CN-121998602-A - Visual management method and system for human resource data based on semantic analysis technology

CN121998602ACN 121998602 ACN121998602 ACN 121998602ACN-121998602-A

Abstract

The invention discloses a visual management method and a visual management system for human resource data based on a semantic analysis technology, which relate to the technical field of human resource management and comprise the steps of collecting employee digital production data and text production data, analyzing and determining employee evaluation indexes; the method comprises the steps of carrying out normalization processing on digital production data and text production data, calculating expected output, determining employee ability evaluation level, constructing a neural network evaluation model, training the model by using the digital production data and the text production data until the model converges, evaluating employee ability by using the converged neural network evaluation model, and outputting employee ability evaluation level. According to the invention, the digital production data and the text production data of staff are collected simultaneously, and preprocessing and semantic analysis are performed, so that the dominant and implicit information in the human resource data can be more comprehensively mined, and the problem that the key information is difficult to extract rapidly and accurately in the traditional data processing mode is solved.

Inventors

QIANG WEI
CHENG CHUANLIANG
YANG ZHIGUO
SUN FENGQIAO
GUO MIAO

Assignees

南京钢铁股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260104

Claims (9)

1. A visual management method of human resource data based on semantic analysis technology is characterized by comprising the following steps: collecting employee digital production data and text production data, analyzing the collected production data, and determining employee evaluation indexes; Normalizing the digital production data and the text production data, calculating expected output of the digital production data and the text production data, and determining employee capability evaluation grades; constructing a neural network evaluation model, and training the neural network evaluation model by using the digital production data and the text production data until the model converges; and evaluating the employee capability by using the converged neural network evaluation model, and outputting the employee evaluation grade.
2. The visual management method of human resource data based on semantic analysis technology according to claim 1, wherein the steps of collecting employee digital production data and text production data, analyzing the collected production data, and determining employee evaluation indexes include: Preprocessing the collected employee digital production data, and taking company knowledge, professional technical knowledge, engineering category, efficiency, equipment management capability, problem solving capability, on-schedule delivery capability, organization coordination capability, disciplinary, innovation and objective contribution as employee dominant evaluation indexes; preprocessing the collected employee text production data, carrying out semantic analysis on the preprocessed text production data, and determining employee invisible evaluation indexes; And calculating a correlation coefficient between the evaluation indexes, and determining the employee evaluation indexes based on the correlation coefficient.
3. The visual management method of human resource data based on semantic analysis technology according to claim 2, wherein the semantic analysis of the preprocessed text production data comprises: Scanning personal evaluation reports of staff, performing word frequency statistics on the personal evaluation reports of the staff, and extracting keywords as invisible rating indexes; Constructing an emotion dictionary, constructing a text semantic matching rule, and calculating emotion values of personnel evaluation reports; And distributing the emotion value of the whole report to each employee in the team according to the contribution degree percentage of the employee in the team, obtaining the data value of each employee under the index, and calculating the contribution degree of each employee according to the data value.
4. The visual management method of human resource data based on semantic analysis technology according to claim 2, wherein the calculating the correlation coefficient between the evaluation indexes comprises: calculating a correlation coefficient between the dominant evaluation index and the invisible evaluation index through a formula I, wherein the formula I is as follows: , wherein, Representing the value of the kth employee under the ith index, Represents the average value of the index of the i-th item, Representing the correlation coefficient between every two indexes.
5. The visual management method of human resource data based on semantic analysis technology according to claim 2, wherein the employee evaluation index comprises a knowledge index, a capability index and a career literacy index.
6. The visual management method of human resource data based on semantic analysis technology according to claim 1, wherein normalizing the digital production data and the text production data comprises: normalizing the digital production data and the text production data by a formula II, wherein the formula II is as follows: , wherein, As an average value of the data, Is the standard deviation of the data.
7. The visual management method of human resource data based on semantic analysis technology according to claim 1, wherein constructing a neural network evaluation model and training the neural network evaluation model by using the digital production data and the text production data until the model converges comprises: Constructing a neural network evaluation model, wherein the neural network evaluation model comprises an input layer, an output layer and a middle layer; training the neural network evaluation model by taking 70% of digital production data and text production data as training data and the remaining 30% as test data; Comparing the output of the neural network model with the expected output, calculating the error between the output of the model and the expected output, and stopping training when the error value is smaller than the preset maximum error value.
8. The visual management method of human resource data based on semantic analysis technology according to claim 7, wherein the number of output layer nodes is 1, and the calculation formula of the number of middle layer nodes is: Wherein k is the number of neurons in the middle layer, m is the number of neurons in the input layer, n is the number of neurons in the output layer, and a is a constant between 1 and 10.
9. A human resource data visual management system based on semantic analysis technology is characterized by comprising: the data acquisition processing module is used for acquiring employee digital production data and text production data, analyzing the acquired production data and determining employee evaluation indexes; The evaluation grade determining module is used for carrying out normalization processing on the digital production data and the text production data, calculating expected output of the digital production data and the text production data and determining employee capability evaluation grade; The model construction module is used for constructing a neural network evaluation model, and training the neural network evaluation model by using the digital production data and the text production data until the model converges; and the employee evaluation module is used for evaluating the employee capability by using the converged neural network evaluation model and outputting the employee evaluation grade.

Description

Visual management method and system for human resource data based on semantic analysis technology Technical Field The invention relates to the technical field of human resource management, in particular to a human resource data visual management method and system based on a semantic analysis technology. Background With the expansion of enterprise scale and the complexity of business, human resource management faces the processing and analysis of massive data. The traditional data processing method is difficult to extract key information rapidly and accurately, so that the decision efficiency is low. The semantic analysis technology can be used for carrying out deep understanding and analysis on text data and extracting valuable information, and the data visualization technology can be used for presenting complex data in an intuitive mode, so that a manager can quickly understand and make decisions. In the prior art, as disclosed in patent application publication No. CN119887139a, an intelligent information screening method and system for human resource system are disclosed, the candidates are intelligently screened by using a bidirectional semantic matching network, and bidirectional recommendation is realized through a blockchain communication link, so that mass recruitment data can be automatically processed, and the recruiters meeting the enterprise requirements can be selected. The prior art has the defect that data analysis can only be carried out according to the resume of the recruiter, and human resource data in a company cannot be comprehensively evaluated, so that the method is suitable for scenes such as employee satisfaction analysis, departure tendency prediction, capability evaluation and the like. Disclosure of Invention The invention aims to solve the technical problem of overcoming the defects of the prior art and providing a visual management method and a visual management system for human resource data based on a semantic analysis technology. In order to solve the technical problems, the technical scheme of the invention is as follows: a visual management method of human resource data based on semantic analysis technology comprises the following steps: collecting employee digital production data and text production data, analyzing the collected production data, and determining employee evaluation indexes; Normalizing the digital production data and the text production data, calculating expected output of the digital production data and the text production data, and determining employee capability evaluation grades; constructing a neural network evaluation model, and training the neural network evaluation model by using the digital production data and the text production data until the model converges; and evaluating the employee capability by using the converged neural network evaluation model, and outputting the employee evaluation grade. The invention relates to a human resource data visual management method based on semantic analysis technology, which comprises the steps of collecting employee digital production data and text production data, analyzing the collected production data, and determining employee evaluation indexes, wherein the employee evaluation indexes comprise: Preprocessing the collected employee digital production data, and taking company knowledge, professional technical knowledge, engineering category, efficiency, equipment management capability, problem solving capability, on-schedule delivery capability, organization coordination capability, disciplinary, innovation and objective contribution as employee dominant evaluation indexes; preprocessing the collected employee text production data, carrying out semantic analysis on the preprocessed text production data, and determining employee invisible evaluation indexes; And calculating a correlation coefficient between the evaluation indexes, and determining the employee evaluation indexes based on the correlation coefficient. As an optimal scheme of the visual management method of human resource data based on the semantic analysis technology, the semantic analysis of the preprocessed text production data comprises the following steps: Scanning personal evaluation reports of staff, performing word frequency statistics on the personal evaluation reports of the staff, and extracting keywords as invisible rating indexes; Constructing an emotion dictionary, constructing a text semantic matching rule, and calculating emotion values of personnel evaluation reports; And distributing the emotion value of the whole report to each employee in the team according to the contribution degree percentage of the employee in the team, obtaining the data value of each employee under the index, and calculating the contribution degree of each employee according to the data value. As an optimal scheme of the human resource data visualization management method based on the semantic analysis technology, the method comprises the following step