CN109492911A - Risk forecast method, device, computer equipment and the storage medium of risk case - Google Patents
Risk forecast method, device, computer equipment and the storage medium of risk case Download PDFInfo
- Publication number
- CN109492911A CN109492911A CN201811346052.9A CN201811346052A CN109492911A CN 109492911 A CN109492911 A CN 109492911A CN 201811346052 A CN201811346052 A CN 201811346052A CN 109492911 A CN109492911 A CN 109492911A
- Authority
- CN
- China
- Prior art keywords
- event
- risk
- parameter
- financial
- severity parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 230000006870 function Effects 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 235000015170 shellfish Nutrition 0.000 claims description 4
- 238000004064 recycling Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 14
- 230000002045 lasting effect Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 238000002360 preparation method Methods 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001568 sexual effect Effects 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
Abstract
The invention discloses the risk forecast method of risk case, device, computer equipment and storage mediums.This method is treated trained model-naive Bayesian by the historical data of operational risk loss event and is trained, it obtains for predicting the non-financial model-naive Bayesian for influencing severity parameter, using the corresponding event description information of operational risk loss event as the input of the model-naive Bayesian, the corresponding non-financial influence severity parameter of operational risk loss event is obtained.The method achieve on the corresponding non-financial automatic calculating for influencing severity parameter of operational risk loss event and intelligent predicting, risk timely can be carried out to operational risk loss event and estimated, convenient for being handled in time risk case.
Description
Technical field
The present invention relates to risk assessment technology field more particularly to a kind of risk forecast methods of risk case, device, meter
Calculate machine equipment and storage medium.
Background technique
Currently, check and He Gui department to the identification of operational risk event, collect, summarize, analyze and report, be
It carries out manually, namely can only be that the non-financial influence severity of operational risk event is analyzed and calculated by hand, cause to imitate
Rate is low.
Summary of the invention
The embodiment of the invention provides a kind of risk forecast method of risk case, device, computer equipment and storages to be situated between
Matter, it is intended to solve to check in the prior art and He Gui department to the identification of operational risk event, collect, summarize, analyze and report
Work be performed manually by, and on the non-financial influence severity of operational risk event analyzed and calculated be also manually into
The problem of going, leading to inefficiency.
In a first aspect, the embodiment of the invention provides a kind of risk forecast methods of risk case comprising:
The historical data for obtaining operational risk loss event, treats trained simplicity as training set for the historical data
Bayesian model is trained, and is obtained for predicting the non-financial model-naive Bayesian for influencing severity parameter；
Using the corresponding event description information of operational risk loss event as the input of the model-naive Bayesian, obtain
Operational risk loses the corresponding non-financial influence severity parameter of event；
Combined influence is obtained according to non-financial influence severity parameter and acquired financial influence severity parameter are corresponding
Severity parameter.
Second aspect, the embodiment of the invention provides a kind of risk estimating devices of risk case comprising:
Historical data training unit makees the historical data for obtaining the historical data of operational risk loss event
Trained model-naive Bayesian is treated for training set to be trained, and is obtained for predicting the non-financial Piao for influencing severity parameter
Plain Bayesian model；
First severity parameter acquiring unit, for using the corresponding event description information of operational risk loss event as institute
The input of model-naive Bayesian is stated, the corresponding non-financial influence severity parameter of operational risk loss event is obtained；
Second severity parameter acquiring unit, for according to non-financial influence severity parameter and acquired financial influence
Severity parameter is corresponding to obtain combined influence severity parameter.
The third aspect, the embodiment of the present invention provide a kind of computer equipment again comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the processor execute the computer program
The risk forecast method of risk case described in the above-mentioned first aspect of Shi Shixian.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, wherein the computer can
It reads storage medium and is stored with computer program, it is above-mentioned that the computer program when being executed by a processor executes the processor
The risk forecast method of risk case described in first aspect.
The embodiment of the invention provides a kind of risk forecast method of risk case, device, computer equipment and storages to be situated between
Matter.This method is treated trained model-naive Bayesian by the historical data for losing event by operational risk and is trained, and obtains
To for predicting the non-financial model-naive Bayesian for influencing severity parameter, the corresponding event of operational risk loss event is retouched
Input of the information as the model-naive Bayesian is stated, the corresponding non-financial influence severity of operational risk loss event is obtained
Parameter.The method achieve on the corresponding non-financial automatic calculating and intelligence for influencing severity parameter of operational risk loss event
Prediction timely can carry out risk to operational risk loss event and estimate, convenient for being handled in time risk case.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of the risk forecast method of risk case provided in an embodiment of the present invention；
Fig. 2 is the sub-process schematic diagram of the risk forecast method of risk case provided in an embodiment of the present invention；
Fig. 3 is another sub-process schematic diagram of the risk forecast method of risk case provided in an embodiment of the present invention；
Fig. 4 is another sub-process schematic diagram of the risk forecast method of risk case provided in an embodiment of the present invention；
Fig. 5 is the schematic block diagram of the risk estimating device of risk case provided in an embodiment of the present invention；
Fig. 6 is the subelement schematic block diagram of the risk estimating device of risk case provided in an embodiment of the present invention；
Fig. 7 is another subelement schematic block diagram of the risk estimating device of risk case provided in an embodiment of the present invention；
Fig. 8 is another subelement schematic block diagram of the risk estimating device of risk case provided in an embodiment of the present invention；
Fig. 9 is the schematic block diagram of computer equipment 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 some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
For the clearer technical solution for understanding the application, the noun in the industry slang of part is explained below
It is bright.
Operational risk is indicated by not perfect or problematic internal processes, employee, Information technology system and external event
The risk of caused loss comprising legal risk, but do not include Strategy Risk and honour risk.
Operational risk loses event, refers on checking and He Gui department causes the operation wind of damage to property or non-financial influence
Dangerous event, it is non-financial to influence to include customer service influence, reputation influence, law/supervision and employee influence.Wherein, operational risk
The common type of loss event has Inner cheat (to refer to and deliberately gain, usurp property or violate supervision regulations, law or company policy by cheating
Caused loss event), External Funtions (refer to that third party deliberately defrauds of, usurps, plunders property, forges important document, attack commercial is checked
And loss event caused by He Gui department IT system or escape Legal Regulation) etc..
Operational risk event collection refers to the identification of operational risk event, collects, summarizes, analyzes and report, wherein
Identification to individual event and make a report on be operational risk event collection basis.
Referring to Fig. 1, Fig. 1 is the flow diagram of the risk forecast method of risk case provided in an embodiment of the present invention,
The risk forecast method of the risk case is applied in management server, and this method passes through the application that is installed in management server
Software is executed.
As shown in Figure 1, the method comprising the steps of S110~S130.
S110, the historical data for obtaining operational risk loss event, treat training using the historical data as training set
Model-naive Bayesian be trained, obtain for predict it is non-financial influence severity parameter model-naive Bayesian.
In the present embodiment, in order to train model-naive Bayesian in advance, need to obtain a large amount of operational risk loss thing
The historical data of part, obtaining the corresponding historical events description information of historical data, (historical events description information can be regarded as more
The set of a keyword), using historical events description information as the input of model-naive Bayesian function, by historical data with
The corresponding non-financial output for influencing severity parameter as model-naive Bayesian function of historical events description information, Ji Kexun
It gets for predicting the non-financial model-naive Bayesian for influencing severity parameter.
Wherein, historical events description information includes: whether (to convert into for loss event, state-event, currency type, amount of money involved
RMB), the potential loss amount of money (equivalent RMB), the actual loss amount of money (equivalent RMB), the actual loss amount of money
(former currency type), whether have recycling, insurance recycling the amount of money, insurance recycling the date, the non-insured recycling amount of money, the non-insured recycling date,
The final ascertainment of damage amount of money.
Rather than financial influence severity parameter include: non-financial influence severity grade, non-financial influence severity whether
It is legal close rule, whether strategy and operations objective, whether business lasting operation and customer service, whether information announcing, whether sound
Reputation influence and whether data and information system.
In one embodiment, as shown in Fig. 2, step S110 includes:
S111, the historical data for obtaining operational risk loss event, historical data is segmented to obtain historical events
Description information；
S112, using the historical events description information as the input of model-naive Bayesian function, will be in historical data
The non-financial output for influencing severity parameter as model-naive Bayesian function corresponding with historical events description information, to institute
It states model-naive Bayesian function to be trained, obtains the model-naive Bayesian.
In the present embodiment, the model-naive Bayesian function is as follows:
Wherein, x1, x2..., xnIndicate each feature in historical events description information, it is understood that it is each keyword,
Such as whether for loss event, state-event, currency type, amount of money involved (equivalent RMB), the potential loss amount of money (equivalent RMB
Member), the actual loss amount of money (equivalent RMB), the actual loss amount of money (former currency type), whether have recycling, insurance recycling the amount of money,
The insurance recycling date, the non-insured recycling amount of money, non-insured recycling date, the final ascertainment of damage amount of money.It is described according to historical events
Each feature in information is divided into class ykPossibility.
Entire Naive Bayes Classification is divided into following multiple stages:
Preparation stage, the task in this stage are that necessary preparation is done for Naive Bayes Classification, and groundwork is
Characteristic attribute is determined as the case may be, and each characteristic attribute is suitably divided, then by manually to a part wait divide
Category is classified, and training sample set is formed.The input in this stage is all data to be sorted, output be characteristic attribute and
Training sample.This stage is the stage for uniquely needing to be accomplished manually in entire Naive Bayes Classification, and quality is to entire mistake
Journey will have a major impact, and the quality of classifier is largely divided by characteristic attribute, characteristic attribute and training sample quality is determined
It is fixed.
Classifier training stage, the task in this stage are exactly to generate classifier, and groundwork is to calculate each classification to exist
The frequency of occurrences and each characteristic attribute in training sample, which divide, estimates the conditional probability of each classification, and result is recorded.
Its input is characteristic attribute and training sample, and output is classifier.This stage is the mechanical sexual stage, according to above-mentioned simple pattra leaves
The formula of this pattern function can calculate completion automatically.
S120, operational risk is lost to the corresponding event description information of event as the defeated of the model-naive Bayesian
Enter, obtains the corresponding non-financial influence severity parameter of operational risk loss event.
In the present embodiment, in order to obtain the corresponding severity of operational risk loss event, one need to be quantized into
Level value, and operational risk loss event is passage description, therefore in order to be quantified as level value, it need to be corresponded to
It is segmented to obtain event description information, then using event description information as the input of the model-naive Bayesian, Ji Kegen
The corresponding non-financial influence severity parameter for obtaining being indicated by level value of the keyword for including according to event description information.And it integrates
The non-financial combined influence for influencing severity parameter and financial influence severity parameter need to be fully considered by influencing severity parameter, therefore
It need to be according to non-financial influence severity parameter and the corresponding weight of financial influence severity parameter come the comprehensive shadow of COMPREHENSIVE CALCULATING
Ring severity parameter.It is realized in the application and verbal description is quantified as the corresponding non-financial influence of operational risk loss event sternly
Severe parameter and combined influence severity parameter.
In one embodiment, as shown in figure 3, step S120 includes:
S121, the corresponding current data of the operational risk loss event is obtained, current data is segmented to obtain
Current event description information；
If the participle number in S122, the current event description information does not reach preset participle number threshold value, obtain
The difference of the participle number threshold value and the participle number in current event description information described to work as participle gap number
Null value identical with the participle gap number, current event description information after being handled are supplemented in preceding event description information；
S123, using current event description information after the processing as the input of the model-naive Bayesian function, obtain
To non-financial influence severity parameter.
In the present embodiment, in order to ensure point in the corresponding current event description information of each operational risk loss event
Word number is all the same, to ensure to be input to the model-naive Bayesian accordingly as normalized number.At this time first by current data
Segmented to obtain current event description information, if the participle number in the current event description information do not reach it is preset
Participle number threshold value obtains current event description information and segments number and segment the absolute value of the difference of number threshold value, supplements and be somebody's turn to do
The identical null value of absolute value number is to convert the current event description information to after the processing of standardized data formats currently
Event description information.
It is defeated namely when using the corresponding multiple fields of historical events description information as after the input of model-naive Bayesian
Non-financial influence severity parameter out is multiple grades numerical value, such as is exported are as follows: non-financial influence severity grade be 4, it is non-
(legal conjunction is considered as value when advising be 1 to the legal conjunction rule of financial influence severity, and illegal conjunction is considered as value and is 0), meets war when advising
(being considered as value when meeting strategy and operations objective is 1, and being considered as value when not meeting strategy and operations objective is for summary and operations objective
0) (it is 1 that the lasting operation and customer service for meeting business, which are considered as value, is not inconsistent for the lasting operation and customer service for, meeting business
The lasting operation and customer service of conjunction business be considered as value be 0), meet information announcing (meeting information announcing to be considered as value is 1,
It does not meet information announcing and is considered as value and be 0), meet reputation and influence that (meeting reputation influence, to be considered as value be 1, does not meet reputation shadow
Ring be considered as value be 0), meet data and information system (meet data and information system to be considered as value be 1, do not meet data and
Information system be considered as value be 0), rather than the value of financial influence severity parameter be above-mentioned parameter in maximum value.
S130, synthesis is obtained according to non-financial influence severity parameter and acquired financial influence severity parameter are corresponding
Influence severity parameter.
In one embodiment, as shown in figure 4, step S130 includes:
S131, non-financial influence severity parameter and financial influence severity parameter are obtained；
S132, by non-financial influence severity parameter multiplied by preset first weighted value to obtain the first parameter value, by wealth
Business influences severity parameter multiplied by preset second weighted value to obtain the second parameter value；
S133, the first parameter value and the second parameter value are summed, obtains combined influence severity parameter.
In the present embodiment, the simple shellfish is input to when losing the corresponding event description information of event according to operational risk
This model of leaf, to obtain the corresponding non-financial influence severity parameter of operational risk loss event (such as current non-financial shadow
Ring severity parameter be 4) after.In order to obtain combined influence severity parameter, financial influence severity parameter (example can also be obtained
If current financial influence severity parameter is 3), by non-financial influence severity parameter multiplied by preset first weighted value (example
It is 0.6) to obtain the first parameter value, by financial influence severity parameter multiplied by preset second weight that the first weighted value, which is such as arranged,
Value (such as it is 0.4 that the second weighted value, which is arranged) is finally summed the first parameter value and the second parameter value with obtaining the second parameter value,
Obtain combined influence severity parameter (such as 4*0.6+3*0.4=3.6).
In one embodiment, after step S130 further include:
If detecting, the corresponding non-financial influence severity parameter of operational risk loss event exceeds preset grade threshold,
Parsing obtains the corresponding event information of operational risk loss event, and event information is filled to email template to obtain great operation
Risk case reports prompting mail, the great operational risk event is reported, mail is reminded to be sent according to mail reception side's information
To corresponding receiving party.
In the present embodiment, if detecting the corresponding non-financial influence severity parameter of operational risk loss event or synthesis
It influences severity parameter and exceeds the grade threshold (such as setting 4 for grade threshold), then it represents that the operational risk loses event
It should be paid close attention to by related personnel and be handled in time, should parse obtain the corresponding event letter of operational risk loss event at this time
Breath, event information is filled to email template to obtain great operational risk event and report prompting mail.
Remind the Mail Contents of mail as follows for example, great operational risk event reports:
Mail matter topics: [operational risk and internal control and management system] great operational risk event reports prompting: < $ event occurs
Department><event title>event
Mail Contents:
You are good,
<$ event generation part door $>report together great operational risk event, concrete condition it is as follows:
One, essential information
Event description:
Two, loss and recycling information
Because event influence is more great, it do pay attention to and relevant departments is supervised to complete processing and rectification under line in time,
It thanks！
Remind: this mail is that system is sent automatically, please don't be replied.
Prompting mail is reported in order to obtain great operational risk event automatically, it need to be according at least to including in the event information
Keyword, corresponding obtain generate above-mentioned great operational risk event such as and report necessary base in the content example for reminding mail
This information and the key messages such as loss and recycling information, then fill keyword each in the event information to email template
Corresponding filling region reports prompting mail to obtain great operational risk event, is automatically positioned by word segmentation processing and content,
Realize automatically generating for mail.
When the non-financial influence severity parameter or combined influence severity parameter have exceeded the grade threshold, elder generation is needed
Know that the operational risk loss event is corresponding according to the non-financial influence severity parameter or combined influence severity parameter
Event category, such as when non-financial influence severity parameter is 4 corresponding event category is Information technology system event,
The corresponding receiving party of current event category is then obtained according to preconfigured mail reception side's configuration information.
It is Information technology system event in the non-wealth configured with event category such as in mail reception side's configuration information
Business influences severity parameter when being 4, corresponding addressee and makes a copy for people's information.
It, can be by the great operational risk thing after the corresponding receiving party of mail reception side's acquisition of information
Part, which reports, reminds mail precisely to push to corresponding receiving party, handles the great operation with timely notification information recipient
Risk case.
The method achieve on operational risk loss event it is corresponding it is non-financial influence severity parameter it is automatic calculate and
Intelligent predicting timely can carry out risk to operational risk loss event and estimate, convenient for being handled in time risk case.
The embodiment of the present invention also provides a kind of risk estimating device of risk case, the risk estimating device of the risk case
For executing any embodiment of the risk forecast method of aforementioned risk event.Specifically, referring to Fig. 5, Fig. 5 is of the invention real
The schematic block diagram of the risk estimating device of the risk case of example offer is provided.The risk estimating device 100 of the risk case can be with
It is configured in management server.
As shown in figure 5, the risk estimating device 100 of risk case includes historical data training unit 110, the first severity
Parameter acquiring unit 120, the second severity parameter acquiring unit 130.
Historical data training unit 110, for obtaining the historical data of operational risk loss event, by the historical data
Trained model-naive Bayesian is treated as training set to be trained, and is obtained for predicting non-financial influence severity parameter
Model-naive Bayesian.
In the present embodiment, in order to train model-naive Bayesian in advance, need to obtain a large amount of operational risk loss thing
The historical data of part, obtaining the corresponding historical events description information of historical data, (historical events description information can be regarded as more
The set of a keyword), using historical events description information as the input of model-naive Bayesian function, by historical data with
The corresponding non-financial output for influencing severity parameter as model-naive Bayesian function of historical events description information, Ji Kexun
It gets for predicting the non-financial model-naive Bayesian for influencing severity parameter.
Wherein, historical events description information includes: whether (to convert into for loss event, state-event, currency type, amount of money involved
RMB), the potential loss amount of money (equivalent RMB), the actual loss amount of money (equivalent RMB), the actual loss amount of money
(former currency type), whether have recycling, insurance recycling the amount of money, insurance recycling the date, the non-insured recycling amount of money, the non-insured recycling date,
The final ascertainment of damage amount of money.
Rather than financial influence severity parameter include: non-financial influence severity grade, non-financial influence severity whether
It is legal close rule, whether strategy and operations objective, whether business lasting operation and customer service, whether information announcing, whether sound
Reputation influence and whether data and information system.
In one embodiment, as shown in fig. 6, the historical data training unit 110 includes:
Historical data participle unit 111 carries out historical data for obtaining the historical data of operational risk loss event
Participle is to obtain historical events description information；
Model training unit 112, for using the historical events description information as the defeated of model-naive Bayesian function
Enter, using non-financial influence severity parameter corresponding with historical events description information in historical data as model-naive Bayesian
The output of function is trained the model-naive Bayesian function, obtains the model-naive Bayesian.
In the present embodiment, the model-naive Bayesian function is as follows:
Wherein, x1, x2..., xnIndicate each feature in historical events description information, it is understood that it is each keyword,
Such as whether for loss event, state-event, currency type, amount of money involved (equivalent RMB), the potential loss amount of money (equivalent RMB
Member), the actual loss amount of money (equivalent RMB), the actual loss amount of money (former currency type), whether have recycling, insurance recycling the amount of money,
The insurance recycling date, the non-insured recycling amount of money, non-insured recycling date, the final ascertainment of damage amount of money.It is described according to historical events
Each feature in information is divided into class ykPossibility.
Entire Naive Bayes Classification is divided into following multiple stages:
Preparation stage, the task in this stage are that necessary preparation is done for Naive Bayes Classification, and groundwork is
Characteristic attribute is determined as the case may be, and each characteristic attribute is suitably divided, then by manually to a part wait divide
Category is classified, and training sample set is formed.The input in this stage is all data to be sorted, output be characteristic attribute and
Training sample.This stage is the stage for uniquely needing to be accomplished manually in entire Naive Bayes Classification, and quality is to entire mistake
Journey will have a major impact, and the quality of classifier is largely divided by characteristic attribute, characteristic attribute and training sample quality is determined
It is fixed.
Classifier training stage, the task in this stage are exactly to generate classifier, and groundwork is to calculate each classification to exist
The frequency of occurrences and each characteristic attribute in training sample, which divide, estimates the conditional probability of each classification, and result is recorded.
Its input is characteristic attribute and training sample, and output is classifier.This stage is the mechanical sexual stage, according to above-mentioned simple pattra leaves
The formula of this pattern function can calculate completion automatically.
First severity parameter acquiring unit 120, for making the corresponding event description information of operational risk loss event
For the input of the model-naive Bayesian, the corresponding non-financial influence severity parameter of operational risk loss event is obtained.
In the present embodiment, in order to obtain the corresponding severity of operational risk loss event, one need to be quantized into
Level value, and operational risk loss event is passage description, therefore in order to be quantified as level value, it need to be corresponded to
It is segmented to obtain event description information, then using event description information as the input of the model-naive Bayesian, Ji Kegen
The corresponding non-financial influence severity parameter for obtaining being indicated by level value of the keyword for including according to event description information.And it integrates
The non-financial combined influence for influencing severity parameter and financial influence severity parameter need to be fully considered by influencing severity parameter, therefore
It need to be according to non-financial influence severity parameter and the corresponding weight of financial influence severity parameter come the comprehensive shadow of COMPREHENSIVE CALCULATING
Ring severity parameter.It is realized in the application and verbal description is quantified as the corresponding non-financial influence of operational risk loss event sternly
Severe parameter and combined influence severity parameter.
In one embodiment, as shown in fig. 7, the first severity parameter acquiring unit 120, comprising:
Current data participle unit 121 will be current for obtaining the corresponding current data of the operational risk loss event
Data are segmented to obtain current event description information；
Supplementary units 122 are segmented, if the participle number in the current event description information does not reach preset point
Word number threshold value, obtain it is described participle number threshold value and the participle number in current event description information difference using as participle it is poor
Away from number, null value identical with the participle gap number is supplemented in the current event description information, after being handled when
Preceding event description information；
Information input computing unit 123, for using current event description information after the processing as the simple pattra leaves
The input of this pattern function obtains non-financial influence severity parameter.
In the present embodiment, in order to ensure point in the corresponding current event description information of each operational risk loss event
Word number is all the same, to ensure to be input to the model-naive Bayesian accordingly as normalized number.At this time first by current data
Segmented to obtain current event description information, if the participle number in the current event description information do not reach it is preset
Participle number threshold value obtains current event description information and segments number and segment the absolute value of the difference of number threshold value, supplements and be somebody's turn to do
The identical null value of absolute value number is to convert the current event description information to after the processing of standardized data formats currently
Event description information.
It is defeated namely when using the corresponding multiple fields of historical events description information as after the input of model-naive Bayesian
Non-financial influence severity parameter out is multiple grades numerical value, such as is exported are as follows: non-financial influence severity grade be 4, it is non-
(legal conjunction is considered as value when advising be 1 to the legal conjunction rule of financial influence severity, and illegal conjunction is considered as value and is 0), meets war when advising
(being considered as value when meeting strategy and operations objective is 1, and being considered as value when not meeting strategy and operations objective is for summary and operations objective
0) (it is 1 that the lasting operation and customer service for meeting business, which are considered as value, is not inconsistent for the lasting operation and customer service for, meeting business
The lasting operation and customer service of conjunction business be considered as value be 0), meet information announcing (meeting information announcing to be considered as value is 1,
It does not meet information announcing and is considered as value and be 0), meet reputation and influence that (meeting reputation influence, to be considered as value be 1, does not meet reputation shadow
Ring be considered as value be 0), meet data and information system (meet data and information system to be considered as value be 1, do not meet data and
Information system be considered as value be 0), rather than the value of financial influence severity parameter be above-mentioned parameter in maximum value.
Second severity parameter acquiring unit 130, for according to non-financial influence severity parameter and acquired finance
Influence the corresponding acquisition combined influence severity parameter of severity parameter.
In one embodiment, as shown in figure 8, the second severity parameter acquiring unit 130 includes:
Parameter acquiring unit 131, for obtaining non-financial influence severity parameter and financial influence severity parameter；
Parameter calculation unit 132, for by non-financial influence severity parameter multiplied by preset first weighted value to obtain
First parameter value, by financial influence severity parameter multiplied by preset second weighted value to obtain the second parameter value；
COMPREHENSIVE CALCULATING unit 133 obtains combined influence severity ginseng for the first parameter value and the second parameter value to be summed
Number.
In the present embodiment, the simple shellfish is input to when losing the corresponding event description information of event according to operational risk
This model of leaf, to obtain the corresponding non-financial influence severity parameter of operational risk loss event (such as current non-financial shadow
Ring severity parameter be 4) after.In order to obtain combined influence severity parameter, financial influence severity parameter (example can also be obtained
If current financial influence severity parameter is 3), by non-financial influence severity parameter multiplied by preset first weighted value (example
It is 0.6) to obtain the first parameter value, by financial influence severity parameter multiplied by preset second weight that the first weighted value, which is such as arranged,
Value (such as it is 0.4 that the second weighted value, which is arranged) is finally summed the first parameter value and the second parameter value with obtaining the second parameter value,
Obtain combined influence severity parameter (such as 4*0.6+3*0.4=3.6).
In one embodiment, the risk estimating device 100 of risk case further include:
Risk case mail push unit, if for detecting that the corresponding non-financial influence of operational risk loss event is serious
It spends parameter and exceeds preset grade threshold, parsing obtains the corresponding event information of operational risk loss event, event information is filled out
Email template is charged to obtain great operational risk event and report prompting mail, the great operational risk event is reported into prompting
Mail is sent to corresponding receiving party according to mail reception side's information.
In the present embodiment, if detecting the corresponding non-financial influence severity parameter of operational risk loss event or synthesis
It influences severity parameter and exceeds the grade threshold (such as setting 4 for grade threshold), then it represents that the operational risk loses event
It should be paid close attention to by related personnel and be handled in time, should parse obtain the corresponding event letter of operational risk loss event at this time
Breath, event information is filled to email template to obtain great operational risk event and report prompting mail.
The arrangement achieves on operational risk loss event it is corresponding it is non-financial influence severity parameter it is automatic calculate and
Intelligent predicting timely can carry out risk to operational risk loss event and estimate, convenient for being handled in time risk case.
The risk estimating device of above-mentioned risk case can be implemented as the form of computer program, which can be with
It is run in computer equipment as shown in Figure 9.
Referring to Fig. 9, Fig. 9 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Refering to Fig. 9, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 are performed, and processor 502 may make to execute the risk forecast method of risk case.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute the risk forecast method of risk case.
The network interface 505 is for carrying out network communication, such as the transmission of offer data information.Those skilled in the art can
To understand, structure shown in Fig. 9, only the block diagram of part-structure relevant to the present invention program, is not constituted to this hair
The restriction for the computer equipment 500 that bright scheme is applied thereon, specific computer equipment 500 may include than as shown in the figure
More or fewer components perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following function
Can: the historical data of operational risk loss event is obtained, the historical data is treated into trained simple pattra leaves as training set
This model is trained, and is obtained for predicting the non-financial model-naive Bayesian for influencing severity parameter；Operational risk is damaged
It is corresponding to obtain operational risk loss event for input of the corresponding event description information of accident part as the model-naive Bayesian
Non-financial influence severity parameter；According to non-financial influence severity parameter and acquired financial influence severity parameter pair
Combined influence severity parameter should be obtained.
In one embodiment, processor 502 is executing the historical data for obtaining operational risk loss event, will be described
Historical data is treated trained model-naive Bayesian as training set and is trained, and obtains for obtaining non-financial influence seriously
It when spending the step of the model-naive Bayesian of parameter, performs the following operations: obtaining the historical data of operational risk loss event, it will
Historical data is segmented to obtain historical events description information；Using the historical events description information as naive Bayesian mould
The input of type function, using non-financial influence severity parameter corresponding with historical events description information in historical data as simplicity
The output of Bayesian model function is trained the model-naive Bayesian function, obtains the model-naive Bayesian.
In one embodiment, processor 502 is described by the corresponding event description information of operational risk loss event in execution
As the input of the model-naive Bayesian, the corresponding non-financial influence severity parameter of operational risk loss event is obtained
It when step, performs the following operations: obtaining the corresponding current data of the operational risk loss event, current data is segmented
To obtain current event description information；If the participle number in the current event description information does not reach preset participle number
Threshold value obtains the difference of the participle number threshold value and the participle number in current event description information using a as participle gap
Number supplements null value identical with the participle gap number, current thing after being handled in the current event description information
Part description information；Using current event description information after the processing as the input of the model-naive Bayesian function, obtain
Non-financial influence severity parameter.
In one embodiment, processor 502 is described according to non-financial influence severity parameter and acquired wealth in execution
When business influences the step of the corresponding acquisition combined influence severity parameter of severity parameter, performs the following operations: obtaining non-financial shadow
Ring severity parameter and financial influence severity parameter；By non-financial influence severity parameter multiplied by preset first weighted value
To obtain the first parameter value, by financial influence severity parameter multiplied by preset second weighted value to obtain the second parameter value；It will
First parameter value and the second parameter value are summed, and combined influence severity parameter is obtained.
In one embodiment, processor 502 is described according to non-financial influence severity parameter and acquired wealth in execution
After business influences severity parameter corresponding the step of obtaining combined influence severity parameter, also perform the following operations: if detecting
Operational risk loses the corresponding non-financial influence severity parameter of event and exceeds preset grade threshold, and parsing obtains operational risk
The corresponding event information of loss event fills event information to email template to obtain great operational risk event and report prompting
The great operational risk event is reported and mail is reminded to be sent to corresponding information reception according to mail reception side's information by mail
Side.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Fig. 9 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different component layouts.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 9,
Details are not described herein.
It should be appreciated that in embodiments of the present invention, processor 502 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 GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Computer readable storage medium is provided in another embodiment of the invention.The computer readable storage medium can be with
For non-volatile computer readable storage medium.The computer-readable recording medium storage has computer program, wherein calculating
Machine program performs the steps of the historical data for obtaining operational risk loss event when being executed by processor, by the history number
It is trained, is obtained for predicting non-financial influence severity parameter according to trained model-naive Bayesian is treated as training set
Model-naive Bayesian；Using the corresponding event description information of operational risk loss event as the model-naive Bayesian
Input obtains the corresponding non-financial influence severity parameter of operational risk loss event；According to non-financial influence severity parameter
And the acquired corresponding acquisition combined influence severity parameter of financial influence severity parameter.
In one embodiment, the historical data for obtaining operational risk loss event, using the historical data as instruction
White silk collection is treated trained model-naive Bayesian and is trained, and obtains for obtaining the non-financial simple shellfish for influencing severity parameter
This model of leaf, comprising: the historical data for obtaining operational risk loss event segments historical data to obtain historical events
Description information；Using the historical events description information as the input of model-naive Bayesian function, by historical data with go through
The corresponding non-financial output for influencing severity parameter as model-naive Bayesian function of history event description information, to the Piao
Plain Bayesian model function is trained, and obtains the model-naive Bayesian.
In one embodiment, described using the corresponding event description information of operational risk loss event as the simple pattra leaves
The input of this model obtains the corresponding non-financial influence severity parameter of operational risk loss event, comprising:
The corresponding current data of the operational risk loss event is obtained, current data is segmented to obtain current thing
Part description information；If the participle number in the current event description information does not reach preset participle number threshold value, institute is obtained
State participle number threshold value and the participle number in current event description information difference using as participle gap number, it is described currently
Null value identical with the participle gap number, current event description information after being handled are supplemented in event description information；It will
Input of the current event description information as the model-naive Bayesian function after the processing obtains non-financial influence seriously
Spend parameter.
In one embodiment, described according to non-financial influence severity parameter and acquired financial influence severity parameter
It is corresponding to obtain combined influence severity parameter, comprising: to obtain non-financial influence severity parameter and financial influence severity ginseng
Number；Non-financial influence severity parameter is obtained into the first parameter value multiplied by preset first weighted value, financial influence is serious
Parameter is spent multiplied by preset second weighted value to obtain the second parameter value；First parameter value and the second parameter value are summed, obtained
Combined influence severity parameter.
In one embodiment, described according to non-financial influence severity parameter and acquired financial influence severity parameter
After corresponding acquisition combined influence severity parameter, further includes: if detecting the corresponding non-financial shadow of operational risk loss event
It rings severity parameter and exceeds preset grade threshold, parsing obtains the corresponding event information of operational risk loss event, by event
Information is filled to email template to obtain great operational risk event and report prompting mail, will be in the great operational risk event
Report reminds mail to be sent to corresponding receiving party according to mail reception side's information.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm
Step can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and software
Interchangeability generally describes each exemplary composition and step according to function in the above description.These functions are studied carefully
Unexpectedly the specific application and design constraint depending on technical solution are implemented in hardware or software.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed unit and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only logical function partition, there may be another division manner in actual implementation, can also will be with the same function
Unit set is at a unit, such as multiple units or components can be combined or can be integrated into another system or some
Feature can be ignored, or not execute.In addition, shown or discussed mutual coupling, direct-coupling or communication connection can
Be through some interfaces, the indirect coupling or communication connection of device or unit, be also possible to electricity, mechanical or other shapes
Formula connection.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The all or part of part or the technical solution that technology contributes can be embodied in the form of software products, should
Computer software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
Personal computer, server or network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic disk or
The various media that can store program code such as person's CD.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of risk forecast method of risk case characterized by comprising
The historical data for obtaining operational risk loss event, treats trained simple pattra leaves as training set for the historical data
This model is trained, and is obtained for predicting the non-financial model-naive Bayesian for influencing severity parameter；
Using the corresponding event description information of operational risk loss event as the input of the model-naive Bayesian, operation is obtained
The corresponding non-financial influence severity parameter of risk of loss event；
It is serious according to non-financial influence severity parameter and the corresponding acquisition combined influence of acquired financial influence severity parameter
Spend parameter.
2. the risk forecast method of risk case according to claim 1, which is characterized in that the acquisition operational risk damage
The historical data of accident part, treats trained model-naive Bayesian as training set for the historical data and is trained, obtain
To for obtaining the non-financial model-naive Bayesian for influencing severity parameter, comprising:
The historical data for obtaining operational risk loss event, historical data is segmented to obtain historical events description information；
Using the historical events description information as the input of model-naive Bayesian function, by historical data with historical events
The corresponding non-financial output for influencing severity parameter as model-naive Bayesian function of description information, to the simple pattra leaves
This pattern function is trained, and obtains the model-naive Bayesian.
3. the risk forecast method of risk case according to claim 1, which is characterized in that described to lose operational risk
It is corresponding to obtain operational risk loss event for input of the corresponding event description information of event as the model-naive Bayesian
Non-financial influence severity parameter, comprising:
The corresponding current data of the operational risk loss event is obtained, current data is segmented to obtain current event and retouch
State information；
If the participle number in the current event description information does not reach preset participle number threshold value, the participle is obtained
The difference of number threshold value and the participle number in current event description information in the current event to describe as participle gap number
Null value identical with the participle gap number, current event description information after being handled are supplemented in information；
Using current event description information after the processing as the input of the model-naive Bayesian function, non-financial shadow is obtained
Ring severity parameter.
4. the risk forecast method of risk case according to claim 1, which is characterized in that described according to non-financial influence
Severity parameter and the corresponding acquisition combined influence severity parameter of acquired financial influence severity parameter, comprising:
Obtain non-financial influence severity parameter and financial influence severity parameter；
Non-financial influence severity parameter is obtained into the first parameter value multiplied by preset first weighted value, financial influence is serious
Parameter is spent multiplied by preset second weighted value to obtain the second parameter value；
First parameter value and the second parameter value are summed, combined influence severity parameter is obtained.
5. the risk forecast method of risk case according to claim 1, which is characterized in that described according to non-financial influence
After severity parameter and the corresponding acquisition combined influence severity parameter of acquired financial influence severity parameter, further includes:
If detecting the corresponding non-financial influence severity parameter of operational risk loss event beyond preset grade threshold, parsing
The corresponding event information of operational risk loss event is obtained, event information is filled to email template to obtain great operational risk
Event reports prompting mail, the great operational risk event is reported, mail is reminded to be sent to pair according to mail reception side's information
The receiving party answered.
6. a kind of risk estimating device of risk case characterized by comprising
Historical data training unit, for obtaining the historical data of operational risk loss event, using the historical data as instruction
White silk collection is treated trained model-naive Bayesian and is trained, and obtains for predicting the non-financial simple shellfish for influencing severity parameter
This model of leaf；
First severity parameter acquiring unit, for using the corresponding event description information of operational risk loss event as the Piao
The input of plain Bayesian model obtains the corresponding non-financial influence severity parameter of operational risk loss event；
Second severity parameter acquiring unit, for serious according to non-financial influence severity parameter and acquired financial influence
Spend the corresponding acquisition combined influence severity parameter of parameter.
7. the risk estimating device of risk case according to claim 6, which is characterized in that the historical data training is single
Member, comprising:
Historical data participle unit, for obtain operational risk loss event historical data, by historical data segment with
Obtain historical events description information；
Model training unit, for will go through using the historical events description information as the input of model-naive Bayesian function
Non-financial influence severity parameter corresponding with historical events description information is as model-naive Bayesian function in history data
Output, is trained the model-naive Bayesian function, obtains the model-naive Bayesian.
8. the risk estimating device of risk case according to claim 6, which is characterized in that the first severity parameter
Acquiring unit, comprising:
Current data participle unit, for obtaining the corresponding current data of operational risk loss event, by current data into
Row participle is to obtain current event description information；
Supplementary units are segmented, if not reaching preset participle number threshold for the participle number in the current event description information
Value, obtain it is described participle number threshold value and the participle number in current event description information difference using as segment gap number,
Null value identical with the participle gap number is supplemented in the current event description information, current event is retouched after being handled
State information；
Information input computing unit, for using current event description information after the processing as the model-naive Bayesian letter
Several inputs obtains non-financial influence severity parameter.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
Any one of described in risk case risk forecast method.
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 make the processor execute such as wind described in any one of claim 1 to 5 when being executed by a processor
The risk forecast method of dangerous event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811346052.9A CN109492911A (en) | 2018-11-13 | 2018-11-13 | Risk forecast method, device, computer equipment and the storage medium of risk case |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811346052.9A CN109492911A (en) | 2018-11-13 | 2018-11-13 | Risk forecast method, device, computer equipment and the storage medium of risk case |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109492911A true CN109492911A (en) | 2019-03-19 |
Family
ID=65694783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811346052.9A Pending CN109492911A (en) | 2018-11-13 | 2018-11-13 | Risk forecast method, device, computer equipment and the storage medium of risk case |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492911A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163470A (en) * | 2019-04-04 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Case evaluating method and device |
| CN110322153A (en) * | 2019-07-09 | 2019-10-11 | 中国工商银行股份有限公司 | Monitor event processing method and system |
| CN110348806A (en) * | 2019-06-26 | 2019-10-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of solution of emergent event |
| CN111178719A (en) * | 2019-12-20 | 2020-05-19 | 中国建设银行股份有限公司 | Method and device for collecting internal loss data of operation risk and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003036346A (en) * | 2001-07-23 | 2003-02-07 | Mitsubishi Trust & Banking Corp | Method for evaluating operational risk and its system |
| CN108009711A (en) * | 2017-11-23 | 2018-05-08 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and readable storage medium storing program for executing |
| CN108062331A (en) * | 2016-11-08 | 2018-05-22 | 南京理工大学 | Increment type naive Bayesian file classification method based on Lifelong Learning |
-
2018
- 2018-11-13 CN CN201811346052.9A patent/CN109492911A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003036346A (en) * | 2001-07-23 | 2003-02-07 | Mitsubishi Trust & Banking Corp | Method for evaluating operational risk and its system |
| CN108062331A (en) * | 2016-11-08 | 2018-05-22 | 南京理工大学 | Increment type naive Bayesian file classification method based on Lifelong Learning |
| CN108009711A (en) * | 2017-11-23 | 2018-05-08 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and readable storage medium storing program for executing |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163470A (en) * | 2019-04-04 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Case evaluating method and device |
| CN110163470B (en) * | 2019-04-04 | 2023-05-30 | 创新先进技术有限公司 | Event evaluation method and device |
| CN110348806A (en) * | 2019-06-26 | 2019-10-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of solution of emergent event |
| CN110322153A (en) * | 2019-07-09 | 2019-10-11 | 中国工商银行股份有限公司 | Monitor event processing method and system |
| CN111178719A (en) * | 2019-12-20 | 2020-05-19 | 中国建设银行股份有限公司 | Method and device for collecting internal loss data of operation risk and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492911A (en) | Risk forecast method, device, computer equipment and the storage medium of risk case | |
| CN109474515A (en) | Mail push method, device, computer equipment and the storage medium of risk case | |
| Sheu | Dynamic relief-demand management for emergency logistics operations under large-scale disasters | |
| Lokanan et al. | Fraud prediction using machine learning: The case of investment advisors in Canada | |
| US7904397B2 (en) | System and method for scalable cost-sensitive learning | |
| US10552735B1 (en) | Applied artificial intelligence technology for processing trade data to detect patterns indicative of potential trade spoofing | |
| CN104834983B (en) | Business data processing method and device | |
| Kowshalya et al. | Predicting fraudulent claims in automobile insurance | |
| CN107844848A (en) | A kind of region flow of the people Forecasting Methodology and system | |
| US20040107161A1 (en) | System, method and computer program for managing credit decisions | |
| US20130346097A1 (en) | Computer system and method for processing data relating to nurse intervention program decisions | |
| Özçelik et al. | Improving a credit card fraud detection system using genetic algorithm | |
| Ghorbani et al. | Fraud detection in automobile insurance using a data mining based approach | |
| CN109685670A (en) | Social security violation detection method, device, equipment and computer readable storage medium | |
| Machemehl et al. | A stochastic dynamic programming approach for the equipment replacement optimization under uncertainty | |
| US20230245241A1 (en) | Claim routing based on liability classification | |
| US8359255B2 (en) | Computer system for applying proactive referral model to long term disability claims | |
| CN108898302A (en) | A kind of private is raised administrator's methods of risk assessment and device | |
| US20220351209A1 (en) | Automated fraud monitoring and trigger-system for detecting unusual patterns associated with fraudulent activity, and corresponding method thereof | |
| JP6569585B2 (en) | Business evaluation system | |
| CN113434575B (en) | Data attribution processing method, device and storage medium based on data warehouse | |
| CN109919675A (en) | Communication user upshift prediction probability recognition methods neural network based and system | |
| CN109409648A (en) | Claims Resolution air control method, apparatus, computer equipment and storage medium | |
| JP6875445B2 (en) | Information processing equipment, information processing methods and programs | |
| CN110148058A (en) | Identify the method and system of suspect vehicle Aftermarket Claims declaration form |
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 |