimal cluster center to perform statistical analysis on the monitoring data.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. 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 4 are implemented.

Images