CN110414806A - Employee's method for prewarning risk and relevant apparatus - Google Patents
Employee's method for prewarning risk and relevant apparatus Download PDFInfo
- Publication number
- CN110414806A CN110414806A CN201910618947.1A CN201910618947A CN110414806A CN 110414806 A CN110414806 A CN 110414806A CN 201910618947 A CN201910618947 A CN 201910618947A CN 110414806 A CN110414806 A CN 110414806A
- Authority
- CN
- China
- Prior art keywords
- risk
- employee
- data
- mentioned
- information
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000003542 behavioural effect Effects 0.000 claims abstract description 185
- 230000006399 behavior Effects 0.000 claims description 271
- 238000012545 processing Methods 0.000 claims description 20
- 241001269238 Data Species 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 8
- 238000007405 data analysis Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (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
The embodiment of the invention discloses a kind of employee's method for prewarning risk and relevant apparatus, this method is suitable for risk management and control.This method comprises: obtaining the behavioral data for recording any employee's image from employee database；Whether behavioral data, which is risk behavior data, is determined to information aggregate based on Hazard ratio；When determining that behavioral data is risk behavior data to any risk comparison information in information aggregate based on Hazard ratio, determine the corresponding type label of any risk comparison information, the corresponding employee's type of type label is determined as to employee's type of the corresponding employee of behavioral data, and the corresponding employee of behavioral data is determined as risk employee；Determine the risk class of risk employee；Warning information is generated, and warning information is sent to Risk-warning platform to carry out Risk-warning to risk employee.Using the embodiment of the present invention, the risk behavior data of risk employee and risk employee can accurately being determined, Risk-warning being carried out to the risk employee determined, applicability is high.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of employee's method for prewarning risk and relevant apparatus.
Background technique
With constantly improve for enterprise staff management system, various enterprises can all pass through the Staffing System of enterprises
Stakeholder Evaluation work is carried out, to filter out the risk employee there are risk behavior and make corresponding pre-alarm and prevention.In tradition side
In formula, the general method combined using artificial and machine, by tentatively being sieved to employee's data in Staffing System
Choosing, then based on artificial sampling, the mode of artificial cognition or personal experience based on early warning personnel from Staffing System really
Make risk employee.
However, the determination of risk employee has stronger subjectivity and unstability in above-mentioned traditional approach, can not yet
It completes to carry out risk judgment to all employees in Staffing System, cause to be difficult to accurately and comprehensively from Staffing System
In determine risk employee.
Summary of the invention
The embodiment of the present invention provides a kind of employee's method for prewarning risk and relevant apparatus, can accurately determine risk employee and
The risk behavior data of risk employee can carry out Risk-warning to the risk employee determined in time, and applicability is high.
In a first aspect, the embodiment of the present invention provides a kind of employee's method for prewarning risk, this method comprises:
The behavioral data for recording any employee's image is obtained from employee database；
Whether above-mentioned behavioral data, which is risk behavior data, is determined to information aggregate based on Hazard ratio；
When based on above-mentioned Hazard ratio to any risk comparison information in information aggregate determine above-mentioned behavioral data be risk
When behavioral data, the corresponding type label of any of the above-described risk comparison information is determined, by the corresponding employee of the above-mentioned type label
Type is determined as employee's type of the corresponding employee of above-mentioned behavioral data, and the corresponding employee of above-mentioned behavioral data is determined as wind
Dangerous employee；
The risk information of above-mentioned behavioral data is obtained, and determines the risk of above-mentioned risk employee based on above-mentioned risk information
Grade；
Warning information is generated based on above-mentioned employee's type, above-mentioned behavioral data and above-mentioned risk class, and will be above-mentioned pre-
Alert information is sent to Risk-warning platform to carry out Risk-warning to above-mentioned risk employee.
With reference to first aspect, in a kind of possible embodiment, above-mentioned obtain from employee database records any member
Before the behavioral data that industrial and commercial bank is, the above method further include:
The risk behavior sample data of the risk employee of at least two employee's types is obtained from employee database, wherein
A kind of corresponding at least two risk behavior sample datas of the risk employee of employee's type, a kind of risk behavior sample data is for remembering
Record a kind of risk behavior；
The risk behavior sample data of risk employee based on above-mentioned at least two employees type constructs risk comparison information
Set.
With reference to first aspect, above-mentioned that at least two members are obtained from employee database in a kind of possible embodiment
The risk behavior sample data of the risk employee of work type includes:
The risk employee of at least two employee's types is determined from employee database；
The risk behavior data of the risk employee of various employee's types are inputted into default nonlinear model, based on above-mentioned default
Nonlinear model obtains the confidence level of various risk behavior data；
Risk behavior data of the confidence level in default confidence interval are determined as risk behavior sample data, to obtain
The risk behavior sample data of the risk employee of above-mentioned at least two employees type.
With reference to first aspect, in a kind of possible embodiment, the above-mentioned wind based on above-mentioned at least two employees type
The risk behavior sample data of dangerous employee constructs Hazard ratio
The corresponding class of above-mentioned every kind of employee type is determined based on the corresponding risk behavior sample data of every kind of employee's type
Type label；
The risk behavior sample data of the risk employee of above-mentioned at least two employees type is subjected to data format processing, with
Obtain the risk behavior sample data with preset data form；
Risk behavior sample number based on the corresponding type label of above-mentioned every kind of employee type and with preset data form
According to one risk comparison information of building to obtain the Hazard ratio including at least two risk comparison informations to information aggregate；
Wherein, above-mentioned Hazard ratio is used to determine the one of a kind of employee's type to a risk comparison information in information aggregate
Whether kind behavioral data is risk behavior data.
With reference to first aspect, in a kind of possible embodiment, above-mentioned risk information includes behavioural characteristic value and/or wind
Dangerous behavioural characteristic word；The risk information of the above-mentioned above-mentioned behavioral data of acquisition, and above-mentioned risk is determined based on above-mentioned risk information
The risk class of employee includes:
The behavioural characteristic value for determining above-mentioned behavioral data is determined based on above-mentioned behavioural characteristic value and default risk class tablet
The risk class of above-mentioned risk employee；And/or
Data parsing is carried out so that above-mentioned behavioral data is converted to risk behavior text to above-mentioned risk behavior data；
Semantics recognition is carried out to determine above-mentioned risk employee from above-mentioned risk behavior text to above-mentioned risk behavior text
Risk behavior Feature Words；
The risk class of above-mentioned risk employee is determined based on above-mentioned risk behavior Feature Words and default risk keywords database.
With reference to first aspect, above-mentioned to be based on above-mentioned employee's type, above-mentioned behavioral data in a kind of possible embodiment
And above-mentioned risk class generates warning information, and above-mentioned warning information is sent to Risk-warning platform to above-mentioned risk person
Work carries out Risk-warning
The employee information of above-mentioned risk employee is obtained from above-mentioned employee database；
Determine whether above-mentioned risk class is greater than default risk class；
If above-mentioned risk class is greater than default risk class, determined based on the employee's image that above-mentioned behavioral data is recorded
The corresponding Forewarning Measures of above-mentioned risk employee out will be default pre- if above-mentioned risk class is not more than above-mentioned default risk class
Alert measure is determined as the corresponding Forewarning Measures of above-mentioned risk employee；
Warning information is generated based on above-mentioned employee information, employee's type and above-mentioned Forewarning Measures and by above-mentioned warning information
It is sent to Risk-warning platform, so that above-mentioned Risk-warning platform shows the employee information and employee's type of above-mentioned risk employee,
And Risk-warning is carried out to above-mentioned risk employee based on the Forewarning Measures in above-mentioned warning information.
Second aspect, the embodiment of the invention provides a kind of employee's Risk-warning device, employee's Risk-warning device packets
It includes:
Acquiring unit, for obtaining the behavioral data for recording any employee's image from employee database；
Judging unit, for determining whether above-mentioned behavioral data is risk behavior data to information aggregate based on Hazard ratio；
Determination unit determines above-mentioned row to any risk comparison information in information aggregate based on above-mentioned Hazard ratio for working as
When for data being risk behavior data, the corresponding type label of any of the above-described risk comparison information is determined, by the above-mentioned type mark
Employee's type that corresponding employee's type is determined as the corresponding employee of above-mentioned behavioral data is signed, and above-mentioned behavioral data is corresponding
Employee is determined as risk employee；
Above-mentioned determination unit is determined for obtaining the risk information of above-mentioned behavioral data, and based on above-mentioned risk information
The risk class of above-mentioned risk employee；
Prewarning unit, for generating early warning letter based on above-mentioned employee's type, above-mentioned behavioral data and above-mentioned risk class
Breath, and above-mentioned warning information is sent to Risk-warning platform to carry out Risk-warning to above-mentioned risk employee.
