Data processing method and system based on enterprise management and storage medium

Abstract

The invention provides a data processing method and system based on enterprise management and a storage medium, and relates to the technical field of data processing, original sample data in the enterprise management is acquired, and text vector conversion is performed on the original sample data to obtain text vector representation data in the enterprise management; clustering and dividing the text vector representation data to obtain a plurality of text vector clusters, selecting one text vector cluster, determining the cluster aggregation degree of the selected text vector cluster in each clustering process, and determining a data convergence and dispersion factor through all the cluster aggregation degrees; the method comprises the steps of obtaining text vector representation data, adjusting and controlling the clustering number of clustering division according to a data convergence and dispersion factor to obtain a final clustering number, performing clustering division on the text vector representation data by using the final clustering number, and generating interest text data in enterprise management according to a clustering division result. The data clustering effect in enterprise management is improved, and interest data of enterprise management is generated.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and more specifically, to a data processing method, system and storage medium based on enterprise management. Background Art

[0002] In modern enterprise management, data has become an important asset for enterprises to optimize decision-making, improve operational efficiency and enhance market competitiveness. Data processing based on enterprise management mainly involves data collection, storage, cleaning, analysis and application to support multiple business areas such as financial management, human resources, marketing, supply chain optimization, etc. Enterprise data comes from a wide range of sources, including financial statements, customer transaction records, employee performance data, market trend analysis, social media data, etc. These data can provide comprehensive insights into the operating status of enterprises through efficient data processing technologies such as data mining, machine learning, natural language processing (NLP), etc., and assist decision makers in making more accurate strategic adjustments.

[0003] However, in actual applications, due to the large amount of information in enterprise management, the information is disorganized, and the data information is relatively scattered, so the process of obtaining key information in enterprise management is relatively complicated, and each text information needs to be checked one by one, which takes a long time and is inefficient, making it more difficult for enterprises to find key project information of interest. Therefore, it is necessary to cluster the original sample data according to the business field of the enterprise or the project direction of interest to form project information of the enterprise's interest category. The existing K-Means clustering algorithm is simple and easy to use, with fast computing speed, high clustering accuracy, and good processing capabilities in processing large-scale data. However, the K-Means clustering algorithm requires the number of clusters to be set in advance, which is subjective, resulting in unsatisfactory final clustering effect and failure to generate the interest data required for enterprise management. Summary of the invention

[0004] The present application provides a data processing method, system and storage medium based on enterprise management, which can screen out the accurate number of clusters to improve the data clustering effect in enterprise management and help generate interest data for enterprise management.

[0005] In a first aspect, the present application provides a data processing method based on enterprise management, the processing method comprising the following steps: Acquire original sample data in enterprise management, perform text vector conversion on the original sample data, and then obtain text vector representation data in enterprise management; Clustering the text vector representation data to obtain multiple text vector families, then selecting a text vector family, determining the family aggregation degree of the selected text vector family in each clustering process, and determining the data convergence factor through all the family aggregation degrees; The number of clusters of the clustering division is regulated according to the data convergence factor to obtain the final number of clusters, and the text vector representation data is clustered using the final number of clusters, and then the text data of interest in enterprise management is generated according to the clustering result.

[0006] In this embodiment, the text vector conversion is performed on the original sample data to obtain the text vector representation data in enterprise management, which specifically includes: Performing text preprocessing on the original sample data to obtain preprocessed sample data; The pre-processed sample data is transformed into vectors using a text vector space model, thereby obtaining text vector representation data for enterprise management.

[0007] In this embodiment, the text vector representation data is clustered according to a preset number of clusters.

[0008] In this embodiment, determining the clustering degree of the selected text vector cluster in each clustering process specifically includes: For each clustering process in clustering partitioning, the total number of text feature items in the text vector family selected in the clustering process is obtained; Determining the vector cluster center of the text vector cluster selected in the clustering process; Determining the feature closeness between each text feature item in the selected text vector cluster and the center of the vector cluster in the clustering process; The cluster aggregation degree of the selected text vector cluster in the clustering process is determined according to the total number of text feature items, the vector cluster center and all feature compactness, and then the cluster aggregation degree of the selected text vector cluster in each clustering process is obtained.

