Intelligent classified storage system and method for enterprise management data based on big data

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent classified storage system and method for enterprise management data based on big data, and the method comprises the steps: carrying out the data clustering processing of collected enterprise historical business information feature data, generating the clustering feature data of the enterprise historical business information, and storing the clustering feature data into an enterprise management data storage unit; setting corresponding enterprise business information category text feature data, and performing data preprocessing on the collected to-be-classified enterprise business information data to generate to-be-classified enterprise business information feature data; performing text feature data search processing according to the to-be-classified enterprise business information feature data and the enterprise business information category text feature data to generate to-be-classified enterprise business information category text feature data, and storing the to-be-classified enterprise business information feature data to an enterprise management data storage unit according to the to-be-classified enterprise business information category text feature data, thereby realizing accurate classification and intelligent storage of enterprise management data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a system and method for intelligent classification and storage of enterprise management data based on big data. Background Art

[0002] With the continuous expansion of enterprise scale and the continuous development of enterprise business, the amount of production and operation data generated in the enterprise management process has also increased exponentially. Faced with massive production and operation data, enterprises often find it difficult to achieve accurate classification.

[0003] The Chinese patent invention with publication number CN117349478B introduces a resource data reconstruction and integration system based on digital transformation enterprises. The system classifies data with different attributes in advance, then uses different models to identify feature vectors of data with different attributes, and merges and analyzes the feature vectors of data with different attributes to obtain the similarity between data with different attributes. The data with different attributes are integrated according to the similarity, the target data integration package is confirmed, and the subsequent target integration packages are confirmed in turn. The overall capacity of the integrated data can be reduced, the corresponding storage space can be reduced, and the storage space can be reasonably used. However, the intelligent classification storage of real-time data and the storage method of new categories of data are not considered. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In order to solve the deficiencies in the background technology, the present invention provides a system and method for intelligent classification and storage of enterprise management data based on big data, so as to realize accurate classification and intelligent storage of enterprise management data.

[0006] (II) Technical solution

[0007] A method for intelligent classification and storage of enterprise management data based on big data, comprising the following steps:

[0008] S1. Collect the characteristic data of the enterprise's historical business information;

[0009] S2. Perform data clustering processing on the enterprise historical business information feature data by using a clustering algorithm to generate enterprise historical business information cluster feature data, store the enterprise historical business information cluster feature data in an enterprise management data storage unit, and set corresponding enterprise business information category text feature data for each category of enterprise historical business information cluster feature data;

[0010] S3. Collecting business information data of enterprises to be classified;

[0011] S4, performing data preprocessing on the enterprise business information data to be classified to generate characteristic data of the enterprise business information to be classified;

[0012] S5, performing a search process on the enterprise business information category text feature data to be classified according to the enterprise business information feature data to be classified and the enterprise business information category text feature data to generate the enterprise business information category text feature data to be classified;

[0013] S6. Storing the enterprise business information feature data to be classified in an enterprise management data storage unit according to the enterprise business information category text feature data to be classified, and pushing the enterprise business information category text feature data to be classified to an enterprise management data storage result platform.

[0014] The present invention generates enterprise historical business information clustering feature data by performing data clustering processing on the collected enterprise historical business information feature data, sets corresponding enterprise business information category text feature data and stores them in an enterprise management data storage unit at the same time, performs data preprocessing on the collected enterprise business information data to be classified to generate enterprise business information feature data to be classified, performs text feature data search processing based on the enterprise business information feature data to be classified and the enterprise business information category text feature data to generate enterprise business information category text feature data to be classified, and stores the enterprise business information feature data to be classified in the enterprise management data storage unit based on the enterprise business information category text feature data to be classified, thereby realizing accurate classification and intelligent storage of enterprise management data.

[0015] Preferably, the specific steps for collecting the characteristic data of the enterprise's historical business information are as follows:

[0016] S11, collect the historical production and operation information feature data of the target enterprise online through the enterprise production and operation data management unit, and generate the enterprise historical business information feature data set A = {a 1 ,a 2 ,…,a i ,…,a k}, where a i represents the i-th historical production and operation information characteristic data of the target enterprise collected online through the enterprise production and operation data management unit, k represents the total number of historical business information characteristic data of the enterprise, and the historical business information characteristic data of the enterprise includes but is not limited to the historical production information of the enterprise, the historical sales information of the enterprise, the historical market information of the enterprise, the historical financial information of the enterprise and the historical human resources information of the enterprise.

