Management method and system based on master data

Abstract

The invention relates to a management method and system based on master data, and relates to the field of electric digital data processing. The method comprises the following steps: adopting an AI analysis model to intelligently analyze each access frequency of a target person in each operation system of a current enterprise in a current time segment on the basis of multiple person associated information of the target person and flow associated data of the target person in multiple historical time segments before the current time segment; and determining the importance level of the target person in the current time segment based on the cumulative value of each time. The invention further relates to a management system based on the master data. According to the invention, in order to solve the technical problem that it is difficult to configure the main data management strategy of each enterprise personnel in the future time segment in advance, the AI analysis model is adopted to intelligently predict the active degree of each enterprise personnel in the future time segment, and then the importance level of the enterprise personnel in the future time segment is identified. Therefore, the technical problem is solved.

Description

Technical Field

[0001] The present invention relates to the field of electronic digital data processing, and in particular to a management method and system based on master data. Background Art

[0002] Master data (MD Master Data) refers to data shared between systems. Compared with transaction data that records business activities and has large fluctuations, master data (also known as benchmark data) changes slowly. For an enterprise, there are various operating systems, such as the current enterprise's financial system, OA collaborative office system, procurement system, capital budget system and human resources system. The same enterprise personnel may exist in these systems, and the associated information of the enterprise personnel changes slowly. The enterprise personnel can be regarded as the master data of the enterprise. The frequency with which the enterprise personnel are accessed in various systems determines the importance of the enterprise personnel as master data, and even determines whether it is necessary to be the master data of the enterprise. For an enterprise, the management level of its master data determines the operating efficiency and even the operating profit of the enterprise.

[0003] For example, the invention patent with publication number CN109508176A proposes an enterprise master data management platform. The existing workflow engine and the business system as a third party are accessed through a unified interface provided by the service layer, which can realize the access of multiple workflow engines, effectively reducing the cost of deployment and implementation in different enterprises; the service layer interacts with the business logic layer through the middleware; the business logic layer interacts with the database through the data access layer, and through calculations, different distribution modes are adopted based on different scenarios, which ensures data security while also ensuring the targeted data distribution; in addition, the present invention introduces a version mechanism, so that administrators and business systems can trace the master data of the specified version and understand the change process of each attribute of the master data.

[0004] For example, the invention patent with publication number CN104751291A proposes a master data management platform, characterized in that the platform includes: a source system module; a data service bus module, which is connected to the source system and manages data services; a master data processing and storage module, which is connected to the data service bus module to realize the extraction, cleaning, mapping, conversion, loading and backup of master data; a master data management module, which is connected to the data service bus module and the master data processing and storage module at the same time, to realize the management of master data business, master data process and master data; a master data application module, which is connected to the master data management module to realize the management of master data application, and it centrally manages data to meet the needs of data sharing and improve the business efficiency of the enterprise.

[0005] However, the above-mentioned technical solutions are only limited to the management layout of master data, which facilitates information tracing of master data. They can only maintain and process the past information of master data that has occurred. It is impossible to predict the frequency of master data being accessed in future time segments, and naturally it is impossible to determine the importance of master data in future time segments, and even it is impossible to determine whether the master data in the past time segments still need to be classified as master data in the future time segments. As a result, the management end of master data cannot plan the management strategy of future time segments of master data in advance, which affects the management efficiency and management level of master data. Summary of the invention

[0006] In order to solve the technical problems in the prior art, the present invention provides a management method and system based on master data, which uses an AI analysis model with a customized structure to intelligently predict the activity level of each employee of the current enterprise in the future time segment based on multiple basic data that are fully and comprehensively screened, and determines the importance level of the employee in the future time segment based on the intelligently predicted activity level, and then determines whether the employee can still be classified as the master data of the current enterprise in the future time segment, thereby completing the master data judgment of enterprise personnel in different time periods and the effective identification of the importance level of enterprise personnel when serving as master data, and providing reliable reference information for the enterprise to customize the master data management strategy for different personnel in the future time segment.

[0007] According to a first aspect of the present invention, there is provided a management method based on master data, the method comprising:

[0008] Obtain the target personnel's employment years, level value, number of managers, and number of managed personnel of the current enterprise as multiple personnel-related information of the target personnel;

[0009] Acquire multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, and the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise within the time segment;

[0010] Performing a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and outputting it as an AI parsing model;

[0011] The AI ​​analysis model is used to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise within the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment of the target person;

[0012] The importance level of the target person in the current time segment is determined based on the cumulative number of times the target person is accessed in each operating system of the current enterprise in the current time segment, and when the importance level is lower than or equal to the set level threshold, the target person will not be managed as master data in the current time segment.

[0013] According to a second aspect of the present invention, there is provided a management system based on master data, the system comprising:

[0014] An information collection device, used to obtain the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple personnel-related information of the target personnel;

[0015] A data capture device is used to obtain multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, and the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise within the time segment;

[0016] An object building device is used to perform a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and output it as an AI analysis model;

[0017] A frequency analysis device, connected to the information collection device, the data capture device and the object assembly device respectively, for using the AI ​​analysis model to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise within the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment of the target person;

[0018] The content mapping device is connected to the frequency analysis device, and is used to determine the importance level of the target person in the current time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, and when the importance level is lower than or equal to the set level threshold, the target person will not be managed as master data in the current time segment.

[0019] It can be seen that the present invention has at least the following four main inventive features:

[0020] Invention point 1: For each person in the current enterprise, based on their active data in various operating systems of the current enterprise in multiple historical time segments and their multiple personnel-related information, intelligently judge the active data of the person in various operating systems of the current enterprise in future time segments, determine the importance level of the person in the future time segments based on the intelligent judgment results, and then judge whether the person in the future time segments belongs to the master data of the current enterprise, thereby completing the master data judgment of enterprise personnel in different time segments and effectively identifying the importance level of enterprise personnel when they are master data, thereby improving the intelligent level of enterprise master data management;

[0021] Invention point 2: The AI ​​parsing model with customized structure design is used to specifically perform intelligent judgment on the active data of each person in the current enterprise in various operating systems of the current enterprise in future time segments. The AI ​​parsing model is a deep neural network after completing each learning operation, and the number of learning operations is monotonically positively correlated with the number of various operating systems of the current enterprise, thereby customizing AI parsing models with different structures for different enterprises;

[0022] Invention point three: Targeted screening of multiple basic data for intelligent judgment of active data of each person participating in the current enterprise in various operating systems of the current enterprise in future time segments. The multiple basic data include the number of various operating systems of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target personnel of the current enterprise, and multiple flow-related data corresponding to the target personnel in multiple historical time segments before the current time segment. The multiple personnel-related information of the target personnel of the current enterprise includes the employment years, level value, number of managers and number of managed personnel of the target personnel. The single flow-related data corresponding to the target personnel in each time segment is the number of times the target personnel is accessed in each operating system of the current enterprise in the time segment. The comprehensive and sufficient targeted screening of the above basic data ensures the effectiveness and stability of the intelligent prediction results.

[0023] Invention point 4: A set number of learning operations are performed on the deep neural network to obtain a deep neural network after completing each learning operation, and the deep neural network is output as an AI analysis model. The value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise, and also includes: in each learning operation performed on the deep neural network, the number of times a certain person of the current enterprise is accessed in each operating system of the current enterprise within a certain historical time segment is used as the output data of the deep neural network, the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the certain person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the certain historical time segment are used as input data of the deep neural network to perform this learning operation, thereby ensuring the learning effect of each learning operation of the deep neural network. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0025] Figure 1 The present invention is a technical flow chart of a management method and system based on master data.

[0026] Figure 2 The figure is a flowchart showing a management method based on master data according to Embodiment 1 of the present invention.

[0027] Figure 3 The figure is a flowchart showing a management method based on master data according to Embodiment 2 of the present invention.

[0028] Figure 4 The present invention is a flowchart showing a method for managing master data based on embodiment 3 of the present invention.

[0029] Figure 5 The internal structure diagram of a management system based on master data according to Embodiment 4 of the present invention is shown.

[0030] Figure 6 1 is an internal structure diagram of a management system based on master data according to Embodiment 5 of the present invention.

[0031] Figure 7 1 is an internal structure diagram of a management system based on master data according to Embodiment 6 of the present invention. DETAILED DESCRIPTION

[0032] like Figure 1 As shown, a technical flow chart of a management method and system based on master data according to the present invention is given.

[0033] like Figure 1 As shown, the specific technical process of the present invention is as follows:

[0034] Step 1: Customize AI analysis models with different structures for different enterprises to provide prediction models for intelligent prediction of the activity level of enterprise personnel in various operation systems of the enterprise in future time segments. The AI ​​analysis model is as follows: Figure 1 As shown;

[0035] For example, each operating system of each enterprise includes the enterprise's financial system, OA collaborative office system, procurement system, capital budget system and human resources system. Obviously, each operating system of each enterprise may not be limited to the above five enterprise systems.

[0036] And by way of example, when the current time segment takes the current moment as the starting point, since the current time segment is an unreached time segment, the current time segment can be regarded as a future time segment;

[0037] Specifically, the AI ​​analysis model is a deep neural network after completing each learning operation, and the number of learning operations is monotonically positively correlated with the number of various operating systems of the current enterprise, so that AI analysis models with different structures are customized for different enterprises, ensuring the reliability and stability of intelligent prediction results;

[0038] More specifically, in each learning operation performed on the deep neural network, the number of times a certain person of the current enterprise is accessed in each operating system of the current enterprise within a certain historical time segment is used as output data of the deep neural network, and the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple pieces of personnel-related information of the certain person of the current enterprise, and multiple pieces of flow-related data corresponding to multiple historical time segments before the certain historical time segment are used as input data of the deep neural network to perform this learning operation, thereby ensuring the learning effect of each learning operation of the deep neural network;

[0039] Step 2: Targeted screening of multiple basic data for intelligent judgment of the activity level of each person involved in the current enterprise in various operating systems of the current enterprise in future time segments;

[0040] Specifically, the multiple basic data include the number of various operating systems of the current enterprise, the number of types of goods sold by the current enterprise, multiple pieces of personnel-related information of the target personnel of the current enterprise, and multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment of the target personnel;

[0041] More specifically, the multiple pieces of personnel-related information of the target personnel of the current enterprise include the target personnel's years of employment, level value, number of managers, and number of managed personnel, and the single piece of flow-related data corresponding to each time segment of the target personnel is the number of times the target personnel is accessed in each operating system of the current enterprise in the time segment;

