CN109615280A - Employee's data processing method, device, computer equipment and storage medium - Google Patents
Employee's data processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109615280A CN109615280A CN201910073369.8A CN201910073369A CN109615280A CN 109615280 A CN109615280 A CN 109615280A CN 201910073369 A CN201910073369 A CN 201910073369A CN 109615280 A CN109615280 A CN 109615280A
- Authority
- CN
- China
- Prior art keywords
- employee
- data
- index
- violation
- screened
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of employee's data processing method, device, computer equipment and the storage mediums in artificial intelligence field.The described method includes: obtaining a variety of data to be assessed of employee to be assessed;Obtain preset violation risk model;It include evaluation index in violation risk model;Achievement data corresponding with evaluation index is extracted from a variety of data to be assessed;Achievement data is inputted into preset violation risk model;Achievement data is calculated by violation risk model, obtains the violation risk score of employee to be assessed;When violation risk score is greater than preset fraction, determine employee to be assessed for violation high risk employee.It can be accurate to determine violation high risk employee by machine learning techniques using this method.
Description
Technical field
This application involves field of computer technology, set more particularly to a kind of employee's data processing method, device, computer
Standby and storage medium.
Background technique
Enterprises usually will do it regular Stakeholder Evaluation work, filter out that there are the employees of violation risk to shift to an earlier date
Pre-alarm and prevention.It is general first according to early warning rule settings corresponding index in traditional approach, it is determined by early warning personnel based on personal experience
After the threshold value of index, investigation is sampled to the employee's inventory for being higher than threshold value, violation high risk employee is determined by artificial screening.
However, the index and threshold value that set in traditional approach are the personal experiences based on early warning personnel, with stronger subjectivity and not
Stability causes to be difficult to accurately determine violation high risk employee.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of member that can accurately determine violation high risk employee
Work data processing method, device, computer equipment and storage medium.
A kind of employee's data processing method, which comprises obtain a variety of data to be assessed of employee to be assessed;It obtains
Preset violation risk model;It include evaluation index in the violation risk model;It is extracted from a variety of data to be assessed
Achievement data corresponding with the evaluation index;The achievement data is inputted into the preset violation risk model;Pass through institute
It states violation risk model to calculate the achievement data, obtains the violation risk score of the employee to be assessed;When described
When violation risk score is greater than preset fraction, determine that the employee to be assessed is violation high risk employee.
In one of the embodiments, before a variety of data to be assessed for obtaining employee to be assessed, further includes: point
The multi-modeling data of normal employee and the multi-modeling data of violation employee are not obtained;Determine that every kind of modeling data is corresponding
Raw performance;According to the corresponding modeling data of each Raw performance, index to be screened is chosen from Raw performance;To each wait sieve
The modeling data of the corresponding normal employee of index, and the modeling data of the corresponding violation employee of corresponding index to be screened is selected to carry out list
Factor analysis, screening obtain multiple evaluation indexes;Violation risk model is established based on the multiple evaluation index.
The corresponding modeling data according to each Raw performance in one of the embodiments, from Raw performance
Choose index to be screened, comprising: the sample size of the corresponding modeling data of each Raw performance is counted respectively, and obtain
The total number of the multi-modeling data;The number of each Raw performance is calculated according to the sample size and the total number
According to miss rate;Filter out the intermediary outcomes that the shortage of data rate is lower than default miss rate;Each intermediary outcomes are carried out
Clustering obtains the data exception rate of each intermediary outcomes;The data exception rate is lower than to the centre of default abnormal rate
Index is as index to be screened.
The modeling data and phase to the corresponding normal employee of each index to be screened in one of the embodiments,
The modeling data of the corresponding violation employee of index to be screened is answered to carry out single factor analysis, screening obtains multiple evaluation indexes, comprising:
The first quantity of the modeling data of the corresponding normal employee of each index to be screened is counted, and accordingly index to be screened is corresponding separated
Advise the second quantity of the modeling data of employee;Processing is grouped to the corresponding modeling data of each index to be screened;Statistics is every
Second subnumber amount of the modeling data of the first subnumber amount and violation employee of the modeling data of normal employee in group;According to described
One quantity, the second quantity, the first subnumber amount and the second subnumber amount calculate the value of information of each index to be screened;When the value of information is in
When default value interval, using the corresponding index to be screened of the value of information as evaluation index.
In one of the embodiments, described according to first quantity, the second quantity, the first subnumber amount and the second son
Quantity calculates after the value of information of each index to be screened, further includes: when the value of information is greater than the upper limit of the default value interval
When value, the corresponding modeling data of corresponding to value of information index to be screened re-starts packet transaction, and recycles execution
Second subnumber amount of the modeling data of the first subnumber amount and violation employee of the modeling data of normal employee in every group of the statistics;
The value of information of each index to be screened is calculated according to first quantity, the second quantity, the first subnumber amount and the second subnumber amount
Step, until the value of information recalculated is in the default value interval.
It is described in one of the embodiments, that violation risk model is established based on the multiple evaluation index, comprising: to obtain
Initial logic regression model;It chooses evaluation index one by one from the multiple evaluation index and the initial logic recurrence mould is added
Type;Calculate the accuracy rate that the intermediate logic regression model of new evaluation index is added;When the accuracy rate of intermediate Logic Regression Models
When less than default accuracy rate, the evaluation index being newly added is screened out;It is preset accurately when the accuracy rate of intermediate Logic Regression Models is greater than
When rate, retain the evaluation index being newly added;Violation risk model is constructed according to the evaluation index of reservation.
A kind of employee's data processing equipment, described device include: acquisition module, for obtain employee to be assessed it is a variety of to
Assess data;Obtain preset violation risk model;It include evaluation index in the violation risk model;Extraction module is used for
Achievement data corresponding with the evaluation index is extracted from a variety of data to be assessed;Input module is used for the finger
It marks data and inputs the preset violation risk model;Evaluation module is used for through the violation risk model to the index
Data are calculated, and the violation risk score of the employee to be assessed is obtained;When the violation risk score is greater than preset fraction
When, determine that the employee to be assessed is violation high risk employee.
Device in one of the embodiments, further include: modeling module is built for obtaining a variety of of normal employee respectively
The multi-modeling data of modulus evidence and violation employee;Determine the corresponding Raw performance of every kind of modeling data;According to each initial finger
Corresponding modeling data is marked, index to be screened is chosen from Raw performance;To the corresponding normal employee's of each index to be screened
Modeling data, and the modeling data of the corresponding violation employee of corresponding index to be screened carry out single factor analysis, and screening obtains multiple
Evaluation index;Violation risk model is established based on the multiple evaluation index.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes above-mentioned each employee's data processing method as described in the examples when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of above-mentioned each employee's data processing method as described in the examples is realized when row.
Above-mentioned employee's data processing method, device, computer equipment and storage medium include that assessment refers to by preset in advance
Mark violation risk model, after getting a variety of data to be assessed of employee to be assessed, can according to evaluation index from it is a variety of to
Achievement data is extracted in assessment data.Achievement data input violation risk model is calculated, obtains employee's to be assessed
Violation risk score.It can determine that whether employee to be assessed is violation high risk employee according to violation risk score.By having system
The violation risk model of one evaluation index treats assessment employee's marking, makes it possible to precisely objectively determine violation high risk person
Work.
Detailed description of the invention
Fig. 1 is the application scenario diagram of employee's data processing method in one embodiment;
Fig. 2 is the flow diagram of employee's data processing method in one embodiment;
Fig. 3 is the flow diagram of employee's data processing method in another embodiment;
Fig. 4 is the structural block diagram of employee's data processing equipment in one embodiment;
Fig. 5 is the structural block diagram of employee's data processing equipment in another embodiment;
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Employee's data processing method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, more
A terminal 102 is communicated with server 104 by network by network.Wherein, terminal 102 can be, but not limited to be various
People's computer, laptop, smart phone, tablet computer and portable wearable device, server 104 can be with independent
The server cluster of server either multiple servers composition is realized.Server 104 can obtain to be evaluated from multiple terminals 102
Estimate a variety of data to be assessed of employee.Server 104, can be from a variety of after obtaining the violation risk model comprising evaluation index
Achievement data corresponding with evaluation index is extracted in data to be assessed, and achievement data is inputted into preset violation risk model.
Server 104 calculates achievement data by violation risk model, and the violation risk point of employee to be assessed can be calculated
Number, and when violation risk score is greater than preset fraction, determine employee to be assessed for violation high risk employee.
In one embodiment, as shown in Fig. 2, providing a kind of employee's data processing method, it is applied to Fig. 1 in this way
In server 104 for be illustrated, comprising the following steps:
Step 202, a variety of data to be assessed of employee to be assessed are obtained.
Data to be assessed refer to the related data for assessing employee's violation risk to be assessed.Can obtain in preset duration to
Assess a variety of data to be assessed of employee.Data to be assessed can be the basic information and behavioural information of employee, can also be body
The data of the characteristics such as ability characteristic, mood personality, the social situation of existing employee to be assessed.
In one embodiment, basic information may include the age of employee to be assessed, gender, educational background level, marital status
Etc. one or more of them population information, may also include that the registration duration of employee to be assessed, current department, professional level be horizontal, post
The one or more of them post information such as transfer, history rewards and punishments, or can also include all kinds of assets of employee to be assessed and negative
Debt holds the assets informations such as situation.Behavioural information may include reimbursement behavior of the employee to be assessed in business system, for example submit an expense account
The amount of money, reimbursement frequency, reimbursement item etc., may also include label report to a higher authorities for approval batch, mail interception, frequency of working overtime, attendance situation etc. of checking card, or
Person may also include bank loan application, insurance purchase and Claims Resolution situation etc..The data for embodying employee's ability characteristic to be assessed can wrap
The performance situation for including employee, situation of participating in training, leading term purpose situation;The data for embodying Employees'Emotions personality to be assessed can then be come
Label record etc. is mutually commented from regularly Psychological Evaluation data and employee;The data for embodying employee's social activity situation to be assessed then may be used
Including employee's social software log duration, social software frequency of usage etc..By obtaining the data of employee's various dimensions to be assessed, energy
It is enough comprehensively to treat assessment employee's progress user's portrait.
Step 204, preset violation risk model is obtained;It include evaluation index in violation risk model.
Violation risk model refers to the assessment filtered out by the multi-modeling data based on normal employee and violation employee
The model of index building.Violation risk model can treat the violation of assessment employee according to a variety of data to be assessed of employee to be assessed
Risk is given a mark.Violation risk refers to that the risk of unlawful practice, unlawful practice occur in following a period of time for employee to be assessed
It can be expense violation, behavior violation etc..Evaluation index refers to the index that can predict violation employee.Evaluation index can be to be evaluated
Estimate index corresponding at least one of a variety of data to be assessed of employee data to be assessed.Preset violation risk model can
Storage also can be stored in other computer equipments, with server so that server can be called.
Step 206, achievement data corresponding with evaluation index is extracted from a variety of data to be assessed.
Achievement data refers to the data to be assessed of employee to be assessed corresponding with evaluation index.Such as if number to be assessed
According to including { 30 years old, male, master is married }, wherein 30 correspond to Age Indices, male corresponds to gender index, master corresponds to academic level
Index, married corresponding marital status index, when evaluation index is that gender and educational background are horizontal, then achievement data is { male, master }.
Step 208, achievement data is inputted into preset violation risk model.
Step 210, achievement data is calculated by violation risk model, obtains the violation risk point of employee to be assessed
Number.
Violation risk score refers to the numerical value for determining the violation risk of employee to be assessed.
In one embodiment, violation risk model can be calculated based on the achievement data of input, export member to be assessed
The probability value of unlawful practice occurs in following a period of time for work.Probability value can be also converted to violation risk point by violation risk model
Number.