[0017] Preferably, the specific steps of performing data clustering processing on the enterprise historical business information feature data by a clustering algorithm to generate enterprise historical business information cluster feature data, storing the enterprise historical business information cluster feature data in an enterprise management data storage unit, and setting corresponding enterprise business information category text feature data for each category of enterprise historical business information cluster feature data are as follows:

[0018] S21, using an agglomerative hierarchical clustering algorithm to perform data clustering on the enterprise historical business information feature data in the enterprise historical business information feature data set, to generate an enterprise historical business information cluster feature data set B = {b 1 ,b 2 ,…,b i ,…,b l}, where b i represents the clustering feature data of the historical business information of the i-th type of enterprise obtained after data clustering processing, and l represents the total number of clustering feature data of the historical business information of the enterprise; the data clustering processing process is as follows:

[0019] S211, each enterprise historical business information feature data in the enterprise historical business information feature data set is regarded as a cluster, and the Euclidean distance between clusters is calculated to generate a distance matrix; the Euclidean distance calculation formula is as follows:

[0020]

[0021] Where D(x,y) represents the Euclidean distance between vector x and vector y, x and y represent the n-dimensional feature vectors of any two cluster centers, respectively. i Represents the value of vector x in the i-th dimension, y i Represents the value of vector y in the i-th dimension;

[0022] S212, merging the two clusters corresponding to the minimum values ​​in the distance matrix into a new cluster, calculating the Euclidean distance between the new cluster and the other clusters, and updating the distance matrix;

[0023] S213, setting a Euclidean distance threshold, if the minimum value in the distance matrix is ​​greater than or equal to the Euclidean distance threshold, then ending the data clustering processing operation, and obtaining a clustering feature data set of enterprise historical business information; otherwise, returning to S212, until the minimum value in the distance matrix is ​​greater than or equal to the Euclidean distance threshold;

[0024] 22. Store the various types of enterprise historical business information clustering feature data in the enterprise historical business information clustering feature data set in the enterprise management data storage unit in sequence, and enter the corresponding enterprise business information category text feature data for each type of enterprise historical business information clustering feature data through the enterprise business information category text entry interface to generate an enterprise business information category text feature data set C = {c 1 ,c 2 ,…,c i ,…,c l}, where c i Represents the enterprise business information category text feature data corresponding to the cluster feature data of the i-th category of enterprise historical business information.

[0025] An agglomerative hierarchical clustering algorithm is used to perform data clustering processing on the characteristic data of the enterprise's historical business information, so as to achieve accurate classification of the characteristic data of the enterprise's historical business information and ensure the accuracy of the clustering characteristic data of the enterprise's historical business information. At the same time, the bottom-up clustering method can make the clustering results more intuitive and can intuitively understand the differences between the characteristic data of different enterprise historical business information.

[0026] Preferably, the specific steps of collecting the business information data of the enterprise to be classified are as follows:

[0027] S31. Collect the production and operation information data of the target enterprise to be classified online through the enterprise business information input interface to be classified, and generate the enterprise business information data D to be classified.

[0028] Preferably, the specific steps of performing data preprocessing on the enterprise business information data to be classified to generate the enterprise business information feature data to be classified are as follows:

[0029] S41, using a wavelet transform filtering method to perform filtering and noise reduction processing on the enterprise business information data D to be classified, to generate enterprise business information feature data D' to be classified.

[0030] The wavelet transform filtering method is used to filter and reduce noise of the enterprise business information data to be classified, which effectively filters out noise in the enterprise business information data to be classified, ensures the accuracy and reliability of the acquired data, and at the same time well preserves the local features of the enterprise business information data to be classified.

[0031] Preferably, the specific steps of performing a search process for the enterprise business information category text feature data to be classified based on the enterprise business information feature data to be classified and the enterprise business information category text feature data to generate the enterprise business information category text feature data to be classified are as follows:

[0032] S51, performing a search process on the enterprise business information category text feature data to be classified on the enterprise business information feature data D' to be classified and the enterprise business information category text feature data in the enterprise business information category text feature data set through a flower pollination optimization algorithm, and generating the enterprise business information category text feature data E to be classified according to the search process result of the enterprise business information category text feature data to be classified;

[0033] The generating of the to-be-classified enterprise business information category text feature data comprises the following steps:

[0034] S511. Construct a pollen population, set the pollen population size to N, the conversion probability to p, the current number of iterations to t, and the maximum number of iterations to t max And the dimension of the search space of text feature data of enterprise business information category is P;

[0035] In the enterprise business information category text feature data search space, N enterprise business information category text feature data are randomly generated, each enterprise business information category text feature data corresponds to a pollen individual in the pollen population, and the initial position set of the pollen population is initialized as X={X 1 ,X 2 ,…,X i ,…,X N}, where X i represents the initial position of the i-th pollen individual in the pollen population;