[0009] In this embodiment, the data convergence factor is determined by all cluster aggregation degrees, and the data convergence factor is determined according to the following formula: in, represents the data convergence factor, n represents the total number of clusters in the clustering partition, and They represent the clustering degree of the selected text vector family in the i-th and i+1-th clustering processes respectively.

[0010] In this embodiment, the number of clusters of cluster division is regulated according to the data convergence factor, and the final number of clusters is obtained, which specifically includes: Obtain a preset convergence and divergence threshold; When the data convergence and divergence factor is less than the convergence and divergence threshold, the preset number of clusters is used as the final number of clusters; When the data convergence and divergence factor is not less than the convergence and divergence threshold, the pre-set number of clusters is updated, and the updated number of clusters is used to cluster the text vector representation data, and then a new data convergence and divergence factor is determined, and the above steps are repeated until the new data convergence and divergence factor is less than the convergence and divergence threshold, and the last updated number of clusters is used as the final number of clusters.

[0011] In this embodiment, using the final number of clusters to cluster the text vector representation data is to use the final number of clusters as the K value in the K-Means clustering algorithm to cluster the text vector representation data.

[0012] In this embodiment, generating the text data of interest in enterprise management according to the clustering results specifically includes: Determine the management interest corresponding to each data family in the clustering result; Filter out all data families whose management interest is greater than the set interest threshold; Generate text data of interest in enterprise management based on all filtered data families.

[0013] In a second aspect, the present application provides a data processing system based on enterprise management, for executing a data processing method based on enterprise management, the processing system comprising: A text conversion module is used to obtain original sample data in enterprise management, convert the original sample data into text vectors, and then obtain text vector representation data in enterprise management; A data processing module is used to cluster the text vector representation data to obtain multiple text vector families, and then select a text vector family, determine the family aggregation degree of the selected text vector family in each clustering process, and determine the data convergence factor through all the family aggregation degrees; The text generation module is used to adjust the number of clusters of the clustering division according to the data convergence factor, and then obtain the final number of clusters, use the final number of clusters to cluster the text vector representation data, and then generate interest text data in enterprise management based on the clustering division results.

[0014] In a third aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned data processing method based on enterprise management when executing.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: By acquiring original sample data in enterprise management, the original sample data is converted into text vectors, and then the text vector representation data in enterprise management is obtained; the text vector representation data is clustered to obtain multiple text vector families, and then a text vector family is selected, and the family aggregation degree of the selected text vector family in each clustering process is determined, and the data convergence factor is determined by all the family aggregation degrees; the number of clusters of cluster division is adjusted according to the data convergence factor, and then the final number of clusters is obtained, and the text vector representation data is clustered using the final number of clusters, and then the interest text data in enterprise management is generated according to the cluster division result.

[0016] It can be seen that in this application, firstly, the original sample data can be converted into processable data through text vector conversion; then, by clustering the data represented by the text vector and calculating the clustering degree of each cluster, the compactness within each cluster can be quantified, and the data convergence factor can be further determined by the clustering degree of all clusters, which helps to measure the compactness and discreteness of the overall data distribution, thereby optimizing the selection of the number of clusters; finally, the number of clusters can be adjusted according to the data convergence factor, which can effectively improve the accuracy and availability of the clustering results, thereby improving the effect of data clustering, and then improving the clustering effect, and finally generating more valuable text data of interest.

