CN115660508A - Staff performance assessment and evaluation method based on BP neural network - Google Patents
Staff performance assessment and evaluation method based on BP neural network Download PDFInfo
- Publication number
- CN115660508A CN115660508A CN202211593088.3A CN202211593088A CN115660508A CN 115660508 A CN115660508 A CN 115660508A CN 202211593088 A CN202211593088 A CN 202211593088A CN 115660508 A CN115660508 A CN 115660508A
- Authority
- CN
- China
- Prior art keywords
- assessment
- parameter
- data
- sample
- parameters
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 title claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 20
- 238000013210 evaluation model Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000005065 mining Methods 0.000 claims abstract description 5
- 230000008859 change Effects 0.000 claims description 43
- 238000000034 method Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a staff performance assessment evaluation method based on a BP neural network, which belongs to the technical field of data processing, and can be used for fitting a neural network on historical assessment data to further obtain a corresponding staff performance assessment evaluation model, automatically assessing the subsequent staff performance through the staff performance assessment evaluation model, avoiding the workload of an accountant and improving the efficiency of performance assessment while ensuring the authenticity and the accuracy of the performance assessment data, and mining abnormal data in original data by using original assessment parameter values and assessment results before obtaining the staff performance assessment evaluation model, thereby avoiding the influence of the abnormal assessment results on the establishment of the subsequent model caused by the intention and the non-intention of the assessment staff and improving the efficiency and the accuracy of the establishment of the subsequent model.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a staff performance assessment method based on a BP neural network.
Background
The neural network has the functions of autonomous learning, nonlinear transformation and the like by simulating the working principle of the human brain, can effectively eliminate randomness and subjectivity, and is an innovation for evaluating experimental capacity. The application of the neural network algorithm in the aspects of education and teaching effect evaluation and the like is widely researched at home and abroad.
In the scene of performance assessment of enterprise employees in seasons or years, compared with a common assessment method, the performance assessment method has the following characteristics: the performance assessment method has a plurality of indexes, and relates to a plurality of indexes such as employee behaviors and employee performances and a large amount of data under each index, and the data processing workload is large; the calculation method is complex, the process of forming the final evaluation index by each index is complex, and a large amount of time is needed for processing, comparing and accounting by a human specialist. Therefore, the staff performance assessment model established through the BP neural network can greatly reduce the work of the staff, even simplify the whole work and greatly improve the work efficiency.
The method for automatically performing performance assessment and ensuring the accuracy of the performance assessment is provided in order to solve the problems that a large amount of time is consumed for manually performing the assessment on the performance assessment indexes of the staff, and particularly when the number of people to be assessed is large, the individual level and the intention of the personnel are greatly influenced through manual assessment, and the assessment result is possibly abnormal.
Disclosure of Invention
The invention aims to provide a staff performance assessment and evaluation method based on a BP (back propagation) neural network, which solves the problems that in the prior art, staff performance assessment indexes are mainly manually checked, a large amount of time is consumed, and in addition, the manual checking is greatly influenced by the personal level and intention of a checking staff, so that abnormal checking results can be caused.
The purpose of the invention can be realized by the following technical scheme:
a staff performance assessment and evaluation method based on a BP neural network comprises the following steps:
s1, mining abnormal data in historical assessment data, and removing the abnormal historical assessment data;
s2, taking the historical assessment data of the assessed staff as sample data, and performing data cleaning on the sample data to obtain training sample data;
s3, learning the training sample data through a BP neural network, and establishing an employee performance assessment model;
and testing the trained employee performance assessment evaluation model through the test sample data, and finally outputting an evaluation result.
As a further scheme of the invention, the method for establishing the employee performance assessment evaluation model comprises the following steps:
(1) Dividing the sample data into input sample data and target sample data, and performing normalization processing;
(2) Importing input sample data and target sample data in a neural network fitting algorithm;
(3) After sample data is imported, the number of neurons in an input layer is set, the number of neurons in an output layer is output, the number of neurons in a hidden layer is set according to an empirical formula, and a Levenberg-Marquardt algorithm is selected;
(4) And performing network training to obtain a corresponding employee performance assessment evaluation model.