[0036] S512, calculating the fitness function value of each pollen individual in the pollen population, arranging the pollen individuals in the pollen population from large to small according to the fitness function value, and selecting the pollen individual with the highest fitness function value as the current optimal individual; the fitness function value formula is as follows:

[0037]

[0038] Among them, Fit i represents the fitness function value of the i-th pollen individual in the pollen population, D i represents the Euclidean distance between the enterprise historical business information clustering feature data corresponding to the enterprise business information category text feature data corresponding to the i-th pollen individual in the pollen population and the enterprise business information feature data to be classified, and φ represents the correction value;

[0039] S513, setting a random number q that obeys a uniform distribution between [0,1] as a control coefficient, and controlling the pollination behavior of each pollen individual in the pollen population in the enterprise business information category text feature data search space through the control coefficient;

[0040] S5131. When q≥p, each pollen individual in the pollen population is pollinated in the enterprise business information category text feature data search space by biological cross-pollination to update the position; the position update formula is as follows:

[0041]

[0042] in, and denote the position of the i-th pollen individual in the pollen population during the t+1th and tth iterations, respectively; L denotes the random step length that follows the Levy distribution; X best Indicates the position of the current optimal individual;

[0043] S5132, when q<p, each pollen individual in the pollen population is pollinated in the enterprise business information category text feature data search space by non-biological self-pollination to update the position; the position update formula is as follows:

[0044]

[0045] Among them, rand represents a random number that is uniformly distributed between [0,1]. and They represent the positions of the jth and zth pollen individuals randomly selected from the pollen population during the tth iteration, respectively;

[0046] S514, calculating the fitness function value of each pollen individual in the pollen population after the position is updated, if the fitness function value of the pollen individual after the position is updated is greater than the fitness function value before the position is updated, then the position of the pollen individual is updated; otherwise, the original position of the pollen individual is retained;

[0047] Rearrange the pollen individuals in the pollen population from large to small according to the fitness function value, and select the pollen individual with the highest fitness function value as the new current optimal individual;

[0048] S515: Determine whether the current number of iterations t is less than the maximum number of iterations t max , if the current number of iterations t is less than the maximum number of iterations t max , then the current iteration number t is increased by 1, and the process returns to S513; otherwise, the current optimal individual is taken as the global optimal solution;

[0049] S516. Set a fitness function threshold. If the fitness function value of the global optimal solution is greater than or equal to the fitness function threshold, it is determined that the enterprise business information category text feature data corresponding to the global optimal solution matches the enterprise business information feature data to be classified successfully, and the enterprise business information category text feature data corresponding to the global optimal solution is output and data identification is performed to generate the enterprise business information category text feature data E to be classified; otherwise, it is determined that the enterprise business information category text feature data corresponding to the global optimal solution does not match the enterprise business information feature data to be classified, and the enterprise business information category text feature data E to be classified is output as temporarily stored business information.

[0050] The flower pollination optimization algorithm is used to perform text feature data search and processing on the enterprise business information feature data to be classified and the enterprise business information category text feature data, thereby ensuring the efficiency of the search process, being able to accurately identify the category of the enterprise business information feature data to be classified, and realizing the scientific classification of the enterprise business information feature data to be classified. At the same time, the flower pollination optimization algorithm can ensure that the search process has good stability and effectively avoid the errors caused by analyzing different data.

[0051] Preferably, the specific steps of storing the enterprise business information feature data to be classified in the enterprise management data storage unit according to the enterprise business information category text feature data to be classified, and pushing the enterprise business information category text feature data to be classified to the enterprise management data storage result platform are as follows:

[0052] S61, storing the enterprise business information feature data D' to be classified into an enterprise management data storage unit according to the enterprise business information category text feature data E to be classified;

[0053] If the enterprise business information category text feature data E to be classified is any enterprise business information category text feature data in the enterprise business information category text feature data set, then the enterprise business information category feature data D' to be classified is stored in the area where the enterprise historical business information cluster feature data corresponding to the enterprise business information category text feature data E to be classified is located in the enterprise management data storage unit;

[0054] If the enterprise business information category text feature data E to be classified is not any enterprise business information category text feature data in the enterprise business information category text feature data set, a temporary area is divided in the enterprise management data storage unit, and the enterprise business information feature data D' to be classified is stored in the temporary area;

[0055] S62: Push the to-be-classified enterprise business information category text feature data to the enterprise management data storage result platform via a wireless communication network and display it on a display screen.

