Enterprise data element treatment method and device based on big data

Abstract

The invention discloses an enterprise data element governance method and device based on big data, and the method comprises the steps: determining a target enterprise needing data element governance, and collecting the public data information of the target enterprise; dividing the public data information into a plurality of data classifications according to data correlation; determining a weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise; determining a mapping relationship between the data classification and the data element tag according to the historical data classification and the historical data element tag, and determining a target data tag of the target enterprise according to the mapping relationship; and according to the target data label and the weight coefficient, generating a target enterprise portrait to complete data element treatment of the target enterprise. According to the method, the data can be classified, weight analysis is carried out by utilizing the multi-dimensional data, specific labels can be conveniently marked on each type of data, the enterprise portraits are generated according to the labels and the corresponding weight coefficients, and convenience is provided for subsequent data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data mining, and in particular, to a method and device for enterprise data element governance based on big data. Background Art

[0002] With the development of big data, "digital transformation" has become the main theme of development in all walks of life. Enterprises are the basic units of social and economic activities and play an important role in promoting the development of the data economy.

[0003] At present, the main difficulty in the digital transformation of enterprises lies in the lack of understanding of their own development status and market competitiveness, which leads to the inability to accurately formulate development strategies that meet their own needs.

[0004] Therefore, it is becoming increasingly important to build a corporate portrait.

[0005] Corporate portraits can utilize multi-dimensional views of data to objectively and truly reflect the characteristics of each company.

[0006] Currently, the way to generate corporate portraits is usually to analyze the company's public data to generate a series of corporate labels.

[0007] Faced with massive amounts of public corporate information, data labelers often have to manually label it, which consumes a lot of manpower costs.

[0008] There are some technologies on the market that use machine learning to analyze public data and generate labels, but this method is less targeted. In the face of huge amounts of public corporate data, the workload of data analysis is very large, and the types and quantities of labels generated are disorganized, which is not conducive to generating corporate portraits with reference value.

[0009] Therefore, people in this field are in urgent need of finding a new technical solution to solve the above problems. Summary of the invention

[0010] In order to overcome the problems existing in the related art, the present invention discloses a method and device for enterprise data element governance based on big data.

[0011] According to a first aspect of an embodiment disclosed in the present invention, a method for enterprise data element governance based on big data is provided, the method comprising: Identify target enterprises that require data element governance and collect public data information of the target enterprises; Dividing the public data information into several data categories according to data relevance; Determine a weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise; Determine a mapping relationship between the data classification and the data element label according to the historical data classification and the historical data element label, so as to determine a target data label of the target enterprise according to the mapping relationship; Based on the target data labels and weight coefficients, a target enterprise portrait is generated to complete the data element governance of the target enterprise.

[0012] Optionally, the determining of the target enterprise that needs to be subject to data element governance and the collection of public data information of the target enterprise include: Identify target enterprises that require data element governance; Collect public data information of the target enterprise from public channels.

[0013] Optionally, the public data information is divided into several data categories according to data relevance, including: For each piece of public data information , respectively calculate the public data information Other public data information The first correlation coefficient between , obtain the first correlation coefficient between the public data information, where, is the expected value; Classify the public data information whose first correlation coefficient is greater than a preset coefficient threshold into a data category; Get several data categories.

[0014] Optionally, determining a weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise includes: According to the correlation between the enterprise type and the data classification, the weight coefficient corresponding to each data classification is determined ,in, is the second correlation coefficient between the ith data classification and the enterprise type, is the maximum value of the second correlation coefficient between all data classifications and enterprise types, It is the minimum value of the second correlation coefficient between all data categories and enterprise types; The method for obtaining the second correlation coefficient is: For each data category, obtain each public data information in the data category The third correlation coefficient between the enterprise type y ; The average of all the third correlation coefficients in the data classification is calculated to obtain the second correlation coefficient between the i-th data classification and the enterprise type.

[0015] Optionally, determining a mapping relationship between data classification and data element label according to historical data classification and historical data element label, and determining a target data label of the target enterprise according to the mapping relationship, includes: According to the historical mapping relationship between historical data classification and historical data element label, each piece of historical public data information in the historical data classification is used as input, and the historical data element label corresponding to the historical data classification is used as output, and the neural network model is trained to obtain a trained data element label generation model; Each piece of public data information in the data classification is used as the input of the data element label generation model, and the data element label corresponding to each data classification of the target enterprise is obtained according to the output of the data element label generation model.

[0016] Optionally, the method further includes: Provide a visual display of the target enterprise portrait.

[0017] According to a second aspect of the disclosed embodiment of the present invention, there is provided an enterprise data element governance device based on big data, the device comprising: The data collection module determines the target enterprises that need to be subject to data element governance and collects the public data information of the target enterprises; A data classification module, connected to the data collection module, divides the public data information into several data categories according to data relevance; A weight coefficient determination module, connected to the data classification module, determines a weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise; A data label determination module, connected to the weight coefficient determination module, determines a mapping relationship between data classification and data element label according to historical data classification and historical data element label, so as to determine a target data label of the target enterprise according to the mapping relationship; The enterprise portrait generation module is connected to the data label determination module, and generates a target enterprise portrait according to the target data label and weight coefficient to complete the data element governance of the target enterprise.

[0018] Optionally, the data classification module includes: The first correlation coefficient determination unit, for each piece of public data information , respectively calculate the public data information Other public data information The first correlation coefficient between , obtain the first correlation coefficient between the public data information, where, is the expected value; A data classification unit, connected to the first correlation coefficient determination unit, classifies public data information whose first correlation coefficient is greater than a preset coefficient threshold into a data classification; The data classification acquisition unit is connected to the data classification unit and acquires a plurality of data classifications.

[0019] Optionally, the weight coefficient determination module includes: According to the correlation between the enterprise type and the data classification, the weight coefficient corresponding to each data classification is determined ,in, is the second correlation coefficient between the ith data classification and the enterprise type, is the maximum value of the second correlation coefficient between all data classifications and enterprise types, The minimum value of the second correlation coefficient between all data categories and enterprise types; The method for obtaining the second correlation coefficient is: For each data category, obtain each public data information in the data category The third correlation coefficient between the enterprise type y ; The average of all the third correlation coefficients in the data classification is calculated to obtain the second correlation coefficient between the i-th data classification and the enterprise type.

[0020] Optionally, the data tag determination module includes: The model training unit, according to the historical mapping relationship between the historical data classification and the historical data element label, takes each piece of historical public data information in the historical data classification as input, takes the historical data element label corresponding to the historical data classification as output, trains the neural network model, and obtains the trained data element label generation model; The data label acquisition unit is connected to the model training unit, takes each public data information in the data classification as the input of the data element label generation model, and obtains the data element label corresponding to each data classification of the target enterprise according to the output of the data element label generation model.

[0021] In summary, the present invention discloses a method and device for enterprise data element governance based on big data, the method comprising: determining a target enterprise that needs to perform data element governance, and collecting public data information of the target enterprise; dividing the public data information into a number of data categories according to data relevance; determining a weight coefficient corresponding to each data category according to the enterprise type of the target enterprise; determining a mapping relationship between data classification and data element label according to historical data classification and historical data element label, so as to determine a target data label of the target enterprise according to the mapping relationship; generating a target enterprise portrait according to the target data label and the weight coefficient, so as to complete data element governance of the target enterprise.

[0022] It is possible to classify the data and use multi-dimensional data for weight analysis, so as to label each type of data with specific labels, generate corporate portraits based on the labels and corresponding weight coefficients, and facilitate subsequent data processing.

[0023] Other features and advantages disclosed in the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to provide further understanding of the present disclosure and constitute a part of the specification. They are used to explain the present disclosure together with the following detailed description, but do not constitute a limitation of the present disclosure.

[0025] In the attached picture: Figure 1 It is a flowchart of a method for managing enterprise data elements based on big data according to an exemplary embodiment; Figure 2 is based on Figure 1 A flow chart of a data classification method is shown; Figure 3 is based on Figure 1 A flow chart of a method for obtaining data tags is shown; Figure 4 It is a structural block diagram of an enterprise data element management device based on big data according to an exemplary embodiment; Figure 5 is based on Figure 4 A structural block diagram of a data classification module is shown; Figure 6 is based on Figure 4 A structural block diagram of a data tag determination module is shown. DETAILED DESCRIPTION

[0026] The specific embodiments disclosed in the present invention are described in detail below with reference to the accompanying drawings.

[0027] It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, but not to limit the present disclosure.

[0028] Figure 1 is a flowchart of a method for managing enterprise data elements based on big data according to an exemplary embodiment. Figure 1 As shown, the method includes: In step 101, the target enterprise that needs to be subject to data element governance is determined, and the public data information of the target enterprise is collected.

[0029] For example, determine the target enterprise that needs to conduct data element governance; collect public data information of the target enterprise from public channels.

[0030] Public channels include: official corporate websites, patent databases, brand registration information, recruitment websites, business query platforms, etc. The company's public information is obtained from the above channels to conduct a multi-dimensional analysis of the company's public data information.

[0031] Public data information obtained from public channels may include: business income, number of social security personnel, industry in which the company is located, types and amount of data assets owned, recruitment data, land use, bidding, patents, software copyrights, news, major authoritative certification lists, etc.

[0032] It is understandable that the methods for obtaining public data information may be: cloud computing service technology, artificial intelligence technology, manual collection by data collectors or provision by third parties, etc.

[0033] In addition, in addition to data obtained from public channels, information data from the target company's internal management system or data provided by a third party can also be integrated to increase data source channels in order to more comprehensively analyze the target company's data element labels.

[0034] It should be noted that enterprises that conduct data element governance usually include: (a) Data resource enterprises: enterprises that own data resources, take data as their core assets, or engage in the integration and utilization of industrial chain data, with data acquisition, accumulation, management and analysis as their core business activities.

[0035] (2) Data technology enterprises: engage in data computing, storage, mining and analysis, and have technical service capabilities such as data aggregation, storage, governance, transmission, management, security and development of algorithm models. They can use technical means or data tools to improve data quality, realize data factorization, and provide basic conditions for data application empowerment.

[0036] (III) Data application enterprises: Focusing on key industrial fields such as intelligent manufacturing, low-altitude economy, intelligent connected vehicles, digital finance, medical health, digital culture, commerce, and logistics, use the accumulated data and public data of enterprises or industries to empower the entire process of enterprise R&D and production and the deep transformation of the industry, improve the experience of life scenarios, and promote business model innovation.

[0037] (IV) Data service companies: With market demand as the core, by providing professional data asset entry, quality assessment, compliance consulting, security assessment and other services, we help companies better understand and use data, thereby improving the company's decision-making quality, operational efficiency, market competitiveness and innovation and development level.

[0038] (V) Data security enterprises: mainly provide network security, information security, and data security protection, and provide services such as classification and grading of sensitive enterprise data, data desensitization, deep access control, security inspection, prevention of data leakage, and traceability to achieve reliable and secure data circulation.

[0039] (6) Data infrastructure enterprises: construction and operation of network infrastructure (5G, Industrial Internet, Internet of Things, etc.), computing power infrastructure (data centers, intelligent computing centers, supercomputing centers, cloud computing, etc.), data circulation facilities (data space, blockchain platform, privacy computing platform, data components, digital network, digital field, etc.), data security infrastructure (data compliance platform, etc.).

[0040] In step 102, the public data information is divided into several data categories according to data relevance.

[0041] For example, the public data information of the target enterprise usually includes multiple dimensions, and the data of different dimensions are divided into respective data categories.

[0042] When classifying, data with high correlation is divided into one data category according to the correlation between public data information, and corresponding data labels are given to target enterprises according to each data category, which helps to improve the accuracy of data labels.

[0043] Faced with the vast amount of public data information obtained, if we directly label each piece of public data, not only will the workload be huge, but the generated labels will not be very targeted, and it will be difficult to draw an accurate corporate portrait based on the labels later.

[0044] First, classify the public data information according to relevance and generate labels for each data classification.

[0045] It is understandable that before public data is divided into various data categories, it is necessary to first perform data cleaning and preprocessing operations on the public data information, including: removing duplicate data records; processing missing data by interpolation, mean filling or deletion; unifying the format of all public data information; identifying and processing outliers through statistical methods or machine learning algorithms.

[0046] Through the above-mentioned noise reduction processing, valid data is retained to facilitate the subsequent data analysis process.

[0047] Specifically, Figure 2 is based on Figure 1 A flow chart of a data classification method is shown in FIG. Figure 2 As shown, step 102 includes: In step 1021, for each piece of public data information, a first correlation coefficient between the public data information and other public data information is calculated.

[0048] Among them, for each piece of public data information , respectively calculate the public data information Other public data information The first correlation coefficient between , obtain the first correlation coefficient between the public data information, is the expected value.

[0049] For example, the information obtained from public channels is sorted to obtain each piece of public data information, and the sorting process can be performed by natural language processing technology, sentiment analysis technology, entity recognition technology, etc. It can be understood that each piece of public data information can be vectorized to facilitate the calculation of the similarity between each vector.

[0050] In step 1022, public data information with a first correlation coefficient greater than a preset coefficient threshold is classified into a data category.

[0051] In step 1023, several data categories are obtained.

[0052] For example, the first correlation coefficients between the public data are calculated, all the first correlation coefficients are traversed, and the public data information with the first correlation coefficient greater than a preset threshold is classified into a data category until all the public data information belongs to the corresponding data category.

[0053] In step 103, a weight coefficient corresponding to each data classification is determined according to the enterprise type of the target enterprise.

[0054] For example, the weight coefficient of each data classification is determined according to the type of the target enterprise (for example: education enterprise, legal service enterprise, technology enterprise, entertainment enterprise, etc.). Different types of enterprises may have different emphases in different dimensions.

[0055] For example, for technology-based enterprises, technological innovation is the core competitiveness of the enterprise. The weight coefficients corresponding to data classifications belonging to dimensions such as patent information, honors won in science and technology innovation competitions, and product innovation should be higher.

[0056] Specifically, the weight coefficient corresponding to each data classification is determined according to the enterprise type of the target enterprise, including: According to the correlation between enterprise type and data classification, determine the weight coefficient corresponding to each data classification ,in, is the second correlation coefficient between the ith data classification and the enterprise type, is the maximum value of the second correlation coefficient between all data classifications and enterprise types, It is the minimum value of the second correlation coefficient between all data categories and enterprise types.

[0057] For example, the enterprise type is also regarded as a piece of public data information of the enterprise, and the second correlation coefficient between the enterprise type and each data classification is calculated, and the weight coefficient corresponding to each data classification is determined according to the second correlation coefficient.

[0058] The method for obtaining the second correlation coefficient is: For each data category, obtain each public data information in the data category The third correlation coefficient with enterprise type y ; The average of all the third correlation coefficients in the data classification is calculated to obtain the second correlation coefficient between the i-th data classification and the enterprise type.

[0059] In step 104, a mapping relationship between data classification and data element label is determined based on the historical data classification and the historical data element label, so as to determine the target data label of the target enterprise based on the mapping relationship.

[0060] Specifically, Figure 3 is based on Figure 1 A flow chart of a method for obtaining data tags is shown in FIG. Figure 3 As shown, step 104 includes: In step 1041, according to the historical mapping relationship between historical data classification and historical data element labels, each piece of historical public data information in the historical data classification is taken as input, and the historical data element label corresponding to the historical data classification is taken as output, and the neural network model is trained to obtain a trained data element label generation model.

[0061] In step 1042, each piece of public data information in the data classification is used as the input of the data element label generation model, and the data element label corresponding to each data classification of the target enterprise is obtained according to the output of the data element label generation model.

[0062] For example, the historical data element labels may be labels manually annotated by a data annotator based on each piece of historical public data. The historical public data may be divided into multiple historical data categories through the correlation coefficient formula in the disclosed embodiment of the present invention, and the historical data element labels corresponding to each historical data category may be sorted out.

[0063] The neural network model is trained through historical data classification and historical data element labeling to obtain a data element label generation model, thereby outputting the data element labels of the target enterprise.

[0064] When training the model, you can use technologies such as pandas and scikit-learn to preprocess text and screen features, use machine learning or deep learning for model training, use scikit-learn technology for model evaluation, and use grid search or Bayesian optimization random parameter tuning technology for model parameter tuning.

[0065] In step 105, a target enterprise portrait is generated based on the target data label and weight coefficient to complete the data element governance of the target enterprise.

[0066] For example, after generating a portrait of the target enterprise, the intelligent recommendation system can be combined with the enterprise portrait to provide accurate enterprise matching services for investors, partners, etc., or combined with the risk warning system to establish a risk warning mechanism to promptly identify potential problems and take countermeasures.

[0067] In addition, the target enterprise portrait can also be displayed visually.

[0068] For example, developing visualization tools, such as charts to show the performance of target companies in various dimensions, can help management make more informed decisions and help companies better understand and apply labeling results.

[0069] Figure 4 is a structural block diagram of an enterprise data element management device based on big data according to an exemplary embodiment. Figure 4 As shown, the device 400 includes: The data collection module 410 determines the target enterprise that needs to be subject to data element governance and collects the public data information of the target enterprise; The data classification module 420 is connected to the data collection module 410 and divides the public data information into several data classifications according to data relevance; The weight coefficient determination module 430 is connected to the data classification module 420 and determines the weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise; The data label determination module 440 is connected to the weight coefficient determination module 430, and determines the mapping relationship between the data classification and the data element label according to the historical data classification and the historical data element label, so as to determine the target data label of the target enterprise according to the mapping relationship; The enterprise portrait generation module 450 is connected to the data label determination module 440, and generates a target enterprise portrait based on the target data label and weight coefficient to complete the data element governance of the target enterprise.

[0070] Figure 5 is based on Figure 4 A structural block diagram of a data classification module is shown in FIG. Figure 5 As shown, the data classification module 420 includes: The first correlation coefficient determination unit 421 determines each piece of public data information. , respectively calculate the public data information Other public data information The first correlation coefficient between , obtain the first correlation coefficient between the public data information, where, is the expected value; The data classification unit 422 is connected to the first correlation coefficient determination unit 421, and classifies the public data information whose first correlation coefficient is greater than a preset coefficient threshold into a data classification; The data classification acquisition unit 423 is connected to the data classification unit 422 and acquires a number of data classifications.

[0071] Optionally, the weight coefficient determination module 430 includes: According to the correlation between industry type and data classification, determine the weight coefficient corresponding to each data classification ,in, is the second correlation coefficient between the ith data classification and the enterprise type, is the maximum value of the second correlation coefficient between all data classifications and enterprise types, The minimum value of the second correlation coefficient between all data categories and enterprise types; The method for obtaining the second correlation coefficient is: For each data category, obtain each public data information in the data category The third correlation coefficient with enterprise type y ; The average of all the third correlation coefficients in the data classification is calculated to obtain the second correlation coefficient between the i-th data classification and the enterprise type.

[0072] Figure 6 is based on Figure 4 A structural block diagram of a data tag determination module is shown in FIG. Figure 6 As shown, the data tag determination module 440 includes: The model training unit 441 trains the neural network model according to the historical mapping relationship between the historical data classification and the historical data element label, taking each piece of historical public data information in the historical data classification as input and the historical data element label corresponding to the historical data classification as output, and obtains the trained data element label generation model; The data label acquisition unit 442 is connected to the model training unit 441, and uses each public data information in the data classification as the input of the data element label generation model, and obtains the data element label corresponding to each data classification of the target enterprise according to the output of the data element label generation model.

[0073] In summary, the present invention discloses a method and device for enterprise data element governance based on big data, the method comprising: determining a target enterprise that needs to perform data element governance, and collecting public data information of the target enterprise; dividing the public data information into a number of data categories according to data relevance; determining a weight coefficient corresponding to each data category according to the enterprise type of the target enterprise; determining a mapping relationship between data classification and data element label according to historical data classification and historical data element label, so as to determine a target data label of the target enterprise according to the mapping relationship; generating a target enterprise portrait according to the target data label and the weight coefficient, so as to complete data element governance of the target enterprise.

[0074] It is possible to classify the data and use multi-dimensional data for weight analysis, so as to label each type of data with specific labels, generate corporate portraits based on the labels and corresponding weight coefficients, and facilitate subsequent data processing.

[0075] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0076] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0077] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for enterprise data element governance based on big data, characterized in that: The method comprises: Identify target enterprises that require data element governance and collect public data information of the target enterprises; Dividing the public data information into several data categories according to data relevance; Determine a weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise; Determine a mapping relationship between the data classification and the data element label according to the historical data classification and the historical data element label, so as to determine a target data label of the target enterprise according to the mapping relationship; Based on the target data labels and weight coefficients, a target enterprise portrait is generated to complete the data element governance of the target enterprise.

2. The enterprise data element governance method based on big data according to claim 1 is characterized in that: The determination of target enterprises that require data element governance and the collection of public data information of the target enterprises include: Identify target enterprises that require data element governance; Collect public data information of the target enterprise from public channels.

3. The enterprise data element governance method based on big data according to claim 1 is characterized in that: The public data information is divided into several data categories according to data relevance, including: For each piece of public data information , respectively calculate the public data information Other public data information The first correlation coefficient between , obtain the first correlation coefficient between the public data information, where, is the expected value; Classify the public data information whose first correlation coefficient is greater than a preset coefficient threshold into a data category; Get several data categories.

4. The enterprise data element governance method based on big data according to claim 3 is characterized in that: Determining the weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise includes: According to the correlation between the enterprise type and the data classification, the weight coefficient corresponding to each data classification is determined ,in, is the second correlation coefficient between the ith data classification and the enterprise type, is the maximum value of the second correlation coefficient between all data classifications and enterprise types, It is the minimum value of the second correlation coefficient between all data categories and enterprise types; The method for obtaining the second correlation coefficient is: For each data category, obtain each public data information in the data category The third correlation coefficient between the enterprise type y ; The average of all the third correlation coefficients in the data classification is calculated to obtain the second correlation coefficient between the i-th data classification and the enterprise type.

5. The enterprise data element governance method based on big data according to claim 1 is characterized in that: The determining of the mapping relationship between the data classification and the data element label according to the historical data classification and the historical data element label, so as to determine the target data label of the target enterprise according to the mapping relationship, includes: According to the historical mapping relationship between historical data classification and historical data element label, each piece of historical public data information in the historical data classification is used as input, and the historical data element label corresponding to the historical data classification is used as output, and the neural network model is trained to obtain a trained data element label generation model; Each piece of public data information in the data classification is used as the input of the data element label generation model, and the data element label corresponding to each data classification of the target enterprise is obtained according to the output of the data element label generation model.

6. The enterprise data element governance method based on big data according to claim 1 is characterized in that: The method further comprises: Provide a visual display of the target enterprise portrait.

7. An enterprise data element management device based on big data, characterized in that: The device comprises: The data collection module determines the target enterprises that need to be subject to data element governance and collects the public data information of the target enterprises; A data classification module, connected to the data collection module, divides the public data information into several data categories according to data relevance; A weight coefficient determination module, connected to the data classification module, determines a weight coefficient corresponding to each data classification according to the enterprise type of the target enterprise; A data label determination module, connected to the weight coefficient determination module, determines a mapping relationship between data classification and data element label according to historical data classification and historical data element label, so as to determine a target data label of the target enterprise according to the mapping relationship; The enterprise portrait generation module is connected to the data label determination module, and generates a target enterprise portrait according to the target data label and weight coefficient to complete the data element governance of the target enterprise.

8. The enterprise data element management device based on big data according to claim 7 is characterized in that: The data classification module comprises: The first correlation coefficient determination unit, for each piece of public data information , respectively calculate the public data information Other public data information The first correlation coefficient between , obtain the first correlation coefficient between the public data information, where, is the expected value; A data classification unit, connected to the first correlation coefficient determination unit, classifies public data information whose first correlation coefficient is greater than a preset coefficient threshold into a data classification; The data classification acquisition unit is connected to the data classification unit and acquires a plurality of data classifications.

9. The enterprise data element management device based on big data according to claim 8 is characterized in that: The weight coefficient determination module comprises: According to the correlation between the enterprise type and the data classification, the weight coefficient corresponding to each data classification is determined ,in, is the second correlation coefficient between the ith data classification and the enterprise type, is the maximum value of the second correlation coefficient between all data classifications and enterprise types, It is the minimum value of the second correlation coefficient between all data categories and enterprise types; The method for obtaining the second correlation coefficient is: For each data category, obtain each public data information in the data category The third correlation coefficient between the enterprise type y The average of all the third correlation coefficients in the data classification is calculated to obtain the second correlation coefficient between the i-th data classification and the enterprise type.

10. The enterprise data element management device based on big data according to claim 7 is characterized in that: The data tag determination module includes: The model training unit, according to the historical mapping relationship between the historical data classification and the historical data element label, takes each piece of historical public data information in the historical data classification as input, takes the historical data element label corresponding to the historical data classification as output, trains the neural network model, and obtains the trained data element label generation model; The data label acquisition unit is connected to the model training unit, and uses each public data information in the data classification as the input of the data element label generation model, and obtains the data element label corresponding to each data classification of the target enterprise according to the output of the data element label generation model.

Images