CN112365155A - Staff skill level multi-dimensional evaluation method - Google Patents

Staff skill level multi-dimensional evaluation method Download PDF

Info

Publication number
CN112365155A
CN112365155A CN202011250179.8A CN202011250179A CN112365155A CN 112365155 A CN112365155 A CN 112365155A CN 202011250179 A CN202011250179 A CN 202011250179A CN 112365155 A CN112365155 A CN 112365155A
Authority
CN
China
Prior art keywords
skill level
layer
staff
evaluation
index
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
Application number
CN202011250179.8A
Other languages
Chinese (zh)
Inventor
李瑶
张正林
李睿
胡松洁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guizhou Power Grid Co Ltd
Original Assignee
Guizhou Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guizhou Power Grid Co Ltd filed Critical Guizhou Power Grid Co Ltd
Priority to CN202011250179.8A priority Critical patent/CN112365155A/en
Publication of CN112365155A publication Critical patent/CN112365155A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q10/06—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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06Q10/06398—Performance of employee with respect to a job function

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Automation & Control Theory (AREA)
  • Computational Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)

Abstract

The invention discloses a staff skill level multi-dimensional evaluation method which comprises the steps of obtaining the skill level information of staff through a server and constructing seven dimensional level index sets; constructing a hierarchical structure model based on a hierarchical analysis strategy, and determining the index weight of the index set by using the model; constructing a staff skill level evaluation model according to the index weight and based on a neural network; iteratively training the evaluation model by using an error energy function, obtaining training precision, and outputting a skill level evaluation value until a precision threshold value is met to finish evaluation; the invention can comprehensively evaluate the skill staff of the power system in a multidimensional way, reflects the advantages and the middle differences of the skill staff from different dimensions and overall results, clearly shows the advantages and the disadvantages of the staff and the skill level, and simultaneously improves the evaluation accuracy by introducing machine learning.

Description

Staff skill level multi-dimensional evaluation method
Technical Field
The invention relates to the technical field of computer evaluation and machine learning, in particular to a multi-dimensional evaluation method for the skill level of an employee.
Background
At present, the skill level of staff in each professional field of an electric power system in work generally has the conditions of 'high scholarship, low quality' or 'high title, low capability' and the like which are not matched with post capability, so that real skilled talents are difficult to find, the service level of the staff can be evaluated only through the scholarship and the seniority in the prior art, and the accuracy is poor by adopting the method.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides a multi-dimensional assessment method for the skill level of employees, which solves the problem that the existing positions and the capabilities of the employees in the professional fields of the following power supply bureau are not matched in work.
In order to solve the technical problems, the invention provides the following technical scheme: acquiring skill level information of employees through a server, and constructing seven dimensional level index sets; constructing a hierarchical structure model based on a hierarchical analysis strategy, and determining the index weight of the index set by using the model; constructing a staff skill level evaluation model according to the index weight and based on a neural network; and (4) iteratively training the evaluation model by using an error energy function, obtaining training precision, outputting a skill level evaluation value until the precision requirement is met, and finishing evaluation.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the set of metrics may include, for example,
Pi＝{P1，P2，P3，P4，P5，P6，P7}
wherein i is the number of dimensional layers, P1For the professional competence dimension, P2For the safety dimension, P3Is a general capability dimension, P4To be innovative capability dimension, P5To qualify the horizontal dimension, P6To complement the status dimension, P7Is a violation dimension.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the building of the hierarchical structure model comprises the following steps:
Figure BDA0002771341490000021
wherein mu is an evaluation score, n is a sub-dimension value, i is a dimension value, K is a maximum characteristic value, and u is a value obtained by normalizing the score of a certain dimension; an index layer: evaluating dimensionality; object layer: and (5) evaluating the object.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the index weight includes a weight of the index,
Figure BDA0002771341490000022
wherein,
Figure BDA0002771341490000023
is the index weight, m is the index element, kiiIs a decision matrix.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the staff skill level evaluation model comprises an input layer: scoring all dimension indexes of the employee; a paste layer:
Figure BDA0002771341490000024
wherein, txFor inputting index data, cxyBeing the centre of the membership function, ωxyIs the width of the membership function; and (3) an inference layer:
Figure BDA0002771341490000025
an output layer:
Figure BDA0002771341490000026
Figure BDA0002771341490000027
as a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the fuzzy layer further comprises setting a parameter of a fuzzy node of the fuzzy layer to zero.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: further comprising weight modification of the input layer to the blur layer,
Δβ＝ηφx
wherein Δ β is a weight coefficient correction value from the input layer to the blur layer, η is a learning rate, φxIs a hidden layer neuron threshold.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the error energy function comprises defining the error energy function based on an error back propagation strategy:
Figure BDA0002771341490000028
wherein o is the actual output value and q is the expected output value.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the iterative training comprises separately aligning the parameters c according toxy、
Figure BDA0002771341490000031
ωxyCarrying out iterative adjustment:
Figure BDA0002771341490000032
Figure BDA0002771341490000033
Figure BDA0002771341490000034
wherein γ is a learning rate of the model, z is an iteration number, and x and y represent the number of levels and the number of nodes in the levels respectively.
As a preferable scheme of the staff skill level multidimensional evaluation method, the staff skill level multidimensional evaluation method comprises the following steps: the accuracy requirement includes setting the training accuracy threshold to 98%.
The invention has the beneficial effects that: the comprehensive evaluation method has the advantages that the comprehensive evaluation can be performed on the skill staff of the power system in a multidimensional mode, all aspects of the staff on the skill posts of all power enterprises are covered in the evaluation, the staff capability embodying and comprehensive capability sequencing is realized in a digital mode through the quantification of evaluation results, the excellence and the weakness of the skill staff are embodied from different dimensions and overall results, the excellence and weakness of the staff and the skill level are clearly and clearly shown, and meanwhile, the evaluation accuracy is improved through the introduction of machine learning.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flowchart of a staff skill level multidimensional assessment method according to a first embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a part of staff multidimensional evaluation results of a staff skill level multidimensional evaluation method according to a first embodiment of the present invention;
fig. 3 is a schematic diagram illustrating the personal analysis results of a part of employees in the employee skill level multidimensional assessment method according to the first embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" 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.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a method for multidimensional assessment of employee skill levels, including:
s1: the skill level information of the staff is obtained through the server, and seven dimensional level index sets are constructed.
The detailed data of the technical personnel of the transformer operation major and the distribution network comprehensive major are collected through the server, and the data comprise the work achievement, the actual operation skill, the training participation degree, the qualification of an internal trainer, the information of a major post, the skill identification, the technical title, the thesis publishing condition, the courseware development, the news report, the safety capability, the regulation, the standard compilation condition, the QC achievement, the patent, the technical improvement contribution, the scientific and technological achievement and the field violation condition of the staff.
Index set based on seven dimensional levels of the above data:
Pi＝{P1，P2，P3，P4，P5，P6，P7}
wherein i is the number of dimensional layers, P1For the professional competence dimension, P2For the safety dimension, P3Is a general capability dimension, P4To be innovative capability dimension, P5To qualify the horizontal dimension, P6To complement the status dimension, P7Is a violation dimension.
In particular, P1Security for on-site electric operation ticketTechnical draft, work ticket transaction quantity, substation patrol work, acceptance work, equipment owner making, two ticket examination, star-level substation, defect discovery rate, three members, typical operation ticket repair and editing and skill competition };
P2the method comprises the following steps of (1) setting safety achievement, rationalization suggestion, auditor qualification of an ampere wind system, safety zone representative, accident incident investigator, first-aid officer and superior activity participation };
P3the method comprises the following steps of (1) establishing a transformer substation operation position level, a transformer substation professional regulation, standard establishment, a transformer substation operation professional skill identification level, a technical job title level and a position competence evaluation certificate };
P4the technical innovation of the power transformation major, the lean management project of the power transformation major, the patent of the power transformation major, the technical improvement contribution of the power transformation major, the scientific and technological achievements of the power transformation major, and the situation published in the recent 3 years);
P5the method comprises the following steps of (1) training participation degree in power transformation professional centralized training, on-duty training, quality of trainees in the power transformation professional, courseware development, teaching and high-skill talent cultivation };
P6the results are that (standing work, honor title, operational ability title, safe advanced person, special contribution prize, and the evaluation of the department's straight line manager);
P7the situation of accident event, situation of wind-clear government and administrative department is { situation of scene violation of regulations, situation of accident event, situation of party wind-clear government and administrative department }.
S2: and constructing a hierarchical structure model based on a hierarchical analysis strategy, and determining the index weight of the index set by using the model.
The hierarchical analysis method is an evaluation method combining quantification and qualification, when the composition structure of the evaluation index is complex and is difficult to quantify by other methods, quantification can be performed by the method, and the combined weight of each layer of index can be calculated from top to bottom because the weight of each level of index is the sum of the weights of the sub-levels of index, so that the hierarchical analysis method is suitable for determining the index weight.
Specifically, the hierarchical structure model comprises a target layer, an index layer and an object layer;
a target layer:
Figure BDA0002771341490000061
wherein mu is an evaluation score, n is a sub-dimension value, i is a dimension value, K is a maximum characteristic value, and u is a value obtained by normalizing the score of a certain dimension;
indication layer: evaluating dimensionality;
object layer: and (5) evaluating the object.
The hierarchical structure of the system is divided into seven levels, so that the weight vectors of seven-level indexes are respectively calculated
Figure BDA0002771341490000062
The weight vector of a certain level of indexes consists of specific index weights in the level;
defining the index weight:
Figure BDA0002771341490000063
wherein,
Figure BDA0002771341490000064
is index weight, m is index element, j is the layer number of the hierarchical structure model;
kiito judge the matrix:
Figure BDA0002771341490000065
due to the complexity of indexes and the subjective judgment difference of evaluation objects, the matrix A is difficult to ensure that the condition of a consistency matrix is met, so that the consistency of the matrix needs to be checked, and the rule for judging the consistency of the matrix is as follows:
Figure BDA0002771341490000066
wherein c.i. represents a consistency index.
S3: and constructing an employee skill level evaluation model according to the index weight and based on the neural network.
The staff skill level evaluation model adopts a 4-layer structure: the system comprises an input layer, a fuzzy layer, an inference layer and an output layer.
Specifically, input layer: inputting scores of all dimension indexes of the employee, wherein 47 sub-dimension indexes under 7 first-level dimension indexes are used as input data by the model, and the total score of each sub-dimension index is 10;
pasting a layer: since the gaussian membership function is a bell-shaped curve and has a property of representing rich fuzzy information by using a simple learning rule, the gaussian membership function is used as a function of a fuzzy layer, that is:
Figure BDA0002771341490000071
wherein, txFor inputting index data, cxyBeing the centre of the membership function, ωxyIs the width of the membership function; preferably, the Gaussian function is adjusted by cxy、ωxyThe two parameters can increase the adaptability and are more stable.
Preferably, the parameter of a fuzzy node of the fuzzy layer is set to zero, that is, a fuzzy node of the fuzzy layer is deleted, so that the performance of the model is improved.
③ reasoning layer: the fuzzy rule is divided into 3 levels: the output value vi of the layer represents the excitation density of the rule, and the formula is as follows:
Figure BDA0002771341490000072
output layer: performing defuzzification processing on the data of each ganglion point to obtain a network output value, wherein the formula is as follows:
Figure BDA0002771341490000073
in order to reduce the requirement for the memory cell, the weight from the input layer to the fuzzy layer is modified according to the following formula:
Δβ＝ηφx
wherein, Delta beta is the weight coefficient correction value from the input layer to the fuzzy layer, eta is the learning rate, phixIs a hidden layer neuron threshold.
S4: and (4) iteratively training the evaluation model by using an error energy function, obtaining training precision, and outputting a skill level evaluation value until a precision threshold value is met to finish evaluation.
Defining an error energy function based on an error back propagation algorithm:
Figure BDA0002771341490000074
where o is the actual output value and q is the expected output value.
Further, the parameter c is individually adjusted according to the following formulaxy、
Figure BDA0002771341490000081
ωxyCarrying out iterative adjustment:
Figure BDA0002771341490000082
Figure BDA0002771341490000083
Figure BDA0002771341490000084
wherein, gamma is the learning rate of the model, z is the iteration times, and x and y respectively represent the number of nodes in the hierarchy level and the hierarchy level.
And when the iteration is carried out until the training precision reaches 98%, terminating the iteration training and outputting a training parameter value.
In the sample training process, the neural network enables the network error to be converged to the target error by adjusting parameters, the optimal effect of the network is finally achieved, when a new object needs to be evaluated, only the index factor vector of the predicted object needs to be input, and the output value of the skill capability evaluation of the staff is obtained through network calculation.
Example 2
In order to verify and explain the technical effects adopted in the method, the embodiment respectively selects the traditional employee evaluation method, the traditional BP neural network training method and the comparison test by adopting the method, and compares the test results by means of scientific demonstration to verify the real effect of the method.
The traditional employee evaluation method can only evaluate the business level of an employee through a school calendar and a seniority calendar, and the evaluation accuracy is low; the traditional BP neural network is long in training time, the running time can be several hours or even longer for some special problems, and the traditional BP neural network is easy to fall into a local minimum value.
In order to verify that the method has more accurate evaluation results and multidimensional evaluation modes compared with the traditional staff evaluation method, in this embodiment, the traditional BP neural network training method, the traditional staff evaluation method and the method are respectively adopted to respectively evaluate and compare part of staff of the transformer substation.
The experimental environment was configured as follows:
table 1: and (4) an experimental environment parameter table.
Figure BDA0002771341490000085
The technical index data of about 100 employees are extracted by utilizing an employee information database of a certain transformer substation and corresponding sampling investigation statistics and are imported into a data set F, wherein the F comprises index scores and evaluation output values. The data set is divided into a training set and a testing set according to the proportion of 7:3, each index value of staff is used as input in the data set, an actual comprehensive evaluation value is used as output, the input and output values are led into a training model of the invention, the network learning rate is set to be 0.02, the maximum iteration number is 2000, the minimum error is 0.001 through continuous learning of a neural network algorithm, and sample data is substituted into the following formula for calculation:
Figure BDA0002771341490000091
wherein sim represents the sum of similarity of each layer of the network, a represents the number of samples, and sij、∈ij、εijRespectively representing the euclidean distance between the networks of the layers.
The number of hidden layer nodes is here chosen to be 7, i.e. the network topology is 47-7-1. After network training, 30 untrained samples were randomly selected, subjected to simulation testing using a fuzzy neural network, and compared with the training test results of a conventional BP neural network, and the comparison results are shown in the following table.
Table 2: and comparing the results of the traditional BP neural network and the model trained by the method.
Training method Maximum error Maximum mean error Training time Number of iterations
Conventional BP neural network 8.12％ 11.37％ 1.32 hours 10
Method for producing a composite material 5.72％ 1.16％ 43.7 minutes 3
The above table shows that the model precision of the method is higher than that of the traditional BP neural network, and the method has good robustness.
Part of employees are respectively selected from the state-of-the-broadcast power supply bureau, the wind and okang power supply bureau, the suburb power supply bureau, the copper and zinc power supply bureau and the obedient power supply bureau, and meanwhile, the traditional employee evaluation method and the method are adopted to evaluate and compare the part of employees, and the evaluation results are shown in table 3, fig. 2 and fig. 3.
Table 3: and a result table for evaluation by adopting a traditional employee evaluation method.
Unit of Number of people evaluated Calendar score (50) Seniority score (50) General score (100)
State of China power supply bureau 1 41 39 80
Wind power supply office 1 38 40 78
Copper-zinc power supply station 1 16 25 41
ZUNYI POWER SUPPLY BUREAU 3 36 37 73
Suburb power supply bureau 2 32 26 58
The actual matching rates of the two methods are respectively 75% and 100%, and therefore, the method not only can comprehensively evaluate the skilled staff, but also improves the matching rate of the posts and the capability, lays a solid foundation for establishing a high-quality specialized staff team for a power system, and simultaneously provides data support for optimizing safety production evaluation and promoting the posts of the staff.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.

Claims (10)

1. A staff skill level multi-dimensional evaluation method is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring skill level information of the staff through a server, and constructing seven dimensional level index sets;
constructing a hierarchical structure model based on a hierarchical analysis strategy, and determining the index weight of the index set by using the model;
constructing a staff skill level evaluation model according to the index weight and based on a neural network;
and iteratively training the evaluation model by using an error energy function, obtaining training precision, and outputting a skill level evaluation value until a precision threshold value is met to finish evaluation.
2. The employee skill level multidimensional assessment method of claim 1, characterized by: the set of metrics may include, for example,
Pi＝{P1，P2，P3，P4，P5，P6，P7}
wherein i is the number of dimensional layers, P1For the professional competence dimension, P2For the safety dimension, P3Is a general capability dimension, P4To be innovative capability dimension, P5To qualify the horizontal dimension, P6To complement the status dimension, P7Is a violation dimension.
3. The employee skill level multidimensional assessment method as claimed in claim 2, characterized in that: the building of the hierarchical structure model includes,
target layer:
Figure FDA0002771341480000011
wherein mu is an evaluation score, n is a sub-dimension value, K is a maximum characteristic value, and u is a value obtained by normalizing the score of a certain dimension;
an index layer: evaluating dimensionality;
object layer: and (5) evaluating the object.
4. The employee skill level multidimensional assessment method as claimed in claim 1 or 3, characterized in that: the index weight includes a weight of the index,
Figure FDA0002771341480000012
wherein,
Figure FDA0002771341480000013
is the index weight, m is the index element, kiiIs a decision matrix.
5. The employee skill level multidimensional assessment method as claimed in claim 2 or 3, characterized in that: the employee skill level assessment model includes,
an input layer: scoring all dimension indexes of the employee;
a paste layer:
Figure FDA0002771341480000021
wherein, txFor inputting index data, cxyBeing the centre of the membership function, ωxyIs the width of the membership function;
and (3) an inference layer:
Figure FDA0002771341480000022
an output layer:
Figure FDA0002771341480000023
6. the employee skill level multidimensional assessment method of claim 5, characterized by: the layer of the paste may further include,
setting a parameter of a fuzzy node of the fuzzy layer to zero.
7. The employee skill level multidimensional assessment method of claim 5, characterized by: further comprising weight modification of the input layer to the blur layer,
Δβ＝ηφx
wherein Δ β is a weight coefficient correction value from the input layer to the blur layer, η is a learning rate, φxIs a hidden layer neuron threshold.
8. The employee skill level multidimensional assessment method as claimed in any one of claims 2, 3, 6, 7, characterized in that: the error energy function may include the function of,
defining the error energy function based on an error back propagation strategy:
Figure FDA0002771341480000024
wherein o is the actual output value and q is the expected output value.
9. The employee skill level multidimensional assessment method of claim 8, characterized by: the iterative training includes the steps of,
respectively for said parameter c according toxy、
Figure FDA0002771341480000025
ωxyCarrying out iterative adjustment:
Figure FDA0002771341480000026
Figure FDA0002771341480000027
Figure FDA0002771341480000028
wherein γ is a learning rate of the model, z is an iteration number, and x and y represent the number of levels and the number of nodes in the levels respectively.
10. The employee skill level multidimensional assessment method of claim 1, characterized by: the precision threshold value may comprise a threshold value of,
setting the training precision threshold to 98%.
CN202011250179.8A 2020-11-11 2020-11-11 Staff skill level multi-dimensional evaluation method Pending CN112365155A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011250179.8A CN112365155A (en) 2020-11-11 2020-11-11 Staff skill level multi-dimensional evaluation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011250179.8A CN112365155A (en) 2020-11-11 2020-11-11 Staff skill level multi-dimensional evaluation method

Publications (1)

Publication Number Publication Date
CN112365155A true CN112365155A (en) 2021-02-12

Family

ID=74509679

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011250179.8A Pending CN112365155A (en) 2020-11-11 2020-11-11 Staff skill level multi-dimensional evaluation method

Country Status (1)

Country Link
CN (1) CN112365155A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113128876A (en) * 2021-04-22 2021-07-16 北京房江湖科技有限公司 Image-based object management method, device and computer-readable storage medium
CN113160646A (en) * 2021-04-14 2021-07-23 国家电网有限公司 Wired access network simulation training oriented trainee model construction and updating method
CN113256169A (en) * 2021-06-25 2021-08-13 深圳市爱挖网络科技有限公司 Talent storage and management system for recruitment platform based on Internet
CN115018471A (en) * 2022-07-19 2022-09-06 希望知舟技术(深圳)有限公司 Data processing method and related device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105590175A (en) * 2016-02-15 2016-05-18 云南电网有限责任公司 Skilled talent evaluation method based on factor analysis and BP neural networks
CN107506941A (en) * 2017-09-09 2017-12-22 杭州数立方征信有限公司 A kind of enterprise in charge of construction's credit assessment method and system based on big data technology
CN111639864A (en) * 2020-06-02 2020-09-08 交通运输部天津水运工程科学研究所 Quantitative assessment method for post security competence of port operating personnel

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105590175A (en) * 2016-02-15 2016-05-18 云南电网有限责任公司 Skilled talent evaluation method based on factor analysis and BP neural networks
CN107506941A (en) * 2017-09-09 2017-12-22 杭州数立方征信有限公司 A kind of enterprise in charge of construction's credit assessment method and system based on big data technology
CN111639864A (en) * 2020-06-02 2020-09-08 交通运输部天津水运工程科学研究所 Quantitative assessment method for post security competence of port operating personnel

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张毅等: "基于机器学习的能力评价与匹配研究", 《计算机工程与科学》 *
江卫东: "基于AHP和BP神经网络的企业R&D人员胜任力评价", 《系统工程理论与实践》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113160646A (en) * 2021-04-14 2021-07-23 国家电网有限公司 Wired access network simulation training oriented trainee model construction and updating method
CN113128876A (en) * 2021-04-22 2021-07-16 北京房江湖科技有限公司 Image-based object management method, device and computer-readable storage medium
CN113256169A (en) * 2021-06-25 2021-08-13 深圳市爱挖网络科技有限公司 Talent storage and management system for recruitment platform based on Internet
CN115018471A (en) * 2022-07-19 2022-09-06 希望知舟技术(深圳)有限公司 Data processing method and related device
CN115018471B (en) * 2022-07-19 2022-12-09 希望知舟技术(深圳)有限公司 Data processing method and related device

Similar Documents

Publication Publication Date Title
CN112365155A (en) Staff skill level multi-dimensional evaluation method
CN109461025B (en) Electric energy substitution potential customer prediction method based on machine learning
CN112054943B (en) Traffic prediction method for mobile network base station
CN106845777A (en) Case workload evaluation method, judge's performance evaluation techniques, modeling method, computing device and computer-readable recording medium
CN111861089A (en) Comprehensive evaluation method for electric power spot market
CN106056235A (en) Power transmission grid efficiency and benefit detection method based on Klee method and matter element extension model
CN112101785A (en) Method for analyzing comprehensive benefits of power and communication sharing iron tower
CN116307841A (en) Construction method of college evaluation system integrating multiple indexes
CN113327047B (en) Power marketing service channel decision method and system based on fuzzy comprehensive model
CN114331041A (en) Smart power plant maturity assessment method and system based on information physical system architecture
CN113592445A (en) Talent management system based on big data
Wang et al. The study of enterprise human resource evaluation research based on neural network
CN111160719A (en) Two-network fused multi-index evaluation method
CN114626594A (en) Medium-and-long-term electric quantity prediction method based on cluster analysis and deep learning
CN112464168A (en) Comprehensive energy potential user targeting evaluation and extraction method
Wei et al. Analysis on the Classification and Evaluation System of Talents in Colleges and Universities from the Perspective of AHP
Huang et al. Research on Bidding Evaluation of Engineering Projects Based on Fuzzy Comprehensive Evaluation Method
Qu Research on Optimization of Human-Skilled Matching of SMEs Based on Ant Colony Optimization Algorithm
Wang et al. A multi-index comprehensive evaluation method for key technology development of AC-DC distribution network based on neural network
CN114330979B (en) Evaluation index system for intelligent power plant of coal-fired unit after construction
You et al. Impact Analysis of College Entrance Examination and General Education on Graduation Achievements
Zhang Research on intelligent college student evaluation system based on CBR and AHP
Wang et al. Analysis of Factors Influencing University Performance Based on Feature Selection Optimization Gray Correlation Analysis Model
Zhuo et al. Research on Performance Evaluation of Construction Project Management Based on Genetic Algorithm
Wang et al. Application of gray fuzzy analytic hierarchy process in air traffic safety of tower control

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