[0017] In summary, the technical solution adopted in this application can screen out the accurate number of clusters to improve the data clustering effect in enterprise management and help generate interest data for enterprise management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 is a flow chart of a data processing method based on enterprise management provided by the present application; Figure 2 is an exemplary flow chart for determining the clustering degree of a selected text vector cluster in each clustering process according to the present application; Figure 3 is an exemplary flow chart for generating interest text data in enterprise management according to the present application; Figure 4 It is a module structure diagram of the data processing system based on enterprise management provided by this application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The embodiment of the present application provides a data processing method, system and storage medium based on enterprise management, the core of which is to obtain the original sample data in enterprise management, perform text vector conversion on the original sample data, and then obtain the text vector representation data in enterprise management; cluster the text vector representation data to obtain multiple text vector families, and then select a text vector family, determine the family aggregation degree of the selected text vector family in each clustering process, and determine the data convergence factor through all family aggregation degrees; regulate the number of clusters of cluster division according to the data convergence factor, and then obtain the final number of clusters, use the final number of clusters to cluster the text vector representation data, and then generate the interest text data in enterprise management according to the cluster division results. The above scheme can screen out the accurate number of clusters to improve the data clustering effect in enterprise management and help generate interest data for enterprise management.

[0022] Embodiment 1: In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG. 1 , this figure is an exemplary flow chart of a data processing method based on enterprise management according to this embodiment of the present application, and the processing method includes the following steps: In step S1, original sample data in enterprise management is obtained, and text vectors are converted to the original sample data to obtain text vector representation data in enterprise management.

[0023] In specific implementation, original sample data related to enterprise management can be obtained from a database through a data management system in the enterprise. The original sample data is a data set consisting of text.

[0024] In this embodiment, the original sample data is converted into text vectors to obtain text vector representation data in enterprise management, which can be specifically implemented in the following manner, namely: Performing text preprocessing on the original sample data to obtain preprocessed sample data; The pre-processed sample data is transformed into vectors using a text vector space model, thereby obtaining text vector representation data for enterprise management.

[0025] In specific implementation, first, the original sample data can be subjected to text preprocessing, that is, data cleaning (such as noise removal, deduplication, stop word removal and text standardization), word segmentation and part-of-speech tagging, word form restoration and spelling checking, so as to obtain preprocessed sample data; then, the preprocessed sample data can be vectorized using a text vector space model, that is, the text in the preprocessed sample data is converted into multiple text feature items, and the data set composed of all text feature items is used as text vector representation data in enterprise management.

[0026] It should be noted that the original sample data can be converted into processable data through text vector conversion, and the redundancy in the data can be reduced through preprocessing, thereby improving the efficiency and accuracy of subsequent processing.

[0027] In step S2, the text vector representation data is clustered to obtain multiple text vector families, and then a text vector family is selected, and the family aggregation degree of the selected text vector family in each clustering process is determined, and the data convergence factor is determined through all the family aggregation degrees.

[0028] In this embodiment, the text vector representation data is clustered according to a preset number of clusters to obtain a plurality of text vector families, wherein the text vector families are data clusters of text feature items obtained through clustering; in specific implementation, the number of clusters can be set according to historical experiments, so that the preset number of clusters can be used as the K value in the K-Means clustering algorithm to cluster the text vector representation data, so that a plurality of text vector families can be obtained.

[0029] Preferably, in this embodiment, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart of determining the class aggregation degree of the selected text vector family in each clustering process in an embodiment of the present application. In this embodiment, determining the class aggregation degree of the selected text vector family in each clustering process can be specifically implemented by the following steps: First, in step S21, for each clustering process in clustering division, the total number of text feature items in the text vector family selected in the clustering process is obtained; Then, in step S22, the vector cluster center of the selected text vector cluster in the clustering process is determined; Secondly, in step S23, the feature closeness between each text feature item in the text vector cluster selected in the clustering process and the center of the vector cluster is determined; Finally, in step S24, the cluster aggregation degree of the selected text vector cluster in the clustering process is determined according to the total number of text feature items, the vector cluster center and all feature densities, and then the cluster aggregation degree of the selected text vector cluster in each clustering process is obtained.

[0030] In the specific implementation, first, for each clustering process in the clustering division, the total number of text feature items in the selected text vector family in the clustering process can be obtained by traversal; then, the vector family center of the selected text vector family in the clustering process can be determined, wherein the vector family center is the data center of the selected text vector family, and the mean of all text feature items in the selected text vector family can be calculated, so as to use the result as the vector family center of the selected text vector family in this clustering; secondly, the feature closeness between each text feature item in the selected text vector family and the vector family center can be determined in the clustering process, wherein the Feature closeness indicates the closeness of the connection between the text feature item and the vector family center. The data similarity between the text feature item and the vector family center can be used as the feature closeness between each text feature item and the vector family center in the selected text vector family in this clustering; finally, the family aggregation degree of the selected text vector family in the clustering process can be determined according to the total number of text feature items, the vector family center and all feature closeness, where the family aggregation degree is an indicator of the overall aggregation degree of all text feature items in the selected text vector family in the clustering process. In actual implementation, the family aggregation degree can be determined according to the following formula: in, represents the clustering degree of the selected text vector family in the i-th clustering process, Represents the total number of text feature items contained in the selected text vector family in the i-th clustering process, Represents text feature items With the vector family center The feature closeness between represents the jth text feature item in the selected text vector family, It represents the vector family center of the selected text vector family in the i-th clustering process. The family aggregation degree of the selected text vector family in each clustering process can be obtained by the above method.

[0031] In this embodiment, the data convergence factor is determined by all cluster aggregation degrees, and the data convergence factor is determined according to the following formula: in, represents the data convergence factor, n represents the total number of clusters in the clustering partition, and They respectively represent the clustering degree of the selected text vector family in the i-th and i+1-th clustering processes. The data convergence factor is an indicator of the data convergence degree of the clustering division results. The smaller the data convergence factor, the higher the data convergence degree of the clustering division results, and the smoother the data changes in the divided text vector family.

[0032] It should be noted that by clustering the text vector representation data and calculating the clustering degree of each cluster, the compactness within each cluster can be quantified. The data convergence factor can be further determined through the aggregation degree of all clusters, which helps to measure the compactness and dispersion of the overall data distribution, thereby optimizing the selection of the number of clusters. Traditional methods (such as the silhouette coefficient and the elbow method) are not sensitive to text data, while the clustering degree combined with the data convergence factor can more accurately measure the data structure, thereby selecting the accurate number of clusters.

[0033] In step S3, the number of clusters of the clustering division is adjusted according to the data convergence factor to obtain the final number of clusters, and the text vector representation data is clustered using the final number of clusters, and then the interest text data in enterprise management is generated based on the clustering results.

[0034] In this embodiment, the number of clusters of cluster division is regulated according to the data convergence factor, and the final number of clusters can be obtained in the following manner, namely: Obtain a preset convergence and divergence threshold; When the data convergence and divergence factor is less than the convergence and divergence threshold, the preset number of clusters is used as the final number of clusters; When the data convergence and divergence factor is not less than the convergence and divergence threshold, the pre-set number of clusters is updated, and the updated number of clusters is used to cluster the text vector representation data, and then a new data convergence and divergence factor is determined, and the above steps are repeated until the new data convergence and divergence factor is less than the convergence and divergence threshold, and the last updated number of clusters is used as the final number of clusters.

[0035] In specific implementation, first, a pre-set convergence and divergence threshold can be obtained. The convergence and divergence threshold can be set by experience or cross-validation method, which will not be repeated here; then, the data convergence and divergence factor is compared with the pre-set convergence and divergence threshold. When the data convergence and divergence factor is less than the convergence and divergence threshold, the pre-set number of clusters can be used as the final number of clusters; when the data convergence and divergence factor is not less than the convergence and divergence threshold, the pre-set number of clusters is updated, that is, the value of the number of clusters can be changed. The updated number of clusters is used as the K value in the K-Means clustering algorithm to cluster the text vector representation data, and the new data convergence and divergence factor is determined by the method in step S2. The above steps are repeated until the new data convergence and divergence factor is less than the convergence and divergence threshold, and the last updated number of clusters is used as the final number of clusters.

[0036] In this embodiment, clustering the text vector representation data using the final number of clusters is to cluster the text vector representation data using the final number of clusters as the K value in the K-Means clustering algorithm. In specific implementation, the text vector representation data is clustered by using the final number of clusters as the K value in the K-Means clustering algorithm, thereby obtaining a clustering result including multiple data families.

