CN109345109A - A kind of Stakeholder Evaluation method and terminal device based on classification prediction model - Google Patents
A kind of Stakeholder Evaluation method and terminal device based on classification prediction model Download PDFInfo
- Publication number
- CN109345109A CN109345109A CN201811122675.8A CN201811122675A CN109345109A CN 109345109 A CN109345109 A CN 109345109A CN 201811122675 A CN201811122675 A CN 201811122675A CN 109345109 A CN109345109 A CN 109345109A
- Authority
- CN
- China
- Prior art keywords
- assessment
- data
- employee
- prediction model
- result
- 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
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
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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"
Abstract
The present invention provides a kind of Stakeholder Evaluation methods and terminal device based on classification prediction model, suitable for technical field of data processing, this method comprises: the assessment of data for obtaining multidigit employee constitutes the first assessment of data collection, employee is grade and evaluating target grade and candidate employee employee all the same before evaluating during promoting evaluation；The assessment of data filtered out corresponding to the group number of same employee greater than 1 is concentrated to constitute the second assessment of data collection from the first assessment of data；Based on first assessment of data collection the first prediction model of training, and it is based on second assessment of data collection the second prediction model of training；The assessment of data of candidate employee is handled based on trained first prediction model and trained second prediction model, obtains the assessment result of corresponding candidate employee.The embodiment of the present invention from different dimensions simultaneously candidate employee is assessed, determine its next time promote successfully possibility how, greatly improve the accuracy rate and efficiency to candidate Stakeholder Evaluation.
Description
Technical field
The invention belongs to technical field of data processing, more particularly to Stakeholder Evaluation method and end based on classification prediction model
End equipment.
Background technique
The employee that enterprise needs to carry out position hierarchy promotion evaluation is very more, promotes evaluation every time and needs to this Shanxi of employee
The operation index result risen in the evaluation corresponding examination period is handled, and whether the judge index result of appraisal, which meet employee, is commented
The grade that sets the goal corresponds to index request, to determine whether employee grade can successfully be elevated to evaluating target etc. before evaluating
Grade, such as handles each month in January to March evaluation of employee period performance data, judges employee in the examination time
Whether the performance data in section, which meets evaluating target grade, corresponds to index request.
It, can be after promoting evaluation failure, to the time for promoting failure in the prior art in order to promote the efficiency to staff's benefits
The operation index result for selecting employee this time to promote evaluation carries out manual evaluation, judges a possibility that candidate employee's next time promotes successfully
How, and to identifying that promoting the larger potentiality of successfully possibility biggish candidate employee next time carries out emphasis label, due to artificial
Assessment identification needs to take a substantial amount of time and manpower, and the prior art is commented according to the subjective sensation of appraiser
Estimate, there is no unified evaluation criterias, therefore the prior art is to the identification assessment side of the biggish employee of potentiality in candidate employee
Method inefficiency and accuracy is not high.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of Stakeholder Evaluation methods based on classification prediction model and terminal to set
Standby, the recognition efficiency to solve candidate employee biggish to potentiality in candidate employee in the prior art is low and accuracy is not high
Problem.
The first aspect of the embodiment of the present invention provides a kind of Stakeholder Evaluation method based on classification prediction model, comprising:
The assessment of data of multidigit employee is obtained, the first assessment of data collection is constituted, the employee is during promoting evaluation
It is homogeneous to promote grade and evaluating target grade before evaluation is evaluated in the process with candidate employee for grade and evaluating target grade before evaluating
Same employee, the primary promotion evaluation process of the corresponding employee of every group of assessment of data；
It is concentrated from first assessment of data and filters out the assessment of data for being greater than 1 corresponding to the group number of same employee, constituted
Second assessment of data collection；
Based on the first prediction model of the first assessment of data collection training, and based on the second assessment of data collection training the
Two prediction models；
Based on trained first prediction model and trained second prediction model, to the candidate employee
Assessment of data handled, obtain the assessment result of the corresponding candidate employee.
The second aspect of the embodiment of the present invention provides a kind of terminal device, and the terminal device includes memory, processing
Device, the computer program that can be run on the processor is stored on the memory, and the processor executes the calculating
Following steps are realized when machine program.
The assessment of data of multidigit employee is obtained, the first assessment of data collection is constituted, the employee is during promoting evaluation
It is homogeneous to promote grade and evaluating target grade before evaluation is evaluated in the process with candidate employee for grade and evaluating target grade before evaluating
Same employee, the primary promotion evaluation process of the corresponding employee of every group of assessment of data；
It is concentrated from first assessment of data and filters out the assessment of data for being greater than 1 corresponding to the group number of same employee, constituted
Second assessment of data collection；
Based on the first prediction model of the first assessment of data collection training, and based on the second assessment of data collection training the
Two prediction models；
Based on trained first prediction model and trained second prediction model, to the candidate employee
Assessment of data handled, obtain the assessment result of the corresponding candidate employee.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, comprising: is stored with computer
Program, which is characterized in that realized when the computer program is executed by processor as described above based on classification prediction model
The step of Stakeholder Evaluation method.
Existing beneficial effect is the embodiment of the present invention compared with prior art: by the Shanxi to candidate employee this time failure
It rises grade and evaluating target grade assessment of data all the same before the evaluation of evaluation to be analyzed, and carries out the first prediction model instruction
Practice building so that the first prediction model can accurately identify candidate employee potentiality how, while according to candidate member
Work situation is similar, at least lives through the primary multiple promotion promoted evaluation failure and also carried out the secondary employee for promoting evaluation
The operation index result of evaluation is analyzed, and is constructed in conjunction with evaluation result is promoted to carry out the training of the second prediction model, thus
Allow the second prediction model how to efficiently identify out employee's potentiality, two prediction models is based ultimately upon, from different dimensions
Simultaneously candidate employee is assessed, determine its next time promote successfully possibility how, to realize in candidate employee
The identification of the next biggish employee of potentiality is assessed, and the accuracy rate and efficiency to candidate Stakeholder Evaluation are greatly improved.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process signal for the Stakeholder Evaluation method based on classification prediction model that the embodiment of the present invention one provides
Figure；
Fig. 2 is the implementation process signal of the Stakeholder Evaluation method provided by Embodiment 2 of the present invention based on classification prediction model
Figure；
Fig. 3 is the implementation process signal for the Stakeholder Evaluation method based on classification prediction model that the embodiment of the present invention three provides
Figure；
Fig. 4 is the implementation process signal for the Stakeholder Evaluation method based on classification prediction model that the embodiment of the present invention four provides
Figure；
Fig. 5 is the implementation process signal for the Stakeholder Evaluation method based on classification prediction model that the embodiment of the present invention five provides
Figure；
Fig. 6 is the implementation process signal for the Stakeholder Evaluation method based on classification prediction model that the embodiment of the present invention six provides
Figure；
Fig. 7 is the structural schematic diagram for the Stakeholder Evaluation device based on classification prediction model that the embodiment of the present invention seven provides；
Fig. 8 is the schematic diagram for the terminal device that the embodiment of the present invention eight provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
To facilitate the understanding of the present invention, first the embodiment of the present invention is briefly described herein, due to promoting evaluation every time
All it is whether examination employee grade can successfully be elevated to evaluating target grade before evaluating, as whether employee can be from junior engineer
It is elevated to intermediate engineer, if intermediate business personnel etc. can be elevated to from primary business personnel, therefore promote evaluation process all every time
One must be corresponded to and evaluate preceding grade and an evaluating target grade.When employee promotes evaluation failure, illustrate its this time Shanxi
The operation index result for rising evaluation is unsatisfactory for corresponding evaluating target class requirement, and the present invention can be as candidate member at this time
Work, and employee identical with candidate employee's promotion evaluation situation and its assessment of data are filtered out, then be based on single group assessment of data
Sample data, and prediction model is constructed respectively based on all assessment of data of employee for sample data, next time is carried out to candidate employee
The forecast assessment for promoting possibility size, determine to promote successfully possibility candidate employee's next time it is whether larger, to be waited from these
Select that evaluate potentiality in employee larger, next time promotes the biggish employee of successfully possibility, and details are as follows:
Fig. 1 shows the implementation process of the Stakeholder Evaluation method based on classification prediction model of the offer of the embodiment of the present invention one
Figure, details are as follows:
S101 obtains the assessment of data of multidigit employee, constitutes the first assessment of data collection, and employee is during promoting evaluation
It is homogeneous to promote grade and evaluating target grade before evaluation is evaluated in the process with candidate employee for grade and evaluating target grade before evaluating
Same employee, the primary promotion evaluation process of the corresponding employee of every group of assessment of data.
Wherein, candidate employee refers to the employee for promoting evaluation failure, in order to realize that the identification to the biggish employee of potentiality is commented
Estimate, it first can be according to grade and evaluating target etc. before the evaluation of the promotion evaluation of candidate employee this time failure in the embodiment of the present invention
Grade is screened to carry out the sample data of following model building, i.e., the embodiment of the present invention can be according to the promotion of candidate employee this time failure
Grade and evaluating target grade before the evaluation of evaluation, to grade and evaluating target etc. before the evaluation of the promotion evaluation of other employees
Grade is matched, and determines the assessment of data of other employees all identical with two grades of candidate employee.For example, it is assumed that candidate member
Work this time failure is evaluated from primary business personnel to the promotion of intermediate business personnel, and the embodiment of the present invention can be from other employees at this time
In the promotion evaluation carried out, finding out is also to evaluate from primary business personnel to the promotion of intermediate business personnel, and obtain corresponding
Assessment of data.Assessment of data refer to promote evaluation in it is required use the promotion of operation index result and generation evaluation knot
Fruit.
Due to each employee promote evaluation be both possible to successfully be also possible to failure, and for failure promotion evaluation and
Speech, employee will necessarily continue promotion evaluation, such as employee A carries out primary business personnel to the Shanxi of intermediate business personnel for the first time
It rises evaluation to have failed, that will necessarily continue to evaluate from primary business personnel to the promotion of intermediate business personnel behind, until most
It promotes and is evaluated successfully eventually, therefore the promotion for each employee, to grade and evaluating target grade before same evaluation
It is unforeseen for evaluating number, and the promotion evaluation result of last time is also unforeseen.It follows that in the present invention
In embodiment, in the assessment of data of the multidigit employee got, the assessment of data of each employee both may be one group may also
It is multiple groups, and both may had been all wherein to promote evaluation failure, it is also possible to comprising promotes evaluation successfully, but in actual conditions
For an enterprise, due to its can not all employees be all same grade, while in order to guarantee promote evaluation it is effective
Property, will not exist, which will promote deliberated index, requires the too low of setting, so that owner one surely once passes through, therefore real
In the situation of border, for single evaluating target grade, it there will necessarily be some promotions and evaluate the member for successfully and promoting evaluation failure
Work and its corresponding assessment of data.In embodiments of the present invention, it in order to realize the prediction to candidate employee's potentiality, can be commented with single group
Fixed number constructs subsequent prediction model according to being sample data, judges to judge its next time of the actual conditions of data according to candidate employee
How is a possibility that promoting successfully.
S102 is concentrated from the first assessment of data and is filtered out the assessment of data for being greater than 1 corresponding to the group number of same employee, constitutes
Second assessment of data collection.
As the above analysis, the assessment of data of each employee both may in the assessment of data of the multidigit employee got
Be one group it is also likely to be multiple groups, in embodiments of the present invention, will continue to screen wherein every employee, it is wherein right to determine
The assessment of data group number answered is greater than 1 employee, then obtains the second required assessment of data collection by its assessment of data.For example, it is assumed that
First assessment of data concentrates employee A to have one group of assessment of data, and employee B has two groups of assessment of data, and employee C has three groups of assessment of data,
The embodiment of the present invention can filter out the assessment of data of employee B and employee C at this time, obtain corresponding second assessment of data collection.