[0056] The present invention also discloses an enterprise management data intelligent classification storage system based on big data, including an enterprise historical business information feature data acquisition module, an enterprise historical business information feature data clustering module, a to-be-classified enterprise business information data acquisition module, a to-be-classified enterprise business information data preprocessing module, an enterprise business information category text feature data search module, and a to-be-classified enterprise business information feature data storage module;

[0057] The enterprise historical business information characteristic data collection module collects the historical production and operation information characteristic data of the target enterprise online through the enterprise production and operation data management unit to generate the enterprise historical business information characteristic data;

[0058] The enterprise historical business information characteristic data clustering module uses an agglomerative hierarchical clustering algorithm to perform data clustering processing on the enterprise historical business information characteristic data in the enterprise historical business information characteristic data set to generate enterprise historical business information clustering characteristic data, stores the enterprise historical business information clustering characteristic data in the enterprise management data storage unit, and enters the corresponding enterprise business information category text characteristic data for each category of enterprise historical business information clustering characteristic data through the enterprise business information category text entry interface;

[0059] The to-be-classified enterprise business information data collection module collects the to-be-classified production and operation information data of the target enterprise online through the to-be-classified enterprise business information input interface to generate the to-be-classified enterprise business information data;

[0060] The enterprise business information data preprocessing module to be classified uses a wavelet transform filtering method to perform filtering and noise reduction processing on the enterprise business information data to be classified, and generates characteristic data of the enterprise business information to be classified;

[0061] The enterprise business information category text feature data search module performs enterprise business information category text feature data search processing on the enterprise business information feature data to be classified and the enterprise business information category text feature data through a flower pollination optimization algorithm, and generates enterprise business information category text feature data to be classified according to the enterprise business information category text feature data search processing result;

[0062] The enterprise business information to be classified feature data storage module stores the enterprise business information to be classified feature data in the enterprise management data storage unit according to the enterprise business information category text feature data to be classified, and pushes the enterprise business information category text feature data to the enterprise management data storage result platform.

[0063] (III) Beneficial effects

[0064] 1. The present invention performs data clustering processing on the collected enterprise historical business information feature data to generate enterprise historical business information cluster feature data, sets corresponding enterprise business information category text feature data and stores them in the enterprise management data storage unit at the same time, performs data preprocessing on the collected enterprise business information data to be classified to generate enterprise business information feature data to be classified, performs text feature data search processing based on the enterprise business information feature data to be classified and the enterprise business information category text feature data to generate enterprise business information category text feature data to be classified, and stores the enterprise business information feature data to be classified in the enterprise management data storage unit based on the enterprise business information category text feature data to be classified, thereby realizing accurate classification and intelligent storage of enterprise management data;

[0065] 2. Use agglomerative hierarchical clustering algorithm to perform data clustering on the characteristic data of the enterprise's historical business information, so as to achieve accurate classification of the characteristic data of the enterprise's historical business information, and ensure the accuracy of the clustering characteristic data of the enterprise's historical business information. At the same time, the bottom-up clustering method can make the clustering results more intuitive, and can intuitively understand the differences between the characteristic data of the historical business information of different enterprises;

[0066] 3. Using the wavelet transform filtering method to filter and reduce noise of the enterprise business information data to be classified, effectively filtering out noise in the enterprise business information data to be classified, ensuring the accuracy and reliability of the acquired data, and at the same time well retaining the local features of the enterprise business information data to be classified;

[0067] 4. The flower pollination optimization algorithm is used to perform text feature data search and processing on the enterprise business information feature data to be classified and the enterprise business information category text feature data, thereby ensuring the efficiency of the search process, being able to accurately identify the category of the enterprise business information feature data to be classified, and realizing the scientific classification of the enterprise business information feature data to be classified. At the same time, the flower pollination optimization algorithm can ensure that the search process has good stability and effectively avoid the errors caused by analyzing different data. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0069] Figure 1A flowchart of a method for intelligent classification and storage of enterprise management data based on big data provided by the present invention;

[0070] Figure 2 A module schematic diagram of an enterprise management data intelligent classification storage system based on big data provided by the present invention. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0073] Embodiment 1 is as follows:

[0074] See also Figure 1 , a method for intelligent classification and storage of enterprise management data based on big data, comprising the following steps:

[0075] S1. Collect the characteristic data of the enterprise's historical business information;

[0076] S11, collect the historical production and operation information feature data of the target enterprise online through the enterprise production and operation data management unit, and generate the enterprise historical business information feature data set A = {a 1 ,a 2 ,…,a i ,…,a k}, where a i represents the i-th historical production and operation information characteristic data of the target enterprise collected online through the enterprise production and operation data management unit, k represents the total number of historical business information characteristic data of the enterprise, and the historical business information characteristic data of the enterprise includes but is not limited to the historical production information of the enterprise, the historical sales information of the enterprise, the historical market information of the enterprise, the historical financial information of the enterprise and the historical human resources information of the enterprise.

