Enterprise personnel information management system
By designing an enterprise personnel information management system, the problem of difficulty in effectively managing and analyzing large-scale employee data in the existing technology is solved, dynamic stratification and classification are realized, and management efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202411543843.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-02-21
AI Technical Summary
The existing technology is difficult to effectively manage and analyze large-scale employee data, which leads to the inability to fully reflect the comprehensive quality of employees, and lacks dynamic update capabilities, making it difficult to meet the management needs of modern enterprises.
A corporate personnel information management system was designed, including information collection module, database establishment module, data classification module, correlation calculation module and data update module. By preprocessing, standardizing, classification and correlation calculation of user attribute information, it generates Implicit attribute information to avoid combination explosion problems.
It realizes dynamic stratification and classification based on real-time changes in employee behavior, performance and other key indicators, improves the flexibility and response speed of the management system, and can more accurately evaluate employee capabilities and improve management efficiency and accuracy.
Smart Images
Figure CN119494580A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of information management technology, and in particular, to an enterprise personnel information management system. Background Art
[0002] At present, with the expansion of enterprise scale and the increase in the number of employees, the traditional employee management model often relies on a single indicator, such as performance score or position level, which is difficult to fully reflect the comprehensive quality of employees and lacks dynamic update capabilities. With the development of big data technology, enterprises have accumulated a large amount of employee data, but the existing methods have limitations in extracting effective information from it and applying it to dynamic stratification and classification, which is difficult to meet the management needs of modern enterprises.
[0003] In the prior art, some data mining methods are used to organize and mine various types of complex data collected, turning them into single-dimensional information that can reflect the capabilities of employees. Currently, the commonly used data mining method is the Apriori algorithm, which can mine the associations between data items.
[0004] When mining large-scale data, the current Apriori algorithm inputs all the data into the Apriori algorithm to mine potential connections in the data. However, this method will have the problem of combinatorial explosion due to the large amount of data. Summary of the invention
[0005] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0006] As a first aspect of the present application, in order to solve the technical problems mentioned in the background technology, the present application provides an enterprise personnel information management system, including:
[0007] The information collection module is used to collect the attribute information of all users and pre-process the attribute information;
[0008] A database building module collects attribute information of each user to build a transaction database for each user;
[0009] The enterprise personnel information management system also includes:
[0010] The data classification module establishes a module signal connection with the database and is used to classify each user into several categories to obtain several transaction sets;
[0011] A correlation calculation module, including a plurality of correlation units;
[0012] The data updating module is connected to the data classification module signal, inputs each category of users into the corresponding association degree calculation unit, and generates implicit attribute information of each user.
[0013] In the technical solution provided in the present application, in order to avoid too many sample types being input into the calculation unit, which would lead to a combinatorial explosion problem when the association unit calculates the implicit attribute information of each user, multiple association units are set up. In this way, the number of samples calculated by each association unit will be reduced, thereby avoiding the combinatorial explosion problem.
[0014] The completeness of attribute information of each user is different. If the attribute information of all users is extracted for correlation, it will lead to the inability to accurately identify the meaning of the attribute information of each user.
[0015] Furthermore, the information collection module includes:
[0016] The information entry unit is used to collect the user's attribute information, including position, education, years of work experience, and performance rating;
[0017] A data preprocessing unit preprocesses the attribute information of each user, removes incomplete information, and supplements the missing information with initial values;
[0018] The data encoding unit inputs each item of the user information into an encoder to obtain a standardized data set for each user.
[0019] In the technical solution provided in the present application, by processing user information into a standardized data set, it is possible to adapt to users with different information completeness, so that the same processing method is adopted for all user information.
[0020] Furthermore, the database establishment module uses the attribute information collected by each user as a transaction database and updates the transaction database T in real time. i ;
[0021] T i ={a1, a1, ...a n}; T i represents the transaction database of the i-th user, i represents the user's index, n represents the total number of attributes, a1 represents the first attribute in the transaction database, a2 represents the second attribute in the transaction database, and a n Represents the nth attribute in a transaction database.
[0022] Furthermore, the correlation calculation module includes:
[0023] Threshold definition unit, used to define support threshold min-s and confidence threshold min-c;
[0024] A calculation unit, used to calculate support and confidence;
[0025] The relevance unit uses the Apriori algorithm to generate frequent itemsets. The process is to gradually increase the size of the itemset from a single item to multiple items until the set support threshold is met.
[0026] Furthermore, the calculation unit calculates the support of each attribute as follows:
[0027] Among them, S(X) represents the support of the Xth feature in the transaction set, |T(X)| represents the total number of the Xth feature in the transaction set, and |T| represents the total number of transaction databases in the transaction set.
[0028] The calculation unit calculates the confidence of each attribute as follows:
[0029]
[0030] in, Indicates the confidence that the Xth feature leads to the Yth attribute.
[0031] Furthermore, the data classification module includes:
[0032] An information updating unit, which establishes a module signal connection with the database, is used to update the transaction database of each user in real time to obtain hierarchical information;
[0033] A stratification calculation unit updates the stratification information of each user in real time and calculates the stratification score of each user based on the stratification information;
[0034] The classification unit classifies the transaction database corresponding to the user into a corresponding transaction set based on the hierarchical score of each user.
[0035] In the technical solution provided in the present application, the transaction set is divided based on the hierarchical scores of the users. Therefore, in a transaction set, the users are relatively close to each other, and the common relationships between the users can be found more easily, thereby deriving the ability differences between the users.
[0036] Furthermore, the calculation formula of the stratified score is:
[0037] L i =α1b1+α2b2+α3b3+…α m b m Among them, L i is the hierarchical score of the i-th user, b m is the user’s mth attribute, α m is the weight coefficient of the mth attribute.
[0038] Furthermore, the data update module includes a demand input unit and an information distribution unit; wherein the demand input module is used to input features that need attention, and the information distribution unit inputs the features that need attention into the data classification module and the association calculation module, so as to control the data classification process of the data classification module and the association calculation process of the association calculation module.
[0039] In the technical solution provided in the present application, the data updating module guides the data stratification according to the input features, so that the implicit attribute information finally calculated by the association calculation module can be more representative.
[0040] This application has the following beneficial effects:
[0041] The present invention can stratify and classify employees according to real-time changes in their behaviors, performance and other key indicators. This dynamic adjustment mechanism greatly improves the flexibility and response speed of the system, allowing management to understand the development of employees' capabilities in real time and make quick decisions based on this, thus improving management efficiency and accuracy.
[0042] The present invention builds a more comprehensive employee capability assessment model by combining employee behavior data, performance indicators, skill growth, teamwork and other multi-dimensional information. Compared with the traditional single-dimensional assessment method, this multi-dimensional comprehensive analysis enables employees' potential and development paths to be more accurately displayed, thus providing more reliable data support for the company's talent training and deployment.
[0043] The present invention adopts big data processing technology, which significantly improves the efficiency of the system in processing large-scale employee data. By optimizing the data processing algorithm, the system can quickly analyze and process a large amount of employee data from different departments and positions, ensuring that managers can obtain accurate analysis results in a timely manner, avoiding the problems of slow processing speed and delayed feedback in the existing system, and improving the performance of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The accompanying drawings, which constitute a part of this application, are used to provide a
[0045] Further understanding makes other features, purposes and advantages of the present application more obvious. The schematic embodiment drawings and descriptions of the present application are used to explain the present application and do not constitute improper limitations on the present application.
[0046] In addition, throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the components and elements are not necessarily drawn to scale.
[0047] Figure 1 This is a structural diagram of the enterprise personnel information management system.
[0048] Figure 2 It is a schematic diagram of the data updating module, data classification module and association calculation module. DETAILED DESCRIPTION
[0049] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.
[0050] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.
[0051] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.
[0052] refer to Figures 1-2 Embodiment 1: An enterprise personnel information management system includes: an information collection module for collecting attribute information of all users and preprocessing the attribute information; a database establishment module for collecting attribute information of each user to establish a transaction database for each user; the enterprise personnel information management system also includes: a data classification module, which is connected to the database establishment module signal, and is used to divide each user into several categories to obtain several transaction sets; a correlation calculation module, including several correlation units; a data update module, which is connected to the data classification module signal, inputs each category of users into the corresponding correlation calculation unit, and generates implicit attribute information of each user. Each user in the enterprise personnel information management system provided in this application is essentially an employee of the enterprise. Implicit attribute information is the implicit information of the comprehensive evaluation of employees.
[0053] Furthermore, the information collection module includes: an information entry unit for collecting attribute information of the user, the attribute information including position, education background, years of work experience, and performance rating.
[0054] Attribute information is the recorded employee capabilities. The number, type, and recording method of attribute information are not specifically limited in this application. Generally, it can be divided into two categories: text information and digital information. Text information is generally discrete information. For example, doctoral students and master's students are two different states, and there is no continuity between the two. Correspondingly, age is a continuous information.
[0055] In this solution, the attribute information includes several attributes, and the attributes include several features. Specifically, the attributes are classified information such as position, education, years of work, and performance score. The features are specific descriptive information under each attribute. For example, ordinary employees, managers, and team leaders under the attribute of position are specific features. For continuous information, the corresponding features are continuous feature values. For example, age and salary are continuous feature values, such as 21 years old and 22 years old.
[0056] The data preprocessing unit preprocesses the attribute information of each user, removes incomplete information, and supplements the missing information with initial values.