[0042] like Figure 1 As shown, multiple pieces of personnel-related information of the target personnel of the current enterprise can be parsed from the enterprise organizational structure of the current enterprise, and multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment of the target personnel can be read from the archives;

[0043] In this way, through comprehensive and sufficient targeted screening of the above basic data, the reliability and stability of the intelligent prediction results are further guaranteed;

[0044] Step 3: Adopt the AI ​​analysis model with customized structure in the first step, based on multiple basic data selected in the second step, to intelligently predict the active data of each enterprise employee in various operating systems of the current enterprise in future time segments;

[0045] like Figure 1 As shown, the AI ​​analysis model outputs the activity data of each enterprise personnel in each operation system of the current enterprise in the future time segment, that is, the activity level of each enterprise personnel in the future time;

[0046] Step 4: Based on the intelligent judgment result of step 3, determine the importance level of enterprise personnel in the future time segment, and then judge whether the enterprise personnel can still be classified as the master data of the current enterprise in the future time segment, so as to complete the master data judgment of enterprise personnel in different time segments;

[0047] For example, when it is determined that the importance level of an enterprise personnel in the future time segment is lower than or equal to the set level threshold, the enterprise personnel is not managed as master data in the current time segment;

[0048] And by way of example, when it is determined that the importance level of the enterprise personnel in the future time segment is higher than the set level threshold, the enterprise personnel is still classified as the master data for management in the current time segment;

[0049] In this way, each enterprise can determine whether the enterprise personnel will still be the enterprise's master data in the future time segment based on the master data information known in advance, and when the enterprise personnel will still be the enterprise's master data in the future time segment, identify the importance level of the future time segment, thereby customizing different master data management strategies for the enterprise personnel in the future time segment;

[0050] For example, the higher the importance level of enterprise personnel as master data in the future time segment, the more attention the enterprise will pay to the enterprise personnel in the future time segment. At the same time, enterprise personnel who are not master data in the future time segment can be removed from the list of concerned personnel associated with the enterprise's future time segment. In this way, the master data management of the same enterprise personnel in different time periods and levels is realized, and the enterprise master data management level is improved;

[0051] The key points of the present invention are: a master data management mechanism for the same enterprise personnel in different time periods and levels, intelligent prediction of the active data of each enterprise personnel in various operating systems of the current enterprise in future time segments, customized structural design of AI analysis models, and targeted screening of multiple basic data.

[0052] Next, a master data-based management method and system of the present invention will be specifically described in the form of an embodiment.

[0053] Example 1

[0054] Figure 2 The figure is a flowchart showing a management method based on master data according to Embodiment 1 of the present invention.

[0055] like Figure 2 As shown, the master data-based management method comprises the following steps:

[0056] Step S101: obtaining the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple pieces of personnel-related information of the target personnel;

[0057] For example, obtaining the employment years, level value, number of managers and number of managed personnel of a target person of the current enterprise as multiple pieces of personnel-related information of the target person includes: using multiple information collection units to respectively collect the employment years, level value, number of managers and number of managed personnel of the target person;

[0058] Step S102: Acquire multiple pieces of flow association data corresponding to multiple historical time segments before the current time segment for the target person, wherein the single piece of flow association data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment;

[0059] Specifically, multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment are obtained. The single piece of flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise within the time segment. Each time segment is a quarter of an hour, that is, 15 minutes. The current time is 11:00 a.m., then the current time segment is a future time segment, which is represented on the time axis as 11:00 a.m. to 11:15 a.m., and the multiple historical time segments before the current time segment are 10:40 a.m. to 11:15 a.m., respectively. 5:00 a.m. to 11:00 a.m., 10:30 a.m. to 10:45 a.m., 10:15 a.m. to 10:30 a.m., 10:00 a.m. to 10:15 a.m., 9:45 a.m. to 10:00 a.m., 9:30 a.m. to 9:45 a.m., 9:15 a.m. to 9:30 a.m., 9:00 a.m. to 9:15 a.m., 8:45 a.m. to 9:00 a.m., 8:30 a.m. to 8:45 a.m., 8:15 a.m. to 8:30 a.m., 8:00 a.m. to 8:15 a.m., and so on, one historical time segment every 15 minutes;

[0060] Step S103: performing a set number of learning operations on the deep neural network to obtain a deep neural network after completing each learning operation, and outputting the deep neural network as an AI analytical model, wherein the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise;

[0061] For example, a set number of learning operations are performed on the deep neural network to obtain a deep neural network after completing each learning operation, and the deep neural network is output as an AI analysis model, and the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise, including: the number of each operating system of the current enterprise is 5, the value of the set number is 100, the number of each operating system of the current enterprise is 8, the value of the set number is 150, the number of each operating system of the current enterprise is 10, the value of the set number is 200, and so on;

[0062] Step S104: The AI ​​analysis model is used to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise within the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple pieces of personnel association information of the target person of the current enterprise, and multiple pieces of flow association data corresponding to multiple historical time segments before the current time segment.

[0063] Specifically, the AI ​​analysis model is used to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise in the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment. The number of times the target person is accessed in each operating system of the current enterprise in the current time segment includes: a numerical simulation mode can be selected to implement the test and simulation of the data processing process of intelligently analyzing the number of times the target person is accessed in each operating system of the current enterprise in the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment;

[0064] Step S105: determining the importance level of the target person in the current time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, and when the importance level is lower than or equal to the set level threshold, the target person is not managed as master data in the current time segment;

[0065] In this way, the target person may be not the master data, the master data of the light importance level, the master data of the medium importance level, or the master data of the high importance level in the current time segment which is the future time segment, which provides an important basis for the subsequent pre-configuration of the master data management strategy for the target person by the current enterprise, such as setting different attention levels;

[0066] Among them, a plurality of flow-related data corresponding to a plurality of historical time segments before the current time segment of the target person are obtained, and a single flow-related data corresponding to each time segment of the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, including: when the target person is not used as master data in a certain time segment, a single flow-related data corresponding to the most recent time segment in which the target person is used as master data before the certain time segment is used as the single flow-related data corresponding to the certain time segment;

[0067] Wherein, determining the importance level of the target person in the current time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment includes: the determined importance level of the target person in the current time segment is proportional to the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment;

[0068] For example, the importance level of the target person determined in the current time segment is proportional to the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, including: the larger the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, the larger the value of the importance level of the target person determined in the current time segment, and the higher the corresponding importance;

[0069] Among them, the multiple flow association data corresponding to the target person in multiple historical time segments before the current time segment, the single flow association data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the number of multiple historical time segments before the current time segment is monotonically positively correlated with the number of each operating system of the current enterprise;

[0070] For example, the number of multiple historical time segments before the current time segment and the number of each operating system of the current enterprise are monotonically positively correlated, including: the number of each operating system of the current enterprise is 5, the number of multiple historical time segments before the current time segment is 20, the number of each operating system of the current enterprise is 8, the number of multiple historical time segments before the current time segment is 32, the number of each operating system of the current enterprise is 10, the number of multiple historical time segments before the current time segment is 40, and so on;

[0071] Among them, obtaining multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the various operating systems of the current enterprise include the financial system, OA collaborative office system, procurement system, capital budget system and human resources system of the current enterprise;

[0072] And by way of example, the various operating systems of the current enterprise are not limited to the financial system, OA collaborative office system, procurement system, capital budget system and human resources system of the current enterprise, but may also be the resource management system, process management system, organizational structure system, personnel management system, business management system, customer management system and supplier management system of the current enterprise;

[0073] At this time, the enterprise personnel that appear in each operating system of the resource management system, process management system, organizational structure system, personnel management system, business management system, customer management system and supplier management system of the current enterprise can be regarded as master data, namely, resource master data, process master data, organizational structure master data, personnel master data, business master data, customer master data and supplier master data. In these operating systems, the data information of the master data used is unified and consistent;

[0074] The present invention faces the master data type of enterprise personnel that appears simultaneously in each operating system of the resource management system, process management system, organizational structure system, personnel management system, business management system, customer management system and supplier management system of the current enterprise, and makes intelligent judgment on the active data of each enterprise personnel in each operating system of the current enterprise in future time segments, that is, the future time activity level of each enterprise personnel, and determines the importance level of the enterprise personnel in the future time segments according to the intelligent judgment result, and then judges whether the enterprise personnel can still be classified as the master data of the current enterprise in the future time segments, thereby completing the time segment master data judgment of the enterprise personnel;

[0075] For example, when it is determined that the importance level of the enterprise personnel in the future time segment is lower than or equal to the set level threshold, the enterprise personnel is not managed as master data in the current time segment;

[0076] And by way of example, when it is determined that the importance level of the enterprise personnel in the future time segment is higher than the set level threshold, the enterprise personnel is still classified as the master data for management in the current time segment;

[0077] And wherein, a set number of learning operations are performed on the deep neural network to obtain a deep neural network after completing each learning operation, and output it as an AI analysis model, and the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise. It also includes: in each learning operation performed on the deep neural network, the number of times a certain person of the current enterprise is accessed in each operating system of the current enterprise within a certain historical time segment is used as the output data of the deep neural network, the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple pieces of personnel-related information of the certain person of the current enterprise, and multiple pieces of flow-related data corresponding to multiple historical time segments before the certain historical time segment are used as input data of the deep neural network to perform this learning operation.

[0078] Example 2

[0079] Figure 3The figure is a flowchart showing a management method based on master data according to Embodiment 2 of the present invention.

[0080] like Figure 3 As shown, before step S102, the master data-based management method further includes:

[0081] Step S301: determining the importance level of the target person in a certain historical time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the certain historical time segment, and managing the target person as master data in the certain historical time segment when the determined importance level of the target person in the certain historical time segment is higher than the set level threshold;

[0082] For example, the importance level of the target person in a certain historical time segment is determined based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise within the certain historical time segment, and when the determined importance level of the target person in the certain historical time segment is higher than the set level threshold, the target person is managed as master data in the certain historical time segment, including: using a programmable logic device to implement a data processing process in which the importance level of the target person in the certain historical time segment is determined based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise within the certain historical time segment, and when the determined importance level of the target person in the certain historical time segment is higher than the set level threshold, the target person is managed as master data in the certain historical time segment.

[0083] Example 3

[0084] Figure 4 The present invention is a flowchart showing a method for managing master data based on embodiment 3 of the present invention.

[0085] like Figure 4 As shown, after step S105, the master data-based management method further includes:

[0086] Step S401: Packing the importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment into the same network data packet and transmitting it to a remote cloud computing management node through a wireless communication network;

[0087] For example, the importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment are packaged into the same network data packet and transmitted to a remote cloud computing management node through a wireless communication network, including: the importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment are packaged into the same IP data packet and transmitted to a remote cloud computing management node through a time division duplex communication network.

[0088] In any of the above embodiments 1-3, optionally, in the master data-based management method:

[0089] Acquiring the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple pieces of personnel association information of the target personnel includes: the level value of the target personnel is the level of the target personnel in the current enterprise, and the larger the level value of the target personnel in the current enterprise, the lower the position of the target personnel in the current enterprise;

[0090] Wherein, obtaining the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple pieces of personnel association information of the target personnel also includes: the number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise;

[0091] The number of managers of the target person refers to the number of people directly managed by the target person in the current enterprise, and the number of managed persons of the target person refers to the number of people who directly manage the target person in the current enterprise, including: the numerical value of the level of the people directly managed by the target person in the current enterprise is greater than the numerical value of the level of the target person in the current enterprise;

[0092] The number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise. The number of personnel who directly manage the target personnel in the current enterprise also includes: the numerical value of the grade of the personnel who directly manage the target personnel in the current enterprise is less than the numerical value of the grade of the target personnel in the current enterprise;

[0093] Among them, the multiple flow-related data corresponding to the target person in multiple historical time segments before the current time segment, the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the current time segment starts at the current time and the duration of each time segment is the same;

[0094] For example, the current time segment starts at the current time and the duration of each time segment is the same, including: the current time is 10:00 a.m., and each time segment is a quarter of an hour, that is, 15 minutes;

[0095] And wherein, the target person has multiple flow-related data corresponding to multiple historical time segments before the current time segment, and the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise within the time segment, and also includes: the current time segment and multiple historical time segments before the current time segment form a complete time interval on the time axis.

[0096] Example 4

[0097] Figure 5 The internal structure diagram of a management system based on master data according to Embodiment 4 of the present invention is shown.

[0098] like Figure 5 As shown, the master data-based management system includes the following components:

[0099] An information collection device, used to obtain the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple personnel-related information of the target personnel;

[0100] For example, obtaining the employment years, level value, number of managers and number of managed personnel of a target person of the current enterprise as multiple pieces of personnel-related information of the target person includes: using multiple information collection units to respectively collect the employment years, level value, number of managers and number of managed personnel of the target person;

[0101] A data capture device is used to obtain multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, and the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise within the time segment;

[0102] Specifically, multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment are obtained. The single piece of flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise within the time segment. Each time segment is a quarter of an hour, that is, 15 minutes. The current time is 11:00 a.m., then the current time segment is a future time segment, which is represented on the time axis as 11:00 a.m. to 11:15 a.m., and the multiple historical time segments before the current time segment are 10:40 a.m. to 11:15 a.m., respectively. 5:00 a.m. to 11:00 a.m., 10:30 a.m. to 10:45 a.m., 10:15 a.m. to 10:30 a.m., 10:00 a.m. to 10:15 a.m., 9:45 a.m. to 10:00 a.m., 9:30 a.m. to 9:45 a.m., 9:15 a.m. to 9:30 a.m., 9:00 a.m. to 9:15 a.m., 8:45 a.m. to 9:00 a.m., 8:30 a.m. to 8:45 a.m., 8:15 a.m. to 8:30 a.m., 8:00 a.m. to 8:15 a.m., and so on, one historical time segment every 15 minutes;

[0103] An object building device is used to perform a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and output it as an AI analysis model, wherein the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise;

[0104] For example, a set number of learning operations are performed on the deep neural network to obtain a deep neural network after completing each learning operation, and the deep neural network is output as an AI analysis model, and the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise, including: the number of each operating system of the current enterprise is 5, the value of the set number is 100, the number of each operating system of the current enterprise is 8, the value of the set number is 150, the number of each operating system of the current enterprise is 10, the value of the set number is 200, and so on;

[0105] A frequency analysis device, connected to the information collection device, the data capture device and the object assembly device respectively, for using the AI ​​analysis model to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise within the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment of the target person;

[0106] Specifically, the AI ​​analysis model is used to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise in the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment. The number of times the target person is accessed in each operating system of the current enterprise in the current time segment includes: a numerical simulation mode can be selected to implement the test and simulation of the data processing process of intelligently analyzing the number of times the target person is accessed in each operating system of the current enterprise in the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment;

[0107] A content mapping device, connected to the frequency analysis device, is used to determine the importance level of the target person in the current time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, and when the importance level is lower than or equal to a set level threshold, the target person is not managed as master data in the current time segment;

[0108] In this way, the target person may be not the master data, the master data of the light importance level, the master data of the medium importance level, or the master data of the high importance level in the current time segment which is the future time segment, which provides an important basis for the subsequent pre-configuration of the master data management strategy for the target person by the current enterprise, such as setting different attention levels;

[0109] Among them, a plurality of flow-related data corresponding to a plurality of historical time segments before the current time segment of the target person are obtained, and a single flow-related data corresponding to each time segment of the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, including: when the target person is not used as master data in a certain time segment, a single flow-related data corresponding to the most recent time segment in which the target person is used as master data before the certain time segment is used as the single flow-related data corresponding to the certain time segment;

[0110] Wherein, determining the importance level of the target person in the current time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment includes: the determined importance level of the target person in the current time segment is proportional to the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment;

[0111] For example, the importance level of the target person determined in the current time segment is proportional to the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, including: the larger the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, the larger the value of the importance level of the target person determined in the current time segment, and the higher the corresponding importance;

[0112] Among them, the multiple flow association data corresponding to the target person in multiple historical time segments before the current time segment, the single flow association data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the number of multiple historical time segments before the current time segment is monotonically positively correlated with the number of each operating system of the current enterprise;

[0113] For example, the number of multiple historical time segments before the current time segment and the number of each operating system of the current enterprise are monotonically positively correlated, including: the number of each operating system of the current enterprise is 5, the number of multiple historical time segments before the current time segment is 20, the number of each operating system of the current enterprise is 8, the number of multiple historical time segments before the current time segment is 32, the number of each operating system of the current enterprise is 10, the number of multiple historical time segments before the current time segment is 40, and so on;

[0114] Among them, obtaining multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the various operating systems of the current enterprise include the financial system, OA collaborative office system, procurement system, capital budget system and human resources system of the current enterprise;

[0115] And wherein, a set number of learning operations are performed on the deep neural network to obtain a deep neural network after completing each learning operation, and output it as an AI analysis model, and the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise. It also includes: in each learning operation performed on the deep neural network, the number of times a certain person of the current enterprise is accessed in each operating system of the current enterprise within a certain historical time segment is used as the output data of the deep neural network, the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple pieces of personnel-related information of the certain person of the current enterprise, and multiple pieces of flow-related data corresponding to multiple historical time segments before the certain historical time segment are used as input data of the deep neural network to perform this learning operation.

[0116] Example 5

[0117] Figure 6 1 is an internal structure diagram of a management system based on master data according to Embodiment 5 of the present invention.

[0118] like Figure 6 As shown, the master data-based management system also includes:

[0119] A level management device, connected to the frequency analysis device, is used to determine the importance level of the target person in a certain historical time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the certain historical time segment, and when the determined importance level of the target person in the certain historical time segment is higher than the set level threshold, manage the target person in the certain historical time segment as master data;

[0120] For example, the importance level of the target person in a certain historical time segment is determined based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise within the certain historical time segment, and when the determined importance level of the target person in the certain historical time segment is higher than the set level threshold, the target person is managed as master data in the certain historical time segment, including: using a programmable logic device to implement the level management device to complete a data processing process of determining the importance level of the target person in the certain historical time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise within the certain historical time segment, and when the determined importance level of the target person in the certain historical time segment is higher than the set level threshold, the target person is managed as master data in the certain historical time segment.

[0121] Example 6

[0122] Figure 7 1 is an internal structure diagram of a management system based on master data according to Embodiment 6 of the present invention.

[0123] like Figure 7 As shown, the master data-based management system also includes:

[0124] A network transmission device, connected to the content mapping device, is used to package the importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment into a same network data packet and transmit it to a remote cloud computing management node through a wireless communication network;

[0125] For example, the importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment are packaged into the same network data packet and transmitted to a remote cloud computing management node through a wireless communication network, including: the importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment are packaged into the same IP data packet and transmitted to a remote cloud computing management node through a time division duplex communication network.

[0126] And in any one of the above embodiments 4-6, optionally, in the master data-based management system:

[0127] Acquiring the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple pieces of personnel association information of the target personnel includes: the level value of the target personnel is the level of the target personnel in the current enterprise, and the larger the level value of the target personnel in the current enterprise, the lower the position of the target personnel in the current enterprise;

[0128] Wherein, obtaining the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple pieces of personnel association information of the target personnel also includes: the number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise;

[0129] The number of managers of the target person refers to the number of people directly managed by the target person in the current enterprise, and the number of managed persons of the target person refers to the number of people who directly manage the target person in the current enterprise, including: the numerical value of the level of the people directly managed by the target person in the current enterprise is greater than the numerical value of the level of the target person in the current enterprise;

[0130] The number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise. The number of personnel who directly manage the target personnel in the current enterprise also includes: the numerical value of the grade of the personnel who directly manage the target personnel in the current enterprise is less than the numerical value of the grade of the target personnel in the current enterprise;

[0131] Among them, the multiple flow-related data corresponding to the target person in multiple historical time segments before the current time segment, the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the current time segment starts at the current time and the duration of each time segment is the same;

[0132] For example, the current time segment starts at the current time and the duration of each time segment is the same, including: the current time is 10:00 a.m., and each time segment is a quarter of an hour, that is, 15 minutes;

[0133] And wherein, the target person has multiple flow-related data corresponding to multiple historical time segments before the current time segment, and the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise within the time segment, and also includes: the current time segment and multiple historical time segments before the current time segment form a complete time interval on the time axis.

[0134] In addition, in a management method and system based on master data according to the present invention:

[0135] The AI ​​analysis model is used to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise in the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment. The method includes: performing binary value conversion processing on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment, and then synchronously inputting them into the AI ​​analysis model;

[0136] For example, the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple pieces of personnel-related information of the target personnel of the current enterprise, and multiple pieces of flow-related data corresponding to multiple historical time segments of the target personnel before the current time segment are respectively converted into binary values ​​and then synchronously input into the AI ​​analysis model, including: using a numerical conversion unit and a synchronous drive interface to collaboratively complete the numerical processing of the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple pieces of personnel-related information of the target personnel of the current enterprise, and multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment are respectively converted into binary values ​​and then synchronously input into the AI ​​analysis model;

[0137] Specifically, the numerical conversion unit is used to perform binary numerical conversion processing on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target personnel of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment of the target personnel, respectively. The synchronous drive interface is connected to the numerical conversion unit, and is used to perform synchronous input of various numerical values ​​obtained after the binary numerical conversion processing to the AI ​​analysis model;

[0138] And wherein, the AI ​​analysis model is used to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise within the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment. It also includes: the number of times the target person is accessed in each operating system of the current enterprise within the current time segment obtained by the intelligent analysis is a numerical representation after binary value conversion processing.

[0139] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A management method based on master data, characterized in that: The method comprises: Obtain the target personnel's employment years, level value, number of managers, and number of managed personnel of the current enterprise as multiple personnel-related information of the target personnel; Acquire multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, and the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise within the time segment; Performing a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and outputting it as an AI parsing model; The AI ​​analysis model is used to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise within the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment of the target person; The importance level of the target person in the current time segment is determined based on the cumulative number of times the target person is accessed in each operating system of the current enterprise in the current time segment, and when the importance level is lower than or equal to the set level threshold, the target person will not be managed as master data in the current time segment.

2. The master data-based management method according to claim 1, characterized in that: Determining the importance level of the target person in the current time segment based on the cumulative values ​​of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment includes: determining the importance level of the target person in the current time segment to be proportional to the cumulative values ​​of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment; Wherein, performing a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and outputting it as an AI analytical model includes: performing a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and outputting it as an AI analytical model, wherein the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise; Among them, a plurality of flow-related data corresponding to a plurality of historical time segments before the current time segment of the target person are obtained, and a single flow-related data corresponding to each time segment of the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, including: when the target person is not used as master data in a certain time segment, a single flow-related data corresponding to the most recent time segment in which the target person is used as master data before the certain time segment is used as the single flow-related data corresponding to the certain time segment; Among them, the multiple flow association data corresponding to the target person in multiple historical time segments before the current time segment, the single flow association data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the number of multiple historical time segments before the current time segment is monotonically positively correlated with the number of each operating system of the current enterprise; Among them, obtaining multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the various operating systems of the current enterprise include the financial system, OA collaborative office system, procurement system, capital budget system and human resources system of the current enterprise; Among them, a set number of learning operations are performed on the deep neural network to obtain a deep neural network after completing each learning operation, and the deep neural network is output as an AI analysis model. The value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise. It also includes: in each learning operation performed on the deep neural network, the number of times a certain person of the current enterprise is accessed in each operating system of the current enterprise within a certain historical time segment is used as the output data of the deep neural network, the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the certain person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the certain historical time segment are used as input data of the deep neural network to perform this learning operation.

3. The master data-based management method according to claim 2, characterized in that: After obtaining multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment, the single piece of flow-related data corresponding to the target person in each time segment is before each number of times the target person is accessed in each operating system of the current enterprise in the time segment, the method further includes: The importance level of the target person in the historical time segment is determined based on the cumulative number of times the target person is accessed in each operating system of the current enterprise within the historical time segment, and when the determined importance level of the target person in the historical time segment is higher than the set level threshold, the target person is managed as master data in the historical time segment.

4. The master data-based management method according to claim 2, characterized in that: After determining the importance level of the target person in the current time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, and not managing the target person as master data in the current time segment when the importance level is lower than or equal to a set level threshold, the method further includes: The importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment are packaged into the same network data packet and transmitted to a remote cloud computing management node through a wireless communication network.

5. The master data-based management method according to any one of claims 2 to 4, characterized in that: The obtaining of the target personnel's employment years, grade value, number of managers and number of managed personnel of the current enterprise as multiple pieces of personnel association information of the target personnel includes: the grade value of the target personnel is the grade level of the target personnel in the current enterprise, and the larger the grade level value of the target personnel in the current enterprise, the lower the position of the target personnel in the current enterprise; The step of obtaining the target personnel's years of employment, level value, number of managers and number of managed personnel of the current enterprise as multiple sets of personnel-related information of the target personnel also includes: the number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise; The number of managers of the target person refers to the number of people directly managed by the target person in the current enterprise, and the number of managed persons of the target person refers to the number of people who directly manage the target person in the current enterprise, including: the numerical value of the level of the people directly managed by the target person in the current enterprise is greater than the numerical value of the level of the target person in the current enterprise; The number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise. The number of personnel who directly manage the target personnel in the current enterprise also includes: the numerical value of the grade of the personnel who directly manage the target personnel in the current enterprise is less than the numerical value of the grade of the target personnel in the current enterprise; Among them, the multiple flow-related data corresponding to the target person in multiple historical time segments before the current time segment, the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the current time segment starts at the current time and the duration of each time segment is the same; Among them, the target person has multiple flow-related data corresponding to multiple historical time segments before the current time segment, and the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise within the time segment, and also includes: the current time segment and multiple historical time segments before the current time segment form a complete time interval on the time axis.

6. A management system based on master data, characterized in that: The system comprises: An information collection device, used to obtain the employment years, level value, number of managers and number of managed personnel of the target personnel of the current enterprise as multiple personnel-related information of the target personnel; A data capture device is used to obtain multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, and the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise within the time segment; An object building device is used to perform a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and output it as an AI analysis model; A frequency analysis device, connected to the information collection device, the data capture device and the object assembly device respectively, for using the AI ​​analysis model to intelligently analyze the number of times the target person is accessed in each operating system of the current enterprise within the current time segment based on the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the target person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the current time segment of the target person; A content mapping device is connected to the frequency analysis device, and is used to determine the importance level of the target person in the current time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment, and when the importance level is lower than or equal to the set level threshold, the target person is not managed as master data in the current time segment. Acquire multiple sets of flow-related data corresponding to the target person in multiple historical time segments before the current time segment. The single set of flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise within the time segment.

7. The master data-based management system according to claim 6, characterized in that: Determining the importance level of the target person in the current time segment based on the cumulative values ​​of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment includes: determining the importance level of the target person in the current time segment to be proportional to the cumulative values ​​of the number of times the target person is accessed in each operating system of the current enterprise in the current time segment; Wherein, performing a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and outputting it as an AI analytical model includes: performing a set number of learning operations on the deep neural network to obtain the deep neural network after completing each learning operation, and outputting it as an AI analytical model, wherein the value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise; Among them, a plurality of flow-related data corresponding to a plurality of historical time segments before the current time segment of the target person are obtained, and a single flow-related data corresponding to each time segment of the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, including: when the target person is not used as master data in a certain time segment, a single flow-related data corresponding to the most recent time segment in which the target person is used as master data before the certain time segment is used as the single flow-related data corresponding to the certain time segment; Among them, the multiple flow association data corresponding to the target person in multiple historical time segments before the current time segment, the single flow association data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the number of multiple historical time segments before the current time segment is monotonically positively correlated with the number of each operating system of the current enterprise; Among them, obtaining multiple pieces of flow-related data corresponding to multiple historical time segments before the current time segment for the target person, the single piece of flow-related data corresponding to each time segment for the target person is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the various operating systems of the current enterprise include the financial system, OA collaborative office system, procurement system, capital budget system and human resources system of the current enterprise; Among them, a set number of learning operations are performed on the deep neural network to obtain a deep neural network after completing each learning operation, and the deep neural network is output as an AI analysis model. The value of the set number is monotonically positively correlated with the number of each operating system of the current enterprise. It also includes: in each learning operation performed on the deep neural network, the number of times a certain person of the current enterprise is accessed in each operating system of the current enterprise within a certain historical time segment is used as the output data of the deep neural network, the number of each operating system of the current enterprise, the number of types of goods sold by the current enterprise, multiple personnel-related information of the certain person of the current enterprise, and multiple flow-related data corresponding to multiple historical time segments before the certain historical time segment are used as input data of the deep neural network to perform this learning operation.

8. The master data-based management system according to claim 7, characterized in that: The system further comprises: A level management device is connected to the frequency analysis device, and is used to determine the importance level of the target person in a certain historical time segment based on the cumulative value of the number of times the target person is accessed in each operating system of the current enterprise within the certain historical time segment, and when the determined importance level of the target person in the certain historical time segment is higher than the set level threshold, the target person is managed as master data in the certain historical time segment.

9. The master data-based management system according to claim 7, characterized in that: The system further comprises: A network transmission device is connected to the content mapping device, and is used to package the importance level of the target person in the current time segment and the number of times the target person is accessed in each operating system of the current enterprise in the current time segment into the same network data packet and transmit it to a remote cloud computing management node through a wireless communication network.

10. The master data-based management system according to any one of claims 7 to 9, characterized in that: The obtaining of the target personnel's employment years, grade value, number of managers and number of managed personnel of the current enterprise as multiple pieces of personnel association information of the target personnel includes: the grade value of the target personnel is the grade level of the target personnel in the current enterprise, and the larger the grade level value of the target personnel in the current enterprise, the lower the position of the target personnel in the current enterprise; The step of obtaining the target personnel's years of employment, level value, number of managers and number of managed personnel of the current enterprise as multiple sets of personnel-related information of the target personnel also includes: the number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise; The number of managers of the target person refers to the number of people directly managed by the target person in the current enterprise, and the number of managed persons of the target person refers to the number of people who directly manage the target person in the current enterprise, including: the numerical value of the level of the people directly managed by the target person in the current enterprise is greater than the numerical value of the level of the target person in the current enterprise; The number of managers of the target personnel refers to the number of personnel directly managed by the target personnel in the current enterprise, and the number of managed personnel of the target personnel refers to the number of personnel who directly manage the target personnel in the current enterprise. The number of personnel who directly manage the target personnel in the current enterprise also includes: the numerical value of the grade of the personnel who directly manage the target personnel in the current enterprise is less than the numerical value of the grade of the target personnel in the current enterprise; Among them, the multiple flow-related data corresponding to the target person in multiple historical time segments before the current time segment, the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise in the time segment, and also includes: the current time segment starts at the current time and the duration of each time segment is the same; Among them, the target person has multiple flow-related data corresponding to multiple historical time segments before the current time segment, and the single flow-related data corresponding to the target person in each time segment is the number of times the target person is accessed in each operating system of the current enterprise within the time segment, and also includes: the current time segment and multiple historical time segments before the current time segment form a complete time interval on the time axis.

Images