[0077] S2. Perform data clustering processing on the enterprise historical business information feature data by using a clustering algorithm to generate enterprise historical business information cluster feature data, store the enterprise historical business information cluster feature data in an enterprise management data storage unit, and set corresponding enterprise business information category text feature data for each category of enterprise historical business information cluster feature data;

[0078] S21, using an agglomerative hierarchical clustering algorithm to perform data clustering on the enterprise historical business information feature data in the enterprise historical business information feature data set, to generate an enterprise historical business information cluster feature data set B = {b 1 ,b 2 ,…,b i ,…,b l}, where b i represents the clustering feature data of the historical business information of the i-th type of enterprise obtained after data clustering processing, and l represents the total number of clustering feature data of the historical business information of the enterprise; the data clustering processing process is as follows:

[0079] S211, each enterprise historical business information feature data in the enterprise historical business information feature data set is regarded as a cluster, and the Euclidean distance between clusters is calculated to generate a distance matrix; the Euclidean distance calculation formula is as follows:

[0080]

[0081] Where D(x,y) represents the Euclidean distance between vector x and vector y, x and y represent the n-dimensional feature vectors of any two cluster centers, respectively. i Represents the value of vector x in the i-th dimension, y i Represents the value of vector y in the i-th dimension;

[0082] S212, merging the two clusters corresponding to the minimum values ​​in the distance matrix into a new cluster, calculating the Euclidean distance between the new cluster and the other clusters, and updating the distance matrix;

[0083] S213, setting a Euclidean distance threshold, if the minimum value in the distance matrix is ​​greater than or equal to the Euclidean distance threshold, then ending the data clustering processing operation, and obtaining a clustering feature data set of enterprise historical business information; otherwise, returning to S212, until the minimum value in the distance matrix is ​​greater than or equal to the Euclidean distance threshold;

[0084] 22. Store the various types of enterprise historical business information clustering feature data in the enterprise historical business information clustering feature data set in the enterprise management data storage unit in sequence, and enter the corresponding enterprise business information category text feature data for each type of enterprise historical business information clustering feature data through the enterprise business information category text entry interface to generate an enterprise business information category text feature data set C = {c 1 ,c 2 ,…,c i ,…,c l}, where c i Represents the enterprise business information category text feature data corresponding to the cluster feature data of the i-th category of enterprise historical business information.

[0085] S3. Collecting business information data of enterprises to be classified;

[0086] S31. Collect the production and operation information data of the target enterprise to be classified online through the enterprise business information input interface to be classified, and generate the enterprise business information data D to be classified.

[0087] S4, performing data preprocessing on the enterprise business information data to be classified to generate characteristic data of the enterprise business information to be classified;

[0088] S41, using a wavelet transform filtering method to perform filtering and noise reduction processing on the enterprise business information data D to be classified, to generate enterprise business information feature data D' to be classified.

[0089] S5, performing a search process on the enterprise business information category text feature data to be classified according to the enterprise business information feature data to be classified and the enterprise business information category text feature data to generate the enterprise business information category text feature data to be classified;

[0090] S51, performing a search process on the enterprise business information category text feature data to be classified on the enterprise business information feature data D' to be classified and the enterprise business information category text feature data in the enterprise business information category text feature data set through a flower pollination optimization algorithm, and generating the enterprise business information category text feature data E to be classified according to the search process result of the enterprise business information category text feature data to be classified;

[0091] The generating of the enterprise business information category text feature data to be classified comprises the following steps:

[0092] S511. Construct a pollen population, set the pollen population size to N, the conversion probability to p, the current number of iterations to t, and the maximum number of iterations to t max And the dimension of the search space of text feature data of enterprise business information category is P;

[0093] In the enterprise business information category text feature data search space, N enterprise business information category text feature data are randomly generated, each enterprise business information category text feature data corresponds to a pollen individual in the pollen population, and the initial position set of the pollen population is initialized as X={X 1 ,X 2 ,…,X i ,…,X N}, where X i represents the initial position of the i-th pollen individual in the pollen population;

[0094] S512, calculating the fitness function value of each pollen individual in the pollen population, arranging the pollen individuals in the pollen population from large to small according to the fitness function value, and selecting the pollen individual with the highest fitness function value as the current optimal individual; the fitness function value formula is as follows:

[0095]

[0096] Among them, Fit i represents the fitness function value of the i-th pollen individual in the pollen population, D i represents the Euclidean distance between the enterprise historical business information clustering feature data corresponding to the enterprise business information category text feature data corresponding to the i-th pollen individual in the pollen population and the enterprise business information feature data to be classified, and φ represents the correction value;

[0097] S513, setting a random number q that obeys a uniform distribution between [0,1] as a control coefficient, and controlling the pollination behavior of each pollen individual in the pollen population in the enterprise business information category text feature data search space through the control coefficient;

[0098] S5131. When q≥p, each pollen individual in the pollen population is pollinated in the enterprise business information category text feature data search space by biological cross-pollination to update the position; the position update formula is as follows:

[0099]

[0100] in, and denote the position of the i-th pollen individual in the pollen population during the t+1th and tth iterations, respectively; L denotes the random step length that follows the Levy distribution; X best Indicates the position of the current optimal individual;

[0101] S5132, when q<p, each pollen individual in the pollen population is pollinated in the enterprise business information category text feature data search space by non-biological self-pollination to update the position; the position update formula is as follows:

[0102]

[0103] Among them, rand represents a random number that is uniformly distributed between [0,1]. and They represent the positions of the jth and zth pollen individuals randomly selected from the pollen population during the tth iteration, respectively;

[0104] S514, calculating the fitness function value of each pollen individual in the pollen population after the position is updated, if the fitness function value of the pollen individual after the position is updated is greater than the fitness function value before the position is updated, then the position of the pollen individual is updated; otherwise, the original position of the pollen individual is retained;

[0105] Rearrange the pollen individuals in the pollen population from large to small according to the fitness function value, and select the pollen individual with the highest fitness function value as the new current optimal individual;

[0106] S515: Determine whether the current number of iterations t is less than the maximum number of iterations t max , if the current number of iterations t is less than the maximum number of iterations t max , then the current iteration number t is increased by 1, and the process returns to S513; otherwise, the current optimal individual is taken as the global optimal solution;

[0107] S516. Set a fitness function threshold. If the fitness function value of the global optimal solution is greater than or equal to the fitness function threshold, it is determined that the enterprise business information category text feature data corresponding to the global optimal solution matches the enterprise business information feature data to be classified successfully, and the enterprise business information category text feature data corresponding to the global optimal solution is output and data identification is performed to generate the enterprise business information category text feature data E to be classified; otherwise, it is determined that the enterprise business information category text feature data corresponding to the global optimal solution does not match the enterprise business information feature data to be classified, and the enterprise business information category text feature data E to be classified is output as temporarily stored business information.

[0108] S6. storing the enterprise business information feature data to be classified into an enterprise management data storage unit according to the enterprise business information category text feature data to be classified, and pushing the enterprise business information category text feature data to be classified to an enterprise management data storage result platform;

[0109] S61, storing the enterprise business information feature data D' to be classified into an enterprise management data storage unit according to the enterprise business information category text feature data E to be classified;

[0110] If the enterprise business information category text feature data E to be classified is any enterprise business information category text feature data in the enterprise business information category text feature data set, then the enterprise business information category feature data D' to be classified is stored in the area where the enterprise historical business information cluster feature data corresponding to the enterprise business information category text feature data E to be classified is located in the enterprise management data storage unit;

[0111] If the enterprise business information category text feature data E to be classified is not any enterprise business information category text feature data in the enterprise business information category text feature data set, a temporary area is divided in the enterprise management data storage unit, and the enterprise business information feature data D' to be classified is stored in the temporary area;

[0112] S62: Push the to-be-classified enterprise business information category text feature data to the enterprise management data storage result platform via a wireless communication network and display it on a display screen.

[0113] Embodiment 2 is as follows:

[0114] See also Figure 2 , an enterprise management data intelligent classification storage system based on big data, including an enterprise historical business information feature data collection module, an enterprise historical business information feature data clustering module, a to-be-classified enterprise business information data collection module, a to-be-classified enterprise business information data preprocessing module, a to-be-classified enterprise business information category text feature data search module, and a to-be-classified enterprise business information feature data storage module;

[0115] The enterprise historical business information characteristic data collection module collects the historical production and operation information characteristic data of the target enterprise online through the enterprise production and operation data management unit to generate the enterprise historical business information characteristic data;

[0116] The enterprise historical business information characteristic data clustering module uses an agglomerative hierarchical clustering algorithm to perform data clustering processing on the enterprise historical business information characteristic data in the enterprise historical business information characteristic data set to generate enterprise historical business information clustering characteristic data, stores the enterprise historical business information clustering characteristic data in the enterprise management data storage unit, and enters the corresponding enterprise business information category text characteristic data for each category of enterprise historical business information clustering characteristic data through the enterprise business information category text entry interface;

[0117] The to-be-classified enterprise business information data collection module collects the to-be-classified production and operation information data of the target enterprise online through the to-be-classified enterprise business information input interface to generate the to-be-classified enterprise business information data;

[0118] The enterprise business information data preprocessing module to be classified uses a wavelet transform filtering method to perform filtering and noise reduction processing on the enterprise business information data to be classified, and generates characteristic data of the enterprise business information to be classified;

[0119] The enterprise business information category text feature data search module performs enterprise business information category text feature data search processing on the enterprise business information feature data to be classified and the enterprise business information category text feature data through a flower pollination optimization algorithm, and generates enterprise business information category text feature data to be classified according to the enterprise business information category text feature data search processing result;

[0120] The enterprise business information to be classified feature data storage module stores the enterprise business information to be classified feature data in the enterprise management data storage unit according to the enterprise business information category text feature data to be classified, and pushes the enterprise business information category text feature data to the enterprise management data storage result platform.

[0121] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0122] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A method for intelligent classification and storage of enterprise management data based on big data, characterized in that: The steps include: S1. Collect the characteristic data of the enterprise's historical business information; S2. Perform data clustering processing on the enterprise historical business information feature data by using a clustering algorithm to generate enterprise historical business information cluster feature data, store the enterprise historical business information cluster feature data in an enterprise management data storage unit, and set corresponding enterprise business information category text feature data for each category of enterprise historical business information cluster feature data; S3. Collecting business information data of enterprises to be classified; S4, performing data preprocessing on the enterprise business information data to be classified to generate characteristic data of the enterprise business information to be classified; S5, performing a search process on the enterprise business information category text feature data to be classified according to the enterprise business information feature data to be classified and the enterprise business information category text feature data to generate the enterprise business information category text feature data to be classified; S6. Storing the enterprise business information feature data to be classified in an enterprise management data storage unit according to the enterprise business information category text feature data to be classified, and pushing the enterprise business information category text feature data to be classified to an enterprise management data storage result platform.

2. According to the method for intelligent classification and storage of enterprise management data based on big data according to claim 1, it is characterized in that: The S1 comprises the following steps: S11, collect the historical production and operation information feature data of the target enterprise online through the enterprise production and operation data management unit, and generate the enterprise historical business information feature data set A = {a1, a2, ..., a i ,…,a k }, where a i represents the i-th historical production and operation information characteristic data of the target enterprise collected online through the enterprise production and operation data management unit, k represents the total number of historical business information characteristic data of the enterprise, and the historical business information characteristic data of the enterprise includes but is not limited to the historical production information of the enterprise, the historical sales information of the enterprise, the historical market information of the enterprise, the historical financial information of the enterprise and the historical human resources information of the enterprise.

3. According to the method for intelligent classification and storage of enterprise management data based on big data in claim 2, it is characterized in that: The S2 comprises the following steps: S21, using an agglomerative hierarchical clustering algorithm to perform data clustering processing on the enterprise historical business information feature data in the enterprise historical business information feature data set, to generate an enterprise historical business information cluster feature data set B = {b1, b2, ..., b i ,…,b l }, where b i represents the clustering feature data of the historical business information of the i-th type of enterprise obtained after data clustering processing, and l represents the total number of clustering feature data of the historical business information of the enterprise; 22. Store the various types of enterprise historical business information clustering feature data in the enterprise historical business information clustering feature data set in the enterprise management data storage unit in turn, and enter the corresponding enterprise business information category text feature data for each type of enterprise historical business information clustering feature data through the enterprise business information category text entry interface to generate an enterprise business information category text feature data set C = {c1, c2, …, c i ,…,c l }, where c i Represents the enterprise business information category text feature data corresponding to the cluster feature data of the i-th category of enterprise historical business information.

4. The method for intelligent classification and storage of enterprise management data based on big data according to claim 3 is characterized in that: The S21 comprises the following steps: S211, treating each enterprise historical business information feature data in the enterprise historical business information feature data set as a cluster, calculating the Euclidean distance between clusters, and generating a distance matrix; S212, merging the two clusters corresponding to the minimum values ​​in the distance matrix into a new cluster, calculating the Euclidean distance between the new cluster and the other clusters, and updating the distance matrix; S213. Set a Euclidean distance threshold. If the minimum value in the distance matrix is ​​greater than or equal to the Euclidean distance threshold, end the data clustering processing operation and obtain a clustering feature data set of the enterprise's historical business information; otherwise, return to S212 until the minimum value in the distance matrix is ​​greater than or equal to the Euclidean distance threshold.