In conjunction with second aspect, in a kind of possible embodiment, above-mentioned acquiring unit is also used to:
The risk behavior sample data of the risk employee of at least two employee's types is obtained from employee database, wherein
A kind of corresponding at least two risk behavior sample datas of the risk employee of employee's type, a kind of risk behavior sample data is for remembering
Record a kind of risk behavior；
Above-mentioned employee's Risk-warning device further include:
Construction unit is also used to the risk behavior sample data structure of the risk employee based on above-mentioned at least two employees type
Hazard ratio is built to information aggregate.
In conjunction with second aspect, in a kind of possible embodiment, above-mentioned determination unit is used for:
The risk employee of at least two employee's types is determined from employee database；
The risk behavior data of the risk employee of various employee's types are inputted into default nonlinear model, based on above-mentioned default
Nonlinear model obtains the confidence level of various risk behavior data；
Risk behavior data of the confidence level in default confidence interval are determined as risk behavior sample data, to obtain
The risk behavior sample data of the risk employee of above-mentioned at least two employees type.
In conjunction with second aspect, in a kind of possible embodiment, above-mentioned determination unit is used for:
The corresponding class of above-mentioned every kind of employee type is determined based on the corresponding risk behavior sample data of every kind of employee's type
Type label；
Above-mentioned employee's Risk-warning device includes: processing unit, for by the risk person of above-mentioned at least two employees type
The risk behavior sample data of work carries out data format processing, to obtain the risk behavior sample number with preset data form
According to；
Above-mentioned construction unit, for based on the corresponding type label of above-mentioned every kind of employee type and with preset data form
Risk behavior sample data construct a risk comparison information to obtain the Hazard ratio including at least two risk comparison informations
To information aggregate；
Wherein, above-mentioned Hazard ratio is used to determine the one of a kind of employee's type to a risk comparison information in information aggregate
Whether kind behavioral data is risk behavior data.
In conjunction with second aspect, in a kind of possible embodiment, above-mentioned risk information includes behavioural characteristic value and/or wind
Dangerous behavioural characteristic word；Above-mentioned determination unit is used for:
The behavioural characteristic value for determining above-mentioned behavioral data is determined based on above-mentioned behavioural characteristic value and default risk class tablet
The risk class of above-mentioned risk employee；
Above-mentioned processing unit, for carrying out data parsing to above-mentioned risk behavior data to be converted to above-mentioned behavioral data
Risk behavior text；
Above-mentioned processing unit, for carrying out semantics recognition from above-mentioned risk behavior text to above-mentioned risk behavior text
Determine the risk behavior Feature Words of above-mentioned risk employee；
Above-mentioned determination unit, for determining above-mentioned wind based on above-mentioned risk behavior Feature Words and default risk keywords database
The risk class of dangerous employee.
In conjunction with second aspect, in a kind of possible embodiment, above-mentioned acquiring unit is used for:
The employee information of above-mentioned risk employee is obtained from above-mentioned employee database；
Above-mentioned judging unit, for determining whether above-mentioned risk class is greater than default risk class；
Above-mentioned determination unit, for being based on above-mentioned behavioral data institute when above-mentioned risk class is greater than default risk class
The employee's image of record determines the corresponding Forewarning Measures of above-mentioned risk employee, when above-mentioned risk class is not more than above-mentioned default wind
When dangerous grade, default Forewarning Measures are determined as the corresponding Forewarning Measures of above-mentioned risk employee；
Above-mentioned prewarning unit, for generating early warning letter based on above-mentioned employee information, employee's type and above-mentioned Forewarning Measures
It ceases and above-mentioned warning information is sent to Risk-warning platform, so that above-mentioned Risk-warning platform shows the member of above-mentioned risk employee
Work information and employee's type, and Risk-warning is carried out to above-mentioned risk employee based on the Forewarning Measures in above-mentioned warning information.
The third aspect, the embodiment of the invention provides a kind of terminal, which includes processor and memory, the processor
It is connected with each other with memory.The memory supports that the terminal executes above-mentioned first aspect and/or first aspect is any for storing
The computer program for the method that the possible implementation of kind provides, which includes program instruction, which is matched
It sets for calling above procedure to instruct, executes above-mentioned first aspect and/or any possible embodiment of first aspect is mentioned
The method of confession.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storage mediums
Matter is stored with computer program, which is executed by processor to realize that above-mentioned first aspect and/or first aspect are appointed
A kind of method provided by possible embodiment.
In embodiments of the present invention, it can determine that the row of any employee in employee database to information aggregate based on Hazard ratio
It whether is risk behavior data for data, and then the case where the behavioral data for determining any of the above-described employee is risk behavior data
Under, determine the information such as the employee's type, employee information, risk class of risk employee and risk employee.Based on above-mentioned realization
Mode, it can be achieved that be measured in real time to whole behavioral datas in employee database, determine in time risk behavior data with
Risk employee.Meanwhile it being determined based on much informations such as employee's type, employee information and the risk class of risk employee corresponding
Forewarning Measures simultaneously indicate that Risk-warning platform carries out Risk-warning to risk employee, avoid due to manual operation or it is subjective because
Early warning inaccuracy situation caused by element, flexibility is good, and applicability is high.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the method flow diagram of employee's Risk-warning provided in an embodiment of the present invention；
Fig. 2 is method flow diagram of the building Hazard ratio provided in an embodiment of the present invention to information aggregate；
Fig. 3 is the structural schematic diagram of employee's Risk-warning device provided in an embodiment of the present invention；
Fig. 4 is the structural schematic diagram of terminal provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
(description for convenience, can the offer of the abbreviation embodiment of the present invention for employee's method for prewarning risk provided in an embodiment of the present invention
Method) be applicable to every field, in each enterprise staff management system in various industries, such as bank clerk manages system
System, employee's image analysis system etc., herein with no restrictions.Method provided in an embodiment of the present invention can be to enterprise staff management system
In employee's image data carry out real-time monitoring, can determine risk behavior data and the corresponding wind of risk behavior data in time
Dangerous employee, and then Risk-warning is made to risk employee, flexibility is high, applied widely.It, below can be a certain for convenience of description
For any Staffing System of a field and/or some Target Enterprise in some industry, in conjunction with Fig. 1 to Fig. 4 point
It is other that method provided in an embodiment of the present invention and relevant apparatus are illustrated.
It is the flow diagram of employee's method for prewarning risk provided in an embodiment of the present invention referring to Fig. 1, Fig. 1.The present invention is real
The method for applying example offer may include following steps S11-S16:
S11, behavioral data for recording any employee's image is obtained from employee database.
In some possible embodiments, can all behavioral datas to all employees in Staffing System into
Row monitoring.For each behavioral data, it can obtain from the employee database in Staffing System and appoint for recording
The behavioral data of one employee's image.Wherein, above-mentioned employee database can be employee's data acquisition system that Staffing System defines,
The memory space for being also possible to the behavioral data for storing enterprise staff generation connecting with Staffing System is (mobile hard
Disk, cloud storage etc.) etc., herein with no restrictions.The data type of the behavioral data of each employee in above-mentioned employee database, number
Herein with no restrictions according to size and data format etc..It should be strongly noted that being not only stored in above-mentioned employee database
The behavioral data of employee is also stored with the non-behavioral data (such as identity data, attendance data) of employee.Therefore, from employee
When obtaining the behavioral data for recording any employee's image in database, the modes such as need to handle by big data analysis from member
Screen and obtain the corresponding behavioral data of any employee in work database, specific data screening mode is herein with no restrictions.
S12, whether above-mentioned behavioral data, which is risk behavior data, is determined to information aggregate based on Hazard ratio.
After getting the behavioral data for recording any employee's image, information aggregate can be determined based on Hazard ratio
Whether above-mentioned behavioral data is risk behavior data.Wherein, above-mentioned Hazard ratio can be before obtaining behavioral data to information aggregate
It is constructed.As shown in Fig. 2, Fig. 2 is method flow diagram of the building Hazard ratio provided in an embodiment of the present invention to information aggregate, this
The building Hazard ratio that inventive embodiments provide includes the following steps S21-S24 to the method for information aggregate:
S21, obtained from employee database at least two employee's types risk employee risk behavior sample data.
