A big data-based intelligent enterprise archives informatization management system

Abstract

The application provides a big data-based intelligent enterprise archive information management system, and belongs to the field of archive information intelligent management systems; the system comprises an information acquisition module, a first information analysis module, an information storage module, a second information analysis module and an application module; the system firstly analyzes user information through big data technology to obtain the classification of user information with different marks in each dimension; then, the support vector machine is used to analyze vectors formed by multiple dimensions of the user information, and the gap of the overall dimension of the user information is considered; finally, the LSTM model is used to further consider the individual differences of the user information in the same classification of the support vector machine, so that the prediction result is more personalized and accurate when the system is used to predict the demand and active trend of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent management of archives information, in particular, to a smart enterprise archives informatization management system based on big data. BACKGROUND

[0002] With the advent of the concept of "Internet+", various Internet information technologies such as cloud computing, big data, and the Internet of Things have penetrated into various fields of society, greatly changing people's way of life and work pattern; in enterprise management, the promotion of informatization has also provided many conveniences for production, operation, and decision-making; however, in the field of enterprise archives management, although computerized management has gradually been achieved, there are still many problems to be solved.

[0003] At present, most of the archives information of enterprises, especially important business, legal documents, financial data, etc., still rely on paper files for storage and management; this traditional management mode not only occupies a large amount of physical space, but also easily leads to the risk of loss and damage of archives; the management and retrieval efficiency of paper archives is low, and enterprises often face difficulties in finding and classifying when dealing with a large number of archives, which seriously affects the speed of information flow and the efficiency of decision-making; in addition, with the expansion of business scale, the amount of archives information increases dramatically, and the traditional manual management method is difficult to meet the efficient information retrieval and updating demand; therefore, there is an urgent need for an electronic archives management system based on modern information technology to improve the management efficiency, security, and intelligent level of enterprise archives.

[0004] Under such circumstances, an enterprise electronic archives information intelligent management system emerges as the times require, which solves the problems existing in the current archives management mode through advanced information technology means, realizes the digitalization and intelligentization of archives management, and improves the security and management efficiency of archives storage; the introduction of this system will bring fundamental changes to the archives management of enterprises, help enterprises realize information transformation, and improve the overall operation efficiency.

[0005] Through big data technology, enterprise information is processed to generate corresponding search reports, which is convenient for the retrieval and management of enterprise information; this technology is relatively mature; through big data technology, user information can be analyzed in multiple different dimensions, and user data can be analyzed in overall dimensions, but the overall user behavior of the industry is usually obtained through big data technology, ignoring the differences between individuals; for individuals, the results predicted by big data technology often differ greatly from reality; therefore, a prediction method that reflects the differences between individuals is needed to accurately predict user needs. SUMMARY

[0006] The present application aims at overcoming the above problems existing in the prior art, and greatly improving the technical effect on the basis of the prior art; the present application provides a smart enterprise archives informatization management system based on big data, which comprises:

[0007] An information acquisition module S100, a first information analysis module S200, an information storage module S300, a second information analysis module S400 and an application module S500.

[0008] The information acquisition module S100 is connected with the first information analysis module S200, and is used for acquiring information and sending the acquired information to the first information analysis module S200; the information acquisition module S100 is composed of a passive information acquisition unit and an active information acquisition unit; the passive information acquisition unit is used for passively acquiring information sent by users and information input by employees, and the active information acquisition unit is used for actively collecting browsing information of active users through various network channels.

[0009] The present application acquires user information through two different ports; the active information of users is actively collected through the API port connected with various network channels, and the information sent by users and the information input by employees are passively received through the SMTP port; when information is acquired through different ports, the corresponding user information and employee information are marked with the corresponding ports.

[0010] The first information analysis module S200 is connected with the information acquisition module S100 and the information storage module S300; the first information analysis module S200 comprises passive user information analysis and active user information analysis; the passive user information and the active user information are analyzed through big data technology respectively, and passive user information analysis reports and active user information analysis reports are generated; the analysis reports comprise classification of user information in different dimensions; and the generated passive user information analysis reports and active user information analysis reports are sent to the information storage module S300.

[0011] The steps of analyzing the passive user information and the active user information through big data technology are data preprocessing, dimension feature extraction and data classification; the passive user information analysis reports and the active user information analysis reports are generated through big data technology, and the generated user information analysis reports are sent to the information storage module S300.

[0012] The information storage module S300 is connected with the first information analysis module S200 and the second information analysis module S400; the information storage module S300 comprises a passive user information storage area and an active user information storage area; the passive user information storage area is used for storing the passive obtained user information analysis report, and the active user information storage area is used for storing the active obtained user information analysis report.

[0013] After obtaining the information transmitted by the first information analysis module S200, it is first determined whether the obtained information is the passive obtained user information analysis report or the active obtained user information analysis report through the marking of the port; the passive obtained user information analysis report is stored in the passive user information storage area according to the marking, and the active obtained user information analysis report is stored in the active user information storage area.

[0014] The second information analysis module S400 is connected with the information storage module S300 and the application module S500; the second information analysis module S400 obtains the classification of user information in different dimensions by searching the user information in the information storage module S300, maps the classification data in different dimensions to a multi-dimensional space through the heterogeneous data integration technology, and generates the multi-dimensional space coordinate information corresponding to the user information; the multi-dimensional space coordinate information is classified through the support vector machine to obtain the support vector machine model; according to the classification result of the support vector machine model, all user information of each same classification is extracted, each dimension data of each user information of the same classification is assigned in layers, and the assigned different dimension data is mapped to the corresponding multi-dimensional space; the multi-dimensional space data before assignment is regarded as X, and the multi-dimensional space data after assignment is regarded as Y, wherein, X={x1, x2, …x i , …x n}, wherein x i represents the data corresponding to the i-th dimension, and n represents the total number of n dimensions; similarly, Y={y1, y2, …y i , …y n}, wherein, y i represents the data corresponding to the i-th dimension after assignment, and n represents the total number of n dimensions; X and Y obtained from each classification in the support vector machine model are respectively taken as the input and output of the long short-term memory neural network LSTM, the LSTM is trained, and the trained LSTM model is obtained.

[0015] Specifically, the second information analysis module S400 obtains the classification of the same marked user information in different dimensions by searching the user information in the passive user information storage area and the active user information storage area in the information storage module S300, respectively; the heterogeneous data integration technology is a data that integrates different types of dimensional data into a multidimensional space, and the data in the multiple dimensional classifications of the obtained user information is integrated into a multidimensional space by the data standardization and normalization technology in the heterogeneous data integration technology, to generate the multidimensional space coordinate information corresponding to the user information, and the coordinate information on the multidimensional space is classified by the support vector machine technology to generate a support vector machine model; the support vector machine technology is an algorithm commonly used for high-dimensional space data classification, which classifies multidimensional data by finding a hyperplane that maximizes the classification interval.

[0016] Specifically, each user information in the same classification in the support vector machine model is extracted, and each dimensional data of each user information is hierarchically assigned; the hierarchical assignment includes interval assignment, classification assignment and result assignment; the assigned data in different dimensions after assignment is mapped into the corresponding multidimensional space to generate the multidimensional space data obtained after assignment; the long short-term memory neural network LSTM is an improved recurrent neural network, which can effectively capture the long-term dependence relationship in time series data by designing complex memory units and gating mechanisms, so that the prediction result is more accurate.

[0017] Specifically, X and Y obtained from each classification in the support vector machine model are taken as the input and output of the long short-term memory neural network LSTM, respectively, and the LSTM is trained to obtain the trained LSTM model corresponding to each classification data in the support vector machine model, that is, the same support vector machine model has A classifications, and finally A trained LSTM models are obtained.

[0018] The application module S500 is connected with the second information analysis module S400 and the information acquisition module S100, the application module S500 acquires user information through the client and sends the user information to the information acquisition module S100; then the user information is classified in different dimensions by the big data technology of the first information analysis module S200, and the classified user information is saved to the information storage module S300; at the same time, the user information classified in different dimensions is mapped into a multidimensional space to form a vector of the multidimensional space, the obtained vector of the multidimensional space is respectively brought into the support vector machine model and the trained LSTM model in the second information analysis module S400, and the demand of the user is judged according to the result.

[0019] The client is connected with the network device of the user, obtains the user information through the browsing information of the user, and sends the user information to the information acquisition module S100, the information acquisition module S100 will judge whether the user information belongs to passive information acquisition or active information acquisition according to the format of the user information, and generate the corresponding user information mark; then, the big data technology processes the user information, generates the user information analysis report with the marked information, and saves the user information analysis report to the corresponding area of the information storage module S300 according to the marked information; at the same time, the classified information of different dimensions in the user information analysis report is sent to the second data analysis module, the second data analysis module maps the obtained user classified information of different dimensions to a multi-dimensional space to form a vector of the multi-dimensional space, and respectively brings the obtained vector of the multi-dimensional space into the support vector machine model and the trained LSTM model in the second information analysis module S400, and determines the activity, demand and shopping possibility of the user according to the output result of the LSTM model.

[0020] The beneficial effects of the present application are:

[0021] The present application provides a big data-based intelligent enterprise archives informatization management system; the system has the following advantages:

[0022] 1. The system divides the user information into passive user information and active user information, and stores and analyzes them respectively, so that the analysis results will be more targeted.

[0023] 2. When analyzing the user information, the system first classifies the user information in each dimension through big data technology, then extracts the dimension data of each user information in the big data information classification to form a multi-dimensional space data, classifies all multi-dimensional space coordinate information with the same mark through the support vector machine to obtain the support vector machine model, extracts the dimension data of the user information with the same classification in the support vector machine model for hierarchical assignment, respectively takes the vectors composed of the user information before assignment and the user information after assignment as the input and output of LSTM to train the LSTM, and predicts through the trained LSTM model; the system not only considers the overall dimension difference of the user information through the support vector machine, but also further considers the individual difference of the user information in the same classification through the LSTM model, so that the prediction result will be more personalized and accurate when predicting the demand and trend of the user through the system. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 It is a schematic view of a big data-based intelligent enterprise archives informatization management system of the present application. DETAILED DESCRIPTION

[0025] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings; it should be understood that the specific embodiments given herein are only for illustration and explanation of the present invention and cannot be used to limit the present invention.

[0026] It should be noted that many specific details are set forth in the following description in order to provide a full understanding of the present invention. However, the present invention may have other embodiments and variations thereof. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0027] like Figure 1 The diagram illustrates a smart enterprise archive information management system based on big data according to an embodiment of the present invention. The diagram includes: an information acquisition module S100; a first information analysis module S200; an information storage module S300; a second information analysis module S400; and an application module S500. The information acquisition module S100 comprises a passive information acquisition unit S101 and an active information collection unit S102, and the information storage module S300 comprises a passive user information storage area S301 and an active user information storage area S302.

[0028] The information acquisition module S100 is connected to the first information analysis module S200 and is used to acquire information and send the acquired information to the first information analysis module S200. The information acquisition module S100 consists of a passive information acquisition unit S101 and an active information collection unit S102. The passive information acquisition unit S101 is used to passively acquire information sent by users and information input by employees, and the active information collection unit S102 is used to actively collect browsing information of active users through various network channels.

[0029] Specifically, user information is acquired through two different ports. The API port actively collects user activity information by connecting to various network channels, while the SMTP port passively receives information sent by users and input by employees. When information is acquired through different ports, the corresponding user and employee information will be marked with the corresponding port identifier. That is, user activity information actively collected through the API port generates an API port identifier, and information passively received through the SMTP port generates an SMTP port identifier. The identifiers can be arbitrarily set, as long as the relevant devices and algorithms can easily distinguish them. Therefore, the information acquisition module S100 consists of two ports: an API port for actively collecting user activity information to prepare for understanding user activity levels and predicting user needs; and an SMTP port for passively receiving information sent by users and input by employees to prepare for understanding user needs and employee work status.

[0030] The first information analysis module S200 is connected with the information acquisition module S100 and the information storage module S300; the first information analysis module S200 is analyzed by the passive obtained user information and the active obtained user information; the passive obtained user information and the active obtained user information are analyzed by the big data technology respectively, and the passive obtained user information analysis report and the active obtained user information analysis report are generated; the analysis report includes the classification of user information in different dimensions; and the generated passive obtained user information analysis report and active obtained user information analysis report are sent to the information storage module S300.

[0031] The step of analyzing the passive obtained user information and the active obtained user information by the big data technology is: data preprocessing, dimension feature extraction and data classification; the passive obtained user information analysis report and the active obtained user information analysis report are generated by the big data technology, and the generated user information analysis report is sent to the information storage module S300.

[0032] The user information analysis report generated by the big data technology can obtain the user information and enterprise related information related to the word in the form of retrieval.

[0033] It should be pointed out that when the big data technology analyzes the related user information, the illegal information and the information not meeting the enterprise regulations are filtered and cleaned through the cleaning and automatic filtering function.

[0034] It should be pointed out that the first information analysis module S200 analyzes the passive obtained user information at the same time, analyzes the information page input by the passive obtained employee, generates the related word of the employee input information according to the big data technology, and generates the analysis report of the employee input information according to the association between the employee input information and the user, and the passive obtained user information, and transmits the analysis report to the information storage module S300.

[0035] The information storage module S300 is connected with the first information analysis module S200 and the second information analysis module S400; the information storage module S300 is divided into passive user information storage area and active user information storage area; the passive user information storage area is used for storing the passive obtained user information analysis report, and the active user information storage area is used for storing the active obtained user information analysis report.

[0036] After obtaining the information transmitted by the first information analysis module S200, the information storage module S300 firstly identifies whether the obtained information is a passive user information analysis report or an active user information analysis report through the mark of the port; and stores the passive user information analysis report into the passive user information storage area and the active user information analysis report into the active user information storage area according to the mark.

[0037] The second information analysis module S400 is connected with the information storage module S300 and the application module S500; the second information analysis module S400 obtains the classification of the user information in different dimensions by searching the user information in the information storage module S300, maps the classification data in different dimensions into a multi-dimensional space through the heterogeneous data integration technology, and generates the multi-dimensional space coordinate information corresponding to the user information; and classifies the multi-dimensional space coordinate information through the support vector machine, and obtains the support vector machine model.

[0038] The passive user information storage area and the active user information storage area in the information storage module S300 are searched respectively to obtain the classification of the user information with the same mark in different dimensions, and the multi-dimensional space vector is composed according to the classification data of each user information in different dimensions through the heterogeneous data integration technology; the heterogeneous data integration technology is a kind of data integrated into a multi-dimensional space from different types of dimension data, the data in the multiple dimensions of the obtained user information is integrated into a multi-dimensional space through the data standardization and normalization technology in the heterogeneous data integration technology, the multi-dimensional space coordinate information corresponding to the user information is generated, and then the coordinate information on the multi-dimensional space is classified through the support vector machine technology, and the support vector machine model is generated; the support vector machine technology is an algorithm commonly used for high-dimensional space data classification, which classifies the multi-dimensional data by finding a hyperplane that can maximize the classification interval.

[0039] It should be noted that the present application obtains information through two ports, each port has a mark; therefore, the classification of the user information with two kinds of marks in different dimensions is obtained; when the coordinate information on the multi-dimensional space with different marks is classified through the support vector machine, a support vector machine model will be generated for the user information with each kind of mark, and the present application generates two different support vector machine models.

[0040] According to the classification result of the support vector machine model, all the user information of each same classification is extracted, each dimension data of each user information of the same classification is assigned hierarchically, and the assigned data in different dimensions after the assignment is mapped into the corresponding multi-dimensional space; the multi-dimensional space data before the assignment is regarded as X, and the multi-dimensional space data after the assignment is regarded as Y, wherein X={x1, x2, …x i , …x n}, wherein xi represents the data corresponding to the i-th dimension, and n represents a total of n dimensions; similarly, Y = {y1, y2, … y i , … y n}, wherein, wherein y i represents the data corresponding to the i-th dimension after assignment, and n represents a total of n dimensions.

[0041] The hierarchical assignment of each dimension data of each user information of the same classification includes: extracting each user information of the same classification in the support vector machine model, and performing hierarchical assignment on each dimension data of each user information; the hierarchical assignment includes interval assignment, classification assignment and result assignment; mapping the assigned data of different dimensions after assignment to the corresponding multi-dimensional space to generate multi-dimensional space data obtained after assignment; the long short-term memory neural network LSTM is an improved recurrent neural network, and the LSTM can effectively capture long-term dependencies in time series data by designing complex memory units and gating mechanisms, so that the prediction result is more accurate.

[0042] Preferably, for example: interval assignment is performed on the time corresponding to the acquisition of user information, 24 hours a day are considered, 0 o'clock to 0 o'clock 30 minutes can be assigned as 1, 0 o'clock 30 minutes to 1 o'clock can be assigned as 2, and so on, until the entire 24-hour time period of a day is assigned; classification assignment is performed on the consumption level of the acquisition of user information, monthly consumption below 500 is considered as low consumption level, and is assigned as 1; consumption between 501 and 2000 is considered as equal consumption level, and is assigned as 2; consumption above 2001 is considered as high consumption level, and is assigned as 3; result assignment is performed on whether the user information is consumed, if the user has consumed, it is assigned as 1, and if the user has not consumed, it is assigned as 0.

[0043] X and Y obtained from each classification in the support vector machine model are taken as the input and output of the long short-term memory neural network LSTM respectively, the LSTM is trained, and a trained LSTM model is obtained.

[0044] X and Y obtained from each classification in the support vector machine model are taken as the input and output of the long short-term memory neural network LSTM respectively, the LSTM is trained, and a trained LSTM model corresponding to each classification data in the support vector machine model is obtained, that is, the same support vector machine model has A classifications, and finally A trained LSTM models are obtained.

[0045] The application module S500 is connected with the second information analysis module S400 and the information acquisition module S100, the application module S500 acquires user information through a client, and sends the user information to the information acquisition module S100; then the user information is classified in different dimensions through the big data technology of the first information analysis module S200, the classified user information is saved to the information storage module S300; meanwhile, the user information classified in different dimensions is mapped into a multi-dimensional space to form a vector of the multi-dimensional space, the obtained vector of the multi-dimensional space is respectively brought into the support vector machine model and the trained LSTM model in the second information analysis module S400, and the demand of the user is judged according to the result.

[0046] The client is connected with the network equipment of the user, acquires user information through the browsing information of the user, and sends the user information to the information acquisition module S100, the information acquisition module S100 judges whether the user information belongs to passive information acquisition or active information collection according to the format of the user information, and generates a mark of the corresponding user information; then, the user information is processed through the big data technology to generate a user information analysis report with marked information, and the user information analysis report is saved to the corresponding area of the information storage module S300 according to the marked information; meanwhile, the classified information in different dimensions in the user information analysis report is sent to the second data analysis module, the second data analysis module maps the obtained user classified information in different dimensions into a multi-dimensional space to form a vector of the multi-dimensional space, the obtained vector of the multi-dimensional space is respectively brought into the support vector machine model and the trained LSTM model in the second information analysis module S400, and the activity, demand and shopping possibility of the user are judged according to the output result of the LSTM model; the above process needs to be distinguished from the establishment of the support vector machine model and the LSTM model, therefore, the data of the process needs to be separately transmitted and analyzed with the data acquired by the information acquisition module S100, and the above technical features can be realized through a multi-thread system.

[0047] The servers, routers, switches, sensors, Internet of Things devices, visualization tools and intelligent algorithms arranged in different modules and unit areas are used to realize the above embodiments of the application.

Claims

1. A big data-based intelligent enterprise archive informatization management system, characterized in that, The system comprises: An information acquisition module S100; a first information analysis module S200; an information storage module S300; a second information analysis module S400; and an application module S500; The information acquisition module S100 is connected to the first information analysis module S200, and is configured to acquire information and send the acquired information to the first information analysis module S200; the information acquisition module S100 comprises a passive information acquisition unit and an active information acquisition unit; the passive information acquisition unit is configured to passively acquire information sent by users and information input by employees, and the active information acquisition unit is configured to actively acquire browsing information of active users through various network channels; The first information analysis module S200 is connected to the information acquisition module S100 and the information storage module S300; the first information analysis module S200 comprises passive user information analysis and active user information analysis; the passive user information and the active user information are analyzed by using big data technology, respectively, and passive user information analysis reports and active user information analysis reports are generated; the analysis reports comprise classifications of user information in different dimensions; and the generated passive user information analysis reports and active user information analysis reports are sent to the information storage module S300; The information storage module S300 is connected to the first information analysis module S200 and the second information analysis module S400; the information storage module S300 comprises a passive user information storage area and an active user information storage area; the passive user information storage area is configured to store the passive user information analysis reports, and the active user information storage area is configured to store the active user information analysis reports; The second information analysis module S400 is connected to the information storage module S300 and the application module S500; the second information analysis module S400 acquires classifications of user information in different dimensions by searching the user information in the information storage module S300, maps the classification data in different dimensions to a multi-dimensional space by using heterogeneous data integration technology, and generates multi-dimensional space coordinate information corresponding to the user information; the multi-dimensional space coordinate information is classified by using a support vector machine, and a support vector machine model is acquired; Based on the classification results of the support vector machine model, all user information for each category is extracted. For each dimension of the user information within the same category, hierarchical values ​​are assigned, and the assigned values ​​for different dimensions are mapped to the corresponding multidimensional space. The multidimensional space data before assignment is considered X, and the multidimensional space data after assignment is considered Y, where X = {x1, x2, ... x...} i , ...x n }, where x i This represents the data corresponding to the i-th dimension, where n represents the total number of dimensions; similarly, Y = {y1, y2, ... y} i , ...y n }, where y i This represents the data corresponding to the i-th dimension after assignment, where n represents the total number of dimensions. The hierarchical assignment of each dimension data of each user information in the same category includes: extracting each user information in the same category from the support vector machine model, and performing hierarchical assignment on each dimension data of each user information. The hierarchical assignment includes interval assignment, classification assignment, and result assignment. The assigned data of different dimensions after assignment are mapped to the corresponding multidimensional space to generate the multidimensional space data after assignment. X and Y obtained in each classification of the support vector machine model are taken as input and output of a long short-term memory neural network LSTM, respectively, the LSTM is trained, and a trained LSTM model is obtained; the long short-term memory neural network LSTM is an improved recurrent neural network; the LSTM can effectively capture long-term dependencies in time series data by using a complex memory unit and a gating mechanism, so that the prediction result is more accurate. The application module S500 is connected with the second information analysis module S400 and the information acquisition module S100, the application module S500 obtains user information through the client, and sends the user information to the information acquisition module S100; then the user information is classified in different dimensions through the big data technology of the first information analysis module S200, the classified user information is saved to the information storage module S300; at the same time, the user information classified in different dimensions is mapped into a multi-dimensional space to form a vector of the multi-dimensional space, the obtained vector of the multi-dimensional space is respectively brought into the support vector machine model and the trained LSTM model in the second information analysis module S400, and the demand of the user is judged according to the result. 2.The big data-based intelligent enterprise archives informatization management system according to claim 1, characterized in that, The information acquisition module S100 comprises: obtaining user information through two different ports; actively collecting active information of the user through the API port connected with various network channels, and passively receiving information sent by the user and information input by the staff through the SMTP port; when information is acquired through different ports, the corresponding user information and staff information are marked with corresponding ports. 3.The big data-based intelligent enterprise archives informatization management system according to claim 1, characterized in that, The first information analysis module S200 comprises: the steps of analyzing the passively obtained user information and the actively obtained user information through the big data technology are: data preprocessing, dimension feature extraction and data classification; generating the passively obtained user information analysis report and the actively obtained user information analysis report convenient for retrieval through the big data technology, and sending the generated user information analysis report to the information storage module S300. 4.The big data-based intelligent enterprise archives informatization management system according to claim 1, characterized in that, The information storage module S300 comprises: after obtaining the information transmitted by the first information analysis module S200, firstly identifying whether the obtained information is the passively obtained user information analysis report or the actively obtained user information analysis report through the port mark; storing the passively obtained user information analysis report in the passive user information storage area according to the mark, and storing the actively obtained user information analysis report in the active user information storage area. 5.The big data-based intelligent enterprise archives informatization management system according to claim 1, characterized in that, The second information analysis module S400 comprises: the second information analysis module S400 respectively obtains the classification of the same marked user information in different dimensions by searching the user information in the passive user information storage area and the active user information storage area in the information storage module S300; the heterogeneous data integration technology is a kind of data integrated into a multi-dimensional space from different types of dimension data, the data in the multiple dimension classifications of the obtained user information is integrated into a multi-dimensional space through the data standardization and normalization technology in the heterogeneous data integration technology, the corresponding multi-dimensional space coordinate information of the user information is generated, and the coordinate information on the multi-dimensional space is classified through the support vector machine technology to generate a support vector machine model; the support vector machine technology is an algorithm commonly used for high-dimensional space data classification, which classifies multi-dimensional data by finding a hyperplane that can maximize the classification interval. 6.The big data-based intelligent enterprise archives informatization management system according to claim 1, characterized in that, The trained LSTM model comprises: taking X and Y obtained by each classification in the support vector machine model as input and output of the long short-term memory neural network LSTM respectively, training the LSTM, and obtaining the trained LSTM model corresponding to each classification data in the support vector machine model, that is, the same support vector machine model has A classifications, and finally A trained LSTM models are obtained. 7.The big data-based intelligent enterprise archives informatization management system according to claim 1, characterized in that, The application module S500 comprises: the client is connected with the network equipment of the user, acquires the user information through the browsing information of the user, and sends the user information to the information acquisition module S100; the information acquisition module S100 judges whether the user information belongs to passive information acquisition or active information collection according to the format of the user information, and generates a mark of the corresponding user information; subsequently, the big data technology processes the user information, generates a user information analysis report with marked information, and saves the user information analysis report to the corresponding area of the information storage module S300 according to the marked information; meanwhile, the classified information of different dimensions in the user information analysis report is sent to the second data analysis module, the second data analysis module maps the obtained classified information of different dimensions of the user to a multi-dimensional space to form a vector of the multi-dimensional space, and the obtained vector of the multi-dimensional space is respectively brought into the support vector machine model and the trained LSTM model in the second information analysis module S400, and the activity, demand and shopping possibility of the user are judged according to the output result of the LSTM model.

Images