As a further scheme of the present invention, the method for mining abnormal data in the historical assessment data in step S1 includes the following steps:
s11, obtaining all assessment parameters required by a performance assessment evaluation model, marking one assessment parameter as a target parameter, marking all the other assessment parameters as auxiliary parameters, and taking all assessment parameter values obtained by an assessed employee in one assessment as a sample group;
acquiring all auxiliary parameters in one sample group, which are sequentially marked as C11, C12, … and C1n, and acquiring all auxiliary parameters in another sample group, which are correspondingly sequentially marked as C21, C22, … and C2n, wherein n is the number of the auxiliary parameters;
wherein C1i and C2i represent the same auxiliary parameter; calculating a difference coefficient Cci of the auxiliary parameters C1i and C2i according to a formula | C1i-C2i |/C1i = Cci, wherein i is more than or equal to 1 and is less than or equal to n;
sequentially calculating corresponding difference coefficients of all auxiliary parameters in the two sample groups, and sequentially marking the obtained n difference coefficients as Cc1, cc2, … and Ccn;
when all the difference coefficients are smaller than a preset coefficient alpha, the two sample groups are considered to belong to the same type of sample group aiming at the target parameter;
acquiring a plurality of groups of similar sample groups, sequentially marking corresponding target parameter values as f1, f2, … and fm in a sequence from small to large in one group of similar sample groups, and sequentially marking performance assessment evaluation values corresponding to target parameters as J1, J2, … and Jm;
calculating m-1 reference change rates B according to a formula B = [ fg-f (g-1) ]/[ Jg-J (g-1) ], wherein g is more than or equal to 2 and is less than or equal to m, sequentially calculating a plurality of corresponding reference change rates B in each group of similar samples, and sequentially marking the finally obtained r reference change rates as B1, B2, … and Br;
according to the formula
Calculating to obtain a dispersion value U of the group of data B1 to Br, when U is less than or equal to Uy, considering the corresponding target parameter as a correlation parameter, and taking Bp as the average reference change rate of the corresponding target parameter;
when U is larger than Uy, deleting the corresponding Bx values in turn according to the sequence of | Bx-Bp | from large to small until U is smaller than or equal to Uy, recording the number r1 of the deleted Bx values at the moment, when r1/r is smaller than or equal to beta, considering the corresponding target parameter as a correlation parameter, and taking Bp as the average reference change rate of the corresponding target parameter; when r1/r > beta, marking the corresponding objective function as a random parameter;
wherein x is more than or equal to 1 and less than or equal to r, bp = (B1 + B2+, …, + Br)/r, uy is a preset value, and beta is a preset value;
s12, processing each assessment parameter according to the method in the step S11, and judging whether each assessment parameter is a correlation parameter or a random parameter;
for the assessment parameters which are related parameters, setting one assessment parameter as a target parameter according to the method in the step S11, dividing the sample group of each assessed employee in one performance assessment needing to be checked into a plurality of similar sample groups, and calculating the verification change rate Bz of each target parameter in one similar sample group;
when the difference value between the verification change rate Bz of one target parameter and the corresponding average reference change rate Bp reaches a preset proportion, the corresponding target parameter is considered to be abnormal;
and when a preset number of abnormal target parameters exist in one sample group, the performance assessment evaluation result of the corresponding sample group is considered to be abnormal.
As a further aspect of the present invention, the calculation method for verifying the change rate includes:
in a group of similar sample groups, sequentially marking corresponding target parameter values as f11, f12, … and f1v from small to large, and sequentially marking performance assessment evaluation values corresponding to the target parameters as J11, J12, … and J1v;
and calculating v-1 reference change rates B of the target parameters corresponding to f1 according to a formula B = [ ft-f1]/[ Jt-J1], taking the average value of the v-1 reference change rates B as a verification change rate Bz, and then calculating the verification change rates Bz corresponding to the target parameters in sequence.
As a further scheme of the present invention, in step S11, the number of similar sample groups in each group of similar sample groups is not less than a preset value sy, and sy is 6.
As a further aspect of the present invention, the value of β is 40%.