[0037] Preferably, in this embodiment, reference Figure 3 As shown, this figure is an exemplary flow chart of generating interest text data in enterprise management in an embodiment of the present application. In this embodiment, generating interest text data in enterprise management according to the clustering results can be implemented by the following steps: First, in step S31, the management interest level corresponding to each data cluster in the clustering result is determined; Then, in step S32, all data clusters whose management interest is greater than a set interest threshold are screened out; Finally, in step S33, text data of interest in enterprise management is generated based on all the screened data families.

[0038] In specific implementation, the management interest corresponding to each data family in the clustering result can be determined, where the management interest is an indicator of the importance of the data family relative to enterprise management, and the management goal can be clarified. The goal of enterprise management usually covers multiple aspects, such as financial management, marketing, human resources, operational efficiency, etc. When analyzing text data, it is necessary to clarify the current management goals of the enterprise. For example, if the enterprise is currently concerned about cost control, the text related to financial management will have a higher relevance, so that the text content of each data family can be compared with the enterprise goals. According to common terms and vocabulary in the management field (such as "financial statements", "market share", "employee performance", etc.), the keywords in the text content of each data family can be matched and the matching degree can be calculated. The matching degree can be used as the management interest corresponding to each data family.

[0039] In addition, in the specific implementation, an interest threshold can be set, and the interest threshold can be set according to the company's historical experience and data analysis. For each data family, if its management interest is greater than the set interest threshold, it is considered that the data family contains important management information. By comparing the interest of each data family with the interest threshold, qualified data families can be screened out; then, interest text data in enterprise management can be generated based on all the screened data families, and keywords or subject terms can be extracted from the screened data families. These keywords should be able to clearly represent the management theme of the data family. A brief summary is generated for each screened data family, and the core content of the data family is extracted for reference by enterprise managers.

[0040] It should be noted that regulating the number of clusters according to the data convergence factor can effectively improve the accuracy and availability of the clustering results. Specifically, by dynamically adjusting the number of clusters, it can ensure that the similarity within each data family is higher and the differences between families are greater, thereby improving the effect of data clustering, and then improving the clustering effect, and ultimately generating more valuable interest text data, directly assisting enterprise management decisions and business insights.

[0041] It can be seen that in this application, firstly, the original sample data can be converted into processable data through text vector conversion; then, by clustering the data represented by the text vector and calculating the clustering degree of each cluster, the compactness within each cluster can be quantified, and the data convergence factor can be further determined by the clustering degree of all clusters, which helps to measure the compactness and discreteness of the overall data distribution, thereby optimizing the selection of the number of clusters; finally, the number of clusters can be adjusted according to the data convergence factor, which can effectively improve the accuracy and availability of the clustering results, thereby improving the effect of data clustering, and then improving the clustering effect, and finally generating more valuable text data of interest.

[0042] In summary, the technical solution adopted in this application can screen out the accurate number of clusters to improve the data clustering effect in enterprise management and help generate interest data for enterprise management.

[0043] Embodiment 2: This application provides a data processing system based on enterprise management, referring to Figure 4 As shown, this figure is a schematic diagram of a processing system according to this embodiment of the present application, and the processing system includes: The text conversion module 100 is used to obtain original sample data in enterprise management, perform text vector conversion on the original sample data, and then obtain text vector representation data in enterprise management; The data processing module 200 is used to cluster the text vector representation data to obtain multiple text vector families, and then select a text vector family, determine the family aggregation degree of the selected text vector family in each clustering process, and determine the data convergence factor through all the family aggregation degrees; The text generation module 300 is used to adjust the number of clusters of the clustering division according to the data convergence factor, and then obtain the final number of clusters, use the final number of clusters to cluster the text vector representation data, and then generate interest text data in enterprise management based on the clustering division results.

[0044] In a third embodiment, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are executed on a computer, the computer implements the above-mentioned data processing method based on enterprise management.

[0045] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0046] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically-erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0047] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A data processing method based on enterprise management, characterized in that: The processing method comprises the following steps: Acquire original sample data in enterprise management, perform text vector conversion on the original sample data, and then obtain text vector representation data in enterprise management; Clustering the text vector representation data to obtain multiple text vector families, then selecting a text vector family, determining the family aggregation degree of the selected text vector family in each clustering process, and determining the data convergence factor through all the family aggregation degrees; The number of clusters of the clustering division is regulated according to the data convergence factor to obtain the final number of clusters, and the text vector representation data is clustered using the final number of clusters, and then the text data of interest in enterprise management is generated according to the clustering result.

2. A data processing method based on enterprise management as claimed in claim 1, characterized in that: The original sample data is converted into a text vector to obtain text vector representation data in enterprise management, which specifically includes: Performing text preprocessing on the original sample data to obtain preprocessed sample data; The pre-processed sample data is transformed into vectors using a text vector space model, thereby obtaining text vector representation data for enterprise management.

3. A data processing method based on enterprise management as claimed in claim 1, characterized in that: The text vector representation data is clustered and divided according to a preset number of clusters.

4. A data processing method based on enterprise management as claimed in claim 1, characterized in that: Determining the clustering degree of the selected text vector cluster in each clustering process specifically includes: For each clustering process in clustering partitioning, the total number of text feature items in the text vector family selected in the clustering process is obtained; Determining the vector cluster center of the text vector cluster selected in the clustering process; Determining the feature closeness between each text feature item in the selected text vector cluster and the center of the vector cluster in the clustering process; The cluster aggregation degree of the selected text vector cluster in the clustering process is determined according to the total number of text feature items, the vector cluster center and all feature compactness, and then the cluster aggregation degree of the selected text vector cluster in each clustering process is obtained.

5. A data processing method based on enterprise management as claimed in claim 1, characterized in that: The data convergence factor is determined by all cluster aggregation degrees, and the data convergence factor is determined according to the following formula: in, represents the data convergence factor, n represents the total number of clusters in the clustering partition, and They represent the clustering degree of the selected text vector family in the i-th and i+1-th clustering processes respectively.

6. A data processing method based on enterprise management as claimed in claim 1, characterized in that: The number of clusters of cluster division is regulated according to the data convergence and divergence factor, and the final number of clusters is obtained, which specifically includes: Obtain a preset convergence and divergence threshold; When the data convergence and divergence factor is less than the convergence and divergence threshold, the preset number of clusters is used as the final number of clusters; When the data convergence and divergence factor is not less than the convergence and divergence threshold, the pre-set number of clusters is updated, and the updated number of clusters is used to cluster the text vector representation data, and then a new data convergence and divergence factor is determined, and the above steps are repeated until the new data convergence and divergence factor is less than the convergence and divergence threshold, and the last updated number of clusters is used as the final number of clusters.

7. A data processing method based on enterprise management as claimed in claim 1, characterized in that: Using the final number of clusters to cluster the text vector representation data is to use the final number of clusters as the K value in the K-Means clustering algorithm to cluster the text vector representation data.

8. A data processing method based on enterprise management as claimed in claim 1, characterized in that: The interest text data in enterprise management generated based on the clustering results specifically includes: Determine the management interest corresponding to each data family in the clustering result; Filter out all data families whose management interest is greater than the set interest threshold; Generate text data of interest in enterprise management based on all filtered data families.

9. A data processing system based on enterprise management, used to execute a data processing method based on enterprise management as claimed in any one of claims 1 to 8, characterized in that: The processing system comprises: A text conversion module is used to obtain original sample data in enterprise management, convert the original sample data into text vectors, and then obtain text vector representation data in enterprise management; A data processing module is used to cluster the text vector representation data to obtain multiple text vector families, and then select a text vector family, determine the family aggregation degree of the selected text vector family in each clustering process, and determine the data convergence factor through all the family aggregation degrees; The text generation module is used to adjust the number of clusters of the clustering division according to the data convergence factor, and then obtain the final number of clusters, use the final number of clusters to cluster the text vector representation data, and then generate interest text data in enterprise management based on the clustering division results.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the data processing method based on enterprise management as described in any one of claims 1 to 8.

Images