In some possible embodiments, the risk of at least two employee's types can be first determined from employee database
Risk behavior sample data is obtained in employee, then the kinds of risks data of the risk employee from least two employee's types.Wherein,
A kind of employee's type can correspond to multiple risk employees, the corresponding at least two risk sample datas of a risk employee, a kind of risk
Behavioral data is for recording a kind of risk behavior.Due to that may remember in the risk behavior data of the risk employee in employee database
The risk behavior data of risk behavior weaker risk behavior data or deposit data inaccuracy are recorded, therefore can be to employee's data
The risk behavior data of the risk employee of at least two employee's types are screened in library.It wherein, can be by various employee's types
The risk behavior data of risk employee input in preset nonlinear model, to calculate every kind of risk behavior based on nonlinear model
The confidence level of data.Whether the confidence level of above-mentioned risk behavior data is used to indicate the credibility of the risk behavior data, i.e.,
For the data of the risk behavior of record risk employee.When the confidence level of a certain risk behavior data is not in default confidence interval
When, it indicates that the risk behavior data are Risk of noneffective behavioral data, does not obtain the risk behavior data at this time using as risk row
For sample data.Therefore, risk behavior data of the confidence level in default confidence interval can be determined as risk behavior sample
Data, and then the risk behavior sample data of the risk employee of at least two employee's types can be got.It needs to illustrate
It is that, when obtaining the risk behavior data of risk employee of at least two employee's types from employee database, can also be based on
Big data analysis obtains the risk behavior data with the consistent risk employee of employee's type in above-mentioned employee database.Namely
It says, the risk behavior sample data of the risk employee of at least two employee's types got may include different types of risk person
The corresponding kinds of risks behavioral data of work.The risk behavior sample number of the risk employee of at least two employee's types got
According to the corresponding kinds of risks behavior of risk employee for describing at least two types, a kind of risk behavior sample data is for retouching
State a kind of risk behavior sample data.Wherein, above-mentioned employee's type can be determined based on the application scenarios of practical Staffing System
(such as in the Staffing System of financial institution, above-mentioned employee's type can be financial employee, investment employee, sales clerk etc.,
In the Staffing System of science-and-technology enterprise, above-mentioned employee's type can be exploitation employee, design employee, O&M employee etc.) In
This is with no restrictions.Optionally, above-mentioned nonlinear model includes but is not limited to GBDT model, ID3 and C4.5 etc., is not done herein
Limitation.Above-mentioned default confidence interval can be determining according to the nonlinear model and practical application scene of practical application, herein
With no restrictions.
S22, determine that above-mentioned every kind of employee type is corresponding based on the corresponding risk behavior sample data of every kind of employee's type
Type label.
In some possible embodiments, get the corresponding risk behavior sample data of every kind of employee's type it
Afterwards, it may be determined that go out the corresponding type label of every kind of employee's type with the member to employee corresponding to every kind of risk behavior sample behavior
Work type is marked.Wherein, the above-mentioned type label is served only for employee's type of label risk employee, and concrete form includes but not
It is limited to one of text, number, letter and character string or multiple combinations, herein with no restrictions.Optionally, due to every kind of member
Work type corresponds to kinds of risks behavior sample data, therefore can sieve from the corresponding kinds of risks behavior sample data of every kind of employee
Select for describe employee's type or can indicate employee's type data segment (including but not limited to text, number, letter and
One or more combinations of character string) to determine the corresponding employee's type of above-mentioned every kind of employee, and then according to the member determined
Work type generates type label and above-mentioned every kind of employee type is marked.Wherein, a kind of employee's type only corresponds to a type
Label belongs to the corresponding type label of kinds of risks behavior sample data of same employee's type, and above-mentioned class label can
It marks again in each risk behavior sample data of same employee's type, can also be marked corresponding by same employee's type respectively
The data acquisition system that is constituted of kinds of risks behavior sample data, specific implementation is herein with no restrictions.
S23, the risk behavior sample data of the risk employee of above-mentioned at least two employees type is carried out at data format
Reason, to obtain the risk behavior sample data with preset data form.
In some possible embodiments, due to the risk behavior number of the employee of employee's types various in employee database
According to data source, acquisition modes it is different, or in the risk row for the employee for obtaining various employee's types based on big data analysis
For that can be obtained by different modes when data, therefore the risk behavior sample number of the risk employee of above-mentioned at least two employees type
According to there are different data formats, such as character type data, numeric type data.In order to construct Hazard ratio based on same data standard
To information aggregate, it is ensured that the accuracy of risk comparison information, it can be by the risk of the risk employee of above-mentioned at least two employees type
Behavior sample data carry out data format processing, to obtain the risk behavior sample data with preset data form.Wherein, on
Stating preset data form can be determined based on practical application scene, herein with no restrictions.For example, working as above-mentioned all risk behavior sample
Numeric type data is more in data, can be by the character type data in all risk behavior sample data when character type data is less
Data format processing is carried out, the character string of character type data is subjected to value, and then obtain the character of every kind of character type data
The value (can sum to obtain according to ANSI code value) of string, so that it is (pre- to convert numeric type for the risk behavior sample data of character type
If data format) risk behavior sample data.
In some possible embodiments, by the risk behavior sample of the risk employee of above-mentioned at least two employees type
After notebook data is converted to the risk behavior sample data of numeric type, due to the data for different risk behavior sample datas
Source, data unprocessed form difference, may cause between different risk behavior sample datas numerical value difference it is larger (such as
A kind of numerical value of risk behavior sample data is 0.1,100) numerical value of another risk behavior sample data is.When numerical value difference
When larger, the higher risk behavior sample data of numerical value can the opposite data shadow for weakening the lower risk behavior sample data of numerical value
Weight is rung, causes Hazard ratio to information against errors.Therefore, min-max standardization, z-score standardization and number can be used
According to the methods of normalization, the risk behavior sample data of whole numeric types is subjected to data normalization processing so that whole numeric types
Risk behavior sample data be in the same order of magnitude, and then promote the risk behavior sample data comparability of whole numeric types
And operability, to accurately construct risk comparison information.
S24, the risk behavior sample based on the corresponding type label of above-mentioned every kind of employee type and with preset data form
Notebook data constructs a risk comparison information to obtain the Hazard ratio including at least two risk comparison informations to information aggregate.
In some possible embodiments, corresponding with present count in the risk employee for getting every kind of employee's type
It, can be corresponding a variety of with preset data by the risk employee of every kind of employee's type after the risk behavior sample data of format
The risk behavior sample data of format generates a risk comparison information together with the corresponding type label of employee's type.Its
In, the risk comparison information of above-mentioned generation is used to indicate the risk behavior of the risk employee of each employee's type.And so on, it can
A variety of risk behavior sample datas with preset data form of multiple risk employees of a variety of employee's types are obtained to obtain
For verify various employee's types employee behavioral data whether be risk behavior data risk comparison information.Specifically,
Each above-mentioned risk behavior sample data with preset data form is the corresponding risk person of the risk behavior sample data
Partial data in employee's data of work.That is, each above-mentioned risk behavior sample number with preset data form
According to may be the corresponding risk employee of the risk behavior sample data employee's data in a certain section of character string, certain passage
And one or more combinations of a certain number of segment word, herein with no restrictions.Wherein, this partial data only indicates a certain risk employee
A certain risk behavior, i.e. this partial data corresponding risk behavior sample of a certain risk behavior for being only a certain risk employee
Data.This partial data can be obtained based on modes such as data parsing, data screenings, and then can be from the biggish risk employee of data volume
Employee's data in choose more effective informations as building risk comparison information data basis, so as to reduce building risk
The data processing amount of comparison information, improves the predictablity rate of employee's Risk-warning, and applicability is stronger.
In some possible embodiments, in the corresponding type label of risk employee based on a kind of employee's type and more
When there is kind the risk behavior sample data of preset data form to construct a risk comparison information, every kind of risk row can be first extracted
For the critical data segment of sample data, the critical data segment of every kind of risk behavior sample data can represent this kind of risk behavior sample
The key feature of the corresponding risk behavior of notebook data, thus a kind of corresponding a variety of keys of the risk employee that employee's type can be obtained
Data segment.And then above-mentioned a variety of critical data segments and the above-mentioned type label can be subjected to permutation and combination and form a Hazard ratio to letter
Above-mentioned a variety of critical data segments can also be carried out data compression to reduce the size of data of above-mentioned a variety of critical data segments by breath, then
With above-mentioned type label together production risk comparison information.Optionally, in order to avoid the data of kinds of risks behavior sample data
The skimble-scamble situation of type can above carry out every kind of risk behavior sample data of the risk employee of employee's type a kind of at data
Every kind of risk behavior sample data is converted risk behavior text information, then is based on semantics recognition technology from risk behavior by reason
It extracts in sample information for describing the characteristic key words of every kind of risk behavior, and then obtains the risk of one employee's type of description
Multiple characteristic key words of the kinds of risks behavior of employee.So as to the various features of the risk employee based on employee's type
Keyword type label corresponding with employee's type generates a risk comparison information, is thus not difficult to obtain comprising a plurality of risk
The Hazard ratio of comparison information is to information aggregate.Wherein, above-mentioned Hazard ratio includes to information to a Hazard ratio in information aggregate
A kind of corresponding multiple characteristic key words of the risk employee of employee's type or kinds of risks behavior critical data.An and risk
Comparison information is for determining whether a kind of a kind of behavioral data of employee's type is risk behavior data, i.e., a Hazard ratio is to letter
Whether the employee's image ceased for determining a kind of employee of employee's type is risk behavior.It should be strongly noted that above-mentioned institute
The implementation shown can be determining based on practical application scene, herein with no restrictions.
It in some possible embodiments, can base when getting the behavioral data for recording any employee's image
Whether above-mentioned behavioral data, which is risk behavior data, is determined to information aggregate in the Hazard ratio of above-mentioned building.Specifically, if above-mentioned
Hazard ratio is that the critical data segment based on kinds of risks behavior sample data constructs to information aggregate, then can be by above-mentioned behavior number
Each risk comparison information in information aggregate is compared according to above-mentioned Hazard ratio, when in above-mentioned behavioral data comprising above-mentioned
When Hazard ratio is to critical data segment in any risk comparison information in information aggregate, it may be determined that above-mentioned behavioral data is risk
Behavioral data.If above-mentioned Hazard ratio is that the characteristic key words based on kinds of risks behavior sample data construct to information aggregate,
Then above-mentioned behavioral data first can be subjected to data processing, above-mentioned behavioral data is converted into behavior text information, based on semanteme
Identification technology extracts the key of the behavior for describing the corresponding employee's image of above-mentioned behavioral data from above-mentioned behavior text information
Word.When above-mentioned Hazard ratio is closed in any bar risk comparison information in information aggregate comprising the corresponding behavior of above-mentioned behavioral data
Keyword, it is determined that above-mentioned behavioral data is risk behavior data.It should be strongly noted that the above-mentioned above-mentioned behavioral data of determination is
The no implementation for risk behavior data need to be determined according to building mode of the above-mentioned Hazard ratio to information aggregate, no longer superfluous herein
It states.
It in embodiments of the present invention, can by obtaining the kinds of risks behavioral data of the risk employee of various employee's types
Risk comparison information as much as possible is obtained, so that Hazard ratio can accurately determine different employee's types to information aggregate
Whether the behavioral data of employee is risk behavior data, promotes the accuracy for determining risk behavior data.It is also possible to use different
Building mode construct Hazard ratio to information aggregate, further promote building Hazard ratio to the accuracy of information aggregate and flexibly
Property.
S13, when determining that above-mentioned behavioral data is to any risk comparison information in information aggregate based on above-mentioned Hazard ratio
When risk behavior data, the corresponding type label of any of the above-described risk comparison information is determined, the above-mentioned type label is corresponding
Employee's type is determined as employee's type of the corresponding employee of above-mentioned behavioral data, and the corresponding employee of above-mentioned behavioral data is determined
For risk employee.
In some possible embodiments, when based on above-mentioned Hazard ratio to any risk comparison information in information aggregate
When determining that above-mentioned behavioral data is risk behavior data, it will can be used to determine that above-mentioned behavioral data to be the risk of risk behavior data
Comparison information is determined as target risk comparison information.Wherein, above-mentioned for determining that above-mentioned behavioral data is risk behavior data
Risk comparison information is contained critical data segment and the matched risk comparison information of above-mentioned behavioral data, or to include above-mentioned row
For the risk comparison information of the corresponding behavior keyword of data.Therefore, after determining target risk comparison information, it may be determined that
Employee's type corresponding to the type label for including in above-mentioned risk comparison information out, and then can be by above-mentioned risk comparison information pair
The employee's type answered is determined as employee's type of the corresponding employee of above-mentioned behavioral data.At this point, since above-mentioned behavioral data is wind
Dangerous behavioral data shows that the employee's image that above-mentioned behavioral data is recorded is risk behavior, therefore can be by above-mentioned behavioral data pair
The employee answered is determined as risk employee, and then can carry out Risk-warning to the risk employee determined.
S14, the risk information for obtaining above-mentioned behavioral data, and determine above-mentioned risk employee's based on above-mentioned risk information
Risk class.
In some possible embodiments, after determining that above-mentioned behavioral data is risk behavior data, it may be determined that on
The behavioural characteristic value of behavioral data is stated, then determines the risk class of above-mentioned risk employee based on above-mentioned behavioural characteristic value.Specifically
, although above-mentioned behavioral data only records a kind of employee's image, still have in above-mentioned behavioral data and employee's image not phase
The data of pass, therefore Feature Selection can be carried out to above-mentioned behavioral data, it obtains related to the employee's image that behavioral data is recorded
Characteristic.Wherein, features described above selection mode can the Filter method based on sequence, the Wrapper method based on assessment
And sequence selection algorithm etc., herein with no restrictions.For example, when the Filter method based on sequence carries out feature selecting, it can
Based on according to corresponding module, (specific module can be based on different behavioral data and reality from above-mentioned behavioral data
Application scenarios are determining, herein with no restrictions) it is that each of above-mentioned behavioral data feature is given a mark.Then according to this point
Number sorts and then chooses feature in the top, and then it is corresponding that feature in the top is determined as above-mentioned employee's image data
Characteristic.At this point, the corresponding feature vector of above-mentioned behavioral data can be constructed based on the characteristic obtained through feature selecting, and
It is based further on the behavioural characteristic value that above-mentioned behavioral data is calculated in the corresponding feature vector of above-mentioned behavioral data.So far, may be used
Based on the corresponding relationship of behavioural characteristic value and risk class in default risk class tablet, the risk etc. of above-mentioned risk employee is determined
Grade.For example, provided when in default risk class tablet, when behavioural characteristic value is less than the first preset threshold, corresponding low risk level,
When behavioural characteristic value is between the first preset threshold and the second preset threshold, corresponding risk grade, when behavioural characteristic value is big
When the second preset threshold, corresponding high-risk grade.At this point, if the behavioural characteristic value of above-mentioned behavioral data is greater than default risk etc.
Grade table in the second preset threshold when, it may be determined that the risk class of above-mentioned risk employee be high-risk grade.Wherein, above-mentioned first
The specific value of preset threshold and above-mentioned second preset threshold setting can based on the data type in actual employee database with
And practical application scene determines, herein with no restrictions.It should be strongly noted that in order to distinguish the wind of above-mentioned risk employee in detail
It is a variety of to determine based on multiple lesser threshold intervals can to set multiple threshold intervals in default risk class tablet for dangerous grade
Different degrees of risk class, details are not described herein for specific setting means.
In some possible embodiments, in order to reduce the Select Error in feature selection process, above-mentioned row is being determined
After being risk behavior data for data, data parsing can be carried out to above-mentioned behavioral data above-mentioned behavioral data is converted to wind
Dangerous behavior text, that is to say, that represent the employee's image recorded in above-mentioned behavioral data in the form of risk behavior text
Come, abstract behavioral data can be intuitively presented in a text form.So as to carry out semantic knowledge to above-mentioned risk behavior text
Not to determine the behavioural characteristic word for describing the employee's image that above-mentioned behavioral data is recorded (as more from above-mentioned risk behavior text
Grade, outgoing mail etc., herein with no restrictions).Wherein, during above-mentioned behavioral data is converted to risk behavior text,
Above-mentioned behavioral data can be converted to binary data, then binary data is converted into risk behavior text to reduce data and turn
The difficulty changed.The modes such as data conversion tools, algorithm can also be directly based upon, above-mentioned behavioral data is converted directly into risk behavior
Text information, specific implementation can be determining based on practical application scene, herein with no restrictions.In addition, determining above-mentioned row
After the corresponding risk behavior Feature Words of data, can by above-mentioned risk behavior Feature Words with it is each in default risk keywords database
A risk Keywords matching.It is consistent or semantic with above-mentioned risk behavior Feature Words when existing in above-mentioned default risk keywords database
It, can be corresponding by target risk keyword when similar risk keyword (for aspect description, hereinafter referred to as target risk keyword)
Risk class be determined as the risk class of above-mentioned risk employee.Wherein, when obtaining multiple risk rows based on above-mentioned behavioral data
After being characterized word and determining the corresponding target risk keyword of each risk behavior Feature Words, each target risk can be closed
Highest risk class is determined as the risk class of above-mentioned risk employee in the corresponding risk class of keyword, may be based on each mesh
Weight proportion COMPREHENSIVE CALCULATING shared by the corresponding each risk class of mark risk keyword obtains the risk etc. of above-mentioned risk employee
Grade, specific implementation is herein with no restrictions.
S15, warning information is generated based on above-mentioned employee's type, above-mentioned behavioral data and above-mentioned risk class.
In some possible embodiments, warning information can be generated after determining risk employee to above-mentioned risk
Employee carries out Risk-warning.Wherein, the employee information, employee's type and Forewarning Measures etc. of above-mentioned risk employee can be arranged
Column combination obtains warning information, or by the modes such as data parsing, data recombination by above-mentioned employee information, employee's type and
Forewarning Measures etc. carry out Data Integration to obtain warning information, and the specific generating mode of above-mentioned warning information is herein with no restrictions.
Wherein, above-mentioned employee information includes but is not limited to the information such as name, gender, the length of service, hiring date, attendance record, is not done herein
Limitation.It should be strongly noted that can also include risk behavior, the risk behavior of above-mentioned risk employee in above-mentioned warning information
The information such as time of origin, warning information sending method, specifically can be from employee's data acquisition of the risk employee in employee database
Related data simultaneously generates warning information with above-mentioned employee information, employee's type and Forewarning Measures etc., herein with no restrictions.
In some possible embodiments, above-mentioned Forewarning Measures can the risk class based on above-mentioned risk employee come really
It is fixed.Specifically, can determine whether the risk class of above-mentioned risk employee is greater than default risk class.If above-mentioned risk employee's
Risk class is not more than default risk class, then default Forewarning Measures can be determined as to the corresponding early warning of above-mentioned risk employee and arranged
It applies.In other words, when the risk class of above-mentioned risk employee is smaller, i.e., negative caused by the risk behavior of risk employee
It influences less, such as is obtained based on smaller (such as 10 yuan) behavioral data of employee's faulty operation, employee's violation reimbursed sum low
Risk class, can be used at this time unified default Forewarning Measures (including but not limited to house organ, simple warning etc., herein not
It is limited) it is used as the corresponding Forewarning Measures of low risk level to simplify early warning process.If it is determined that the risk of above-mentioned risk employee
Grade is greater than default risk class, then employee's image (the i.e. risk person that can be recorded based on the behavioral data of above-mentioned risk employee
The risk behavior of work) determine the corresponding Forewarning Measures of above-mentioned risk employee.Optionally, if the risk class of above-mentioned risk employee
It is to be determined based on default risk class tablet, it at this time can be based on determining that characteristic obtained in employee's type procedure determines
The behavioural characteristic of above-mentioned risk employee.If the risk class of above-mentioned risk employee is determined based on default risk keywords database,
It can will then be determined as the behavior of above-mentioned risk employee in the behavioural characteristic word for determining employee's image obtained in employee's type procedure
Feature.After the behavioural characteristic for obtaining above-mentioned risk employee, above-mentioned risk employee can be determined based on above-mentioned behavioural characteristic
Corresponding Forewarning Measures may be based on above-mentioned behavioural characteristic and employee's data associated with above-mentioned behavioural characteristic to determine
The corresponding Forewarning Measures of above-mentioned risk employee.For example, when above-mentioned behavioural characteristic shows that above-mentioned risk employee has reimbursement row in violation of rules and regulations
Can then to obtain reimbursement time, reimbursed sum, reimbursement number, accumulative reimbursed sum from employee's data of above-mentioned risk employee
Etc. information, to determine corresponding Forewarning Measures according to principal elements such as violation reimbursed sums and based on default Forewarning Measures standard
(such as transferring supervision team).
S16, above-mentioned warning information is sent to Risk-warning platform to carry out Risk-warning to above-mentioned risk employee.
It in some possible embodiments, can after above-mentioned warning information is sent to Risk-warning information platform
Indicate that above-mentioned Risk-warning platform shows employee's type in above-mentioned warning information, employee information, risk class and employee's row
For etc. information.Optionally, the information such as employee's type, employee information and the risk class in above-mentioned warning information are also based on
Indicate that above-mentioned Risk-warning platform is based on above-mentioned Forewarning Measures and carries out Risk-warning to above-mentioned risk employee.For example, can be based on upper
It states employee's type in warning information and indicates that above-mentioned Forewarning Measures are sent to specified warning information by above-mentioned Risk-warning platform
Reception staff (such as above-mentioned risk employee is sales clerk, then above-mentioned Forewarning Measures is sent to sales manager).For another example can base
Risk class in above-mentioned warning information indicates that above-mentioned Risk-warning platform takes above-mentioned risk employee according to Forewarning Measures
(when such as above-mentioned risk class is highest risk class, above-mentioned Risk-warning platform needs immediately according to pre- the timeliness of Risk-warning
The above-mentioned risk employee of Forewarning Measures in alert information takes measures).Wherein, indicate above-mentioned Risk-warning platform to above-mentioned risk person
The concrete mode that work carries out Risk-warning can be determining based on the particular content and practical application scene of above-mentioned warning information, herein not
It is limited.
In embodiments of the present invention, it can determine that the row of any employee in employee database to information aggregate based on Hazard ratio
It whether is risk behavior data for data, and then the case where the behavioral data for determining any of the above-described employee is risk behavior data
Under, determine the information such as the employee's type, employee information, risk class of risk employee and risk employee.Based on above-mentioned realization
Mode, it can be achieved that be measured in real time to whole behavioral datas in employee database, determine in time risk behavior data with
Risk employee.Meanwhile it being determined based on much informations such as employee's type, employee information and the risk class of risk employee corresponding
Forewarning Measures simultaneously indicate that Risk-warning platform carries out Risk-warning to risk employee, avoid due to manual operation or it is subjective because
Furthermore early warning inaccuracy situation caused by element can flexibly take alarm mode based on the different information contents in warning information, mention
The flexibility of employee's Risk-warning is risen, applicability is high.
It is the structural schematic diagram of employee's Risk-warning device provided in an embodiment of the present invention referring to Fig. 3, Fig. 3.The present invention is real
Applying employee's Risk-warning device that example provides includes:
Acquiring unit 31, for obtaining the behavioral data for recording any employee's image from employee database；
Judging unit 32, for determining whether above-mentioned behavioral data is risk behavior number to information aggregate based on Hazard ratio
According to；
Determination unit 33, for above-mentioned when being determined based on above-mentioned Hazard ratio to any risk comparison information in information aggregate
When behavioral data is risk behavior data, the corresponding type label of any of the above-described risk comparison information is determined, by the above-mentioned type
The corresponding employee's type of label is determined as employee's type of the corresponding employee of above-mentioned behavioral data, and above-mentioned behavioral data is corresponding
Employee be determined as risk employee；Above-mentioned determination unit 33, for obtaining the risk information of above-mentioned behavioral data, and based on above-mentioned
Risk information determines the risk class of above-mentioned risk employee；
Prewarning unit 34, for generating early warning based on above-mentioned employee's type, above-mentioned behavioral data and above-mentioned risk class
Information, and above-mentioned warning information is sent to Risk-warning platform to carry out Risk-warning to above-mentioned risk employee.
In some possible embodiments, above-mentioned acquiring unit 31 is also used to:
The risk behavior sample data of the risk employee of at least two employee's types is obtained from employee database, wherein
A kind of corresponding at least two risk behavior sample datas of the risk employee of employee's type, a kind of risk behavior sample data is for remembering
Record a kind of risk behavior；
Above-mentioned employee's Risk-warning device further include:
Construction unit 35 is also used to the risk behavior sample data of the risk employee based on above-mentioned at least two employees type
Hazard ratio is constructed to information aggregate.
In conjunction with second aspect, in a kind of possible embodiment, above-mentioned determination unit 33 is used for:
The risk employee of at least two employee's types is determined from employee database；
The risk behavior data of the risk employee of various employee's types are inputted into default nonlinear model, based on above-mentioned default
Nonlinear model obtains the confidence level of various risk behavior data；
Risk behavior data of the confidence level in default confidence interval are determined as risk behavior sample data, to obtain
The risk behavior sample data of the risk employee of above-mentioned at least two employees type.
In some possible embodiments, above-mentioned determination unit 33 is used for:
The corresponding class of above-mentioned every kind of employee type is determined based on the corresponding risk behavior sample data of every kind of employee's type
Type label；
Above-mentioned employee's Risk-warning device includes:
Processing unit 36, for carrying out the risk behavior sample data of the risk employee of above-mentioned at least two employees type
Data format processing, to obtain the risk behavior sample data with preset data form；
Above-mentioned construction unit 35, for based on the corresponding type label of above-mentioned every kind of employee type and with preset data lattice
The risk behavior sample data of formula constructs a risk comparison information to obtain the risk including at least two risk comparison informations
Comparison information set；
Wherein, above-mentioned Hazard ratio is used to determine the one of a kind of employee's type to a risk comparison information in information aggregate
Whether kind behavioral data is risk behavior data.
In some possible embodiments, above-mentioned risk information includes behavioural characteristic value and/or risk behavior Feature Words；
Above-mentioned determination unit 33 is used for:
The behavioural characteristic value for determining above-mentioned behavioral data is determined based on above-mentioned behavioural characteristic value and default risk class tablet
The risk class of above-mentioned risk employee；
Above-mentioned processing unit 36, for carrying out data parsing to above-mentioned risk behavior data to convert above-mentioned behavioral data
For risk behavior text；
Above-mentioned processing unit 36, for carrying out semantics recognition to above-mentioned risk behavior text with from above-mentioned risk behavior text
The risk behavior Feature Words of the middle above-mentioned risk employee of determination；
Above-mentioned determination unit 33, it is above-mentioned for being determined based on above-mentioned risk behavior Feature Words and default risk keywords database
The risk class of risk employee.
In some possible embodiments, above-mentioned acquiring unit 31 is used for:
The employee information of above-mentioned risk employee is obtained from above-mentioned employee database；
Above-mentioned judging unit 32, for determining whether above-mentioned risk class is greater than default risk class；
Above-mentioned determination unit 33, for being based on above-mentioned behavioral data when above-mentioned risk class is greater than default risk class
The employee's image recorded determines the corresponding Forewarning Measures of above-mentioned risk employee, when above-mentioned risk class is default no more than above-mentioned
When risk class, default Forewarning Measures are determined as the corresponding Forewarning Measures of above-mentioned risk employee；
Above-mentioned prewarning unit 34, for generating early warning based on above-mentioned employee information, employee's type and above-mentioned Forewarning Measures
Above-mentioned warning information is simultaneously sent to Risk-warning platform by information, so that above-mentioned Risk-warning platform shows above-mentioned risk employee's
Employee information and employee's type, and Risk-warning is carried out to above-mentioned risk employee based on the Forewarning Measures in above-mentioned warning information.
In the specific implementation, above-mentioned employee's Risk-warning device can be executed by modules built in it and/unit it is as above
Fig. 1 implementation provided by each step into Fig. 2.For example, above-mentioned acquiring unit 31 can be used for obtaining from employee database
It takes in the behavioral data and other implementations for recording any employee's image, for details, reference can be made to realize provided by above-mentioned each step
Mode, details are not described herein.Above-mentioned judging unit 32 can be used for for determining above-mentioned behavior number to information aggregate based on Hazard ratio
Whether according to being risk behavior data and other implementations, for details, reference can be made to implementations provided by above-mentioned each step, herein not
It repeats again.Above-mentioned determination unit 33 can be used for when above-mentioned Hazard ratio any risk comparison information in information aggregate is determined it is above-mentioned
When behavioral data is risk behavior data, corresponding type label of any of the above-described risk comparison information and other implementations is determined,
For details, reference can be made to implementations provided by above-mentioned each step, and details are not described herein.Above-mentioned prewarning unit 34 can be used for being based on
Above-mentioned employee's type, above-mentioned behavioral data and above-mentioned risk class generate warning information, and above-mentioned warning information is sent to
For Risk-warning platform to carry out Risk-warning and other implementations to above-mentioned risk employee, for details, reference can be made to above-mentioned each steps to be mentioned
The implementation of confession, details are not described herein.Above-mentioned construction unit 35 can be used for the risk based on above-mentioned at least two employees type
The risk behavior sample data building Hazard ratio of employee is to information aggregate and other implementations, and for details, reference can be made to above-mentioned each step institutes
The implementation of offer, details are not described herein.Above-mentioned processing unit 36 can be used for carrying out data solution to above-mentioned risk behavior data
Analysis is to be converted to risk behavior text and other implementations for above-mentioned behavioral data, and for details, reference can be made to provided by above-mentioned each step
Implementation, details are not described herein.
In embodiments of the present invention, it can determine that the row of any employee in employee database to information aggregate based on Hazard ratio
It whether is risk behavior data for data, and then the case where the behavioral data for determining any of the above-described employee is risk behavior data
Under, determine the information such as the employee's type, employee information, risk class of risk employee and risk employee.Based on above-mentioned realization
Mode, it can be achieved that be measured in real time to whole behavioral datas in employee database, determine in time risk behavior data with
Risk employee.Meanwhile it being determined based on much informations such as employee's type, employee information and the risk class of risk employee corresponding
Forewarning Measures simultaneously indicate that Risk-warning platform carries out Risk-warning to risk employee, avoid due to manual operation or it is subjective because
Furthermore early warning inaccuracy situation caused by element can flexibly take alarm mode based on the different information contents in warning information, mention
The flexibility of employee's Risk-warning is risen, applicability is high.
Referring to fig. 4, Fig. 4 is the structural schematic diagram of terminal provided in an embodiment of the present invention.As shown in figure 4, in the present embodiment
Terminal may include: one or more processors 41 and memory 42.Above-mentioned processor 41 and memory 42 pass through bus 43
Connection.Memory 42 is for storing computer program, which includes program instruction, and processor 41 is for executing storage
The program instruction that device 42 stores, performs the following operations:
The behavioral data for recording any employee's image is obtained from employee database；
Whether above-mentioned behavioral data, which is risk behavior data, is determined to information aggregate based on Hazard ratio；
When based on above-mentioned Hazard ratio to any risk comparison information in information aggregate determine above-mentioned behavioral data be risk
When behavioral data, the corresponding type label of any of the above-described risk comparison information is determined, by the corresponding employee of the above-mentioned type label
Type is determined as employee's type of the corresponding employee of above-mentioned behavioral data, and the corresponding employee of above-mentioned behavioral data is determined as wind
Dangerous employee；
The risk information of above-mentioned behavioral data is obtained, and determines the risk of above-mentioned risk employee based on above-mentioned risk information
Grade；
Warning information is generated based on above-mentioned employee's type, above-mentioned behavioral data and above-mentioned risk class, and will be above-mentioned pre-
Alert information is sent to Risk-warning platform to carry out Risk-warning to above-mentioned risk employee.
In some possible embodiments, above-mentioned processor 41 is also used to:
The risk behavior sample data of the risk employee of at least two employee's types is obtained from employee database, wherein
A kind of corresponding at least two risk behavior sample datas of the risk employee of employee's type, a kind of risk behavior sample data is for remembering
Record a kind of risk behavior；
The risk behavior sample data of risk employee based on above-mentioned at least two employees type constructs risk comparison information
Set.
In some possible embodiments, above-mentioned processor 41 is used for:
The risk employee of at least two employee's types is determined from employee database；
The risk behavior data of the risk employee of various employee's types are inputted into default nonlinear model, based on above-mentioned default
Nonlinear model obtains the confidence level of various risk behavior data；
Risk behavior data of the confidence level in default confidence interval are determined as risk behavior sample data, to obtain
The risk behavior sample data of the risk employee of above-mentioned at least two employees type.