The invention has the beneficial effects that:
(1) According to the method, the abnormal data in the original data can be mined by using the original assessment parameter values and the assessment results, so that the influence of the abnormal assessment results on the establishment of the subsequent model caused by the intention and the intention of assessment personnel is avoided, and the efficiency and the accuracy of the establishment of the subsequent model are improved;
(2) According to the invention, the corresponding employee performance assessment model can be obtained by fitting the historical assessment data through the neural network, and the subsequent employee performance is automatically assessed through the employee performance assessment model, so that the authenticity and the accuracy of the performance assessment data are ensured, the workload of an accounting staff is avoided, and the efficiency of the performance assessment is improved.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A staff performance assessment and evaluation method based on a BP neural network comprises the following steps:
s1, obtaining various assessment parameters required by a performance assessment and evaluation model, judging whether the assessment parameters are related parameters or random parameters, and obtaining an average reference change rate of the related parameters, wherein the method specifically comprises the following steps:
marking one assessment parameter as a target parameter, marking all the other assessment parameters as auxiliary parameters, and taking each assessment parameter value obtained by one assessed employee in one assessment as a sample group;
acquiring all auxiliary parameters in one sample group, which are sequentially marked as C11, C12, … and C1n, and acquiring all auxiliary parameters in another sample group, which are correspondingly sequentially marked as C21, C22, … and C2n, wherein n is the number of the auxiliary parameters;
wherein C1i and C2i represent the same auxiliary parameter, but the specific numerical values are different; calculating a difference coefficient Cci of the auxiliary parameters C1i and C2i according to a formula | C1i-C2i |/C1i = Cci, wherein i is more than or equal to 1 and is less than or equal to n;
sequentially calculating corresponding difference coefficients of all auxiliary parameters in the two sample groups, and sequentially marking the obtained n difference coefficients as Cc1, cc2, … and Ccn;
when all the difference coefficients are smaller than a preset coefficient alpha, the two sample groups are considered to belong to the same type of sample group aiming at the target parameter;
according to the method, a plurality of groups of similar sample groups are obtained, the number of the similar sample groups in each group of similar sample groups is not less than a preset value sy, and in one embodiment of the invention, sy takes the value of 6;
in a group of similar sample groups, sequentially marking the corresponding target parameter values as f1, f2, … and fm from small to large, and sequentially marking the performance assessment evaluation values corresponding to the target parameters as J1, J2, … and Jm;
calculating m-1 reference change rates B according to a formula B = [ fg-f (g-1) ]/[ Jg-J (g-1) ], wherein the reference change rate B represents the change rate correlation degree between a target parameter value and a performance assessment evaluation value, g is more than or equal to 2 and is less than or equal to m, then calculating a plurality of corresponding reference change rates B in the same type sample groups of each group in sequence, and marking the finally obtained r reference change rates as B1, B2, … and Br in sequence;
according to the formula
Calculating to obtain a dispersion value U of the group of data B1 to Br, when U is less than or equal to Uy, considering the corresponding target parameter as a correlation parameter, and taking Bp as the average reference change rate of the corresponding target parameter;
when U is larger than Uy, deleting the corresponding Bx values in turn according to the sequence of | Bx-Bp | from large to small until U is smaller than or equal to Uy, recording the number r1 of the deleted Bx values at the moment, when r1/r is smaller than or equal to beta, considering the corresponding target parameter as a correlation parameter, and taking Bp as the average reference change rate of the corresponding target parameter; when r1/r > beta, marking the corresponding objective function as a random parameter;
wherein x is not less than 1 and not more than r, bp = (B1 + B2+, …, + Br)/r, uy is a preset value, and β is a preset value, and in one embodiment of the present invention, β is 40%;
s2, processing each assessment parameter according to the method in the step S1, and judging whether each assessment parameter is a correlation parameter or a random parameter;
for the assessment parameters which are related parameters, setting one assessment parameter as a target parameter according to the method in the step S1, dividing the sample group of each assessed employee in one performance assessment needing to be checked into a plurality of similar sample groups, and calculating the verification change rate Bz of each target parameter in one similar sample group;
when the difference value between the verification change rate Bz of one target parameter and the corresponding average reference change rate Bp reaches a preset proportion, the corresponding target parameter is considered to be abnormal;
and when a preset number of target parameters with abnormity exist in one sample group, the performance assessment evaluation result corresponding to the sample group is considered to have abnormity.
The calculation method for verifying the change rate comprises the following steps:
in a group of similar sample groups, sequentially marking corresponding target parameter values as f11, f12, … and f1v from small to large, and sequentially marking performance assessment evaluation values corresponding to the target parameters as J11, J12, … and J1v;
calculating v-1 reference change rates B of the target parameters corresponding to f1 according to a formula B = [ ft-f1]/[ Jt-J1], taking the average value of the v-1 reference change rates B as a verification change rate Bz, and then calculating the verification change rates Bz corresponding to the target parameters in sequence;
abnormal data in the original data can be mined by using the original assessment parameter values and assessment results through the methods in the steps S1 and S2, so that the influence of the abnormal assessment results on the establishment of the subsequent model caused by the intention and the intention of assessment personnel is avoided, and the efficiency and the accuracy of the establishment of the subsequent model are improved;
s3, after the abnormal performance assessment evaluation result is eliminated, taking the remaining historical assessment data of the assessed staff as sample data, and performing data cleaning on the sample data to obtain training sample data;
s4, learning the training sample data through a BP neural network, and establishing an employee performance assessment model;
testing the employee performance assessment evaluation model obtained through training through the test sample data, and finally outputting an evaluation result;
the specific method for establishing the employee performance assessment evaluation model comprises the following steps:
(1) Dividing the sample data into input sample data and target sample data, and carrying out normalization processing on the input sample data and the target sample data;
(2) Importing input sample data and target sample data in a neural network fitting algorithm;
(3) After sample data is imported, the number of neurons in an input layer is set, the number of neurons in an output layer is output, the number of neurons in a hidden layer is set according to an empirical formula, and a Levenberg-Marquardt algorithm is selected;
(4) Network training is carried out to obtain a corresponding staff performance assessment model;
in the network training process, the system model performance is measured through indexes such as an obtained Mean Squared Error (MSE), a parameter change process, a correlation coefficient R value and the like.
Wherein, by respectively setting epoch (iteration number), gradient (gradient) and validation check as a preset fixed value, the network training reaches any index of the three, and the network training is stopped;
and measuring the correlation between the sample output value and the target expected value through a correlation coefficient R value, wherein the correlation coefficient R value is 1 to represent a close relation, and 0 represents a random relation.
The historical assessment data is as follows: the method comprises the following steps of (1) assessing the staff of a company on the aspects of staff behaviors, work performance and the like according to an assessment index standard, and obtaining corresponding data through personal assessment and colleague leadership scoring;
randomly extracting from the sample data according to the proportion of 70%, 15% and 15% of training sample data, verification data and test data respectively, and performing network training;
according to the invention, the corresponding employee performance assessment model can be obtained by fitting the historical assessment data through the neural network, and the subsequent employee performance is automatically assessed through the employee performance assessment model, so that the authenticity and the accuracy of the performance assessment data are ensured, the workload of an accounting staff is avoided, and the performance assessment efficiency is improved;
in the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is illustrative and explanatory only and is not intended to be exhaustive or to limit the invention to the precise embodiments described, and various modifications, additions, and substitutions may be made by those skilled in the art without departing from the scope of the invention or exceeding the scope of the claims.
Claims (5)
1. An employee performance assessment and evaluation method based on a BP neural network is characterized by comprising the following steps:
s1, mining abnormal data in historical assessment data, and removing the abnormal historical assessment data;
s2, taking the historical assessment data of the assessed employee as sample data, and performing data cleaning on the sample data to obtain training sample data;
s3, learning the training sample data through a BP neural network, and establishing an employee performance assessment model;
testing the employee performance assessment evaluation model obtained through training through the test sample data, and finally outputting an evaluation result;
the method for mining abnormal data in historical assessment data comprises the following steps:
s11, obtaining all assessment parameters required by a performance assessment evaluation model, marking one assessment parameter as a target parameter, marking all the other assessment parameters as auxiliary parameters, and taking all assessment parameter values obtained by an assessed employee in one assessment as a sample group;
acquiring all auxiliary parameters in one sample group, which are sequentially marked as C11, C12, … and C1n, and acquiring all auxiliary parameters in another sample group, which are correspondingly sequentially marked as C21, C22, … and C2n, wherein n is the number of the auxiliary parameters;
wherein C1i and C2i represent the same auxiliary parameter; calculating a difference coefficient Cci of the auxiliary parameters C1i and C2i according to a formula | C1i-C2i |/C1i = Cci, wherein i is more than or equal to 1 and is less than or equal to n;
sequentially calculating corresponding difference coefficients of all auxiliary parameters in the two sample groups, and sequentially marking the obtained n difference coefficients as Cc1, cc2, … and Ccn;
when all the difference coefficients are smaller than a preset coefficient alpha, the two sample groups are considered to belong to the same type of sample group aiming at the target parameter;
acquiring a plurality of groups of similar sample groups, sequentially marking corresponding target parameter values as f1, f2, … and fm in a sequence from small to large in one group of similar sample groups, and sequentially marking performance assessment evaluation values corresponding to target parameters as J1, J2, … and Jm;
calculating m-1 reference change rates B according to a formula B = [ fg-f (g-1) ]/[ Jg-J (g-1) ], wherein g is more than or equal to 2 and is less than or equal to m, sequentially calculating a plurality of corresponding reference change rates B in each group of similar samples, and sequentially marking the finally obtained r reference change rates as B1, B2, … and Br;
according to the formula
Calculating to obtain a dispersion value U of the group of data B1 to Br, when U is less than or equal to Uy, considering the corresponding target parameter as a correlation parameter, and taking Bp as the average reference change rate of the corresponding target parameter;
when U is larger than Uy, deleting the corresponding Bx values in turn according to the sequence of | Bx-Bp | from large to small until U is smaller than or equal to Uy, recording the number r1 of the deleted Bx values at the moment, when r1/r is smaller than or equal to beta, considering the corresponding target parameter as a correlation parameter, and taking Bp as the average reference change rate of the corresponding target parameter; when r1/r > beta, marking the corresponding objective function as a random parameter;
wherein x is more than or equal to 1 and less than or equal to r, bp = (B1 + B2+, …, + Br)/r, uy is a preset value, and beta is a preset value;
s12, processing each assessment parameter according to the method in the step S11, and judging whether each assessment parameter is a correlation parameter or a random parameter;
for the assessment parameters which are related parameters, setting one assessment parameter as a target parameter according to the method in the step S11, dividing the sample group of each assessed employee in one performance assessment needing to be checked into a plurality of similar sample groups, and calculating the verification change rate Bz of each target parameter in one similar sample group;
when the difference value between the verification change rate Bz of one target parameter and the corresponding average reference change rate Bp reaches a preset proportion, the corresponding target parameter is considered to be abnormal;
and when a preset number of target parameters with abnormity exist in one sample group, the performance assessment evaluation result corresponding to the sample group is considered to have abnormity.
2. The staff performance assessment method based on the BP neural network as claimed in claim 1, wherein the method for establishing staff performance assessment evaluation model comprises the following steps:
(1) Dividing the sample data into input sample data and target sample data, and performing normalization processing;
(2) Importing input sample data and target sample data in a neural network fitting algorithm;
(3) After sample data is imported, the number of neurons in an input layer is set, the number of neurons in an output layer is output, the number of neurons in a hidden layer is set according to an empirical formula, and a Levenberg-Marquardt algorithm is selected;
(4) And performing network training to obtain a corresponding staff performance assessment evaluation model.
3. The staff performance assessment method based on the BP neural network as claimed in claim 1, wherein the calculation method for verifying the change rate is as follows:
in a group of similar sample groups, sequentially marking corresponding target parameter values as f11, f12, … and f1v from small to large, and sequentially marking performance assessment evaluation values corresponding to the target parameters as J11, J12, … and J1v;
and calculating v-1 reference change rates B of the target parameters corresponding to f1 according to a formula B = [ ft-f1]/[ Jt-J1], taking the average value of the v-1 reference change rates B as a verification change rate Bz, and then calculating the verification change rates Bz corresponding to the target parameters in sequence.
4. The method for assessing the performance of the employee based on the BP neural network as claimed in claim 1, wherein in step S11, the number of the similar sample groups in each group of the similar sample groups is not less than a preset value sy, and sy has a value of 6.
5. The employee performance assessment evaluation method based on the BP neural network as claimed in claim 1, wherein the β value is 40%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211593088.3A CN115660508A (en) | 2022-12-13 | 2022-12-13 | Staff performance assessment and evaluation method based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211593088.3A CN115660508A (en) | 2022-12-13 | 2022-12-13 | Staff performance assessment and evaluation method based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660508A true CN115660508A (en) | 2023-01-31 |
Family
ID=85017088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211593088.3A Pending CN115660508A (en) | 2022-12-13 | 2022-12-13 | Staff performance assessment and evaluation method based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660508A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117764448A (en) * | 2023-12-25 | 2024-03-26 | 苏州优鲜信网络生活服务科技有限公司 | Property personnel performance assessment method and system based on visual work result |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005128703A (en) * | 2003-10-22 | 2005-05-19 | Ueno Business Consultants:Kk | Personnel evaluation method, program for personnel evaluation system, server device for personnel evaluation system, terminal device for personnel evaluation system, and personnel evaluation system |
| 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 |
| CN110222925A (en) * | 2019-04-24 | 2019-09-10 | 深圳证券交易所 | Performance quantization wire examination method, device and computer readable storage medium |
| US20210295162A1 (en) * | 2019-01-04 | 2021-09-23 | Ping An Technology(Shenzhen)Co.,Ltd. | Neural network model training method and apparatus, computer device, and storage medium |
| CN113807728A (en) * | 2021-09-27 | 2021-12-17 | 平安国际智慧城市科技股份有限公司 | Performance assessment method, device, equipment and storage medium based on neural network |
| CN114037288A (en) * | 2021-11-11 | 2022-02-11 | 青岛民航凯亚系统集成有限公司 | Performance adjusting system and method based on machine learning |
| CN115222259A (en) * | 2022-07-20 | 2022-10-21 | 北京维基飞翔科技有限公司 | Strategic target-based comprehensive performance management method and system |
-
2022
- 2022-12-13 CN CN202211593088.3A patent/CN115660508A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005128703A (en) * | 2003-10-22 | 2005-05-19 | Ueno Business Consultants:Kk | Personnel evaluation method, program for personnel evaluation system, server device for personnel evaluation system, terminal device for personnel evaluation system, and personnel evaluation system |
| 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 |
| US20210295162A1 (en) * | 2019-01-04 | 2021-09-23 | Ping An Technology(Shenzhen)Co.,Ltd. | Neural network model training method and apparatus, computer device, and storage medium |
| CN110222925A (en) * | 2019-04-24 | 2019-09-10 | 深圳证券交易所 | Performance quantization wire examination method, device and computer readable storage medium |
| CN113807728A (en) * | 2021-09-27 | 2021-12-17 | 平安国际智慧城市科技股份有限公司 | Performance assessment method, device, equipment and storage medium based on neural network |
| CN114037288A (en) * | 2021-11-11 | 2022-02-11 | 青岛民航凯亚系统集成有限公司 | Performance adjusting system and method based on machine learning |
| CN115222259A (en) * | 2022-07-20 | 2022-10-21 | 北京维基飞翔科技有限公司 | Strategic target-based comprehensive performance management method and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117764448A (en) * | 2023-12-25 | 2024-03-26 | 苏州优鲜信网络生活服务科技有限公司 | Property personnel performance assessment method and system based on visual work result |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111950918B (en) | Market risk assessment method based on power transaction data | |
| CN110634080B (en) | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium | |
| CN108228706A (en) | For identifying the method and apparatus of abnormal transaction corporations | |
| CN106886915B (en) | Advertisement click estimation method based on time attenuation sampling | |
| CN112700319A (en) | Enterprise credit line determination method and device based on government affair data | |
| CN112101480A (en) | Multivariate clustering and fused time sequence combined prediction method | |
| CN108399453A (en) | A kind of Electric Power Customer Credit Rank Appraisal method and apparatus | |
| CN109359770B (en) | Model and method for predicting heatstroke occurrence based on machine learning | |
| CN111723367B (en) | Method and system for evaluating service scene treatment risk of power monitoring system | |
| CN111079937B (en) | Method for fast modeling | |
| CN112613977A (en) | Personal credit loan admission credit granting method and system based on government affair data | |
| CN111325619A (en) | Credit card fraud detection model updating method and device based on joint learning | |
| CN115660508A (en) | Staff performance assessment and evaluation method based on BP neural network | |
| CN107341731A (en) | Insurance business risk score system and its construction method | |
| CN110796539A (en) | Credit investigation evaluation method and device | |
| CN112783100A (en) | Memory, chemical enterprise safety production risk early warning method, equipment and device | |
| CN113516336A (en) | Method and system for determining electricity stealing suspected user | |
| CN110059126B (en) | LKJ abnormal value data-based complex correlation network analysis method and system | |
| CN111178690A (en) | Electricity stealing risk assessment method for electricity consumers based on wind control scoring card model | |
| CN108830444B (en) | Method and device for evaluating and correcting sounding observation data | |
| CN113988519A (en) | Method for representing risk of cultural relic preservation environment in collection of cultural relics | |
| CN113723871A (en) | Multi-source information-based current situation flood consistency processing method and system | |
| CN105260944A (en) | Method for calculating statistical line loss based on LSSVM (Least Square Support Vector Machine) algorithm and association rule mining | |
| CN112348281A (en) | Power data processing method and device | |
| CN106021978A (en) | Assembling method for de novo sequencing data based on optics map platform Irys |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230131 |
|
| RJ01 | Rejection of invention patent application after publication |