For example, the violation risk score 60 that probability value can be converted to hundred-mark system is divided when probability value is 0.6.It can be with
Multiple value intervals are divided to probability value, and corresponding violation risk score or violation risk etc. are preset to each value interval
Grade.For example, violation risk score is 1 point when probability value is in (0,0.2) section;When probability value is in (0.2,0.4) section
When, violation risk score is 2 points;When probability value is in (0.4,0.6) section, violation risk score is 3 points;At probability value
When (0.6,0.8) section, violation risk score is 4 points;When probability value is in (0.8,1) section, violation risk score is 5
Point.
Step 212, when violation risk score is greater than preset fraction, determine employee to be assessed for violation high risk employee.
When violation risk score is greater than preset fraction, illustrates that the violation risk of the employee to be assessed is larger, then can determine that
Employee to be assessed corresponding greater than the violation risk score of preset fraction is violation high risk employee.
In one embodiment, assessment marking can be carried out by the above method to multiple employees to be assessed, according to being determined as
Violation high risk employee generates early warning list, and early warning list is sent to relevant departments and carries out pre-alarm and prevention.
In above-mentioned employee's data processing method, includes evaluation index violation risk model by preset in advance, getting
After a variety of data to be assessed of employee to be assessed, index number can be extracted from a variety of data to be assessed according to evaluation index
According to.Achievement data input violation risk model is calculated, the violation risk score of employee to be assessed is obtained.According to violation wind
Dangerous score can determine that whether employee to be assessed is violation high risk employee.By having the violation risk model of unified evaluation index
Assessment employee's marking is treated, makes it possible to precisely objectively determine violation high risk employee.
In one embodiment, before a variety of data to be assessed for obtaining employee to be assessed, further includes: obtain respectively just
The normal multi-modeling data of employee and the multi-modeling data of violation employee;Determine the corresponding Raw performance of every kind of modeling data;
According to the corresponding modeling data of each Raw performance, index to be screened is chosen from Raw performance;To each index pair to be screened
The modeling data of the normal employee answered, and the modeling data of the corresponding violation employee of corresponding index to be screened carry out single factor test point
Analysis, screening obtain multiple evaluation indexes;Violation risk model is established based on multiple evaluation indexes.
Normal employee refers to the employee that unlawful practice does not occur in preset duration, and violation employee, which refers in preset duration, to be occurred
The employee of unlawful practice.Modeling data refers to the relevant historical data of employee, for constructing violation risk model.Correspondingly, it builds
Modulus can also be the ability characteristic for embodying employee to be assessed, mood according to the basic information and behavioural information that are also possible to employee
The data of the characteristics such as personality, social situation.It can determine that every kind of modeling data is corresponding by the multi-modeling data of a large amount of employees
Raw performance.It is usually relatively more a large amount of in Raw performance, more useless index can be related to.Useless index refers to
The no index that unlawful practice occurs and influences, useless index are not used to the violation risk of prediction employee.Therefore, it is necessary first to first
Beginning index is tentatively chosen, and index to be screened is obtained.
In one embodiment, it according to the corresponding modeling data of each Raw performance, chooses from Raw performance wait sieve
Select index, comprising: count the sample size of the corresponding modeling data of each Raw performance, and the multi-modeling obtained respectively
The total number of data;The shortage of data rate of each Raw performance is calculated according to sample size and total number;Filter out data
Miss rate is lower than the intermediary outcomes of default miss rate;Clustering is carried out to each intermediary outcomes and obtains the number of each intermediary outcomes
According to abnormal rate;Data exception rate is lower than the intermediary outcomes of default abnormal rate as index to be screened.
Shortage of data rate can be calculated by the following formula: shortage of data rate=(total number-sample size)/totality number
Amount.Data exception rate can carry out point group point by the corresponding modeling data to each Raw performance such as k-means clustering algorithm
It analyses, whether there is a large amount of outliers or exceptional value in analysis modeling data distribution.By the shortage of data rate for analyzing Raw performance
With data abnormal rate, shortage of data rate height can be rejected or there are a large amount of outliers or the useless indexs of exceptional value, to obtain
The more complete index to be screened of corresponding modeling data.
In one embodiment, to the modeling data of the corresponding normal employee of each index to be screened, and it is corresponding to be screened
The modeling data of the corresponding violation employee of index carries out single factor analysis, and screening obtains multiple evaluation indexes, comprising: statistics is each
First quantity of the modeling data of the corresponding normal employee of index to be screened, and the corresponding violation employee of corresponding index to be screened
Second quantity of modeling data;Processing is grouped to the corresponding modeling data of each index to be screened;Count normal in every group
Second subnumber amount of the modeling data of the first subnumber amount and violation employee of the modeling data of employee;According to the first quantity, second
Quantity, the first subnumber amount and the second subnumber amount calculate the value of information of each index to be screened;When the value of information is in default value area
Between when, using the corresponding index to be screened of the value of information as evaluation index.
For example, the corresponding modeling data of index to be screened is grouped processing (being divided into n group).For example, treating sieve
Index " age " is selected to be grouped, 18-25,25-35,35-45,45-55,55 or more are respectively one group;For another example, to finger to be screened
Mark " reimbursement number of employee's reimbursed sum in specific sections " is grouped, and 0-10,10-20,20 or more are respectively one group.It unites respectively
Normal the first quantity of employee and the second quantity of violation employee in the corresponding whole modeling datas of index to be screened " age " are counted,
And in every group the first subnumber amount of normal employee and violation employee the second subnumber amount.
In one embodiment, formula can be passed throughIt calculates
The value of information IV of each index to be screened.Value of information IV is the sub-information value IV of each groupingiThe sum of.Wherein, #Bi is i-th point
The second subnumber amount of violation employee in group, #BT are the second quantity of expense violation employee in entirety, and #Gi is normal in the i-th grouping
The first subnumber amount of employee, #GT are the first quantity of normal employee in entirety.The value of information reflects the every of each index to be screened
Under a grouping, violation employee is to violation employee in normal employee's accounting and totality to the difference between normal employee's accounting.Pass through
Index to be screened more can targetedly portray user's portrait of expense violation employee, reduce the interference of unnecessary factor.
In one embodiment, it is calculated each according to the first quantity, the second quantity, the first subnumber amount and the second subnumber amount
After the value of information of index to be screened, further includes: when the value of information is greater than the upper limit value of default value interval, to the value of information pair
The corresponding modeling data of index to be screened answered re-starts packet transaction, and recycles and execute building for normal employee in every group of statistics
Second subnumber amount of the modeling data of the first subnumber amount and violation employee of modulus evidence;According to the first quantity, the second quantity, first
The step of subnumber amount and the second subnumber amount calculate the value of information of each index to be screened, until the value of information recalculated is in pre-
If value interval.
When the value of information is greater than the upper limit value of default value interval, illustrate that there may be grouped unbalanced special case situation to lead
The situation for causing the value of information excessively high.Therefore it needs to readjust grouping, so that grouping more freely can avoid special case situation from causing
The excessively high situation of the value of information, so that the value of information for the index to be screened that analysis obtains more is bonded actual conditions.Work as information
When value is less than the lower limit value of default value interval, illustrate that corresponding variable to be screened can not predict violation person well
Work, it is therefore desirable to reject the too low variable to be screened of corresponding informance value.It is constantly screened by treating screening index, obtains energy
It is enough in the evaluation index of prediction violation employee.
In one embodiment, decision Tree algorithms can also be promoted by gradient, calculates the feature of each index to be screened
Importance, selected characteristic index to be screened of high importance is as evaluation index.And it is straight by the evaluation index that screening obtains
Capable modeling is tapped into, violation risk model is obtained.
In one embodiment, violation risk model is established based on multiple evaluation indexes, comprising: obtain initial logic and return
Model;It chooses evaluation index one by one from multiple evaluation indexes and initial logic regression model is added;The new assessment of addition is calculated to refer to
The accuracy rate of target intermediate logic regression model;When the accuracy rate of intermediate Logic Regression Models is less than default accuracy rate, screen out
The evaluation index being newly added;When the accuracy rate of intermediate Logic Regression Models is greater than default accuracy rate, retain the assessment being newly added
Index;Violation risk model is constructed according to the evaluation index of reservation.
By stepwise regression method, evaluation index is chosen one by one, initial logic regression model is added, and be added by generating
ROC curve (the receiver operating characteristic of the intermediate logic regression model of new evaluation index
Curve, Receiver operating curve) or confusion matrix etc., obtain AUC (the Area Under of intermediate logic regression model
Curve, the area under ROC curve) value, accuracy rate, accurate rate or recall ratio, intermediate Logic Regression Models are verified.It can
Have according to the value of information and arrive small sequence greatly, initial logic regression model is added in corresponding evaluation index one by one.Work as intermediate logic
The accuracy rate of regression model is less than default accuracy rate, then illustrates that the evaluation index being newly added is not applicable, then need the new addition
Evaluation index reject;Preset accuracy rate when the accuracy rate of intermediate Logic Regression Models is greater than, then it can be by the assessment of the new addition
Index reservation is incorporated to mould.
In one embodiment, can also be modeled for each assessment variable, and by the output result of multiple models into
Row combination, obtains violation risk model.For example, initial logic regression model is obtained, shown in following formula: employee to be assessed
Probability for violation high risk employee isThe probability that then employee to be assessed is normal employee isWherein, y=1 indicates the case where employee to be assessed is high risk employee, and y=0 indicates to be evaluated
Estimate the case where employee is normal employee.Enable θTX=g (x)=β0+β1x+β2x2+...+βkxk, wherein β0For constant, β1……βk
For fitting coefficient.Employee to be assessed is that the likelihood ratio of violation high risk employee and normal employee areTo two
While taking logarithm is then linear functionAccording to the assessment of selection
The corresponding modeling data of index is fitted training to linear function, obtains the occurrence of fitting coefficient.It is obtained according to fitting
Logic Regression Models after the available fitting of occurrence.It can be by the corresponding data to be assessed of the evaluation index of employee to be assessed
It brings corresponding Logic Regression Models into, obtains the violation risk probability for the evaluation index.It is corresponding to obtain each evaluation index
Fitting after Logic Regression Models after, each Logic Regression Models can be integrated and obtain violation risk model.Violation risk mould
Type can be used for being weighted summation to the calculated probability of each Logic Regression Models, be converted to corresponding violation risk score,
The violation risk size of employee to be assessed is measured with this.Such as altogether there are four evaluation index, each evaluation index is patrolled accordingly
Collecting the calculated violation risk probability of regression model is P1, P2, P3, P4, and corresponding weight is W1, W2, W3, W4, then violation
Risk score can are as follows: Q=P1*W1+P2*W2+P3*W3+P4*W4.
In one embodiment, the ROC curve of the corresponding Logic Regression Models of each evaluation index can be drawn, is calculated each
The corresponding AUC value of ROC curve, the weight of respective logic regression model is determined according to AUC value.Logistic regression is measured according to AUC value
The accuracy rate and stability of model, so that can accurately determine each assessment in the case where considering multiple evaluation indexes and refer to
Target can refer to degree, to improve the scoring accuracy of violation risk model.
In one embodiment, as shown in figure 3, providing a kind of employee's data processing method, it is applied to Fig. 1 in this way
In server 104 for be illustrated, comprising the following steps:
Step 302, the multi-modeling data of normal employee and the multi-modeling data of violation employee are obtained respectively.
Step 304, the corresponding Raw performance of every kind of modeling data is determined.
Step 306, the sample size of the corresponding modeling data of each Raw performance is counted respectively, and is obtained a variety of
The total number of modeling data.
Step 308, the shortage of data rate of each Raw performance is calculated according to sample size and total number.
Step 310, the intermediary outcomes that shortage of data rate is lower than default miss rate are filtered out.
Step 312, clustering is carried out to each intermediary outcomes and obtains the data exception rate of each intermediary outcomes.
Step 314, data exception rate is lower than the intermediary outcomes of default abnormal rate as index to be screened.
Step 316, count the first quantity of the modeling data of the corresponding normal employee of each index to be screened, and accordingly to
Second quantity of the modeling data of the corresponding violation employee of screening index.
Step 318, processing is grouped to the corresponding modeling data of each index to be screened.
Step 320, the modeling data of the first subnumber amount and violation employee of the modeling data of normal employee in every group is counted
The second subnumber amount.
Step 322, each finger to be screened is calculated according to the first quantity, the second quantity, the first subnumber amount and the second subnumber amount
The target value of information.
Step 324, when the value of information is in default value interval, refer to the corresponding index to be screened of the value of information as assessment
Mark.
Step 326, when the value of information is greater than the upper limit value of default value interval, index to be screened corresponding to the value of information
Corresponding modeling data re-starts packet transaction.
Circulation executes step 320 and step 322, until the value of information recalculated is in default value interval.
Step 328, violation risk model is established based on multiple evaluation indexes.
Step 330, a variety of data to be assessed of employee to be assessed are obtained.
Step 332, preset violation risk model is obtained;It include evaluation index in violation risk model.
Step 334, achievement data corresponding with evaluation index is extracted from a variety of data to be assessed.
Step 336, achievement data is inputted into preset violation risk model.
Step 338, achievement data is calculated by violation risk model, obtains the violation risk point of employee to be assessed
Number.
Step 340, when violation risk score is greater than preset fraction, determine employee to be assessed for violation high risk employee.
In above-mentioned employee's data processing method, obtained by the multi-modeling data of normal employee and violation employee a variety of first
Beginning index.Shortage of data rate and the lower index to be screened of data abnormal rate are extracted from Raw performance.By to be screened
The corresponding modeling data of index is calculated, and the value of information of each index to be screened is obtained.The value of information is accurate and quantitatively reflects
The property of can refer to of index to be screened, and filter out the high evaluation index of the property of can refer to again.According in evaluation index at least
One is modeled, and violation risk model is obtained.By preset in advance include evaluation index violation risk model, get to
After a variety of data to be assessed for assessing employee, achievement data can be extracted from a variety of data to be assessed according to evaluation index.
Achievement data input violation risk model is calculated, the violation risk score of employee to be assessed is obtained.According to violation risk
Score can determine that whether employee to be assessed is violation high risk employee.By having the violation risk model pair of unified evaluation index
Employee's marking to be assessed, makes it possible to precisely objectively determine violation high risk employee.
It should be understood that although each step in the flow chart of Fig. 2 and 3 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 2 and 3 at least
A part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily in same a period of time to multiple sub-steps
Quarter executes completion, but can execute at different times, the execution in these sub-steps or stage be sequentially also not necessarily according to
Secondary progress, but in turn or can replace at least part of the sub-step or stage of other steps or other steps
Ground executes.
In one embodiment, as shown in figure 4, providing a kind of employee's data processing equipment 400, comprising: obtain module
402, for obtaining a variety of data to be assessed of employee to be assessed;Obtain preset violation risk model;In violation risk model
Include evaluation index;Extraction module 404, for extracting achievement data corresponding with evaluation index from a variety of data to be assessed;
Input module 406, for achievement data to be inputted preset violation risk model;Evaluation module 408, for passing through violation risk
Model calculates achievement data, obtains the violation risk score of employee to be assessed;When violation risk score is greater than default point
When number, determine employee to be assessed for violation high risk employee.
In one embodiment, as shown in figure 5, providing a kind of employee's data processing equipment 500, the device further include:
Modeling module 502, for obtaining the multi-modeling data of normal employee and the multi-modeling data of violation employee respectively;It determines
The corresponding Raw performance of every kind of modeling data;According to the corresponding modeling data of each Raw performance, chosen from Raw performance to
Screening index;To the modeling data of the corresponding normal employee of each index to be screened, and the corresponding violation of corresponding index to be screened
The modeling data of employee carries out single factor analysis, and screening obtains multiple evaluation indexes;Violation wind is established based on multiple evaluation indexes
Dangerous model.
In one embodiment, modeling module 502 is also used to count the corresponding modeling data of each Raw performance respectively
Sample size, and obtain multi-modeling data total number;It is calculated according to sample size and total number each first
The shortage of data rate of beginning index;Filter out the intermediary outcomes that shortage of data rate is lower than default miss rate;To each intermediary outcomes into
Row clustering obtains the data exception rate of each intermediary outcomes;The intermediary outcomes that data exception rate is lower than default abnormal rate are made
For index to be screened.
In one embodiment, modeling module 502 is also used to count building for each corresponding normal employee of index to be screened
First quantity of modulus evidence, and accordingly the second quantity of the modeling data of the corresponding violation employee of index to be screened;To it is each to
The corresponding modeling data of screening index is grouped processing;Count in every group the first subnumber amount of the modeling data of normal employee and
Second subnumber amount of the modeling data of violation employee;According to the first quantity, the second quantity, the first subnumber amount and the second subnumber meter
Calculate the value of information of each index to be screened;When the value of information is in default value interval, by the corresponding index to be screened of the value of information
As evaluation index.
In one embodiment, modeling module 502 is also used to when the value of information is greater than the upper limit value of default value interval,
The corresponding modeling data of corresponding to value of information index to be screened re-starts packet transaction, and recycles in every group of execution statistics just
Second subnumber amount of the modeling data of the first subnumber amount and violation employee of the modeling data of normal employee;According to the first quantity,
The step of two quantity, the first subnumber amount and the second subnumber amount calculate the value of information of each index to be screened, until recalculate
The value of information is in default value interval.
In one embodiment, modeling module 502 is also used to obtain initial logic regression model;From multiple evaluation indexes
Evaluation index is chosen one by one, and initial logic regression model is added;Calculate the intermediate logic regression model that new evaluation index is added
Accuracy rate;When the accuracy rate of intermediate Logic Regression Models is less than default accuracy rate, the evaluation index being newly added is screened out;Work as centre
When the accuracy rate of Logic Regression Models is greater than default accuracy rate, retain the evaluation index being newly added;According to the evaluation index of reservation
Construct violation risk model.
Specific about employee's data processing equipment limits the limit that may refer to above for employee's data processing method
Fixed, details are not described herein.Modules in above-mentioned employee's data processing equipment can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing violation risk model.The network interface of the computer equipment is used to pass through with external terminal
Network connection communication.To realize a kind of employee's data processing method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of a variety of numbers to be assessed for obtaining employee to be assessed when executing computer program
According to;Obtain preset violation risk model;It include evaluation index in violation risk model;From a variety of data to be assessed extract with
The corresponding achievement data of evaluation index;Achievement data is inputted into preset violation risk model;By violation risk model to finger
Mark data are calculated, and the violation risk score of employee to be assessed is obtained;When violation risk score is greater than preset fraction, determine
Employee to be assessed is violation high risk employee.
In one embodiment, when processor executes computer program, in a variety of of the acquisition employee to be assessed realized
It is further comprising the steps of before the step of data to be assessed: to obtain multi-modeling data and the violation employee of normal employee respectively
Multi-modeling data;Determine the corresponding Raw performance of every kind of modeling data;According to the corresponding modeling data of each Raw performance,
Index to be screened is chosen from Raw performance;To the modeling data of the corresponding normal employee of each index to be screened, and accordingly to
The modeling data of the corresponding violation employee of screening index carries out single factor analysis, and screening obtains multiple evaluation indexes;Based on multiple
Evaluation index establishes violation risk model.
In one embodiment, when processor executes computer program, the correspondence according to each Raw performance realized
Modeling data, the step of index to be screened is chosen from Raw performance, comprising the following steps: count each Raw performance respectively
Corresponding modeling data sample size, and obtain multi-modeling data total number;According to sample size and always
Body quantity calculates the shortage of data rate of each Raw performance;Filter out the intermediary outcomes that shortage of data rate is lower than default miss rate;
Clustering is carried out to each intermediary outcomes and obtains the data exception rate of each intermediary outcomes;Data exception rate is different lower than presetting
The intermediary outcomes of normal rate are as index to be screened.
In one embodiment, when processor executes computer program, that is realized is corresponding to each index to be screened
The modeling data of normal employee, and the modeling data of the corresponding violation employee of corresponding index to be screened carry out single factor analysis, sieve
The step of choosing obtains multiple evaluation indexes, comprising the following steps: count the modeling of the corresponding normal employee of each index to be screened
First quantity of data, and accordingly the second quantity of the modeling data of the corresponding violation employee of index to be screened;To each wait sieve
The corresponding modeling data of index is selected to be grouped processing;It counts the first subnumber amount of the modeling data of normal employee in every group and disobeys
Advise the second subnumber amount of the modeling data of employee;It is calculated according to the first quantity, the second quantity, the first subnumber amount and the second subnumber amount
The value of information of each index to be screened;When the value of information is in default value interval, the corresponding index to be screened of the value of information is made
For evaluation index.
In one embodiment, it when processor executes computer program, is being realized according to the first quantity, the second number
It is further comprising the steps of after the step of amount, the first subnumber amount and the second subnumber amount calculate the value of information of each index to be screened:
When the value of information is greater than the upper limit value of default value interval, the corresponding modeling data weight of corresponding to value of information index to be screened
It newly is grouped processing, and recycles and executes the first subnumber amount of the modeling data of normal employee and violation employee in every group of statistics
Second subnumber amount of modeling data;It is calculated according to the first quantity, the second quantity, the first subnumber amount and the second subnumber amount each wait sieve
The step of selecting the value of information of index, until the value of information recalculated is in default value interval.
In one embodiment, when processor executes computer program, being established based on multiple evaluation indexes for being realized is disobeyed
The step of advising risk model, comprising the following steps: obtain initial logic regression model;It chooses and comments one by one from multiple evaluation indexes
Estimate index and initial logic regression model is added;Calculate the accuracy rate that the intermediate logic regression model of new evaluation index is added;When
When the accuracy rate of intermediate logic regression model is less than default accuracy rate, the evaluation index being newly added is screened out;When intermediate logistic regression
When the accuracy rate of model is greater than default accuracy rate, retain the evaluation index being newly added;It is constructed in violation of rules and regulations according to the evaluation index of reservation
Risk model.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of a variety of data to be assessed for obtaining employee to be assessed when being executed by processor;Obtain preset disobey
Advise risk model;It include evaluation index in violation risk model;It is extracted from a variety of data to be assessed corresponding with evaluation index
Achievement data;Achievement data is inputted into preset violation risk model;Achievement data is calculated by violation risk model,
Obtain the violation risk score of employee to be assessed;When violation risk score is greater than preset fraction, determine that employee to be assessed is separated
Advise high risk employee.
In one embodiment, when computer program is executed by processor, in the more of the acquisition employee to be assessed realized
It is further comprising the steps of: to obtain multi-modeling data and the violation person of normal employee respectively before the step of kind data to be assessed
The multi-modeling data of work;Determine the corresponding Raw performance of every kind of modeling data;According to the corresponding modeling number of each Raw performance
According to choosing index to be screened from Raw performance;To the modeling data of the corresponding normal employee of each index to be screened, and it is corresponding
The modeling data of the corresponding violation employee of index to be screened carries out single factor analysis, and screening obtains multiple evaluation indexes;Based on more
A evaluation index establishes violation risk model.
In one embodiment, when computer program is executed by processor, pair according to each Raw performance realized
The modeling data answered, the step of index to be screened is chosen from Raw performance, comprising the following steps: each initially finger of statistics respectively
The sample size of the corresponding modeling data of target, and obtain multi-modeling data total number;According to sample size and
Total number calculates the shortage of data rate of each Raw performance;The centre that shortage of data rate is filtered out lower than default miss rate refers to
Mark;Clustering is carried out to each intermediary outcomes and obtains the data exception rate of each intermediary outcomes;By data exception rate lower than pre-
If the intermediary outcomes of abnormal rate are as index to be screened.
In one embodiment, when computer program is executed by processor, that is realized is corresponding to each index to be screened
Normal employee modeling data, and the modeling data of the corresponding violation employee of corresponding index to be screened carries out single factor analysis,
The step of screening obtains multiple evaluation indexes, comprising the following steps: count building for each corresponding normal employee of index to be screened
First quantity of modulus evidence, and accordingly the second quantity of the modeling data of the corresponding violation employee of index to be screened;To it is each to
The corresponding modeling data of screening index is grouped processing;Count in every group the first subnumber amount of the modeling data of normal employee and
Second subnumber amount of the modeling data of violation employee;According to the first quantity, the second quantity, the first subnumber amount and the second subnumber meter
Calculate the value of information of each index to be screened;When the value of information is in default value interval, by the corresponding index to be screened of the value of information
As evaluation index.
In one embodiment, it when computer program is executed by processor, is being realized according to the first quantity, the second number
It is further comprising the steps of after the step of amount, the first subnumber amount and the second subnumber amount calculate the value of information of each index to be screened:
When the value of information is greater than the upper limit value of default value interval, the corresponding modeling data weight of corresponding to value of information index to be screened
It newly is grouped processing, and recycles and executes the first subnumber amount of the modeling data of normal employee and violation employee in every group of statistics
Second subnumber amount of modeling data;It is calculated according to the first quantity, the second quantity, the first subnumber amount and the second subnumber amount each wait sieve
The step of selecting the value of information of index, until the value of information recalculated is in default value interval.
In one embodiment, when computer program is executed by processor, that is realized is established based on multiple evaluation indexes
The step of violation risk model, comprising the following steps: obtain initial logic regression model;It is chosen one by one from multiple evaluation indexes
Initial logic regression model is added in evaluation index;Calculate the accuracy rate that the intermediate logic regression model of new evaluation index is added;
When the accuracy rate of intermediate Logic Regression Models is less than default accuracy rate, the evaluation index being newly added is screened out;When intermediate logic is returned
When the accuracy rate of model being returned to be greater than default accuracy rate, retain the evaluation index being newly added;It is disobeyed according to the building of the evaluation index of reservation
Advise risk model.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of employee's data processing method, which comprises
Obtain a variety of data to be assessed of employee to be assessed;
Obtain preset violation risk model;It include evaluation index in the violation risk model;
Achievement data corresponding with the evaluation index is extracted from a variety of data to be assessed;
The achievement data is inputted into the preset violation risk model;
The achievement data is calculated by the violation risk model, obtains the violation risk point of the employee to be assessed
Number;
When the violation risk score is greater than preset fraction, determine that the employee to be assessed is violation high risk employee.
2. the method according to claim 1, wherein in a variety of data to be assessed for obtaining employee to be assessed
Before, further includes:
The multi-modeling data of normal employee and the multi-modeling data of violation employee are obtained respectively;
Determine the corresponding Raw performance of every kind of modeling data;
According to the corresponding modeling data of each Raw performance, index to be screened is chosen from Raw performance;
To the modeling data of the corresponding normal employee of each index to be screened, and the corresponding violation employee of corresponding index to be screened
Modeling data carries out single factor analysis, and screening obtains multiple evaluation indexes;
Violation risk model is established based on the multiple evaluation index.
3. according to the method described in claim 2, it is characterized in that, the corresponding modeling number according to each Raw performance
According to choosing index to be screened from Raw performance, comprising:
The sample size of the corresponding modeling data of each Raw performance, and the multi-modeling data obtained are counted respectively
Total number;
The shortage of data rate of each Raw performance is calculated according to the sample size and the total number;
Filter out the intermediary outcomes that the shortage of data rate is lower than default miss rate;
Clustering is carried out to each intermediary outcomes and obtains the data exception rate of each intermediary outcomes;
The data exception rate is lower than the intermediary outcomes of default abnormal rate as index to be screened.
4. according to the method described in claim 2, it is characterized in that, described to the corresponding normal employee's of each index to be screened
Modeling data, and the modeling data of the corresponding violation employee of corresponding index to be screened carry out single factor analysis, and screening obtains multiple
Evaluation index, comprising:
The first quantity of the modeling data of the corresponding normal employee of each index to be screened is counted, and corresponding index to be screened corresponds to
Violation employee modeling data the second quantity;
Processing is grouped to the corresponding modeling data of each index to be screened;
Count the second subnumber amount of the modeling data of the first subnumber amount and violation employee of the modeling data of normal employee in every group;
The information of each index to be screened is calculated according to first quantity, the second quantity, the first subnumber amount and the second subnumber amount
Value;
When the value of information is in default value interval, using the corresponding index to be screened of the value of information as evaluation index.
5. according to the method described in claim 4, it is characterized in that, described according to first quantity, the second quantity, first
Subnumber amount and the second subnumber amount calculate after the value of information of each index to be screened, further includes:
When the value of information is greater than the upper limit value of the default value interval, index to be screened corresponding to the value of information is corresponding
Modeling data re-start packet transaction, and recycle the first son for executing the modeling data of normal employee in every group of the statistics
Second subnumber amount of the modeling data of quantity and violation employee;According to first quantity, the second quantity, the first subnumber amount and
Two subnumber amounts calculate the step of value of information of each index to be screened, until the value of information recalculated is in the default value
Section.
6. according to the method described in claim 2, it is characterized in that, described establish violation risk based on the multiple evaluation index
Model, comprising:
Obtain initial logic regression model;
It chooses evaluation index one by one from the multiple evaluation index and the initial logic regression model is added;
Calculate the accuracy rate that the intermediate logic regression model of new evaluation index is added;
When the accuracy rate of intermediate Logic Regression Models is less than default accuracy rate, the evaluation index being newly added is screened out;
When the accuracy rate of intermediate Logic Regression Models is greater than default accuracy rate, retain the evaluation index being newly added;
Violation risk model is constructed according to the evaluation index of reservation.
7. a kind of employee's data processing equipment, which is characterized in that described device includes:
Module is obtained, for obtaining a variety of data to be assessed of employee to be assessed;Obtain preset violation risk model;It is described to disobey
Advising includes evaluation index in risk model;
Extraction module, for extracting achievement data corresponding with the evaluation index from a variety of data to be assessed;
Input module, for the achievement data to be inputted the preset violation risk model;
Evaluation module obtains the member to be assessed for calculating by the violation risk model the achievement data
The violation risk score of work;When the violation risk score is greater than preset fraction, determine that the employee to be assessed is high in violation of rules and regulations
Risk employee.
8. device according to claim 7, which is characterized in that the device further include: modeling module, for obtaining respectively just
The normal multi-modeling data of employee and the multi-modeling data of violation employee;Determine the corresponding Raw performance of every kind of modeling data;
According to the corresponding modeling data of each Raw performance, index to be screened is chosen from Raw performance;To each index pair to be screened
The modeling data of the normal employee answered, and the modeling data of the corresponding violation employee of corresponding index to be screened carry out single factor test point
Analysis, screening obtain multiple evaluation indexes;Violation risk model is established based on the multiple evaluation index.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910073369.8A CN109615280A (en) | 2019-01-25 | 2019-01-25 | Employee's data processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910073369.8A CN109615280A (en) | 2019-01-25 | 2019-01-25 | Employee's data processing method, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109615280A true CN109615280A (en) | 2019-04-12 |
Family
ID=66018349
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910073369.8A Pending CN109615280A (en) | 2019-01-25 | 2019-01-25 | Employee's data processing method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109615280A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110378560A (en) * | 2019-06-14 | 2019-10-25 | 平安科技(深圳)有限公司 | Arbitrator's data screening method, apparatus, computer equipment and storage medium |
CN110443458A (en) * | 2019-07-05 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
CN110675017A (en) * | 2019-08-13 | 2020-01-10 | 平安科技(深圳)有限公司 | Performance evaluation method and device based on artificial intelligence |
CN111144690A (en) * | 2019-11-26 | 2020-05-12 | 泰康保险集团股份有限公司 | Target object evaluation system and target object evaluation method |
CN111754044A (en) * | 2020-06-30 | 2020-10-09 | 深圳前海微众银行股份有限公司 | Employee behavior auditing method, device, equipment and readable storage medium |
CN112418738A (en) * | 2020-12-17 | 2021-02-26 | 泸州银行股份有限公司 | Staff operation risk prediction method based on logistic regression |
CN113095365A (en) * | 2021-03-15 | 2021-07-09 | 北京大学 | Medical insurance violation data identification method and device |
CN113780804A (en) * | 2021-09-09 | 2021-12-10 | 平安科技(深圳)有限公司 | Employee behavior risk prediction method and device based on data analysis and storage medium |
-
2019
- 2019-01-25 CN CN201910073369.8A patent/CN109615280A/en active Pending
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110378560A (en) * | 2019-06-14 | 2019-10-25 | 平安科技(深圳)有限公司 | Arbitrator's data screening method, apparatus, computer equipment and storage medium |
CN110378560B (en) * | 2019-06-14 | 2023-06-23 | 平安科技(深圳)有限公司 | Method, device, computer equipment and storage medium for filtering data of arbitrator |
CN110443458A (en) * | 2019-07-05 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
CN110675017A (en) * | 2019-08-13 | 2020-01-10 | 平安科技(深圳)有限公司 | Performance evaluation method and device based on artificial intelligence |
CN111144690A (en) * | 2019-11-26 | 2020-05-12 | 泰康保险集团股份有限公司 | Target object evaluation system and target object evaluation method |
CN111754044A (en) * | 2020-06-30 | 2020-10-09 | 深圳前海微众银行股份有限公司 | Employee behavior auditing method, device, equipment and readable storage medium |
CN111754044B (en) * | 2020-06-30 | 2024-04-30 | 深圳前海微众银行股份有限公司 | Employee behavior auditing method, device, equipment and readable storage medium |
CN112418738A (en) * | 2020-12-17 | 2021-02-26 | 泸州银行股份有限公司 | Staff operation risk prediction method based on logistic regression |
CN113095365A (en) * | 2021-03-15 | 2021-07-09 | 北京大学 | Medical insurance violation data identification method and device |
CN113780804A (en) * | 2021-09-09 | 2021-12-10 | 平安科技(深圳)有限公司 | Employee behavior risk prediction method and device based on data analysis and storage medium |
CN113780804B (en) * | 2021-09-09 | 2024-03-12 | 平安科技(深圳)有限公司 | Employee behavior risk prediction method and device based on data analysis and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109615280A (en) | Employee's data processing method, device, computer equipment and storage medium | |
WO2020143233A1 (en) | Method and device for building scorecard model, computer apparatus and storage medium | |
CN110246031A (en) | Appraisal procedure, system, equipment and the storage medium of business standing | |
CN109146662A (en) | A kind of risk control method and device | |
US20050080821A1 (en) | System and method for managing collections accounts | |
JP2012150788A (en) | System and method for prediction of frequency related to loss in future and related automatic processing of loss determination unit | |
CN106875270A (en) | A kind of method and system design for building and verifying credit scoring equation | |
CN109949154A (en) | Customer information classification method, device, computer equipment and storage medium | |
CN109583682A (en) | Recognition methods, device and the computer equipment of business finance fraud risk | |
CN110276677A (en) | Refund prediction technique, device, equipment and storage medium based on big data platform | |
CN109508807A (en) | Lottery user liveness prediction technique, system and terminal device, storage medium | |
CN112990989B (en) | Value prediction model input data generation method, device, equipment and medium | |
CN111061948A (en) | User label recommendation method and device, computer equipment and storage medium | |
CN114493686A (en) | Operation content generation and pushing method and device | |
CN112766814A (en) | Training method, device and equipment for credit risk pressure test model | |
CN112508689A (en) | Method for realizing decision evaluation based on multiple dimensions | |
Al-Halabi et al. | The impact of designing accounting information systems on the level of accounting conservatism-a field study | |
US10699335B2 (en) | Apparatus and method for total loss prediction | |
CN113450010A (en) | Method and device for determining evaluation result of data object and server | |
CN114612239A (en) | Stock public opinion monitoring and wind control system based on algorithm, big data and artificial intelligence | |
Ocal et al. | Corporate ratings and a model proposition for the manufacturing industry at Borsa Istanbul | |
CN110570301A (en) | Risk identification method, device, equipment and medium | |
KR102669893B1 (en) | Automatic calculation system for profit and loss by IT project using smart work log | |
Menvouta et al. | mCube: Multinomial Micro-level reserving Model | |
Benavente-Peces et al. | Applied Data Analytics |
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 |