Using single group assessment of data as sample data to construct prediction model when, although the sample data volume that can be got compared with
Greatly, but since each sample data is single group assessment of data, finite data length is only capable of indicating that single promotes the finger of evaluation
Mark the result of appraisal and promote evaluation result relationship how, and single promote evaluation by various factors interfere a possibility that compared with
Greatly, so that the accidental error possibility of assessment of data is larger.Therefore, in order to promote the reliability of sample data, the present invention
Embodiment using single group assessment of data be sample data to construct prediction model while, can also filter out corresponding evaluation
After employee of the data group number greater than 1, the every employee filtered out is corresponded to after all assessment of data combine as sample data
Another prediction model is constructed, due at this time when by the combination of employee's multiple groups assessment of data as a sample data, sample number
It is stronger according to longer anti-interference ability, so that the unfailing performance of sample data is high.It wherein should explanatorily, due to actual conditions
The middle process for promoting evaluation is all continuously that is, employee only can when a certain evaluating target grade is not promoted and evaluated successfully
Continue always to carry out promotion evaluation to the evaluating target grade, until just will do it the promotion of higher evaluating target grade after success
Evaluation, for example, employee can be carried out continuously always primary business personnel when primary business personnel promotes evaluation failure to intermediate business personnel
Promotion to intermediate business personnel is evaluated, and can just start to carry out it intermediate business personnel only after success to higher level service person's promotion
Evaluation, therefore in embodiments of the present invention, the corresponding assessment of data of same employee necessarily data continuous in time, thus into
When the same employee's assessment of data of row combines to obtain sample data, it is only necessary to be ranked up combination sequentially in time.
S103 is based on first assessment of data collection the first prediction model of training, and is based on the second assessment of data collection training second
Prediction model.
After getting required the first assessment of data collection and the second assessment of data collection, two datasets are started based on
The training building of prediction model is carried out respectively.
In view of as long as the prediction model in the embodiment of the present invention is able to achieve to whether candidate employee's next time can successfully promote
Prediction, and prediction model type is more in the prior art, therefore not to specifically used prediction in the embodiment of the present invention
Model is defined, and can be chosen or be designed according to actual needs by technical staff, due to employee Shanxi in the embodiment of the present invention
Rise evaluation result and there was only two kinds of success or failure, therefore when carrying out prediction model selection, preferably can be used BP, RBF or
The neural network models such as person PNN construct two disaggregated models, at this time only need by assessment of data operation index result and Shanxi
Liter evaluation result is input to these two disaggregated models and is trained, and the corresponding employee's promotion evaluation result that can be used for can be obtained and predict
Model.
Wherein, it is contemplated that the employee that candidate employee inherently operation index result is not met the requirements, therefore directly make
Prediction model training building, the accuracy rate of finally obtained prediction model are carried out with operation index result and promotion evaluation result
It is difficult to be guaranteed well, therefore, in embodiments of the present invention, it is preferable that operation index result can be carried out further
The processing on ground, then process-based result and promotion evaluation result construct to carry out prediction model training, such as to operation index knot
Fruit carries out the analysis of data variation trend, and carries out prediction model based on obtained variation tendency score and promotion evaluation result
Training building, specifically refers to the embodiment of the present invention two and the embodiment of the present invention three.
S104 is based on trained first prediction model and trained second prediction model, the evaluation to candidate employee
Data are handled, and the assessment result of corresponding candidate employee is obtained.
After obtaining two prediction models, the assessment of data that candidate employee promotes evaluation failure is directly inputted into two
Prediction model is handled, and the potentiality recognition result from two different dimensions to candidate employee can be obtained, pre- further according to two
Result is surveyed to determine finally to the recognition result of candidate employee.
Since the prediction result of two prediction models may have differences, such as it is possible that a prediction result is should
Candidate employee's potentiality larger next time promotes and can succeed, another is then that the less next promotion of employee's potentiality will fail, therefore be
The uniqueness and accuracy of the finally obtained prediction result of guarantee needs to preset in the embodiment of the present invention pre- at two
Survey processing rule of result when having differences, wherein processing rule specifically can by technical staff, demand is arranged according to the actual situation,
Including but not limited to for example when prediction result has differences, again to two prediction models be trained building and again in advance
It surveys, or corresponding weight coefficient is arranged to two prediction models in advance, when prediction result has differences, according to weight coefficient
Processing is carried out to prediction result and determines final prediction result etc..
In embodiments of the present invention, pass through grade and evaluation mesh before the evaluation of the promotion evaluation to candidate employee this time failure
Mark grade assessment of data all the same is analyzed, and carries out the training building of the first prediction model, so that the first prediction mould
Type can accurately identify candidate employee potentiality how, while in view of using single group assessment of data be sample data progress mould
When type training, data volume is although more, but by various factors interfere a possibility that it is larger, therefore in the embodiment of the present invention also
It is similar for candidate employee's situation, at least live through the primary employee for promoting evaluation failure and also having carried out secondary promotion evaluation
The multiple assessment of data combination for promoting evaluation analyzed, and the training building of the second prediction model is carried out, so that second
The sample data reliability of prediction model is stronger, how can efficiently identify out employee's potentiality, is based ultimately upon two prediction moulds
Type, from different dimensions simultaneously candidate employee is assessed, determine its next time promote successfully possibility how, to realize
Identification assessment to the biggish employee of potentiality in candidate employee, greatly improves the accuracy rate and effect to candidate Stakeholder Evaluation
Rate.
A kind of specific implementation as the first prediction model training in the embodiment of the present invention one, it is contemplated that directly use
Operation index result and promotion evaluation result in assessment of data construct to carry out prediction model training, finally obtained prediction mould
The accuracy rate of type is difficult to be guaranteed well, therefore the accurate and effective in order to guarantee finally obtained prediction model, such as Fig. 2 institute
Show, the embodiment of the present invention two, comprising:
S201 obtains the first assessment of data and concentrates each group assessment of data corresponding examination period for promoting evaluation process.
Whether meet index request both for operation index result of the employee within the examination period due to promoting evaluation
It is examined, therefore, each process for promoting evaluation must correspond to an examination period, such as extremely in January, 2017
In March, 2017, employee performance data were examined, and were judged whether it meets from primary business personnel to the promotion of intermediate business personnel and were commented
Determine index request, at this time in January, 2017 in March, 2017 is the examination period for this time promoting evaluation.
S202, data variation of the operation index result within the corresponding examination period parsed in each group assessment of data become
Gesture obtains the corresponding first variation tendency score of every group of assessment of data.
In view of in actual conditions, although how the potentiality of employee can not directly directly obtain according to operation index result,
But within the examination period whole operation index results change trend can reflect to a certain extent employee potentiality how,
It is as escribed above to examine the period when operation index result of a certain employee within the examination period is always incremented by double
In in January, 2017 in March, 2017, the achievement of the employee monthly is all several times of last month, even if the employee this time promotes at this time
Evaluation has failed, but is equally to promote evaluation failure, but monthly other constant always employees of achievement in the examination period relatively
For, the potentiality of the employee are undoubtedly bigger, and the successful possibility that next time promotes evaluation is bigger.Therefore in embodiments of the present invention,
It, can be first to each assessment of data in its examination before carrying out the training of the first prediction model in order to guarantee the accuracy of prediction model
The variation tendency of operation index result carries out quantitative analysis in period, with the first change of each assessment of data after quantify
Change trend fractional value.Wherein specific variation tendency quantitative analysis method can not be limited herein by technical staff's sets itself,
All overall variation trend methods that can embody operation index result in the examination period, including but not limited to such as will
The examination period is divided into multiple and different periods, and using each period as a timing node after, by operation index
As a result the corresponding index of each timing node is split as a result, carrying out curve fitting again to index result, and with slope of a curve
As variation tendency score.
S203 concentrates promotion evaluation result and corresponding first change in each group assessment of data based on the first assessment of data
Change trend score, the first prediction model of training.
After obtaining the first variation tendency score of each assessment of data, by each assessment of data first variation become
Gesture score promotes evaluation result } vector data is used as sample data, and it is trained to carry out prediction model, determine that the first variation becomes
Corresponding relationship between gesture score and promotion evaluation result, the first prediction model that you can get it finally.In the embodiment of the present invention
The model specifically used some relative complex neural network models can both can be used and carried out by technical staff's sets itself
Prediction also can be used some relatively simple two disaggregated models such as Logic Regression Models etc and be predicted.
It should explanatorily, due to using { the first of assessment of data when carrying out model training in the embodiment of the present invention
Variation tendency score, promote evaluation result vector data as sample data, therefore one S104 of the embodiment of the present invention be based in advance
When surveying the assessment of data processing of the candidate employee of model progress, equally also need the assessment of data of candidate employee first carrying out transformation trend
Score calculates, and prediction model is recycled to be handled.
A kind of specific implementation as the second prediction model training in the embodiment of the present invention one, it is contemplated that directly use
Operation index result and promotion evaluation result in assessment of data construct to carry out prediction model training, finally obtained prediction mould
The accuracy rate of type is difficult to be guaranteed well, therefore the accurate and effective in order to guarantee finally obtained prediction model, such as Fig. 3 institute
Show, the embodiment of the present invention three, comprising:
S301 obtains the second assessment of data and concentrates each group assessment of data corresponding examination period for promoting evaluation process.
S302, each employee corresponding for the second assessment of data collection parse the finger in its corresponding all assessment of data
Data variation trend of the result of appraisal within the corresponding examination period is marked, unique corresponding second variation of each employee is obtained and becomes
Gesture score.
S303, final promotion evaluation result and the second variation tendency based on the corresponding employee of the second assessment of data collection point
Number, the second prediction model of training, final evaluation result of promoting is that employee's corresponding examination period is nearest apart from current time
The promotion evaluation result of assessment of data.
The choosing of examination period, data variation trend, variation tendency score and prediction model in the embodiment of the present invention
The related contents such as take identical with the embodiment of the present invention two, therefore it will not go into details herein, details can refer to the embodiment of the present invention
Two.
The embodiment of the present invention and the embodiment of the present invention two the difference is that, it is contemplated that using single assessment of data as sample number
According to carry out prediction model training when, although the sample data volume that can be got is larger, due to single assessment of data reliability compared with
It is low to be interfered vulnerable to other factors, therefore in order to enhance the reliability that the anti-interference of sample data improves sample data, this hair
It is not handled using single assessment of data as sample data in bright embodiment, single employee is concentrated with the second assessment of data
The combination of all assessment of data be used as sample data, therefore in the embodiment of the present invention when carrying out data variation trend analysis, needle
Pair be the operation index result that each employee corresponds to all assessment of data total data variation tendency, it is assumed for example that employee A exists
Second assessment of data is concentrated with 3 assessment of data, and the embodiment of the present invention can be according to the examination period sequentially by 3 evaluation numbers at this time
According to being combined, and as a whole by 3 assessment of data after combination, operation index result wherein included is counted
According to analysis of trend, the unique corresponding second variation tendency score of each employee is obtained.In another example assuming the second evaluation
In data set, it is three January~March, April~June and July~September evaluation numbers that employee B, which has the corresponding examination period,
According to sequence obtains the combination of January~September assessment of data sequentially in time at this time, then combines interior January~September to assessment of data
Operation index result carry out data variation trend analysis, obtain the operation index result in this 9 months it is corresponding second variation
Trend score.
Simultaneously as each employee can only obtain a corresponding second variation tendency score in the embodiment of the present invention, together
When the embodiment of the present invention want to be accomplished that transformation trend score with whether can promote successful Relationship Prediction, therefore the present invention is real
The promotion evaluation result that example has only selected each employee final is applied as the required data of prediction model training, and with every zooid
{ the second variation tendency score, finally promote evaluation result } vector data of work carries out prediction model training as sample data
Building.
Should explanatorily, the embodiment of the present invention three and the embodiment of the present invention are second is that training building side to two prediction models
Method both can be applied independently in the embodiment of the present invention one, can also be applied simultaneously, i.e., two present invention are implemented
The characteristics of example can apply the embodiment of the present invention one simultaneously, with realization according to two assessment of data collection include data, to carry out not
With the prediction model training building of mode.
As a kind of specific reality for carrying out data variation trend analysis in the embodiment of the present invention two and the embodiment of the present invention three
Existing mode, as shown in figure 4, the embodiment of the present invention four, comprising:
S401, obtain examination the period in include multiple examination timing nodes, and by operation index result be split as with
The one-to-one result of appraisal of multiple examination timing nodes.
S402 carries out linear function fit to the result of appraisal, and using the slope value of the linear function fitted as correspondence
Variation tendency score.
Examination timing node refers to each period after the examination period to be divided into multiple isometric periods, wherein
Specific period division rule can be by technical staff's sets itself according to the actual situation, such as when examining to employee performance data
Between section be January~March, at this time can will examination period segmentum intercalaris when being divided into January, 2 months and three examinations in March as unit of the moon
Point, and operation index result is split, obtain each month performance data.
In view of the examination period for promoting evaluation every time general in actual conditions is all shorter, the operation index knot for being included
The data volume of fruit is smaller, it is assumed for example that promoting evaluation all every time is the performance data examined in employee nearly three months, at this time index
The result of appraisal only include trimestral performance data, therefore in order to protect simultaneously in reduction to the workload of data analysis of trend
The reliability of analysis is demonstrate,proved, can directly carry out the fitting of linear function in the embodiment of the present invention to the operation index result after fractionation,
And using the slope value of obtained linear function as required variation tendency score.The assessment of data to each employee combine into
When row analysis of trend, equally directly the assessment of data combination corresponding examination period carries out examination timing node division, and
The fractionation of operation index result and linear function fit are carried out, such as above-mentioned employee B is corresponding with the combination of January~September assessment of data,
Assuming that carrying out the division of examination timing node as unit of the moon, operation index result can be split as to 9 at this time and corresponding examined
Core is as a result, such as each month performance data of January~September, then carries out linear function fit.
As a kind of specific implementation predicted in the embodiment of the present invention one using two prediction models, it is contemplated that
The prediction result of two prediction models may have differences in actual conditions, final pre- in order to determine when having differences
It surveys as a result, as shown in figure 5, the embodiment of the present invention five, comprising:
S501 is based on trained first prediction model and trained second prediction model, the evaluation to candidate employee
Data are handled, and corresponding first prediction result and the second prediction result are obtained.
Wherein, the sample data selection of the prediction model in the embodiment of the present invention and model training mode etc., specifically may be used
With reference to the embodiment of the present invention one, the embodiment of the present invention two or the embodiment of the present invention three.
S502 reduces the first prediction model and second in advance if the first prediction result has differences with the second prediction result
The training error of the corresponding model training of model is surveyed, and returns to execution and is based on first assessment of data collection the first prediction model of training,
And the operation based on second assessment of data collection the second prediction model of training.
It is practical when carrying out prediction model training building, it is necessary to preset the training error of what a model training with
It is such as settable to terminate when the error rate classified to sample data is not higher than 10% to model as the condition that model training terminates
Training, 10% allowed at this time be training error.
In view of being that the candidate employee promotes can succeed that another is then under the employee next time when there is prediction result
When secondary promotion will fail, it may be possible to which forecasting inaccuracy caused by training error is excessive when two prediction model training is true, therefore this hair
Bright embodiment can reduce the training error of two prediction models, and be based on the first assessment of data when prediction result has differences
Collect with the second assessment of data collection and training is re-started to two prediction models, training error is such as reduced to 8% simultaneously from 10%
Re -training, to improve the accuracy rate of prediction.Wherein, specific minishing method can be set by technical staff, can such as be set in advance
It sets a fixed step-length and carries out each reduction operation, or the decreasing value of the several fixations of setting to be adjusted.
As an embodiment of the present invention, it is contemplated that even if each prediction result has differences in the embodiment of the present invention five
When all reduce training error and re -training, be likely to occur two prediction result situations different always, therefore still in order to protect
The uniqueness and accuracy for demonstrate,proving final prediction result, the embodiment of the present invention includes:
The reduction number and occurrence of training error are monitored.If two prediction results have differences, and training
The reduction number of error reaches frequency threshold value or the occurrence of training error reaches error threshold, pre- based on two obtained
It surveys as a result, determining finally to the prediction result of candidate employee.
Since the occurrence that the reduction number when training error reaches frequency threshold value or training error reaches error threshold
Value illustrates that the method by the embodiment of the present invention five can not carry out the unification of prediction result, therefore meeting in the embodiment of the present invention
Stop the adjustment to training error, but directly determines final result according to two final prediction results.Wherein have
The method that body determines final assessment result according to two prediction results, can be including but unlimited by technical staff's sets itself
In being such as subject to wherein some prediction result.
As a kind of specific implementation predicted in the embodiment of the present invention one using two prediction models, it is contemplated that
The prediction result of two prediction models may have differences in actual conditions, final pre- in order to determine when having differences
It surveys as a result, as shown in fig. 6, the embodiment of the present invention six, comprising:
S601 is based on trained first prediction model and trained second prediction model, the evaluation to candidate employee
Data are handled, and corresponding first prediction result and the second prediction result are obtained.
S602 ties the first prediction result and the second prediction if the first prediction result has differences with the second prediction result
Fruit carries out weight calculation, determines the assessment result to candidate employee.
In embodiments of the present invention, it is contemplated that actual conditions technical staff may not be directly this using two disaggregated models
The model of two definitive results of output is only capable of to carry out the building of prediction model, but uses some such as neural network models can
To export the model progress prediction model training building that employee promotes the probability of success next time, what two prediction models exported at this time is
Prediction result is two and promotes successful probability, therefore, in order to guarantee the uniqueness and reliability of final prediction result, this hair
It can be respectively corresponded when two prediction results have differences using pre-set two prediction models in bright embodiment
Weight coefficient to carry out weight calculations to two prediction results, to obtain final prediction result, it is assumed for example that the first prediction
The weight coefficient of model and the second prediction model is respectively 0.4 and 0.6, and two prediction results are respectively 60% and 40%, at this time
Final prediction result=0.4*60%+0.6*40%=48%, therefore final prediction result is candidate employee Shanxi next time
Rising successful probability is 48%.
In embodiments of the present invention, pass through grade and evaluation mesh before the evaluation of the promotion evaluation to candidate employee this time failure
It marks grade assessment of data all the same and carries out the analysis of operation index result data variation tendency, and carry out the first prediction model instruction
Practice building so that the first prediction model can accurately identify candidate employee potentiality how, while according to candidate
Employee's situation is similar, at least lives through the primary multiple Shanxi promoted evaluation failure and also carried out the secondary employee for promoting evaluation
The operation index result for rising evaluation carries out the analysis of data variation trend, and carries out second in conjunction with final promotion evaluation result
Prediction model training building, so that how the second prediction model can efficiently identify out employee's potentiality, therefore the present invention
The selection processing of sample data has sufficiently been carried out in embodiment in terms of the data volume of sample data and data reliability two,
So that two prediction models simultaneously can assess candidate employee from different dimensions, determine that its next time promotes successfully
How is possibility, realizes the identification assessment to the biggish employee of next potentiality in candidate employee, greatly improves to candidate
The accuracy rate and efficiency of Stakeholder Evaluation.
Corresponding to the method for foregoing embodiments, Fig. 7 shows provided in an embodiment of the present invention based on prediction model of classifying
The structural block diagram of Stakeholder Evaluation device, for ease of description, only parts related to embodiments of the present invention are shown.Fig. 7 example
Based on classification prediction model Stakeholder Evaluation device can be previous embodiment one offer based on classification prediction model member
The executing subject of work appraisal procedure.
Referring to Fig. 7, should include: based on the Stakeholder Evaluation device of classification prediction model
First data set acquisition module 71 constitutes the first assessment of data collection, institute for obtaining the assessment of data of multidigit employee
Stating employee is grade and evaluating target grade before evaluating during promoting evaluation, is evaluated during promoting evaluation with candidate employee
Preceding grade and evaluating target grade employee all the same, the primary promotion evaluation process of the corresponding employee of every group of assessment of data.
Second data set acquisition module 72, for filtering out from first assessment of data concentration corresponding to same employee's
Group number is greater than 1 assessment of data, constitutes the second assessment of data collection.
Model training module 73, for being based on the first prediction model of the first assessment of data collection training, and based on described
Second assessment of data collection the second prediction model of training.
Stakeholder Evaluation module 74, based on trained first prediction model and the trained second prediction mould
Type handles the assessment of data of the candidate employee, obtains the assessment result of the corresponding candidate employee.
Further, model training module 73, comprising:
First time period obtains module, concentrates the corresponding promotion of each group assessment of data for obtaining first assessment of data
The examination period of evaluation process.
First trend analysis module, for parsing the operation index result in each group assessment of data in the corresponding examination
Data variation trend in period obtains the corresponding first variation tendency score of every group of assessment of data.
First model training module, for concentrating the promotion evaluation in each group assessment of data based on first assessment of data
As a result and corresponding first variation tendency score, training first prediction model.
Further, model training module 73, further includes:
Second time period obtains module, concentrates the corresponding promotion of each group assessment of data for obtaining second assessment of data
The examination period of evaluation process.
Second trend analysis module is used for each employee corresponding for the second assessment of data collection, parses its correspondence
All assessment of data in operation index result it is corresponding it is described examination the period in data variation trend, obtain each
The unique corresponding second variation tendency score of employee.
Second model training module evaluates knot for the final promotion based on the corresponding employee of the second assessment of data collection
Fruit and the second variation tendency score, training second prediction model, the final promotion evaluation result are employee couple
The promotion evaluation result of the assessment of data of the examination period answered apart from current time recently.
Further, trend analysis module, further includes:
The multiple examination timing nodes for including in the examination period are obtained, and operation index result is split as and institute
State the one-to-one result of appraisal of multiple examination timing nodes.
Linear function fit is carried out to the result of appraisal, and using the slope value of the linear function fitted as corresponding
Variation tendency score.
Further, Stakeholder Evaluation module 74, comprising:
First prediction module, for based on trained first prediction model and the trained second prediction mould
Type handles the assessment of data of the candidate employee, obtains corresponding first prediction result and the second prediction result.
Training module is updated, if having differences for first prediction result and second prediction result, reduces institute
The training error of the first prediction model and the corresponding model training of second prediction model is stated, and returns and is based on described in execution
The first prediction model of the first assessment of data collection training, and based on the second prediction model of the second assessment of data collection training
Operation.
Further, Stakeholder Evaluation module 74, further includes:
Second prediction module, for based on trained first prediction model and the trained second prediction mould
Type handles the assessment of data of the candidate employee, obtains corresponding first prediction result and the second prediction result.
Weight identification module, if if first prediction result has differences with second prediction result, to described
One prediction result and second prediction result carry out weight calculation, determine the assessment result to the candidate employee.
Each module realizes respective function in Stakeholder Evaluation device provided in an embodiment of the present invention based on classification prediction model
Process, specifically refer to the description of aforementioned embodiment illustrated in fig. 1 one, details are not described herein again.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Although will also be appreciated that term " first ", " second " etc. are used in some embodiment of the present invention in the text
Various elements are described, but these elements should not be limited by these terms.These terms are used only to an element
It is distinguished with another element.For example, the first table can be named as the second table, and similarly, the second table can be by
It is named as the first table, without departing from the range of various described embodiments.First table and the second table are all tables, but
It is them is not same table.
Fig. 8 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 8, the terminal of the embodiment is set
Standby 8 include: processor 80, memory 81, and the computer that can be run on the processor 80 is stored in the memory 81
Program 82.The processor 80 realizes that above-mentioned each employee based on classification prediction model comments when executing the computer program 82
Estimate the step in embodiment of the method, such as step 101 shown in FIG. 1 is to 107.Alternatively, the processor 80 executes the calculating
The function of each module/unit in above-mentioned each Installation practice, such as the function of module 71 to 77 shown in Fig. 7 are realized when machine program 82
Energy.
The terminal device 8 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The terminal device may include, but be not limited only to, processor 80, memory 81.It will be understood by those skilled in the art that Fig. 8
The only example of terminal device 8 does not constitute the restriction to terminal device 8, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal device can also include input sending device, net
Network access device, bus etc..
Alleged processor 80 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 81 can be the internal storage unit of the terminal device 8, such as the hard disk or interior of terminal device 8
It deposits.The memory 81 is also possible to the External memory equipment of the terminal device 8, such as be equipped on the terminal device 8
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 81 can also both include the storage inside list of the terminal device 8
Member also includes External memory equipment.The memory 81 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 81, which can be also used for temporarily storing, have been sent or data to be sent.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.
Wherein, the computer program includes computer program code, and the computer program code can be source code
Form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium may include: can
Carry any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer of the computer program code
Memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), electric carrier signal, telecommunication signal and software distribution medium etc..
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the essence of corresponding technical solution is departed from the spirit and scope of the technical scheme of various embodiments of the present invention, it should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of Stakeholder Evaluation method based on classification prediction model characterized by comprising
The assessment of data of multidigit employee is obtained, the first assessment of data collection is constituted, the employee is to evaluate during promoting evaluation
It is all the same to promote grade and evaluating target grade before evaluation is evaluated in the process with candidate employee for preceding grade and evaluating target grade
Employee, the primary promotion evaluation process of the corresponding employee of every group of assessment of data；
It is concentrated from first assessment of data and filters out the assessment of data for being greater than 1 corresponding to the group number of same employee, constitute second
Assessment of data collection；
Based on the first prediction model of the first assessment of data collection training, and it is pre- based on the second assessment of data collection training second
Survey model；
Based on trained first prediction model and trained second prediction model, the candidate employee is commented
Fixed number obtains the assessment result of the corresponding candidate employee according to being handled.
2. the Stakeholder Evaluation method as described in claim 1 based on classification prediction model, which is characterized in that the assessment of data
In the corresponding operation index result promoted during evaluation and evaluation result is promoted including corresponding employee, it is described to be based on institute
State first assessment of data collection the first prediction model of training, comprising:
It obtains first assessment of data and concentrates each group assessment of data corresponding examination period for promoting evaluation process；
Data variation trend of the operation index result within the corresponding examination period in each group assessment of data is parsed, is obtained
To the corresponding first variation tendency score of every group of assessment of data；
Promotion evaluation result and corresponding first variation in each group assessment of data is concentrated to become based on first assessment of data
Gesture score, training first prediction model.
3. the Stakeholder Evaluation method as described in claim 1 based on classification prediction model, which is characterized in that the assessment of data
In the corresponding operation index result promoted during evaluation and evaluation result is promoted including corresponding employee, it is described to be based on institute
State second assessment of data collection the second prediction model of training, comprising:
It obtains second assessment of data and concentrates each group assessment of data corresponding examination period for promoting evaluation process；
Each employee corresponding for the second assessment of data collection parses the operation index in its corresponding all assessment of data
As a result the data variation trend within the corresponding examination period obtains unique corresponding second variation tendency of each employee
Score；
Final promotion evaluation result and second variation tendency based on the corresponding employee of the second assessment of data collection point
Number, training second prediction model, the final promotion evaluation result are that the corresponding examination period distance of employee is worked as
The promotion evaluation result of the assessment of data of preceding time recently.
4. the Stakeholder Evaluation method as claimed in claim 2 or claim 3 based on classification prediction model, which is characterized in that the data
The process of analysis of trend, comprising:
Obtain it is described examination the period in include multiple examination timing nodes, and by operation index result be split as with it is described more
The one-to-one result of appraisal of a examination timing node；
Linear function fit is carried out to the result of appraisal, and using the slope value of the linear function fitted as corresponding variation
Trend score.
5. the Stakeholder Evaluation method based on classification prediction model as described in claims 1 to 3 any one, which is characterized in that
It is described to be based on trained first prediction model and trained second prediction model, the candidate employee is commented
Fixed number obtains the assessment result of the corresponding candidate employee according to being handled, comprising:
Based on trained first prediction model and trained second prediction model, the candidate employee is commented
Fixed number obtains corresponding first prediction result and the second prediction result according to being handled；
If first prediction result has differences with second prediction result, reduce first prediction model and described
The training error of the corresponding model training of second prediction model, and it is described based on the first assessment of data collection training to return to execution
First prediction model, and the operation based on the second prediction model of the second assessment of data collection training.
6. the Stakeholder Evaluation method based on classification prediction model as described in claims 1 to 3 any one, which is characterized in that
It is described to be based on trained first prediction model and trained second prediction model, the candidate employee is commented
Fixed number obtains the assessment result of the corresponding candidate employee according to being handled, further includes:
Based on trained first prediction model and trained second prediction model, the candidate employee is commented
Fixed number obtains corresponding first prediction result and the second prediction result according to being handled；
If first prediction result has differences with second prediction result, to first prediction result and described second
Prediction result carries out weight calculation, determines the assessment result to the candidate employee.
7. a kind of terminal device, which is characterized in that the terminal device includes memory, processor, is stored on the memory
There is the computer program that can be run on the processor, the processor realizes following step when executing the computer program
It is rapid:
The assessment of data of multidigit employee is obtained, the first assessment of data collection is constituted, the employee is to evaluate during promoting evaluation
It is all the same to promote grade and evaluating target grade before evaluation is evaluated in the process with candidate employee for preceding grade and evaluating target grade
Employee, the primary promotion evaluation process of the corresponding employee of every group of assessment of data；
It is concentrated from first assessment of data and filters out the assessment of data for being greater than 1 corresponding to the group number of same employee, constitute second
Assessment of data collection；
Based on the first prediction model of the first assessment of data collection training, and it is pre- based on the second assessment of data collection training second
Survey model；
Based on trained first prediction model and trained second prediction model, the candidate employee is commented
Fixed number obtains the assessment result of the corresponding candidate employee according to being handled.
8. terminal device as claimed in claim 7, which is characterized in that the assessment of data includes corresponding employee corresponding
It promotes the operation index result during evaluation and promotes evaluation result, it is described based on the first assessment of data collection training the
One prediction model, specifically includes:
It obtains first assessment of data and concentrates each group assessment of data corresponding examination period for promoting evaluation process；
Data variation trend of the operation index result within the corresponding examination period in each group assessment of data is parsed, is obtained
To the corresponding first variation tendency score of every group of assessment of data；
Promotion evaluation result and corresponding first variation in each group assessment of data is concentrated to become based on first assessment of data
Gesture score, training first prediction model.