[0057] In order to ensure that the information collected by each employee can be accurately understood, the information collected by each employee needs to be arranged according to pre-set rules. Therefore, if there is incomplete information, on the one hand it needs to be removed, and on the other hand it needs to be supplemented.
[0058] For example, you need to collect three pieces of information: age, education, and performance. All three pieces of information can be collected for user A. However, user B cannot collect education information. In this case, you need to complete the education information column with initial information, such as "no education information", so that user B's attribute information can also fully include age, education, and performance information.
[0059] The data encoding unit inputs each item of the user information into an encoder to obtain a standardized data set for each user.
[0060] After the data preprocessing unit preprocesses the user's attribute information, the attributes in the attribute information of each user are arranged in the same way. However, some of this information is text information and some is digital information, and it also belongs to natural language. For this reason, it needs to be input into the encoder for processing. The encoder is essentially a labeling process for the attribute information. For status information, different states are assigned to different numbers, such as setting a doctoral student to 3 and a master's student to 2. For digital information, a normalized method can be used to transfer it to a fixed range, and then a standardized data set can be obtained. For each user's standardized data set, the data format is the same, and the data type and data quantity are the same, which can accurately reflect the user's own abilities.
[0061] The database establishment module takes the attribute information collected by each user as a transaction database and updates the transaction database in real time. i ; T i ={a1, a1, ...a n}; T irepresents the transaction database of the i-th user, i represents the user's index, n represents the total number of attributes, a1 represents the first attribute in the transaction database, a2 represents the second attribute in the transaction database, and a n Represents the nth attribute in the transaction database.
[0062] The database establishment module establishes a dynamically updated database for each user, which is updated according to the user's standardized data set. i ={a1, a1, ...a n} is essentially a concrete representation of the standard data set.
[0063] The association calculation module is mainly used to calculate the association and support of each attribute. In order to avoid data explosion, it is necessary to use a data classification unit to classify all the collected databases.
[0064] The data update module includes a demand input unit and an information distribution unit; wherein the demand input module is used to input features that need attention, and the information distribution unit inputs the features that need attention into the data classification module and the association calculation module, and is used to control the data classification process of the data classification module and the association calculation process of the association calculation module.
[0065] Specifically: the correlation calculation module includes: a threshold definition unit, a calculation unit and a correlation unit.
[0066] The threshold definition unit is used to define the support threshold min-s and the confidence threshold min-c. The support threshold and the confidence threshold are preset.
[0067] The calculation unit is used to calculate the support and confidence, and filter the item set based on the initial support and confidence.
[0068] The calculation unit calculates the support of each attribute as follows:
[0069] Among them, S(X) represents the support of the Xth feature in the transaction set, |T(X)| represents the total number of the Xth feature in the transaction set, and |T| represents the total number of transaction databases in the transaction set. Among them, the feature is a specific label under the attribute, for example, academic qualifications are attributes, and doctoral students and master students are features. Using support calculation is actually to calculate the proportion of a specific attribute in the entire transaction set.
[0070] The calculation unit calculates the confidence of each attribute as follows:
[0071]
[0072] in, Indicates the confidence that the Xth feature leads to the Yth attribute.
[0073] The above is the calculation method of support and confidence.
[0074] The way to filter the item set is as follows: the information distribution unit sends the required features to the calculation unit. The features here are generally the characteristics of concern, such as high performance, strong work ability, strong communication skills, and other specific features under such attributes. After obtaining the feature, the calculation unit will calculate the confidence and support of the remaining attributes related to the feature. If it exceeds the threshold, the attribute can be used as an attribute set to input into the Apriori algorithm. If not, the attribute will be removed from the entire transaction set.
[0075] Because we need to avoid the combinatorial explosion problem of the Apriori algorithm, we need to stratify it first. The stratification method is as follows:
[0076] Specifically: The data classification module includes:
[0077] An information updating unit, which establishes a module signal connection with the database, is used to update the transaction database of each user in real time to obtain hierarchical information;
[0078] The stratification calculation unit updates the stratification information of each user in real time and calculates the stratification score of each user based on the stratification information; the calculation formula of the stratification score is:
[0079] L i =α1b1+α2b2+α3b3+…α m b m Among them, L i is the hierarchical score of the i-th user, b m is the user’s mth attribute, α m is the weight coefficient of the mth attribute.
[0080] When the hierarchical calculation unit calculates the hierarchical scores, the attributes and weight coefficients need to be changed according to the requirements of the data update module.
[0081] The classification unit classifies the transaction database corresponding to the user into the corresponding transaction set based on the hierarchical score of each user. Specifically, the hierarchical score can be divided into three levels, for example, 0 to 33 is a low level, 34 to 66 is a middle level, and 67 to 100 is a high level.
[0082] Therefore, for each user, it is necessary to calculate the stratification score and determine the user's level based on the stratification score, and then all users can be divided into three categories.
[0083] The above is the basic calculation method of stratified scores. The update method of weight coefficients and attribute types will be affected by the input features. Specifically, when calculating stratified scores, the attributes relied on are the attributes selected in the calculation unit. The remaining irrelevant attributes need to be deleted.
[0084] For example, if the input feature is high performance, after screening, it is found that education, age, and work experience are associated with high performance, while other attributes such as hobbies and specialties are not associated with high performance. This type of information will not be included in the stratification calculation.
[0085] As for the weight coefficient, it is related to the confidence of each attribute and the input feature. If the confidence is higher, the corresponding weight coefficient will be larger.
[0086] The correlation unit uses the Apriori algorithm to generate the required implicit information. The Apriori algorithm is a common algorithm in this field. The specific construction method will not be repeated here. After adopting the above scheme, all users can be divided into three levels, that is, divided into three transaction sets. Each transaction set is input into the Apriori algorithm separately, and the implicit relationship between each user and the input characteristics can be calculated. For example, the characteristic we input is high performance, and then after inputting the three-level samples into the Apriori algorithm, for each user, we can get an implicit score with high performance. Generally speaking, the lower the implicit score, the worse the correlation with the remaining high performance, and vice versa. In this way, when the company's managers discover high-performance employees, they can train certain key employees based on the correlation information.
[0087] The above description is only some preferred embodiments of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present application is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with (but not limited to) the technical features with similar functions disclosed in the embodiments of the present application to form a technical solution.
Claims
1. An enterprise personnel information management system: including: The information collection module is used to collect the attribute information of all users and pre-process the attribute information; A database building module collects attribute information of each user to build a transaction database for each user; Features: The enterprise personnel information management system also includes: The data classification module establishes a module signal connection with the database and is used to classify each user into several categories to obtain several transaction sets; A correlation calculation module, including a plurality of correlation units; The data updating module is connected to the data classification module signal, inputs each category of users into the corresponding association unit, and generates implicit attribute information of each user.
2. The enterprise personnel information management system according to claim 1, characterized in that: The information collection module includes: The information entry unit is used to collect the user's attribute information, including position, education, years of work experience, and performance rating; A data preprocessing unit preprocesses the attribute information of each user, removes incomplete information, and supplements the missing information with initial values; The data encoding unit inputs each item of the user information into an encoder to obtain a standardized data set for each user.
3. The enterprise personnel information management system according to claim 1, characterized in that: The database establishment module takes the attribute information collected by each user as a transaction database and updates the transaction database T in real time. i ; T i ={a1, a1, ...a n }; T i represents the transaction database of the i-th user, i represents the user's index, n represents the total number of attributes, a1 represents the first attribute in the transaction database, a2 represents the second attribute in the transaction database, and a n Represents the nth attribute in a transaction database.
4. The enterprise personnel information management system according to claim 1, characterized in that: The correlation calculation module includes: Threshold definition unit, used to define support threshold min-s and confidence threshold min-c; A calculation unit, used to calculate support and confidence, and filter item sets based on initial support and confidence; The relevance unit uses the Apriori algorithm to generate frequent itemsets. The process is to gradually increase the size of the itemset from a single item to multiple items until the set support threshold is met.
5. The enterprise personnel information management system according to claim 4, characterized in that: The calculation unit calculates the support of each attribute as follows: Among them, S(X) represents the support of the Xth feature in the transaction set, |T(X)| represents the total number of the Xth feature in the transaction set, and |T| represents the total number of transaction databases in the transaction set. The calculation unit calculates the confidence of each attribute as follows: in, Indicates the confidence that the Xth feature leads to the Yth attribute.
6. According to claim 5, the enterprise personnel information management system: the data classification module comprises: An information updating unit, which establishes a module signal connection with the database, is used to update the transaction database of each user in real time to obtain hierarchical information; A stratification calculation unit updates the stratification information of each user in real time and calculates the stratification score of each user based on the stratification information; The classification unit classifies the transaction database corresponding to the user into a corresponding transaction set based on the hierarchical score of each user.
7. The enterprise personnel information management system according to claim 6, characterized in that: The calculation formula for the stratified score is: L i =α1b1+α2b2+α3b3+…α m b m Among them, L i is the hierarchical score of the i-th user, b m is the user’s mth attribute, α m is the weight coefficient of the mth attribute.
8. The enterprise personnel information management system according to claim 6, characterized in that: The data update module includes a demand input unit and an information distribution unit; wherein the demand input module is used to input features that need attention, and the information distribution unit inputs the features that need attention into the data classification module and the association calculation module, and is used to control the data classification process of the data classification module and the association calculation process of the association calculation module.