In some possible embodiments, above-mentioned processor 41 is used for:
Based on the corresponding risk behavior sample data of every kind of employee's type=determine that above-mentioned every kind of employee type is corresponding
Type label；The risk behavior sample data of the risk employee of above-mentioned at least two employees type is subjected to data format processing,
To obtain the risk behavior sample data with preset data form；
Risk behavior sample number based on the corresponding type label of above-mentioned every kind of employee type and with preset data form
According to one risk comparison information of building to obtain the Hazard ratio including at least two risk comparison informations to information aggregate；
Wherein, above-mentioned Hazard ratio is used to determine the one of a kind of employee's type to a risk comparison information in information aggregate
Whether kind behavioral data is risk behavior data.
In some possible embodiments, above-mentioned risk information includes behavioural characteristic value and/or risk behavior Feature Words；
Above-mentioned processor 41 is used for:
The behavioural characteristic value for determining above-mentioned behavioral data is determined based on above-mentioned behavioural characteristic value and default risk class tablet
The risk class of above-mentioned risk employee；
And/or data parsing is carried out so that above-mentioned risk behavior data are converted to risk row to above-mentioned risk behavior data
For text；
Semantics recognition is carried out to determine above-mentioned risk employee from above-mentioned risk behavior text to above-mentioned risk behavior text
Risk behavior Feature Words；
The risk class of above-mentioned risk employee is determined based on above-mentioned risk behavior Feature Words and default risk keywords database.
In some possible embodiments, above-mentioned processor 41 is used for:
The employee information of above-mentioned risk employee is obtained from above-mentioned employee database；
Determine whether above-mentioned risk class is greater than default risk class；
If above-mentioned risk class is greater than default risk class, the employee's image recorded based on above-mentioned behavioral data is determined
The corresponding Forewarning Measures of above-mentioned risk employee arrange default early warning if above-mentioned risk class is not more than above-mentioned default risk class
It applies and is determined as the corresponding Forewarning Measures of above-mentioned risk employee；
Warning information is generated based on above-mentioned employee information, employee's type and above-mentioned Forewarning Measures and by above-mentioned warning information
It is sent to Risk-warning platform, so that above-mentioned Risk-warning platform shows the employee information and employee's type of above-mentioned risk employee,
And Risk-warning is carried out to above-mentioned risk employee based on the Forewarning Measures in above-mentioned warning information.
It should be appreciated that in some possible embodiments, above-mentioned processor 41 can be central processing unit
(central processing unit, CPU), which 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) or other can
Programmed 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 etc..
The memory 42 may include read-only memory and random access memory, and provide instruction sum number to processor 41
According to.The a part of of memory 42 can also include nonvolatile RAM.It is set for example, memory 42 can also store
The information of standby type.
In the specific implementation, above-mentioned terminal can be executed by each functional module built in it as above-mentioned Fig. 1 is each into Fig. 2
Implementation provided by step, for details, reference can be made to implementations provided by above-mentioned each step, and details are not described herein.
In embodiments of the present invention, it can determine that the row of any employee in employee database to information aggregate based on Hazard ratio
It whether is risk behavior data for data, and then the case where the behavioral data for determining any of the above-described employee is risk behavior data
Under, determine the information such as the employee's type, employee information, risk class of risk employee and risk employee.Based on above-mentioned realization
Mode, it can be achieved that be measured in real time to whole behavioral datas in employee database, determine in time risk behavior data with
Risk employee.Meanwhile it being determined based on much informations such as employee's type, employee information and the risk class of risk employee corresponding
Forewarning Measures simultaneously indicate that Risk-warning platform carries out Risk-warning to risk employee, avoid due to manual operation or it is subjective because
Early warning inaccuracy situation caused by element, applicability are high.
The embodiment of the present invention also provides a kind of computer readable storage medium, which has meter
Calculation machine program is executed by processor to realize Fig. 1 method provided by each step into Fig. 2, and for details, reference can be made to above-mentioned each
Implementation provided by step, details are not described herein.
Above-mentioned computer readable storage medium can be the Task Processing Unit or above-mentioned that aforementioned any embodiment provides
The internal storage unit of terminal, such as the hard disk or memory of electronic equipment.The computer readable storage medium is also possible to the electricity
The plug-in type hard disk being equipped on the External memory equipment of sub- equipment, such as the electronic equipment, intelligent memory card (smart media
Card, SMC), secure digital (secure digital, SD) card, flash card (flash card) etc..It is above-mentioned computer-readable to deposit
Storage media can also include magnetic disk, CD, read-only memory (read-only memory, ROM) or random storage memory
Body (randomaccess memory, RAM) etc..Further, which can also both include the electronics
The internal storage unit of equipment also includes External memory equipment.The computer readable storage medium is for storing the computer program
And other programs and data needed for the electronic equipment.The computer readable storage medium can be also used for temporarily storing
Data through exporting or will export.
Claims of the present invention and term " first " in specification and attached drawing, " second " etc. are for distinguishing difference
Object is not use to describe a particular order.In addition, term " includes " and " having " and their any deformations, it is intended that
It covers and non-exclusive includes.Such as it contains the process, method, system, product or equipment of a series of steps or units and does not limit
Due to listed step or unit, but optionally further comprising the step of not listing or unit, or optionally further comprising it is right
In the intrinsic other step or units of these process, methods, product or equipment.Referenced herein " embodiment " is it is meant that knot
The a particular feature, structure, or characteristic for closing embodiment description may include at least one embodiment of the present invention.In specification
In each position show that the phrase might not each mean identical embodiment, nor the independence with other embodiments mutual exclusion
Or alternative embodiment.Those skilled in the art explicitly and implicitly understand, embodiment described herein can be with
It is combined with other embodiments.Refer in description of the invention to term "and/or" used in the appended claims related
Join any combination and all possible combinations of one or more of item listed, and including these combinations.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (10)
1. a kind of employee's method for prewarning risk, which is characterized in that the described method includes:
The behavioral data for recording any employee's image is obtained from employee database；
Whether the behavioral data, which is risk behavior data, is determined to information aggregate based on Hazard ratio；
When based on the Hazard ratio to any risk comparison information in information aggregate determine the behavioral data be risk behavior
When data, the corresponding type label of any risk comparison information is determined, by the corresponding employee's type of the type label
It is determined as employee's type of the corresponding employee of the behavioral data, and the corresponding employee of the behavioral data is determined as risk person
Work；
The risk information of the behavioral data is obtained, and determines the risk etc. of the risk employee based on the risk information
Grade；
Warning information is generated based on employee's type, the behavioral data and the risk class, and the early warning is believed
Breath is sent to Risk-warning platform to carry out Risk-warning to the risk employee.
2. the method according to claim 1, wherein described obtain from employee database records any employee's row
For behavioral data before, the method also includes:
The risk behavior sample data of the risk employee of at least two employee's types is obtained from employee database, wherein a kind of
The corresponding at least two risk behavior sample datas of the risk employee of employee's type, a kind of risk behavior sample data is for recording one
Kind risk behavior；
The risk behavior sample data building Hazard ratio of risk employee based on at least two employees type is to information aggregate.
3. according to the method described in claim 2, it is characterized in that, described obtain at least two employee's classes from employee database
The risk behavior sample data of the risk employee of type includes:
The risk employee of at least two employee's types is determined from employee database；
The risk behavior data of the risk employee of various employee's types are inputted into default nonlinear model, based on it is described preset it is non-thread
Property model obtains the confidence level of various risk behavior data；
Risk behavior data of the confidence level in default confidence interval are determined as risk behavior sample data, it is described to obtain
The risk behavior sample data of the risk employee of at least two employee's types.
4. according to the method in claim 2 or 3, which is characterized in that the wind based on at least two employees type
The risk behavior sample data of dangerous employee constructs Hazard ratio
The corresponding type mark of every kind of employee type is determined based on the corresponding risk behavior sample data of every kind of employee's type
Label；
The risk behavior sample data of the risk employee of at least two employees type is subjected to data format processing, to obtain
Risk behavior sample data with preset data form；
Risk behavior sample data structure based on the corresponding type label of every kind of employee type and with preset data form
A risk comparison information is built to obtain the Hazard ratio including at least two risk comparison informations to information aggregate；
Wherein, the Hazard ratio is used to determine a kind of a kind of row of employee's type to a risk comparison information in information aggregate
It whether is risk behavior data for data.