9. terminal device as claimed in claim 7, which is characterized in that the assessment of data includes corresponding employee corresponding
It promotes the operation index result during evaluation and promotes evaluation result, it is described based on the second assessment of data collection training the
Two prediction models, comprising:
It obtains second assessment of data and concentrates each group assessment of data corresponding examination period for promoting evaluation process；
Each employee corresponding for the second assessment of data collection parses the operation index in its corresponding all assessment of data
As a result the data variation trend within the corresponding examination period obtains unique corresponding second variation tendency of each employee
Score；
Final promotion evaluation result and second variation tendency based on the corresponding employee of the second assessment of data collection point
Number, training second prediction model, the final promotion evaluation result are that the corresponding examination period distance of employee is worked as
The promotion evaluation result of the assessment of data of preceding time recently.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 6 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811122675.8A CN109345109A (en) | 2018-09-26 | 2018-09-26 | A kind of Stakeholder Evaluation method and terminal device based on classification prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811122675.8A CN109345109A (en) | 2018-09-26 | 2018-09-26 | A kind of Stakeholder Evaluation method and terminal device based on classification prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109345109A true CN109345109A (en) | 2019-02-15 |
Family
ID=65306929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811122675.8A Pending CN109345109A (en) | 2018-09-26 | 2018-09-26 | A kind of Stakeholder Evaluation method and terminal device based on classification prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109345109A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009109A (en) * | 2019-03-01 | 2019-07-12 | 上海拍拍贷金融信息服务有限公司 | Model prediction method, apparatus, equipment 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 |
| CN111144950A (en) * | 2019-12-30 | 2020-05-12 | 北京顺丰同城科技有限公司 | Model screening method and device, electronic equipment and storage medium |
| CN112734147A (en) * | 2019-10-28 | 2021-04-30 | 北京京东乾石科技有限公司 | Method and device for equipment evaluation management |
| CN113379207A (en) * | 2021-05-28 | 2021-09-10 | 李洪涛 | Control method of practical training platform, practical training platform and readable storage medium |
| CN113435746A (en) * | 2021-06-28 | 2021-09-24 | 平安银行股份有限公司 | User workload scoring method and device, electronic equipment and storage medium |
-
2018
- 2018-09-26 CN CN201811122675.8A patent/CN109345109A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009109A (en) * | 2019-03-01 | 2019-07-12 | 上海拍拍贷金融信息服务有限公司 | Model prediction method, apparatus, equipment and storage medium |
| CN110009109B (en) * | 2019-03-01 | 2021-09-10 | 上海拍拍贷金融信息服务有限公司 | Model prediction method for predicting overdue repayment probability of user and related equipment |
| 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 |
| CN110222925B (en) * | 2019-04-24 | 2022-04-08 | 深圳证券交易所 | Performance quantitative assessment method and device and computer readable storage medium |
| CN112734147A (en) * | 2019-10-28 | 2021-04-30 | 北京京东乾石科技有限公司 | Method and device for equipment evaluation management |
| CN111144950A (en) * | 2019-12-30 | 2020-05-12 | 北京顺丰同城科技有限公司 | Model screening method and device, electronic equipment and storage medium |
| CN113379207A (en) * | 2021-05-28 | 2021-09-10 | 李洪涛 | Control method of practical training platform, practical training platform and readable storage medium |
| CN113379207B (en) * | 2021-05-28 | 2023-12-22 | 李洪涛 | Control method of training platform, training platform and readable storage medium |
| CN113435746A (en) * | 2021-06-28 | 2021-09-24 | 平安银行股份有限公司 | User workload scoring method and device, electronic equipment and storage medium |
| CN113435746B (en) * | 2021-06-28 | 2022-09-27 | 平安银行股份有限公司 | User workload scoring method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109345109A (en) | A kind of Stakeholder Evaluation method and terminal device based on classification prediction model | |
| US20230297890A1 (en) | Customizable machine learning models | |
| Song et al. | Environmental performance evaluation with big data: Theories and methods | |
| Chen et al. | Project delivery system selection of construction projects in China | |
| Digalwar et al. | An overview of existing performance measurement frameworks in the context of world class manufacturing performance measurement | |
| Wu et al. | Maintenance effort estimation for open source software: A systematic literature review | |
| CN102262663B (en) | Method for repairing software defect reports | |
| WO2017071369A1 (en) | Method and device for predicting user unsubscription | |
| McGee et al. | Software requirements change taxonomy: Evaluation by case study | |
| Dai et al. | Generational differences on craft workers’ perceptions of the factors affecting labour productivity | |
| Aramali et al. | Forward-looking state-of-the-art review on earned value management systems: The disconnect between academia and industry | |
| Górecki et al. | Who risks and wins?—Simulated cost variance in sustainable construction projects | |
| Zheng et al. | An activity-based defect management framework for product development | |
| CN102402717A (en) | Data analysis facility and method | |
| Mouhib et al. | TSMAA‐TRI: A temporal multi‐criteria sorting approach under uncertainty | |
| Castelblanco et al. | Environmental impact assessment effectiveness in public–private partnerships: Study on the Colombian toll road program | |
| Kumar et al. | Exploring and measure the performance of the Indian petroleum supply chain | |
| US8352407B2 (en) | Systems and methods for modeling consequences of events | |
| Xu et al. | Selection bias in build-operate-transfer transportation project appraisals | |
| US8504412B1 (en) | Audit automation with survey and test plan | |
| US20140316959A1 (en) | Estimating financial risk based on non-financial data | |
| US20160217425A1 (en) | Systems, methods, and devices for implementing a referral processor | |
| Scholta | Semi-automatic inductive derivation of reference process models that represent best practices in public administrations | |
| Szafranko | Evaluation of data obtained from expert opinions in multi-criteria analyses of construction investment variants | |
| US20160092807A1 (en) | Automatic Detection and Resolution of Pain Points within an Enterprise |
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 |