5. The method for intelligent classification and storage of enterprise management data based on big data according to claim 4 is characterized in that: The S3 comprises the following steps: S31. Collect the production and operation information data of the target enterprise to be classified online through the enterprise business information input interface to be classified, and generate the enterprise business information data D to be classified.

6. The method for intelligent classification and storage of enterprise management data based on big data according to claim 5 is characterized in that: The S4 comprises the following steps: S41, using a wavelet transform filtering method to perform filtering and noise reduction processing on the enterprise business information data D to be classified, to generate enterprise business information feature data D' to be classified.

7. The method for intelligent classification and storage of enterprise management data based on big data according to claim 6 is characterized in that: The S5 comprises the following steps: S51. Performing a search process on the enterprise business information category text feature data to be classified on the enterprise business information feature data D' to be classified and the enterprise business information category text feature data in the enterprise business information category text feature data set through a flower pollination optimization algorithm, and generating the enterprise business information category text feature data E to be classified according to the search process result of the enterprise business information category text feature data to be classified.

8. The method for intelligent classification and storage of enterprise management data based on big data according to claim 7 is characterized in that: The step S51 of generating the text feature data of the enterprise business information category to be classified includes the following steps: S511. Construct a pollen population, set the pollen population size to N, the conversion probability to p, the current number of iterations to t, and the maximum number of iterations to t max And the dimension of the search space of text feature data of enterprise business information category is P; Randomly generate N enterprise business information category text feature data in the enterprise business information category text feature data search space, each enterprise business information category text feature data corresponds to a pollen individual in the pollen population, and initialize the initial position set of the pollen population; S512, calculating the fitness function value of each pollen individual in the pollen population, arranging the pollen individuals in the pollen population from large to small according to the fitness function value, and selecting the pollen individual with the highest fitness function value as the current optimal individual; S513, setting a random number q that obeys a uniform distribution between [0,1] as a control coefficient, and controlling the pollination behavior of each pollen individual in the pollen population in the enterprise business information category text feature data search space through the control coefficient; S5131, when q≥p, each pollen individual in the pollen population is pollinated in the enterprise business information category text feature data search space by using biological cross-pollination to update the position; S5132, when q<p, each pollen individual in the pollen population pollinates in the enterprise business information category text feature data search space by non-biological self-pollination to update the position; S514, calculating the fitness function value of each pollen individual in the pollen population after the position is updated, if the fitness function value of the pollen individual after the position is updated is greater than the fitness function value before the position is updated, then the position of the pollen individual is updated; otherwise, the original position of the pollen individual is retained; Rearrange the pollen individuals in the pollen population from large to small according to the fitness function value, and select the pollen individual with the highest fitness function value as the new current optimal individual; S515: Determine whether t is less than t max , if t is less than t max , then t is increased by 1, and the process returns to S513; otherwise, the current optimal individual is taken as the global optimal solution; S516. Set a fitness function threshold. If the fitness function value of the global optimal solution is greater than or equal to the fitness function threshold, it is determined that the enterprise business information category text feature data corresponding to the global optimal solution matches the enterprise business information feature data to be classified successfully, and the enterprise business information category text feature data corresponding to the global optimal solution is output and data identification is performed to generate the enterprise business information category text feature data E to be classified; otherwise, it is determined that the enterprise business information category text feature data corresponding to the global optimal solution does not match the enterprise business information feature data to be classified, and the enterprise business information category text feature data E to be classified is output as temporarily stored business information.

9. The method for intelligent classification and storage of enterprise management data based on big data according to claim 8 is characterized in that: The S6 comprises the following steps: S61, storing the enterprise business information feature data D' to be classified into an enterprise management data storage unit according to the enterprise business information category text feature data E to be classified; If the enterprise business information category text feature data E to be classified is any enterprise business information category text feature data in the enterprise business information category text feature data set, then the enterprise business information category feature data D' to be classified is stored in the area where the enterprise historical business information cluster feature data corresponding to the enterprise business information category text feature data E to be classified is located in the enterprise management data storage unit; If the enterprise business information category text feature data E to be classified is not any enterprise business information category text feature data in the enterprise business information category text feature data set, a temporary area is divided in the enterprise management data storage unit, and the enterprise business information feature data D' to be classified is stored in the temporary area; S62: Push the to-be-classified enterprise business information category text feature data to the enterprise management data storage result platform via a wireless communication network and display it on a display screen.

10. A system for implementing the method for intelligent classification and storage of enterprise management data based on big data as described in any one of claims 1 to 9.

Images