5. 1 to 4 described in any item methods according to claim, which is characterized in that the risk information includes behavior spy
Value indicative and/or risk behavior Feature Words；The risk information for obtaining the behavioral data, and determined based on the risk information
The risk class of the risk employee includes: out
The behavioural characteristic value for determining the behavioral data, based on described in the behavioural characteristic value and the determination of default risk class tablet
The risk class of risk employee；And/or
Data parsing is carried out so that the behavioral data is converted to risk behavior text to the risk behavior data；
Semantics recognition is carried out to determine the wind of the risk employee from the risk behavior text to the risk behavior text
Dangerous behavioural characteristic word；
The risk class of the risk employee is determined based on the risk behavior Feature Words and default risk keywords database.
6. method according to any one of claims 1 to 5, which is characterized in that described to be based on employee's type, the row
Warning information is generated for data and the risk class, and the warning information is sent to Risk-warning platform to described
Risk employee carries out Risk-warning
The employee information of the risk employee is obtained from the employee database；
Determine whether the risk class is greater than default risk class；
If the risk class is greater than default risk class, institute is determined based on the employee's image that the behavioral data is recorded
The corresponding Forewarning Measures of risk employee are stated, if the risk class is not more than the default risk class, default early warning is arranged
It applies and is determined as the corresponding Forewarning Measures of the risk employee；
Warning information is generated based on the employee information, employee's type and the Forewarning Measures and sends the warning information
To Risk-warning platform, so that the Risk-warning platform shows the employee information and employee's type of the risk employee, and base
Forewarning Measures in the warning information carry out Risk-warning to the risk employee.
7. a kind of employee's Risk-warning device, which is characterized in that employee's Risk-warning device includes:
Acquiring unit, for obtaining the behavioral data for recording any employee's image from employee database；
Judging unit, for determining whether the behavioral data is risk behavior data to information aggregate based on Hazard ratio；
Determination unit determines the behavior number to any risk comparison information in information aggregate based on the Hazard ratio for working as
When according to for risk behavior data, the corresponding type label of any risk comparison information is determined, by the type label pair
The employee's type answered is determined as employee's type of the corresponding employee of the behavioral data, and by the corresponding employee of the behavioral data
It is determined as risk employee；
The determination unit for obtaining the risk information of the behavioral data, and is determined based on the risk information described
The risk class of risk employee；
Prewarning unit, for generating warning information based on employee's type, the behavioral data and the risk class, and
The warning information is sent to Risk-warning platform to carry out Risk-warning to the risk employee.
8. employee's Risk-warning device according to claim 7, which is characterized in that
The acquiring unit is also used to obtain the risk behavior of the risk employee of at least two employee's types from employee database
Sample data, wherein a kind of corresponding at least two risk behavior sample datas of the risk employee of employee's type, a kind of risk behavior
Sample data is for recording a kind of risk behavior；
Employee's Risk-warning device further include:
Construction unit is also used to the risk behavior sample data building wind of the risk employee based on at least two employees type
Dangerous comparison information set.
9. a kind of terminal, which is characterized in that including processor and memory, the processor and memory are connected with each other；
The memory is for storing computer program, and the computer program includes program instruction, and the processor is configured
For calling described program to instruct, such as method as claimed in any one of claims 1 to 6 is executed.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program are executed by processor to realize method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910618947.1A CN110414806B (en) | 2019-07-10 | 2019-07-10 | Employee risk early warning method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910618947.1A CN110414806B (en) | 2019-07-10 | 2019-07-10 | Employee risk early warning method and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110414806A true CN110414806A (en) | 2019-11-05 |
| CN110414806B CN110414806B (en) | 2024-05-14 |
Family
ID=68360880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910618947.1A Active CN110414806B (en) | 2019-07-10 | 2019-07-10 | Employee risk early warning method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110414806B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861281A (en) * | 2020-08-05 | 2020-10-30 | 中国银行股份有限公司 | Knowledge graph-based risk employee discovery method and device |
| CN111882411A (en) * | 2020-07-15 | 2020-11-03 | 国网河北省电力有限公司信息通信分公司 | Intelligent electric power financial information management system |
| CN113032435A (en) * | 2021-03-18 | 2021-06-25 | 上海数禾信息科技有限公司 | Data processing method and device for risk assessment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020077825A1 (en) * | 2000-08-22 | 2002-06-20 | Silverman Stephen E. | Methods and apparatus for evaluating near-term suicidal risk using vocal parameters |
| EP3109782A1 (en) * | 2015-06-08 | 2016-12-28 | Fujitsu Limited | A risk determining apparatus and risk determining method |
| CN109255518A (en) * | 2018-08-01 | 2019-01-22 | 阿里巴巴集团控股有限公司 | Data application risk appraisal procedure, device and system |
| CN109508825A (en) * | 2018-11-12 | 2019-03-22 | 平安科技（深圳）有限公司 | Employee's image method for prewarning risk and relevant apparatus |
| CN109766766A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Employee work condition monitoring method, device, computer equipment and storage medium |
| WO2019095572A1 (en) * | 2017-11-17 | 2019-05-23 | 平安科技（深圳）有限公司 | Enterprise investment risk assessment method, device, and storage medium |
-
2019
- 2019-07-10 CN CN201910618947.1A patent/CN110414806B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020077825A1 (en) * | 2000-08-22 | 2002-06-20 | Silverman Stephen E. | Methods and apparatus for evaluating near-term suicidal risk using vocal parameters |
| EP3109782A1 (en) * | 2015-06-08 | 2016-12-28 | Fujitsu Limited | A risk determining apparatus and risk determining method |
| WO2019095572A1 (en) * | 2017-11-17 | 2019-05-23 | 平安科技（深圳）有限公司 | Enterprise investment risk assessment method, device, and storage medium |
| CN109255518A (en) * | 2018-08-01 | 2019-01-22 | 阿里巴巴集团控股有限公司 | Data application risk appraisal procedure, device and system |
| CN109508825A (en) * | 2018-11-12 | 2019-03-22 | 平安科技（深圳）有限公司 | Employee's image method for prewarning risk and relevant apparatus |
| CN109766766A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Employee work condition monitoring method, device, computer equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882411A (en) * | 2020-07-15 | 2020-11-03 | 国网河北省电力有限公司信息通信分公司 | Intelligent electric power financial information management system |
| CN111861281A (en) * | 2020-08-05 | 2020-10-30 | 中国银行股份有限公司 | Knowledge graph-based risk employee discovery method and device |
| CN113032435A (en) * | 2021-03-18 | 2021-06-25 | 上海数禾信息科技有限公司 | Data processing method and device for risk assessment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110414806B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Brown-Liburd et al. | Big Data and audit evidence | |
| CN110414806A (en) | Employee's method for prewarning risk and relevant apparatus | |
| Shadabfar et al. | Resilience-based design of infrastructure: Review of models, methodologies, and computational tools | |
| CN107993143A (en) | A kind of Credit Risk Assessment method and system | |
| CN111738549A (en) | Food safety risk assessment method, device, equipment and storage medium | |
| CN106656536A (en) | Method and device for processing service invocation information | |
| CN109508825A (en) | Employee's image method for prewarning risk and relevant apparatus | |
| US9304991B2 (en) | Method and apparatus for using monitoring intent to match business processes or monitoring templates | |
| CN112419030B (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN112631889B (en) | Portrayal method, device, equipment and readable storage medium for application system | |
| CN117473048B (en) | Financial abnormal data monitoring and analyzing system and method based on data mining | |
| CN110851611A (en) | Hidden danger data knowledge graph construction method, device, equipment and medium | |
| CN113919630A (en) | Enterprise economic crime detection method, system and equipment | |
| CN113177840B (en) | Customer risk identification method and device | |
| US20110191143A1 (en) | Method and Apparatus for Specifying Monitoring Intent of a Business Process or Monitoring Template | |
| CN116664021B (en) | Factory inspection auxiliary decision-making system and method based on mobile terminal | |
| Hou | Financial Abnormal Data Detection System Based on Reinforcement Learning | |
| CN107766311A (en) | Risk investment method for reporting data and system are automatically generated based on OnlineBox systems | |
| Juma et al. | Exploratory Analysis of Risk Management Process of UAE Police Department | |
| CN111754340A (en) | Guarantee network risk investigation system based on graph database | |
| KR20070111878A (en) | A intelligent regular auditing system and a auditing methode thereof | |
| CN115271514A (en) | Communication enterprise monitoring method and device, electronic equipment and storage medium | |
| CN113379212A (en) | Block chain-based logistics information platform default risk assessment method, device, equipment and medium | |
| CN114331679A (en) | Data problem analysis method and related device | |
| CN113379211A (en) | Block chain-based logistics information platform default risk management and control system and method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |