CN116485021A - Coal enterprise technical skill person sentry matching prediction method and system - Google Patents
Coal enterprise technical skill person sentry matching prediction method and system Download PDFInfo
- Publication number
- CN116485021A CN116485021A CN202310428380.8A CN202310428380A CN116485021A CN 116485021 A CN116485021 A CN 116485021A CN 202310428380 A CN202310428380 A CN 202310428380A CN 116485021 A CN116485021 A CN 116485021A
- Authority
- CN
- China
- Prior art keywords
- index
- clustering
- coal enterprise
- staff
- technical skill
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003245 coal Substances 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000005286 illumination Methods 0.000 claims description 55
- 238000009499 grossing Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000011002 quantification Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 abstract description 23
- 238000004422 calculation algorithm Methods 0.000 abstract description 14
- 238000007621 cluster analysis Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000007115 recruitment Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 101000637771 Homo sapiens Solute carrier family 35 member G1 Proteins 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 102000053339 human SLC35G1 Human genes 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a coal enterprise technical skill person post matching prediction method and system, comprising the following steps: quantifying the technical skill employee competency evaluation index of each target employee; clustering all quantized samples by taking the primary index points and the secondary index points as feature dimensions to obtain a clustering analysis classification result; training the SVR regression model by using the secondary index points of each target employee to obtain a coal enterprise post matching prediction model; and (5) completing the person post matching of the target staff by using the person post matching prediction model of the coal enterprise. According to the invention, the samples are classified by adopting cluster analysis, and the class attribution category of each sample, namely the classification result, is obtained, so that the problem of consideration of multi-index point weight setting when each sample is classified is avoided. In addition, the support vector machine algorithm adopted by the invention maps the variables to a high-dimensional space and constructs a linear classification function, so that the model has stronger generalization capability, and simultaneously, the occurrence of dimension disasters is well avoided.
Description
Technical Field
The invention relates to the technical field of human resources and data analysis, in particular to a coal enterprise technical skill person post matching prediction method and system.
Background
Coal mine enterprises are currently evolving towards a green intelligent direction. Under the form, the coal enterprises have higher and higher requirements on the quality of technical skill talents, and the use efficiency of the talents needs to be further improved. The traditional talent recruitment and talent post allocation cannot meet the requirements, so that the development of coal enterprises is seriously hindered, and an advanced intelligent technical skill talent post matching prediction method and system are urgently required to be developed.
At present, the traditional recruitment and post allocation lacks effective prediction standards and theoretical supports, and particularly lacks corresponding evaluation indexes and evaluation models in the aspect of post matching of technical skill personnel of coal enterprises, so that further research is needed. In the aspect of establishing an evaluation index system, most of the industrial characteristics of coal enterprises and the actual requirements of the green intelligent transformation development at the present stage are not considered, and the weight factors among index points are designed by virtue of subjective experience. In the aspect of the algorithm of model construction, although the BP neural network has good effect on the human post matching research of enterprises, the traditional neural network is easy to fall into local optimum, the network topology structure needs to be repeatedly tested and determined by experiments, the 'dimension disaster' is easy to fall into during multiple inputs, and the number of neurons of an implicit layer, the weight and the threshold value need to be optimally determined. Therefore, how to provide a coal enterprise technical skill person sentry matching prediction method and system, which effectively solve the problems, is a technical problem which needs to be solved in the modern green intelligent transformation development process of coal.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a coal enterprise technical skill person post matching prediction method and system.
In order to achieve the above target area, the present invention provides the following solutions:
a coal enterprise technical skill person sentry matching prediction method comprises the following steps:
establishing a technical skill employee competence evaluation index of a coal enterprise; the technical skill staff competence evaluation index comprises a plurality of first-level index points; each first-level index point comprises a plurality of corresponding second-level index points;
quantifying the technical skill employee competence evaluation index of each target employee to obtain a quantified sample;
clustering all quantized samples by taking a secondary index point under each primary index point as a characteristic dimension to obtain a corresponding sample classification result under each primary index;
clustering the sample classification results again by taking the first-level index points as feature dimensions to obtain final clustering analysis classification results;
taking the secondary index points of each target employee as input variables of an SVR regression model, taking a clustering analysis classification result as output variables, and training the SVR regression model to obtain a coal enterprise sentry matching prediction model;
and (5) completing the person post matching of the target staff by using the person post matching prediction model of the coal enterprise.
Preferably, the first-level index point includes: technical quality, competence quality and thought quality; the secondary index points corresponding to the technical quality comprise: expert knowledge, information technology knowledge and operating skills; the secondary index points corresponding to the competence comprise: emergency processing capability, physical fitness, predictive capability, problem solving capability, learning capability, innovation capability, cross-border integration capability, organization coordination capability, autonomous decision making capability, and data mining capability; the secondary index points corresponding to the thought quality comprise: responsibility awareness, safety awareness and business spirit.
Preferably, the step of quantifying physical fitness of the target employee to obtain a physical fitness quantified sample includes:
acquiring body type data of target staff in a coal enterprise; the body type data includes a whole body photograph, height and weight of the employee;
sequentially carrying out gray level processing and smoothing processing on the whole body illumination of the staff to generate smoothed whole body illumination;
dividing the smoothed whole body illumination to obtain body illumination;
taking the body type of staff and the corresponding height and weight of staff as training samples, inputting the training samples into a neural network model for training to obtain a physical quality calculation model;
and calculating the physical quality of the target staff by using the physical quality calculation model to obtain a physical quality quantification sample of the corresponding staff.
Preferably, gray processing and smoothing processing are sequentially performed on the whole body illumination of the staff to generate a smoothed whole body illumination, including:
gray scale processing is carried out on the whole body illumination of staff to obtain a gray scale image of the corresponding whole body illumination;
carrying out smoothing treatment on the gray level map of the whole body illumination by using a gray level smoothing model to generate a smoothed whole body illumination; the gray level smoothing model is as follows:
where p (x, y) represents the smoothed whole-body illumination, q (x, y) represents the gray value at the (x, y) position on the gray map of the whole-body illumination, and α represents the adjustable parameter.
Preferably, the dividing the smoothed whole body illumination to obtain body type illumination includes:
dividing the smoothed whole body illumination into two groups by adopting a preset gray value;
calculating average gray values in the two groups of images to obtain a first group of average gray values and a second group of average gray values;
continuously adjusting the preset gray values to enable the difference value between the first group of average gray values and the second group of average gray values to be maximum; the difference calculation formula of the first group of average gray values and the second group of average gray values is as follows:
wherein d (k) represents a difference value, P 1 Representing the number of pixels on the first group of images, N representing the total number of pixels of the smoothed whole body illumination, and P 2 Represents the number of pixels, mu, on the second group of images 1 Represents a first set of average gray values, mu 2 Representing a second set of average gray values, μ representing the gray average of the smoothed whole body illumination;
and taking the corresponding gray value with the maximum average gray value difference value as a segmentation value, and segmenting the smoothed whole body illumination by using the segmentation value to obtain a body illumination and a background area gray image.
Preferably, clustering all quantized samples by taking a secondary index point under each primary index point as a feature dimension to obtain a sample classification result corresponding to each primary index, including:
constructing a clustering objective function, and carrying out iterative solution on the clustering objective function to obtain a sample classification result corresponding to each level of index; wherein, the clustering objective function is:
wherein d ij The Euclidean distance between the ith sample and the jth class center point is n is the number of samples, c is the number of cluster centers, b t Mu, as weighted index ij The membership degree between the ith sample and the jth class center point.
The invention also provides a coal enterprise technical skill person post matching prediction system, which comprises:
the evaluation index construction module is used for establishing a technical skill staff competence evaluation index of the coal enterprise; the technical skill staff competence evaluation index comprises a plurality of first-level index points; each first-level index point comprises a plurality of corresponding second-level index points;
the index quantization module is used for quantizing the technical skill employee competence evaluation index of each target employee to obtain quantized samples;
the first clustering module is used for clustering all quantized samples by taking the secondary index point under each primary index point as a characteristic dimension to obtain a corresponding sample classification result under each primary index;
the second clustering module is used for clustering the sample classification results again by taking the first-level index points as feature dimensions to obtain final clustering analysis classification results;
the training module is used for taking the secondary index points of each target employee as input variables of the SVR regression model, taking the clustering analysis classification result as output variables, and training the SVR regression model to obtain a coal enterprise sentry matching prediction model;
and the person post matching module is used for completing person post matching of the target staff by using the person post matching prediction model of the coal enterprise.
The invention also provides a computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps in the coal enterprise technical skill person post matching prediction method.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
compared with the prior art, the invention classifies the samples by adopting cluster analysis to obtain the class attribution category of each sample, namely the classification result, and avoids the problem of consideration of multi-index point weight setting when each sample is classified. In addition, the support vector machine algorithm adopted by the invention maps the variables to a high-dimensional space and constructs a linear classification function, so that the model has stronger generalization capability, and simultaneously, the occurrence of dimension disasters is well avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a coal enterprise technical skill person post matching prediction method provided by the invention;
FIG. 2 is a schematic diagram of a coal enterprise technical skill person post matching prediction system provided by the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims of this application and in the drawings, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, inclusion of a list of steps, processes, methods, etc. is not limited to the listed steps but may alternatively include steps not listed or may alternatively include other steps inherent to such processes, methods, products, or apparatus.
In order that the manner in which the above recited objects, features and advantages of the present invention are obtained will become more readily apparent, a more particular description of the invention briefly described above will be rendered by reference to the appended drawings and appended drawings.
Referring to fig. 1, a coal enterprise technical skill person sentry matching prediction method includes:
step 1: establishing a technical skill employee competence evaluation index of a coal enterprise; the technical skill staff competence evaluation index comprises a plurality of first-level index points; each first-level index point comprises a plurality of corresponding second-level index points;
according to the invention, a set of brand-new technical skill staff competence evaluation index system is established according to the self industry characteristics of coal enterprises and the actual requirements of the green intelligent transformation development of the coal enterprises at the current stage, and the first-level evaluation index point is formulated as 3 items based on post competence consideration: technical quality, competence quality and thought quality. The technological quality establishment secondary index point 3 items are as follows: expertise, information technology, and operating skills. The capability quality establishment secondary index point 10 items are as follows: emergency processing capability, physical fitness, predictive capability, problem solving capability, learning capability, innovation capability, cross-border integration capability, organization coordination capability, autonomous decision making capability, and data mining capability. The thought quality establishment secondary index point 3 items are as follows: responsibility awareness, safety awareness and business spirit. The coal enterprise employee evaluation index system established by the invention comprises 3 primary index points and 16 secondary index points, and the competence quality of the technical skill post requirements of the coal enterprise is covered.
Step 2: quantifying the technical skill employee competence evaluation index of each target employee to obtain a quantified sample;
furthermore, employee information data in the coal enterprises are used as basic sample data, and the data are screened according to the principles of diversity, representativeness and uniformity of sample selection, so that data samples meeting the requirements are obtained. Quantifying evaluation index points of each sample in a back-to-back scoring mode of employing experts according to the competence evaluation index of the technical skill staff established in the step 1, wherein the formulated scoring rule is as follows: full score 100 points, five grades, score in [0,60 ] interval set as failed, score in [60, 70) interval set as failed, score in [70, 80) interval set as medium, score in [80, 90) interval set as good, score in [90,100] interval set as excellent.
In the invention, the physical quality of the target staff is quantified to obtain a physical quality quantification sample by a machine learning mode, and the specific process comprises the following steps:
acquiring body type data of target staff in a coal enterprise; the body type data includes a whole body photograph, height and weight of the employee;
sequentially carrying out gray level processing and smoothing processing on the whole body illumination of the staff to generate smoothed whole body illumination;
further, the invention completes the smoothing process of the whole body illumination through the following steps:
gray scale processing is carried out on the whole body illumination of staff to obtain a gray scale image of the corresponding whole body illumination;
carrying out smoothing treatment on the gray level map of the whole body illumination by using a gray level smoothing model to generate a smoothed whole body illumination; the gray level smoothing model is as follows:
where p (x, y) represents the smoothed whole-body illumination, q (x, y) represents the gray value at the (x, y) position on the gray map of the whole-body illumination, and α represents the adjustable parameter.
According to the invention, the image is subjected to smoothing denoising treatment by using the gray level smoothing model, so that the image is clearer under the condition of retaining the original information of the image as much as possible, and the training of a subsequent neural network is facilitated.
Dividing the smoothed whole body illumination to obtain body illumination;
the step of dividing the smoothed whole body illumination is as follows:
dividing the smoothed whole body illumination into two groups by adopting a preset gray value;
calculating average gray values in the two groups of images to obtain a first group of average gray values and a second group of average gray values;
continuously adjusting the preset gray values to enable the difference value between the first group of average gray values and the second group of average gray values to be maximum; the difference calculation formula of the first group of average gray values and the second group of average gray values is as follows:
wherein d (k) represents a difference value, P 1 Representing the number of pixels on the first group of images, N representing the total number of pixels of the smoothed whole body illumination, and P 2 Represents the number of pixels, mu, on the second group of images 1 Represents a first set of average gray values, mu 2 Representing a second set of average gray values, μ representing the gray average of the smoothed whole body illumination;
and taking the corresponding gray value with the maximum average gray value difference value as a segmentation value, and segmenting the smoothed whole body illumination by using the segmentation value to obtain a body illumination and a background area gray image.
The invention divides the image based on the thought of the histogram, can obtain the optimal gray value division value on the whole according to the probability of the gray value distribution of the image, and can separate the background region gray image and noise together by dividing the image by using the gray value division value, thereby not only improving the definition of the image, but also accelerating the convergence of the neural network.
Taking the body type of staff and the corresponding height and weight of staff as training samples, inputting the training samples into a neural network model for training to obtain a physical quality calculation model;
and calculating the physical quality of the target staff by using the physical quality calculation model to obtain a physical quality quantification sample of the corresponding staff.
Step 3: clustering all quantized samples by taking a secondary index point under each primary index point as a characteristic dimension to obtain a corresponding sample classification result under each primary index;
step 4: clustering the sample classification results again by taking the first-level index points as feature dimensions to obtain final clustering analysis classification results;
it should be noted that, the invention adopts the fuzzy C-means clustering algorithm to carry out multi-layer multi-dimension clustering analysis on the quantized samples, and the specific process is as follows:
and clustering all samples by taking the secondary index point under each primary index point as a characteristic dimension to obtain a sample classification result corresponding to each primary index, wherein the clustering result is used as an inner layer clustering result, namely a clustering intermediate result. And then clustering all samples again by taking the first-level index points as characteristic dimensions, wherein the clustering result is used as a final classification result of cluster analysis, so that the class attribution category of each sample, namely the classification result, is obtained.
Firstly, selecting a data sample taking a corresponding secondary index point under each primary index point as a characteristic parameter, and then classifying the data sample by using a fuzzy C-means clustering algorithm, wherein the algorithm comprises the following calculation processes:
let the number n of samples x= { X 1 ，x 2 ，…，x i ，…，x n } T Dividing into c classes, and clustering the centers V= { V of all the classes 1 ，v 2 ，…，v j ，…，v c }, v is j Is the j-th class center point. Similarity classification matrix u= { μ ij I j=1, 2, …, n, i=1, 2, …, c }, where μ ij For sample point x i For the center point v j The membership degree of the random sample points to all the clustering centers is added to be equal to 1, and the membership degree of the random sample points to be added to be equal to 1.
Algorithm objective function:
wherein d ij Euclidean distance between the ith sample and the jth class center point; b t The weighted index, also called ambiguity parameter, is greater than or equal to 1.
Euclidean distance:
d ij ＝||x i -v j ||，i＝1，2，…，n，j＝1，2，…，c (2)
the clustering problem is essentially a constrained optimization problem with respect to the independent variables (U, V), and an iterative formula of clustering centers and membership degrees is deduced according to the Coulomb-Tak condition (Kuhn-Tucker conditions) of extreme points:
the calculation process of the fuzzy C-means clustering algorithm is an iterative process, and the flow of the algorithm is shown as follows. In batch mode, the cluster center V and the similarity classification matrix U are determined according to the following steps:
(1) the iteration end threshold is set to be 1e-6, and the maximum iteration number T max Set to 30, cluster number c set to 10, power exponent b t Set to 3 and the number of initialization iterations h set to 0. The clustering center V is initialized, c points may be randomly taken from all sample points, or c points may be randomly generated between the minimum value and the maximum value of the samples.
(2) First, a membership matrix U is calculated according to formula (4) (h+1) Then, the clustering center V is calculated according to the formula (3) (h+1) Let h=h+1.
(3) If V is (h+1) -V (h) ||<Epsilon, or the number of iterations h>T max And when the iterative process is finished, storing the classification result. Otherwise, returning to the step (2), and then performing the next iteration.
And calculating a corresponding sample classification result under each level of index by using the fuzzy C-means clustering algorithm.
And calculating a sample classification result taking one type of index points as a characteristic dimension by using the fuzzy C-means clustering algorithm, namely a final sample classification result.
The clustering method adopts the steps of dividing the layers of the primary index points and the secondary index points of the data sample, and simultaneously the formulated primary index points and secondary index points both comprise multiple dimensions, so that a multi-layer and multi-dimensional clustering calculation idea is designed, and the problems of 'quantitative change' and 'qualitative change' caused by 'dimension disasters' can be effectively reduced.
Step 5: taking the secondary index points of each target employee as input variables of an SVR regression model, taking a clustering analysis classification result as output variables, and training the SVR regression model to obtain a coal enterprise sentry matching prediction model;
a Support Vector Machine (SVM) belongs to a supervised learning method, is widely applied to statistical classification and regression analysis, and is used for mapping an input variable into a high-dimensional space by means of a kernel function and solving an optimal classification surface to obtain a mapping relation between the input variable and an output variable. The problem belongs to the convex quadratic optimization problem, the regression fitting problem can be solved, and a support vector machine (SVR) capable of solving the regression problem is obtained by introducing an epsilon insensitive loss function. SVM classification is a plane that seeks one classification such that the support vectors or all data of two classification sets are furthest from the plane, and SVR regression is a plane that seeks one regression such that all data in a set is closest to the plane. SVR is an important branch of the application of SVM.
The algorithm for SVR is as follows:
(1) given training set t= { (x) 1 ,y 1 ),…,(x n ,y n )}∈(R×y) n Wherein x is i ∈R n ,y i E y=r, i=1, …, n; the x is i A vector composed of features of the ith sample data, y i And (5) the class attribution category corresponding to the ith sample data is the clustering result.
(2) Selecting a proper kernel function K (x, x') and proper precision epsilon > 0 and penalty parameter C > 0;
(3) constructing and solving convex quadratic programming problem
Obtaining solution
(4) Calculation ofSelecting +.>Component (S)>Or->
If chosen isThen:
if chosen isThen:
(5) constructing a decision function
The invention selects SVR algorithm, takes 16 index points of secondary index as the index pointsAnd taking the classification result of the multi-layer multi-dimensional cluster analysis as an output variable according to the input variable of the SVR regression model. In view of the large impact of the type of kernel and model parameters on model training, it is desirable to consider the best type of kernel and the best combination of parameters when selecting both. The invention adopts a default RBF kernel function, adopts cross validation to search the optimal parameters (punishment factor c and kernel function variance g), and utilizes the optimal parameters to train a model. After model training is finished, the simulation test of the SVR regression model is completed by utilizing the function svmpredirect in the libwvm software package, so that the corresponding predicted value, the mean square error E of the test set and the decision coefficient R are obtained 2 . Finally, use E and R 2 And evaluating the performance of the regression model, and if the performance does not meet the requirements, modifying the kernel function type and the model parameters to meet the requirements.
Step 6: and (5) completing the person post matching of the target staff by using the person post matching prediction model of the coal enterprise.
In practical application, the SVR regression model, namely the coal enterprise post matching prediction model, is used for carrying out post matching prediction on the coal company during personnel recruitment and post configuration, so that the post matching result is obtained by utilizing the intelligent algorithm model.
Referring to fig. 2, the invention further provides a coal enterprise technical skill person post matching prediction system, which comprises:
the evaluation index construction module is used for establishing a technical skill staff competence evaluation index of the coal enterprise; the technical skill staff competence evaluation index comprises a plurality of first-level index points; each first-level index point comprises a plurality of corresponding second-level index points;
the index quantization module is used for quantizing the technical skill employee competence evaluation index of each target employee to obtain quantized samples;
the first clustering module is used for clustering all quantized samples by taking the secondary index point under each primary index point as a characteristic dimension to obtain a corresponding sample classification result under each primary index;
the second clustering module is used for clustering the sample classification results again by taking the first-level index points as feature dimensions to obtain final clustering analysis classification results;
the training module is used for taking the secondary index points of each target employee as input variables of the SVR regression model, taking the clustering analysis classification result as output variables, and training the SVR regression model to obtain a coal enterprise sentry matching prediction model;
and the person post matching module is used for completing person post matching of the target staff by using the person post matching prediction model of the coal enterprise.
Compared with the prior art, the beneficial effects of the coal enterprise technical skill person post matching prediction system provided by the invention are the same as those of the coal enterprise technical skill person post matching prediction method described in the technical scheme, and the details are omitted herein.
The invention also provides a computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps in the coal enterprise technical skill person post matching prediction method.
Compared with the prior art, the beneficial effects of the computer readable storage medium provided by the invention are the same as those of the coal enterprise technical skill person post matching prediction method described in the technical scheme, and the detailed description is omitted.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the method disclosed in the embodiment, since it corresponds to the device disclosed in the embodiment, the description is relatively simple, and the relevant points are referred to the device part description.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (8)
1. A coal enterprise technical skill person sentry matching prediction method is characterized by comprising the following steps:
establishing a technical skill employee competence evaluation index of a coal enterprise; the technical skill staff competence evaluation index comprises a plurality of first-level index points; each first-level index point comprises a plurality of corresponding second-level index points;
quantifying the technical skill employee competence evaluation index of each target employee to obtain a quantified sample;
clustering all quantized samples by taking a secondary index point under each primary index point as a characteristic dimension to obtain a corresponding sample classification result under each primary index;
clustering the sample classification results again by taking the first-level index points as feature dimensions to obtain final clustering analysis classification results;
taking the secondary index points of each target employee as input variables of an SVR regression model, taking a clustering analysis classification result as output variables, and training the SVR regression model to obtain a coal enterprise sentry matching prediction model;
and (5) completing the person post matching of the target staff by using the person post matching prediction model of the coal enterprise.
2. The coal enterprise technical skill person post matching prediction method according to claim 1, wherein the method comprises the following steps: the first-level index point comprises: technical quality, competence quality and thought quality; the secondary index points corresponding to the technical quality comprise: expert knowledge, information technology knowledge and operating skills; the secondary index points corresponding to the competence comprise: emergency processing capability, physical fitness, predictive capability, problem solving capability, learning capability, innovation capability, cross-border integration capability, organization coordination capability, autonomous decision making capability, and data mining capability; the secondary index points corresponding to the thought quality comprise: responsibility awareness, safety awareness and business spirit.
3. The coal enterprise technical skill person post matching prediction method according to claim 2, wherein the method is characterized in that: quantifying the physical fitness of the target employee to obtain a physical fitness quantified sample, including:
acquiring body type data of target staff in a coal enterprise; the body type data includes a whole body photograph, height and weight of the employee;
sequentially carrying out gray level processing and smoothing processing on the whole body illumination of the staff to generate smoothed whole body illumination;
dividing the smoothed whole body illumination to obtain body illumination;
taking the body type of staff and the corresponding height and weight of staff as training samples, inputting the training samples into a neural network model for training to obtain a physical quality calculation model;
and calculating the physical quality of the target staff by using the physical quality calculation model to obtain a physical quality quantification sample of the corresponding staff.
4. The coal enterprise technical skill person post matching prediction method according to claim 3, wherein the method comprises the following steps: sequentially performing gray level processing and smoothing processing on the whole body illumination of the staff to generate smoothed whole body illumination, wherein the method comprises the following steps:
gray scale processing is carried out on the whole body illumination of staff to obtain a gray scale image of the corresponding whole body illumination;
carrying out smoothing treatment on the gray level map of the whole body illumination by using a gray level smoothing model to generate a smoothed whole body illumination; the gray level smoothing model is as follows:
where p (x, y) represents the smoothed whole-body illumination, q (x, y) represents the gray value at the (x, y) position on the gray map of the whole-body illumination, and α represents the adjustable parameter.
5. The coal enterprise technical skill person post matching prediction method according to claim 4, wherein the method comprises the following steps: dividing the smoothed whole body illumination to obtain body type illumination, including:
dividing the smoothed whole body illumination into two groups by adopting a preset gray value;
calculating average gray values in the two groups of images to obtain a first group of average gray values and a second group of average gray values;
continuously adjusting the preset gray values to enable the difference value between the first group of average gray values and the second group of average gray values to be maximum; the difference calculation formula of the first group of average gray values and the second group of average gray values is as follows:
wherein d (k) represents a difference value, P 1 Representing the number of pixels on the first group of images, N representing the total number of pixels of the smoothed whole body illumination, and P 2 Represents the number of pixels, mu, on the second group of images 1 Represents a first set of average gray values, mu 2 Representing a second set of average gray values, μ representing the gray average of the smoothed whole body illumination;
and taking the corresponding gray value with the maximum average gray value difference value as a segmentation value, and segmenting the smoothed whole body illumination by using the segmentation value to obtain a body illumination and a background area gray image.
6. The coal enterprise technical skill person post matching prediction method according to claim 3, wherein the method comprises the following steps: clustering all quantized samples by taking a secondary index point under each primary index point as a characteristic dimension to obtain a sample classification result corresponding to each primary index, wherein the method comprises the following steps:
constructing a clustering objective function, and carrying out iterative solution on the clustering objective function to obtain a sample classification result corresponding to each level of index; wherein, the clustering objective function is:
wherein d ij The Euclidean distance between the ith sample and the jth class center point is n is the number of samples, c is the number of cluster centers, b t Mu, as weighted index ij The membership degree between the ith sample and the jth class center point.
7. The utility model provides a coal enterprise technical skill person sentry matching prediction system which characterized in that includes:
the evaluation index construction module is used for establishing a technical skill staff competence evaluation index of the coal enterprise; the technical skill staff competence evaluation index comprises a plurality of first-level index points; each first-level index point comprises a plurality of corresponding second-level index points;
the index quantization module is used for quantizing the technical skill employee competence evaluation index of each target employee to obtain quantized samples;
the first clustering module is used for clustering all quantized samples by taking the secondary index point under each primary index point as a characteristic dimension to obtain a corresponding sample classification result under each primary index;
the second clustering module is used for clustering the sample classification results again by taking the first-level index points as feature dimensions to obtain final clustering analysis classification results;
the training module is used for taking the secondary index points of each target employee as input variables of the SVR regression model, taking the clustering analysis classification result as output variables, and training the SVR regression model to obtain a coal enterprise sentry matching prediction model;
and the person post matching module is used for completing person post matching of the target staff by using the person post matching prediction model of the coal enterprise.
8. A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of a coal enterprise skill man on post matching prediction method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310428380.8A CN116485021A (en) | 2023-04-20 | 2023-04-20 | Coal enterprise technical skill person sentry matching prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310428380.8A CN116485021A (en) | 2023-04-20 | 2023-04-20 | Coal enterprise technical skill person sentry matching prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116485021A true CN116485021A (en) | 2023-07-25 |
Family
ID=87213239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310428380.8A Pending CN116485021A (en) | 2023-04-20 | 2023-04-20 | Coal enterprise technical skill person sentry matching prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485021A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117496431A (en) * | 2023-11-03 | 2024-02-02 | 广州准捷电子科技有限公司 | Outdoor operation safety monitoring method based on indoor and outdoor positioning system |
-
2023
- 2023-04-20 CN CN202310428380.8A patent/CN116485021A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117496431A (en) * | 2023-11-03 | 2024-02-02 | 广州准捷电子科技有限公司 | Outdoor operation safety monitoring method based on indoor and outdoor positioning system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107392919B (en) | Adaptive genetic algorithm-based gray threshold acquisition method and image segmentation method | |
| CN108805193B (en) | Electric power missing data filling method based on hybrid strategy | |
| CN110827260B (en) | Cloth defect classification method based on LBP characteristics and convolutional neural network | |
| CN112685504B (en) | Production process-oriented distributed migration chart learning method | |
| CN111160750A (en) | Distribution network analysis and investment decision method based on association rule mining | |
| CN113537728A (en) | Intelligent recommendation system and recommendation method based on business recruitment in industrial park | |
| CN110009030A (en) | Sewage treatment method for diagnosing faults based on stacking meta learning strategy | |
| CN106971197A (en) | The Subspace clustering method of multi-view data based on otherness and consistency constraint | |
| CN113642486A (en) | Unmanned aerial vehicle distribution network inspection method with airborne front-end identification model | |
| CN116485021A (en) | Coal enterprise technical skill person sentry matching prediction method and system | |
| CN113822499A (en) | Train spare part loss prediction method based on model fusion | |
| CN110968651A (en) | Data processing method and system based on grey fuzzy clustering | |
| Tiruneh et al. | Feature selection for construction organizational competencies impacting performance | |
| CN113935413A (en) | Distribution network wave recording file waveform identification method based on convolutional neural network | |
| CN113591947A (en) | Power data clustering method and device based on power consumption behaviors and storage medium | |
| CN113792984B (en) | Cloud model-based anti-air defense anti-pilot command control model capability assessment method | |
| CN112465253B (en) | Method and device for predicting links in urban road network | |
| CN115423091A (en) | Conditional antagonistic neural network training method, scene generation method and system | |
| CN114444654A (en) | NAS-oriented training-free neural network performance evaluation method, device and equipment | |
| CN113283604A (en) | Multi-element situation self-adaptive reasoning method and application | |
| WO1992017853A2 (en) | Direct data base analysis, forecasting and diagnosis method | |
| CN112633622B (en) | Smart power grid operation index screening method | |
| CN114281994B (en) | Text clustering integration method and system based on three-layer weighting model | |
| Pan | Study of Methods for Constructing Intelligent Learning Models Supported by Artificial Intelligence | |
| Aggarwal et al. | Heuristics-based modelling of human decision process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |